Revolutionizing Predictive Maintenance: AI-Driven Wear Life Prediction for Al-SiC-Zinc Stearate Pre-Forms

Abstract

Abstract In this research, investigations were made on abrasive wear characteristics of Al-SiC- C36H70O4Zn (zinc Stearate) powder pre-forms. Al-SiC- Zinc Stearate powder pre-forms of one composition were tested, considering compacting pressure and sintering temperature. At room temperature, the wear tests were carried out in a purpose built pin-on-disc apparatus in opposition to abrasive silicon carbide paper under multi-pass conditions. Abrasive wear studies were performed under several operating conditions which includes varied applied load (0.5 kg to 3 kg), constant sliding velocity (300 rpm), constant time in seconds (180 seconds) and varied abrasive grit sizes (1/0, 2/0, 3/0 & 4/0). The weight loss indicates the wear. The test results are obtained in terms of weight loss, wear rate and specific wear rate. The relationships between weight loss and load applied with varied abrasive grit size, applied load and specific wear rate, applied and wear rate with grit size of abrasive paper 3/0 were established in the form of tribo graphs. The experimental data were trained and tested using an artificial neural network model. The result displays the actual data and predicted data relation with the correlation coefficient and mean square error value as 0.99951 and 0.0063107 respectively.