The current Husqvarna chainsaw lubrication process uses a sensor system requiring  multiple sensors to modify oil flow. This study aimed to explore the use of a vibration sensor to modify oil flow in the goal to reduce complexity and cost for developing and producing chainsaws. To identify which model would be best suited for this study a literature study was performed to assess which model could potentially provide the best performance. This literature study showed that logistic regression held the largest potential in a chainsaw lubrication system due to its use in parallel research topics and its performance on other machine learning tasks. 

The chainsaw lubrication system made use of an existing Husqvarna chainsaw with a vibration sensor attached to it to see when the chainsaw stops, which would tell valuable information about the lubrication of the chainsaw. In order to adequately evaluate when oil needed to be added data was obtained, which was used to train the model. Once the model was trained the system needed to be verified. The verification process encompassed two tests: a validation test to assess the model's accuracy and an empirical test to confirm its suitability for the study. The results of the verification process demonstrated the appropriateness of the logistic regression method for integrating the oil pump system and the vibration sensor. With the system demonstrating an accuracy of 93.94%. However, it is important to note that these tests were performed under controlled conditions and with limited data and more work is needed to fully verify and develop a working system. This does show that a vibration sensor, logistic regression lubrication system could be possible showing the potential of it to reduce cost and complexity.