PNN Neural Network Research Articles

An online detection method for the mechanical fault of circuit breakers of rural distribution lines based on continuous wavelet transform and vibration signal characteristics

Rural distribution lines are widely distributed and dispersed, involving numerous circuit breaker equipment. Detecting mechanical faults on each circuit breaker requires significant time and human resources. It can bring significant interference and power outage risks to the operation of the line. Therefore, an online detection method is studied for mechanical faults in rural distribution line circuit breakers. Continuous wavelet transform technology is used to extract the characteristics of circuit breaker vibration signals. This feature is used to locate the faulty section. The PNN neural network is introduced to identify fault feature samples and achieve online detection of mechanical faults. To test the application performance of this method, a comparative experiment is designed. The results verified that when using this method to extract the vibration signal of circuit breaker mechanical faults, the error is low, and the fault detection accuracy is high.

Mostar Index of Neural Networks and Applications

Neural networks are mathematical models that use learning algorithms inspired by the brain to store information. These networks have been extensively used to operate cognitive functions, robustness, fault tolerance, flexibility, collective computation, and ability to deal with fuzzy and inconsistent information. In recent years, probabilistic neural network PNN and convolutional neural network CNN have been employed in optimization problems such as input normalization and decision making tasks. The flow of data in PNN and CNN will be optimized if its peripherality is minimized. Topological index (TI) is a graph invariant initially introduced to study physiochemical properties of chemical networks. They are further applicable to study certain mathematical aspects of a network such as irregularity, centrality and peripherality. Recently, the Mostar index and edge Mostar index have been introduced to study peripherality of various networks. In the current work, Mostar indices for PNN and CNN have been computed and their application in context of data flow problem together with graphical analysis is presented.

Research on modulation recognition of Communication Radar Based on spread spectrum technology

Aiming at the problem that the traditional radar signal recognition method needs to be completed under the noiseless condition, which leads to the low recognition accuracy of low SNR signal, the modulation recognition method of communication radar signal based on spread spectrum technology is studied. The phase difference and instantaneous frequency characteristics of communication radar signal are extracted after the spread spectrum processing of communication radar signal with direct sequence spread spectrum. The training sample is used to train PNN neural network, and the modulation recognition of communication radar signal is completed. Simulation experiments under different parameters show that the recognition method based on spread spectrum technology has an effective recognition rate higher than 90% for low SNR signal, which is superior to the traditional method and can be applied in practice.

PNN and BP Neural Network Fault Diagnosis Research on Electronic Accelerator Pedal Detection

Background: The working state of electronic accelerator pedal directly affects the safety of vehicles and drivers. Effective fault detection and judgment for the working state of the accelerator pedal can prevent accidents. Methods: Aiming at different working conditions of electronic accelerator pedal, this paper used PNN and BP diagnosis model to detect the state of electronic accelerator pedal according to the principle and characteristics of PNN and BP neural network. The fault diagnosis test experiment of electronic accelerator pedal was carried out to get the data acquisition. Results: After the patents for electronic accelerator pedals are queried and used, the first measured voltage, the upper limit of first voltage, the first voltage lower limit, the second measured voltage, the upper limit of second voltage and the second voltage lower limit are tested to build up the data samples. Then the PNN and BP fault diagnosis models of electronic accelerator pedal are established. Six fault samples are defined through the design of electronic accelerator pedal fault classifier and the fault diagnosis processes are executed to test. Conclusion: The fault diagnosis results were analyzed and the comparisons between the PNN and the BP research results show that BP neural network is an effective method for fault detection of electronic throttle pedal, which is obviously superior to PNN neural network based on the experiment data.

Data mining and application of ship impact spectrum acceleration based on PNN neural network

The selection of the smoothing coefficient of the probabilistic neural network directly affects the performance of the network. Traditionally, all the mode layer neurons use a uniform smoothing coefficient, and then the optimal smoothing parameters suitable for this problem are searched by the optimization algorithm. In this study, the smoothing coefficients of the mode layer neurons connected by the same summation layer are set to the same value, which not only reflects the relationship between the training samples of the same pattern, but also highlights the difference between the training samples of different modes. Two probabilistic neural network models are applied to the ship impact environment prediction respectively. The results show that the classification effect of multiple smoothing factors is further improved than the single smoothing factor network.

Transformer Fault Diagnosis Based on BP‐Adaboost and PNN Series Connection

Dissolved gas‐in‐oil analysis (DGA) is a powerful method to diagnose and detect transformer faults. It is of profound significance for the accurate and rapid determination of the fault of the transformer and the stability of the power. In different transformer faults, the concentration of dissolved gases in oil is also inconsistent. Commonly used gases include hydrogen (H2), methane (CH4), acetylene (C2H2), ethane (C2H6), and ethylene (C2H4). This paper first combines BP neural network with improved Adaboost algorithm, then combines PNN neural network to form a series diagnosis model for transformer fault, and finally combines dissolved gas‐in‐oil analysis to diagnose transformer fault. The experimental results show that the accuracy of the series diagnosis model proposed in this paper is greatly improved compared with BP neural network, GA‐BP neural network, PNN neural network, and BP‐Adaboost.

Improvement of control method over the environment of cognitive radio system using a neural network

In the course of present research, we examined a method to control the environment of a cognitive radio using a PNN neural network as a decision-making system. As a result of research into the WRAN environment control architecture using a neural network, a flow chart of the environment control algorithm has been developed. Its special feature is that a neural network is located at each base station and interacts with other WRANs according to the IEEE 802.22 standard. The cognitive radio environment control architecture has been improved using a PNN network. This is achieved by applying a special case of radial basis networks ‒ a probabilistic neural network and a hybrid learning system, as well as a hybrid form of error correction and accumulating the experience of past iterations. To simulate a PNN neural network, the MATLAB software package was selected using standard functions of Neural and Simulink sections. To determine the two measurable vectors of the input set, four domains of input vectors with a normal distribution law with arbitrary values have been created. As a result of the network simulation, a connectivity matrix corresponding to the input vector has been generated. A PNN neural network simulation showed statistically confirmed results. The network has one competing layer and a layer for receiving and splitting the attributes of the input vector. This ensures the use of a small number of network neurons and, accordingly, the fast learning ability of the network – 1200 ms, which is 1.67 times faster than the required value, which is achieved by employing parallel processing of information. Moreover, the improved method provides the ability to work in the presence of a large number of uninformative, noise input signals, as well as the adaptation to environmental changes

Study on the Fault Diagnosis of Gear Pump Based on PNN Neural Network

The principle of neural network’s PNN algorithm was introduced, Combining with the structure feature and work principle of the hydraulic pump, a fault diagnosis system based on PNN neural network was established. The feasibility of the system was proved through the identification, emulation and experimentation of hydraulic system’s fault patterns. The PNN control model was simulated using Matlab/Simulink toolbox. This model analyzed and studied the PNN network predictive diagnostic rate. Under different sample size and SPREAD, the simulation’s results show that this method has favorable identified capability of fault mode and favorable applicability to the hydraulic pump.

Study on the PNN Neural Network Inversion Based on the Integration of Seismic Multi-Attribute with Frequency Division RGB - Fuyu Oil Layer in Gaotaizi Area, Songliao Basin is Taken for an Example

Fuyu oil layer in Changyuan of Daqing is a strategic area for Daqing oil field to increase and stabilize production at present, but its reservoir is structured mostly by riverway sand bodies. The sand bodies are thin and change with complexity, so they are difficult to identify. Through PNN probability neural network, and combined with the seismic multi-attribute and earthquake frequency division data, wave impedance inversions are implemented, and the maximum correlation coefficient is 0.517 if a single attribute is described and it is raised to 0.773 by linear weighting, and also 9 independent attributes are used for PNN network training so that a more complex nonlinear relationship is obtained. Then, the correlation coefficient continues to increase until 0.869, so that the spatial distribution characteristics of the sandstones in the study area are accurately described. This indicates that the PNN neural network inversion based on the integration of seismic multi-attribute with frequency division RGB can play an obvious effect in the areas of thin and changing sand bodies, and can meet the needs of the oil field exploration and development.

Research on Evaluation of Leather Handle Property Based on PNN Neural Network

Evaluation of leather handle property is always a focus question all over the world. HEM method is widely used to evaluate leather handle property nowadays. In this easy, PNN neural network was used as a new method to evaluate leather handle property. At first, basic theory about PNN neural network was briefly introduced. Second, PNN neural network mathematical model for leather handle property evaluation was set up after the mechanical characteristics parameters were selected. Process of PNN neural network designing and Matlab program were given. Third, the ability of PNN neural network to classify leather rank was proofed through program training and sample testing. The result is precise and it indicates that PNN neural network mathematical model has important practical and theory value.

The application of elastic impedance inversion in reservoir prediction at the Jinan area of Tarim Oilfield

The Triassic reservoir in the Jinan area of Tarim Oilfield consists largely of interbedded sand and shale. Because of the large overlap between sandstone and shale impedance, it is difficult to distinguish sandstone from shale by acoustic impedance alone. Compared to acoustic impedance, elastic impedance contains more lithologic and physical information of the reservoir. Based on meticulous well-tie calibration, elastic impedance data volumes for 10°, 20°, and 30° emergence angles are obtained using pre-stack elastic impedance inversion. A non-linear statistical relationship between elastic impedance and shale content is set up by a PNN neural network. The non-linear mapping relationship is used to predict the reservoir shale content from elastic impedance, which will depict and predict the reservoir oil-bearing sands.

Probalistic Neural Network Application to Warship Radio Station Identification

The article presents use of PNN to identify ship's radio stations. Two methods of PNN acceleration are included. The first one is a combination of PNN and Kohonen neural network. The task of Kohonen neural network is to roughly classify radio station. The final identification is performed by PNN. The second speeding up approach consists in using average data instead of original one. Moreover, a modification of PNN decision rule is applied.