期刊名称：Journal of Materials and Environmental Science
印刷版ISSN：2028-2508
出版年度：2018
卷号：9
期号：7
页码：2009-2016
出版社：University of Mohammed Premier Oujda
摘要：Electronics System has become the integral part of our daily life. From toy to radar,system is dependent on electronics. The health conditions of humidity sensor need to bemonitored regularly. Temperature can be taken as a quality parameter for electronicssystem which works under variable conditions tends to failure of the systems. Usingvarious environmental testing techniques, the performance of DHT11 has beenanalysed. The failure of humidity sensor has been detected using accelerated life testingand an expert system is modelled using various artificial intelligence techniques i.e.Artificial Neural Network, Fuzzy Inference System and Adaptive Neuro-FuzzyInference system. A comparison has been made in between the response of actual andprediction techniques, which enable us to choose the best technique on the basis ofminimum error and maximum accuracy. It has been observed that ANFIS is proved asthe best technique with minimum error for developing intelligent model. The meanlifetime of DHT11 using environmental testing has been calculated as 26.65 hours. Theaccuracy of ANFIS is 97.52% in comparison with other artificial intelligencetechniques.
关键词：Humidity sensor;Health Prognostics;Environmental Testing;Failure Prediction;Accelerated life testing.
