CN116629627A - Intelligent detection system of power transmission on-line monitoring device - Google Patents
Intelligent detection system of power transmission on-line monitoring device Download PDFInfo
- Publication number
- CN116629627A CN116629627A CN202310452186.3A CN202310452186A CN116629627A CN 116629627 A CN116629627 A CN 116629627A CN 202310452186 A CN202310452186 A CN 202310452186A CN 116629627 A CN116629627 A CN 116629627A
- Authority
- CN
- China
- Prior art keywords
- model
- data
- training
- machine learning
- prediction
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 35
- 238000012806 monitoring device Methods 0.000 title claims abstract description 25
- 238000001514 detection method Methods 0.000 title claims abstract description 14
- 238000012549 training Methods 0.000 claims abstract description 78
- 238000011156 evaluation Methods 0.000 claims abstract description 42
- 238000010801 machine learning Methods 0.000 claims abstract description 41
- 238000012545 processing Methods 0.000 claims abstract description 23
- 238000000034 method Methods 0.000 claims abstract description 22
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 20
- 230000008569 process Effects 0.000 claims abstract description 9
- 238000003745 diagnosis Methods 0.000 claims abstract description 8
- 238000009826 distribution Methods 0.000 claims description 20
- 238000012360 testing method Methods 0.000 claims description 18
- 238000005457 optimization Methods 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 10
- 238000013079 data visualisation Methods 0.000 claims description 7
- 238000012795 verification Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 5
- 238000002360 preparation method Methods 0.000 claims description 4
- 238000004321 preservation Methods 0.000 claims description 3
- 238000010200 validation analysis Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000012800 visualization Methods 0.000 claims description 3
- 230000005611 electricity Effects 0.000 claims 1
- 230000008439 repair process Effects 0.000 abstract description 4
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 238000003066 decision tree Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000009434 installation Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000012706 support-vector machine Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- QVFWZNCVPCJQOP-UHFFFAOYSA-N chloralodol Chemical compound CC(O)(C)CC(C)OC(O)C(Cl)(Cl)Cl QVFWZNCVPCJQOP-UHFFFAOYSA-N 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
-
- 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
-
- 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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- 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
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- 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
-
- 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
- G06N3/0985—Hyperparameter optimisation; Meta-learning; Learning-to-learn
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- 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
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Marketing (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Power Engineering (AREA)
- Game Theory and Decision Science (AREA)
- Biophysics (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Human Computer Interaction (AREA)
Abstract
The invention discloses an intelligent detection system of an on-line power transmission monitoring device, which comprises: and a data acquisition module: the power transmission on-line monitoring device is responsible for collecting data; and a data processing module: the method is responsible for processing the acquired data; machine learning model training module: the method is in charge of performing model training on the processed data by using a machine learning algorithm; model evaluation module: the method is responsible for evaluating the trained machine learning model; and a fault prediction module: is responsible for predicting and diagnosing future faults using the trained machine learning model. The invention can analyze and process the monitoring data and improve the intelligent level of the monitoring device, thereby realizing the prediction, diagnosis and repair of the power grid faults.
Description
Technical Field
The invention relates to the technical field of power transmission, in particular to an intelligent detection system of an on-line power transmission monitoring device.
Background
The power transmission on-line monitoring device is equipment for monitoring a power transmission line of a power system. The system is generally composed of a sensor, a data acquisition device, a data processing unit, a communication module and the like, can monitor parameters such as voltage, current, temperature, humidity, vibration and the like of a power transmission line in real time, and transmits data to a monitoring center or a control center for analysis and processing.
The power transmission on-line monitoring device has the main functions of improving the operation safety and reliability of the power system, preventing and avoiding line faults and guaranteeing the stable power supply of the power system. By means of real-time monitoring and data analysis of the power transmission line, abnormal conditions of the line can be timely found, occurrence of faults is predicted, timely maintenance and repair are conducted, accordingly influences of the faults on a power grid are reduced, and reliability and stability of the power grid are improved. However, the existing power transmission on-line monitoring device cannot predict, diagnose and repair the power transmission on-line monitoring device, so a system is urgently needed to solve the above problems.
Disclosure of Invention
In order to solve the problems, the invention provides an intelligent detection system of an on-line power transmission monitoring device.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
an intelligent detection system of an on-line power transmission monitoring device, comprising:
and a data acquisition module: the power transmission on-line monitoring device is responsible for collecting data; and a data processing module: the method is responsible for processing the acquired data; machine learning model training module: the method is in charge of performing model training on the processed data by using a machine learning algorithm; model evaluation module: the method is responsible for evaluating the trained machine learning model; and a fault prediction module: is responsible for predicting and diagnosing future faults using the trained machine learning model.
Further: the data processing module comprises the following steps:
data preprocessing: preprocessing the collected original data;
feature extraction: extracting features from the preprocessed data;
and (3) establishing a model: using a machine learning algorithm to build a model of the relationship between the feature vector and the grid fault;
prediction and diagnosis: predicting and diagnosing power grid faults by using the established model; according to the input of the feature vector, the model can predict whether a fault exists or not, and the type and the position of the fault are determined; outputting the prediction and diagnosis results through a user interface;
storing and managing data: and storing the processed data into a cloud platform for subsequent analysis and processing.
Further: the machine learning model training module comprises the following steps:
data preparation: dividing the processed data set into a training set, a verification set and a test set; the training set is used for training the model, the verification set is used for adjusting the model super-parameters, and the test set is used for evaluating the performance of the model;
feature selection: selecting the characteristics for training according to the importance and the relativity of the characteristics;
model selection: selecting a machine learning algorithm for training;
model training: training the model by using a training set and a selected machine learning algorithm; training comprises adjusting parameters of the model through an optimization algorithm to minimize errors of the model on a training set;
super parameter tuning: the super-parameters of the model are adjusted to improve the generalization capability of the model;
model evaluation: evaluating the trained model using the validation set;
model preservation: and saving the trained model to a local or cloud end for subsequent deployment and application.
Further: super parameter tuning includes:
step 1: determining a priori distribution of super parameters: selecting a prior distribution for each super parameter;
step 2: generating initial samples from the prior distribution: generating a certain number of samples according to the prior distribution, and using the samples for training and evaluating a model;
step 3: selecting an evaluation index: selecting an evaluation index according to the task type and the target of the model;
step 4: training and evaluating a model: training and evaluating the model by using an initial sample, and recording an evaluation result and training time of each group of super parameters;
step 5: the posterior probability is calculated according to a Bayes formula: according to a Bayes formula, the posterior probability of each group of super parameters is calculated and is used as the prior distribution of the next round of optimization;
step 6: selecting the following set of super parameters: selecting a next set of hyper-parameters in the posterior distribution using a gaussian process and using them to train and evaluate the model;
iterative optimization process: repeating the steps 4-6 until the preset optimization times are reached or the evaluation index reaches the optimal value.
Further: the model evaluation module comprises the following steps:
selecting an evaluation index: selecting an evaluation index according to specific application scenes and task requirements;
preparing a data set: dividing the data set into a training set and a testing set; the training set is used for training the model, and the testing set is used for evaluating the performance of the model;
loading a model: loading a trained machine learning model from a local or cloud;
prediction result: predicting by using the test set data, and comparing the prediction result with the real label;
calculating an evaluation index: calculating the performance of the model on the test set according to the selected evaluation index;
and (5) visualizing the result: visually displaying the evaluation result;
and (3) improving a model: and (5) improving and optimizing the model according to the evaluation result.
Further: the fault prediction module comprises the following steps:
data preprocessing: the collected data is subjected to cleaning, denoising and missing value processing pretreatment operation so as to improve the data quality;
feature extraction: according to specific application scenes and task demands, extracting meaningful features from the preprocessed data so as to be used for training and predicting a fault prediction model;
feature selection: selecting features useful for a prediction target from the extracted features, and removing redundant and useless features to improve the prediction performance of the model;
model selection: selecting a machine learning model for training and predicting according to specific application scenes and task requirements;
model training: training the selected machine learning model by using the data set after feature extraction and selection;
model parameter adjustment: according to the performance of the model on the training set, parameter adjustment is carried out on the model so as to improve the generalization capability and the prediction performance of the model;
model prediction: predicting the state of a future power transmission system by using the trained model so as to detect whether a fault risk exists;
visualization of results: and visually displaying the prediction result.
