CN116498435A - Method and device for monitoring use state based on diesel generator set - Google Patents

Method and device for monitoring use state based on diesel generator set Download PDF

Info

Publication number
CN116498435A
CN116498435A CN202310796653.4A CN202310796653A CN116498435A CN 116498435 A CN116498435 A CN 116498435A CN 202310796653 A CN202310796653 A CN 202310796653A CN 116498435 A CN116498435 A CN 116498435A
Authority
CN
China
Prior art keywords
vector
data
attention
feature map
diesel generator
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
Application number
CN202310796653.4A
Other languages
Chinese (zh)
Other versions
CN116498435B (en
Inventor
徐荣
邹清洋
简金鹏
张飞
熊记伟
张玉兴
李金石
冯力东
王喾
王耀辉
马龙
沈业春
张晓辉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xi'an Shanchai Heavy Industry Nuclear Emergency Equipment Co ltd
Shannxi Diesel Engine Heavy Industry Co Ltd
Original Assignee
Xi'an Shanchai Heavy Industry Nuclear Emergency Equipment Co ltd
Shannxi Diesel Engine Heavy Industry Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Xi'an Shanchai Heavy Industry Nuclear Emergency Equipment Co ltd, Shannxi Diesel Engine Heavy Industry Co Ltd filed Critical Xi'an Shanchai Heavy Industry Nuclear Emergency Equipment Co ltd
Priority to CN202310796653.4A priority Critical patent/CN116498435B/en
Publication of CN116498435A publication Critical patent/CN116498435A/en
Application granted granted Critical
Publication of CN116498435B publication Critical patent/CN116498435B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
    • F02B—INTERNAL-COMBUSTION PISTON ENGINES; COMBUSTION ENGINES IN GENERAL
    • F02B77/00—Component parts, details or accessories, not otherwise provided for
    • F02B77/08—Safety, indicating, or supervising devices
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/253—Fusion techniques of extracted features
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Probability & Statistics with Applications (AREA)
  • Computational Linguistics (AREA)
  • Mechanical Engineering (AREA)
  • Combustion & Propulsion (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Chemical & Material Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Testing And Monitoring For Control Systems (AREA)

Abstract

The invention relates to the field of generator set state monitoring, and discloses a method and a device for monitoring the use state based on a diesel generator set, wherein the method comprises the following steps: calculating a distance vector between operation data of the diesel generating set and a preset data matrix; calculating the vector weight of each vector element in the distance vector, and constructing the difference vector according to the vector weight; vector reconstruction is carried out on the difference vector to obtain a reconstructed vector, and a data feature map is generated according to the reconstructed vector by using a preset state monitoring model; performing attention distribution on the data feature map according to an attention layer in the state monitoring model to obtain an attention feature map of the operation data; and carrying out state early warning on the diesel generator based on the attention feature map to obtain the real-time use state of the diesel generator, and carrying out event recording on the real-time use state. The invention can improve the accuracy of monitoring the use state of the diesel generator set.

