CN115833400A - Monitoring and early warning method and system for power equipment of transformer substation - Google Patents
Monitoring and early warning method and system for power equipment of transformer substation Download PDFInfo
- Publication number
- CN115833400A CN115833400A CN202310070009.9A CN202310070009A CN115833400A CN 115833400 A CN115833400 A CN 115833400A CN 202310070009 A CN202310070009 A CN 202310070009A CN 115833400 A CN115833400 A CN 115833400A
- Authority
- CN
- China
- Prior art keywords
- equipment
- monitoring
- result
- abnormal
- temperature
- 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.)
- Granted
Links
Images
Landscapes
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention provides a monitoring and early warning method and a system for substation power equipment, which relate to the technical field of equipment monitoring and early warning, wherein basic information of acquisition equipment is used for laying monitoring nodes, setting node characteristic identification, acquiring historical operation information of the acquisition equipment and extracting equipment characteristics, acquiring an interaction data set of the monitoring nodes, constructing an anomaly detection model, and performing model analysis on the interaction data set to output an anomaly prediction result; the method comprises the steps of collecting and monitoring the temperature of the electric power equipment, obtaining a temperature collection set, combining an abnormal prediction result to generate abnormal early warning information, carrying out monitoring management on the electric power equipment, solving the technical problems that the monitoring early warning method of the electric power equipment in the prior art is conventional, is not intelligent enough, causes low detection efficiency and insufficient detection result precision, cannot guarantee the timeliness of abnormal early warning, and causes the defect of equipment operation and maintenance, and realizing intelligent, accurate and efficient detection of the abnormality of the electric power equipment and continuous normal operation of maintenance equipment by optimizing the rigidness of a data processing flow and the method.
Description
Technical Field
The invention relates to the technical field of equipment monitoring and early warning, in particular to a monitoring and early warning method and system for substation power equipment.
Background
The transformer substation is provided with various power devices which can be refined into primary devices and secondary devices and used as main control devices and auxiliary control devices for transmitting and distributing electric energy so as to realize conversion, monitoring and adjustment of the electric energy. In the operation process of the transformer substation, equipment abnormity can be caused inevitably, and electric energy regulation and control influence is caused.
At present, the conventional power equipment monitoring method is used for carrying out periodical preventive inspection and judging abnormity based on the appearances, indicating instruments and the like by means of professional experience, the detection method is conventional, certain subjectivity exists, the abnormal detection result of the equipment cannot be obtained in time, follow-up maintenance cannot follow the equipment in time, certain flaws exist, and further optimization is needed.
In the prior art, the monitoring and early warning method for the power equipment is conventional and not intelligent enough, so that the detection efficiency is low, the precision of a detection result is not enough, the timeliness of abnormal early warning cannot be guaranteed, and the operation and maintenance defects of the equipment are caused.
Disclosure of Invention
The application provides a monitoring and early warning method and system for power equipment of a transformer substation, which are used for solving the technical problems that the monitoring and early warning method for the power equipment in the prior art is conventional, is not intelligent enough, causes low detection efficiency and insufficient detection result precision, cannot ensure the timeliness of abnormal early warning, and causes the defect of equipment operation and maintenance.
In view of the above problems, the present application provides a monitoring and early warning method and system for substation power equipment.
In a first aspect, the present application provides a monitoring and early warning method for substation power equipment, where the method includes:
acquiring and acquiring device basic information of monitoring power equipment, wherein the device basic information comprises device attribute information;
laying monitoring nodes according to the basic information of the equipment, and setting node characteristic marks;
acquiring and obtaining historical equipment operation information of the monitored power equipment, and extracting equipment characteristics according to the historical equipment operation information to obtain an equipment characteristic extraction result;
performing equipment operation information interaction on the monitoring node through the data interaction device to obtain an interaction data set, wherein the interaction data set is provided with the node characteristic identifier;
constructing an abnormal detection model according to the equipment basic information, the node feature identification and the big data, and performing model correction on the abnormal detection model according to the equipment feature extraction result;
inputting the interactive data set with the node feature identification into the abnormal detection model after model modification, and outputting an abnormal prediction result;
acquiring the temperature of the monitoring power equipment through the temperature monitoring device to obtain a temperature acquisition set;
and generating abnormity early warning information according to the temperature collection set and the abnormity prediction result, and monitoring and managing the monitoring power equipment according to the abnormity early warning information.
In a second aspect, the present application provides a monitoring and early warning system for substation power equipment, the system includes:
the system comprises an information acquisition module, a monitoring module and a monitoring module, wherein the information acquisition module is used for acquiring and acquiring equipment basic information of the monitored power equipment, and the equipment basic information comprises equipment attribute information;
the node characteristic identifier setting module is used for laying monitoring nodes according to the equipment basic information and setting node characteristic identifiers;
the characteristic extraction module is used for acquiring and obtaining historical equipment operation information of the monitored power equipment, extracting equipment characteristics according to the historical equipment operation information and obtaining an equipment characteristic extraction result;
the information interaction module is used for carrying out equipment operation information interaction on the monitoring node through the data interaction device to obtain an interaction data set, wherein the interaction data set is provided with the node feature identifier;
the model construction module is used for constructing an abnormal detection model according to the equipment basic information, the node feature identification and the big data, and performing model correction on the abnormal detection model according to the equipment feature extraction result;
a result output module, configured to input the interaction data set with the node feature identifier into the abnormal detection model after model modification, and output an abnormal prediction result;
the temperature acquisition module is used for acquiring the temperature of the monitoring power equipment through the temperature monitoring device to obtain a temperature acquisition set;
and the abnormal early warning management module is used for generating abnormal early warning information according to the temperature acquisition set and the abnormal prediction result, and monitoring and managing the monitoring power equipment through the abnormal early warning information.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
according to the monitoring and early warning method for the power equipment of the transformer substation, the equipment basic information of the monitored power equipment is acquired and obtained, the equipment basic information comprises equipment attribute information, monitoring nodes are distributed according to the equipment basic information, and node characteristic marks are set; acquiring historical operation information of equipment to extract equipment characteristics, and obtaining an equipment characteristic extraction result; performing equipment operation information interaction on the monitoring node through the data interaction device to obtain an interaction data set, wherein the interaction data set is provided with the node characteristic identification; constructing an anomaly detection model according to the equipment basic information, the node feature identification and the big data, performing model correction of the anomaly detection model based on the equipment feature extraction result, inputting the interaction data set into the anomaly detection model after model correction, and outputting an anomaly prediction result; the monitoring management of the monitoring power equipment is carried out, the technical problems that the monitoring early warning method of the power equipment is conventional and not intelligent enough, the detection efficiency is low, the accuracy of the detection result is not enough, the timeliness of the abnormal early warning cannot be guaranteed, and the operation and maintenance defects of the equipment are caused are solved.
Drawings
Fig. 1 is a schematic flow chart of a monitoring and early warning method for substation power equipment provided in the present application;
fig. 2 is a schematic diagram illustrating an abnormal detection model obtaining process in a monitoring and early warning method for substation power equipment provided by the present application;
fig. 3 is a schematic diagram illustrating an abnormal early warning information acquisition process in a monitoring early warning method for substation power equipment provided in the present application;
fig. 4 provides a schematic structural diagram of a monitoring and early warning system of a substation power device.
Description of the reference numerals: the system comprises an information acquisition module 11, a node feature identifier setting module 12, a feature extraction module 13, an information interaction module 14, a model construction module 15, a result output module 16, a temperature acquisition module 17 and an abnormity early warning management module 18.
Detailed Description
The monitoring and early warning method and system for the power equipment of the transformer substation are provided, wherein basic information of the equipment is collected to carry out monitoring node arrangement, a node characteristic mark is set, historical operation information of the equipment is collected to carry out equipment characteristic extraction, a monitoring node interaction data set is obtained, an abnormality detection model is built according to the basic information of the equipment, the node characteristic mark and big data, and an abnormality prediction result is output by carrying out model analysis on the interaction data set; the method comprises the steps of collecting and monitoring the temperature of the electric power equipment, acquiring a temperature collection set, generating abnormal early warning information by combining an abnormal prediction result, and carrying out monitoring management on the electric power equipment, wherein the technical problems that the monitoring and early warning method of the electric power equipment is conventional, not intelligent enough, low in detection efficiency, insufficient in detection result precision, incapable of guaranteeing the timeliness of abnormal early warning and defective in operation and maintenance of the equipment are caused are solved.
Example one
As shown in fig. 1, the present application provides a monitoring and early warning method for substation power equipment, the method is applied to a monitoring and early warning system, the monitoring and early warning system is in communication connection with a data interaction device and a temperature monitoring device, and the method includes:
step S100: acquiring and acquiring device basic information of monitoring power equipment, wherein the device basic information comprises device attribute information;
specifically, a plurality of power devices are installed in the substation for transmission and distribution of electric energy to realize conversion, monitoring and adjustment of electric energy. In the operation process of a transformer substation, equipment abnormity can inevitably exist to cause electric energy regulation and control influence, the monitoring and early warning method of the power equipment of the transformer substation is applied to the monitoring and early warning system, the monitoring and early warning system is a master control system for carrying out the power equipment of the transformer substation, the system is in communication connection with the data interaction device and the temperature monitoring device, based on the data interaction device, equipment operation interaction data of a plurality of monitoring nodes can be determined, the temperature monitoring device is used for carrying out real-time temperature acquisition on the power equipment, and equipment abnormal operation analysis and prediction is carried out based on the real-time acquisition data.
Specifically, the monitoring power equipment in the substation to be monitored is collected, the monitoring power equipment comprises main control equipment such as an electric energy conversion device and a transmission device and auxiliary monitoring equipment such as a measuring instrument and a relay protection device, and the monitoring power equipment is subjected to equipment attribute information analysis, namely common characteristic information of the same kind of equipment, including control, operation and maintenance and the like of the power equipment, and is subjected to basic index determination, such as equipment model, structural information, layout information and the like, on the monitoring power equipment, equipment attribution integration is performed on the information to generate the equipment basic information, and the equipment basic information is a basic data source for performing operation analysis on the monitoring power equipment.
Step S200: laying monitoring nodes according to the basic information of the equipment, and setting node characteristic marks;
step S300: acquiring and obtaining historical equipment operation information of the monitored power equipment, and extracting equipment characteristics according to the historical equipment operation information to obtain an equipment characteristic extraction result;
specifically, the device basic information is acquired by acquiring information of the monitoring power device. And extracting the equipment layout information and the structure information of the transformer substation based on the equipment basic information, determining a plurality of positions of the structures to be monitored aiming at the equipment running state, and setting the positions as the monitoring nodes. And further performing equipment visualization feature extraction on the monitoring node, for example, performing mapping correspondence on the extracted features and the monitoring power equipment to obtain the node feature identifier, wherein the static features and the dynamic features of the equipment structure points are used for extracting the equipment visualization features.
Furthermore, a preset time granularity is obtained, namely a time interval for collecting historical operation live of the equipment is obtained, historical operation information of the equipment is collected by the monitoring power equipment based on the prime number preset time granularity, time sequence integration is carried out on collected data, and information orderliness is improved. Based on historical operation information of the equipment, the monitoring power equipment respectively carries out equipment operation feature extraction under a plurality of acquisition time nodes, namely differentiation features of the equipment, such as frequent open circuit or short circuit positions, rapid temperature rise or aging of parts and the like, are associated and correspond to the acquired equipment features and the monitoring power equipment to generate an equipment feature extraction result. And taking the node feature identification and the equipment feature extraction result as equipment anomaly detection reference information to provide an anomaly evaluation basis.
Step S400: performing equipment operation information interaction on the monitoring node through the data interaction device to obtain an interaction data set, wherein the interaction data set is provided with the node characteristic identifier;
specifically, the data interaction device is an auxiliary device for performing device operation data circulation, the detection node is used as a data interaction monitoring position, operation data interaction of the monitoring node is realized based on the data interaction device, device operation interaction data acquisition is performed on the monitoring node, a data acquisition result and the node feature identifier are associated and correspond to each other, so that data orderliness and definition are improved, identification and distinguishing are facilitated, and the interaction data set is obtained and is source data to be subjected to anomaly detection.
Step S500: constructing an abnormal detection model according to the equipment basic information, the node feature identification and the big data, and performing model correction on the abnormal detection model according to the equipment feature extraction result;
further, as shown in fig. 2, step S500 of the present application further includes:
step S510-1: extracting and obtaining an equipment operation data set based on big data according to the equipment basic information and the node characteristic identification;
step S520-1: carrying out data identification on the equipment operation data set, and carrying out identification classification on the equipment operation data set to obtain a training set and a test set;
step S530-1: setting a plurality of monitoring thresholds, and constructing a plurality of initial anomaly detection models according to the monitoring thresholds and the training set;
step S540-1: calculating the recall ratio and precision ratio of the plurality of initial anomaly detection models through the test set to obtain the calculation results of the recall ratio and the precision ratio;
step S550-1: and performing model screening of the plurality of initial anomaly detection models according to the recall ratio and the precision ratio calculation result, and obtaining the anomaly detection models according to the screening result.
Specifically, the device basic information and the node feature identifier are used as indexes, operation data acquisition is performed based on big data, acquired data are normalized, and the device operation data set is generated. Further, the device node identification is carried out on the device operation data set, so that a data division ratio is determined, the data division ratio can be dynamically adjusted to guarantee the final training effect of the model, illustratively, the device operation data set is divided into k groups, the training set and the test set, namely model training samples, are determined based on the data division ratio, and the operation data and the abnormal recognition result identification are respectively carried out on the training set and the test set. Setting a plurality of monitoring thresholds, namely, performing a node data anomaly determination critical value, based on the device node, wherein the plurality of monitoring thresholds include a plurality of threshold standards, constructing a main framework of an anomaly detection model by training a neural network, for example, the main framework may be a multi-level network layer including a node data recognition layer and a data anomaly detection layer, inputting the plurality of monitoring thresholds and the training set into the main framework of the anomaly detection model, and performing model training to generate the plurality of initial anomaly detection models, wherein the plurality of initial anomaly detection models correspond to the plurality of detection thresholds.
And further inputting the test set into the plurality of initial anomaly detection models to obtain a model output result, further performing proofreading on the model output result and the anomaly identification result in the test set, performing ratio calculation on the two to determine the recall ratio and the precision ratio based on the deviation of the proofreading result, and obtaining the recall ratio and precision ratio calculation results. And then selecting the optimal one of the initial anomaly detection models as the anomaly detection model by taking the recall ratio and the precision ratio calculation result as a screening basis. And inputting the equipment feature extraction result into the anomaly detection model, and performing model optimization and perfection. The abnormal operation detection analysis of the equipment is carried out through the training model, and the accuracy of the abnormal detection result can be effectively improved to objectivity.
Further, step S550-1 of the present application further includes:
step S551-1: setting a comparison reference value, wherein the comparison reference value is the ratio of recall ratio to precision ratio;
step S552-1: respectively calculating comparison reference values of the plurality of initial anomaly detection models according to the recall ratio and precision ratio calculation results to obtain comparison reference value calculation results;
step S553-1: and performing sequential sorting according to the comparison reference value calculation result, and screening based on the sequential sorting result to obtain the anomaly detection model.
Specifically, the test set is input into the plurality of initial anomaly detection models, a model output result is obtained, deviation analysis is further performed on the model output result and an anomaly identification result in the test set, and running deviation data is obtained, wherein the running deviation data is running deviation of the models. And calculating the detection completeness and the detection accuracy of the abnormal information based on the model output result and the abnormal recognition result, namely calculating the ratio of the two related data. Further setting the ratio of the recall ratio to the precision ratio as the comparison reference value, respectively calculating the comparison reference values of the models for the plurality of initial anomaly detection models based on the recall ratio and the precision ratio calculation results, and obtaining the comparison reference value calculation results. And performing data angle on the comparison reference values, performing decreasing sorting, obtaining the sequential sorting result, selecting the optimal one, and taking the corresponding initial anomaly detection model as the finally determined anomaly detection model, so that the optimization of the anomaly detection model can be effectively guaranteed, and the actual attaching degree of the output result is improved.
Further, step S500 of the present application further includes:
step S510-2: obtaining an exception handling result of the monitoring power equipment;
step S520-2: constructing a feedback optimization unit and setting an optimization compensation period;
step S530-2: when the optimal compensation period is reached, feedback feature extraction is carried out through the feedback optimization unit based on the abnormal processing result, and a feedback feature extraction result is obtained;
step S540-2: and performing model optimization of the anomaly detection model according to the feedback feature extraction result.
Specifically, based on the generated abnormality early warning information, the detected power equipment is actually detected, and the abnormality processing result is obtained, where the abnormality processing result has a node feature identifier. And constructing the feedback optimization unit, namely an auxiliary function unit for optimizing a model mechanism, wherein the feedback optimization unit comprises a hierarchical data identification node and a hierarchical feature extraction node and is used for identifying a data source of input information and extracting data features. And setting a model optimization time zone as the optimization compensation period, and periodically performing information coverage on the feedback optimization unit based on the optimization compensation period so as to improve the actual fitting degree of the model operation result. And when the optimization compensation period is reached, starting the feedback optimization unit, identifying and analyzing the input exception handling result, determining the deviation between the exception handling result and the exception early warning information, identifying deviation data based on the hierarchical data identification node, and transmitting the deviation data to the hierarchical feature extraction node to extract the feedback feature to serve as the feedback feature extraction result. And taking the feedback feature extraction result as a model optimization direction, and performing mechanism optimization on the anomaly detection model to reduce the detection deviation of the anomaly detection model and ensure the anomaly detection accuracy.
Step S600: inputting the interactive data set with the node feature identification into the abnormal detection model after model modification, and outputting an abnormal prediction result;
step S700: acquiring the temperature of the monitoring power equipment through the temperature monitoring device to obtain a temperature acquisition set;
step S800: and generating abnormity early warning information according to the temperature collection set and the abnormity prediction result, and monitoring and managing the monitoring power equipment according to the abnormity early warning information.
Specifically, the anomaly detection model is optimized and corrected based on the device feature extraction result, the interaction data set with the node feature identification is input into the anomaly detection model, the interaction data is identified and attributed based on the node data identification layer, and then the interaction data is transmitted to the corresponding detection node in the data anomaly detection layer, and the data detection result of the monitoring node is obtained and is output as the anomaly prediction result. The temperature monitoring device is an auxiliary device for acquiring real-time running temperature of the monitoring power equipment, and based on the temperature monitoring device, the monitoring nodes of the monitoring power equipment acquire temperature, including real-time static temperature and temperature gradient rate, as the temperature acquisition set. The temperature collection set and the abnormity prediction result are used as abnormity early warning directions, a temperature threshold value is set to judge the temperature collection set, abnormity temperature data are recognized, abnormity information integration is conducted in combination with the abnormity prediction result, the abnormity early warning information is generated, and based on the abnormity early warning information, targeted detection and correction are conducted on the monitoring power equipment, so that accurate recognition and control of abnormal operation of the monitoring power equipment are achieved, the equipment control energy efficiency is improved, and reasonable utilization of resources is achieved.
Further, as shown in fig. 3, the monitoring and early warning system is in communication connection with the ambient temperature monitoring device, and step S800 of the present application further includes:
step S810: collecting the ambient temperature through the ambient temperature monitoring device to obtain ambient temperature information;
step S820: analyzing the equipment influence of the monitoring power equipment based on the environmental temperature information to generate a temperature influence analysis result;
step S830: performing temperature anomaly analysis through the temperature collection set to obtain an anomaly analysis result;
step S840: performing abnormal compensation on the temperature analysis result according to the temperature influence analysis result to obtain a temperature abnormal compensation result;
step S850: and generating the abnormal early warning information according to the temperature abnormal compensation result and the abnormal prediction result.
