This work aims to develop a cost-effective Machine Learning (ML) based methodology to identify different implements like primary tillage implements, secondary tillage implements, other implements like Loader, snow blower, etc. For this study, engine, vehicle, and beacon data were collected using a data logger mounted on vehicles operating with two primary implements: a loader and a secondary tillage implement. Firstly, time series data has been examined for noise, peaks, and missing values. Following the parameter analysis, parameters displaying trends or specific patterns for different implements have been selected. By selecting the most effective parameters, various classification machine learning algorithms, such as KNN, Decision Tree, and Support Vector Machine (SVM), have been developed and trained to accurately identify the implement attached to the vehicle. The developed methodology was tested on new data and demonstrated an average accuracy of 92.5%. This study is useful for product validation & design team to get effective duty cycle & make useful decision in off-highway vehicle development. Moreover, different implement requires to run at a specific setting, so this study can suggest the customer optimal settings for different implement which results in better fuel economy & lower emission. Also, this study will help a customer to know about the total number of hours completed by the vehicle in one operation in a particular timeline which would be helpful in effective fleet management & planning schedule maintenance.