Search

In order to manufacture functional parts using filament deposition modelling (FDM), an understanding of the machine's capabilities is necessary. Eliciting this understanding poses a significant challenge due to a lack of knowledge relating manufacturing process parameters to mechanical properties of the manufactured part. Prior work has proposed that this could be overcome through the creation of capability profiles for FDM machines. However, such an approach has yet to be implemented and incorporated into the overall design process. Correspondingly, the aim of this paper is two-fold and includes the creation of a comprehensive capability profile for FDM and the implementation of the profile and evaluation of its utility within a generative design methodology. To provide the foundations for the capability profile, this paper first reports an experimental testing programme to characterise the influence of five manufacturing parameters on a part's ultimate tensile strength (UTS) and tensile modulus (E). This characterisation is used to train an artificial neural network (ANN). This ANN forms the basis of a capability profile that is shown to be able to represent the mechanical properties with RMSEP of 1.95 MPa for UTS and 0.82 GPa for E. To validate the capability profile, it is incorporated into a generative design methodology enabling its application to the design and manufacture of functional parts. The resulting methodology is used to create two load bearing components where it is shown to be able to generate parts with satisfactory performance in only a couple of iterations. The novelty of the reported work lies in demonstrating the practical application of capability profiles in the FDM design process and how, when combined with generative approaches, they can make effective design decisions in place of the user. [ABSTRACT FROM AUTHOR]

The role of prognostics and health management is ever more prevalent with advanced techniques of estimation methods. However, data processing and remaining useful life prediction algorithms are often very different. Some difficulties in accurate prediction can be tackled by redefining raw data parameters into more meaningful and comprehensive health level indicators that will then provide performance information. Proper data processing has a significant importance on remaining useful life predictions, for example, to deal with data limitations or/and multi-regime operating conditions. The framework proposed in this paper considers a similarity-based prognostic algorithm that is fed by the use of data normalisation and filtering methods for operational trajectories of complex systems. This is combined with a data-driven prognostic technique based on feed-forward neural networks with multi-regime normalisation. In particular, the paper takes a close look at how pre-processing methods affect algorithm performance. The work presented herein shows a conceptual prognostic framework that overcomes challenges presented by short-term test datasets and that increases the prediction performance with regards to prognostic metrics. [ABSTRACT FROM AUTHOR]

This paper reports an intelligent approach for modeling and optimisation of filling system design (FSD) in the case of sand casting process of aluminium alloy. In order to achieve this purpose, physics-based process modeling using finite element method (FEM) has been integrated with artificial neural networks (ANN) and genetic algorithm (GA) soft computing techniques. A three-dimensional FE model of the studied process has been developed and validated, using experimental literature data, to predict two melt flow behaviour (MFB) indexes named ingate velocity and jet high. Two feed-forward back-propagation ANN-based process models were developed and optimised to establish the relationship between the FSD input parameters and each studied MFB index. Both ANN models were trained, tested and tuned by using database generated from FE computations. It was found that both ANN models could independently predict, with a high accuracy, the values of the ingate velocity and the jet high for training and test data. The developed ANN models were coupled with an evolutionary GA to select the optimal FSD for each one. The validity of the found solutions was tested by comparing ANN-GA prediction with FE computation for both studied MFB indexes. It was found that error between predicted and simulated values does not exceed 5.61% and 6.31% respectively for the ingate velocity and the jet high, which proves that the proposed approach is reliable and robust for FSD optimisation. [ABSTRACT FROM AUTHOR]

The conventional methods of tool life estimation take a long time and consume a lot of work piece material. In this paper, a quicker method for the estimation of tool life is proposed, which requires less consumption of work piece material and tools. In this method the tool life is estimated by fitting a best-fit line on the data falling in the steady wear zone and finding the time till tool failure by extrapolation. Neural networks are used to predict lower, upper and most likely estimates of the tool life. Comparison between neural networks and multiple regression shows the superiority of the former. The paper also proposes a methodology for continuous monitoring of tool use in the shop floor and updating/obtaining the tool life estimates based on the shop floor feed back. [ABSTRACT FROM AUTHOR]

An electromagnetic forming process of FeP04 steel sheets is studied over a wide range of variation of technological parameters aiming at finding optimal values providing maximum deformation of the part. The process parameters considered in this paper are deformed part diameter ( d), thickness of specimen ( t), distance coil-specimen ( D), number of coil turns ( N), capacitance of capacitor bank ( C), and the charging voltage ( V). Each specimen was freely deformed on a die of ring type through a unique combination of input parameters included in the study, and the maximum depth of the deformed parts center ( h) was considered output parameter. Radial basis function neural networks are used for modeling the functional dependence between technological parameters and the resulting deformation of the material. Modeling results indicate an average mean square error around 4 % and a correlation between experimental data and neural model output exceeding 0.99. Sensitivity analysis reveals significant input parameters that decisively influence the output of the model. Simulation results are in good agreement with the experimental data, suggesting that neural networks can be considered a viable modeling alternative to existing approaches. [ABSTRACT FROM AUTHOR]

The capability to generate complex geometry features at tight tolerances and fine surface roughness is a key element in implementation of Creep Feed grinding process in specialist applications such as the aerospace manufacturing environment. Based on the analysis of 3D cutting forces, this paper proposes a novel method of predicting the profile deviations of tight geometrical features generated using Creep Feed grinding. In this application, there are several grinding passes made at varying depths providing an incremental geometrical change with the last cut generating the final complex feature. With repeatable results from coordinate measurements, both the radial and tangential forces can be gauged versus the accuracy of the ground features. The results of the tangential force were found more sensitive to the deviation of actual cut depth from the theoretical one. However, to make a more robust prediction on the profile deviation, its values were considered as a function of both force components. In addition, the power signals were obtained as these signals are also proportional to force and deviation measurements. Genetic programming (GP), an evolutionary programming technique, has been used to compute the prediction rules of part profile deviations based on the extracted radial and tangential force and correlated with the initial 'gauging' methodology. It was found that using this technique, complex rules can be achieved and used online to dynamically control the geometrical accuracy of the ground features. The GP complex rules are based on the correlation between the measured forces and recorded deviation of the theoretical profile. The mathematical rules are generated from Darwinian evolutionary strategy which provides the mapping between different output classes. GP works from crossover recombination of different rules, and the best individual is evaluated in terms of the given best fitness value so far which closes on an optimal solution. Once the best rule has been generated, this can be further used independently or in combination with other close-to-best rules to control the evolution of output measures of machining processes. The best GP terminal sets will be realised in rule-based embedded coded systems which will finally be implemented into a real-time Simulink simulation. This realisation gives a view of how such a control regime can be utilised within an industrial capacity. Neural networks were also used for GP rule verification. [ABSTRACT FROM AUTHOR]

This paper presents an intelligent process planning system using STEP features (ST-FeatCAPP) for prismatic parts. The system maps a STEP AP224 XML data file, without using a complex feature recognition process, and produces the corresponding machining operations to generate the process plan and corresponding STEP-NC in XML format. It carries out several stages of process planning such as operations selection, tool selection, machining parameters determination, machine tools selection and setup planning. A hybrid approach of most recent techniques (neural networks, fuzzy logic and rule-based) of artificial intelligence is used as the inference engine of the developed system. An object-oriented approach is used in the definition and implementation of the system. An example part is tested and the corresponding process plan is presented to demonstrate and verify the proposed CAPP system. The paper thus suggests a new feature-based intelligent CAPP system for avoiding complex feature recognition and knowledge acquisition problems. [ABSTRACT FROM AUTHOR]

This paper investigates an intelligent system that selects dispatching rules to apply locally for each machine in a job shop. Randomly generated problems are scheduled using optimal permutations of three different dispatching rules on five machines. A neural network is then trained to associate between a statistical characterization of the job mix in each of these problems, with the best combination of dispatching rules to use. Once trained, the neural network is able to recommend for new problems a dispatching rule to use on each machine. Two networks are trained separately for minimizing makespan and the mean flowtime in the job shop. Test results show that the combinations of dispatching rules suggested by the trained networks produce better results, for both objectives, than the alternative of using a single rule common to all machines. [ABSTRACT FROM AUTHOR]

