Gearboxes are the most widely used component to transfer speed and power in many industries, and high precision gearbox fault diagnosis (FD) is pretty crucial for ensuring the safe operation of the machine. However, traditional FD methods often need a great quantity of labeled data, and are prone to noise interference in practical work, resulting in a relatively low diagnosis accuracy. With the intention of overcoming these problems, this paper proposes a semi-supervised FD approach based on feature pre-extraction mechanism and improved generative adversarial network (IGAN). First, the data is preprocessed by the feature pre-extraction mechanism based on wavelet transform. Then, limited labeled samples and a large number of unlabeled samples are sent to the IGAN model. Finally, two typical gearbox fault datasets are utilized to evaluate the feasibility and effectiveness of the proposed approach in limited labeled samples and noise environment. Trial results denote that the proposed approach has better diagnosis accuracy and anti-noise robustness than other approaches.

Superconducting fault current limiter (SFCL) has been recommended as an idea current limiting method. And Inductive SFCL is one of the potential candidates of SFCL, with its advantages of fast responding, no quench and quick recovery characteristics. Recently years, several ISFCLs have been installed in demonstration projects all around the world. This paper focuses on the optimal configuration of ISFCL designed for distribution networks. Considering the current limiting performance and total cost of ISFCL, the optimal model of ISFCL parameters is established to choose suitable parameters for target system. Results of this paper are used to guide the design and fabrication of ISFCL prototypes.

In order to overcome the barriers of data sharing in the electric power industry, enhance the whole life cycle management level of power equipment, Handle identity resolution is used. This article introduces the application of data sharing of Handle identity resolution in electric systems. Through the application of handle identity resolution technology, the electrical equipment research and development process data, on-site operation data and all kinds of piecemeal data are to be integrate and apply. Power equipment production enterprises understand the production process quickly and accurately, monitory product health in real-time, handle problem products timely, grasp the upstream and downstream operations of electrical products at all levels, reduce enterprise logistics costs, master the real-time process of products, quickly freeze and recall problematic products, improve product quality, improve market credibility and competitiveness. Electric enterprises can grasp the electric power operation situation in a timely manner, reduce production costs and improve production efficiency. It strengthens the management of the whole life cycle of electrical equipment of power enterprises and power equipment manufacturers.

In order to enhance the network security protection level of intelligent substation, this paper puts forward a model of intelligent substation network security defense system through the analysis of intelligent substation network security risk and protection demand, and using example proved the feasibility and effectiveness of the defense system. It is intelligent substation network security protection provides a new solution.

The reliability and performance of high-voltage circuit breakers (HVCBs) will directly affect the safety and stability of the power system itself, and mechanical failures of HVCBs are one of the important factors affecting the reliability of circuit breakers. Moreover, the existing fault diagnosis methods for circuit breakers are complex and inefficient in feature extraction. To improve the efficiency of feature extraction, a novel mechanical fault feature selection and diagnosis approach for high-voltage circuit breakers, using features extracted without signal processing is proposed. Firstly, the vibration signal of the HVCBs' operating system, which collects the amplitudes of signals from normal vibration signals, is segmented by a time scale, and obviously changed. Adopting the ensemble learning method, features were extracted from each part of the divided signal, and used for constructing a vector. The Gini importance of features is obtained by random forest (RF), and the feature is ranked by the features' importance index. After that, sequential forward selection (SFS) is applied to determine the optimal subset, while the regularized Fisher's criterion (RFC) is used to analyze the classification ability. Then, the optimal subset is input to the hierarchical hybrid classifier, and based on a one-class support vector machine (OCSVM) and RF for fault diagnosis, the state is accurately recognized by OCSVM. The known fault types are identified using RF, and the identification results are calibrated with OCSVM of a particular fault type. The experimental proves that the new method has high feature extraction efficiency and recognition accuracy by the measured HVCBs vibration signal, while the unknown fault type data of the untrained samples is effectively identified.

To improve the accuracy of the recognition of complicated mechanical faults in bearings, a large number of features containing fault information need to be extracted. In most studies regarding bearing fault diagnosis, the influence of the limitation of fault training samples has not been considered. Furthermore, commonly used multi-classifiers could misidentify the type or severity of faults without using normal samples as training samples. Therefore, a novel bearing fault diagnosis method based on the one-class classification concept and random forest is proposed for reducing the impact of the limitations of the fault training sample. First, the bearing vibration signals are decomposed into numerous intrinsic mode functions using empirical wavelet transform. Then, 284 features including multiple entropy are extracted from the original signal and intrinsic mode functions to construct the initial feature set. Lastly, a hybrid classifier based on one-class support vector machine trained by normal samples and a random forest trained by imbalanced fault data without some specific severities is set up to accurately identify the mechanical state and specific fault type of the bearings. The experimental results show that the proposed method can significantly improve the classification accuracy compared with traditional methods in different diagnostic target.

In order to improve the information security level of intelligent substation, this paper proposes an intelligent substation information security assessment tool through the research and analysis of intelligent substation information security risk and information security assessment method, and proves that the tool can effectively detect it. It is of great significance to carry out research on industrial control systems, especially intelligent substation information security.

Large-scale integration of wind power will affect the static voltage stability of the power system. Through the power flow calculation of the regional power grid with wind turbines, the voltage stability of the power grid connected to the wind farm is analyzed based on the P-V curve method. Moreover, the variation of voltage is analyzed by changing the control mode of the fan and adding the reactive power compensator. The results show that the voltage stability of the constant voltage control mode is better than that of the constant power control mode, and the voltage level is obviously improved after adding reactive power compensation.

Access to new energy large scale has changed our traditional characteristics produced during operation of electric power system, relay protection of our traditional and automatic safety devices bring higher requirements and challenges [1-2]. This paper introduces the situation of new energy power generation connected to a power grid, analyzes the operation risk of new energy access on distance protection and safety device and puts forward some suggestions and measures to resist the risk of power grid relay protection and self-installation. Research and analysis on relay protection and safety device for distributed new energy access to a regional power grid.

With the development of science and technology and economic progress, the car as people's conventional means of transport, a lot of people into the daily life of people. In the overall structure of the car, the engine is the most burden of the region, is the most common failure of the components. The normal operation of the car engine is an important condition for ensuring that the vehicle is running normally. When the car engine failure, we should adopt a more reasonable inspection measures. Only to determine the cause of the car engine failure, and thus according to the reasons for the corresponding repair, and ultimately ensure the good operation of the car engine to ensure the safety of road driving. In the overall structure of the car engine is a key component, shorten the maintenance time, for improving the engine economy, power and environmental protection is of great significance.

With the prevalence of renewable energy source in power system, it is necessary to appraise the voltage stability of the integration system by probabilistic methods. The traditional Markov Chain Monte Carlo (MCMC) simulation could show great calculation precision for the probabilistic assessment, but it is always involved with complicated sampling iterations because of the Gibbs sampling method currently used in MCMC simulation. Instead of Gibbs sampling method, this paper presents the application of slice sampling in MCMC simulation for the voltage stability probabilistic assessment of the power system with renewable source. Firstly, the probabilistic models of renewable source generation are constructed. Then, the sample space of renewable source outputs is obtained by slice sampling, and the samples from the sample space are calculated by power flow. Finally, the voltage stability margin is obtained by the result of the power flow calculation, and the probabilistic assessment of the voltage stability is implemented. Furthermore, the MCMC simulations using Gibbs sampling and slice sampling are compared by Gelman-Rubin diagnostic and Kullback-Leibler divergence tests on IEEE 14-bus system and IEEE 39-bus system, respectively. The results show that the slice sampling method is simpler and more efficient than Gibbs sampling method in the voltage stability probabilistic assessment.

In a neutral nongrounding power system, the excitation impedance of an electromagnetic potential transformer (PT) and a ground capacitance power transmission line of an electric power system can form a resonant circuit that causes ferroresonance and endangers the security and stability of the power system. This study analyzes a theory of ferromagnetic resonance that occurs under a single-phase earth fault in the power system of a PT, and Simulink is used to establish a simulation model of PT ferromagnetic resonance. Through this model, Simulink conducts an analysis of the ferromagnetic resonance simulation for the isolated operation of an ordinary PT and a low magnetic flux density-type PT, the parallel operation of these two PTs, and the parallel operation of two low magnetic flux density-type PTs. Simulation results show that ferromagnetic resonance phenomenon does not occur easily in a PT with good excitation characteristics. However, ferromagnetic resonance can be generated easily in PT parallel connections.

As multi-sensor integration hydrogen detection systems can not diagnose the working state by itself,an expert system of fault diagnosis based on knowledge was analyzed and a fault diagnosis method based on knowledge management and knowledge pushing was proposed.The hierarchical structure of the fault diagnosis method used in the multi-sensor integration hydrogen detection systemwas investigated.On the basis of the principle of expert systems,the texture of expert system based on knowledge pushing actively was presented.After the fault modes were analyzed,a knowledge base fault diagnosis design was discussed.Then the method and step of inference engine based on knowledge pushing actively were researched by its established model.Finally,the fault diagnosis unit for multi-sensor integration hydrogen detection system based on knowledge pushing was designed.Experimental results indicate that the fault diagnosis accuracy rate of the proposed method reaches above 97%,which verifies the effectiveness of the method.It can transfer initiatively the knowledge to the decision-maker at opportune moment,and improve the speed and accuracy rate of fault diagnosis.

