CN117411184A - Intelligent command system for emergency treatment of medium-low voltage power supply - Google Patents
Intelligent command system for emergency treatment of medium-low voltage power supply Download PDFInfo
- Publication number
- CN117411184A CN117411184A CN202311395151.7A CN202311395151A CN117411184A CN 117411184 A CN117411184 A CN 117411184A CN 202311395151 A CN202311395151 A CN 202311395151A CN 117411184 A CN117411184 A CN 117411184A
- Authority
- CN
- China
- Prior art keywords
- module
- power supply
- emergency
- data
- supply system
- 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
- 238000011282 treatment Methods 0.000 title claims abstract description 71
- 238000003745 diagnosis Methods 0.000 claims abstract description 53
- 238000007405 data analysis Methods 0.000 claims abstract description 47
- 230000005540 biological transmission Effects 0.000 claims abstract description 40
- 238000012423 maintenance Methods 0.000 claims abstract description 40
- 238000012544 monitoring process Methods 0.000 claims abstract description 27
- 238000004458 analytical method Methods 0.000 claims abstract description 14
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 14
- 238000005457 optimization Methods 0.000 claims abstract description 11
- 238000004891 communication Methods 0.000 claims abstract description 10
- 230000006870 function Effects 0.000 claims description 76
- 238000000034 method Methods 0.000 claims description 44
- 230000008569 process Effects 0.000 claims description 36
- 238000012545 processing Methods 0.000 claims description 27
- 230000002159 abnormal effect Effects 0.000 claims description 18
- 230000008859 change Effects 0.000 claims description 15
- 230000007613 environmental effect Effects 0.000 claims description 13
- 230000005856 abnormality Effects 0.000 claims description 11
- 230000004044 response Effects 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 10
- 230000000694 effects Effects 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 238000011156 evaluation Methods 0.000 claims description 8
- 238000011835 investigation Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 7
- 230000003044 adaptive effect Effects 0.000 claims description 6
- 230000036541 health Effects 0.000 claims description 5
- 230000009471 action Effects 0.000 claims description 3
- 238000012790 confirmation Methods 0.000 claims description 3
- 238000011217 control strategy Methods 0.000 claims description 3
- 238000009795 derivation Methods 0.000 claims description 3
- 238000012804 iterative process Methods 0.000 claims description 3
- 238000007726 management method Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 230000035772 mutation Effects 0.000 claims description 3
- 238000010223 real-time analysis Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 239000002699 waste material Substances 0.000 claims description 3
- 230000002238 attenuated effect Effects 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 12
- 238000001514 detection method Methods 0.000 abstract description 6
- 238000013439 planning Methods 0.000 abstract description 2
- 239000003245 coal Substances 0.000 description 7
- 238000011084 recovery Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 5
- 230000006399 behavior Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000036632 reaction speed Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Human Computer Interaction (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to the field of power resource planning and intelligent algorithms, in particular to an intelligent command system for emergency treatment of medium-low voltage power supply, which comprises a sensor acquisition module, a data transmission module, a data analysis and diagnosis module, a fault diagnosis module, an emergency scheme generation module, a command and control module, a real-time monitoring and optimization module, a communication module, an alarm and notification module, a user interface module, a log recording and analysis module and a maintenance and update module. The system realizes accurate detection, automatic analysis and intelligent command of low-voltage faults in the power supply system by combining the Internet of things technology, an artificial intelligence algorithm and real-time data analysis, so that the power supply is quickly recovered, and the safe and stable operation of the power supply system is ensured.
Description
Technical Field
The invention relates to the field of power resource planning and intelligent algorithms, in particular to an intelligent command system for emergency treatment of medium-low voltage power supply.
Background
In modern society, power supply is regarded as a core support of modern economy and life, and stable and reliable power supply is not available in both industrial production and daily life. While power supply systems often face various failures and risks during operation, these problems can lead to power outages, equipment damage, and even safety accidents. Accordingly, in order to ensure safe, stable and efficient operation of the power supply system, increasing attention is focused on how to cope with various problems that may occur in the power supply system through an intelligent technology.
