Papers by Keyword: Fuzzy Neural Network

Abstract: Precision grinding is generally used as the final finishing process, and it determines the surface quality of the machined component. It’s very difficult to achieve on-line measurement of the surface roughness. The purpose of this research was to study the surface roughness prediction and avoid the defect happening in the grinding process. A surface roughness prediction model was proposed in this paper, which presented the relationship between surface roughness and the wear condition of grinding wheel and grinding parameters. An AE sensor was used to collect the grinding signals during the grinding process to obtain the grinding wheel wear condition. Besides, a fuzzy neural network was used to obtain the prediction surface roughness. Grinding trials were performed on a high precision CNC cylindrical grinder (MGK1420) to evaluate the surface roughness prediction model. Experiment verified that the developed prediction system was feasible and had high prediction accuracy.

Abstract: Using a controller is necessary for any automation system. The controller must be cheap, reliable, user friendly and not cause any problems for inputs and outputs. Classical control systems like proportional integral derivative (PID) put adequate results of linear systems and continuous-time. In fact, real control systems are time-variant, with non-linearity and poorly calculated dynamic variables. For this reason, conventional control systems need an expert person to adjust controller parameters in general. Sometimes an operator is required to solve control problems. Human control is not completely reliable. Also, it does not include any electronic communication. In modern factories, every point must be monitored and electronically controlled from remote points when necessary. In this study, including every electronic communication channel, a simplified handling, low-cost, reliable, Fuzzy Neural Network Controller (FNNC) is designed.

Abstract: By the analysis of the operational principle of electricity powered four-wheel steering system, a new system based on the fuzzy neural network. Since this is a complex multivariate and non-linear system, by making use of the characteristics of fuzzy control and the neural network, a fuzzy neural network can be established. The speed of car and front-wheel steering angle being the input and steering model being the output, the side-slip angle of the in the process of steering can be control to zero. At last, by emulating this system with the software Matlab/Simulink, it shows that self-healing control technology can effectively control the side-slip angle and improve the motility and stability of a car.

Abstract: Internalization of environment cost assessment measures the level of an enterprise’s environmental cost internalization. It’s also the basis of carrying out recycling economic in an enterprise. First of all, we established an environmental cost analysis model, in line with which we build the internalization of environment cost index system. Then adopting comprehensive evaluation method basing on fuzzy neural network can help us assess the effect brought by the internalization of environment cost. Finally, we conducted an experiment which comparing fuzzy neural network with the fuzzy evaluation of environment cost objectively. So we can think it’s an effective method.

Abstract: Based on the theory of roughness during grinding and the theory of fuzzy-neural network, a new intelligent prediction model is developed in this paper. The inputs for the model are the grinding parameters and the AE signals. Beijing Shenghua SAEU2S system was used to collect and analyze the signals of acoustic emission. The experiment was conducted, and the results verify the feasibility of the proposed model.

Abstract: This paper introduces the basic mathematical model of fuzzy neural network and T-S model. It uses the fuzzy neural network for targeted emulational signal-noise separation and presents evaluation indexes of the fuzzy neural network’s denoising effect, analyzes its mean square error (MSE), signal-to-noise ratio (SNR), SNR gain, and similarity of signal and theoretical reference signal after denoising. The simulation results show that this algorithm has prominent effect of separation under high and low SNR environment. At last, the experiments for the second lake of Fenhe also validated the superiority and effectiveness of this algorithm.

Abstract: Material inventory management plays an increasingly important role in modern operations management within manufacturing enterprises. And a multi-attribute classification model has been put up based on the application of the decide tree model and fuzzy artificial neural network. First the material inventory styles are classified. Then a decision tree model is defined based on inventory classification result. The value of the node is decided by Fuzzy Neural Network if multi-attribute decision is needed and material inventory strategy can be decided with the classification tree and inventory strategy table. In the end, the implementation of the model in a manufacturing enterprise resource plan system is presented.

Abstract: During the course of building an innovative country and enhancing the independent innovation capability, universities are the main force and the important source of high-tech innovation. The evaluation on the university's innovation ability, not only may improve university's efficiency and level of scientific research, but also make a significant sense to perfect the china' scientific research innovation system. Based on Referring to the recent research achievements at home and abroad, research and design work was carried out in the following area. Firstly, the multi-university research innovation ability evaluating indicator system is designed in this paper. By the principle of science and justice, through questionnaires, expert opinion and reference to relevant research results. The paper designed the multi-university's research innovation ability evaluating indicator system. A variety of typical evaluation models and methods are studied. Then two evaluation models between PCA-BP and PCA-FNN are taken into comparison. And the results show that the research and application of PCA-FNN is proved to be a new method and made a significant attempt for the university’s evaluation of research innovation ability.

Abstract: The modern design theory and method of the differential case is discussed in this paper. The various factors affecting on the reliability of differential case are analyzed. The influences of these factors on the reliability of differential case are found to be a nonlinear relationship. The reliability calculation model of differential case is established on the basis of the theory of fuzzy-neural network. After the model was established, samples are used to train the network to determine the weight and threshold in the model. After using the sample parameters to train the network model, and then using the sample parameters to test the network, the results need to meet the requirements.The reliability of differential case of an electric car is calculated. The result shows that the model is correct and effective. Key Words: model; differential; reliability; fuzzy neural network

Abstract: Due to the complexity of greenhouse environment, greenhouse system cannot be controlled perfectly by traditional control method. This paper proposes a novel greenhouse control system based on fuzzy neural network to regulate the internal climate of the greenhouse. Temperature and humidity are selected as the inputs of controller, while the skylight, sun-shade net, circulation fan, side windows, fuel heater, and micro-mist humidifier are selected as the outputs. After analyzing every situation that may occur in the control process and the corresponding control strategies, we obtain 35 control “IF-THEN” rules. Simulation results show that the fuzzy neural network controller have certain improvements than the conventional PID controller in the aspects of overshoot, stability and response time.