As the technology advances, the reliability becomes the main constraint for the successful operation of the electronic product. To fully automate the system, the electronic devices become more and more complex. Reliability becomes a challenge with the regular demand of low cost and high-speed devices. Residual life estimation of passive devices such as resistor, capacitor etc. is of a great concern. Failure of one small component can lead to fully damage of whole system. In this paper, a practical approach i.e. accelerated life testing is deployed to calculate remaining useful life of the ceramic capacitor. An intelligent model is formulated using various artificial intelligence techniques. Artificial Neural Network (ANN), Fuzzy Inference System (FIS) as well as Adaptive Neuro Fuzzy Inference System (ANFIS) are deployed to predict the remaining useful lifetime of an electrolytic capacitor. An error analysis is conducted to estimate the most accurate intelligent technique. A fuzzy based decision support system is modelled, which provides an interactive GUI to users. The user can access the live health status of electrolytic capacitor at various input parameters. It will warn the user to replace or repair the upcoming fault in the component or device, before it actually degrades or shut downs the complete system. The comparative analysis of all the artificial intelligence techniques shows that Adaptive Neuro Fuzzy Inference System (ANFIS) has the highest accuracy i.e. 99.5%, as compare to Artificial Neural Network (ANN) and Fuzzy Inference System (FIS), where accuracy rate is 98.06% and 97.84% respectively. This prediction system is helpful to reduce the problem of electronic e-waste by enabling the user to reuse the component
Correction to: Comparison of Self‑Organizing Map, Artificial Neural Network, and Co‑Active Neuro‑Fuzzy Inference System Methods in Simulating Groundwater Quality: Geospatial Artificial Intelligence
