Rajeswaran Nagalingam, Thangaraj Rajesh, Mihet-Popa Lucian, Krishna Vajjala Kesava Vamsi, Özer Özen
Electrical and Electronics Engineering, Malla Reddy Engineering College, Secunderabad 500100, India.
Faculty of Information Technology, Engineering, and Economics, Oestfold University College, 1757 Halden, Norway.
Micromachines (Basel). 2022 Apr 23;13(5):663. doi: 10.3390/mi13050663.
In modern industrial manufacturing processes, induction motors are broadly utilized as industrial drives. Online condition monitoring and diagnosis of faults that occur inside and/or outside of the Induction Motor Drive (IMD) system make the motor highly reliable, helping to avoid unscheduled downtimes, which cause more revenue loss and disruption of production. This can be achieved only when the irregularities produced because of the faults are sensed at the moment they occur and diagnosed quickly so that suitable actions to protect the equipment can be taken. This requires intelligent control with a high-performance scheme. Hence, a Field Programmable Gate Array (FPGA) based on neuro-genetic implementation with a Back Propagation Neural network (BPN) is suggested in this article to diagnose the fault more efficiently and almost instantly. It is reported that the classification of the neural network will provide the output within 2 µs although the clone procedure with microcontroller requires 7 ms. This intelligent control with a high-performance technique is applied to the IMD fed by a Voltage Source Inverter (VSI) to diagnose the fault. The proposed approach was simulated and experimentally validated.
在现代工业制造过程中，感应电动机被广泛用作工业驱动器。对感应电动机驱动（IMD）系统内部和/或外部出现的故障进行在线状态监测和诊断，可使电动机具有高度可靠性，有助于避免意外停机，因为意外停机会导致更多的收入损失和生产中断。只有当故障产生的异常在发生时被检测到并迅速诊断出来，以便采取适当的措施保护设备，才能实现这一点。这需要采用高性能方案的智能控制。因此，本文提出了一种基于现场可编程门阵列（FPGA）的神经遗传实现方法，并结合反向传播神经网络（BPN），以更高效、几乎即时地诊断故障。据报道，尽管使用微控制器的克隆过程需要7毫秒，但神经网络的分类将在2微秒内提供输出。这种采用高性能技术的智能控制应用于由电压源逆变器（VSI）供电的IMD，以诊断故障。对所提出的方法进行了仿真和实验验证。
