In the recent studies says that is the state of the art of process mining algorithms were used in different applications such as healthcare, sales and inventory, etc. But in my previous research paper, first time we have implemented the process mining algorithms in the domain of dyeing units. Normally, the dyeing unit is complex in nature, because it involves dynamic features in the process. Moreover, it is also critical to keep a check on the automated processes to produce the expected results in the form of quality and timely dyeing processes. Delivering these processes is a complex, because colour shades are difficult to identify the little difference and also various dyeing problems were identified after dye mix. The main process of dyeing process is dye mix process; it involved various treatments, these treatments were very difficult to maintain the shade matching. Therefore, the process mining algorithms were used to identify the better process control against the difficulties of dyeing process. These process mining algorithms produce a diagrammatic process model, which is very easy to understand by the dyers, but when the process has more number of activities then the complex process models were produced. The outcome of these process models were not easy to understand, so some clustering techniques were used but at the same time the missing activities produce more noise, that is the process model after clustering misses the originality. To overcome these limitations, the association rule mining algorithms were used in the domain of dyeing unit and the related issues are also compared in this paper.