Gear Fault Diagnosis with Neural Network Based on Niche Genetic Algorithm

Learning Classifier Systems (LCS) evolve IF-THEN rules for classification and control tasks. The earliest Michigan-style LCS used a panmictic Genetic Algorithm (GA) (in which all rules compete for selection) but newer ones tend to use a niche GA (in which only a certain subset of rules compete for selection at any one time). The niche GA was thought to be advantageous in all learning tasks, but recent research suggests it has difficulties when the rules composing the solution overlap. Furthermore, the niche GA's effects are implicit, making it difficult study, and fixed, which prevents tuning its performance. Given these issues, we set out on a long-term project to reevaluate the niche GA. This work is our starting point and in it we address the implicit and unquantified effects of the niche GA by building a mathematical model of the probability of rule selection. This model reveals a number of insights into the components of rule fitness, particularly the bonus for rule generality and penalty for overlaps, both previously unquantified. These theoretical results are our primary contribution. However, to demonstrate one way to apply this theory, we then introduce a new variant of the UCS algorithm, which uses a hybrid panmictic/niche GA. Preliminary results suggest, unexpectedly, that the niche GA may have even more drawbacks than previously thought.

Electric power sector is broadly categorised into four sections as electric power generation, transmission, distribution and utilisation. Generated power has to be transmitted from generating station to load centre through transmission system with higher efficiency. It is necessary to know various types of faults and their impact on power system reliability. Power system faults are broadly classified into open circuit and short circuit faults. In this paper, effect of short circuit faults on a three phase transmission system has been analysed. Entire work has been done using MATLAB simulink environment. The complete modelling and proposed simulation work have been done, and the analysis of transient faults was carried out with the MATLAB simulink software. In this work, MATLAB software is used for creating various types of faults for shorter duration on transmission lines such as L-G fault, LL-G fault, LL fault and three phase short circuit and it also analysed the effect of faults on voltage and current through different phases.

Gear fault diagnosis based on CS-improved variational mode decomposition and probabilistic neural network

In our globally connected world, threats from various aspects are going at an alarming rate. These are controlling with different security systems such as metal detector, closed circuit cameras, and scanning systems. All these aids are meant to recognize and identify the explosives and others weapons. Here, it is more important to identify the particular person or persons, who were planning to distract the society or particular event. This paper is aimed to design that to control the threats by identifying the suspected people by a simple face recognition technique using simple PC or laptop with the help of scientific software MATLAB and its neural network tool box. In general, all major events are fully securitized with well-developed protection systems but only problem with non-major and small events, where security systems are matter of financial issues. So, militants and other destroyers are taking advantage of these situations and creating a panic and terror situations. This paper is also designed like that a PC or laptop with camera can be a face recognition system to identify the suspected peoples and most wanted criminal. By recognizing the people, we can mostly avoid the threats from these people and dangerous situations. Neural network is a science that has been extensively applied to numerous pattern recognition problems such as character recognition, object recognition, and face recognition, where this paper has programmed for face recognition with the back-propagation algorithm and simulated with the software MATLAB and its neural network tool box. Here, the back propagation plays the central operation role to get the key features were extracted from the picture for training the network. Since the major role of the project is mainly focusing on the training of the neural network, already extracted key features of the person’s image from the database were taken for training the back-propagation network. Here, we have taken 7 input units, 6 hidden units, and 4 output units contained back-propagation network. The output unit, 4 output units, generates the 4-bit output which gives the person identity.

This paper proposes a new scheme for locating the faults of three‐terminal double‐circuit transmission line without transposer in the phase domain that is not affected by type of fault. Synchronous voltage and current were measured by phasor measurement units (PMUs) installed at three busbars. Considering the coupling effect of parallel lines, the distribution line model was used to obtain more accurate results and third‐order Taylor series expansion to decouple distributed line model. The phase and branch of all faults on the transmission lines were effectively identified, and various types of faults were accurately located including normal shunt fault, evolving fault and cross‐country fault. The proposed algorithm was tested under different fault locations, resistances, initial angles and types (including cross‐country faults and evolving faults). In addition, the effects of different sampling rates, measurement errors, earth resistivities and transmission line parameter errors were also considered. The simulation calculation was performed in MATLAB software and three‐terminal transmission lines were simulated in PSCAD/EMTP software. The results indicate that maximum estimated error was less than 1.8631%.

The Sixth International Symposium on Neural Networks (ISNN 2009)

Deep learning techniques for transmission line fault classification – A comparative study

The significant advantages of permanent magnet synchronous motors, such as very good dynamic properties, high efficiency and power density, have led to their frequent use in many drive systems today. However, like other types of electric motors, they are exposed to various types of faults, including stator winding faults. Stator winding faults are mainly inter-turn short circuits and are among the most common faults in electric motors. In this paper, the possibility of using the spectral analysis of symmetrical current components to extract fault symptoms and the machine-learning-based K-Nearest Neighbors (KNN) algorithm for the detection and classification of the PMSM stator winding fault is presented. The impact of the key parameters of this classifier on the effectiveness of stator winding fault detection and classification is presented and discussed in detail, which has not been researched in the literature so far. The proposed solution was verified experimentally using a 2.5 kW PMSM, the construction of which was specially prepared for carrying out controlled inter-turn short circuits.

High voltage circuit breaker is an important equipment to protect the normal operation of power system. In this paper, based on the mechanical fault characteristics of the circuit breaker, a mechanical fault diagnosis expert system of high voltage circuit breaker has been developed using the fuzzy matrix algorithm and neural network technology. Expert database of the system is constructed on real-time online monitoring data and fault database, while extracting the feature signal of condition monitoring from online monitoring data and combining fault database, the system can diagnosis, analysis, and draw a conclusion through fuzzy matrix algorithm, with the RBF neural network as an auxiliary decision-making means. When the diagnosis conclusions of the two methods are identical, maintenance method would be suggested according to the concluded location of the fault. When there is a difference between the two conclusions, conclusion will be drew by further calculation and analysis with linear fitting rules. Through the experimental verification by various types of faults, the fault recognition accuracy of the system is effectively improved. The system could be applied to delivery test and field fault warning as well as maintenance work, providing support for circuit breakers from a regular maintenance to condition-based maintenance, which can be helpful to improve the reliability and economy of circuit breaker.

Engines are prone to various types of faults, and it is crucial to detect and indeed classify them accurately. However, manual fault type detection is time‐consuming and error‐prone. Automated fault type detection promises to reduce inter‐ and intra‐observer variability while ensuring time invariant attention during the observation duration. We have proposed an automated fault‐type detection model based on sound signals to realize these advantageous properties. We have named the detection model prism pattern network (PrismPatNet) to reflect the fact that our design incorporates a novel feature extraction algorithm that was inspired by a 3D prism shape. Our prism pattern model achieves high accuracy with low‐computational complexity. It consists of three main phases: (i) prism pattern inspired multilevel feature generation and maximum pooling operator, (ii) feature ranking and feature selection using neighbourhood component analysis (NCA), and (iii) support vector machine (SVM) based classification. The maximum pooling operator decomposes the sound signal into six levels. The proposed prism pattern algorithm extracts parameter values from both the signal itself and its decompositions. The generated parameter values are merged and fed to the NCA algorithm, which extracts 512 features from that input. The resulting feature vectors are passed on to the SVM classifier, which labels the input as belonging to 1 of 27 classes. We have validated our model with a newly collected dataset containing the sound of (1) a normal engine and (2) 26 different types of engine faults. Our model reached an accuracy of 99.19% and 98.75% using 80:20 hold‐out validation and 10‐fold cross‐validation, respectively. Compared with previous studies, our model achieved the highest overall classification accuracy even though our model was tasked with identifying significantly more fault classes. This performance indicates that our PrismPatNet model is ready to be installed in real‐world applications.

We propose a new framework of computing-inspired multifocal cancer detection procedure (MCDP). Under the rubric of MCDP, the tumor foci to be detected are regarded as solutions of the objective function, the tissue region around the cancer areas represents the parameter space, and the nanorobots loaded with contrast medium molecules for cancer detection correspond to the optimization agents. The process that the nanorobots detect tumors by swimming in the high-risk tissue region can be regarded as the process that the agents search for the solutions of an objective function in the parameter space with some constraints. For multimodal optimization (MMO) aiming to locate multiple optimal solutions in a single simulation run, the niche technology has been widely used. Specifically, the niche genetic algorithm (NGA) has been shown to be particularly effective in solving MMO. It can be used to identify the global optima of multiple hump functions in a running, effectively keep the diversity of the population, and prematurely avoid the genetic algorithm. Learning from the optimization procedure of NGA, we propose the NGA-inspired MCDP in order to locate the tumor targets efficiently while taking into account realistic in vivo propagation and controlling of nanorobots, which is different from the use scenario of the standard NGA. To improve the performance of the MCDP, we also modify the crossover operator of the original NGA from crossing within a population to crossing between two populations. Finally, we present comprehensive numerical examples to demonstrate the effectiveness of the NGA-inspired MCDP when the biological objective function is associated with the blood flow velocity profile caused by tumor-induced angiogenesis.

