CN110516988A - One kind being fitted Power Material method based on neural network - Google Patents

One kind being fitted Power Material method based on neural network Download PDF

Info

Publication number
CN110516988A
CN110516988A CN201910610517.5A CN201910610517A CN110516988A CN 110516988 A CN110516988 A CN 110516988A CN 201910610517 A CN201910610517 A CN 201910610517A CN 110516988 A CN110516988 A CN 110516988A
Authority
CN
China
Prior art keywords
neural network
goods
materials
sorting
material method
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201910610517.5A
Other languages
Chinese (zh)
Inventor
吴健超
胡旭光
朱晓程
葛军萍
章伟勇
吴建锋
丁宏琳
金从友
王婧
胡恺锐
王筠琛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Corp of China SGCC
State Grid Zhejiang Electric Power Co Ltd
Jinhua Power Supply Co of State Grid Zhejiang Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
State Grid Zhejiang Electric Power Co Ltd
Jinhua Power Supply Co of State Grid Zhejiang Electric Power Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by State Grid Corp of China SGCC, State Grid Zhejiang Electric Power Co Ltd, Jinhua Power Supply Co of State Grid Zhejiang Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN201910610517.5A priority Critical patent/CN110516988A/en
Publication of CN110516988A publication Critical patent/CN110516988A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Abstract

The invention discloses one kind to be fitted Power Material method based on neural network.Method includes determining neural network structure, is trained to neural network；Goods and materials type is checked by neural network fitting algorithm according to goods and materials image；According to goods and materials data, pass through neural network fitting algorithm, output sort state value；Judge that goods and materials sort state according to sorting state value.Goods and materials type and quantity are checked by neural network fitting algorithm, and quantity when quantity backtracking storage is neutralized according to sorting, error amount is calculated by algorithm, and sorting state is judged by setting shape.The accuracy of sorting can be accurately detected, effectively outbound sorting is monitored.

Description

One kind being fitted Power Material method based on neural network
Technical field
The present invention relates to sorting monitoring technologies, are fitted Power Material side based on neural network more particularly, to a kind of Method.
Background technique
Many power equipments storages and sorting at present is all and to be easy to make during manual operation by manually being operated It at mistake or fails to register, so that the goods and materials of sorting and the goods and materials of storage form mistake.
Summary of the invention
The present invention mainly solves above-mentioned the problems of the prior art, provides a kind of based on neural network fitting electric power object Capital's method.
Above-mentioned technical problem of the invention is mainly to be addressed by following technical proposals: one kind is based on neural network It is fitted Power Material method, comprising the following steps:
S1. it determines neural network structure, neural network is trained；
S2. goods and materials type is checked by neural network fitting algorithm according to goods and materials image；
S3. according to goods and materials data, pass through neural network fitting algorithm, output sort state value；
S4. judge that goods and materials sort state according to sorting state value.
The present invention checks goods and materials type and quantity by neural network fitting algorithm, according to sorting neutralize quantity recall into Quantity when library calculates error amount by algorithm, and judges sorting state by setting shape.The present invention can be detected accurately The accuracy of sorting is effectively monitored outbound sorting.
As a preferred embodiment, the detailed process of step S1 includes:
Determine that neural network includes CNN neural network and RBF neural；
Goods and materials image is collected as training set, CNN neural network is imported and is trained；
Document, sensing data and the historical weight data of goods and materials are collected as training set, RBF neural is imported and is instructed Practice.
As a preferred embodiment, the detailed process of step S2 includes:
The goods and materials image of input sorting obtains matched goods and materials title by CNN neural network image fitting algorithm；
As a preferred embodiment, the detailed process of step S3 includes:
Associated task document information, sensing data, historical weight data are inputted, by RBF neural fitting algorithm, is obtained Sort error amount K；
As a preferred embodiment, the detailed process of step S4 includes:
S41. sorting task correctness section is preset,
K < 0-n*a is correct
N*a < K < n*2a pays attention to
K > n*2a is abnormal；
S42. the K value of acquisition is compared with degree of striving for section, according to the section that K value is fallen into, obtains sorting state.
Therefore, the invention has the advantages that goods and materials type and quantity are checked by neural network fitting algorithm, according to sorting Quantity when quantity backtracking storage is neutralized, error amount is calculated by algorithm, and sorting state is judged by setting shape.It can The accuracy of accurate detection sorting, is effectively monitored outbound sorting.
Detailed description of the invention
Fig. 1 is flow diagram in the present invention.
Specific embodiment
Below with reference to the embodiments and with reference to the accompanying drawing the technical solutions of the present invention will be further described.
Embodiment:
The present embodiment one kind is based on neural network and is fitted Power Material method, as shown in Figure 1, include the following steps,
S1. it determines neural network structure, neural network is trained；Detailed process includes:
Determine that neural network includes CNN neural network and RBF neural；
Goods and materials image is collected as training set, CNN neural network is imported and is trained；
Document, sensing data and the historical weight data of goods and materials are collected as training set, RBF neural is imported and is instructed Practice.
S2. goods and materials type is checked by neural network fitting algorithm according to goods and materials image；Detailed process includes:
The goods and materials image of input sorting obtains matched goods and materials title by CNN neural network image fitting algorithm；
S3. according to goods and materials data, pass through neural network fitting algorithm, output sort state value；Detailed process includes:
Associated task document information, sensing data, historical weight data are inputted, by RBF neural fitting algorithm, is obtained Sort error amount K；
S4. judge that goods and materials sort state according to sorting state value.Detailed process includes:
S41. sorting task correctness section is preset,
K < 0-n*a is correct
N*a < K < n*2a pays attention to
K > n*2a is abnormal；
S42. the K value of acquisition is compared with degree of striving for section, according to the section that K value is fallen into, obtains sorting state.
Specific embodiment described herein is only an example for the spirit of the invention.The neck of technology belonging to the present invention The technical staff in domain can make various modifications or additions to the described embodiments or replace by a similar method In generation, however, it does not deviate from the spirit of the invention or beyond the scope of the appended claims.

Claims (5)

1. one kind is fitted Power Material method based on neural network, it is characterised in that: the following steps are included:
S1. it determines neural network structure, neural network is trained；
S2. goods and materials type is checked by neural network fitting algorithm according to goods and materials image；
S3. according to goods and materials data, pass through neural network fitting algorithm, output sort state value；
S4. judge that goods and materials sort state according to sorting state value.
2. it is according to claim 1 a kind of based on neural network fitting Power Material method, it is characterized in that the tool of step S1 Body process includes:
Determine that neural network includes CNN neural network and RBF neural；
Goods and materials image is collected as training set, CNN neural network is imported and is trained；
Document, sensing data and the historical weight data of goods and materials are collected as training set, RBF neural is imported and is instructed Practice.
3. it is according to claim 1 a kind of based on neural network fitting Power Material method, it is characterized in that the tool of step S2 Body process includes:
The goods and materials image of input sorting obtains matched goods and materials title by CNN neural network image fitting algorithm.
4. it is according to claim 1 a kind of based on neural network fitting Power Material method, it is characterized in that the tool of step S3 Body process includes:
Associated task document information, sensing data, historical weight data are inputted, by RBF neural fitting algorithm, is obtained Sort error amount K.
5. it is according to claim 1 a kind of based on neural network fitting Power Material method, it is characterized in that the tool of step S4 Body process includes:
S41. sorting task correctness section is preset,
K < 0-n*a is correct
N*a < K < n*2a pays attention to
K > n*2a is abnormal；
S42. the K value of acquisition is compared with degree of striving for section, according to the section that K value is fallen into, obtains sorting state.
CN201910610517.5A 2019-07-08 2019-07-08 One kind being fitted Power Material method based on neural network Pending CN110516988A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910610517.5A CN110516988A (en) 2019-07-08 2019-07-08 One kind being fitted Power Material method based on neural network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910610517.5A CN110516988A (en) 2019-07-08 2019-07-08 One kind being fitted Power Material method based on neural network

Publications (1)

Publication Number Publication Date
CN110516988A true CN110516988A (en) 2019-11-29

Family

ID=68623791

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910610517.5A Pending CN110516988A (en) 2019-07-08 2019-07-08 One kind being fitted Power Material method based on neural network

