Long Wen

A New Convolutional Neural Network-Based Data-Driven Fault Diagnosis Method

Fault diagnosis is vital in manufacturing system, since early detections on the emerging problem can save invaluable time and cost. With the development of smart manufacturing, the data-driven fault diagnosis becomes a hot topic. However, the traditional data-driven fault diagnosis methods rely on the features extracted by experts. The feature extraction process is an exhausted work and greatly impacts the final result. Deep learning (DL) provides an effective way to extract the features of raw data automatically. Convolutional neural network (CNN) is an effective DL method. In this study, a new CNN based on LeNet-5 is proposed for fault diagnosis. Through a conversion method converting signals into two-dimensional (2-D) images, the proposed method can extract the features of the converted 2-D images and eliminate the effect of handcrafted features. The proposed method which is tested on three famous datasets, including motor bearing dataset, self-priming centrifugal pump dataset, and axial piston hydraulic pump dataset, has achieved prediction accuracy of 99.79%, 99.481%, and 100%, respectively. The results have been compared with other DL and traditional methods, including adaptive deep CNN, sparse filter, deep belief network, and support vector machine. The comparisons show that the proposed CNN-based data-driven fault diagnosis method has achieved significant improvements.

A PSO-Fuzzy group decision-making support system in vehicle performance evaluation

Group decision-making (GD) is a fuzzy problem with high complexity and difficult to be handled. Usually the rule-based Group decision-making Support System (GDSS) is used to solve GD problem. But the definition of fuzzy rules and membership functions in GDSS are generally affected by subjective decision. So the rationality of GDSS is difficult to be judged. In this paper, the Particle Swarm Optimization (PSO) algorithm is introduced to improve the fuzzy rule base through optimize the position and shape of fuzzy rule set and weights of rules. A PSO-FUZZY GDSS is set up and used to a real application of vehicle performance evaluation. According to the contrast of three methods: Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), non-weighted fuzzy rule base, and PSO-FUZZY GDSS, the result shows that weighted fuzzy rule base after PSO optimized is better than non-weighted fuzzy rule base, and the evaluation values of PSO-FUZZY GDSS are very close to the TOPSIS. Therefore, the PSO-FUZZY GDSS is an efficient method for vehicle performance evaluation and can be applied to more domains.

A New Deep Transfer Learning Based on Sparse Auto-Encoder for Fault Diagnosis

Fault diagnosis plays an important role in modern industry. With the development of smart manufacturing, the data-driven fault diagnosis becomes hot. However, traditional methods have two shortcomings: 1) their performances depend on the good design of handcrafted features of data, but it is difficult to predesign these features and 2) they work well under a general assumption: the training data and testing data should be drawn from the same distribution, but this assumption fails in many engineering applications. Since deep learning (DL) can extract the hierarchical representation features of raw data, and transfer learning provides a good way to perform a learning task on the different but related distribution datasets, deep transfer learning (DTL) has been developed for fault diagnosis. In this paper, a new DTL method is proposed. It uses a three-layer sparse auto-encoder to extract the features of raw data, and applies the maximum mean discrepancy term to minimizing the discrepancy penalty between the features from training data and testing data. The proposed DTL is tested on the famous motor bearing dataset from the Case Western Reserve University. The results show a good improvement, and DTL achieves higher prediction accuracies on most experiments than DL. The prediction accuracy of DTL, which is as high as 99.82%, is better than the results of other algorithms, including deep belief network, sparse filter, artificial neural network, support vector machine and some other traditional methods. What is more, two additional analytical experiments are conducted. The results show that a good unlabeled third dataset may be helpful to DTL, and a good linear relationship between the final prediction accuracies and their standard deviations have been observed.

Free Pattern Search for global optimization

An efficient algorithm named Pattern search (PS) has been used widely in various scientific and engineering fields. However, even though the global convergence of PS has been proved, it does not perform well on more complex and higher dimension problems nowadays. In order to improve the efficiency of PS and obtain a more powerful algorithm for global optimization, a new algorithm named Free Pattern Search (FPS) based on PS and Free Search (FS) is proposed in this paper. FPS inherits the global search from FS and the local search from PS. Two operators have been designed for accelerating the convergence speed and keeping the diversity of population. The acceleration operator inspired by FS uses a self-regular management to classify the population into two groups and accelerates all individuals in the first group, while the throw operator is designed to avoid the reduplicative search of population and keep the diversity. In order to verify the performance of FPS, two famous benchmark instances are conducted for the comparisons between FPS with Particle Swarm Optimization (PSO) variants and Differential Evolution (DE) variants. The results show that FPS obtains better solutions and achieves the higher convergence speed than other algorithms.