Description

Method and device for monitoring use state based on diesel generator set
Technical Field
The invention relates to the technical field of generator set state monitoring, in particular to a using state monitoring method and device based on a diesel generator set.
Background
The diesel generator set is energy conversion equipment, converts chemical energy into heat energy, converts the heat energy into mechanical energy and finally converts the mechanical energy into required electric energy, is core equipment for emergency power generation, can provide emergency power supply for safety level equipment under the condition that the power failure of the whole plant is caused by the failure of an external power grid of a nuclear power plant, ensures safe shutdown of the unit, prevents important and critical damage to shutdown equipment, and plays a role in nuclear safety. The background monitoring and diagnosing system is required to monitor the running state of the generator set in the working process of the diesel generator set, so that the abnormal condition of the generator set is found in time, and the continuous safe operation of the generator set is ensured.
However, the existing method for monitoring the use state of the diesel generator set mainly needs an operator to analyze real-time monitoring data based on a computer monitoring system and real-time monitoring data of a state monitoring system in the running process of the diesel generator set so as to judge the use state of the diesel generator set, but the related monitoring and control data has large information quantity, and the fault cause cannot be analyzed timely after the diesel generator set is stopped due to faults, so that the operator needs to have higher knowledge reserve, and the accuracy of monitoring the use state of the diesel generator set by the operator is poor.
Disclosure of Invention
The invention provides a method and a device for monitoring the use state based on a diesel generator set, and mainly aims to improve the accuracy of monitoring the use state of the diesel generator set.
In order to achieve the above object, the present invention provides a method for monitoring a usage state of a diesel generator set, comprising:
when the switching value of the diesel generator set changes, collecting the operation data of the diesel generator set, and calculating a distance vector between the operation data and a preset data matrix;
calculating the vector weight of each vector element in the distance vector, and constructing a difference vector of the operation data according to the vector weight;
the vector weight of each vector element in the distance vector is calculated using the following formula:
；
wherein ,representing the>Vector weights of the individual vector elements, +.>Representing the>The vector elements>Representing preset function parameters;
vector reconstruction is carried out on the difference vector to obtain a reconstructed vector of the difference vector, and a data feature map of the operation data is generated according to the reconstructed vector by using a preset state monitoring model;
Performing attention distribution on the data feature map according to an attention layer in the state monitoring model to obtain an attention feature map of the operation data;
and carrying out state early warning on the diesel generator based on the attention characteristic diagram to obtain the real-time use state of the diesel generator, and carrying out event recording on the real-time use state.
Optionally, the calculating a distance vector between the operation data and a preset data matrix includes:
searching matrix data corresponding to each index data in the operation data in the data matrix;
calculating a data distance between each index data in the operation data and the matrix data;
calculating a data distance between each index data in the operation data and the matrix data using the following formula:
；
wherein ,indicate->Data distance between the individual index data and the matrix data, < >>Representing the +.>Personal index data,/->Indicate->1 st matrix data corresponding to the index data, < >>Indicate->The +.o corresponding to the individual index data>Individual matrix data,/->Indicate->The total number of matrix data corresponding to the index data;
And generating a distance vector between the operation data and the data matrix according to the data distance.
Optionally, the constructing the difference vector of the operation data according to the vector weight includes:
calculating a data difference value corresponding to each index data in the operation data according to the vector weight;
and generating a difference vector of the operation data according to the data difference value.
Optionally, the calculating, according to the vector weight, a data difference value corresponding to each index data in the running data includes:
calculating a data difference value of each index data in the operation data by using the following formula:
；
wherein ,indicate->Data difference value of index data corresponding to each vector element, ">Representing the>Vector weights of the individual vector elements, +.>Indicate->Index data corresponding to each vector element, +.>Representing the total number of index data in the operational data.
Optionally, the performing vector reconstruction on the disparity vector to obtain a reconstructed vector of the disparity vector includes:
vector encoding is carried out on the difference vector by using a preset encoding layer, so that an encoding vector is obtained;
decoding the coded vector to obtain a reconstructed vector of the difference vector;
Decoding the encoded vector using the following formula:
；
wherein ,representing the reconstruction vector, ++>Representing an activation function->Representing preset decoding weights, +.>Representing the coding vector->Representing the cell bias of the hidden layer.
Optionally, the generating the data feature map of the operation data according to the reconstruction vector by using a preset state monitoring model includes:
performing multiple convolution on the reconstruction vector by using a first convolution layer in the state monitoring model to obtain a first convolution diagram and a second convolution diagram;
convolving the first convolution map by using a second convolution layer in the state monitoring model to obtain a first feature map, and convolving the second convolution map by using a third convolution layer in the state monitoring model to obtain a second feature map;
and carrying out feature fusion on the first convolution graph, the first feature graph and the second feature graph to obtain a data feature graph of the operation data.
Optionally, the performing attention distribution on the data feature map according to an attention layer in the state monitoring model to obtain an attention feature map of the operation data, including:
global pooling is carried out on the data feature map to obtain a pooled feature map;
Compressing the pooled feature map by using an attention layer in the state monitoring model to obtain the attention weight of each convolution channel in the pooled feature map;
and correspondingly multiplying the attention weight with a convolution channel of the data feature map to obtain the attention feature map of the operation data.
Optionally, the performing state early warning on the diesel generator based on the attention feature map to obtain a real-time use state of the diesel generator includes:
carrying out global average pooling on the attention feature map to obtain a pooled feature map;
fully connecting the pooled feature images to obtain feature vectors of the attention feature images;
and performing activation calculation on the feature vector to obtain the classification probability of the attention feature map, and selecting a state early warning corresponding to the maximum value of the classification probability as a real-time use state of the diesel generator.
