Power battery self-discharge abnormity identification model based on deep belief network

You are here: Homepage > Search

Power battery self-discharge abnormity identification model based on deep belief network

Free access

WAN XINMING / YAN WEN / WANG PENG / CAO XI / WANG XINGYUE / LIANG XINMIAO / HU QINGAO / WU ERDONG / MA LIUKE / FENG SONG / ... [more]

Abstract

The invention relates to the technical field of power batteries, and discloses a power battery self-discharge anomaly identification model based on a deep belief network, comprising the following construction steps: S1, constructing a reference data set for model training and verification; the reference data set comprises historical operation data of the vehicle; when the reference data set is constructed, a preset fault identification strategy is adopted to carry out fault identification on the historical operation data of the vehicle, and a fault identification result is used as a label to calibrate the historical operation data of the vehicle; s2, dividing the reference data set into a training set and a verification set, and training the anomaly recognition model; a DBN network is arranged in the anomaly recognition model; and S3, outputting the trained anomaly recognition model. The vehicle safety state can be accurately and efficiently recognized, and accurate judgment and fault recognition of the comprehensive state of the vehicle are achieved.

本发明涉及动力电池技术领域，公开了一种基于深度置信网络的动力电池自放电异常识别模型，包括以下构建步骤：S1，构建用于模型训练与验证的参考数据集；所述参考数据集中包括车辆历史运行数据；在构建参考数据集时，还采用预设的故障识别策略对车辆历史运行数据进行故障识别，并将故障识别结果作为标签，对车辆历史运行数据进行标定；S2，将参考数据集划分为训练集和验证集，对异常识别模型进行训练；所述异常识别模型中设有DBN网络；S3，输出训练后的异常识别模型。本发明能够准确且高效地识别车辆安全状态，实现对车辆综合状态的精准判定与故障识别。

Access

Download

Export, share and cite

Document information

Title :

Power battery self-discharge abnormity identification model based on deep belief network

Additional title:

一种基于深度置信网络的动力电池自放电异常识别模型

Contributors:

WAN XINMING (author) / YAN WEN (author) / WANG PENG (author) / CAO XI (author) / WANG XINGYUE (author) / LIANG XINMIAO (author) / HU QINGAO (author) / WU ERDONG (author) / MA LIUKE (author) / FENG SONG (author)

Publication date :

2024-03-22

Type of media :

Patent

Type of material :

Electronic Resource

Language :

Chinese

Classification :

IPC:

G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / B60L PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES , Antrieb von elektrisch angetriebenen Fahrzeugen / G01R Messen elektrischer Größen , MEASURING ELECTRIC VARIABLES / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen