CN111401425A - Non-invasive electrical cluster load electrical performance autonomous learning processing method - Google Patents
Non-invasive electrical cluster load electrical performance autonomous learning processing method Download PDFInfo
- Publication number
- CN111401425A CN111401425A CN202010165815.0A CN202010165815A CN111401425A CN 111401425 A CN111401425 A CN 111401425A CN 202010165815 A CN202010165815 A CN 202010165815A CN 111401425 A CN111401425 A CN 111401425A
- Authority
- CN
- China
- Prior art keywords
- neural network
- electrical
- basic
- network model
- model
- 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
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 11
- 239000013598 vector Substances 0.000 claims abstract description 41
- 238000000034 method Methods 0.000 claims abstract description 28
- 238000003062 neural network model Methods 0.000 claims abstract description 24
- 238000012549 training Methods 0.000 claims abstract description 12
- 230000001537 neural effect Effects 0.000 claims abstract description 8
- 238000012216 screening Methods 0.000 claims abstract description 4
- 230000006870 function Effects 0.000 claims description 27
- 210000002569 neuron Anatomy 0.000 claims description 18
- 238000013528 artificial neural network Methods 0.000 claims description 17
- 230000004913 activation Effects 0.000 claims description 7
- 230000005284 excitation Effects 0.000 claims description 3
- 230000001131 transforming effect Effects 0.000 claims 1
- 230000008569 process Effects 0.000 description 7
- 238000004590 computer program Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013144 data compression Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
- G06F18/2113—Selection of the most significant subset of features by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a non-invasive electrical cluster load electrical performance autonomous learning processing method, which relates to the technical field of electric power, and comprises the steps of establishing a feature vector library of electrical load signals by standardizing different types of electrical load signals, normalizing feature values corresponding to feature vectors in the feature vector library, screening the feature vectors of the feature vectors in the feature vector library by adopting a multi-stage classification method, establishing a basic network neural model, inputting the feature vector library into the basic neural network model as training data, training the basic neural network model, and generating the trained neural network model.
Description
Technical Field
The invention relates to the technical field of electric power, in particular to a non-invasive electric cluster load electric performance autonomous learning processing method.
Background
At present, there are many methods for detecting, analyzing and evaluating the performance of electrical equipment, but the learning and accumulation of the performance identification capability of electrical equipment are still in the manual maintenance stage. Therefore, although the analysis and evaluation of the performance of the electrical equipment can be met, blind areas are inevitably formed through manual maintenance, and due to the fact that the parameter calculation capacity set manually and the breadth and the dimensionality of data processing are limited, the performance of the electrical equipment is not completely identified, and the accuracy of identifying the performance of the electrical equipment is low.
Disclosure of Invention
In order to solve the defects of the prior art, the embodiment of the invention provides a non-intrusive type electrical cluster load electrical performance autonomous learning processing method.
The non-invasive electrical cluster load electrical performance autonomous learning processing method provided by the embodiment of the invention comprises the following steps:
standardizing different types of electric load signals, and establishing a characteristic vector library of the electric load signals;
normalizing the characteristic values corresponding to the characteristic vectors in the characteristic vector library;
screening each feature vector of each feature vector in the feature vector library by adopting a multi-stage classification method;
establishing a basic network neural model, comprising:
selecting a BP neural network as a basic network neural model;
determining a hidden layer of the BP neural network, wherein the number a of hidden layer neurons of the BP neural network and the number b of input layer neurons have a relation: a is 2b + 1;
modeling a neuron with n inputs, X ═ X (X)1,x2,……xn) As input to the input layer neurons of the BP neural network;
changing W to (W)1,w2,w3……wn) As a signal offset signal, the signal offset signal is used for establishing an excitation threshold of a neuron, and u and f are respectively used as a basis function and an activation function of the neuron, wherein the basis function u is a multi-input single-output function, u equals to u (), the activation function f has the function of squeezing the output of the basis function, y equals to f (u), namely u is transformed into a specified range through a nonlinear function f;
and inputting the characteristic vector library serving as training data into a basic neural network model, training the basic neural network model, generating a trained neural network model, and finishing the autonomous learning of the electrical performance of the non-invasive power load signal.
Preferably, after generating the trained neural network model, the method further comprises:
and revising the parameters of each module in the basic neural network model by using the neural network model.
Preferably, the electrical load signals of the different loads comprise:
different loads, different performance of each component, different life cycles of the electrical load signal.
The non-invasive electrical cluster load electrical performance autonomous learning processing method provided by the embodiment of the invention has the following beneficial effects:
the method and the device realize the independent learning of the electrical performance of the electrical load signal and improve the accuracy of electrical equipment performance identification.
Detailed Description
The present invention will be described in detail with reference to the following embodiments.
The non-invasive electrical cluster load electrical performance autonomous learning processing method provided by the embodiment of the invention comprises the following steps:
s101, standardizing different types of electric load signals, and establishing a feature vector library of the electric load signals.
As a specific embodiment, any electrical equipment and corresponding components are unified into a model, which facilitates subsequent manual learning and autonomous learning, and even facilitates simplification of data collection. The unified standardized format is: identification code, description, feature set, current performance value, current performance versus host influence, set of indirect impact objects.
The above is a model description, and the definitions of two of the sets are described next.
The characteristic set comprises characteristic identification codes, characteristic descriptions, characteristic values, characteristic weights, characteristic influence degrees, characteristic ranges, characteristic correction values and characteristic deviations, and the indirect influence object set comprises object descriptions and brief influence degrees.
Through the definition, the method can be defined aiming at the type of the power load signal, and all parameters are mutually restricted, mutually influenced and in accordance with reality to form a tree-shaped cross-correlation performance network, thereby being convenient for the description and the operation of the problems.
S102, normalizing the characteristic values corresponding to the characteristic vectors in the characteristic vector library.
S103, screening each feature vector of each feature vector in the feature vector library by adopting a multi-stage classification method.
S104, establishing a basic network neural model, including:
s1041, selecting a BP neural network as a basic network neural model; the basic neural network is completed by adopting a BP neural network algorithm, and the BP neural network has the main purposes that:
(1) approximating the function: training a network to approximate a function using the input vectors and corresponding output vectors;
(2) pattern recognition: associating it with the input vector with a particular output vector;
(3) and (4) classification: classifying the input vector in a defined suitable manner;
(4) data compression: the output vector dimension is reduced for ease of transmission and storage.
S1042, determining the hidden layer of the BP neural network, wherein the number a of the hidden layer neurons of the BP neural network and the number b of the input layer neurons have a relation: a is 2b + 1;
s1043, changing the neuron model X with n inputs to (X)1,x2,……xn) As input to the input layer neurons of the BP neural network;
s1044, changing W to (W)1,w2,w3……wn) And as a signal offset signal, the signal offset signal is used for establishing an excitation threshold of the neuron, and u and f are respectively used as a basis function and an activation function of the neuron, wherein the basis function u is a multi-input single-output function, u is equal to u (), the activation function f has the function of squeezing the output of the basis function, and y is equal to f (u), namely, u is transformed into a specified range through a nonlinear function f.
And S105, inputting the characteristic vector library serving as training data into the basic neural network model, training the basic neural network model, generating the trained neural network model, and finishing the autonomous learning of the electrical performance of the non-invasive power load signal.
Wherein units (and corresponding connections) are randomly removed from the neural network during the training process, thus preventing over-adaptation between units. In the training process, samples are removed from the network with exponentially different "sparsity". In the testing stage, the prediction results of the sparse networks are easily approximated by averaging the prediction results of the sparse networks by using a single unwrapped network with a smaller weight, which can effectively avoid overfitting and can obtain greater performance improvement compared with other regularization methods. Dropout technology has been demonstrated to improve neural network performance in supervised learning tasks in the areas of computer vision, speech recognition, text classification, and computational biology, with the best results in multiple benchmark datasets.
Optionally, after generating the trained neural network model, the method further comprises:
and modifying the parameters of each module in the basic neural network model by using the neural network model.
Optionally, the electrical load signals of the different loads comprise:
different loads, different performance of each component, different life cycles of the electrical load signal.
According to the non-invasive electrical cluster load electrical performance autonomous learning processing method provided by the embodiment of the invention, different types of electrical load signals are standardized, the feature vector library of the electrical load signals is established, the feature values corresponding to the feature vectors in the feature vector library are normalized, a multi-stage classification method is adopted to screen the feature vectors of the feature vectors in the feature vector library, a basic network neural model is established, the feature vector library is used as training data to be input into the basic neural network model, the basic neural network model is trained, and the trained neural network model is generated, so that the electrical performance of the electrical load signals is autonomously learned, and the accuracy of electrical equipment performance recognition is improved.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
It will be appreciated that the relevant features of the method and apparatus described above are referred to one another. In addition, "first", "second", and the like in the above embodiments are for distinguishing the embodiments, and do not represent merits of the embodiments.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In addition, the memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (3)
1. A non-intrusive electrical cluster load electrical performance autonomous learning processing method is characterized by comprising the following steps:
standardizing different types of electric load signals, and establishing a characteristic vector library of the electric load signals;
normalizing the characteristic values corresponding to the characteristic vectors in the characteristic vector library;
screening each feature vector of each feature vector in the feature vector library by adopting a multi-stage classification method;
establishing a basic network neural model, comprising:
selecting a BP neural network as a basic network neural model;
determining a hidden layer of the BP neural network, wherein the number a of hidden layer neurons of the BP neural network and the number b of input layer neurons have a relation: a is 2b + 1;
modeling a neuron with n inputs, X ═ X (X)1,x2,……xn) As input for the input layer neurons of the BP neural network, wherein the neuron model X ═ X1,x2,……xn) Is adjustable;
changing W to (W)1,w2,w3……wn) As signal offset signals for establishing excitation thresholds of neuronsTaking u and f as a basis function and an activation function of the neuron respectively, wherein the basis function u is a multi-input single-output function, the activation function f has the function of squeezing the output of the basis function u, and y ═ f (u) is used for transforming the basis function u into a specified range through the activation function f;
and inputting the characteristic vector library serving as training data into a basic neural network model, training the basic neural network model, generating a trained neural network model, and finishing the autonomous learning of the electrical performance of the non-invasive power load signal.
2. The non-intrusive electrical trunked load electrical performance autonomous learning processing method of claim 1, wherein after generating the trained neural network model, the method further comprises:
and revising the parameters of each module in the basic neural network model by using the neural network model.
3. The method of claim 1, wherein the electrical load signals of different loads comprise:
different loads, different performance of each component, different life cycles of the electrical load signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010165815.0A CN111401425A (en) | 2020-03-11 | 2020-03-11 | Non-invasive electrical cluster load electrical performance autonomous learning processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010165815.0A CN111401425A (en) | 2020-03-11 | 2020-03-11 | Non-invasive electrical cluster load electrical performance autonomous learning processing method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111401425A true CN111401425A (en) | 2020-07-10 |
Family
ID=71436211
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010165815.0A Pending CN111401425A (en) | 2020-03-11 | 2020-03-11 | Non-invasive electrical cluster load electrical performance autonomous learning processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111401425A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023201820A1 (en) * | 2022-04-18 | 2023-10-26 | 石家庄科林电气股份有限公司 | Non-intrusive load identification method based on bp neural network model |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015210747A (en) * | 2014-04-30 | 2015-11-24 | 国立研究開発法人情報通信研究機構 | Learning system and learning method of hierarchical neural network |
| CN106093652A (en) * | 2016-07-07 | 2016-11-09 | 天津求实智源科技有限公司 | A kind of non-intrusive electrical load monitoring System and method for possessing self-learning function |
| CN109685265A (en) * | 2018-12-21 | 2019-04-26 | 积成电子股份有限公司 | A kind of prediction technique of power-system short-term electric load |
| CN110543932A (en) * | 2019-08-12 | 2019-12-06 | 珠海格力电器股份有限公司 | air conditioner performance prediction method and device based on neural network |
-
2020
- 2020-03-11 CN CN202010165815.0A patent/CN111401425A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015210747A (en) * | 2014-04-30 | 2015-11-24 | 国立研究開発法人情報通信研究機構 | Learning system and learning method of hierarchical neural network |
| CN106093652A (en) * | 2016-07-07 | 2016-11-09 | 天津求实智源科技有限公司 | A kind of non-intrusive electrical load monitoring System and method for possessing self-learning function |
| CN109685265A (en) * | 2018-12-21 | 2019-04-26 | 积成电子股份有限公司 | A kind of prediction technique of power-system short-term electric load |
| CN110543932A (en) * | 2019-08-12 | 2019-12-06 | 珠海格力电器股份有限公司 | air conditioner performance prediction method and device based on neural network |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023201820A1 (en) * | 2022-04-18 | 2023-10-26 | 石家庄科林电气股份有限公司 | Non-intrusive load identification method based on bp neural network model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11741361B2 (en) | Machine learning-based network model building method and apparatus | |
| Arteaga et al. | Deep learning for power system security assessment | |
| Kim et al. | Classification of steel surface defect using convolutional neural network with few images | |
| CN110008082B (en) | Abnormal task intelligent monitoring method, device, equipment and storage medium | |
| US20200286095A1 (en) | Method, apparatus and computer programs for generating a machine-learning system and for classifying a transaction as either fraudulent or genuine | |
| Kim et al. | Multi-class classifier-based adaboost algorithm | |
| WO2020078235A1 (en) | Boosting ai identification learning | |
| CN111366800A (en) | Non-invasive intelligent identification method for electrical load | |
| CN116662817A (en) | Asset identification method and system of Internet of things equipment | |
| Sarangpure et al. | Automating the Machine Learning Process using PyCaret and Streamlit | |
| CN111401425A (en) | Non-invasive electrical cluster load electrical performance autonomous learning processing method | |
| CN115239946A (en) | Small sample transfer learning training and target detection method, device, equipment and medium | |
| EP3973501A1 (en) | Dynamic image resolution assessment | |
| KR20200038072A (en) | Entropy-based neural networks partial learning method and system | |
| JP2023523426A (en) | Abnormal wafer image classification | |
| Porwik et al. | Detection of data drift in a two-dimensional stream using the Kolmogorov-Smirnov test | |
| CN117589233A (en) | Intelligent detection method and system for running state of relay protection device | |
| Heger et al. | Anomaly detection in formed sheet metals using convolutional autoencoders | |
| CN113012088A (en) | Circuit board fault detection and twin network training method, device and equipment | |
| CN111709766A (en) | User behavior prediction method and device, storage medium and electronic equipment | |
| CN115661595A (en) | Multi-model dynamic fusion method in deep learning object detection and storage medium | |
| Aldosari et al. | Image-Based Partial Discharge Identification in High Voltage Cables Using Hybrid Deep Network | |
| Han et al. | Using source code and process metrics for defect prediction-A case study of three algorithms and dimensionality reduction. | |
| Mansour et al. | Focal Point of Learning | |
| Tejale et al. | Performance evaluation of algorithms for gender classification |
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 |