Specifically, a plurality of environment temperature acquisition point locations are arranged, and real-time environment temperature acquisition is carried out on the environment temperature monitoring device at the plurality of environment temperature acquisition point locations to acquire environment temperature information. Based on the environmental temperature information, environmental impact analysis is performed on the monitoring power equipment, illustratively, multi-stage environmental temperatures can be defined, equipment impact energy efficiency is determined by performing big data research, the multi-stage environmental temperatures are associated and correspond to the equipment impact energy efficiency, a temperature impact list is generated, the temperature impact list is traversed, the environmental temperature information is matched and identified on the monitoring power equipment, and a temperature impact analysis result is obtained. And carrying out abnormity judgment on the temperature acquisition set, namely the equipment operation temperature of the monitoring node, determining abnormal temperature, configuring temperature abnormity grade, and generating an abnormity analysis result. The ambient temperature can cause equipment temperature detection error to a certain extent, and the direction and the scale of correction are determined based on the temperature influence analysis result, and the temperature analysis result is subjected to abnormal compensation to generate the temperature abnormal compensation result, so that the ambient error is eliminated and the temperature abnormal compensation result is more accurate. And determining an abnormal temperature node based on the temperature abnormality compensation result, generating the abnormality early warning information by combining the abnormality prediction result, effectively improving the degree of engagement between the abnormality early warning information and the monitored power equipment, and warning the equipment operation abnormality based on the abnormality early warning information.
Further, step S850 in the present application further includes:
step S851: performing anomaly matching analysis based on the temperature anomaly compensation result and the anomaly prediction result to generate an anomaly matching result;
step S852: judging whether the abnormal matching result meets a preset abnormal matching threshold value or not;
step S853: and when the abnormal matching result can meet the abnormal matching threshold, performing prediction adjustment on the abnormal prediction result according to the abnormal matching result, and generating the abnormal early warning information according to the prediction adjustment result.
Further, step S853 of the present application further includes:
step S8531: when the abnormal matching result cannot meet the preset abnormal matching threshold, generating a verification window;
step S8532: continuously acquiring interactive data and temperature data through the verification window to obtain a verification data set;
step S8533: matching and correcting the abnormal matching result according to the verification data set to obtain a corrected matching result;
step S8534: and generating the abnormal early warning information according to the corrected matching result.
Specifically, the ambient temperature information is collected to compensate the temperature collection set, and the temperature anomaly compensation result is generated. And traversing the abnormal prediction result, and performing abnormal matching with the temperature abnormal compensation result to obtain the abnormal matching result, wherein the temperature abnormal compensation result and the abnormal prediction result have a monitoring node corresponding relationship. Acquiring the preset abnormal matching threshold, namely a critical value for limiting the matching degree of the temperature abnormal compensation result and the abnormal prediction result, judging whether the abnormal matching result meets the preset abnormal matching threshold, if so, indicating that the data is complete and the monitoring node data corresponds to each other, determining the data adjusting direction and the adjusting scale based on the temperature abnormal compensation result, performing prediction adjustment on the abnormal prediction result, further improving the actual fitting degree of the abnormal prediction result, and generating the abnormal early warning information.
Further, when the abnormal matching result does not meet the preset abnormal matching threshold, it indicates that the data completeness is insufficient, and data omission or acquisition deviation may exist, and generates the verification window, that is, performs auxiliary inspection and secondary acquisition space for data determination. And aiming at the monitoring node, continuously acquiring the interaction data and the temperature data based on the verification window, and performing time sequence identification normalization on the acquired data to generate the verification data set. Traversing the abnormal matching result, matching and corresponding to the verification data set, adjusting and correcting the abnormal matching result, ensuring data completeness and accuracy, and generating the corrected matching result. And determining an equipment early warning node, an early warning state and an early warning grade based on the corrected matching result, performing information integration to generate the abnormal early warning information, and performing repair management on the monitored power equipment based on the abnormal early warning information.
Example two
Based on the same inventive concept as the monitoring and early warning method for the power equipment of the transformer substation in the foregoing embodiment, as shown in fig. 4, the present application provides a monitoring and early warning system for the power equipment of the transformer substation, where the system includes:
the system comprises an information acquisition module 11, a monitoring module and a monitoring module, wherein the information acquisition module 11 is used for acquiring and acquiring equipment basic information of the monitored power equipment, and the equipment basic information comprises equipment attribute information;
a node characteristic identifier setting module 12, where the node characteristic identifier setting module 12 is configured to lay monitoring nodes according to the device basic information and set node characteristic identifiers;
the feature extraction module 13 is configured to acquire and obtain historical operation information of the monitoring power equipment, perform equipment feature extraction according to the historical operation information of the monitoring power equipment, and obtain an equipment feature extraction result;
the information interaction module 14 is configured to perform device operation information interaction on the monitoring node through the data interaction device to obtain an interaction data set, where the interaction data set has the node feature identifier;
the model construction module 15 is configured to construct an anomaly detection model according to the device basic information, the node feature identifiers and the big data, and perform model correction on the anomaly detection model according to the device feature extraction result;
a result output module 16, where the result output module 16 is configured to input the interaction data set with the node feature identifier into the abnormal detection model after model modification, and output an abnormal prediction result;
the temperature acquisition module 17 is used for acquiring the temperature of the monitoring power equipment through the temperature monitoring device to obtain a temperature acquisition set;
and the abnormal early warning management module 18 is configured to generate abnormal early warning information according to the temperature collection set and the abnormal prediction result, and monitor and manage the monitoring power equipment according to the abnormal early warning information.
Further, the system further comprises:
the environment temperature acquisition module is used for acquiring the environment temperature through the environment temperature monitoring device to obtain environment temperature information;
the temperature influence analysis module is used for analyzing the equipment influence of the monitoring power equipment based on the environmental temperature information to generate a temperature influence analysis result;
the temperature anomaly analysis module is used for carrying out temperature anomaly analysis through the temperature collection set to obtain an anomaly analysis result;
the result compensation module is used for carrying out abnormal compensation on the temperature analysis result according to the temperature influence analysis result to obtain a temperature abnormal compensation result;
and the information generation module is used for generating the abnormal early warning information according to the temperature abnormal compensation result and the abnormal prediction result.
Further, the system further comprises:
an anomaly matching analysis module, configured to perform anomaly matching analysis based on the temperature anomaly compensation result and the anomaly prediction result to generate an anomaly matching result;
the threshold judging module is used for judging whether the abnormal matching result meets a preset abnormal matching threshold or not;
and the result adjusting module is used for carrying out prediction adjustment on the abnormal prediction result according to the abnormal matching result and generating the abnormal early warning information according to the prediction adjustment result when the abnormal matching result can meet the abnormal matching threshold.