Optionally, the global average pooling of the attention feature map to obtain a pooled feature map includes:
and carrying out global average pooling on the attention characteristic map by using the following formula to obtain a pooled characteristic map:
；
wherein ,the pooling feature map is +. >、/>Characteristic value (not graph) at position junction, -a position junction, and a position junction>Length of the attention profile, < >>A width of the attention profile, < >>Representing the attention profile at +.>、/>Characteristic values of the position junctions.
In order to solve the above problems, the present invention further provides a usage status monitoring device based on a diesel generator set, the device comprising:
the distance vector calculation module is used for collecting the operation data of the diesel generator set when the switching value of the diesel generator set changes and calculating a distance vector between the operation data and a preset data matrix;
the difference vector calculation module is used for calculating the vector weight of each vector element in the distance vector and constructing a difference vector of the operation data according to the vector weight;
the data feature map generation module is used for carrying out vector reconstruction on the difference vector to obtain a reconstructed vector of the difference vector, and generating a data feature map of the operation data according to the reconstructed vector by using a preset state monitoring model;
the attention distribution module is used for distributing the attention to the data feature map according to the attention layer in the state monitoring model to obtain an attention feature map of the operation data;
And the event recording module is used for carrying out state early warning on the diesel generator based on the attention characteristic diagram, obtaining the real-time use state of the diesel generator and carrying out event recording on the real-time use state.
According to the embodiment of the invention, the deviation between the current operation data and the normal data of the diesel generator set can be reflected by calculating the distance vector between the operation data of the diesel engine set and the preset data matrix, so that the state of the diesel generator set is monitored; calculating the vector weight of each vector element in the distance vector, constructing a difference vector according to the vector weight, and accurately calculating the data difference between the operation data and the data in the normal operation state so as to improve the accuracy of state monitoring; the method has the advantages that the original characteristic information of the difference vector can be reserved by carrying out vector reconstruction on the difference vector, meanwhile, the characteristic information can be expanded, the characteristic information with high representation of the reconstructed vector can be extracted by generating a data characteristic diagram, and the characteristic information of the reconstructed vector is extracted in depth to obtain more accurate characteristic information; then, the attention distribution is carried out on the data feature map, so that the effective features in the operation data are improved, and the ineffective features are reduced; therefore, the state early warning can be carried out on the diesel generator according to the attention characteristic diagram, the accurate real-time use state of the diesel generator set is obtained, and the accuracy of monitoring the use state of the diesel generator set is effectively improved. Therefore, the method and the device for monitoring the use state based on the diesel generator set can solve the problem of low accuracy of monitoring the use state of the diesel generator set.
Drawings
FIG. 1 is a flow chart of a method for monitoring usage status of a diesel-electric set according to an embodiment of the present invention;
FIG. 2 is a flow chart of calculating a distance vector according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a method for generating a data feature map according to an embodiment of the present invention;
FIG. 4 is a functional block diagram of a device for monitoring usage status of a diesel-electric set according to an embodiment of the present invention;
the achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The embodiment of the application provides a use state monitoring method based on a diesel generator set. The execution subject of the diesel generator set-based use state monitoring method includes, but is not limited to, at least one of a server, a terminal and the like capable of being configured to execute the method provided by the embodiment of the application. In other words, the method for monitoring the usage status based on the diesel generator set may be performed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
Referring to fig. 1, a flow chart of a method for monitoring a usage status of a diesel generator set according to an embodiment of the invention is shown. In this embodiment, the method for monitoring a usage state based on a diesel generator set includes:
s1, when the switching value of a diesel generator set changes, collecting operation data of the diesel generator set, and calculating a distance vector between the operation data and a preset data matrix.
In the embodiment of the invention, the switching value is the switching state when the on-off signal, the passive signal and the resistance are 0 or infinity; the switching value mainly refers to the opening quantity and the opening quantity, and refers to auxiliary contacts of a device, such as auxiliary contacts of a relay of a temperature controller of a motor, air compressor start-stop, air bottle start-up, protective stop, diesel generator set fault stop and the like; the invention can detect the switching value deflection through the programmable logic controller (Programmable Logic Controller, PLC for short), and timely analyze the cause of the shutdown event of the diesel generator set, thereby facilitating the investigation and the resolution of the use state causing the failure shutdown.
In the embodiment of the invention, the operation data of the diesel generator set is real-time experimental data of the diesel generator set, and comprises high performance indexes and a plurality of functional characteristic indexes required by the operation of the diesel generator set, such as operation monitoring data of voltage, power, energy, air pressure and the like, so that the operation state of the diesel generator set is monitored timely, comprehensively and timely.
In the embodiment of the invention, the operation data of the diesel generating set can be acquired through the lower computer, wherein the lower computer adopts a double-fujit (TwinCAT) technology, can rapidly complete high performance indexes and numerous functional characteristic data required by data acquisition and recording work, can store or backup the recorded data, and can copy the data through a USB interface.
In the embodiment of the invention, the data matrix is composed of monitoring data in a historical normal running state of the diesel generator set, for example, the j data of the i row in the data matrix represents the j data of the i running index of the diesel generator set, and the data distance between the running data and the normal state is calculated through the data matrix to reflect the data difference between the running data and the normal data of the diesel generator set and further reflect the running state of the diesel generator set.
In an embodiment of the present invention, referring to fig. 2, the calculating a distance vector between the operation data and a preset data matrix includes:
s21, searching matrix data corresponding to each index data in the operation data in the data matrix;
s22, calculating the data distance between each index data in the operation data and the matrix data;
S23, generating a distance vector between the operation data and the data matrix according to the data distance.
In the embodiment of the present invention, the data distance is a distance vector obtained by combining the data distances with a vector according to a data distance between each index data in the operation data and the corresponding matrix data in the data matrix, for example, the distance vector may be represented by a vector of 1*n, where each vector element represents a data distance between each index data and the data matrix.
In the embodiment of the invention, the data distance between each index data in the operation data and the matrix data is calculated by using the following formula:
；
wherein ,indicate->Data distance between the individual index data and the matrix data, < >>Representing the +.>Personal index data,/->Indicate->1 st matrix data corresponding to the index data, < >>Indicate->The +.o corresponding to the individual index data>Individual matrix data,/->Indicate->The total number of matrix data corresponding to the individual index data.
In the embodiment of the invention, the deviation between the current operation data and the normal data of the diesel generating set can be reflected by calculating the distance vector between the operation data and the data matrix, and the larger the data distance is, the more the operation of the diesel generating set deviates from the normal operation state, the abnormal state can occur, and further whether the operation state of the diesel generating set is normal or not is judged, so that the use state of the diesel generating set is monitored.
S2, calculating the vector weight of each vector element in the distance vector, and constructing a difference vector of the operation data according to the vector weight.
In the embodiment of the invention, the vector weight represents the importance of each vector element in the distance vector, the importance of each vector element represents the importance of each index data in the diesel generator set, the larger the vector weight is, the more serious the data deviation between the corresponding index data and the data in the normal state is, and the state analysis is required to be performed in a targeted manner so as to obtain a more accurate state monitoring result.
In an embodiment of the present invention, the calculating a vector weight of each vector element in the distance vector includes:
the vector weight of each vector element in the distance vector is calculated using the following formula:
；
wherein ,representing the>Vector weights of the individual vector elements, +.>Representing the>The vector elements>Representing preset function parameters.
In the embodiment of the invention, the vector weight of each vector element is calculated through the formula, the limited dimension data of each vector element is mapped to a high-dimension space, the larger the space distance is, the larger the distance between the vector element and the normal state data is, and then the higher weight is allocated, otherwise, the smaller the space distance is, the smaller the distance between the vector element and the normal state data is, and the allocated vector weight is smaller.
In the embodiment of the invention, the difference vector is a prediction vector for constructing the operation data according to the vector weight and the distance vector, and the difference vector comprehensively represents the data difference between the operation data and the data in the normal operation state, so that the current state of the diesel generator set can be accurately monitored in real time.
In an embodiment of the present invention, the constructing the difference vector of the operation data according to the vector weight includes:
calculating a data difference value corresponding to each index data in the operation data according to the vector weight;
and generating a difference vector of the operation data according to the data difference value.
In the embodiment of the invention, the distance vector represents the distance between each index data in the operation data and the data matrix, and the data difference of each index data in the operation data can be correspondingly calculated through the vector weight of each vector element in the distance vector, so as to construct a difference vector of the operation data.
In the embodiment of the invention, the data difference value of each index data in the operation data is calculated by using the following formula:
；
wherein ,indicate->Index data corresponding to each vector elementData difference value- >Representing the>Vector weights of the individual vector elements, +.>Indicate->Index data corresponding to each vector element, +.>Representing the total number of index data in the operational data.
According to the embodiment of the invention, the data difference between the operation data of the diesel generating set and the data in the normal operation state can be calculated through the difference vector, so that the operation state of the diesel generating set can be accurately monitored.
And S3, carrying out vector reconstruction on the difference vector to obtain a reconstructed vector of the difference vector, and generating a data feature map of the operation data according to the reconstructed vector by using a preset state monitoring model.
In the embodiment of the invention, the vector reconstruction is to perform mapping coding on the difference vector by using a reconstruction layer with a plurality of nerve nodes, so that the reconstruction vector has more characteristic information, has the same physical meaning as the difference vector, and retains the characteristic information of the difference vector.
In the embodiment of the present invention, the performing vector reconstruction on the difference vector to obtain a reconstructed vector of the difference vector includes:
vector encoding is carried out on the difference vector by using a preset encoding layer, so that an encoding vector is obtained;
And decoding the encoded vector to obtain a reconstructed vector of the difference vector.
In the embodiment of the invention, the reconstruction layer comprises a coding layer and a hiding layer, the coding layer and the hiding layer are provided with a plurality of neural nodes for vector mapping, the coding layer is used for coding the difference vector, the hiding layer is used for decoding the coding vector to obtain the reconstruction vector with the same node, and further, the original characteristic information of the difference vector can be maintained and the characteristic information can be expanded to obtain a more accurate reconstruction vector.
In the embodiment of the invention, the encoded vector is decoded by using the following formula:
decoding the encoded vector using the following formula:
；
wherein ,representing the reconstruction vector, ++>Representing an activation function->Representing preset decoding weights, +.>Representing the coding vector->Representing the cell bias of the hidden layer.
In the embodiment of the invention, the state monitoring model is a neural network model with a classification prediction function, wherein the state monitoring model comprises a convolution layer and an attention layer, the reconstruction vector can be converted into a characteristic diagram of n x n through the convolution layer in the state monitoring model, the reconstruction vector is mapped to a high-dimensional space through the characteristic diagram, the characteristic information of high representation of the reconstruction vector can be extracted, and the characteristic information of the reconstruction vector is extracted deeply.
In an embodiment of the present invention, referring to fig. 3, the generating, by using a preset state monitoring model, a data feature map of the operation data according to the reconstruction vector includes:
s31, performing multiple convolution on the reconstruction vector by using a first convolution layer in the state monitoring model to obtain a first convolution diagram and a second convolution diagram;