Country Status (1)

Country Link
CN (1) CN110516988A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116273908A (en) * 2023-04-24 2023-06-23 天津万事达物流装备有限公司 Goods shelves letter sorting system based on intelligence is made

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106470122A (en) * 2016-09-20 2017-03-01 北京汇通金财信息科技有限公司 A kind of network failure locating method and device
CN107103441A (en) * 2017-04-21 2017-08-29 美林数据技术股份有限公司 Power Material sorting technique based on Self-Organizing Feature Maps
CN108805216A (en) * 2018-06-19 2018-11-13 合肥工业大学 Face image processing process based on depth Fusion Features
US20180341849A1 (en) * 2017-05-25 2018-11-29 International Business Machines Corporation Two-terminal metastable mixed-conductor memristive devices
CN109420622A (en) * 2017-08-27 2019-03-05 南京理工大学 Tobacco leaf method for sorting based on convolutional neural networks

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106470122A (en) * 2016-09-20 2017-03-01 北京汇通金财信息科技有限公司 A kind of network failure locating method and device
CN107103441A (en) * 2017-04-21 2017-08-29 美林数据技术股份有限公司 Power Material sorting technique based on Self-Organizing Feature Maps
US20180341849A1 (en) * 2017-05-25 2018-11-29 International Business Machines Corporation Two-terminal metastable mixed-conductor memristive devices
CN109420622A (en) * 2017-08-27 2019-03-05 南京理工大学 Tobacco leaf method for sorting based on convolutional neural networks
CN108805216A (en) * 2018-06-19 2018-11-13 合肥工业大学 Face image processing process based on depth Fusion Features

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116273908A (en) * 2023-04-24 2023-06-23 天津万事达物流装备有限公司 Goods shelves letter sorting system based on intelligence is made
CN116273908B (en) * 2023-04-24 2023-09-19 天津万事达物流装备有限公司 Goods shelves letter sorting system based on intelligence is made

Similar Documents

Publication Publication Date Title
WO2023071217A1 (en) Multi-working-condition process industrial fault detection and diagnosis method based on deep transfer learning
EP2905665B1 (en) Information processing apparatus, diagnosis method, and program
EP3444724B1 (en) Method and system for health monitoring and fault signature identification
CN104390657B (en) A kind of Generator Unit Operating Parameters measurement sensor fault diagnosis method and system
US10613153B2 (en) Method and apparatus for defect pre-warning of power device
US20060142990A1 (en) Information processor, state judging unit and diagnostic unit, information processing method, state judging method and diagnosing method
CN104677997B (en) A kind of transformer oil chromatographic on-line monitoring differentiation method for early warning
CN104913797A (en) Pointer type instrument number reading and recognition method and system
CN111069819A (en) Welding quality prediction system and method based on artificial intelligence
CN103824130A (en) Grain condition forecasting and early warning method and system based on SVM
CN109840805A (en) A kind of procurement price control method and system based on normal distribution model
CN111079978B (en) Coal and gas outburst prediction method based on logistic regression and reinforcement learning
CN105137376A (en) Fault diagnosis method for intermediate voltage sensor of locomotive traction current transformer
CN111833594B (en) Traffic flow prediction method, traffic flow prediction device, electronic device, and storage medium
CN115455746B (en) Nuclear power device operation monitoring data anomaly detection and correction integrated method
KR20170127430A (en) Method and system for detecting, classifying and / or mitigating sensor error
CN110276385A (en) Mechanical part remaining life prediction technique based on similitude
CN108287327A (en) Metering automation terminal fault diagnostic method based on Bayes&#39;s classification
CN102763047A (en) Method and system for diagnosing compressors
CN110516988A (en) One kind being fitted Power Material method based on neural network
CN111179576B (en) Power utilization information acquisition fault diagnosis method and system with inductive learning function
KR102618023B1 (en) Failure prediction diagnosis system and method through pattern analysis according to failure type
CN102419593B (en) Sensor fault diagnosis method based on data mining
CN105741184A (en) Transformer state evaluation method and apparatus
CN116502134A (en) Self-diagnosis early warning abnormal functional state identification system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20191129

RJ01 Rejection of invention patent application after publication