With the continuous development of information technology, internet of things technology and artificial intelligence technology, the application of intelligent technology in the electric power field is receiving attention. The intelligent sensor is widely applied to real-time data acquisition and monitoring, and meanwhile, the artificial intelligence technology can analyze and predict the state of a power supply system, so that early warning and quick response of faults are realized.
In the traditional power supply system, the detection, diagnosis and treatment of faults usually depend on manual operation, and the problems of low reaction speed, high misjudgment rate and the like exist. This not only affects the operating efficiency of the power supply system, but may also lead to the occurrence of electrical safety accidents.
In addition, as the demand for efficiency and sustainability of power supplies continues to increase, as well as the demand for skill of power system operators increases, there is a need for a technique that can automatically identify personnel's operational behaviors, check operational steps, and provide guidance. This will help to improve the safety, accuracy and efficiency of the operation flow, reducing the risk of accidents caused by manual operations. Meanwhile, the requirements of power supply in the special industry of coal mines on safety are more outstanding. Once the power supply system fails, production interruption can be caused, and mine safety accidents can be caused. Therefore, the fault recovery and emergency treatment of the coal mine power supply system are more urgent, and the application of the medium-low voltage power supply emergency treatment intelligent command system has important significance in the special environments.
Under the research background, the invention develops the medium-low voltage power supply emergency treatment intelligent command system comprehensively applying the technologies of the Internet of things, the artificial intelligence and the data analysis, and aims to realize real-time analysis of the state of a power supply system, automatic diagnosis of faults, intelligent generation of an emergency scheme, automatic identification and verification of personnel operation and quick recovery of the power supply system under the special environment of a coal mine, thereby improving the safety, stability and efficiency of the power supply system.
Disclosure of Invention
Aiming at the problems, the invention aims to provide an intelligent command system for emergency treatment of medium-low voltage power supply.
The aim of the invention is realized by the following technical scheme:
the intelligent command system for the medium-low voltage power supply emergency treatment comprises a sensor acquisition module, a data transmission module, a data analysis and diagnosis module, a fault diagnosis module, an emergency scheme generation module, a command and control module, a real-time monitoring and optimizing module, a communication module, an alarm and notification module, a user interface module, a log recording and analysis module and a maintenance and updating module, wherein the sensor acquisition module is used for deploying a sensor in a power supply system to monitor electrical parameters and environmental information in real time so as to acquire data of the running state of the power supply system; the data transmission module transmits real-time data acquired by the sensor from the site to a server or a central control unit of the system so as to perform data analysis, processing and emergency command; the data analysis and diagnosis module processes the real-time data transmitted from the sensor acquisition module, and processes, diagnoses and analyzes the data by applying artificial intelligence and a data analysis algorithm so as to realize accurate judgment and fault diagnosis of the state of the power supply system; the fault diagnosis module detects, analyzes and diagnoses abnormal conditions and faults in the power supply system to help operators accurately judge the cause of the problem, so that proper emergency treatment measures are adopted; the emergency scheme generating module automatically generates an emergency treatment scheme suitable for various fault conditions according to the data analysis result and the state of the power supply system; the command and control module transmits the generated emergency scheme to operators, and after the emergency scheme is confirmed, the real-time monitoring and optimizing module continuously monitors the state of the power supply system in the emergency treatment process, ensures the execution effect of the emergency scheme, adjusts and optimizes the emergency scheme when necessary to ensure the stable operation of the power supply system, and the communication module is connected with each module in the system to realize the transmission of data, the issuing of instructions and the coordination and communication among the modules; when an abnormal situation, fault or emergency is found, the alarm and notification module sends an alarm and notification to the relevant personnel so that they can take appropriate action quickly; the user interface module provides a platform for operators to interact with the system, so that the operators can monitor the state of the power supply system, execute emergency treatment and check alarm information; the log record and analysis module records operation, event and state information in the running process of the system and provides analysis functions so as to carry out fault investigation, performance evaluation and optimization work, the module records various operations of operators in the system, including emergency treatment operation, configuration change and alarm response, records various events such as faults, alarms and notices occurring in the system, each log entry should contain a time stamp so as to trace the occurrence time of the event, and besides normal operation, the module should also record system abnormality, error and warning conditions so as to carry out fault investigation and record performance data such as response time and processing speed of the system so as to evaluate the running condition of the system; the maintenance and update module is responsible for daily maintenance, upgrading and updating of the system to ensure that the system is always in a good running state and keeps the latest functions and performances, continuously monitors the running state, performance indexes and resource utilization rate of the system, discovers potential problems in time, regularly performs health check on the system to check whether the database, the storage and the network connection are in normal operation, and when the system needs to be added with new functions, loopholes are repaired or performance is improved, the maintenance and update module performs system upgrading operation, and for the part related to hardware, the maintenance and update module coordinates maintenance and replacement of fault equipment operation, and the maintenance and update module provides data backup and restoration functions to prevent data loss and restore the system.