In this paper, common faults in main components of industrial three-shaft gas turbine are simulated through the nonlinear steady-state model, and the effects of these faults on the performance of all five main components and main measurement parameters are analyzed in both part and full load. Meanwhile, the sensitivity of these parameters to the location and type of fault and the fault severity in both part and full load is analyzed. In this study, in order to improve the accuracy of the non-linear steady-state model, the variable specific heat is considered with fitting formulas. In this model, the faults simulation is performed by changing the flow capacity and isentropic efficiency of each component via modification of the compressors and turbines characteristic curve. Meanwhile, a Genetic Algorithm (GA) based non-linear gas turbine steady-state performance simulation approach has been presented to best estimate the unknown component parameters. The fault simulation results in both part and full-load conditions indicate that by increasing the faults severity, the component performance parameters and the measurement parameters will deviate almost linearly from clean condition. Moreover, the sensitivity of these parameters varies with the location and type of the fault and also varies with the operating condition. Therefore, it can be used as the basis for selection of key parameters to identify the location and type of the fault. Furthermore, it also shows that considering the effects of load variations in design of a gas turbine diagnosis system is needed.

The decomposition number $K$ and penalty factor $\alpha $ in the variational mode decomposition (VMD) algorithm have a great influence on the decomposition effect and the accuracy of subsequent fault diagnosis. Therefore, a gear fault diagnosis method based on genetic mutation particle swarm optimization VMD and probabilistic neural network (GMPSO-VMD-PNN) algorithm is proposed in this paper. Firstly, the GMPSO algorithm is used to optimize the $[K,\alpha]$ parameter combination in the VMD algorithm, and the optimal $[K,\alpha]$ parameter combination of each gear fault vibration signal to be decomposed is selected. Then, the gear fault vibration signal is decomposed into several intrinsic mode functions (IMFs) by VMD, and the sample entropy value of each IMFs is extracted to form the feature vector of subsequent fault diagnosis. Finally, the characteristic vector of gear fault vibration signal is input into PNN model, and gear fault is accurately classified. By comparing with fixed parameter VMD algorithm, empirical mode decomposition (EMD) and complete ensemble empirical mode decomposition adaptive noise (CEEMDAN) algorithm, the superiority of this method in gear fault diagnosis is verified. Therefore, the GMPSO-VMD-PNN algorithm proposed in this paper has certain application value for gear fault diagnosis.

We propose a new batch bioprocess monitoring approach which combines the Gaussian mixture model (GMM) with the multiway analysis in localized discriminant embedding subspace for detecting and classifying different types of faults. Due to the inherent process multimodality within abnormal points, the capability of traditional multimay locality preserving projection (MLPP) is degraded. For the routine bioprocess operation with abnormal events, GMM is used to partition the training set with various types of faults into different clusters. Three localized distance matrices reflecting the relationships of nearby points are then computed. The extracted leading discriminant embedding directions can not only separate the normal and faulty data by maximizing the distance among nearby data points from different clusters, but also preserve the intrinsic geometrical structure within the multiple faulty clusters by minimizing the small distance and penalizing the large distance among neighboring data from the same cluster. The newly developed multiway localized discriminant embedding (MLDE) approach is applied to two test scenarios in the fed-batch penicillin fermentation process and compared with the conventional MLPP method. The results demonstrate that the MLDE approach is superior to the MFDA method in detecting abnormal events and classifying different types of faults in fed-batch process with higher accuracy and sensitivity.

Because of its long running time, complex working environment, and for other reasons, a gear is prone to failure, and early failure is difficult to detect by direct observation; therefore, fault diagnosis of gears is very necessary. Neural network algorithms have been widely used to realize gear fault diagnosis, but the structure of the neural network model is complicated, the training time is long and the model is not easy to converge. To solve the above problems and combine the advantages of the ResNeXt50 model in the extraction of image features, this paper proposes a gearbox fault detection method that integrates the convolutional block attention module (CBAM). Firstly, the CBAM is embedded in the ResNeXt50 network to enhance the extraction of image channels and spatial features. Secondly, the different time–frequency analysis method was compared and analyzed, and the method with the better effect was selected to convert the one-dimensional vibration signal in the open data set of the gearbox into a two-dimensional image, eliminating the influence of the redundant background noise, and took it as the input of the model for training. Finally, the accuracy and the average training time of the model were obtained by entering the test set into the model, and the results were compared with four other classical convolutional neural network models. The results show that the proposed method performs well both in fault identification accuracy and average training time under two working conditions, and it also provides some references for existing gear failure diagnosis research.