Wuhan University

Chaolong Zhang

Yigang He

Liulu He

Guolong Shi

Hui Zhang

Yongbo Sui

Bolun Du

Jiajun Duan

Hui Shao

Baiqiang Yin

Xiaoxin Wu

Weibo Yuan

Yuan Huang

Zhong Li

Wenjie Wu

Yuan Chen

Wei Wu

Jin Tong

Jinguang Jiang

A transformer failure diagnosis method and system based on an integrated deep belief network are provided. The disclosure relates to the fields of electronic circuit engineering and computer vision. The method includes the following: obtaining a plurality of vibration signals of transformers of various types exhibiting different failure types, retrieving a feature of each of the vibration signals, and establishing training data through the retrieved features; training a plurality of deep belief networks exhibiting different learning rates through the training data and obtaining a failure diagnosis correct rate of each of the deep belief networks; and keeping target deep belief networks corresponding to the failure diagnosis correct rates that satisfy requirements, building an integrated deep belief network through each of the target deep belief networks, and performing a failure diagnosis on the transformers through the integrated deep belief network.

Transformer failure diagnosis method and system based on integrated deep belief network

A method and a system for predicting a gas content in transformer oil based on a joint model are provided and belong a field of transformer failure prediction. The method includes the following: determining a type and a time series of gas to be predicted related to a failure, processing an original series by adopting empirical mode decomposition (EMD) and local mean decomposition (LMD) for a non-stationarity characteristic of a dissolved gas concentration series in oil; performing normalization on each sub-series component, dividing a training sample and a test sample; and establishing a deep belief network (DBN) prediction model for each of the sub-series components for training, performing superposition and reconstruction on the established DBN prediction model to perform characteristic extraction and classification on multi-dimensional data of the failure, evaluating prediction performance of the prediction model through calculating an error index.

Method and system for predicting gas content in transformer oil based on joint model

A method and a system of predicting an electric system load based on wavelet noise reduction and empirical mode decomposition-autoregressive integrated moving average (EMD-ARIMA) are provided. The method and the system belong to a field of electric system load prediction. The method includes the following steps. Raw load data of an electric system is obtained first. Next, noise reduction processing is performed on the load data through wavelet analysis. The noise-reduced load data is further processed through an EMD method to obtain different load components. Finally, ARIMA models corresponding to the different load components are built. Further, the ARIMA models are optimized through an Akaike information criterion (AIC) and a Bayesian information criterion (BIC). The load components obtained through predicting the different ARIMA models are reconstructed to obtain a final prediction result, and accuracy of load prediction is therefore effectively improved.

Method and system of predicting electric system load based on wavelet noise reduction and EMD-ARIMA

A method and a system for online monitoring of a health status of an insulated-gate bipolar transistor (IGBT) module are provided, which belong to the field of IGBT status monitoring. In order to overcome the inability to real-time monitor health statuses of existing IGBT modules, the method of the disclosure includes the following steps. A current sensor is used to measure a collector current of each IGBT module. A collected current value is substituted into a simulation model to obtain a current imbalance rate. A failure module is located according to the current imbalance rate and temperature to achieve the objective of monitoring an IGBT health status.

Method and system for online monitoring of health status of insulated-gate bipolar transistor module

A method and a system for identifying third-order model parameters of a lithium battery based on a likelihood function are provided, which relates to a method for estimating battery model parameters of a lithium battery under different temperatures, different system-on-chips (SOCs), and charge-discharge currents. The method includes the following steps. A third-order battery model of the lithium battery is established. A battery model output voltage Uand a total battery current I under different temperatures, different SOCs, and charge-discharge currents are collected. The likelihood function is adopted to construct an identification model, and the collected data is substituted into the identification model to calculate the battery model parameters. Identified parameters are substituted into the third-order battery model to obtain a battery terminal voltage to be compared with a measured terminal voltage. The operation method of the disclosure is simple and effective, and can accurately estimate internal resistance parameters of the lithium battery.

Method and system for identifying third-order model parameters of lithium battery based on likelihood function

A transformer state evaluation method combining a FAHP method, a DEMATEL method, and a CRITIC method is provided and includes: selecting a plurality of groups of state quantities, building a hierarchical indicator system; calculating an influencing degree and an influenced degree by using the DEMATEL method on a subjective level, calculating a weight of each of a plurality of indicators of an indicator layer through the FAHP method and the DEMATEL method, calculating the weights of the indicators of the indicator layer through the CRITIC method on an objective level; calculating an optimal weight according to the indicator subjective weights and the indicator objective weights; and calculating state scores layer by layer, finally determining an actual health condition of each of a plurality of transformers by combining state level classification rules. In the disclosure, the weights are calculated based on the subjective level and the objective level.

Transformer state evaluation method combining FAHP method, DEMATEL method and critic method

Provided are a time domain channel prediction method and a time domain channel prediction system for an OFDM wireless communication system, which relate to the technical field of adaptive transmission in wireless communication. Frequency domain channel information is converted into time domain tap information by inverse Fourier transform. With respect to each time domain tap information, tap information prediction based on an extreme learning machine is realized, and finally predicted tap information is converted into frequency domain channel information by Fourier transform. To improve a generalization ability of a channel predictor, an output weight of the extreme learning machine is punished by a combination of lregularization and lregularization. The disclosure may provide satisfactory prediction performance and may output a sparse output weight, which reduces the requirement for memory storage. The disclosure ensures adaptive transmission and adaptive coding of wireless communication.

Time domain channel prediction method and time domain channel prediction system for OFDM wireless communication system

A method and a system for selecting important delay taps of channel impulse response are provided, which belong to the field of adaptive transmission technology of wireless communication. The method performs local predictability estimation on all delay taps in the channel impulse response in wireless communication, thereby selecting the important delay taps in the channel impulse response. The disclosure uses recurrence rates of the delay taps to estimate local predictability of the delay taps. Noise delay taps are distinguished from the important delay taps through the local predictability of the delay taps, which improves the identification rate of the important delay taps of the channel impulse response in wireless communication. The disclosure may implement the selection of the important delay taps of the channel impulse response, which provides guarantee for implementing adaptive transmission and adaptive coding of wireless communication.

Method and system for selecting important delay taps of channel impulse response

A time-frequency block-sparse channel estimation method based on compressed sensing includes the following steps. Step 1: A channel model is established. Step 2: According to the channel model obtained in Step 1, a sparse signal estimation value is solved by a compressed sensing method to further calculate an index set. Step 3: According to the index set obtained in Step 2, a channel matrix estimation value is solved. The method provides a generalized block adaptive gBAMP algorithm, which uses time-frequency joint block sparsity of a massive MIMO system to further optimize selection of an index set in an algorithm iteration process to improve stability of the algorithm. Then, without a specified threshold parameter, based on an F norm, an adaptive iteration stop condition is determined based on a residual, and the validity of the method is proved.

Time-frequency block-sparse channel estimation method based on compressed sensing

The disclosure discloses a channel prediction method and system for a MIMO wireless communication system. The method includes the following steps: obtaining frequency domain channel information of each antenna pair of the MIMO wireless communication system through channel estimation; processing, by inverse Fourier transform, frequency domain channel information of each antenna pair to obtain information of each effective delay path of the MIMO wireless communication system; training the width learning system; utilizing the trained width learning system to predict each effective delay path of each antenna pair, so as to obtain the information of the next moment of each effective delay path of each antenna pair; after summarizing the information of the next moment of each effective delay path of each antenna pair obtained through prediction, the Fourier transform is utilized to convert the information into predicted frequency domain channel information. The invention can provide satisfactory prediction performance.

Channel prediction method and system for MIMO wireless communication system

A channel prediction system and a channel prediction method for an OFDM wireless communication system include a standard echo state network and a two-layer adaptive elastic network. In the method, with respect to each subcarrier of a pilot OFDM symbol, an echo state network is trained by using frequency domain channel information of each subcarrier obtained by channel estimation. The trained echo state network may realize short-term prediction of the frequency domain channel information. To overcome a likely ill-conditioned solution of an output weight in an echo state network, the output weight in the echo state network is estimated by using a two-layer adaptive elastic network.

Channel prediction system and channel prediction method for OFDM wireless communication system

A Deep Belief Network (DBN) feature extraction-based analogue circuit fault diagnosis method comprises the following steps: a time-domain response signal of a tested analogue circuit is acquired, where the acquired time-domain response signal is an output voltage signal of the tested analogue circuit; DBN-based feature extraction is performed on the acquired voltage signal, wherein learning rates of restricted Boltzmann machines in a DBN are optimized and acquired by virtue of a quantum-behaved particle swarm optimization (QPSO); a support vector machine (SVM)-based fault diagnosis model is constructed, wherein a penalty factor and a width factor of an SVM are optimized and acquired by virtue of the QPSO; and feature data of test data are input into the SVM-based fault diagnosis model, and a fault diagnosis result is output, where the feature data of the test data is generated by performing the DBN-based feature extraction on the test data.

Growing community of inventors

Hubei, China

Chaolong Zhang