Further, the sensor acquisition module is responsible for deploying sensors in the power supply system, monitoring electrical parameters and environmental information in real time to acquire data of the running state of the power supply system, selecting proper sensor types according to the characteristics and requirements of the power supply system, including a current sensor, a voltage sensor and a temperature sensor, sensing the change of the electrical parameters and the temperature change of the environment, arranging the selected sensors at key positions of the power supply system, including circuit branches, equipment connection points and the inside of a control box, so as to ensure that various electrical parameters and environmental information can be accurately monitored, and acquiring data of the electrical parameters and the environmental information, including current magnitude, voltage value, temperature and humidity data transmitted by the current sensor, the voltage sensor and the temperature sensor, and transmitting the data to a server or a central control unit of the system for processing through the internet of things technology, and carrying out real-time analysis, storage and recording.
Further, the data transmission module transmits real-time data acquired by the sensor to a server or a central control unit of the system from the site so as to perform data analysis, processing and emergency command, in order to reduce bandwidth occupation of data transmission and improve data safety, the data transmission module compresses and encrypts the data, real-time monitoring and emergency processing of the power supply system are performed, the data transmission module needs to ensure timely transmission of the data so as to ensure that the system can quickly respond to any abnormal situation, the data transmission module controls the transmitted data quantity according to the requirement so as to avoid data congestion and resource waste, remote access is supported, operators can acquire real-time data from any place and perform remote monitoring and command, in the transmission process, if network interruption or abnormality occurs, the data transmission module has a data caching and retransmission mechanism, so that the data cannot be lost, an unstable network environment can be met, the stability of the data transmission can be ensured, and the data transmission module can be well integrated with other modules of the system, and meanwhile, the data transmission module is compatible with the existing power supply equipment and network.
Further, the data analysis and diagnosis module processes the real-time data transmitted from the sensor acquisition module, processes, diagnoses and analyzes the data by applying artificial intelligence and a data analysis algorithm, so as to realize accurate judgment and fault diagnosis of the state of the power supply system, and specifically comprises the following steps:
assuming that the training dataset contains N sample points, each sample point is characterized by x i (i=1, 2, …, N) and the corresponding class label is y i ，y i E { -1,1}, defining a minimized objective function as:
wherein C is regularization parameter, the regularization parameter controls punishment force of the model to misclassification samples in the training process, A smaller C.fwdarw.0 will result in some misclassification allowed by the model, while a larger C.fwdarw. +.infinity will force the model to emphasize classification accuracy more, the invention defines C as C= [0.01,100 ]]Wherein C.fwdarw.0.01 denotes that certain misclassification is allowed, C.fwdarw.100 denotes that the forcing model is classified as correctly as possible, max (0, 1-y i (w T x i +b)) 2 Representing sample points (x i ,y i ) Is determined, if the sample points are correctly classified, max (0, 1-y i (w T x i +b)) 2 Is 0, max (0, 1-y i (w T x i +b)) 2 The invention introduces an adaptive weight alpha with a positive value i Multiplying the loss term for each sample point by a corresponding weight, namely:
Wherein alpha is i Representing adaptive weights, reflecting the importance of the sample points, determining the weight of each sample according to certain criteria,is a regularization term for controlling the complexity of the model, preventing the model from overfitting the training data, by limiting the weight vector, w i For the rightThe i-th weight value of the weight vector w;
to pair withSearching an optimal sample point, and defining a searching strategy:
x g+1 ＝x g +γ g *d g *β g
where g is the number of iterations, x g+1 For g+1 iteration sample points, γ is the search step of g < th >, d g Search direction for the g-th iteration, beta g For the searching power of the g time, the searching power is attenuated along with the deviation from the current iteration number, thereby meeting the requirements ofA is peak intensity, sigma is attenuation coefficient, forAt x i ＝x g+1 And (3) expanding:
(x i -x g+1 )+o(x i -x g+1 ) 2
wherein o (x i -x g+1 ) 2 Is a loss factor, and o (x i -x g+1 ) 2 →0,Representing the objective function at x i ＝x g+1 Defining H g+1 The method comprises the following steps:
the inverse matrix of (2) is present: />Adding a proof compensation operator Q g With H g+1 ＝H g +Q g Hold, let->Wherein a is g ，b g The size of (2) is N1, theta 1 And theta 1 The super parameters are:the establishment is found by mathematical derivation:
furthermore, the self-adaptive weight is introduced to be applied to a data analysis and diagnosis module to help identify the state and fault condition of a key power supply system, so that the performance and reliability of the system are improved, and the F1 score and the area under a curve are defined by the classification accuracy, the F1 score and the area under the curve, wherein the F1 score is defined as the F1 score, and the system has the following functions of Define AUC as the area under the curve, with auc= ≡ 0 1 In TRP (FRP) dFPR, PR is the precision rate, call is the recall rate, TPR is the true positive rate, FPR is the false positive rate, and the ith sample feature X is defined i And a target variable Y satisfying length (N) =length (X i ) =length (Y), where length represents the length function, +.>Assuming that each sample contains Z features, there is i ε (0, Z]Defining an optimal information queue R (X; Y) as: /> Wherein p (x) i Y) is a feature X i And a target variable p (x i Y) probability of simultaneous occurrence, p (x) i ) And p (y) are each the respective marginal probabilities, x i Is a characteristic element, satisfies x i ∈{X 1 ,X 2 ,…,X Z Y is a target variable element, defining a margin value Γ, satisfying:
wherein,when N0 is satisfied, 1 is added to N0, N0 is the number of correctly classified samples, A is defined as the classification accuracy, and there is +.>N0 is the number of correctly classified samples, the classification accuracy directly measures the judgment accuracy of the model for different power supply states and fault types, the F1 fraction can ensure that the model can capture important power supply problems while maintaining high accuracy, in emergency treatment, the AUC helps to measure the overall classification performance of the model, the influence of classification threshold values is avoided, and in order to eliminate dimension, a normalized evaluation index matrix Z is constructed:
Wherein A is 1 Represents the classification accuracy of sample 1, A 2 Represents the classification accuracy of sample 2, A N Represents the classification accuracy of the Nth sample, F1 1 Represents the F1 fraction of sample 1, F1 2 Represents the F1 fraction, F1, of sample 2 N Represents the F1 fraction, AUC, of the Nth sample 1 Area under curve, AUC, representing sample 1 2 Under the curve representing sample 2Product AUC N Area under curve, Z, representing the Nth sample A ,Z AUC And respectively defining a comprehensive overall function S for the normalized classification accuracy, the F1 fraction and the area under the curve:
wherein w is A ，w AUC The invention assumes +.A weight of classification accuracy, F1 fraction, area under curve, respectively, to obtain an optimal comprehensive overall function S>μ i ,τ i The mean and standard deviation of the ith weight are respectively used to generate new weight combinations by using weighted average and linear combinationWherein (1)>Child weights for classification accuracy, +.>For parent weight, ε of classification accuracy A For cross parameters of classification accuracy, +.>Child weight for F1 score, +.>Parent weight for F1 score, +.>Cross parameter for F1 score, +.>Is the child weight of the area under the curve, +.>Is the parent weight of the area under the curve, epsilon AUC The present invention then uses a sine function to perform the mutation operation for the crossover parameter of the area under the curve: Wherein eta is the variation amplitude and defines the maximum iteration number G * In the iterative process of each generation, the optimal comprehensive overall function S of the current generation is recorded best And the optimal comprehensive overall function S of the previous generation pbest Calculating the percentage change rate delta S of the comprehensive overall function change: />Increasing the termination threshold Δs th And adjusting according to the mean value and standard deviation: />Wherein->For dynamically adjusted threshold value, l is the adjustment coefficient, delta ΔS Standard deviation of the overall function is integrated.
