Method for Event Detection in Mechatronic Systems Using Deep Learning

Sammanfattning: Artificial Intelligence and Deep Learning are new drivers for technological change, and finds their way into more and more applications. These technologies have the ability to learn com-plex tasks previously hard to automate. In this thesis, the usage of deep learning is applied and evaluated in the context of product assembly where components are joined together. The specific problem studied is the process of clamping by using threaded fasteners. The thesis evaluates several deep learning models, such as Recurrent Neural Networks (RNN), Long Short-Term Memory Neural Networks (LSTM) and Convolutional Neural Networks (CNN), and presents a new method for estimating the rotational angle at which the fastener mates with the material, also called snug-angle, using a combined detection-by-classification and regression approach with stacked LSTM neural networks. The method can be imple-mented to make precision clamping using angle tightening instead of torque tightening. Thistightening method offers an increase in clamp force accuracy, from ±43% to ±17%. Various estimation methods and inference frequencies are evaluated to offer insight in the lim-itations of the model. The top method achieves a precision of 0.05 2.35¶ when estimating the snug-angle and can classify where the snug-angle occurs wi≠th 99.±26% accuracy. The thesis also takes into account the demanding requirements of an implementation on mechatronic systems and presents advantages and disadvantages of the state-of-the-art model compression methods used to achieve a lightweight and efficient algorithm. Usage of these methods can give compression rates, energy efficiency and speed that are in the order of 10◊ to 100◊ compared to the original model, without loss of performance.