Modeling of the Feed-Motor Transient Current in End Milling by Using Varying-Coefficient Model

In order to ensure the stability of the machining process, it is vital to control the machining condition during the milling process. While the feed-motor current is related to many physical variables, such as the cutting force and tool wear, we can indicate it as the key variables to monitoring the conditions of the milling process. A predictive model of the feed-motor current amplitude is established in this paper. The change regulation of the transient current amplitude during the milling process is investigated, and the effect of the spindle speed on the transient current amplitude is studied as well. Since the transient current amplitude is time-varying, the predictive model is a typical panel data type. In this case, the varying-coefficient model (VCM), a potential soft computing method, is applied to solve this predictive model. Then several experiments are conducted to evaluate the performance of VCM method. Results show that the predicted values match the experimental value well, and the correctness of the predictive model for transient current amplitude is also validated.

Modeling of cutting forces in a face-milling operation with Gene Expression Programming

Cutting forces is one of the most fundamental elements that affect the performance of cutting operation. Finding the rules that how process and environment factors affect the values of cutting forces will help to set the process parameters of the future cutting operation and further improve production quality and efficiency. Since cutting forces is impacted by different machining parameters and the inherent uncertainties in the machining process, how to predict the cutting forces becomes a challengeable problem for the researchers and engineers. 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, so it should be suitable to solve the above problem. In this paper, a method based on GEP has been proposed to construct the prediction model of cutting forces in a face-milling operation. At the basis of defining a GEP environment for the problem and improving the method of constant creation, an explicit prediction model of cutting forces has been constructed. To verify the feasibility and performance of the proposed approach, experimental studies have been conducted to compare this approach with some previous works. The obtained results show that the constructed prediction model fits very well with the experimental data, and can be used to estimate the cutting forces and optimize the cutting parameters. The proposed method will lead to the reduction in production costs and production time, and improvement of product quality.

Scheduling flexible job shop in dynamic environment based on a memetic algorithm

Scheduling for the flexible job shop scheduling problem is very important in the fields of production management and combinatorial optimization. However, in most real manufacturing environment, schedules are usually inevitable with the presence of a variety of unexpected disruptions. This paper proposes an efficient memetic algorithm to solve the flexible job shop scheduling problem with random job arrivals. Firstly, a periodic policy is presented to up date the problem condition and generate the rescheduling point. Secondly, the efficient memetic algorithm with a new local search procedure is proposed to optimize the problem in each rescheduling point. The new local search uses five kinds of neighborhood structures. Otherwise, the performance measures investigated respectively are: minimization of the makespan and minimization of the mean tardiness. Moreover, several experiments have been designed to test and evaluated the performance of the memetic algorithm. The experimental results show that the proposed algorithm is efficient with respect to bi-objectives and different due date tightness.

Modeling the performance of electrochemical machining process using free pattern search

Electrochemical machining is increasing in importance. It provides an economical and effective way to machine extremely difficult to cut metals and always have a higher machining rate, better surface roughness and control. In this paper, a new predictive approach called Free Pattern Search (FPS) is used to explicitly modeling the performance of electrochemical machining. FPS is based on the expression tree of gene expression programming (GEP) to encode the individuals and express them to a non-determinative tree using a fixed length individual. FPS is inspired by Pattern Search (PS) and Free Search (FS), and it hybrids a scatter manipulator to keep the diversity of the population. Three machining parameters, the feed rate, voltage and flow rate of electrolyte are used as the independent input variables when prediction the material remove rate, surface roughness and over cut. Experiments are conducted to verify the performance of FPS and FPS obtains good results in prediction. The predictive model found by FPS agrees with the experimental results well. The relationships between variables and performance are also showed clearly in the predictive model, and the results shows that they are fit to the experiments well.

Application of Free Pattern Search on the surface roughness prediction in end milling

Surface roughness has a great influence on the product properties. Predicting the surface roughness is an important work for modern manufacturing industry. In this paper, a novel prediction method called Free Pattern Search (FPS) is proposed to explicitly construct the surface roughness prediction model. FPS takes the advantage of the expression tree in gene expression programming (GEP) to encode the solution and to expresses a non-determinative tree using a fixed length individual. FPS is inspired by Pattern Search (PS) and hybrid a scatter manipulator to keep the diversity of the population. Three machining parameters, the spindle speed, feed rate and the depth of cut are used as the independent input variables when prediction the surface roughness in end milling. Experiments are conducted to verify the performance of FPS and FPS obtains good results compared with other algorithm. The predictive model found by FPS agrees with the experimental result. The variable relations are also showed in the predictive model, and the results shows that they are fit to the experiments well.