A Study On Fault Detection And Diagnosis Of Dryer Based On Artificial Neural Network

Home appliances, one kind of important electromechanical product, are widely used in various homes. People utilize them almost every day, so if there were any faults or even serious incidents occurred, they would impact people's life negatively. Many home appliance makers are studying on the theories and the technique of the product reliability, i.e. the study on fault mechanism and fault diagnosis, reliability theories and testing method, to estimate and improvement of their quality and reliability continuously.Because that home appliance is one kind of long-life, repairable, complex product, it usually consists of electronic controller, heating/cooling system, motor drive system, airflow system, and etc. Meanwhile the appliance used under different environmental condition, so the fault distributions are various. One method of the study on the distribution is to run the reliability test and acquire data. We can use different method to detect and diagnose faults, but the most important thing is to find the practical and new diagnosis method. After studying various conventional fault diagnosis method and artificial neural network, the way of fault detection and diagnosis based on artificial neural network and fault tree analysis for dryer is provided in this paper.To acquire data of the running dryer is a basis for the fault detection and diagnosis, but since the constraint of the hardware and/or cost, some signal could not be measured directly, the soft sensing technique based on the neural network is provided to solve these issues.Presenting the advantage of neural network technology, neural network is introduced to the system. For decreasing the uncertainty of the diagnosis system, the information fusion pattern based on neural network is discussed. The approach of multi-sensor data fusion based on neural network is shown to be practical and effective through comparing the results of experiment.The concept and structure of virtual instrument is discussed deeply. Then we designed a new universal platform of dryer fault detection and diagnosis system, which is based on the virtual instrument and an integration of artificial neural network. Meanwhile, modularization design technique is applied fully on the programming, so the system can work stably and could be updated easily.