Further, the emergency scheme generating module automatically generates emergency treatment schemes suitable for various fault conditions according to the data analysis result and the state of the power supply system, the schemes comprise switching, adjusting circuits and maintenance operation steps, so that normal operation of the power supply system is quickly and efficiently restored, the emergency scheme generating module obtains fault diagnosis results from the data analysis and diagnosis module, the results can serve as a basis for generating the emergency scheme, the emergency scheme generating module comprises a preset scheme library, the preset scheme library stores various common fault condition treatment schemes, the schemes are customized and adjusted according to different conditions, the emergency scheme generating module can automatically generate the emergency treatment schemes suitable for the current fault on the basis of obtaining the fault diagnosis results and real-time data, the generated emergency scheme comprises a series of steps, the operation steps of emergency treatment are described in detail, switching, adjusting and maintenance operation are required to be executed, the emergency scheme generating module determines which steps need to be executed firstly according to the priority and sequence of operation so as to minimize the power supply interruption time, the design of the scheme generating module allows operators to adjust and modify according to the actual conditions so as to adapt to different emergency conditions and different conditions and to the actual operation conditions and the optimal result and the generated actual operation conditions.
Further, the command and control module conveys the generated emergency plan to operators, and after the operators confirm the emergency plan, the operators need to confirm to execute the plan after receiving the emergency treatment plan, so that the operators can understand the plan content and are ready to execute the emergency plan, after the operators confirm the plan, the command and control module automatically controls the equipment to switch, adjust and operate so as to resume the normal operation of the power supply system according to the steps in the plan, according to the different plans, the command and control module needs to adopt different control strategies, during the execution of the emergency treatment plan, the command and control module continuously monitors the state of the power supply system so as to ensure the execution effect of each step, and for equipment needing to be remotely operated, the command and control module needs to transmit an operation command to the equipment to realize remote control, if problems occur in the process of executing the emergency treatment plan, the operators can carry out emergency stop operation through the command and control module so as to avoid further damage.
Further, the real-time monitoring and optimizing module continuously monitors the state of the power supply system in the emergency treatment process, ensures the execution effect of the emergency scheme, and adjusts and optimizes the emergency scheme when necessary so as to ensure the stable operation of the power supply system.
Further, the alarm and notification module sends alarms and notifications to related personnel when abnormal conditions, faults or emergency events are found, so that the alarm and notification module can quickly take appropriate measures, the module acquires real-time data from the sensor acquisition module and the data analysis and diagnosis module, detects the abnormal conditions in the power supply system, judges whether the power supply system has faults or not according to the results of the fault diagnosis module, supports different types of alarms including sound alarms, visual alarms (such as flash lamps) and notifications of texts or images, sets different alarm levels according to the emergency degree, so that personnel can carry out corresponding processing according to the severity of the alarms, the alarms are transmitted to the personnel in various modes including mobile phone short messages, mails, app pushing and audible alarm devices, and when the abnormality or the fault is detected, the alarm and notification module can automatically trigger the alarms and notifications without manual intervention, and supports the manual triggering of the alarms by operators so as to notify other personnel to carry out emergency processing.
