一种基于多层前馈神经网络的储能电站智能监测方法

• Format: Patent
• Language: Chinese
• Published: 07.02.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIRCHEMICAL OR PHYSICAL PROPERTIES; MEASURING; MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR; TESTING; TESTING STATIC OR DYNAMIC BALANCE OF MACHINES ORSTRUCTURES; TESTING STRUCTURES OR APPARATUS NOT OTHERWISE PROVIDED FOR

本发明公开了一种基于多层前馈神经网络的储能电站智能监测方法，涉及储能电站监测技术领域。本发明步骤如下：传感器在不同测点采集气体的浓度信号，形成三种气体浓度的时空矩阵；将每个传感器的浓度时间序列构造对应的Hankel矩阵，再提取该矩阵的奇异值作为放电的特征值；将去噪后的二维浓度矩阵在特定时间断面上进行插值并进行归一化处理得到三种气体的综合浓度指标；将归一化后的数据作为测试集输入神经网络，通过输出的行号和列号判断泄露位置。本发明通过监测三种热失控后主要气体的浓度变化实现电池组热失控的精确预警，并采用Hankel矩阵奇异值分解的方法，在滤波的同时也提高了信号处理的效率，快速计算出泄漏源位置。 The invention discloses an energy storage power station intelligent monitoring method based on a multilayer feedforward neural network, and relates to the technical field of energy storage power station monitoring. The method comprises the following steps: a sensor collects concentration signals of gas at different measuring points to form a space-time matrix of three gas concentrations; constructing a corresponding Hankel matrix according to the concentration time sequence of each sensor, and extracting a singular value of the matrix as a characteristic value of discharge; carrying out interpolation on the denoised two-dimensional concentration matrix on a specific time section, and carrying out normalization process