Since the traditional integrated navigation fault diagnosis algorithm has high requirement to the accuracy of system model,and the limited processing ability to the nonlinear integrated navigation system,the fault diagnosis of SINS/GPS/DVL integrated navigation system based on adaptive neural network is proposed. The mathematical model of the integrated navigation fault diagnosis is established and the fault information is extracted. The genetic algorithm is adopted to optimize the local minimum problem and network structure encountered in the process of fault diagnosis with BP neural network,which can improve the execution speed and efficiency of the algorithm,and enhance the fault diagnosis accuracy and system reliability. The validity of the algorithm is verified by simulation tests.

In allusion to the degenerative state recognition of rolling bearing,a performance degenerative recognition method based on mathematical morphological fractal dimension( MMFD) and fuzzy center means( FCM) is proposed by combining mathematical morphology and fuzzy assemble theory. MMFD is calculated for the performance degenerative feature of rolling bearing to describe its complexity and irregularity in the view of fractal. In consideration of the fuzziness among different performance degradation boundaries,FCM is introduced into fuzzy clustering for characteristic index,and the performance degradation could be recognized effectively in line with maximum subordinate principle. The fatigue life enhancement test of rolling bearing was carried out to gather the whole life data at Hangzhou Bearing Test Research Center. The method is applied to the whole life data of rolling bearing,the overall state successful recognition rate reachs 96%. The results show that the method has a small calculating cost and ahigh efficiency,and can efficiently identify the performance degenerative state of rolling bearings.

With the annual capacity growth of wind power integration, the stochastic wind power makes it increasingly difficult to optimize traditional unit commitment with fixed load and wind power percentage. Considering load and wind powder uncertainty, the multiple scenario model of load and wind power was established using scenario reduction techniques. To explore effect of load and wind power uncertainty, the positive and negative spinning reserve needs of the unit commitment were determined based on the maximum variation ranges of load and wind power under different scenarios. Considering effect of different loads and wind powers under different scenarios on the unit dispatch optimization, taking the weighted sum of mean and variance of generating cost under all scenarios as the objective function, a model for unit dispatch optimization that considers load and wind power uncertainty was established. This model was solved using improved particle swarm optimization (PSO) algorithm. PSO-oriented dynamic adjustment of unit output range was proposed in order to improve the convergence performance of the PSO algorithm during iteration. The accuracy and validity of the proposed model and algorithm were verified by a case study based on a typical 10-unit commitment.

This paper studies the user response characteristic to the time of use price, and establishes the user load response characteristic curve to the time of use price on the basis of consumer psychology. Based on the optimal operation model, the paper analyses the effect of demand side. The paper establishes the optimal TOU model based on economic operation and the demand side response. The power supply enterprise benefit maximization is the goal in this model, the best time of use price and optimal scheduling scheme can be made according to the prediction of the load. The model can be used to formulate the best scheme of TOU in a given time period, and provides a quantitative basis for electricity pricing of microgrid. Example analysis results show that the operation cost of microgrid reduces and the power supply enterprise benefit increases when considering the demand side response, the model has important guiding significance on the formulation of grid electricity price and scheduling scheme.

The optimal capacity combination model of an isolated microgrid is established, which considers the pollution emissions, the punishment of renewable energy waste, the effect of charge and discharge process of lead-acid battery to its lifetime and reliability, the total cost and punishment of renewable energy waste are considered as the two objective functions. This paper establishes isolated microgrid multi-target capacity optimization configuration model, and the adaptive genetic algorithm is proposed to solve the problem,then the paper analyses the effect of the punishment of wind energy waste and the reliability to capacity combination of microgrid. Example analysis results show that the punishment of wind energy waste has great effect to capacity combination of microgrid. The punishment of wind energy waste should be considered in the network planning; the reliability also has a great influence on the microgrid planning, and the different investment schemes should be selected according the different user reliability requirements.

Bearing fault owns great proportion in motor common faults,moreover,it can easily couple with rotor faults,inducing compound faults.AF/FM always appears as the character of motor bearing fault.Morphological gradient demodulation was proposed to extract fault feature.On the basis of analyzing the effect of different morphological operation in signal processing,in allusion to the boundedness of traditional envelope demodulation in processing double plus low frequency signal,test and verify the effectiveness of morphology gradient and morphology D-value operator.By means of analyzing impact on extraction nature of structure length,the advantages of morphology gradient was proved.Simulation and experiment results show that the method of morphological gradient demodulation,which has overcome the shortcoming of envelope demodulation,could extract motor bearing fault feature more effectively.