Further, the system further comprises:
a verification window generation module, configured to generate a verification window when the abnormal matching result cannot meet the preset abnormal matching threshold;
the data acquisition module is used for continuously acquiring interactive data and temperature data through the verification window to obtain a verification data set;
the result correction module is used for carrying out matching correction on the abnormal matching result according to the verification data set to obtain a corrected matching result;
and the abnormal early warning information generating module is used for generating the abnormal early warning information according to the corrected matching result.
Further, the system further comprises:
the data extraction module is used for extracting and obtaining an equipment operation data set based on big data according to the equipment basic information and the node feature identification;
carrying out data identification on the equipment operation data set, and carrying out identification classification on the equipment operation data set to obtain a training set and a test set;
the model building module is used for setting a plurality of monitoring thresholds and building a plurality of initial anomaly detection models according to the monitoring thresholds and the training set;
the parameter calculation module is used for calculating the recall ratio and the precision ratio of the plurality of initial anomaly detection models through the test set to obtain the calculation results of the recall ratio and the precision ratio;
and the model screening module is used for screening the plurality of initial anomaly detection models according to the recall ratio and precision ratio calculation results and obtaining the anomaly detection models according to screening results.
Further, the system further comprises:
the device comprises a reference value setting module, a comparison module and a comparison module, wherein the reference value setting module is used for setting a comparison reference value, and the comparison reference value is the ratio of recall ratio to precision ratio;
the comparison reference value calculation module is used for calculating the comparison reference values of the plurality of initial anomaly detection models according to the recall ratio and the precision ratio calculation results to obtain comparison reference value calculation results;
and the result sorting module is used for carrying out sequential sorting through the comparison reference value calculation results and screening and obtaining the anomaly detection model based on the sequential sorting results.
Further, the system further comprises:
an exception handling result obtaining module, configured to obtain an exception handling result of the monitoring power device;
the unit construction module is used for constructing a feedback optimization unit and setting an optimization compensation period;
the characteristic extraction module is used for performing feedback characteristic extraction on the basis of the abnormal processing result through the feedback optimization unit when the optimal compensation period is reached, so as to obtain a feedback characteristic extraction result;
and the model optimization module is used for carrying out model optimization on the anomaly detection model according to the feedback feature extraction result.
In the present description, through the foregoing detailed description of the monitoring and early warning method for the substation power equipment, those skilled in the art can clearly know that the monitoring and early warning method and system for the substation power equipment in the present embodiment are described in a simpler manner as the device disclosed in the embodiment corresponds to the method disclosed in the embodiment, and reference may be made to the method for the relevant part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A monitoring and early warning method for substation power equipment is characterized in that the method is applied to a monitoring and early warning system, the monitoring and early warning system is in communication connection with a data interaction device and a temperature monitoring device, and the method comprises the following steps:
acquiring and acquiring device basic information of monitoring power equipment, wherein the device basic information comprises device attribute information;
laying monitoring nodes according to the basic information of the equipment, and setting node characteristic marks;
acquiring and obtaining historical equipment operation information of the monitored power equipment, and extracting equipment characteristics according to the historical equipment operation information to obtain an equipment characteristic extraction result;
performing equipment operation information interaction on the monitoring node through the data interaction device to obtain an interaction data set, wherein the interaction data set is provided with the node characteristic identifier;
constructing an abnormal detection model according to the equipment basic information, the node feature identification and the big data, and performing model correction on the abnormal detection model according to the equipment feature extraction result;
inputting the interactive data set with the node feature identification into the abnormal detection model after model modification, and outputting an abnormal prediction result;
acquiring the temperature of the monitoring power equipment through the temperature monitoring device to obtain a temperature acquisition set;
and generating abnormity early warning information according to the temperature collection set and the abnormity prediction result, and monitoring and managing the monitoring power equipment according to the abnormity early warning information.
2. The method of claim 1, wherein the monitoring and forewarning system is communicatively coupled to an ambient temperature monitoring device, the method comprising:
collecting the ambient temperature through the ambient temperature monitoring device to obtain ambient temperature information;
analyzing the equipment influence of the monitoring power equipment based on the environmental temperature information to generate a temperature influence analysis result;
performing temperature anomaly analysis through the temperature collection set to obtain an anomaly analysis result;
performing abnormal compensation on the temperature analysis result according to the temperature influence analysis result to obtain a temperature abnormal compensation result;
and generating the abnormal early warning information according to the temperature abnormal compensation result and the abnormal prediction result.
3. The method of claim 2, wherein the method comprises:
performing anomaly matching analysis based on the temperature anomaly compensation result and the anomaly prediction result to generate an anomaly matching result;
judging whether the abnormal matching result meets a preset abnormal matching threshold value or not;
and when the abnormal matching result can meet the abnormal matching threshold, performing prediction adjustment on the abnormal prediction result according to the abnormal matching result, and generating the abnormal early warning information according to the prediction adjustment result.
4. The method of claim 3, wherein the method comprises:
when the abnormal matching result cannot meet the preset abnormal matching threshold, generating a verification window;
continuously acquiring interactive data and temperature data through the verification window to obtain a verification data set;
matching and correcting the abnormal matching result according to the verification data set to obtain a corrected matching result;
and generating the abnormal early warning information according to the corrected matching result.
5. The method of claim 1, wherein the method comprises:
extracting and obtaining an equipment operation data set based on big data according to the equipment basic information and the node characteristic identification;
carrying out data identification on the equipment operation data set, and carrying out identification classification on the equipment operation data set to obtain a training set and a test set;
setting a plurality of monitoring thresholds, and constructing a plurality of initial anomaly detection models according to the monitoring thresholds and the training set;
calculating the recall ratio and precision ratio of the plurality of initial anomaly detection models through the test set to obtain the calculation results of the recall ratio and the precision ratio;
and performing model screening of the plurality of initial anomaly detection models according to the recall ratio and the precision ratio calculation result, and obtaining the anomaly detection model according to the screening result.
6. The method of claim 5, wherein the method comprises:
setting a comparison reference value, wherein the comparison reference value is the ratio of recall ratio to precision ratio;
respectively calculating comparison reference values of the plurality of initial anomaly detection models according to the recall ratio and precision ratio calculation results to obtain comparison reference value calculation results;
and performing sequential sorting according to the comparison reference value calculation result, and screening based on the sequential sorting result to obtain the anomaly detection model.
7. The method of claim 1, wherein the method comprises:
obtaining an exception handling result of the monitoring power equipment;
constructing a feedback optimization unit and setting an optimization compensation period;
when the optimal compensation period is reached, feedback feature extraction is carried out through the feedback optimization unit based on the abnormal processing result, and a feedback feature extraction result is obtained;
and performing model optimization of the anomaly detection model according to the feedback feature extraction result.
