Search

Remaining useful life (RUL) prediction of aircraft engine (AE) is of great importance to improve its reliability and availability, and reduce its maintenance costs. This article proposes a novel deep bidirectional recurrent neural networks (DBRNNs) ensemble method for the RUL prediction of the AEs. In this method, several kinds of DBRNNs with different neuron structures are built to extract hidden features from sensory data. A new customized loss function is designed to evaluate the performance of the DBRNNs, and a series of the RUL values is obtained. Then, these RUL values are reencapsulated into a predicted RUL domain. By updating the weights of elements in the domain, multiple regression decision tree (RDT) models are trained iteratively. These models integrate the predicted results of different DBRNNs to realize the final RUL prognostics with high accuracy. The proposed method is validated by using C-MAPSS datasets from NASA. The experimental results show that the proposed method has achieved more superior performance compared with other existing methods.

Deep-learning-based methods have been successfully applied to fault diagnosis of rotating machinery. However, the domain mismatch among different operating conditions significantly deteriorates diagnostic performance of these methods in industrial applications. To solve this problem, a new fault diagnosis model based on capsule neural network (Cap-net) is constructed, and a novel online domain adaptation learning method based on deep reinforcement learning (DRL) is proposed in this article to improve the adaptivity of the fault diagnosis model. In this method, the Cap-net is first introduced into the DRL as an agent to extract representative features and diagnoses fault. Moreover, the online domain adaptation learning of the agent is conducted based on the Q-learning of the DRL so as to adapt to different operating domains that have never been experienced. Specifically, an online feature dictionary combined with cosine similarity is designed to coarsely label the online data collected from different operating domain, while a reward mechanism is defined to evaluate the obtained label. Subsequently, the online data, the corresponding label, and the reward are used to optimize the agent to obtain the desired diagnostic model. Two experiment studies are implemented to verify the effectiveness of the proposed method. The experimental results show that the proposed method has more excellent diagnostic performance and adaptivity than the existing popular methods.

Remaining useful life (RUL) prediction is a key solution to improve the reliability, availability and maintainability of engineering systems. Long short-term memory (LSTM) and convolution neural networks (CNN) are the current hotspots in the field of RUL prediction. However, the LSTM-based prognostic approach has a slow loop step to process large-scale time-series data since the dependence of the data processing process at each time on the output of the previous time limits parallelism, and the CNN-based prognostic approach is not fit for time-series data although it can process the data in parallel. In this paper, a new auto-encoder quasi-recurrent neural networks (AEQRNN) based prognostic approach is proposed for RUL prediction of the engineering systems. The AEQRNN contains convolution components that can process input data in parallel, and pooling components which has two LSTM-like gate structures to process time-series data. In addition, the AEQRNN can automatically extract hidden features from monitoring signals without manual feature design. The effectiveness of the proposed prognostic approach is validated by three prognostic benchmarking datasets, including a turbofan engine dataset, a rolling bearing dataset, and a machining tool dataset. Experimental results demonstrate that this approach has both superior prognostic performance and training speed in comparison with other kinds of recurrent neural network-based approaches and various state-of-the-art approaches in the recent literature.

Accurate health evaluation is crucial to reliable operation of complex degradation systems. Although traditional machine learning methods such as artificial neural network (ANN) and support vector machine (SVM) have been used widely, state assessment schemes based on a single classification model still suffer from low multiclass classification efficiency, high variance, and deviation. To solve these problems, this article proposes a novel health evaluation method based on stacking ensemble learning and generalized multiclass support vector machine (GMSVM) algorithm. The proposed health evaluation framework includes three parts: 1) abnormal value elimination and missing value processing are applied for multiple sensor data; 2) statistical features are extracted from the observed data and the Pearson correlation coefficient is applied for feature selection; and 3) ensemble generalized multiclass support vector machines (EGMSVMs) are utilized to evaluate the health situation of a degradation system. Unlike the binary classifiers and deep-learning-based classifiers, EGMSVMs utilize the stacking-based method to combine several GMSVMs as submodels and random forest as a metamodel, and the metamodel ensembles the results of submodels to reach a satisfied performance. Compared to traditional SVM- and ANN-based algorithms, EGMSVMs, in processing multiclass problems, achieve high efficiency and, meanwhile, low variance and deviation. The proposed method is verified using a hydraulic test rig. The experimental results show the feasibility and applicability of the proposed health evaluation framework.

PurposeEngineering design optimization involving computational simulations is usually a time-consuming, even computationally prohibitive process. To relieve the computational burden, the adaptive metamodel-based design optimization (AMBDO) approaches have been widely used. This paper aims to develop an AMBDO approach, a lower confidence bounding approach based on the coefficient of variation (CV-LCB) approach, to balance the exploration and exploitation objectively for obtaining a global optimum under limited computational budget.Design/methodology/approachIn the proposed CV-LCB approach, the coefficient of variation (CV) of predicted values is introduced to indicate the degree of dispersion of objective function values, while the CV of predicting errors is introduced to represent the accuracy of the established metamodel. Then, a weighted formula, which takes the degree of dispersion and the prediction accuracy into consideration, is defined based on the already-acquired CV information to adaptively update the metamodel during the optimization process.FindingsTen numerical examples with different degrees of complexity and an AIAA aerodynamic design optimization problem are used to demonstrate the effectiveness of the proposed CV-LCB approach. The comparisons between the proposed approach and four existing approaches regarding the computational efficiency and robustness are made. Results illustrate the merits of the proposed CV-LCB approach in computational efficiency and robustness.Practical implicationsThe proposed approach exhibits high efficiency and robustness in engineering design optimization involving computational simulations.Originality/valueCV-LCB approach can balance the exploration and exploitation objectively.

