Bearing fault diagnosis method for submersible motor in complex noise environment based on current signal

• Main Authors: YIN DIANKAI, FENG RUI, GAN YUAN, GUAN BOKAI, BAO XIAOHUA, QIU HAOTIAN
• Format: Patent
• Language: Chinese; English
• Published: 15.03.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; MEASURING; MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES; PHYSICS; TESTING; TESTING STATIC OR DYNAMIC BALANCE OF MACHINES ORSTRUCTURES; TESTING STRUCTURES OR APPARATUS NOT OTHERWISE PROVIDED FOR

The invention discloses a bearing fault diagnosis method for a submersible motor in a complex noise environment based on a current signal, and the method comprises the steps: constructing a single-phase fault current data set based on the obtaining of a single-phase current signal, constructing a one-dimensional convolutional neural network, and carrying out the optimization of the network through a loss function. The bearing of the submersible motor is easy to be damaged in various forms in the service life, due to the characteristics of non-observability and slow occurrence of bearing faults, diagnosis of the faults is always the key point of the industry, and the purpose of the invention is to carry out non-intrusive, more efficient and more timely fault diagnosis on the submersible motor. 本发明公开了一种基于电流信号的潜水电机复杂噪声环境下的轴承故障诊断方法，包括：基于获取单相电流信号，构建单相故障电流数据集，构建一维卷积神经网络，并通过损失函数进行对该网络的优化。潜水电机的轴承在其运行寿命中容易受到各种形式的损伤，由于轴承故障的不可观察性和缓慢发生的性质，对这类故障的诊断一直是工业界的重点，本发明的目的在于对潜水电机做非侵入式、更高效、更及时的故障诊断。