Furthermore, the user interface module provides a platform for operators to interact with the system, so that the operators can monitor the state of the power supply system, execute emergency treatment and view alarm information, the user interface adopts a graphical interface, so that the operators can interact in the form of charts, images and buttons, the user interface module provides real-time monitoring data display, the operators can know the current state of the power supply system, the generated emergency treatment scheme and the detailed description of each step are displayed, the operators are guided to execute the steps in the emergency scheme, the user interface needs to display alarm and notification information, the operators can know the abnormal conditions in time, for the steps needing manual intervention, the user interface needs to provide buttons for operation confirmation, the operators can understand and confirm the operation, and the user interface has a user right management function, so that the operators with different levels can only access the functions within the right range.
Further, the log record and analysis module records operation, event and state information during the running process of the system and provides analysis functions for fault detection, performance evaluation and optimization, the module records various operations of operators in the system, including emergency treatment operation, configuration change and alarm response, records various events such as faults, alarms and notices occurring in the system, each log entry should contain a timestamp so as to trace the occurrence time of the event, besides normal operation, the module also records system abnormality, error and warning conditions so as to carry out fault detection, and records performance data such as response time and processing speed of the system so as to evaluate the running condition of the system.
Further, the maintenance and update module is responsible for daily maintenance, upgrading and updating of the system to ensure that the system is always in a good running state and maintains the latest functions and performances, the running state, performance indexes and resource utilization rate of the system are continuously monitored, potential problems are timely found, the system is regularly subjected to health check, whether a database, storage and network connection are normally operated or not is checked, when the system needs to be added with new functions, loopholes are repaired or performance is improved, the maintenance and update module performs system upgrading operation, and for the parts related to hardware, the maintenance and update module coordinates maintenance and fault equipment replacement operation, and the maintenance and update module provides data backup and restoration functions to prevent data loss and restore the system.
The invention has the beneficial effects that: the intelligent command system for the medium-low voltage power supply emergency treatment provided by the invention can timely early warn before the occurrence of a fault by monitoring and analyzing the state of the power supply system in real time, and help operators to quickly take emergency measures, so that the occurrence of the accident is avoided. The automatic diagnosis and intelligent emergency scheme generation capability of the system can shorten the fault processing time, relieve the pressure of manual intervention and improve the running stability and reliability of the power supply system. The traditional power supply system fault diagnosis and recovery often need manual inspection and investigation, and is time-consuming and labor-consuming. The intelligent command system can rapidly identify the fault type and position through automatically analyzing the data and the state, help operators to rapidly locate and repair the fault, reduce the power failure time and improve the availability of power supply. In the emergency treatment process, the intelligent command system can identify and check the behaviors of operators in real timeGuiding. This helps to reduce misjudgment and error of personnel operation, improves accuracy and security of operation flow. Operators can operate according to the guidance of the system, and the operation risk is reduced, so that accidents caused by human factors are avoided. The intelligent command system not only can monitor the running state of the power supply system in real time, but also can evaluate and optimize the performance and energy efficiency of the system. By analyzing historical data and trends, the system provides operation suggestions, helps to optimize the operation of the power supply system, reduces energy