Development of quality prediction model and control mechanism for clinching process

Abstract

Many mass production lines in the industry use the joining technique known as clinching. Reasons for the high demand for the clinching process are the unnecessity of additional binding agent, process speed, waterproofness, eco-friendliness, and ease of implemantation. In the clinching process, metal sheets are formed under mechanical force that is applied by punch and die tools. The tools are designed and produced specifically according to the thickness and material properties of metal sheets. Despite the fact that there are electromechanical or hydro-pneumatic powered, conventional hydraulic powered clinching stations are the most preferred as sources of mechanical force because of their investment cost, process speed, versatility and size advantages. However, hydraulic powered systems bring along some drawbacks such as a lack of precision on the quality of clinched joints, eccentricity between punch and die, power consumption and control difficulty because of the single pump that feeds multi-cylinder systems. Although there are three major quality indicators of clinched joints, the bottom thickness of the joint is the most used and critical one because it is both the simplest measurement in an production environment and the most related to quality. Nevertheless, inspection of all produced clinched joints is not feasible based on the measurements of a single operator. Therefore, a quality prediction model is developed in this study. The study is conducted with force and displacement data that is collected from 16 different clinching cylinders at a 1200 Hz sampling rate. Linear, ridge, lasso, decision tree, random forest, extreme gradient boosting, support vector machine and k-nearest neighbors machine learning models are experimented with and validated systematically. The random forest regressor is found to be the best validation scored model. Additionally, a smart decision mechanism (SDM) is developed and implemented based on force and displacement sensor data to overcome major malfunctions that cause a remarkable amount of scrap and production line stoppage. Moreover, a part-to-part feedback control mechanism is developed and implemented to control clinching quality in the optimum range. The bottom thickness of a clinched joint for 0.4 and 0.5 mm stainless metal sheet joining must be between 0.3 mm and 0.4 mm in order to be evaluated as optimum, while the range of 0.25–0.5 mm is accepted as a proper joint. The control mechanism uses force and displacement sensor data to observe system behavior, and utilizes the prediction model and periodic manual measurements to build reference thresholds. In conclusion, an application that stores sensor data, runs control algorithms and makes visualization, is developed for two clinching stations that consist of 16 hydraulic cylinders. In future, the study can be maintained to predict quality more precisely and maintenance dates with regard to the expanding data set and the advanced machine learning algorithms.