Lean Optimization of newly established Assembly Line using Data Analysis of Quality by the feed from Image recognition Industry 4.0 and Jishuken Study

Electric vehicles are emerging and evolving with time future-oriented tend to more automation and data-oriented results which is more near to the accuracy. This leads to taking fast decision-making. Covid -19 pandemic accelerated automation further which is a part of Industry 4.0. with the growing trend of connecting different sectors of industries among each other all activities are associated with both Value Addition (VA) and Non-Value Addition (NVA) traits. A lean approach can be adopted in order to reduce NVA through waste reduction. Where the data are being collected from the assembly line from operations which automatic or manually performed. The thesis proposes a technique focusing on optimizing a newly established Assembly line eliminating wastes and quality defects to improve the OEE (overall equipment effectiveness). Data collected by MES (Manufacturing Execution System) through Images with pattern recognition and process deviation. In case anomalies are being found in the process data which are being further characterized as defects. These defects are further processed for scrap analysis of the overall line, which is being bifurcated to every operation level which provide results for analysis of the outliers. Whereas Jishuken is more about finding out Lean wastes which result in indicating all the NVA (Non-Value addition) and VA (Value Addition) from time study of operations. By removing NVA’s of every operation, it results in an overall reduction of cycle time. With this approach, indications are fetched for the number of activities being scheduled, whereas few are being implemented and some are in progress as per the plan. Improvement is being monitored on the dashboard of the organization to keep a record.