Further: the method also comprises a data visualization module: and the processed data and the prediction result are presented to the user in a visual form, so that the user can conveniently analyze and make decisions.
Compared with the prior art, the invention has the following technical progress:
the system performs model training and fault prediction by collecting data in the power transmission on-line monitoring device and utilizing a machine learning technology, so as to realize intelligent prediction, diagnosis and repair of power grid faults. Meanwhile, through data visualization, a user can conveniently conduct data analysis and decision, and the operation efficiency and safety of the power grid are improved.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention.
In the drawings:
FIG. 1 is a block diagram of a system of the present invention;
FIG. 2 is a flow chart of the super parameter tuning of the present invention.
Detailed Description
The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.
As shown in fig. 1, the present invention discloses an intelligent detection system of an on-line power transmission monitoring device, comprising: and a data acquisition module: and the power transmission on-line monitoring device is responsible for collecting data from the power transmission on-line monitoring device, including parameters such as voltage, current, temperature, humidity, vibration and the like, and transmitting the data to the data processing module.
And a data processing module: and the machine learning model training module is responsible for processing the acquired data, including preprocessing work such as data cleaning, data normalization and feature extraction, and then transmitting the processed data to the machine learning model training module.
Machine learning model training module: is responsible for model training of the processed data using machine learning algorithms. The data may be trained and modeled using some common machine learning algorithms, such as support vector machines, decision trees, neural networks, etc., to enable prediction and diagnosis of faults.
Model evaluation module: and the method is responsible for evaluating the trained machine learning model so as to ensure the accuracy and reliability of the model. The model may be evaluated and optimized using cross-validation techniques or the like to improve the performance of the model.
And a fault prediction module: and the system is responsible for predicting and diagnosing future faults by using a trained machine learning model, and can send an alarm to maintenance personnel and give information such as the type and the position of the faults when the system detects signals of possible faults, thereby providing assistance for the maintenance personnel.
And a data visualization module: and the processed data and the prediction result are presented to the user in a visual form, so that the user can conveniently analyze and make decisions.
The data acquisition module is realized by the following steps:
determining parameters to be monitored: before designing the data acquisition module, it is necessary to specify the parameters that need to be monitored. The power grid operation data generally comprise parameters such as voltage, current, temperature, humidity, vibration and the like, and the parameters to be monitored are selected according to actual needs.
Selecting a suitable sensor: and selecting a proper sensor according to the parameters to be monitored. The selection of the sensor should take into account factors such as accuracy, stability, sensitivity and the like of the sensor, and also the installation position and the installation mode of the sensor.
And (3) installing a sensor: and installing the selected sensor at a position to be monitored, such as a power transmission line, a transformer substation and the like. When installing the sensor, attention is required to be paid to the installation position and the installation mode of the sensor so as to ensure that the acquired data are accurate and stable.
And (3) connecting acquisition equipment: the sensor is connected with a data acquisition device. The data acquisition device is usually a microcontroller or a single-chip microcomputer, and acquires power grid operation data by acquiring an electric signal output by the sensor. The acquisition device may be connected to the data processing module using a serial port, USB interface, or the like.
And (3) data transmission: and transmitting the acquired data to a data processing module. Data transmission may be accomplished using wireless communication technology (e.g., wiFi, bluetooth, loRa, etc.) or wired communication technology (e.g., ethernet, RS485, etc.).
The data processing module is realized by the following steps: data preprocessing: preprocessing the collected original data. This includes data filtering, denoising, normalization, sample rate reduction, etc. The purpose of the preprocessing is to remove noise and outliers, making the data more reliable and accurate.
Feature extraction: features are extracted from the preprocessed data. Features describe properties of the data such as voltage, current, etc. The purpose of feature extraction is to convert the data into a computable feature vector for further analysis and processing.
