Chung-Chi Huang

Fuzzy sliding mode-based control for PMSG maximum wind energy capture with compensated pitch angle

This paper presents the design of a fuzzy sliding mode loss-minimization control for the speed of a permanent magnet synchronous generator (PMSG) and proportional-integral (PI) for the turbine pitch angle control. The PMSG speed uses maximum power point tracking below the rated speed, which corresponds to low and high wind speed, and the maximum energy can be captured from the wind. A sliding mode controller with an integral-operation switching surface is designed, in which a fuzzy inference mechanism is utilized to estimate the upper bound of uncertainties. Furthermore, the fuzzy inference mechanism with center adaptation is investigated to estimate the optimal bound of uncertainties.

Development of intelligent quality prediction for manufacturing system

The main purpose of this research is to develop an intelligent quality prediction system. We are proposing a parameter of quality prediction module that selected 12 factors from MEPH and 16 quality evaluation factors of manufacturing system. By using back-propagation neural network method, the module is built up. The module could be used by calculating the quality evaluation from the quality factors such as material, machine, product, and staff. However, we could get the prediction of quality through the way of data fusion by the 16 quality indicators. After all, this research will test the prediction of quality by an experimentation of manufacturing system in order to prove the feasibility of the parameters and the intelligent prediction methodology.

A machine tool performance monitoring system for use on common hand-held devices

This paper aims to develop a machine tool performance monitoring system for use on common hand-held devices, which would allow remote monitoring of the machine tools performance during the machining process, with the aim of increasing its working life. The system will acquire and analyze the vibration signals of various states coming from a given machine tool using Wavelet Packet Theory and Principal Component Analysis. The calculated results are then saved in the database, and a training model is established using Bayesian Classification. In order to assess the machine tools condition, the acquired vibration signals can be compared with the stored signal results from the training model. Then by using WebService and XML technologies, the system will be able to display the results on all common hand-held devices, allowing for a range of different equipments, including PC, Notebook, PDA and Smartphones to access the information remotely. As a result of this research, engineers will be able to monitor and assess a machine tools performance almost anywhere in the world.

Intelligent diagnosis and prescription for a customized physical fitness and healthcare system.

With the advent of the era of global high-tech industry and commerce and its associated sedentary lifestyle, opportunities for physical activity are reduced. Peoples physical fitness and health is deteriorating. Therefore, it is necessary to develop a system that can enhance peoples physical fitness and health. However, it is difficult for general physical fitness and healthcare systems to meet individualized needs. The main purpose of this research is to develop a method of intelligent diagnosis and prescription for a customized physical fitness and healthcare system. The proposed system records all processes of the physical fitness and healthcare system via a wireless sensor network and the results of the diagnosis and prescription will be generated by fuzzy logic inference. It will improve individualized physical fitness and healthcare. Finally, we demonstrate the advantages of intelligent diagnosis and prescription for a customized physical fitness and healthcare system.

Hardware design of features extraction using wavelet packet method for intelligent diagnostic system

This paper aims to develop a hardware architecture of features extraction using wavelet packet method for an intelligent diagnostic system. Verilog-based features extraction architecture is proposed and implemented. Test results verify the design architecture of features extraction using wavelet packet method. A CNC spindle motor commonly featured in intelligent diagnosis of manufacturing systems is chosen to verify this architecture. Under the normal and eccentric spindle states, system modeling is built up for a high speed (10,000RPM), medium speed (5,000RPM) and low speed (1,000RPM) The test results of samples of different rotating speeds under the normal and eccentric spindle states show the effect of the hardware of features extraction and verify the feasibility of hardware design.

Intelligent scheduling of execution for customized physical fitness and healthcare system.

Physical fitness and health of white collar business person is getting worse and worse in recent years. Therefore, it is necessary to develop a system which can enhance physical fitness and health for people. Although the exercise prescription can be generated after diagnosing for customized physical fitness and healthcare. It is hard to meet individual execution needs for general scheduling of physical fitness and healthcare system. So the main purpose of this research is to develop an intelligent scheduling of execution for customized physical fitness and healthcare system. The results of diagnosis and prescription for customized physical fitness and healthcare system will be generated by fuzzy logic Inference. Then the results of diagnosis and prescription for customized physical fitness and healthcare system will be scheduled and executed by intelligent computing. The scheduling of execution is generated by using genetic algorithm method. It will improve traditional scheduling of exercise prescription for physical fitness and healthcare. Finally, we will demonstrate the advantages of the intelligent scheduling of execution for customized physical fitness and healthcare system.

