A novel adaptive cost-sensitive convolution neural network based dynamic imbalanced fault diagnosis framework for manufacturing processes

Abstract Due to the influences of sensor faults, communication lines, and human factors, it is difficult to collect and label fault data in large quantities, resulting in the imbalance between normal and fault data, and between fault and fault data. Those kinds of data imbalances violate the assumption of relatively balanced distribution of most traditional fault diagnosis methods. Associated with those trends, some imbalanced fault diagnosis methods have been put forward. However, most of those methods only consider that the proportion of various samples remains unchanged, that is, the imbalance rate is stable. In the actual manufacturing processes, the industrial data flows are fast, continuous, and dynamically changing. The imbalance rates of all kinds of samples often change continuously, showing the dynamic imbalanced characteristic. To solve this problem, a novel adaptive cost-sensitive convolution neural network based dynamic imbalanced fault diagnosis framework is designed for manufacturing processes. More specifically, a new adaptive cost-sensitive convolutional neural network is firstly constructed by coordinating the cross entropy loss function with a specific cost sensitive index, of which the dynamic imbalance rates and the diagnosis performance indicators are comprehensively considered. Subsequently, a dynamic time factor is reasonably designed and introduced to make the diagnosis model pay more attention to identification of new fault data in the industrial data flow, aiming at improving the fault diagnosis performance. Finally, sufficient simulation experiments are conducted by a typical manufacturing process, the hot rolling process, to demonstrate the superiority of the proposed framework compared with some classical algorithms.