And (3) establishing a model: the relationship between the feature vector and the grid fault is modeled using machine learning or other algorithms. Common algorithms include decision trees, neural networks, support vector machines, and the like. Training of the model requires the use of a large number of data sets, including grid fault data and normal data, to give the model good generalization ability.
Prediction and diagnosis: and predicting and diagnosing the power grid faults by using the established model. Based on the input of the feature vector, the model can predict whether a fault exists and determine the type and location of the fault. The results of the predictions and diagnostics may be output through a user interface or alarm system.
Storing and managing data: and storing the processed data into a database or a cloud platform for subsequent analysis and processing. Data management includes data backup, recovery, cleaning and security management
The machine learning model training module is realized by the following steps: data preparation: the processed data set is divided into a training set, a verification set and a test set. The training set is used for training the model, the verification set is used for adjusting the model super-parameters, and the test set is used for evaluating the performance of the model.
Feature selection: the most valuable features are selected for training based on the importance and relevance of the features. The purpose of feature selection is to remove redundant features and noise features and improve the generalization capability of the model.
Model selection: and selecting a proper machine learning algorithm for training. Common algorithms include decision trees, random forests, neural networks, support vector machines, and the like. And selecting a proper algorithm for training according to different application scenes and data characteristics.
Model training: the model is trained using a training set and a selected machine learning algorithm. The training process is to continuously adjust parameters of the model through an optimization algorithm, so that errors of the model on a training set are minimized.
Super parameter tuning: and adjusting the super parameters of the model to improve the generalization capability of the model. Super parameters include learning rate, regularization coefficient, decision tree depth, etc.
Model evaluation: the trained model is evaluated using the validation set. The evaluated metrics include precision, recall, F1 value, etc. The evaluation result can help us know the performance and the advantages and disadvantages of the model, so as to further improve and optimize.
Model preservation: and saving the trained model to a local or cloud end for subsequent deployment and application.
As shown in fig. 2, the learning rate, regularization coefficient, batch size, etc. have important effects on the performance and training speed of the model, so that proper tuning is required, and the super-parameter tuning specifically includes:
step 1: determining a priori distribution of super parameters: one a priori distribution, e.g., gaussian distribution, beta distribution, etc., is selected for each super parameter.
Step 2: generating initial samples from the prior distribution: a number of samples are generated from the a priori distribution and used to train and evaluate the model.
Step 3: selecting an evaluation index: according to the task type and the target of the model, proper evaluation indexes such as accuracy, precision, recall rate and the like are selected.
Step 4: training and evaluating a model: the model is trained and evaluated by using the initial sample, and the evaluation result and training time of each group of super parameters are recorded.
Step 5: the posterior probability is calculated according to a Bayes formula: and calculating posterior probability of each group of super parameters according to a Bayesian formula, and taking the posterior probability as prior distribution of the next round of optimization.
Step 6: selecting the following set of super parameters: the gaussian process is used to select the next set of hyper-parameters in the posterior distribution and to train and evaluate the model.
Step 7: iterative optimization process: repeating the steps 4-6 until the preset optimization times are reached or the evaluation index reaches the optimal value.
The model evaluation module is realized by the following steps: selecting an evaluation index: and selecting a proper evaluation index according to specific application scenes and task requirements. Common evaluation metrics include accuracy, recall, F1 values, ROC curves, AUC, etc.
Preparing a data set: the data set is divided into a training set and a test set. The training set is used to train the model and the test set is used to evaluate the performance of the model.
Loading a model: and loading the trained machine learning model from the local or cloud.
Prediction result: and predicting by using the test set data, and comparing the prediction result with the real label.
Calculating an evaluation index: and calculating the performance of the model on the test set according to the selected evaluation index. For example, for a classification problem, indices such as accuracy, recall, F1 value, etc. may be calculated.
And (5) visualizing the result: and the evaluation results are visually displayed by using modes such as charts, curves and the like, so that a user can conveniently and intuitively know the performance of the model.