Fool-proofing design and crisis management for customized intelligent physical fitness and healthcare system

In recent years, it is quite important to develop a customized system which can enhance physical fitness and health for people. And the system reliability is more important. In the paper, a fool-proofing design and crisis management for customized physical fitness and healthcare system is proposed. It is designed to prevent the failure of the various mechanisms of customized physical fitness and healthcare system, including records, surveillance, assessments, predictions, diagnosis, prescription, and scheduling. It is separated into (1) fool-proofing design module (2) crisis management module. The fool-proofing indexes are set to prevent the failure of the various mechanisms. The states of the various mechanisms are managed by the auto-checked fool-proofing indexes. If mistakes prevention was fail, we have to execute the crisis management for stopping harmful results. The crisis management will find the error level and response the solution by using fuzzy method. By the experiments, we can find the advantages of the fool-proofing design and crisis management for customized physical fitness and healthcare system. And it is effective to prevent the failure of the various mechanisms of intelligent customized physical fitness and healthcare system.

Using Wavelet Hybrid Self-Organizing Feature Map Network for V-I Based Multiple Harmonic Sources Classification

This paper proposes a method using non-linear voltage-current characteristics for multiple harmonic sources classification using wavelet hybrid neural network (WHNN). Typical voltage-current characteristics of harmonic sources are non-linear closed curves in the time-domain, referring to the converters, reactors, and non-linear loads. The hybrid neural network is a two-subnetwork architecture, consisting of wavelet layer and a self-organizing feature map (SOFM) network connected in cascade. The effectiveness of the proposed method is demonstrated by numerical tests. The results of multiple harmonic sources show the computational efficiency and accurate classification.

The Improved Customer Satisfaction Prediction System on Airlines Service by Using Cloud Computing Based Intelligent Strategy System

The main purpose of this research is applying an intelligent strategy to improve the customer satisfaction prediction system of airlines service. Historically, the measurement of customer satisfaction collects by questionnaire. We collect and computing the customer satisfaction of each flight by the cloud computing based prediction system. It compares the customer questionnaire, then continuous modifying the accuracy of prediction system by neural network methodology. It is more efficiency and precisely to improve the customer satisfaction for the long-term perspective. We are proposing a parameter of evaluation module that selected 12 influence factors from MEPH and 12 satisfaction evaluation factors of airlines service (by customer perception of service quality). In this study, we are using back-propagation neural network method to build the module. The module could be used by calculating the airlines service satisfaction from the quality factors such as material, machine, product, and staff. However, we could get the prediction of service satisfaction through the way of data fusion by the 12 satisfaction indicators. The results could be used to make the service quality strategy, in order to lead a higher customer satisfaction. The findings help airlines managers to predict their customer satisfaction more efficiently, making changes to service quality strategy easily to meet the customers’ satisfaction level. Even if the managers pre-set a customers’ satisfaction level, a real-time cloud computing could help managers deploy the resources to achieve the goal. After all, in order to prove the feasibility of the parameters and the intelligent evaluation methodology, this study will collect data and test the evaluation of quality from an experimentation of airlines service system in Kaohsiung city in Taiwan.

Design and Implementation of Cloud-Dust Based Intelligent System

In the paper, design and Implementation of cloud-dust based intelligent system is proposed. For achieving applications of intelligent system, such as records, surveillance, assessments, predictions, diagnosis, prescription, scheduling and fool-proofing checks, an architecture named Cloud-Dust is developed. The intelligent system is separated into the cloud system and the dust system. The dust system contains (1) Wireless sensors network (2) Features extraction circuits (3) Intelligent computing circuits (4) Embedded system. It can play a role as real-time preprocessor very well, just like an intelligent agent. However, the cloud system contains (1) Cloud database (2) Intelligent computing engine (3) Ubiquitous human-machine-interface. It can flexibly use computing resources and integrate information from many different dust systems. By the experiments, we can find the advantages of the cloud-dust based intelligent system. It meets the both needs of real-time and integration for intelligent systems. So it is necessary to develop the cloud-dust based system for design and implementation of the intelligent system.