consumption and improves the power utilization efficiency. In special industries, such as coal mines, the safety and stability requirements for power supply are higher. The intelligent command system can realize the rapid recovery of the faults of the coal mine power supply system, ensure the continuity and the safety of production and make great contribution to the efficient production in special industries. In the data analysis and diagnosis module, the data are processed, diagnosed and analyzed by applying artificial intelligence and data analysis algorithm to realize accurate judgment and fault diagnosis of the state of the power supply system, the invention constructs an objective function, and constrains regularization parameter C, namely C is defined as C= [0.01,100 ] ]Where C0.01 indicates that some misclassification is allowed, C100 indicates that the model is forced to classify as correctly as possible, since a smaller C0 would result in the model allowing some misclassification, while larger C →+++ is forced the model is more emphasis on the accuracy of the classification, to prevent under-fitting or over-fitting of the objective function, regularization parameters are constrained to [0.01,100 ]]Within the interval, by establishing a secondary interval loss max (0, 1-y i (w T x i +b)) 2 Amplifying the deviation result of data classification, and further, the invention adds the self-adaptive weight alpha i Reflecting the importance of the sample points, determining the weight of each sample according to specific criteria, defining a search strategy, adding search power, and the search power decays along with the deviation from the current iteration number, ensuring that the search power is most relevant to the last iteration result, further developing an objective function, further optimizing the objective function, and approximating the inverse of the Herson matrix by using the information of the previous iteration to gradually optimize parameters, wherein the approximation update can accelerate the convergence of the optimizationThe process ensures that the approximated hessian matrix remains positive, the situation that instability or invalidity is generated in the updating direction can be avoided by keeping the positive, the method is more applicable to the processing of large-scale optimization problems, efficient searching and parameter updating can be performed in a high-dimensional space, and the method is insensitive to an initial point. Further, the invention defines classification accuracy, F1 fraction and area under the curve, performs normalization processing for eliminating dimension, defines comprehensive overall function, performs Gaussian distribution for initial samples of weights of the classification accuracy, F1 fraction and area under the curve for obtaining optimal comprehensive overall function value, innovates by utilizing the improved genetic algorithm provided by the invention, uses weighted average and linear combination in a cross operation link to generate new weight combination, adopts sine function to perform variation operation in a variation operation link, more finely controls the variation and evolution process of the weights, thereby more effectively optimizing the comprehensive overall function, and increases the termination threshold delta S in a termination condition link th And the method adjusts according to the mean value and the standard deviation to dynamically and more robustly obtain the optimal solution of the comprehensive overall function. The data analysis module of the intelligent command system can process a large amount of real-time data and historical data, extract useful information from the data, and help a decision maker to make a more intelligent decision. This helps to optimize the operating strategy of the power supply system, improving the scientificity and accuracy of the decision. The introduction of the intelligent command system can promote the power industry to advance to an intelligent direction. The traditional power supply system is upgraded into an intelligent and automatic system through the integrated internet of things and artificial intelligence front technology, so that new power is brought to the development of the power industry.
Drawings
The invention will be further described with reference to the accompanying drawings, in which embodiments do not constitute any limitation on the invention, and other drawings can be obtained by one of ordinary skill in the art without undue effort from the following drawings.
Fig. 1 is a schematic diagram of the structure of the present invention.
Detailed Description
The invention is further described in connection with the following examples.