s32, convolving the first convolution map by using a second convolution layer in the state monitoring model to obtain a first feature map, and convolving the second convolution map by using a third convolution layer in the state monitoring model to obtain a second feature map;
and S33, carrying out feature fusion on the first convolution graph, the first feature graph and the second feature graph to obtain a data feature graph of the operation data.
In the embodiment of the invention, the convolution layers in the state monitoring model are formed by connecting a plurality of convolution layers in parallel, each convolution layer has different convolution step sizes and convolution kernels with filling sizes, for example, the convolution kernel size of a first convolution layer is 1*1, the convolution kernel size of a second convolution layer is 3*3, the convolution kernel size of a third convolution layer is 5*5, the convolution kernels with different sizes are simultaneously carried out, the feature information with different scales can be obtained, further, the feature map with richer feature information can be obtained by the feature-fused data feature map, the accuracy of the state monitoring of the diesel generator set is improved, and the embodiment of the invention can sample the first convolution map, the first feature map and the second feature map to the same size to realize feature fusion.
And S4, performing attention distribution on the data feature map according to an attention layer in the state monitoring model to obtain an attention feature map of the operation data.
In the embodiment of the invention, the attention layer gives different attention weights to each convolution channel in the data feature map, so that the attention distribution is carried out on the data feature map, the effective features are improved, the irrelevant features are reduced, and the monitoring precision of the state monitoring model is improved.
In an embodiment of the present invention, the performing attention allocation on the data feature map according to the attention layer in the state monitoring model to obtain an attention feature map of the operation data includes:
global pooling is carried out on the data feature map to obtain a pooled feature map;
compressing the pooled feature map by using an attention layer in the state monitoring model to obtain the attention weight of each convolution channel in the pooled feature map;
and correspondingly multiplying the attention weight with a convolution channel of the data feature map to obtain the attention feature map of the operation data.
In the embodiment of the invention, the dimension of the data feature map can be reduced through global pooling to obtain a one-dimensional feature map formed by each convolution channel, then the pooled feature map is subjected to full-connection compression processing through an attention layer to obtain the attention weight of each convolution channel, the attention weight is multiplied by the corresponding convolution channel in the data feature map to obtain the attention feature map of operation data, the effective feature in the operation data is improved, for example, the operation data of the charge air inlet pressure in a diesel generator set is abnormal, the operation data of the main cooling water pressure is normal, the charge air inlet pressure is the effective data of the state monitoring of the diesel generator set, and more attention weights are required to be given to improve the accuracy of the state monitoring.
S5, carrying out state early warning on the diesel generator based on the attention characteristic diagram to obtain a real-time use state of the diesel generator, and carrying out event recording on the real-time use state.
In the embodiment of the invention, the state early warning is to monitor the abnormal state of the diesel generator set according to the operation data of the diesel generator set, and upload the real-time use state to a preset upper computer interface for event recording so as to enable professionals to maintain the state of the diesel generator set and ensure the normal operation of the diesel generator set, wherein the upper computer is software for analyzing the cause of the fault shutdown event of the emergency diesel generator set afterwards, and the sequence of the occurrence of the event can be checked on an event monitoring system software interface; meanwhile, the upper computer invokes the operation data recorded by the diesel generator set in an Ethernet communication mode, and stores all the data in a hard disk of an upper computer system, so that the subsequent data invoking and inquiring are convenient.
In the embodiment of the present invention, the performing a state early warning on the diesel generator based on the attention feature map to obtain a real-time use state of the diesel generator includes:
Carrying out global average pooling on the attention feature map to obtain a pooled feature map;
fully connecting the pooled feature images to obtain feature vectors of the attention feature images;
and performing activation calculation on the feature vector to obtain the classification probability of the attention feature map, and selecting a state early warning corresponding to the maximum value of the classification probability as a real-time use state of the diesel generator.
In the embodiment of the invention, the full connection is to flatten the pooled feature map, convert the pooled feature map into one-dimensional vectors, and further map the one-dimensional feature vectors into a pre-constructed state classification space through an activation function to obtain the classification probability of the attention feature map, thereby selecting the corresponding state early warning with the maximum classification probability as the real-time use state of the diesel generator and realizing the real-time state monitoring of the diesel generator set.
In the embodiment of the invention, the attention feature map is subjected to global average pooling by using the following formula to obtain a pooled feature map:
；
wherein ,the pooling feature map is +.>、/>Characteristic value (not graph) at position junction, -a position junction, and a position junction>Length of the attention profile, < >>A width of the attention profile, < > >Representing the attention profile at +.>、/>Characteristic values of the position junctions.
In the embodiment of the invention, the real-time use state of the diesel generator set can be the use state of the diesel generator set such as electrical failure, mechanical failure, low-temperature water system failure, engine abnormality, protective shutdown and the like, and the real-time use state is used for monitoring the state of the diesel generator set in real time, so that a worker can repair the state of the diesel generator set, and the normal work of the diesel generator set is ensured.
In another alternative embodiment of the invention, the real-time use state can be uploaded to a preset upper computer interface to record events, a time stamp for switching value conversion is added, the time stamp and the real-time use state are simultaneously displayed on the upper computer interface to record the use state of the diesel generating set, the reason for the change of the switching value of the diesel generating set is determined, for example, the real-time use state such as electric failure, low control air pressure or just start and stop of an air compressor is determined, the sequence of the real-time use state can be recorded in the upper computer, all data of the event record such as time, use state and the like are intuitively presented, and the system is convenient for workers to check.