8. The utility model provides a monitoring and early warning system of transformer substation's power equipment, its characterized in that, the system and data interaction device, temperature monitoring device communication connection, the system includes:
the system comprises an information acquisition module, a monitoring module and a monitoring module, wherein the information acquisition module is used for acquiring and acquiring equipment basic information of the monitored power equipment, and the equipment basic information comprises equipment attribute information;
the node characteristic identifier setting module is used for laying monitoring nodes according to the equipment basic information and setting node characteristic identifiers;
the characteristic extraction module is used for acquiring and obtaining historical equipment operation information of the monitored power equipment, extracting equipment characteristics according to the historical equipment operation information and obtaining an equipment characteristic extraction result;
the information interaction module is used for carrying out equipment operation information interaction on the monitoring node through the data interaction device to obtain an interaction data set, wherein the interaction data set is provided with the node feature identifier;
the model construction module is used for constructing an abnormal detection model according to the equipment basic information, the node feature identification and the big data, and performing model correction on the abnormal detection model according to the equipment feature extraction result;
a result output module, configured to input the interaction data set with the node feature identifier into the abnormal detection model after model modification, and output an abnormal prediction result;
the temperature acquisition module is used for acquiring the temperature of the monitoring power equipment through the temperature monitoring device to obtain a temperature acquisition set;
and the abnormity early warning management module is used for generating abnormity early warning information according to the temperature collection set and the abnormity prediction result, and monitoring and managing the monitoring power equipment according to the abnormity early warning information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310070009.9A CN115833400B (en) | 2023-02-07 | 2023-02-07 | Monitoring and early warning method and system for power equipment of transformer substation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310070009.9A CN115833400B (en) | 2023-02-07 | 2023-02-07 | Monitoring and early warning method and system for power equipment of transformer substation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115833400A true CN115833400A (en) | 2023-03-21 |
| CN115833400B CN115833400B (en) | 2023-04-18 |
Family
ID=85520853
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310070009.9A Active CN115833400B (en) | 2023-02-07 | 2023-02-07 | Monitoring and early warning method and system for power equipment of transformer substation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115833400B (en) |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115993504A (en) * | 2023-03-23 | 2023-04-21 | 山东盛日电力集团有限公司 | Intelligent fault diagnosis method and system for electrical equipment |
| CN115993807A (en) * | 2023-03-23 | 2023-04-21 | 日照鲁光电子科技有限公司 | Production monitoring optimization control method and system for silicon carbide |
| CN116011794A (en) * | 2023-03-23 | 2023-04-25 | 北京万讯博通科技发展有限公司 | Infrastructure supervision method and system based on cloud operation and maintenance |
| CN116151521A (en) * | 2023-04-04 | 2023-05-23 | 四川省自然资源科学研究院(四川省生产力促进中心) | Big data information acquisition method and system |
| CN116345693A (en) * | 2023-04-21 | 2023-06-27 | 沈阳工程学院 | Safety monitoring management method and system for transformer substation |
| CN116359658A (en) * | 2023-05-31 | 2023-06-30 | 广东电网有限责任公司湛江供电局 | Power equipment abnormality judgment method and device, electronic equipment and storage medium |
| CN116399630A (en) * | 2023-06-06 | 2023-07-07 | 苏州卓晟裕智能科技有限公司 | Operation monitoring management method and system based on equipment working condition |
| CN116399400A (en) * | 2023-04-13 | 2023-07-07 | 大唐绥化热电有限公司 | Method and system for detecting operation faults of boiler unit |
| CN116423005A (en) * | 2023-06-14 | 2023-07-14 | 苏州松德激光科技有限公司 | Tin soldering process optimization method and system for improving welding precision |
| CN116488352A (en) * | 2023-06-20 | 2023-07-25 | 北京航能绿电科技有限公司 | Circuit safety monitoring and early warning method for energy storage power station |
| CN116543357A (en) * | 2023-07-05 | 2023-08-04 | 南通玖方新材料科技有限公司 | Surface defect identification and early warning method and system for solar photovoltaic carrier |
| CN116562508A (en) * | 2023-07-05 | 2023-08-08 | 北京城建设计发展集团股份有限公司 | Optimal critical value acquisition and analysis system based on track traffic station reservation engineering |
| CN116610482A (en) * | 2023-07-18 | 2023-08-18 | 山东理工大学 | Intelligent monitoring method for operation state of electrical equipment |
| CN116699335A (en) * | 2023-06-16 | 2023-09-05 | 广州友智电气技术有限公司 | Partial discharge monitoring method and system for high-voltage power equipment |
| CN116862741A (en) * | 2023-07-25 | 2023-10-10 | 杭州超腾能源技术股份有限公司 | Intelligent monitoring method and system for carbon emission of industrial park |
| CN116859843A (en) * | 2023-07-05 | 2023-10-10 | 安徽如柒信息科技有限公司 | Production equipment fault monitoring method and system based on industrial big data |
| CN116859838A (en) * | 2023-06-28 | 2023-10-10 | 三峡高科信息技术有限责任公司 | Early warning system for monitoring equipment operation condition |
| CN117277592A (en) * | 2023-11-21 | 2023-12-22 | 西安晟昕科技股份有限公司 | Protection switching method for monitoring high-voltage circuit signals |
| CN117269655A (en) * | 2023-11-17 | 2023-12-22 | 国网山东省电力公司东营供电公司 | Transformer substation power equipment temperature anomaly monitoring method, system, terminal and medium |
| CN117312294A (en) * | 2023-11-28 | 2023-12-29 | 深圳汉光电子技术有限公司 | New energy equipment quality monitoring system based on cloud computing |
| CN117375234A (en) * | 2023-10-17 | 2024-01-09 | 国网福建省电力有限公司 | Automatic acceptance method and system for monitoring information of transformer substation |
| CN117436771A (en) * | 2023-12-20 | 2024-01-23 | 天津撒布浪斯探测仪器有限公司 | Intelligent on-line quality monitoring and optimizing control system for vermicular cast iron products |
| CN117620324A (en) * | 2023-12-21 | 2024-03-01 | 杭州新世宝电动转向***有限公司 | Worm gear running-in device of steering gear |
| CN117806912A (en) * | 2024-02-28 | 2024-04-02 | 济南聚格信息技术有限公司 | Method and system for monitoring server abnormality |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101081929B1 (en) * | 2011-03-07 | 2011-11-10 | 박기주 | A distributing switch watch system |
| CN111146865A (en) * | 2019-12-25 | 2020-05-12 | 上海电力大学 | Intelligent monitoring system for operation and maintenance state of power equipment |
| CN111444169A (en) * | 2020-03-30 | 2020-07-24 | 国网江苏省电力有限公司连云港市赣榆区供电分公司 | Transformer substation electrical equipment state monitoring and diagnosis system and method |
| CN112615436A (en) * | 2020-12-24 | 2021-04-06 | 国网北京市电力公司 | Health diagnosis and monitoring system and method for integrated automation device of transformer substation |
| CN112649696A (en) * | 2020-10-26 | 2021-04-13 | 国网河北省电力有限公司邢台供电分公司 | Power grid abnormal state identification method |
| CN112861421A (en) * | 2021-01-08 | 2021-05-28 | 陕西比瑞控制技术设备有限公司 | Intelligent analysis early warning system and method for power equipment |
| CN113536206A (en) * | 2021-07-19 | 2021-10-22 | 国网陕西省电力公司 | Power distribution network area early warning method and system, terminal equipment and readable storage medium |
| CN113595251A (en) * | 2021-09-29 | 2021-11-02 | 北京智盟信通科技有限公司 | Automatic monitoring and early warning system and method for substation power equipment |
| CN114865793A (en) * | 2022-06-01 | 2022-08-05 | 沈强 | Substation equipment intelligent management system and method based on big data |
| CN115423127A (en) * | 2022-08-30 | 2022-12-02 | 南方电网调峰调频发电有限公司西部检修试验分公司 | Power equipment field operation and maintenance method and system based on artificial intelligence |
| CN115426177A (en) * | 2022-09-01 | 2022-12-02 | 北京赛博易安科技有限公司 | Abnormal data detection method and system based on big data |
| CN115549094A (en) * | 2022-12-01 | 2022-12-30 | 速度时空信息科技股份有限公司 | Early warning evaluation method and system for substation equipment of smart power grid |
| CN115643159A (en) * | 2022-11-18 | 2023-01-24 | 奇点创新(江苏)智能科技有限公司 | Equipment abnormity early warning method and system based on edge calculation |
-
2023
- 2023-02-07 CN CN202310070009.9A patent/CN115833400B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101081929B1 (en) * | 2011-03-07 | 2011-11-10 | 박기주 | A distributing switch watch system |
| CN111146865A (en) * | 2019-12-25 | 2020-05-12 | 上海电力大学 | Intelligent monitoring system for operation and maintenance state of power equipment |
| CN111444169A (en) * | 2020-03-30 | 2020-07-24 | 国网江苏省电力有限公司连云港市赣榆区供电分公司 | Transformer substation electrical equipment state monitoring and diagnosis system and method |
| CN112649696A (en) * | 2020-10-26 | 2021-04-13 | 国网河北省电力有限公司邢台供电分公司 | Power grid abnormal state identification method |
| CN112615436A (en) * | 2020-12-24 | 2021-04-06 | 国网北京市电力公司 | Health diagnosis and monitoring system and method for integrated automation device of transformer substation |
| CN112861421A (en) * | 2021-01-08 | 2021-05-28 | 陕西比瑞控制技术设备有限公司 | Intelligent analysis early warning system and method for power equipment |
| CN113536206A (en) * | 2021-07-19 | 2021-10-22 | 国网陕西省电力公司 | Power distribution network area early warning method and system, terminal equipment and readable storage medium |
| CN113595251A (en) * | 2021-09-29 | 2021-11-02 | 北京智盟信通科技有限公司 | Automatic monitoring and early warning system and method for substation power equipment |
| CN114865793A (en) * | 2022-06-01 | 2022-08-05 | 沈强 | Substation equipment intelligent management system and method based on big data |
| CN115423127A (en) * | 2022-08-30 | 2022-12-02 | 南方电网调峰调频发电有限公司西部检修试验分公司 | Power equipment field operation and maintenance method and system based on artificial intelligence |
| CN115426177A (en) * | 2022-09-01 | 2022-12-02 | 北京赛博易安科技有限公司 | Abnormal data detection method and system based on big data |
| CN115643159A (en) * | 2022-11-18 | 2023-01-24 | 奇点创新(江苏)智能科技有限公司 | Equipment abnormity early warning method and system based on edge calculation |
| CN115549094A (en) * | 2022-12-01 | 2022-12-30 | 速度时空信息科技股份有限公司 | Early warning evaluation method and system for substation equipment of smart power grid |
Cited By (41)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115993504A (en) * | 2023-03-23 | 2023-04-21 | 山东盛日电力集团有限公司 | Intelligent fault diagnosis method and system for electrical equipment |
| CN115993807A (en) * | 2023-03-23 | 2023-04-21 | 日照鲁光电子科技有限公司 | Production monitoring optimization control method and system for silicon carbide |
| CN116011794A (en) * | 2023-03-23 | 2023-04-25 | 北京万讯博通科技发展有限公司 | Infrastructure supervision method and system based on cloud operation and maintenance |
| CN115993504B (en) * | 2023-03-23 | 2023-08-18 | 山东盛日电力集团有限公司 | Intelligent fault diagnosis method and system for electrical equipment |
| CN116151521B (en) * | 2023-04-04 | 2023-07-04 | 四川省自然资源科学研究院(四川省生产力促进中心) | Big data information acquisition method and system |
| CN116151521A (en) * | 2023-04-04 | 2023-05-23 | 四川省自然资源科学研究院(四川省生产力促进中心) | Big data information acquisition method and system |
| CN116399400B (en) * | 2023-04-13 | 2023-12-15 | 大唐绥化热电有限公司 | Method and system for detecting operation faults of boiler unit |
| CN116399400A (en) * | 2023-04-13 | 2023-07-07 | 大唐绥化热电有限公司 | Method and system for detecting operation faults of boiler unit |
| CN116345693A (en) * | 2023-04-21 | 2023-06-27 | 沈阳工程学院 | Safety monitoring management method and system for transformer substation |
| CN116359658A (en) * | 2023-05-31 | 2023-06-30 | 广东电网有限责任公司湛江供电局 | Power equipment abnormality judgment method and device, electronic equipment and storage medium |
| CN116399630A (en) * | 2023-06-06 | 2023-07-07 | 苏州卓晟裕智能科技有限公司 | Operation monitoring management method and system based on equipment working condition |
| CN116399630B (en) * | 2023-06-06 | 2023-09-05 | 苏州卓晟裕智能科技有限公司 | Operation monitoring management method and system based on equipment working condition |
| CN116423005A (en) * | 2023-06-14 | 2023-07-14 | 苏州松德激光科技有限公司 | Tin soldering process optimization method and system for improving welding precision |
| CN116423005B (en) * | 2023-06-14 | 2023-10-31 | 苏州松德激光科技有限公司 | Tin soldering process optimization method and system for improving welding precision |
| CN116699335A (en) * | 2023-06-16 | 2023-09-05 | 广州友智电气技术有限公司 | Partial discharge monitoring method and system for high-voltage power equipment |
| CN116699335B (en) * | 2023-06-16 | 2024-03-08 | 广州友智电气技术有限公司 | Partial discharge monitoring method and system for high-voltage power equipment |
| CN116488352B (en) * | 2023-06-20 | 2023-09-12 | 北京航能绿电科技有限公司 | Circuit safety monitoring and early warning method for energy storage power station |
| CN116488352A (en) * | 2023-06-20 | 2023-07-25 | 北京航能绿电科技有限公司 | Circuit safety monitoring and early warning method for energy storage power station |
| CN116859838B (en) * | 2023-06-28 | 2024-02-06 | 三峡高科信息技术有限责任公司 | Early warning system for monitoring equipment operation condition |
| CN116859838A (en) * | 2023-06-28 | 2023-10-10 | 三峡高科信息技术有限责任公司 | Early warning system for monitoring equipment operation condition |
| CN116859843A (en) * | 2023-07-05 | 2023-10-10 | 安徽如柒信息科技有限公司 | Production equipment fault monitoring method and system based on industrial big data |
| CN116543357A (en) * | 2023-07-05 | 2023-08-04 | 南通玖方新材料科技有限公司 | Surface defect identification and early warning method and system for solar photovoltaic carrier |
| CN116562508B (en) * | 2023-07-05 | 2023-10-03 | 北京城建设计发展集团股份有限公司 | Optimal critical value acquisition and analysis system based on track traffic station reservation engineering |
| CN116543357B (en) * | 2023-07-05 | 2023-11-21 | 南通玖方新材料股份有限公司 | Surface defect identification and early warning method and system for solar photovoltaic carrier |
| CN116562508A (en) * | 2023-07-05 | 2023-08-08 | 北京城建设计发展集团股份有限公司 | Optimal critical value acquisition and analysis system based on track traffic station reservation engineering |
| CN116859843B (en) * | 2023-07-05 | 2024-01-09 | 安徽如柒信息科技有限公司 | Production equipment fault monitoring method and system based on industrial big data |
| CN116610482B (en) * | 2023-07-18 | 2023-10-17 | 山东理工大学 | Intelligent monitoring method for operation state of electrical equipment |
| CN116610482A (en) * | 2023-07-18 | 2023-08-18 | 山东理工大学 | Intelligent monitoring method for operation state of electrical equipment |
| CN116862741B (en) * | 2023-07-25 | 2024-05-28 | 杭州超腾能源技术股份有限公司 | Intelligent monitoring method and system for carbon emission of industrial park |
| CN116862741A (en) * | 2023-07-25 | 2023-10-10 | 杭州超腾能源技术股份有限公司 | Intelligent monitoring method and system for carbon emission of industrial park |
| CN117375234A (en) * | 2023-10-17 | 2024-01-09 | 国网福建省电力有限公司 | Automatic acceptance method and system for monitoring information of transformer substation |
| CN117269655A (en) * | 2023-11-17 | 2023-12-22 | 国网山东省电力公司东营供电公司 | Transformer substation power equipment temperature anomaly monitoring method, system, terminal and medium |
| CN117269655B (en) * | 2023-11-17 | 2024-02-06 | 国网山东省电力公司东营供电公司 | Transformer substation power equipment temperature anomaly monitoring method, system, terminal and medium |
| CN117277592B (en) * | 2023-11-21 | 2024-02-13 | 西安晟昕科技股份有限公司 | Protection switching method for monitoring high-voltage circuit signals |
| CN117277592A (en) * | 2023-11-21 | 2023-12-22 | 西安晟昕科技股份有限公司 | Protection switching method for monitoring high-voltage circuit signals |
| CN117312294A (en) * | 2023-11-28 | 2023-12-29 | 深圳汉光电子技术有限公司 | New energy equipment quality monitoring system based on cloud computing |
| CN117436771A (en) * | 2023-12-20 | 2024-01-23 | 天津撒布浪斯探测仪器有限公司 | Intelligent on-line quality monitoring and optimizing control system for vermicular cast iron products |
| CN117436771B (en) * | 2023-12-20 | 2024-03-08 | 天津撒布浪斯探测仪器有限公司 | Intelligent on-line quality monitoring and optimizing control system for vermicular cast iron products |
| CN117620324A (en) * | 2023-12-21 | 2024-03-01 | 杭州新世宝电动转向***有限公司 | Worm gear running-in device of steering gear |
| CN117806912A (en) * | 2024-02-28 | 2024-04-02 | 济南聚格信息技术有限公司 | Method and system for monitoring server abnormality |
| CN117806912B (en) * | 2024-02-28 | 2024-05-14 | 济南聚格信息技术有限公司 | Method and system for monitoring server abnormality |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115833400B (en) | 2023-04-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115833400B (en) | Monitoring and early warning method and system for power equipment of transformer substation | |
| CN105846780B (en) | A kind of photovoltaic module method for diagnosing faults based on decision-tree model | |
| CN109583520B (en) | State evaluation method of cloud model and genetic algorithm optimization support vector machine | |
| CN107273924B (en) | Multi-data fusion power plant fault diagnosis method based on fuzzy clustering analysis | |
| CN105139585A (en) | Intelligent early warning and prediction method for soil slope danger | |
| CN116011703B (en) | Management method and system of dynamic environment monitoring station | |
| CN113036913B (en) | Method and device for monitoring state of comprehensive energy equipment | |
| CN115329812B (en) | Bridge infrastructure anomaly monitoring method based on artificial intelligence | |
| CN112039073B (en) | Collaborative optimization method and system suitable for fault judgment of power distribution room equipment | |
| CN116614177B (en) | Optical fiber state multidimensional parameter monitoring system | |
| CN115643159A (en) | Equipment abnormity early warning method and system based on edge calculation | |
| CN116207845B (en) | Automatic monitoring method and system for protecting power equipment | |
| CN115514679B (en) | Abnormal source monitoring method and system based on communication module | |
| CN114994261A (en) | Remote calibration method for sensor for ambient air monitoring | |
| CN117538710B (en) | Intelligent early warning method and system for local dynamic discharge monitoring | |
| CN118013450A (en) | Photovoltaic optimization system based on total solar radiation calculation | |
| CN117553840A (en) | Instrument based on intelligent management and system thereof | |
| CN118070171A (en) | Safety monitoring method for medium and small reservoirs and dams with multiple data fusion | |
| CN116566839A (en) | Communication resource quality evaluation system for power enterprises | |
| CN110909774A (en) | Power transformation equipment heating defect reason distinguishing method based on Bayesian classification | |
| CN116938676A (en) | Communication risk combined early warning method based on data source analysis | |
| CN111695634A (en) | Data abnormal mutation point detection algorithm based on limited accompanying censoring mechanism | |
| CN116993232B (en) | Energy consumption management optimization method and system for comprehensive energy station | |
| CN116823215B (en) | Intelligent operation and maintenance management and control method and system for power station | |
| CN117870034B (en) | Control method, device and system for environmental parameters of clean room |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |