Search

Abstract The shuffled frog leaping algorithm (SFLA) is a promising metaheuristic bionics algorithm, which has been designed by the shuffled complex evolution and the particle swarm optimization (PSO) framework. However, it is easily trapped into local optimum and has the low optimization accuracy when it is used to optimize complex engineering problems. To overcome the shortcomings, a novel modified shuffled frog leaping algorithm (MSFLA) with inertia weight is proposed in this paper. To extend the scope of the direction and length of the updated worst frog (vector) of the original SFLA, the inertia weight α was introduced and its meaning and range of the new parameters are fully explained. Then the convergence of the MSFLA is deeply analyzed and proved theoretically by a new dynamic equation formed by Z-transform. Finally, we have compared the solution of the 7 benchmark functions with the original SFLA, other improved SFLAs, genetic algorithm, PSO, artificial bee colony algorithm, and the grasshopper optimization algorithm with invasive weed optimization. The testing results showed that the modified algorithms can effectively improve the solution accuracy and convergence property, and exhibited an excellent ability of global optimization in high-dimensional space and complex function problems.

In response to the challenge of noise filtering for the impulsive vibration signals of rolling bearings, this paper presented a novel filtering method based on the improved Morlet wavelet, which has clear physical meaning and is more conducive to parameter optimization through employing Gaussian waveform width to replace the traditional Morlet wavelet shape factor. Simultaneously, the marine predation algorithm was employed and the minimum Shannon entropy was used as the parameter optimization index while optimizing the shape width and center frequency of the improved Morlet wavelet. The vibration waveform of the rolling bearing was matched perfectly by using the optimized Morlet wave. Shannon entropy was used as the evaluation index of noise filtering, and the quantitative analysis of noise filtering was realized. Through experimental validation, this method was proved to be effective in noise elimination for rolling bearing. It is significance to preprocessing of vibration signal, feature extraction and fault recognition of rolling bearing.

Abstract Background Characterizing cancer molecular subtypes is crucial for improving prognosis and individualized treatment. Integrative analysis of multi-omics data has become an important approach for disease subtyping, yielding better understanding of the complex biology. Current multi-omics integration tools and methods for cancer subtyping often suffer challenges of high computational efficiency as well as the problem of weight assignment on data types. Results Here, we present an efficient multi-omics integration via weighted affinity and self-diffusion (MOSD) to dissect cancer heterogeneity. MOSD first construct local scaling affinity on each data type and then integrate all affinities by weighted linear combination, followed by the self-diffusion to further improve the patients’ similarities for the downstream clustering analysis. To demonstrate the effectiveness and usefulness for cancer subtyping, we apply MOSD across ten cancer types with three measurements (Gene expression, DNA methylation, miRNA). Conclusions Our approach exhibits more significant differences in patient survival and computationally efficient benchmarking against several state-of-art integration methods and the identified molecular subtypes reveal strongly biological interpretability. The code as well as its implementation are available in GitHub: https://github.com/DXCODEE/MOSD .

In cluster analysis, determining the number of clusters is an important issue because there is less information about the most appropriate number of clusters in the real problem. Automatic clustering is a clustering method that automatically finds the most appropriate number of clusters and divides instances into the corresponding clusters. In this paper, a novel automatic clustering algorithm based on the improved marine predator algorithm (IMPA) and K-means algorithm is proposed. The new IMPA utilizes refracted opposition-based learning in population initialization, generates opposite solutions to improve the diversity of the population and produces more accurate solutions. In addition, the sine-cosine algorithm is incorporated to balance global exploration and local development of the algorithm for dynamic updating of the predator and prey population positions. At the same time, the Gaussian-Cauchy mutation is combined to improve the probability of obtaining the globally optimal solution. The proposed IMPA is validated with some benchmark data sets. The calculation results show that IMPA is superior to the original MPA in automatic clustering. In addition, IMPA is also used to solve the problem of fault classification of Xi*an Jiaotong University bearing data. The results show that the IMPA has better and more stable results than other algorithms such as the original MPA, whale optimization algorithm, fuzzy C-means and K-means in automatic clustering.

In order to overcome the low accuracy of traditional Extreme Learning Machine (ELM) network in the performance evaluation of Rotate Vector (RV) reducer, a pattern recognition model of ELM based on Ensemble Empirical Mode Decomposition (EEMD) fusion and Improved artificial Jellyfish Search (IJS) algorithm was proposed for RV reducer fault diagnosis. Firstly, it is theoretically proved that the torque transmission of RV reducer has periodicity during normal operation. The characteristics of data periodicity can be effectively reflected by using the test signal periodicity characteristics of rotating machinery and EEMD. Secondly, the Logistic chaotic mapping of population initialization in JS algorithm is replaced by tent mapping. At the same time, the competition mechanism is introduced to form a new IJS. The simulation results of standard test function show that the new algorithm has the characteristics of faster convergence and higher accuracy. The new algorithm was used to optimize the input layer weight of the ELM, and the pattern recognition model of IJS-ELM was established. The model performance was tested by XJTU-SY bearing experimental data set of Xi'an Jiaotong University. The results show that the new model is superior to JS-ELM and ELM in multi-classification performance. Finally, the new model is applied to the fault diagnosis of RV reducer. The results show that the proposed EEMD-IJS-ELM fault diagnosis model has higher accuracy and stability than other models.

In order to understand the physical heat dissipation structure of welding robot controllers, the author proposes a research based on the design and simulation analysis of the physical heat dissipation structure of welding robot controllers. The author first analyzed that the design of welding heating system is the key to the research of welding robot heating technology, which is divided into the design of induction heating system temperature control circuit and temperature control program. The induction heating system is closely related to power electronics technology, with inverter design and soft switching technology being the focus and difficulty of this chapter. Secondly, using modular design methods, an induction heating system with a frequency of 450KHz and a power of 100 W is designed. This part is connected through an optocoupler and an induction heating system for power regulation and temperature control. Starting from designing the minimum system of a microcontroller, through keyboard input, temperature signal processing, analog-to-digital conversion, and finally to digital tube display output, the design of each module of the temperature control circuit was completed. Finally, in order to verify the effectiveness of the design, actual heat dissipation testing is required. By establishing an appropriate testing environment in the laboratory, the temperature changes and heat dissipation efficiency of the controller under different working conditions can be measured. Based on the actual test results, further adjustments and improvements can be made to the design to meet the heat dissipation needs of the welding robot.

According to BESO’s principle of binarizing continuous design variables and the excellent performance of the standard HPO algorithm in terms of solving continuous optimization problems, a discrete binary Hunter-prey optimization algorithm is introduced to construct an efficient topology optimization model. It was used to solve the problems that the BESO method of topology optimization has, such as easily falling into the local optimal value and being unable to obtain the optimal topology configuration; the metaheuristic algorithm was able to solve the topology optimization model’s low computational efficiency and could easily produce intermediate elements and unclear boundaries. Firstly, the BHPO algorithm was constructed by discrete binary processing using the s-shape transformation function. Secondly, BHPO-BESO topology optimization theory was established by combining the BHPO algorithm with BESO topology optimization. Using the sensitivity information of the objective function and the updated principle of the meta-heuristic of the BHPO algorithm, a semi-random search for the optimal topology configuration was carried out. Finally, numerical simulation experiments were conducted by using the three typical examples of the cantilever beam, simply supported beam, and clamping beam as optimization objects and the results were compared with the solution results of BESO topology optimization. The experimental results showed that compared with BESO, BHPO-BESO could find the optimal topology configuration with lower compliance and maximum stiffness, and it has higher computational efficiency, which can solve the above problems.

With the increase of service time, the rotation period of rotating machinery may become irregular, and the Ensemble Empirical Mode Decomposition (EEMD)can effectively reflect its periodic state. In order to accurately evaluate the working state of the Rotate Vector (RV) reducer, the torque transfer formula of the RV reducer is first derived to theoretically prove periodicity of torque transfer in normal operation. Then, EEMD is able to effectively reflect the characteristics of data periodicity. A fault diagnosis model based on EEMD-MPA-KELM was proposed, and a bearing experimental dataset from Xi‘an Jiaotong University was used to verify the performance of the model. In view of the characteristics of the industrial robot RV reducer fault was not obvious and the sample data is few, spectrum diagram was used to diagnose the fault from the RV reducer measured data. The EEMD decomposition was performed on the data measured by the RV reducer test platform to obtain several Intrinsic Mode Functions (IMF). After the overall average checking and optimization of each IMF, several groups of eigenvalues were obtained. The eigenvalues were input into the Kernel Extreme Learning Machine (KELM) optimized by the Marine Predators Algorithm (MPA), and the fault diagnosis model was established. Finally, compared with other models, the prediction results showed that the proposed model can judge the working state of RV reducer more effectively.

Bearing is an important part of rotating machinery, and its early fault diagnosis and accurate classification have always been difficult in engineering application. At present, the models based on the fusion of various optimization algorithms and neural networks have become one of the emerging techniques for accurate fault identification. Firstly, an improved antlion optimizer (ALO) algorithm based on estimation of distribution algorithm (EDA) and variable-step Lévy flight strategy, abbreviated as ELALO, is proposed as a new bionic intelligence. During the initialization of population, the individuals with poor fitness are redistributed by the Gaussian probability model. In view of the stagnation of iteration, Lévy flight strategy is introduced and the adaptive change of disturbance step length is controlled. Experimental results on 4 benchmark functions show that the novel ELALO can effectively improve the solution accuracy and convergence speed, compared with the original ALO. Secondly, in order to solve the disadvantage that extreme learning machine (ELM) network is easy to fall into local optimization, this ELALO algorithm is used to initialize the weights and thresholds of its network and to form the new pattern recognition model, ELALO-ELM. Finally, the bearing data of 8 patterns from Western Reserve University are decomposed by local mean decomposition (LMD), and then the symbolic entropy (SE) of the first three product function (PF) components signals is extracted and used as the input eigenvectors. Compared with the standard ELM and ALO-ELM models, the ELALO-ELM model has better generalization and stronger robustness and it can effectively improve the efficiency of network training and the accuracy of early fault pattern classification in bearing fault diagnosis. The new ELALO-ELM model can also be used for other difficult classification problems.

In order to design an active deformation mirror for projection objective aberration imaging quality control, a topology optimization design method of active deformation mirrors based on discrete orthogonal Zernike polynomials is proposed in this paper. Firstly, in order to solve the problem that continuous Zernike polynomials do not have orthogonality on the discrete coordinates inside the unit circle, which causes the instability of topology optimization results, discrete orthogonal Zernike polynomials are used to characterize the active deformation mirror wave aberrations. Then, the optical and structural deformations are combined to establish an optical-mechanical coupling topology optimization model with the help of the variable density method to derive the sensitivity of the mathematical model. Finally, a wave aberration corrected deformation mirror in an optical machine system is used as an arithmetic example for topology optimization, and the results show that the absolute value of the Zernike coefficient Z4 after optimization is improved by nearly one order of magnitude compared with the value before optimization, and the vibration characteristics of the optimized structure meet the design requirements. The optimization effect is significant, which improves the optical performance of the deformed mirror and provides a new scheme for the design of the deformed mirror structure which has a certain practical value for engineering.

Hard turning has become an attractive alternative to the more time-consuming and costly grinding technique. Unfortunately, high-quality prediction of the surface roughness generated during hard turning is difficult due to the technical complexities involved. Hence, it is currently receiving much research attention. The objective of this paper is to survey the current state of the soft computing techniques for surface roughness prediction in hard turning. It focuses on three areas: data acquisition, feature selection, and prediction model of surface roughness. First, the characteristics of hard turning and surface roughness are introduced, and a framework of the soft computing techniques is presented. Then, the three key areas are surveyed thoroughly. Finally, the recommendations and challenges faced by industry and academia are discussed, and the conclusions are drawn.

In order to solve the problem of predicting the residual life of mechanical products accurately based on small-sample data, this paper proposes a small-sample adaptive residual life prediction model of mechanical products based on feature matching preprocessor-LSTM. First, aiming at the problem of low accuracy of remaining life prediction for small samples of mechanical products caused by multiple time scales and multiple fault states, the failure time data and performance degradation data are fused, and the failure rate and standard deviation are used as the remaining life prediction criteria to intuitively reflect The possibility of failure of a component or system at a certain point in time. Considering the demand of adaptive small-sample residual life prediction data, this paper establishes the adaptive matching pre-processor model of life characteristics. On this basis, the LSTM neural network is used to establish a small-sample adaptive residual life prediction model. Then, the XJTU-SY bearing life data set and the test data of the small-sample life characteristics measured by the RV reducer are used as the research objects, and a small amount of the data set is randomly selected. The remaining life expectancy is predicted from the sample data and compared with its standard remaining life, respectively. The comparison results show that the overall prediction error is small. This study shows that the remaining life prediction model established can better predict the remaining life of mechanical product sub-sample data and provides a feasible method for predicting the remaining life of mechanical product sub-samples.

Aiming at the problem that the traditional reliability models of mechanical products are used to predict the reliability of hydraulic automatic transmission and the expected result is relatively large, firstly, the empirical distribution model line is used to statistically analyze the failure distribution law of the hydraulic automatic transmission; then, the Fourier transform is used to perform frequency domain analysis on experience distribution; on this basis, comprehensively consider the characteristics of experience distribution and frequency domain characteristics of experience distribution, constructs the reliability model of exponential decay oscillation distribution and the corresponding reliability, failure efficiency and average life calculation model; meanwhile, studies the influence of attenuation coefficient, oscillation amplitude, oscillation angle frequency, and other parameters on the probability distribution characteristics. On this basis, the established probability distribution models are adopted to fit the failure time data of hydraulic automatic gearbox carried by a forklift, and the fitting results are compared with exponential distribution models, three-parameter Weibull models, and “bathtub curve” models. The comparing results show that the established exponential decayed oscillation distribution model can better describe the probability distribution characteristics of the fault-free working time of automatic transmission, and the use of this model can obtain a smaller root mean square error. Simultaneously, the research conclusions of this paper can provide meaningful guidance and reference for the analysis of the life distribution model of mechanical products with exponentially attenuated oscillation probability density change law.

Many condition monitoring systems based on artificial intelligence process models for machining process monitoring have been developed intensively. However, given that machining processes are very complex (i.e., nonlinear and nonstationary), there is still no clear methodology to acquire machining monitoring systems allowing machining processes to be optimized, predicted, or controlled. In this paper, the coupled hidden Markov model, based on dynamic Bayesian networks, is proposed to monitor a machining process by using multi-directional data fusion and to analyze the effect of the sensor layout on the monitoring accuracy. The features extracted by a singular spectrum and wavelet analysis constitute the input information to the system. The technique is tested and validated successfully by using two scenarios: tool wear condition monitoring (initial wear, gradual wear, or accelerated wear) for the milling process and surface roughness accuracy grade prediction (accuracy grade 9, accuracy grade 8, or accuracy grade 7) for the turning process. In the first case, the maximum recognition rate obtained by the single-sensor placement for tool wear is 83%, whereas in the case of the three-sensor placement, the model recognition rate is 89%. In the second application for turning, the maximum recognition rate obtained by the single-sensor and the double-sensor placements for surface roughness accuracy prediction is 77% and 85%, respectively. In the case of the three-sensor placement, the model recognition rate is 89%. The proposed approach can also be integrated into the diagnosis architecture for condition monitoring in other complex machining systems.

Sensor deployment to robustly monitor operation parameters is the cornerstone for timely diagnosing variations that lead to product quality defects. A sensor system with optimal placement can help manufacturers improve product quality and reduce process downtime. However, current literature lacks investigation in methodologies that consider the mechanism of variation propagation, heterogeneity among sensor and variation properties, and multi-objective optimization involved in the sensor layout for variation diagnosis in an assembly process. In our approach, sensing information from fixture error and part machining error is integrated into a stepindexed state space model based on an understanding of variation propagation mechanism for the stream of assembly set variation described in a single-station multi-step assembly process. The effectiveness of such sensor system is quantified by some indexes, which are used to quantitatively characterize the diagnosability. Based on digraph theory, a quantitative fuzzy binary graph-based approach is developed to model the cause-effect relationship between part variations and sensor measurements considering the heterogeneous properties of sensor and variation, thus an improved shuffled frog-leaping algorithm is proposed to determine the sensor types, numbers, and locations to achieve full diagnosability. An example for the differential assembly illustrates the methodology. [ABSTRACT FROM AUTHOR]