AI-based intelligent diagnosis method, system and device

Abstract

The present invention relates to the field of smart grids, in particular to an AI-based intelligent diagnosis method, system and device. The core is AI+IoT, which consists of standardized and industrialized IoT edge computing hardware devices plus customized AI modules, including: the collection unit of IoT devices collects power consumption data; the cloud platform trains AI models based on historical data, and uses new data to Constantly improve the AI ​​model dynamically, and the edge computing unit of the IoT device inputs the collected power consumption data into the trained artificial intelligence AI model to obtain relevant data. Realize the real-time prediction of governance, effectively improve the real-time monitoring level of abnormally exceeded energy indicators, and change the previous working mode of semi-manual system detection and manual verification to a fully automatic intelligent AI analysis mode. Finally, a new software and hardware form of cloud platform + edge computing equipment + smart field terminal + smart IoT chipset module will be realized, the user-side energy system and power distribution management system will be redefined, and the era of "software-defined energy" will be opened.

Description

technical field [0001] The invention relates to the field of smart grids, in particular to an AI-based intelligent diagnosis method, system and device. Background technique [0002] At present, the construction of the ubiquitous electric power Internet of Things is progressing steadily, and tasks in six major fields, including basic support, data sharing, and internal and external business, have been carried out successively. As one of the core economic and technical indicators of power grid enterprises, line loss reflects the operating costs and economic benefits of the enterprise. Strengthening line loss management is a long-term strategic task and systematic project for power grid enterprises. The smart grid is a multi-objective function constrained by balance. Its factors are numerous, the conditions are random, the line loss is changeable, and the causes are complex. Factors change dynamically, making physical modeling difficult. Manual experience and existing methods ...

AI Technical Summary

Problems solved by technology

[0008] 1. "Energy index management is not predictable" - the current energy index management system is mainly based on monitoring and data storage, a large amount of data does not play a role, and it is impossible to predict energy indexes in real time, so that it is impossible to accurately judge the abnormal situation of energy indexes;

[0009] 2. "Difficulty in diagnosing the cause of abnormal energy indicators" - most of the energy indicator management systems currently in use are based on data calculation, with weak analysis capabilities, and cannot accurately locate the real-time abnormalities of each station, equipment, line, station area, and user It is very difficult to manage energy indicators, and the diagnosis of abnormal energy indicators depends heavily on the professional level of personnel, and there are risks of misjudgment and missed judgment;

[0010] 3. "Governance decisions rely on manual work" - the current energy index management is at a semi-automated level, heavily dependent on manual experience and manual decision-making, and lacks effective technical and data support

[0011] 4. "Insufficient utilization of data value" - most of the current analysis work of energy index management relies on the linkage of major business systems. Insufficient value mining

Images