Search

Six new Pd(II), Pt(II) and Ag(I) complexes, (1);{Pd (L

AI and machine learning are revolutionary technologies being explored by the communication industry to integrate them into communication networks, provide modern services, improve network efficiency and user experience. The intrusion detection system is important for ensuring security of the industrial control system. Hence, in this paper, a machine learning assisted intrusion detection system (MLAIDS) has been proposed to analyse data flow characteristics in industrial network communication security. The progressive use of proposed ML algorithms will improve IDS functionality, especially in industrial control systems. Analysis of data flow characteristics given in this article involves the method of ensuring an adequate degree of security for a dispersed industrial network concerning some main elements, including system features, the present state of requirements, the implementation of suitable countermeasures that may lead to reducing the security risk under a predefined, acceptable threshold. The numerical results show that proposed MLAIDS method achieves high detection accuracy of 98.2%, a performance ratio of 97.5%, a prediction ratio of 96.7%, F1-score of 95.8%, and less root mean square error of 10.5% than other existing methods.

A novel apparatus is introduced in this paper used to measure high voltage electric energy based on three-phase four-wire virtual-ground theory. The virtual-ground design, Faraday shielding technique and Warner DC (Direct Current) self-supply method are integrated in this apparatus based on new I/V, V/V techniques to realize high accuracy, reliability and wide-linear range measuring. The effectiveness of the apparatus has been proved by in-house calibration and on-site test . The test result shows that it can be used in high voltage grid on-site calibration . Its measurement uncertainty can be limited to 0.1% under the condition of PF=1.0~0.8, and can reach 0.15% as PF=0.5. In summary, the apparatus discussed in this paper can be applied as high voltage electric energy measurement instrument to meet the requirement of online metrological verification and calibration. Furthermore, it is very useful for building the system of Advanced Metering Infrastructure (AMI) in smart grid.

Neural networks have been shown to be pow-erful tools for solving optimization problems. In this paper, we first retrospect Chen’s chaotic neural network and then propose several novel chaotic neural networks. Second, we plot the figures of the state bifurcation and the time evolution of most positive Lyapunov exponent. Third, we apply all of them to search global minima of continuous functions, and respec-tively plot their time evolution figures of most positive Lyapunov exponent and energy func-tion. At last, we make an analysis of the per-formance of these chaotic neural networks.

This paper discusses the basic scheme for establishing advanced metering infrastructure (AMI) by applying a high-voltage electric energy on-site calibration apparatus. The apparatus can work as an on-site working standard for implementing on-site calibration or verification to kinds of meters, electric energy metering cabinet and electric energy device in AMI. Furthermore, this paper provides a technical mean for calculating parameters of power grid, such as transformer loss and wire loss, in accordance with the principle of energy conservation. 10kV high voltage on-site calibration apparatus had been developed successfully and has been running in the power grid, on-site test results can prove that the scheme is feasible. Establishing a complete AMI system is of great significance for building a strong smart grid.

The new model can solve the 10-city traveling salesman problem more effectively because of Morlet wavelet being a kind of basic function. First, the chaotic dynamics of the neuron was analyzed, and the figures of the reversed bifurcation and the maximal Lyapunov exponents of single neural unit were given. Second, the new model was applied to solve function optimizations and the evolution figures of the energy function were plotted. Finally, 10-city traveling salesman problem was given and simultaneously a group of parameters for the network in solving the 10-city traveling salesman problem were proved to be efficient by the computer simulation. Seen from the simulation results, the new model is powerful.

Chaotic neural networks have been proved to be powerful tools for escaping from local minima. In this paper, we first review Chen’s chaotic neural network and then propose a novel chaotic neural network model. Second, we make an analysis of the most positive Lyapunov exponent of the neural units of Chen’s and the proposed model. Third, 10-city traveling salesman problem (TSP) is given to make a comparison between them. Finally we conclude that the novel chaotic neural network model we proposed is more valid.

By the use of the properties of ergodicity, a chaos algorithm for multilayer feedforward neural network is proposed with combining logistic mapping and BP algorithm. This algorithm can make BP algorithm to skip the local minimum and can find the global minimum finally.

Chaotic neural networks have been applied to solve function optimization problems successfully. To improve the optimization capacity of the chaotic neural network, a new chaotic neural network model called wavelet chaotic neural network was presented by transferring sigmoid function to wavelet function. The reversed bifurcation figures of signal neural unit were given and the parameters of the new model were discussed. The wavelet function is a non-monotonic function, so the new model can spend the less time than the common chaotic neural network model in function optimization. The simulation result shows that the new chaotic neural network model is superior to the common neural network model.