Machine health monitoring is of great importance in industrial informatics field. Recently, deep learning methods applied to machine health monitoring have been proven effective. However, the existing methods face enormous difficulties in extracting heterogeneous features indicating the variation until failure and revealing the inherent high-dimensional features of massive signals, which affect the accuracy and efficiency of machine health monitoring. In this paper, a novel data-driven machine health monitoring method is proposed using adaptive kernel spectral clustering (AKSC) and deep long short-term memory recurrent neural networks (LSTM-RNN). This method include three steps: First, features in the time domain, frequency domain, and time-frequency domain are, respectively, extracted from massive measured signals. And, an Euclidean distance based algorithm is designed to select degradation features. Second, the AKSC algorithm is introduced to adaptively identify machine anomaly behaviors from multiple degradation features. Third, a new deep learning model (LSTM-RNN) is constructed to update and predict the failure time of the machine. The effectiveness of the proposed method is validated using a set of test-to-failure experimental data. The results show that the performance of the proposed method is competitive with other existing methods.

Bayesian optimization is a metamodel-based global optimization approach that can balance between exploration and exploitation. It has been widely used to solve single-objective optimization problems. In engineering design, making trade-offs between multiple conflicting objectives is common. In this work, a multi-objective Bayesian optimization approach is proposed to obtain the Pareto solutions. A novel acquisition function is proposed to determine the next sample point, which helps improve the diversity and convergence of the Pareto solutions. The proposed approach is compared with some state-of-the-art metamodel-based multi-objective optimization approaches with four numerical examples and one engineering case. The results show that the proposed approach can obtain satisfactory Pareto solutions with significantly reduced computational cost.

Full penetrated welded joint (WJ) without visible flaws were obtained under the optimized welding process. Owing to the inhomogeneous distribution of the chemical elements, the fusion zone (FZ) solidified as first δ-ferrite under the F-A solidification mode in most area and first γ-austenite under the A–F or A solidification mode in the remaining local area. Various temperature histories from the lower layer to the upper layer lead to different degrees of grain growth and phase transformation within the FZ, which subsequently influenced the performance of the WJ. Hardness of the weld center decreased from the lower layer to the upper layer while the tensile properties deteriorated from the lower layer to the upper layer. Different mechanical properties between different layers were considered to be closely related to the growing grain sizes from the lower layer to the upper layer. All tensile specimens failed at the weld zones with massive dimples distributing on the fracture surfaces, indicating a characteristic ductile fracture. The rapid cooling rate inhibited the transition from the high-temperature phase (δ-ferrite) to the low-temperature phase (γ-austenite), which lead to the δ-ferrite content increase within the FZ and weakened the corrosion resistance of the WJ.

Magnetism aided mitigation of deformation and residual stress was researched in dissimilar joint 316 L with EH36. Application of external magnetic field, microstructure was refined, weld profile was regulated by narrowing upper width and broadening bottom width. A simulation method by integrating image extraction and fitting of actual weld profile into thermal elastic plastic finite element analysis was proposed to evaluate welding deformation and residual stress in the dissimilar joint with an asymmetrical weld shape. Considering the effect of external magnetic field, welding deformation was decreased by ∼34%, the tensile stress was reduced. Mitigation mechanism by external magnetic field was that temperature gradient and cooling rate of the weld pool were decreased by Lorentz force stir with low micro-strain and micro-stress. This work offered an effective method to regulate deformation and residual stress of dissimilar joint in laser welding.

Crack growth rate (CGR) in air for welds produced by 24 mT magnetic field assisted laser-MIG hybrid welding was decreased by 33%. CGR in 3.5% NaCl solution for welds produced by 16 mT magnetic field assisted welding was reduced by 20%. Texture variation in welds was investigated through electron backscattered diffraction (EBSD). External magnetic field lowered thermal gradient and changed orientations of maximum thermal gradient (∇Tmax), resulting in weaker texture intensity and less ferrite. Reduced intensity of {100} planes and 〈100〉 orientations improved resistance to cyclic plastic deformation. Reduced ferrite increased the volume of strain-induced martensite at crack tip, improving fatigue cracking resistance.

Purpose This paper aims to propose hybrid global optimization based on multiple metamodels for improving the efficiency of global optimization. Design/methodology/approach The method has fully utilized the information provided by different metamodels in the optimization process. It not only imparts the expected improvement criterion of kriging into other metamodels but also intelligently selects appropriate metamodeling techniques to guide the search direction, thus making the search process very efficient. Besides, the corresponding local search strategies are also put forward to further improve the optimizing efficiency. Findings To validate the method, it is tested by several numerical benchmark problems and applied in two engineering design optimization problems. Moreover, an overall comparison between the proposed method and several other typical global optimization methods has been made. Results show that the global optimization efficiency of the proposed method is higher than that of the other methods for most situations. Originality/value The proposed method sufficiently utilizes multiple metamodels in the optimizing process. Thus, good optimizing results are obtained, showing great applicability in engineering design optimization problems which involve costly simulations.

A mixed-model two-sided assembly line is a manufacturing system designed for the production of large-sized products. In order to describe the actual condition, this paper presents a novel multiobjective programming model for balancing a mixed-model two-sided assembly line subject to multiple constraints, in which, additional constraints including zoning, synchronous, and positional constraints are considered besides the traditional constraints, e.g., the precedence constraint. Two objectives are simultaneously to be optimized, one is to minimize the combination of the weighted line efficiency and the weighted smoothness index, and the other is to minimize the weighted total relevant costs per unit of a product. A novel multiobjective hybrid imperialist competitive algorithm (MOHICA) is proposed to solve this problem. In the presented MOHICA, the sigma method is employed to quantify every individual, a novel merging method is introduced to reserve better individuals into the evolutionary population, and late acceptance hill-climbing (LAHC) algorithm is presented as a local search algorithm to achieve accurate balance between intensification and diversification. The experimental results on the selected benchmark instances and a practical case show that the proposed multiobjective algorithm outperforms nondominated sorting genetic algorithm (NSGA)-II, multiobjective improved teaching-learning-based optimization, and NSGA-III existing in the literature.