Prediction of machine tool failure has been very important in modern metal cutting operations in order to meet the growing demand for product quality and cost reduction. This paper presents the study of building a neural network model for predicting the behavior of a boring process during its full life cycle. This prediction is achieved by the fusion of the predictions of three principal components extracted as features from the joint time–frequency distributions of energy of the spindle loads observed during the boring process. Furthermore, prediction uncertainty is assessed using nonlinear regression in order to quantify the errors associated with the prediction. The results show that the implemented Elman recurrent neural network is a viable method for the prediction of the feature behavior of the boring process, and that the constructed confidence bounds provide information crucial for subsequent maintenance decision making based on the predicted cutting tool degradation. [ABSTRACT FROM AUTHOR]

The concept design of checking fixtures for auto-body parts is a highly complex process that requires a human designer to draw from his rich experience. By exploiting recent advances in CAD/CAM and artificial intelligence techniques, one may constrain multiple solutions such that only good designs are considered. In this paper, a method of selecting type for checking fixtures is proposed that harnesses advantages of neural networks. This method attempts to capture relevant domain knowledge and is used to produce acceptable solutions. The method is applied to a case problem and the suggested checking fixture type is compared to one offered by a human designer. The agreement between the two solutions is very close. [ABSTRACT FROM AUTHOR]

Adjusting control factors (independent variables) to achieve an optimal level of output (response variable) is usually required in many real-world manufacturing problems. Common optimization methods often begin with estimating the relationship between a response and independent variables. Among these techniques, response surface methodology (RSM), due to its simplicity, has recently attracted extensive attention. However, on the one hand, in some cases, the relationship between a response and independent variables is too complex to be estimated using polynomial regression models. On the other hand, solving the obtained optimization model is not easy by exact methods. This paper introduces a new methodology to solve multi-response statistical optimization problems. The novel hybrid approach of this research involves a modeling technique, a neural network methodology, and a genetic algorithm. The modeling technique that is selected among three common available methods is responsible to model the multi-response statistical problem. The neural network approach generates required input data, and finally, the genetic algorithm tries to optimize the model and find the adjusted levels of the control factors. At the end, the application and the performance of the proposed methodology are demonstrated using numerical examples. The results of several statistical analyses show that the proposed methodology is superior to other available methods in the literature. [ABSTRACT FROM AUTHOR]

The quality of a tube-hydroformed component as well as the tooling cost and processing time involved in the process are notably affected by the component’s preform. Hence, it is necessary to produce a proper preform shape for the successful hydroforming from the initial tube to final shape. In this paper, the notion of equi-potential lines (EPLs) is used to find an appropriate preform shape in the tube hydroforming process for the first time. The EPLs generated between two conductors of different voltages show minimum work paths between the initial and final shapes. Based on this similarity, the EPLs method is utilized for preform shape design. Next, the forming pressure of the preform is determined using finite element analysis. Finally, the computationally expensive procedure introduced above is significantly facilitated by employing a multi-layer perceptron neural network which is trained using results from application of the procedure to a set of uniformly distributed random input vectors. Real-world examples are presented to demonstrate the applicability and efficiency of the proposed approach. [ABSTRACT FROM AUTHOR]

Experimental identification of anisotropic behavior law is currently obtained by performing several complicated tests and a long duration of experiments. This paper describes a new technique allowing for the identification of HILL anisotropic parameters by inverse technique method based on deep drawing of a cylindrical cup. The identification approach is based on the artificial neural network (ANN) computation trained from finite element simulation. The results obtained by ANN models and by the finite element method shows a good agreement. [ABSTRACT FROM AUTHOR]

Although image-based inspection has been applied to a wide range of industrial applications, inspection accuracy remains a challenging issue due to the complexity involved in industrial inspection. The common method adopted in industry is to use a qualified image as a template image to inspect each live image on a pixel-by-pixel basis. In this paper, a tolerance method is presented to replace the template image method. The said tolerance is formed by two indices computed from a sample image, instead of using the whole image for inspection. To ensure an accurate tolerance zone, a neural networks method is used to take the noise and uncertainties in the images under inspection into consideration. To improve neural networks training speed, the Taguchi method is adopted to select a minimum number of the sample images needed for training. Once a tolerance zone is obtained, live images are inspected against it. If the indices of a live image fall inside the tolerance zone, the part is regarded as good, otherwise defective. Three examples are given: one for auto part inspection, one for label inspection, and one for machining part inspection. The inspection accuracy achieved is above 94%. [ABSTRACT FROM AUTHOR]