And (3) improving a model: and (3) according to the evaluation result, improving and optimizing the model, and improving the performance and generalization capability of the model.
The fault prediction module is realized by the following steps: data preprocessing: and carrying out preprocessing operations such as cleaning, denoising, missing value processing and the like on the acquired data so as to improve the data quality.
Feature extraction: according to specific application scenes and task requirements, meaningful features are extracted from the preprocessed data so as to be used for training and prediction of the fault prediction model.
Feature selection: and selecting features useful for the prediction target from the extracted features, and removing redundant and useless features to improve the prediction performance of the model.
Model selection: and selecting a proper machine learning model for training and predicting according to specific application scenes and task requirements. Common models include decision trees, random forests, neural networks, and the like.
Model training: the selected machine learning model is trained using the feature extracted and selected dataset.
Model parameter adjustment: and adjusting parameters of the model according to the performance of the model on the training set so as to improve the generalization capability and the prediction performance of the model.
Model prediction: and predicting the future state of the power transmission system by using the trained model so as to detect whether the fault risk exists.
Visualization of results: and the prediction results are visually displayed by using modes such as charts, curves and the like, so that a user can conveniently and intuitively know the state and the fault risk of the power transmission system.
The data visualization module is realized by the following steps: data preparation: the collected data is cleaned, processed, and converted for graphical presentation. For example, the data is sorted and categorized in time series, and the data is filtered and grouped.
Chart selection: and selecting a proper chart type according to the type of the data and the display requirement. Such as a line graph, bar graph, pie graph, scatter graph, etc.
Graph design: according to the graph type and the display requirement, the layout, the color, the label and other elements of the graph are designed. For example, selecting an appropriate coordinate axis, setting a data tag and a legend, and the like.
Generating a chart: a chart is generated using a data visualization tool or programming language. Common data visualization tools include Tableau, power BI, etc., and common programming languages include Python, R, etc.
Graph adjustment: and adjusting and modifying the chart according to feedback and requirements of users so as to improve the display effect and legibility.
Graph derivation: the generated chart is exported as an image file or a web page file for sharing and use by the user.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (7)
1. Intelligent detection system of transmission of electricity on-line monitoring device, its characterized in that includes:
and a data acquisition module: the power transmission on-line monitoring device is responsible for collecting data; and a data processing module: the method is responsible for processing the acquired data; machine learning model training module: the method is in charge of performing model training on the processed data by using a machine learning algorithm; model evaluation module: the method is responsible for evaluating the trained machine learning model; and a fault prediction module: is responsible for predicting and diagnosing future faults using the trained machine learning model.
2. The intelligent detection system of an on-line power transmission monitoring device according to claim 1, wherein: the data processing module comprises the following steps:
data preprocessing: preprocessing the collected original data;
feature extraction: extracting features from the preprocessed data;
and (3) establishing a model: using a machine learning algorithm to build a model of the relationship between the feature vector and the grid fault;
prediction and diagnosis: predicting and diagnosing power grid faults by using the established model; according to the input of the feature vector, the model can predict whether a fault exists or not, and the type and the position of the fault are determined; outputting the prediction and diagnosis results through a user interface;
storing and managing data: and storing the processed data into a cloud platform for subsequent analysis and processing.
3. The intelligent detection system of an on-line power transmission monitoring device according to claim 2, wherein: the machine learning model training module comprises the following steps:
data preparation: dividing the processed data set into a training set, a verification set and a test set; the training set is used for training the model, the verification set is used for adjusting the model super-parameters, and the test set is used for evaluating the performance of the model;
feature selection: selecting the characteristics for training according to the importance and the relativity of the characteristics;
model selection: selecting a machine learning algorithm for training;
model training: training the model by using a training set and a selected machine learning algorithm; training comprises adjusting parameters of the model through an optimization algorithm to minimize errors of the model on a training set;
super parameter tuning: the super-parameters of the model are adjusted to improve the generalization capability of the model;
model evaluation: evaluating the trained model using the validation set;
model preservation: and saving the trained model to a local or cloud end for subsequent deployment and application.
4. The intelligent detection system of an on-line power transmission monitoring device according to claim 3, wherein: super parameter tuning includes:
step 1: determining a priori distribution of super parameters: selecting a prior distribution for each super parameter;
step 2: generating initial samples from the prior distribution: generating a certain number of samples according to the prior distribution, and using the samples for training and evaluating a model;
step 3: selecting an evaluation index: selecting an evaluation index according to the task type and the target of the model;
step 4: training and evaluating a model: training and evaluating the model by using an initial sample, and recording an evaluation result and training time of each group of super parameters;
step 5: the posterior probability is calculated according to a Bayes formula: according to a Bayes formula, the posterior probability of each group of super parameters is calculated and is used as the prior distribution of the next round of optimization;
step 6: selecting the following set of super parameters: selecting a next set of hyper-parameters in the posterior distribution using a gaussian process and using them to train and evaluate the model;
step 7: iterative optimization process: repeating the steps 4-6 until the preset optimization times are reached or the evaluation index reaches the optimal value.
5. The intelligent detection system of an on-line power transmission monitoring device according to claim 4, wherein: the model evaluation module comprises the following steps:
selecting an evaluation index: selecting an evaluation index according to specific application scenes and task requirements;
preparing a data set: dividing the data set into a training set and a testing set; the training set is used for training the model, and the testing set is used for evaluating the performance of the model;
loading a model: loading a trained machine learning model from a local or cloud;
prediction result: predicting by using the test set data, and comparing the prediction result with the real label;
calculating an evaluation index: calculating the performance of the model on the test set according to the selected evaluation index;
and (5) visualizing the result: visually displaying the evaluation result;
and (3) improving a model: and (5) improving and optimizing the model according to the evaluation result.
6. The intelligent detection system of an on-line power transmission monitoring device according to claim 5, wherein: the fault prediction module comprises the following steps:
data preprocessing: the collected data is subjected to cleaning, denoising and missing value processing pretreatment operation so as to improve the data quality;
feature extraction: according to specific application scenes and task demands, extracting meaningful features from the preprocessed data so as to be used for training and predicting a fault prediction model;
feature selection: selecting features useful for a prediction target from the extracted features, and removing redundant and useless features to improve the prediction performance of the model;
model selection: selecting a machine learning model for training and predicting according to specific application scenes and task requirements;
model training: training the selected machine learning model by using the data set after feature extraction and selection;
model parameter adjustment: according to the performance of the model on the training set, parameter adjustment is carried out on the model so as to improve the generalization capability and the prediction performance of the model;
model prediction: predicting the state of a future power transmission system by using the trained model so as to detect whether a fault risk exists;
visualization of results: and visually displaying the prediction result.
7. The intelligent detection system of an on-line power transmission monitoring device according to claim 6, wherein: the method also comprises a data visualization module: and the processed data and the prediction result are presented to the user in a visual form, so that the user can conveniently analyze and make decisions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310452186.3A CN116629627A (en) | 2023-04-25 | 2023-04-25 | Intelligent detection system of power transmission on-line monitoring device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310452186.3A CN116629627A (en) | 2023-04-25 | 2023-04-25 | Intelligent detection system of power transmission on-line monitoring device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116629627A true CN116629627A (en) | 2023-08-22 |
Family
ID=87601686
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310452186.3A Pending CN116629627A (en) | 2023-04-25 | 2023-04-25 | Intelligent detection system of power transmission on-line monitoring device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116629627A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116980279A (en) * | 2023-09-25 | 2023-10-31 | 之江实验室 | Fault diagnosis system and fault diagnosis method for programmable network element equipment |
| CN117176560A (en) * | 2023-11-03 | 2023-12-05 | 山东智云信息科技有限公司 | Monitoring equipment supervision system and method based on Internet of things |
| CN117237392A (en) * | 2023-09-27 | 2023-12-15 | 青岛金账本信息技术有限公司 | Intelligent financial alarm management host system and method based on Internet of things technology |
| CN117474357A (en) * | 2023-11-02 | 2024-01-30 | 深圳汉驰科技有限公司 | Power distribution room operation and maintenance management method and system based on deep learning |
| CN117767579A (en) * | 2024-02-22 | 2024-03-26 | 国网山东省电力公司电力科学研究院 | AutoML-based power grid big data analysis method and automatic modeling system |
-
2023
- 2023-04-25 CN CN202310452186.3A patent/CN116629627A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116980279A (en) * | 2023-09-25 | 2023-10-31 | 之江实验室 | Fault diagnosis system and fault diagnosis method for programmable network element equipment |
| CN116980279B (en) * | 2023-09-25 | 2023-12-12 | 之江实验室 | Fault diagnosis system and fault diagnosis method for programmable network element equipment |
| CN117237392A (en) * | 2023-09-27 | 2023-12-15 | 青岛金账本信息技术有限公司 | Intelligent financial alarm management host system and method based on Internet of things technology |
| CN117474357A (en) * | 2023-11-02 | 2024-01-30 | 深圳汉驰科技有限公司 | Power distribution room operation and maintenance management method and system based on deep learning |
| CN117176560A (en) * | 2023-11-03 | 2023-12-05 | 山东智云信息科技有限公司 | Monitoring equipment supervision system and method based on Internet of things |
| CN117176560B (en) * | 2023-11-03 | 2024-01-26 | 山东智云信息科技有限公司 | Monitoring equipment supervision system and method based on Internet of things |
| CN117767579A (en) * | 2024-02-22 | 2024-03-26 | 国网山东省电力公司电力科学研究院 | AutoML-based power grid big data analysis method and automatic modeling system |
| CN117767579B (en) * | 2024-02-22 | 2024-05-17 | 国网山东省电力公司电力科学研究院 | AutoML-based power grid big data analysis method and automatic modeling system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116629627A (en) | Intelligent detection system of power transmission on-line monitoring device | |
| US8868985B2 (en) | Supervised fault learning using rule-generated samples for machine condition monitoring | |
| CN108320043B (en) | Power distribution network equipment state diagnosis and prediction method based on electric power big data | |
| KR102427205B1 (en) | Apparatus and method for generating training data of artificial intelligence model | |
| CN110515781B (en) | Complex system state monitoring and fault diagnosis method | |
| CN117196066A (en) | Intelligent operation and maintenance information analysis model | |
| CN111444169A (en) | Transformer substation electrical equipment state monitoring and diagnosis system and method | |
| CN115358155A (en) | Power big data abnormity early warning method, device, equipment and readable storage medium | |
| CN113962299A (en) | Intelligent operation monitoring and fault diagnosis general model for nuclear power equipment | |
| CN117639251A (en) | Intelligent online monitoring system for high-voltage switch cabinet | |
| CN113420162A (en) | Equipment operation chain state monitoring method based on knowledge graph | |
| CN115037603A (en) | Diagnosis evaluation method, device and system of electricity consumption information acquisition equipment | |
| CN116418117A (en) | Equipment detection system for intelligent power grid | |
| CN102929241B (en) | Safe operation guide system of purified terephthalic acid device and application of safe operation guide system | |
| CN114118222A (en) | Coal mill state early warning system and fault identification and diagnosis method | |
| CN117607780A (en) | Abnormality analysis system and analysis method for electric energy metering device | |
| CN110455370B (en) | Flood-prevention drought-resisting remote measuring display system | |
| CN117609716A (en) | Power equipment residual life remote prediction method and system based on state health information | |
| CN117172751A (en) | Construction method of intelligent operation and maintenance information analysis model | |
| CN117074852A (en) | Power distribution network electric energy monitoring and early warning management method and system | |
| CN116611953A (en) | Electric energy meter production and manufacturing real-time data management method and system based on Internet of things | |
| CN116070140A (en) | Power distribution substation safe operation state monitoring system and method | |
| CN114236268A (en) | Transformer fault diagnosis method and system based on machine learning | |
| CN112363432A (en) | Monitoring system and monitoring method for hydropower station auxiliary equipment | |
| CN117589444B (en) | Wind driven generator gear box fault diagnosis method based on federal learning |
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 |