Online dynamic sensing method for energy routing equipment based on deep self-encoding network
A self-encoding network and state-aware technology, applied in the field of online dynamic perception of energy routing equipment, can solve the problems of many types of monitoring data, large quantities, and low efficiency of state monitoring
Active Publication Date: 2021-04-20
南方电网人工智能科技有限公司
View PDF7 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The present invention provides an online dynamic perception method for energy routing equipment based on a deep self-encoding network, which aims to solve the problems of the existing monitoring data types, large quantities, and low state monitoring efficiency of energy routing equipment in the existing energy Internet of Things, and the analysis of these problems. Data technical issues that put a lot of pressure on Energy IoT hub servers
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0044]The technical solution of the present invention will be described in detail with reference to the accompanying drawings.
[0045]Such asfigure 1 with2As shown, the present invention discloses an energy routing device based on a deep self-encoded network, including two parts: off-line model training and online state;
[0046]During offline model training, multivariate data fusion is performed from various historical monitoring data in the fully fault process in the same type of energy routing device, using the fused data to train deep self-coding network, computing energy routing equipment State feature indicatorY，And store the depth self-coding network model of training completion;
[0047]The implementation steps of the online state perception process are as follows:
[0048]Step 1: Collect the vibration frequency, temperature, voltage, current, and pressure data during the operation of the energy router, and categorize and store.
[0049]Step 2: The edge calculation processing is performed...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an online dynamic sensing method for energy routing equipment based on a deep self-encoding network. The online dynamic sensing method comprises an offline model training part and an online state sensing part, offline model training: training the deep self-encoding network by utilizing historical monitoring data of the energy routing equipment, and calculating state characteristic indexes of the energy routing equipment; the online state sensing process comprises the following steps: step 1, collecting index data during operation of the energy router; 2, processing the data acquired in the step 1 to obtain a state feature vector of the energy routing equipment; 3, calculating a state monitoring index of the energy routing equipment by using a deep self-encoding network model, and judging the state of the equipment; 4, if the equipment fails, adding the operation data of the equipment into a historical database, and recalculating the state characteristic indexes; and if the fault does not occur, continuously sensing. The method can be used for monitoring the operation state of the energy routing equipment on line, reducing the fault frequency and reducing the maintenance cost.
Description
Technical field[0001]The present invention relates to artificial intelligence and energy networking technology, and more particularly to an energy-sensing method of an energy routing device based on a deep self-encoded network.Background technique[0002]The Internet of Things passes through mass, multi-type high-precision sensors to connect different entities through the Internet architecture. The energy network is a general case of pannetting, which achieves multi-energy mutual conversion, intelligent monitoring and control functions by key technologies such as intelligent equipment state perception technology, smart human-computer interactive configuration techniques, and intelligent power saving control gateways.[0003]Energy routing equipment is the core device of the energy distribution, responsible for input, output, conversion, and storage of different energy carriers, ensuring that the security and stable operation of energy routing equipment is the weight, and the variety of ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): H04L12/26H04L12/24G06N3/04G06N3/08
Inventor 李鹏于力张斌姜臻姚森敬郭志诚陈煜敏陈浩敏敖榜
Owner 南方电网人工智能科技有限公司