This paper proposes a neurogenetic-based optimization scheme for predicting localized stable cutting parameters in inward turning operation. A set of cutting experiments are performed in inward orthogonal turning operation. The cutting forces, surface roughness, and critical chatter locations are predicted as a function of operating variables including tool overhang length. Radial basis function neural network is employed to develop the generalization models. Optimum cutting parameters are predicted from the model using binary-coded genetic algorithms. Results are illustrated with the data corresponding to four work materials, i.e., EN8 steel, EN24 steel, mild steel, and aluminum operated over a high speed steel tool. [ABSTRACT FROM AUTHOR]

Ultrasonic techniques have the potential to be used to detect sub-surface defects in aluminium castings. However, ultrasonic sensing techniques have not been successfully used to detect sub-surface defects in aluminium die castings with rough surfaces or in the ‘as-cast’ state due to the poor quality of signals. Ultrasonic signal noise caused by rough surfaces and grain size variations of the castings is difficult to eliminate. Hence, there is a need to process noisy ultrasonic signals to identify defects within the rough surface castings. This paper documents an investigation of ultrasonic signal analysis using artificial neural networks and hybrid signal pre-processing approaches for the purpose of detecting defects from noisy ultrasonic signals. In this investigation, ultrasonic signals were obtained from aluminium castings with different levels of surface roughness. The signals were first pre-processed using hybrid signal analysis techniques and then classified using an artificial neural network classifier. The hybrid pre-processing techniques utilised various combinations of fast Fourier transform (FFT), wavelet transform (WT) and principal component analysis. The best signal classification performance was generally achieved with a hybrid WT/FFT signal pre-processing technique. [ABSTRACT FROM AUTHOR]

In this paper we address the forward kinematics problem of a parallel manipulator and propose an iterative neural network strategy for its real-time solution to a desired level of accuracy. Parallel manipulators are closed kinematic structures that possess requisite rigidity to yield a high payload to self-weight ratio. Because of this unique feature, they have been employed in manufacturing, flight simulation systems, and medical robotics. However, it is this closed kinematic structure that has led to difficulty in their kinematic control, especially the forward kinematics control. The iterative neural network strategy we propose employs a trained neural network and an error compensation algorithm in the feedback loop. The proposed strategy was tested with data from a real-world flight simulation system. Results show that solutions with a maximum error in the position and orientation parameters of 0.25 mm and 0.01°, respectively, can be achieved in less than five iterations (or about 1 second). Because of the nature of this strategy, it is possible to implement it in a hardware form, which can result in a multi-fold reduction in the solution time for the same accuracy level. [ABSTRACT FROM AUTHOR]

The abrasive water jet machining process, a material removal process, uses a high velocity jet of water and an abrasive particle mixture. The estimation of appropriate values of the process parameters is an essential step toward an effective process performance. This has led to the development of numerous mathematical and empirical models. However, the complexity of the process confines the use of these models for limited operating conditions; e.g., some of these models are valid for special material combinations while others are based on the selection of only the most critical variables such as pump pressure, traverse rate, abrasive mass flow rate and others that affect the process. Furthermore, these models may not be generalized to other operating conditions. In this respect, a neural network approach has been proposed in this paper. Two neural network approaches, backpropagation and radial basis function networks, are proposed. The results from these two neural network approaches are compared with that from the linear and non-linear regression models. The neural networks provide a better estimation of the parameters for the abrasive water jet machining process. [ABSTRACT FROM AUTHOR]

The work presented in this paper is an investigation of the prediction of amplitudes of the specific grinding force components. An improved method for artificial neural networks (ANNs) establishment is proposed here allowing accurate prediction of specific normal and tangential grinding forces. This method can determine the optimal set of inputs to be used for these ANN. This set of inputs is composed of significant factors and interactions among factors that could possibility offer the best learning and generalization of ANNs simultaneously. A 48-run experimental design (MED) is used in this research to train the ANNs and a total of 81 experiments are conducted to test the generalization performances of ANNs. Results have indicated that the developed ANNs show low deviations from the training data, and acceptable deviations from the testing data. In addition, the accuracies of these ANNs are found to be significantly better than those of other approaches used for modelling of the specific grinding force components. These approaches use regression models, power models, genetic algorithms or the common ANNs for which only factors of the MED are usually used in the input layer. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of scheduling a set of independent jobs with sequence-dependent setups and distinct due dates on non-uniform multi-machines to minimize the total weighted earliness and tardiness, and explores the use of artificial neural networks as a valid alternative to the traditional scheduling approaches. The objective is to propose a dynamical gradient neural network, which employs a penalty function approach with time varying coefficients for the solution of the problem which is known to be NP-hard. After the appropriate energy function was constructed, the dynamics are defined by steepest gradient descent on the energy function. The proposed neural network system is composed of two maximum neural networks, three piecewise linear and one log-sigmoid network all of which interact with each other. The motivation for using maximum networks is to reduce the network complexity and to obtain a simplified energy function. To overcome the tradeoff problem encountered in using the penalty function approach, a time varying penalty coefficient methodology is proposed to be used during simulation experiments. Simulation results of the proposed approach on a scheduling problem indicate that the proposed coupled network yields an optimal solution which makes it attractive for applications of larger sized problems. [ABSTRACT FROM AUTHOR]

Seamless tubing is the most commonly used process for high quality pipe products due to its ability to provide material consistency. However, the yield is hindered by complex workmanship and manufacturing operations, with the resulting risk of flaws, low productivity, and high manufacturing costs. This paper describes a systematic procedure to implement a data-driven process modeling technology in a seamless tubing factory, using neural networks to model relationships between controlled and uncontrolled process parameters and the yield. The issues of data collection/analysis and dimensionality reduction are discussed. It was found that model predictive ability improves when only important variables are included in the model. A software tool is developed, which offers such functions as response surface visualization and yield prediction. [ABSTRACT FROM AUTHOR]

In response to increasing international competition, enterprises have been investigating new ways of cooperating with each other to cope with today’s unpredictable market behaviour. Advanced developments in information & communication technology (ICT) enabled reliable and fast cooperation to support real-time alliances. In this context, the virtual enterprise (VE) represents an appropriate cooperation alternative and competitive advantage for the enterprises. VE is a temporary network of independent companies or enterprises that can quickly bring together a set of core competencies to take advantage of market opportunity. In this emerging business model of VE, the key to enhancing the quality of decision making in the partner companies’ performance evaluation function is to take advantage of the powerful computer-related concepts, tools and technique that have become available in the last few years. This paper attempts to introduce a neural network model, which is able to contribute to the extrapolation of the probable outcomes based on available pattern of events in a virtual enterprise. Quality, delivery and progress were selected as determinant factors effecting the performance assessment. Considering the features of partner performance assessment and neural network models, a back-propagation neural network that includes a two hidden layers was used to evaluate the partner performance. [ABSTRACT FROM AUTHOR]

Neural networks can be considered to be new modelling tools in process control and especially in non-linear dynamical systems cases. Their ability to approximate non-linear functions has been very often demonstrated and tested by simulation and experimental studies. In this paper, a predictive control strategy of a semi-batch reactor based on neural network models is proposed. Results of a non-linear control of the reactant temperature of a semi-batch reactor are presented. The process identification is composed of an off-line phase that consists in training the network, and of an on-line phase that corresponds to the neural model adaptation so that it fits any modification of the process dynamics. Experimental results when using this method to control a semi-batch reactor are reported and show the great potential of this strategy in controlling non-linear processes. [ABSTRACT FROM AUTHOR]

The single EWMA controller has been proven to have excellent performance for small disturbances in the run-to-run process. However, incorrect selection of the EWMA parameter can have the opposite effect on the controlled process output. An adaptive system is necessary to automatically adjust the controller parameters on-line in order to have better performance. In this study, a simple and efficient algorithm based on neural networks (NN) is proposed to minimise the inflation of the output variance on line. The authors have shown that the sequence of EWMA gains, generated by a NN-based adaptive approach, converges close to the optimal controller value under IMA (1, 1), step and trend disturbance models. The paper also shows that the NN-based adaptive EWMA controller has a superior performance than its predecessors. [ABSTRACT FROM AUTHOR]

