A convolutional neural network approach on bead geometry estimation for a laser cladding system
Laser cladding is a complex manufacturing process which requires fine-tuning to achieve the desired geometry. In order to further understand this process, an automated method for clad bead final geometry estimation on a laser cladding system is proposed. To do so, six different convolutional neural network architectures were developed to analyze the process’ molten pool image acquired by a 50-fps coaxial camera. Those networks receive both the camera image and the process parameters as inputs, yielding width and height of the clad beads as outputs. The results of the network’s performances show testing error mean values as little as 8 µm for clad beads around a millimeter thick. In 95% of the cases, the error remained under 180 µm. Plots of the target versus the estimated values show coefficients of determination over 0.95 on the testing set. The architectures are then compared, and their performances are discussed. Deeper convolutional layers far exceeded the performance of shallower ones, nonetheless, deeper densely connected layers decreased the performances of the networks when compared to shallower ones. Those results represent yet another alternative on intelligent process monitoring with potential for real-time usage, taking the researches one step further into developing a closed loop control for this process.