Purpose Metamodels are widely used to replace simulation models in engineering design optimization to reduce the computational cost. The purpose of this paper is to develop a novel sequential sampling strategy (weighted accumulative error sampling, WAES) to obtain accurate metamodels and apply it to improve the quality of global optimization. Design/methodology/approach A sequential single objective formulation is constructed to adaptively select new sample points. In this formulation, the optimization objective is to select a sample point with the maximum weighted accumulative predicted error obtained by analyzing data from previous iterations, and a space-filling criterion is introduced and treated as a constraint to avoid generating clustered sample points. Based on the proposed sequential sampling strategy, a two-step global optimization approach is developed. Findings The proposed WAES approach and the global optimization approach are tested in several cases. A comparison has been made between the proposed approach and other existing approaches. Results illustrate that WAES approach performs the best in improving metamodel accuracy and the two-step global optimization approach has a great ability to avoid local optimum. Originality/value The proposed WAES approach overcomes the shortcomings of some existing approaches. Besides, the two-step global optimization approach can be used for improving the optimization results.

A process method with steady magnetic field assist laser-MIG hybrid welding was proposed, grain refinement and ferrite variation were investigated through Electron Backscattered Diffraction test. The related low-temperature (−40 °C) impact toughness of weld metals was found to be improved by 36%. Stirring effect in weld pool brought by external magnetic field promoted grain refinement and ferrite reduction. Brittle fracture was found to appear at interface between ferrite and stress-induced martensite, thus decrease of ferrite contributed to the increase of impact crack initiation energy. Grain refinement and random distribution of ferrite increased crack propagation barrier. The remarkable increase in the low-temperature impact toughness of weld metal was attributed to the decreased volume of ferrite, random distribution of ferrite and refinement of microstructure.

Multi-fidelity (MF) metamodeling approaches have recently attracted a significant amount of attention in simulation-based design optimization due to their ability to conduct trade-offs between high accuracy and low computational expenses by integrating the information from high-fidelity (HF) and low-fidelity (LF) models. While existing MF metamodel assisted design optimization approaches may yield an inferior or even infeasible solution since they generally treat the MF metamodel as the real HF model and ignore the interpolation uncertainties from the MF metamodel. This situation will be more serious in non-deterministic optimization. Hence, in this work, a MF metamodel assisted robust optimization approach is developed, in which the interpolation uncertainty of the MF metamodel and design variable uncertainty are quantified and taken into consideration. To demonstrate the effectiveness and merits of the proposed approach, two numerical examples and a long cylinder pressure vessel design optimization problem are tested. Results show that for the test cases the proposed approach can obtain a solution that is both optimal and within the feasible region even with perturbation of the uncertain variables.

Purpose Rolling bearings based on rotating machinery are one of the most widely used in industrial applications because of their low cost, high performance and robustness. The purpose of this paper is to describe how to identify degradation condition of rolling bearing and predict its fault time in big data environment in order to achieve zero downtime performance and preventive maintenance for the rolling bearing. Design/methodology/approach The degradation characteristic parameters of rolling bearings including intrinsic mode energy and failure frequency were, respectively, extracted from the pre-processed original vibration signals using EMD and Hilbert transform. Then, Spearman’s rank correlation coefficient and PCA were used to obtain the health index of the rolling bearing so as to detect the appearance of degradations. Furthermore, the degradation condition of the rolling bearings might be identified through implementing the monotonicity analysis, robustness analysis and degradation analysis of the health index. Findings The effectiveness of the proposed method is verified by a case study. The result shows that the proposed method can be applied to monitor the degradation condition of the rolling bearings in industrial application. Research limitations/implications Further experiment remains to be done so as to validate the effectiveness of the proposed method using Apache Hadoop when massive sensor data are available. Practical implications The paper proposes a methodology for rolling bearing condition monitoring representing the steps that need to be followed. Real-time sensor data are utilized to find the degradation characteristics. Originality/value The result of the work presented in this paper form the basis for the software development and implementation of condition monitoring system for rolling bearings based on Hadoop.

Purpose Uncertainty is inevitable in real-world engineering optimization. With an outer-inner optimization structure, most previous robust optimization (RO) approaches under interval uncertainty can become computationally intractable because the inner level must perform robust evaluation for each design alternative delivered from the outer level. This paper aims to propose an on-line Kriging metamodel-assisted variable adjustment robust optimization (OLK-VARO) to ease the computational burden of previous VARO approach. Design/methodology/approach In OLK-VARO, Kriging metamodels are constructed for replacing robust evaluations of the design alternative delivered from the outer level, reducing the nested optimization structure of previous VARO approach into a single loop optimization structure. An on-line updating mechanism is introduced in OLK-VARO to exploit the obtained data from previous iterations. Findings One nonlinear numerical example and two engineering cases have been used to demonstrate the applicability and efficiency of the proposed OLK-VARO approach. Results illustrate that OLK-VARO is able to obtain comparable robust optimums as to that obtained by previous VARO, while at the same time significantly reducing computational cost. Practical implications The proposed approach exhibits great capability for practical engineering design optimization problems under interval uncertainty. Originality/value The main contribution of this paper lies in the following: an OLK-VARO approach under interval uncertainty is proposed, which can significantly ease the computational burden of previous VARO approach.

Variable-fidelity (VF) modelling methods have been widely used in complex engineering system design to mitigate the computational burden. Building a VF model generally includes two parts: design of experiments and metamodel construction. In this article, an adaptive sampling method based on improved hierarchical kriging (ASM-IHK) is proposed to refine the improved VF model. First, an improved hierarchical kriging model is developed as the metamodel, in which the low-fidelity model is varied through a polynomial response surface function to capture the characteristics of a high-fidelity model. Secondly, to reduce local approximation errors, an active learning strategy based on a sequential sampling method is introduced to make full use of the already required information on the current sampling points and to guide the sampling process of the high-fidelity model. Finally, two numerical examples and the modelling of the aerodynamic coefficient for an aircraft are provided to demonstrate the approximation capability of the proposed approach, as well as three other metamodelling methods and two sequential sampling methods. The results show that ASM-IHK provides a more accurate metamodel at the same simulation cost, which is very important in metamodel-based engineering design problems.