According to the embodiment of the invention, the deviation between the current operation data and the normal data of the diesel generator set can be reflected by calculating the distance vector between the operation data of the diesel engine set and the preset data matrix, so that the state of the diesel generator set is monitored; calculating the vector weight of each vector element in the distance vector, constructing a difference vector according to the vector weight, and accurately calculating the data difference between the operation data and the data in the normal operation state so as to improve the accuracy of state monitoring; the method has the advantages that the original characteristic information of the difference vector can be reserved by carrying out vector reconstruction on the difference vector, meanwhile, the characteristic information can be expanded, the characteristic information with high representation of the reconstructed vector can be extracted by generating a data characteristic diagram, and the characteristic information of the reconstructed vector is extracted in depth to obtain more accurate characteristic information; then, the attention distribution is carried out on the data feature map, so that the effective features in the operation data are improved, and the ineffective features are reduced; therefore, the state early warning can be carried out on the diesel generator according to the attention characteristic diagram, the accurate real-time use state of the diesel generator set is obtained, and the accuracy of monitoring the use state of the diesel generator set is effectively improved. Therefore, the use state monitoring method based on the diesel generator set can solve the problem of low use state monitoring accuracy of the diesel generator set.
Fig. 4 is a functional block diagram of a usage status monitoring device based on a diesel generator set according to an embodiment of the present invention.
The use state monitoring device 400 based on the diesel generator set can be installed in electronic equipment. Depending on the functions implemented, the usage monitoring device 400 based on the diesel generator set may include a distance vector calculation module 401, a difference vector calculation module 402, a data feature map generation module 403, an attention distribution module 404, and an event recording module 405. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
In the present embodiment, the functions concerning the respective modules/units are as follows:
the distance vector calculation module 401 is configured to collect operation data of a diesel generator set when a switching value of the diesel generator set changes, and calculate a distance vector between the operation data and a preset data matrix;
the disparity vector calculation module 402 is configured to calculate a vector weight of each vector element in the distance vector, and construct a disparity vector of the operation data according to the vector weight;
The data feature map generating module 403 is configured to perform vector reconstruction on the difference vector to obtain a reconstructed vector of the difference vector, and generate a data feature map of the operation data according to the reconstructed vector by using a preset state monitoring model;
the attention allocation module 404 is configured to allocate attention to the data feature map according to an attention layer in the state monitoring model, so as to obtain an attention feature map of the operation data;
the event recording module 405 is configured to perform state early warning on the diesel generator based on the attention feature map, obtain a real-time usage state of the diesel generator, and perform event recording on the real-time usage state.
In detail, each module in the usage status monitoring device 400 based on a diesel generator set in the embodiment of the present invention adopts the same technical means as the usage status monitoring method based on a diesel generator set described in fig. 1 to 3, and can generate the same technical effects, which is not described herein.
The invention also provides an electronic device which can comprise a processor, a memory, a communication bus and a communication interface, and can also comprise a computer program which is stored in the memory and can run on the processor, such as a use state monitoring method program based on a diesel generator set.
The processor may be formed by an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be formed by a plurality of integrated circuits packaged with the same function or different functions, including one or more central processing units (Central Processing unit, CPU), a microprocessor, a digital processing chip, a graphics processor, a combination of various control chips, and the like. The processor is a Control Unit (Control Unit) of the electronic device, connects various components of the entire electronic device using various interfaces and lines, executes or executes programs or modules stored in the memory (for example, executes a usage state monitoring method program based on a diesel generator set, etc.), and invokes data stored in the memory to perform various functions of the electronic device and process data.
The memory includes at least one type of readable storage medium including flash memory, removable hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory may in some embodiments be an internal storage unit of the electronic device, such as a mobile hard disk of the electronic device. The memory may in other embodiments also be an external storage device of the electronic device, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device. Further, the memory may also include both internal storage units and external storage devices of the electronic device. The memory can be used for storing application software installed in the electronic equipment and various data, such as codes of a using state monitoring method program based on a diesel generating set, and the like, and can be used for temporarily storing data which is output or is to be output.
The communication bus may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory and at least one processor or the like.
The communication interface is used for communication between the electronic equipment and other equipment, and comprises a network interface and a user interface. Optionally, the network interface may include a wired interface and/or a wireless interface (e.g., WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a Display (Display), an input unit such as a Keyboard (Keyboard), or alternatively a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device and for displaying a visual user interface.
Only an electronic device having components is shown, and it will be understood by those skilled in the art that the structures shown in the figures do not limit the electronic device, and may include fewer or more components than shown, or may combine certain components, or a different arrangement of components.
Specifically, the specific implementation method of the above instruction by the processor may refer to descriptions of related steps in the corresponding embodiment of the drawings, which are not repeated herein.
Further, the electronic device integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. The computer readable storage medium may be volatile or nonvolatile. For example, the computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).
The present invention also provides a computer readable storage medium storing a computer program which, when executed by a processor of an electronic device, implements the steps of the diesel-electric set-based usage state monitoring method and apparatus as described above:
Storage media includes both permanent and non-permanent, removable and non-removable media, and information storage may be implemented by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media may include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, read only compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.
In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.

Claims (10)

1. A method for monitoring a usage state of a diesel generator set, the method comprising:
when the switching value of the diesel generator set changes, collecting the operation data of the diesel generator set, and calculating a distance vector between the operation data and a preset data matrix;
calculating the vector weight of each vector element in the distance vector, and constructing a difference vector of the operation data according to the vector weight;
the vector weight of each vector element in the distance vector is calculated using the following formula:
；
wherein ,representing the>Vector weights of the individual vector elements, +.>Representing the first of the distance vectorsThe vector elements>Representing preset function parameters;
vector reconstruction is carried out on the difference vector to obtain a reconstructed vector of the difference vector, and a data feature map of the operation data is generated according to the reconstructed vector by using a preset state monitoring model;
Performing attention distribution on the data feature map according to an attention layer in the state monitoring model to obtain an attention feature map of the operation data;
and carrying out state early warning on the diesel generator based on the attention characteristic diagram to obtain the real-time use state of the diesel generator, and carrying out event recording on the real-time use state.
2. The method for monitoring the usage status of a diesel-electric generator set according to claim 1, wherein the calculating a distance vector between the operation data and a preset data matrix comprises:
searching matrix data corresponding to each index data in the operation data in the data matrix;
calculating a data distance between each index data in the operation data and the matrix data;
calculating a data distance between each index data in the operation data and the matrix data using the following formula:
；
wherein ,indicate->Personal index dataData distance from matrix data, +.>Representing the +.>Personal index data,/->Indicate->1 st matrix data corresponding to the index data, < >>Indicate->The +.o corresponding to the individual index data >Individual matrix data,/->Indicate->The total number of matrix data corresponding to the index data;
and generating a distance vector between the operation data and the data matrix according to the data distance.
3. The diesel-generator-set-based usage state monitoring method according to claim 1, wherein the constructing a difference vector of the operation data according to the vector weights includes:
calculating a data difference value corresponding to each index data in the operation data according to the vector weight;
and generating a difference vector of the operation data according to the data difference value.
4. The method for monitoring the usage status of a diesel generator set according to claim 3, wherein the calculating the data difference value corresponding to each index data in the operation data according to the vector weight comprises:
calculating a data difference value of each index data in the operation data by using the following formula:
；
wherein ,indicate->Data difference value of index data corresponding to each vector element, ">Representing the>Vector weights of the individual vector elements, +.>Indicate->Index data corresponding to each vector element, +.>Representing the total number of index data in the operational data.
5. The method for monitoring a usage state of a diesel generator set according to claim 1, wherein the performing vector reconstruction on the difference vector to obtain a reconstructed vector of the difference vector comprises:
vector encoding is carried out on the difference vector by using a preset encoding layer, so that an encoding vector is obtained;
decoding the coded vector to obtain a reconstructed vector of the difference vector;
decoding the encoded vector using the following formula:
；
wherein ,representing the reconstruction vector, ++>Representing an activation function->Representing preset decoding weights, +.>Representing the coding vector->Representing the cell bias of the hidden layer.
6. The method for monitoring the usage status of a diesel generator set according to claim 1, wherein the generating the data feature map of the operation data according to the reconstruction vector by using a preset status monitoring model comprises:
performing multiple convolution on the reconstruction vector by using a first convolution layer in the state monitoring model to obtain a first convolution diagram and a second convolution diagram;
convolving the first convolution map by using a second convolution layer in the state monitoring model to obtain a first feature map, and convolving the second convolution map by using a third convolution layer in the state monitoring model to obtain a second feature map;
And carrying out feature fusion on the first convolution graph, the first feature graph and the second feature graph to obtain a data feature graph of the operation data.
7. The method for monitoring the usage status of a diesel generator set according to claim 1, wherein the performing attention distribution on the data feature map according to an attention layer in the status monitoring model to obtain an attention feature map of the operation data comprises:
global pooling is carried out on the data feature map to obtain a pooled feature map;
compressing the pooled feature map by using an attention layer in the state monitoring model to obtain the attention weight of each convolution channel in the pooled feature map;
and correspondingly multiplying the attention weight with a convolution channel of the data feature map to obtain the attention feature map of the operation data.
8. The method for monitoring the usage status of the diesel generator set according to claim 1, wherein the step of performing status early warning on the diesel generator based on the attention profile to obtain the real-time usage status of the diesel generator comprises the following steps:
carrying out global average pooling on the attention feature map to obtain a pooled feature map;
Fully connecting the pooled feature images to obtain feature vectors of the attention feature images;
and performing activation calculation on the feature vector to obtain the classification probability of the attention feature map, and selecting a state early warning corresponding to the maximum value of the classification probability as a real-time use state of the diesel generator.
9. The method for monitoring the usage status of a diesel generator set according to claim 8, wherein the global averaging pooling of the attention profile to obtain a pooled profile comprises:
and carrying out global average pooling on the attention characteristic map by using the following formula to obtain a pooled characteristic map:
；
wherein ,the pooling feature map is +.>、/>Characteristic value (not graph) at position junction, -a position junction, and a position junction>Length of the attention profile, < >>A width of the attention profile, < >>Representing the attention profile at +.>、/>Characteristic values of the position junctions.
10. A use state monitoring device based on a diesel generator set, characterized in that the device comprises:
the distance vector calculation module is used for collecting the operation data of the diesel generator set when the switching value of the diesel generator set changes and calculating a distance vector between the operation data and a preset data matrix;
The difference vector calculation module is used for calculating the vector weight of each vector element in the distance vector and constructing a difference vector of the operation data according to the vector weight;
the data feature map generation module is used for carrying out vector reconstruction on the difference vector to obtain a reconstructed vector of the difference vector, and generating a data feature map of the operation data according to the reconstructed vector by using a preset state monitoring model;
the attention distribution module is used for distributing the attention to the data feature map according to the attention layer in the state monitoring model to obtain an attention feature map of the operation data;
and the event recording module is used for carrying out state early warning on the diesel generator based on the attention characteristic diagram, obtaining the real-time use state of the diesel generator and carrying out event recording on the real-time use state.
CN202310796653.4A 2023-07-03 2023-07-03 Method and device for monitoring use state based on diesel generator set Active CN116498435B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310796653.4A CN116498435B (en) 2023-07-03 2023-07-03 Method and device for monitoring use state based on diesel generator set

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310796653.4A CN116498435B (en) 2023-07-03 2023-07-03 Method and device for monitoring use state based on diesel generator set

Publications (2)

Publication Number Publication Date
CN116498435A true CN116498435A (en) 2023-07-28
CN116498435B CN116498435B (en) 2023-09-15

Family

ID=87318843

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310796653.4A Active CN116498435B (en) 2023-07-03 2023-07-03 Method and device for monitoring use state based on diesel generator set

Country Status (1)

Country Link
CN (1) CN116498435B (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH10197404A (en) * 1997-01-08 1998-07-31 Power Reactor & Nuclear Fuel Dev Corp Apparatus for monitoring abnormality of diesel generator
CN207647613U (en) * 2017-06-22 2018-07-24 首帆动力科技股份有限公司 A kind of diesel generating set health state evaluation and display instrument
CN113985284A (en) * 2021-11-25 2022-01-28 海南核电有限公司 System and method for monitoring additional diesel generator of nuclear power station
WO2022050863A1 (en) * 2020-09-01 2022-03-10 Акционерное Общество "Российский Концерн По Производству Электрической И Тепловой Энергии На Атомных Станциях" Method for monitoring the technical condition of a diesel generator when in operation
CN114841580A (en) * 2022-05-12 2022-08-02 新疆大学 Generator fault detection method based on hybrid attention mechanism
CN114856811A (en) * 2022-05-25 2022-08-05 哈尔滨工业大学（威海） Diesel engine air system health assessment method
CN115422970A (en) * 2022-08-29 2022-12-02 华能国际电力开发公司吉林通榆风电分公司 Onshore fan running state monitoring system and method thereof
CN115438694A (en) * 2022-08-18 2022-12-06 兰州理工大学 Fault diagnosis method for wind driven generator with bidirectional wavelet convolution long-time and short-time memory network

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH10197404A (en) * 1997-01-08 1998-07-31 Power Reactor & Nuclear Fuel Dev Corp Apparatus for monitoring abnormality of diesel generator
CN207647613U (en) * 2017-06-22 2018-07-24 首帆动力科技股份有限公司 A kind of diesel generating set health state evaluation and display instrument
WO2022050863A1 (en) * 2020-09-01 2022-03-10 Акционерное Общество "Российский Концерн По Производству Электрической И Тепловой Энергии На Атомных Станциях" Method for monitoring the technical condition of a diesel generator when in operation
CN113985284A (en) * 2021-11-25 2022-01-28 海南核电有限公司 System and method for monitoring additional diesel generator of nuclear power station
CN114841580A (en) * 2022-05-12 2022-08-02 新疆大学 Generator fault detection method based on hybrid attention mechanism
CN114856811A (en) * 2022-05-25 2022-08-05 哈尔滨工业大学（威海） Diesel engine air system health assessment method
CN115438694A (en) * 2022-08-18 2022-12-06 兰州理工大学 Fault diagnosis method for wind driven generator with bidirectional wavelet convolution long-time and short-time memory network
CN115422970A (en) * 2022-08-29 2022-12-02 华能国际电力开发公司吉林通榆风电分公司 Onshore fan running state monitoring system and method thereof

Also Published As

Publication number Publication date
CN116498435B (en) 2023-09-15

Similar Documents

Publication Publication Date Title
CN108537426B (en) Power equipment running state estimation method and device and computer equipment
Kang et al. Big data analytics in China's electric power industry: modern information, communication technologies, and millions of smart meters
CN105637432A (en) Identifying anomalous behavior of a monitored entity
CN111522858A (en) Multi-dimensional state vector-based pumping unit performance degradation early warning method
CN116231871B (en) Power grid situation supervision method, system and storage medium based on digital twinning
CN115730749B (en) Power dispatching risk early warning method and device based on fusion power data
CN115796708A (en) Intelligent quality inspection method, system and medium for big data for engineering construction
CN116428124A (en) Fault diagnosis method based on large number of equipment of same type
CN116498435B (en) Method and device for monitoring use state based on diesel generator set
CN114784882A (en) Unit combination optimization processing method and device
CN116882790B (en) Carbon emission equipment management method and system for mine ecological restoration area
CN106649765A (en) Smart power grid panoramic data analysis method based on big data technology
CN117252108A (en) Data rationality verification method, system and storage medium based on semantic integrity
CN112444697A (en) Power line information monitoring system and method
CN112380641B (en) Emergency diesel engine health state evaluation method and computer terminal
CN114662589A (en) Ammeter fault research and judgment method, device, equipment and readable storage medium
CN114691769A (en) Unstructured data processing method and device of power monitoring system
JP6818658B2 (en) Power system monitoring system, power system monitoring method, and program
CN115877269B (en) Intelligent bus-based power distribution early warning method, device, equipment and storage medium
CN115829543B (en) Method for determining validity of preventive test of power equipment based on fault detection interval
CN114024302B (en) Method and device for evaluating a region
CN117171617A (en) Transformer fault detection method, device, equipment and medium based on power cabinet
CN116010763A (en) Power grid state estimation method, system, computer equipment and storage medium
Al-Suod et al. Marine Electric Generating Plants Control Systems Software Functional Testing
CN117974071A (en) Electric power system intelligent management method and device based on multidimensional analysis

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