Neural network models can be effectively used to predict any type of functional relationship. In this paper, a neural network model is used to predict roll force and roll torque in a cold flat rolling process, as a function of various process parameters. A strategy is developed to obtain a prescribed accuracy of prediction with a minimum number of data for training and testing. The effect of increasing the size of training and testing data set is also examined. After the prediction of most likely value, upper and lower bound estimates are also found with the help of the neural network. With these estimates, the predicted value can be represented as a fuzzy number for use in fuzzy-logic based systems. [ABSTRACT FROM AUTHOR]

Porosity is a critical defect in laser powder bed fusion that limits the adoption of this technology. The variations in process parameters affect the level of porosity in additively manufactured parts. Due to the complex multiphysics of the laser powder bed fusion process, surrogate models can be used to predict the amount of porosity from the process parameters. Regression and machine learning approaches have been used for the porosity prediction. However, these models are developed for certain materials. This study compares different surrogate models for correlating the amount of porosity and the process parameters in combination with proposed dimensionless numbers that are dependent to both the process parameters and powder material properties. Regression, support vector machine, and neural networks models are trained using lack of fusion porosity synthetic data for three different materials. The results show that the support vector machine and the multi-layer neural network models that use process parameters and the dimensionless numbers as the independent variables can effectively predict the amount of porosity regardless of materials. [ABSTRACT FROM AUTHOR]

This work examines the possibility of using some classical optimization methods (augmented Lagrange multiplier method) or genetic algorithms and neural networks to optimize the cooling regime in hot-rolled complex beam processing. The objective is to optimize the cooling conditions so as to minimize the residual stresses. A detailed example shows that using this stochastic method and neural networks can be efficient. In other words, this work involves finite element analyses of both mechanical and thermodynamic properties of cooling beams, neural networks, genetic algorithms, and optimization to find a cooling regime with minimum residual stresses. [ABSTRACT FROM AUTHOR]

This study explores the application of bio-inspired algorithms (BIAs) in training artificial neural networks (ANNs) in the area of the nonlinear chemical process modeling. Motivated by the increasing complexity and operational efficiency of chemical processes, the need for schemes that can improve model identification of highly nonlinear systems is demanded. As a case study, the Tennessee Eastman (TE) chemical reactor problem is considered. The key issue is to find a particular architecture for an ANN that best model the TE chemical process. We propose the use of BIAs of bat algorithm (BA), firefly algorithm (FA), and artificial bee colony (ABC) algorithm as mechanisms to automatically update the synaptic weights of ANN. These algorithms were conducted to increase the ability of ANN to adapt the dynamic aspect of the TE process and prevent trapping into a local optimum. The proposed modeling framework was devised with extensive experiments and statistical analysis to illustrate the usability and suitability of the entire modeling and identification procedures. The results were explored with a discussion using the mean square error (MSE) and the variance account for (VAF) criteria to assess the degree of identification performance of the TE case study model. The reliability of the presented models was compared with previously developed models for the same subsystems of the TE reactor using competitive, intelligent approaches. The comparative results show that the proposed approach provides superior modeling performance and outperforms its competitors. [ABSTRACT FROM AUTHOR]

The article presents a new methodology for modelling the influence of parameters and conditions of surface grinding process on the value of roughness and grinding forces. Grinding processes are characterised by numerous factors influencing results of the process with a complex mechanism of the cumulative effects of their interactions. Therefore, authors for the development of the model used an artificial neural network. The input parameters of the model, apart from the processing parameters, were the properties of the workpiece and features of the grinding wheel. In the selection process of the neural model structure, an evaluation criterion was proposed which included the character of the influence of processing parameters on the resultant values of the grinding process for the given pair workpiece-tool. A high ability to data generalisation by the developed neural model was demonstrated. [ABSTRACT FROM AUTHOR]