Remaining useful life (RUL) prediction is very important for improving the availability of a system and reducing its life cycle cost. This paper proposes a deep long short-term memory (DLSTM) network-based RUL prediction method using multiple sensor time series signals. The DLSTM model fuses multi-sensor monitoring signals for accurate RUL prediction, which is able to discover the hidden long-term dependencies among sensor time series signals through deep learning structure. By grid search strategy, the network structure and parameters of the DLSTM are efficiently tuned using an adaptive moment estimation algorithm so as to realize an accurate and robust prediction. Two various turbofan engine datasets are adopted to verify the performance of the DLSTM model. The experimental results demonstrate that the DLSTM model has a competitive performance in comparison with state-of-the-arts reported in literatures and other neural network models.

In general, sampling strategy plays a very important role in metamodel based design optimization, especially when computationally expensive simulations are involved in the optimization process. The research on new optimization methods with less sampling points and higher convergence speed receives great attention in recent years. In this paper, a multi-point sampling method based on kriging (MPSK) is proposed for improving the efficiency of global optimization. The sampling strategy of this method is based on a probabilistic distribution function converted from the expected improvement (EI) function. It can intelligently draw appropriate new samples in an area with certain probability according to corresponding EI values. Besides, three strategies are also proposed to speed up the sequential sampling process and the corresponding convergence criterions are put forward to stop the searching process reasonably. In order to validate the efficiency of this method, it is tested by several numerical benchmark problems and applied in two engineering design optimization problems. Moreover, an overall comparison between the proposed method and several other typical global optimization methods has been made. Results show that the higher global optimization efficiency of this method makes it particularly suitable for design optimization problems involving computationally expensive simulations.

Multi-fidelity metamodeling provides an efficient way to approximate expensive black-box problems by utilizing the samples of multiple fidelities. While it still faces the challenge of "curse-of-dimensionality" when used in approximating high dimensional problems. On the other hand, the high dimensional model representation (HDMR) method, as an efficient tool to tackle high dimensional problems, can only handle single-fidelity samples in approximation. Therefore, a hybrid metamodel which combines Cut-HDMR with Co-kriging and kriging is proposed to improve the metamodeling efficiency for high dimensional problems. The developed HDMR, termed as MF-HDMR, can efficiently use multi-fidelity samples to approximate black-box problems by using a two stage metamodeling strategy. It can naturally explore and exploit the linearity/nonlinearity and correlations among variables of underlying problems, which are unknown or computationally expensive. Besides, to further improve the efficiency of MF-HDMR, an extended maximin distance sequential sampling method is proposed to add new sample points of different fidelities in the metamodeling process. Moreover, a mathematical function is used to illustrate the modeling theory and procedures of MF-HDMR. In order to validate the proposed method, it is tested by several numerical benchmark problems and successfully applied in the optimal design of a long cylinder pressure vessel. Moreover, an overall comparison between the proposed method and several other metamodeling methods has been made. Results show that the proposed method is very efficient in approximating high dimensional problems by using multi-fidelity samples, thus making it particularly suitable for high dimensional engineering design problems involving computationally expensive simulations.

In this study, a method combining magnetic, MIG, and laser was applied to weld the 304 stainless steel with a thickness of 4 mm. The effect of magnetic field on the weld microstructures and mechanical properties was investigated. The weld geometry and microstructure were characterized by optical microscope (OM) and scanning electric microscopy. Electron back scattered diffraction (EBSD) was used to determine the grain sizes and crystallographic orientations. Residual stress and tensile stress of welds were measured and compared with the laser-arc hybrid welds without an external magnetic field. The results showed that with an appropriate magnetic field intensity, an optimal joint was obtained with tensile strength enhanced by nearly 12% and tensile residual stresses reduced. In addition, the grain refining and promotion of the phase transformation with the magnetic field were analyzed.

Using computationally cheap low-fidelity (LF) model and more accurate but expensive high-fidelity (HF) model, variable fidelity (VF) model has been widely used in engineering design to replace the actual computationally expensive experiments or computer simulations. To further extend the application of VF to reliability-based design optimization (RBDO), a new framework based on sequential linear programming (SLP) is proposed in this paper. Combining the advantages of additive scaling method and multiplicative scaling method, a hybrid scaling method based on least squares (LSHS) is developed. In LSHS method, the VF model is introduced to replace the implicit performance function in RBDO by using the HF function values and gradient values at all evaluated points around the current design. With the failure probability and its gradient calculated by Monte Carlo Simulation (MCS) at current design, SLP is adopted to calculate the next design. A novel method which considers the target reliability index and the influence domain at the current design is also developed to determine the step size in every sub-optimization problem. Two numerical examples and the shape optimization problem of a curved beam are analyzed in order to demonstrate the performance of the proposed methodology. The comparison results show that the proposed method is very accurate and efficient.

Purpose – The purpose of this paper is to present a modified bi-level integrated system collaborative optimization (BLISCO) to avoid the non-separability of the original BLISCO. Besides, to mitigate the computational burden caused by expensive simulation codes and employ both efficiently simplified and expensively detailed information in multidisciplinary design optimization (MDO), an effective framework combining variable fidelity metamodels (VFM) and modified BLISCO (MBLISCO) (VFM-MBLISCO) is proposed. Design/methodology/approach – The concept of the quasi-separable MDO problems is introduced to limit range of applicability about the BLISCO method and then based on the quasi-separable MDO form, the modification of BLISCO method without any derivatives is presented to solve the problems of BLISCO. Besides, an effective framework combining VFM-MBLISCO is presented. Findings – One mathematical problem conforms to the quasi-separable MDO form is tested and the overall results illustrate the feasibility and robustness of the MBLISCO. The design of a Small Waterplane Area Twin Hull catamaran demonstrates that the proposed VFM-MBLISCO framework is a feasible and efficient design methodology in support of design of engineering products. Practical implications – The proposed approach exhibits great capability for MDO problems with tremendous computational costs. Originality/value – A MBLISCO is proposed which can avoid the non-separability of the original BLISCO and an effective framework combining VFM-MBLISCO is presented to efficiently integrate the different fidelities information in MDO.

Laser-MIG hybrid welding of 316L stainless steel was carried out to investigate influence of welding process parameters, i.e., laser power (P), welding current (I), distance between laser and arc (D), and welding speed (V) on arc characteristics, droplet transfer, and weld quality. Arc characteristics and droplet transfer behavior were investigated using high-speed imaging technology. Microstructures of the joint were observed by optical microscope, and microhardness was measured by microhardness tester. The results showed that the maximum deviation angle of the arc from the wire axis decreases with the increasing laser power. Welding current played a dominant role in arc length and droplet transfer mode. Optimal weld with no spatters and humps was obtained when P = 3 kW, I = 140 A, D = 3 mm, and V = 1.2 m/min. Microstructures in the weld zone mainly consist of columnar and equiaxed dendrites. Microhardness decreased toward the center of the weld zone, increased toward the WZ boundary, and decreased sharply at the heat-affected zone (HAZ).

Laser arc hybrid welding became a useful method to weld thick plates. But a sound weld is not so easy to obtain because of the uncontrollability of droplet transfer state, especially in ultra-narrow gap welding process. In this study, V-like ultra-narrow gap welds were carried out using 80 % Ar + 20 % CO2 blend as shielding gas. A high-speed video system was used to observe the droplet transfer behaviors. The results showed that the transfer mode did not change with the same welding current. The transfer mode changed from the short circuiting transfer to the mixture of the short circuiting and the globular transfer and then to spray transfer as the welding current increased. The relationship between the droplet transfer process and the welded defects was studied to obtain high-quality weld joint with a stable transfer process. The optimal parameter window between welding current and groove size was found. Only when the welding current was 200 to 270 A and groove gap was 2 to 3 mm, can a good welded joint be got. Finally, 30-mm-thick plate with 5.49-mm maximum groove gap was welded well by one pass laser autogenous welding and seven passes laser arc hybrid welding process.

Laser brazing (LB) provides a promising way to join the galvanized steels in automotive industry. The process parameters of LB have significant effects on the bead profile and hence the quality of joint. Since the relationships between the process parameters and bead profiles cannot be expressed explicitly, it is impractical to determine the optimal process parameters intuitively. This paper proposes an optimization methodology by combining Kriging surrogate and particle swarm optimization (PSO) to address the process parameters optimization of the bead profiles in LB with crimping butt of 0.8-mm-thick galvanized steel. Firstly, an experiment using Taguchi L 25 orthogonal array is conducted where welding speed (WS), wire speed rate (WF), and gap (GAP) are taken into consideration as the input parameters, while the bead profiles are the output responses. Secondly, the relationships between the inputs and outputs are established using the Kriging model. Thirdly, the effects of the input parameters on the bead profiles are analyzed, and the global process parameters are obtained by the presented Kriging-PSO approach. At last, the verification experiments were conducted to verify the effectiveness of the optimal values. On the whole, the proposed hybrid method, Kriging-PSO, shows great promise for improving the effectiveness and stability of LB welding process.

LMPP is developed to enhance the accuracy and efficiency of Kriging-based RBDO.LMPP locates samples mainly in a local region around the current MPP.Feasibility of probabilistic constraint at the current design is checked in LMPP.LEFF criterion is proposed to determine the sequential samples in local region.IS using MPP as sampling center is used to perform reliability analysis. Kriging approximation has been widely used in reliability-based design optimization (RBDO) to replace the complex black-box performance functions. In this paper, a new local approximation method using the most probable point (LMPP) is proposed to improve the accuracy and efficiency of RBDO methods using Kriging model. In the LMPP, the concept of local sampling region is used and the most probable point (MPP) is chosen as the sampling center. The size of the local region is determined by target reliability and the linearity of probability constraint around MPP. Rather than fitting the Kriging model for all the probabilistic constraints, the new method uses the MPP to find feasible constraints, and only these feasible constraints are accurately approximated, which can significantly improve the optimization efficiency. Importance Sampling method using the MPP obtained above as sampling center is utilized to perform reliability analysis and reliability sensitivity calculation. A numerical example, a honeycomb material design problem and a box girder design application are used to demonstrate the computational capability of the LMPP method. The comparison results demonstrate that RBDO using the proposed method is very effective.

Metamodels are often used in engineering design optimization problems with expensive simulations to save computational cost. But these metamodels often face "curse-of-dimensionality" when used in approximating high dimensional problems. Therefore, a new high dimensional model representation (HDMR) by combining Cut-HDMR with an enhanced RBF based on ensemble model is proposed. The developed HDMR, termed as ERBF-HDMR, sufficiently utilizes advantages of RBF and ensemble model in the modeling process. It can naturally explore and exploit the linearity/nonlinearity and correlations among variables of underlying problems, which are unknown or computationally expensive. Besides, to improve the efficiency of the ERBF-HDMR, an adaptive sampling method is proposed to add new sample points. Moreover, a mathematical function is used to illustrate the modeling principles and procedures of the adaptive ERBF-HDMR. And a comprehensive comparison between the adaptive ERBF-HDMR and other different Cut-HDMRs in literature has been made on eleven numerical examples with a wide scope of dimensionalities to show the prediction ability of different HDMRs. Finally, the proposed HDMR is used in the structural design optimization of the bearings of an all-direction propeller with the aim of reducing vibration.

The angular distortion is a typical out-of-plane distortion, and it has negative effects on the performance of welded structures. However, the researches on angular distortion of welded structures using intelligent algorithm and mathematical analysis are comparatively less. In this article, the influence from the bead profile on the angular distortion is analyzed, and the angular distortion of tungsten inert gas arc welding with no gap would be predicted by back propagation neural network and the novel inherent strain considering the actual bead geometry model, and the prediction accuracy is also evaluated through comparative analysis of the results with each other. The average relative error of the model built using inherent strain considering the actual bead geometry model method is only 1.289 % and better than that predicted by back propagation neural network algorithm (4.772 %). Meanwhile, the inherent strain considering the actual bead geometry model prediction stability that is estimated using standard deviation is also clearly better than that of back propagation neural network. Actually, the prediction methods by back propagation neural network algorithm and inherent strain considering the actual bead geometry model are proved to be correct and stable. Therefore, the proposed methods can be used to predict the angular distortion of the welded structures with no gap butt joint and guide the actual welding process to decrease the welding deformation.

Process planning and scheduling are two crucial components in a manufacturing system. The integration of the two functions has an important significance on improving the performance of the manufacturing system. However, integrated process planning and scheduling is an intractable non-deterministic polynomial-time (NP)-hard problem, and the multiple objectives requirement widely exists in real-world production situations. In this paper, a multi-objective mathematical model of integrated process planning and scheduling is set up with three different objectives: the overall finishing time (makespan), the maximum machine workload (MMW), and the total workload of machines (TWM). A multi-objective memetic algorithm (MOMA) is proposed to solve this problem. In MOMA, all the possible schedules are improved by a problem-specific multi-objective local search method, which combines a variable neighborhood search (VNS) procedure and an effective objective-specific intensification search method. Moreover, we adopt the TOPSIS method to select a satisfactory schedule scheme from the optimal Pareto front. The proposed MOMA is tested on typical benchmark instances and the experimental results are compared with those obtained by the well-known NSGA-II. Computational results show that MOMA is a promising and very effective method for the multi-objective IPPS problem.

Purpose– Kriging model has been widely adopted to reduce the high computational costs of simulations in Reliability-based design optimization (RBDO). To construct the Kriging model accurately and efficiently in the region of significance, a local sampling method with variable radius (LSVR) is proposed. The paper aims to discuss these issues.Design/methodology/approach– In LSVR, the sequential sampling points are mainly selected within the local region around the current design point. The size of the local region is adaptively defined according to the target reliability and the nonlinearity of the probabilistic constraint. Every probabilistic constraint has its own local region instead of all constraints sharing one local region. In the local sampling region, the points located on the constraint boundary and the points with high uncertainty are considered simultaneously.Findings– The computational capability of the proposed method is demonstrated using two mathematical problems, a reducer design and a box girder design of a super heavy machine tool. The comparison results show that the proposed method is very efficient and accurate.Originality/value– The main contribution of this paper lies in: a new local sampling region computational criterion is proposed for Kriging. The originality of this paper is using expected feasible function (EFF) criterion and the shortest distance to the existing sample points instead of the other types of sequential sampling criterion to deal with the low efficiency problem.

In the present paper, the application of laser cleaning technology in thick plate ultra-narrow gap multi-pass multi-layer laser non-autogenous welding process was described. The comparison between weld cross sections and the amount of oxide on the weld surface before and after welding tested by environmental scanning electron microscopy (ESEM) proved the laser cleaning method does play an important role in cleaning the weld. The influence rule of some cleaning parameters to welded joints, including groove angle, laser power, defocusing amount, and cleaning speed, was studied, and the welding defects decreased obviously with the optimal cleaning parameters. Combining this cleaning technology and the laser non-autogenous welding system comprised of the laser autogenous welding, laser wire filling welding, and the laser arc hybrid welding, a 40-mm-thick plate was welded well using a 4-kW fiber laser.

Process planning and scheduling are two of the most important functions of a manufacturing system. Traditionally, these two functions are executed separately. Since they are interrelated, conducting process planning and scheduling simultaneously will provide more advantages. In this paper, according to the characteristics of the integrated process planning and scheduling (IPPS) problem, a hybrid honey bee mating optimization (HBMO) algorithm, which combines the HBMO algorithm and variable neighborhood search (VNS), is proposed to settle the problem with makespan criterion. Different with conventional HBMO, we utilize VNS with two effective and efficient neighborhood structures in the algorithm to simulate the workers’ brood caring action to avoid premature convergence and to find more excellent broods. In addition, a novel individual initialization method is developed in the algorithm. The proposed algorithm is tested on typical benchmark instances taken from related literature, and the computational results are compared with those of other algorithms. Experimental results show the effectiveness and efficiency of the hybrid HBMO algorithm. New upper bounds have been captured for 16 instances, and most instances have been improved within reasonable CPU times.

Surface roughness is a technical requirement for machined products and one of the main product quality specifications. In order to avoid the costly trial-and-error process in machining parameters determination, the Gaussian process regression (GPR) was proposed for modeling and predicting the surface roughness in end face milling. Cutting experiments on C45E4 steel were conducted and the results were used for training and verifying the GPR model. Three parameters, spindle speed, feed rate, and depth of cut were considered; the experiment results showed that depth of cut is the main factor affecting the surface roughness and regression results showed that the GPR model has a good precision in predicting the surface roughness in different cutting conditions. The prediction accuracy was nearly about 84.3 %. Based on the GPR prediction model, 3D-maps of surface roughness under various cutting parameters could be obtained. It is very concise and useful to select the appropriate cutting parameters according to the maps. As experimental results did not conform to the empirical knowledge, frequency spectrums of the tool were analyzed according to the 3D-maps, it was found that tool vibration is also a crucial factor affecting the machined surface quality.

In this paper, we describe a method employing a suction device adapted to provide a negative pressure zone on the surface of the keyhole to allow the highly-pressurized zinc vapor to escape. The microstructure and properties of the lap joint were studied, and the distribution of zinc element in the joints was analyzed using synchrotron radiation X-ray. A high-speed video camera was used to record the dynamic behavior of the laser-induced plasma plume and the zinc vapor. Experimental results demonstrated that this suction method can not only facilitate venting of the high pressure zinc vapor from the molten pool and the keyhole, but also stabilizes the laser-induced plasma plume during the welding process. A lap joint with a good surface quality and excellent mechanical strength was obtained using this method.

This paper describes a study on laser butt welding of 4 and 2 mm SUS301L stainless steel and a detailed analysis of welding joints. The gap tolerance of butt joint was also studied with optimized process parameters. The electrolytic etching in 10 % oxalate solution was used to test the intergranular corrosion of the 4 mm SUS301L welded joint. Fatigue property of the 2 mm SUS301L welded joint was tested under the conditional cycle times of 1 × 107. Using optical microscopy, the changes of metallurgical microstructure in the weld zone of 4 mm SUS301L were also studied. It has been found that laser butt welding of 4 mm SUS301L is able to achieve sound metallurgical morphology and high strength weld joint when the butt gap is within certain tolerance. The weld joint also has good resistance to intergranular corrosion and has a fatigue limit of 310 MPa.

Engineering design, especially for complex engineering systems, is usually a time-consuming process involving computation-intensive computer-based simulation and analysis methods. A difference mapping method using least square support vector regression is developed in this work, as a special metamodelling methodology that includes variable-fidelity data, to replace the computationally expensive computer codes. A general difference mapping framework is proposed where a surrogate base is first created, then the approximation is gained by a mapping the difference between the base and the real high-fidelity response surface. The least square support vector regression is adopted to accomplish the mapping. Two different sampling strategies, nested and non-nested design of experiments, are conducted to explore their respective effects on modelling accuracy. Different sample sizes and three approximation performance measures of accuracy are considered.

Engineering design is usually a daunting optimization task which often involving time-consuming, even computation-prohibitive process. To reduce the computational expense, metamodels are commonly used to replace the actual expensive simulations or experiments. In this paper, a new and efficient metamodeling method named prior-knowledge input least square support vector regression (PKI-LSSVR) is developed, in which samples from different levels of fidelity are incorporated to gain an accurate approximation with limited times of the high-fidelity (HF) expensive simulations. The low-fidelity (LF) output serves as a prior-knowledge of the real response function, and then is used as the input variables of least square support vector regression (LSSVR). When the corresponding HF response is gained, a function that maps the LF outputs to HF outputs is constructed via LSSVR. The predictive accuracy of LSSVR models is highly dependent on their learning parameters. Therefore, a novel optimization method, cellular particle swarm optimization (CPSO), is exploited to seek the optimal hyper-parameters for PKI-LSSVR in order to improve its generalization capability. To get a better optimization performance, a new neighborhood function is developed for CPSO where the global and local search is efficiently balanced by adaptively varied neighbor radius. Several numerical experiments and one engineering case verify the efficiency of the proposed PKI-LSSVR method. Sample quality merits including sample sizes and noise, and metamodel performance evaluation measures incorporating accuracy, robustness, and efficiency are considered.

Reliability prediction is of great importance to improve the operational safety of machinery and decreasing their maintenance costs. In this paper, a new method combining double-Wiener process model with Monte Carlo algorithm is proposed to solve the problem of degradation modeling and reliability prediction of machinery with multiple degradation characteristics. Unlike other Wiener process-based prediction methods that only the mean is modelled, this method considers the degradation of both mean and variance, making degradation modelling more accurate. Meanwhile, the proposed method estimates reliability level of the machinery based on its entire monitoring information to date through an expectation maximization algorithm and a Monte Carlo algorithm, which does not require historical degradation data of other machines in a population. A numerical degradation case and a bearing degradation case with a set of degradation data are studied to validate the proposed method. The results demonstrate the effectiveness of the proposed method compared with other existing methods.

Optimization for the surface grinding process is a problem with high complexity and nonlinearity. Hence, evolutionary algorithms are needed to apply to get the optimum solution of the problem instead of the traditional optimization algorithms. In this work, a hybrid particle swarm optimization (HPSO) algorithm which combines the dynamic neighborhood particle swarm optimization (DN-PSO) algorithm with the strategy of mutation considering constraints is presented to handle multi-objective optimization for surface grinding process. Such four process parameters as wheel speed, workpiece speed, depth of dressing, and lead of dressing are considered as the variables for optimization, and the following three objectives such as production cost, production rate, and surface roughness are used in a multi-objective function model with a weighted approach. Meanwhile, the constraints of thermal damage, wheel wear, and machine tool stiffness are considered. Computational experiments are conducted on cases of both rough grinding and finish grinding, and comparison results with the previously published results obtained by using other optimization techniques shows the efficiency of the proposed algorithm.

This paper discusses how to improve the position precision of a semi-closed loop servo system. A support vector regression algorithm is chosen to model and predict position error. The predicted error is then fed back to the input entry to compensate the error. Fuzzy PID control is introduced to adjust the controlling rule of the PID controller in the semi-closed loop servo system so as to improve the dynamic response characteristics of the servo system and reach a high degree of position precision. A case study is implemented. The simulation and experimental results show that combining the improved fuzzy control with predicted position error feedback ensures a high degree of position precision and a high degree of dynamic response characteristics.

In the medium-speed wire electrical discharge machining (MS-WEDM) process, the extremely high temperature and massive electrical discharges in a fraction of 1 s result in the poor surface quality such as high tensile residual stresses, high surface roughness, white layers, and micro cracks. In this paper, an experimental plan for central composite design (CCD) of processing the tool steel (SKD11) has been conducted according to response surface methodology (RSM). The aim is to develop the mathematical model that can correlate the main process parameters of MS-WEDM with machining performance and to seek the optimal parameters on material removal rate (MRR) and 3D surface quality (Sq) by integrated RSM and Non-dominated Sorting Genetic Algorithm-II (NSGA-II). Then, a set of pareto-optimal solutions is obtained. Moreover, from the confirmation experiment, it has been proved that the optimal process-parameter combinations are suitable on the MRR and the 3D surface texture. Eventually, it has also demonstrated that the method of integrated RSM and NSGA-II is an effective way for multi-objective optimization.

Cutting force is one of the fundamental elements that can provide valuable insight in the investigation of cutter breakage, tool wear, machine tool chatter, and surface finish in face milling. Analyzing the relationship between process factors and cutting force is helpful to set the process parameters of the future cutting operation and further improve production quality and efficiency. Since cutting force is impacted by the inherent uncertainties in the machining process, how to predict the cutting force presents a significant challenge. In the meantime, face milling is a complex process involving multiple experts with different domain knowledge, collaborative evaluation of the cutting force model should be conducted to effectively evaluate the constructed predictive model. Gene Expression Programming (GEP) combines the advantages of the Genetic Algorithm (GA) and Genetic Programming (GP), and has been successfully applied in function mining and formula finding. In this paper, a new approach to predict the face milling cutting force based on GEP is proposed. At the basis of defining a GEP environment for the cutting force prediction, an explicit predictive model has been constructed. To verify the effectiveness of the proposed approach, a case study has been conducted. The comparisons between the proposed approach and some previous works show that the constructed model fits very well with the experimental data and can predict the cutting force with a high accuracy. Moreover, in order to better apply the constructed predictive models in actual face milling process, a collaborative model evaluation method is proposed to provide a distributed environment for geographical distributed experts to evaluate the constructed predictive model collaboratively, and four kinds of collaboration mode are discussed.

The core loss of the grain-oriented silicon steel influences the energy loss of transformer. Pulse energy, point spacing, and scribing spacing are the three key parameters of laser scribing process, which determine the core loss of silicon steel. In this study, the relationship between the three key parameters and core loss reduction was investigated and analyzed. Experiments of laser scribing on 30Q130 silicon steel with different parameter combinations were implemented. The results showed that there was no obvious silicon coating burns in the surface of the steel after laser scribing and that the core loss reduction rate (reduction rate) significantly increased with the increasing laser energy density. However, when the energy density exceeded a certain range, the reduction rate decreased and gradually tended to a stable level. Hence, the parameters had significant influence on the reduction rate of core loss, and the two-factor interaction effects of reduction rate of core loss were prominent when parameters of high pulse energy, small point spacing, and small scribing spacing were selected. The optimization combination values of the three key parameters of laser scribing process on 30Q130 silicon steel was acquired by genetic algorithm–enhanced artificial neural network algorithm. For achieving high reduction of core loss, the optimized combination of pulse energy of 2.52 mJ, small point spacing of 0.22 mm, and small scribing spacing of 3.03 mm were selected, and the reduction rate of 13.12 % was verified through experiment.

Currently, sustainable manufacturing (SM) attracts more and more attentions due to the increasing environmental pollution and energy shortage threat. Energy consumption is a fundamental element of SM for its valuable effect in the environmental impacts and business opportunities. Analyzing the relationship between process parameters and energy consumption is helpful to reduce production costs, eliminate negative environmental impacts, and increase business opportunities. Since energy consumption is impacted by the inherent uncertainties in the machining process, how to model energy consumption presents a significant challenge. Gene Expression Programming (GEP) combines the advantages of the Genetic Algorithm and Genetic Programming, and has been successfully applied in formula finding. In this paper, a Greedy Randomized Adaptive Search Procedure (GRASP)-based Gene Expression Programming, named GGEP, is proposed to predict the face milling energy consumption. In this proposed GGEP approach, a GRASP-based learning mechanism and an iterative re-start mechanism have been introduced into the basic GEP. At the basis of defining a GGEP environment for the energy consumption prediction, an explicit model has been constructed. To verify the effectiveness of the proposed approach, a case study has been conducted. The analysis of experiment results reveals that the proposed approach models and predicts the energy consumption with high accuracy and high-speed convergence. Moreover, in order to better study the mechanism of machining, the influence and contribution of different impact factors on energy consumption in face milling are analyzed.

Life cycle assessment (LCA), as an assessment tool for environmental performance, is used widely in decision making of product design. However, apparently, it is not sufficient to make final decision only depending on environmental assessment results for profit-directed organizations. One of the main purposes of this paper is to propose a methodology for integration of LCA and economic analysis tool-life cycle costing (LCC) in order to get the integrated evaluation results. A framework of integration of LCA and LCC has been introduced, which is contained by four components: the definition of unity time and physical boundaries, integration of inventory analysis, integration of impact assessment, environmental and economic interpretation. However, the integrated evaluation results always indicate that the relationship between economic and environmental performance is not in balance. Optimization is as important as integration to eco-balance. An optimization method is proposed to improve the initial product design with maximizing the integrated environmental and economic benefit for mechanical product. In optimization step, product system is divided two parts with environmental subsystem and economic subsystem. The integrated evaluation results are adopted to support for the optimization. Some mathematic optimization models are set up for environmental and economic subsystems. Multidisciplinary design optimization is applied to optimize these models so that the initial mechanical product design can achieve the best environmental and economic performance result. A case study of type 4135G diesel engine is presented to validate the rationality and feasibility.

Flexible job-shop problem has been widely addressed in literature. Due to its complexity, it is still under consideration for research. This paper addresses flexible job-shop scheduling problem (FJSP) with three objectives to be minimized simultaneously: makespan, maximal machine workload, and total workload. Due to the discrete nature of the FJSP problem, conventional particle swarm optimization (PSO) fails to address this problem and therefore, a variant of PSO for discrete problems is presented. A hybrid discrete particle swarm optimization (DPSO) and simulated annealing (SA) algorithm is proposed to identify an approximation of the Pareto front for FJSP. In the proposed hybrid algorithm, DPSO is significant for global search and SA is used for local search. Furthermore, Pareto ranking and crowding distance method are incorporated to identify the fitness of particles in the proposed algorithm. The displacement of particles is redefined and a new strategy is presented to retain all non-dominated solutions during iterations. In the presented algorithm, pbest of particles are used to store the fixed number of non-dominated solutions instead of using an external archive. Experiments are performed to identify the performance of the proposed algorithm compared to some famous algorithms in literature. Two benchmark sets are presented to study the efficiency of the proposed algorithm. Computational results indicate that the proposed algorithm is significant in terms of the number and quality of non-dominated solutions compared to other algorithms in the literature.

Along with the increasing attention on the environment and resources, green design and green manufacturing has become a tendency nowadays. In order to mitigate the computational burden when solving green design problem of the complex engineering system, a variable fidelity metamodel-based analytical target cascading framework (VFATC) is developed to explore the application of variable fidelity (VF) metamodels in analytical target cascading (ATC). In this VFATC framework, a VF approximation modeling method is developed, which employs both computationally efficient simplified (low fidelity, LF) and expensively detailed (high fidelity, HF) information. To efficiently integrate the LF and HF information, kriging is enhanced to scale LF model (LFM) to HF model (HFM). Then, the scaled LFM is used as an approximation model to replace the analysis models in VFATC. The effectiveness of VFATC framework is applied into a lightweight design problem of cantilever beams and a ship design problem with the objective of oil consumption reduction. Overall results show the VFATC methods introduced in this paper provide an effective way of improving computational efficiency of multidisciplinary green design optimization problems based on complex HF simulation models.