Acoustic emission (AE) is very sensitive to minuscule molecular changes which allow it to be used in a dynamic control manner. The work presented here specifically investigates approaching grit and workpiece interaction during grinding processes. The single grit (SG) tests used in this work display that the intensities from air, occurring in between the grit and workpiece, show an increasing intensity as the grit tends towards the workpiece with 1-μm increments. As the grit interacts with the workpiece, a scratch is formed; different intensities are recorded with respect to a changing measured depth of cut (DOC). In the first instance, various AE were low tending towards high signal to noise ratios which is indicative of grit approaching contact; when contact is made, frictional rubbing is noticed, then ploughing with low DOC and, finally, actual cutting with a higher associated DOC. Dynamic control is obtained from the AE sensor extracting increasing amplitude significant of elastic changing towards greater plastic material deformation. Such control methods can be useful for grinding dressing ratios as well as achieving near optimal surface finish when faced with difficult to cut geometries. Two different materials were used for the same SG tests (aerospace alloys: CMSX4 and titanium-64) to verify that the control regime is robust and not just material dependent. The AE signals were then classified using neural networks (NNs) and classification and regression trees (CART)-based rules. A real-time simulation is provided showing such interactions allowing dynamic micro precision control. The results show clear demarcation between the extracted synthesized signals ensuring high accuracy for determining different phenomena: 3-1 μm approaching touch, touch, slight plastic deformation and, increasing plastic deformation. In addition to dressing ratios, the results are also important for micron accuracy set-up considerations. [ABSTRACT FROM AUTHOR]

A neural network (NN) modeling approach is presented for the prediction of laminated object manufacturing (LOM) process performance. A NN was developed using experimental data which were conducted on a LOM 1015 machine according to the principles of Taguchi design of experiments (DoE) method. The process parameters considered in the experiment to investigate LOM process performance were nominal layer thickness (NLT), heater temperature (HT), platform retract (PR), heater speed (HS), laser speed (LS), feeder speed (FS), and platform speed (PS). LOM process performance is divided in dimensional errors in X and Y directions (Ex and Ey), actual layer thickness (ALT), average surface roughness of vertical supporting frame (VSF-Ra), and tensile strength in X direction (TSx). It was found that NN approach can be applied in an easy way on designed experiments and predictions can be achieved, fast and quite accurate. The developed NN is constrained by the experimental region in which the designed experiment is conducted. Thus, it is very important to select parameters’ levels as well as the limits of the experimental region and the structure of the orthogonal experiment. The above analysis is useful for LOM users when prediction of process performance is needed. This methodology could be easily applied to different materials and initial conditions for optimization of other Rapid Prototyping (RP) processes. [ABSTRACT FROM AUTHOR]

In this work, the roll force and roll torque in a cold flat rolling process are modelled using first order Takagi–Sugeno fuzzy models. The fuzzy models predict the most likely lower and upper estimates of the roll force and roll torque. Although the fuzzy models can be based on the experimental data, in the present work, the required data is generated by radial basis function neural networks. The neural networks, in turn, are trained by a finite element method-based code. It is demonstrated that the coefficients of the linear crisp function used to represent the output variables in the fuzzy inference system can be used for assessing the sensitivity of these variables with respect to the process variables. An algorithm to detect and suppress the outliers in the data is proposed. The effectiveness of the proposed algorithm is demonstrated through an example. [ABSTRACT FROM AUTHOR]

Progressive shearing process of a thin metal sheet is regarded as one of the most important fabrication processes in the 3C industry. In this process, the problem of punch wear is a time-series issue that would be changed along with the increase of time and deciding the size of the punched hole. This study proposes a neural network to modeling the time-series problem involving three kinds of presentations. First, the time-characteristic diagram is plotted based on the characteristic values that the network inferred. Second, the characteristic value of the un-examined time could be derived by network inferring. Third, a band-type diagram is built to present the possible variation range of the characteristic analyzed. Two cases of punch wearing band and punched hole bands for IC (integrated circuit) leadframe dam-bar shearing process are discussed to demonstrate the construction of the network model. The verification experiments show that the network inferring results are in agreement with the actual process, and derive more accurate predictions than that of the curve-fitting methods commonly used in engineering. [ABSTRACT FROM AUTHOR]

This work examines the possibility of using genetic algorithms and some neural networks to optimise mechanisms. A detailed example shows that using this stochastic method along with neural networks is very efficient. We can thus speak of a metamodel for optimisation in the context of integrated design . [ABSTRACT FROM AUTHOR]