Referring to fig. 1, the medium-low voltage power supply emergency treatment intelligent command system of the embodiment comprises a sensor acquisition module, a data transmission module, a data analysis and diagnosis module, a fault diagnosis module, an emergency scheme generation module, a command and control module, a real-time monitoring and optimization module, a communication module, an alarm and notification module, a user interface module, a log recording and analysis module and a maintenance and update module, wherein the sensor acquisition module is used for deploying a sensor in a power supply system, and monitoring electrical parameters and environmental information in real time to acquire data of the running state of the power supply system; the data transmission module transmits real-time data acquired by the sensor from the site to a server or a central control unit of the system so as to perform data analysis, processing and emergency command; the data analysis and diagnosis module processes the real-time data transmitted from the sensor acquisition module, and processes, diagnoses and analyzes the data by applying artificial intelligence and a data analysis algorithm so as to realize accurate judgment and fault diagnosis of the state of the power supply system; the fault diagnosis module detects, analyzes and diagnoses abnormal conditions and faults in the power supply system to help operators accurately judge the cause of the problem, so that proper emergency treatment measures are adopted; the emergency scheme generating module automatically generates an emergency treatment scheme suitable for various fault conditions according to the data analysis result and the state of the power supply system; the command and control module transmits the generated emergency scheme to operators, and after the emergency scheme is confirmed, the real-time monitoring and optimizing module continuously monitors the state of the power supply system in the emergency treatment process, ensures the execution effect of the emergency scheme, adjusts and optimizes the emergency scheme when necessary to ensure the stable operation of the power supply system, and the communication module is connected with each module in the system to realize the transmission of data, the issuing of instructions and the coordination and communication among the modules; when an abnormal situation, fault or emergency is found, the alarm and notification module sends an alarm and notification to the relevant personnel so that they can take appropriate action quickly; the user interface module provides a platform for operators to interact with the system, so that the operators can monitor the state of the power supply system, execute emergency treatment and check alarm information; the log record and analysis module records operation, event and state information in the running process of the system and provides analysis functions so as to carry out fault investigation, performance evaluation and optimization work, the module records various operations of operators in the system, including emergency treatment operation, configuration change and alarm response, records various events such as faults, alarms and notices occurring in the system, each log entry should contain a time stamp so as to trace the occurrence time of the event, and besides normal operation, the module should also record system abnormality, error and warning conditions so as to carry out fault investigation and record performance data such as response time and processing speed of the system so as to evaluate the running condition of the system; the maintenance and update module is responsible for daily maintenance, upgrading and updating of the system to ensure that the system is always in a good running state and keeps the latest functions and performances, continuously monitors the running state, performance indexes and resource utilization rate of the system, discovers potential problems in time, regularly performs health check on the system to check whether the database, the storage and the network connection are in normal operation, and when the system needs to be added with new functions, loopholes are repaired or performance is improved, the maintenance and update module performs system upgrading operation, and for the part related to hardware, the maintenance and update module coordinates maintenance and replacement of fault equipment operation, and the maintenance and update module provides data backup and restoration functions to prevent data loss and restore the system.
Specifically, the sensor acquisition module is responsible for deploying sensors in the power supply system, monitoring electrical parameters and environmental information in real time to acquire data of the running state of the power supply system, selecting proper sensor types including a current sensor, a voltage sensor and a temperature sensor according to the characteristics and requirements of the power supply system, sensing the change of the electrical parameters and the temperature change of the environment, arranging the selected sensors at key positions of the power supply system, including circuit branches, equipment connection points and the inside of a control box, so as to ensure that various electrical parameters and environmental information can be accurately monitored, acquiring data of the electrical parameters and the environmental information in real time, including current magnitude, voltage value, temperature and humidity data transmitted by the current sensor, the voltage sensor and the temperature sensor, transmitting the data to a server or a central control unit of the system for processing through the technology of the internet of things, and analyzing, storing and recording in real time.
Specifically, the data transmission module transmits real-time data acquired by the sensor to a server or a central control unit of the system from the site so as to perform data analysis, processing and emergency command, in order to reduce the bandwidth occupation of data transmission and improve the safety of the data, the data transmission module compresses and encrypts the data, real-time monitoring and emergency processing of the power supply system are performed, the data transmission module needs to ensure timely transmission of the data so as to ensure that the system can quickly respond to any abnormal situation, the data transmission module controls the transmitted data quantity according to the requirement so as to avoid data congestion and resource waste, remote access is supported, operators can acquire real-time data from any place and perform remote monitoring and command, in the transmission process, if network interruption or abnormality occurs, the data transmission module has a data caching and retransmission mechanism, ensures that the data cannot be lost, can cope with an unstable network environment, ensures the stability of the data transmission, can be well integrated with other modules of the system, and is compatible with the existing power supply equipment and network.
Preferably, the data analysis and diagnosis module processes the real-time data transmitted from the sensor acquisition module, processes, diagnoses and analyzes the data by applying artificial intelligence and a data analysis algorithm, so as to realize accurate judgment and fault diagnosis of the state of the power supply system, and specifically comprises the following steps:
assuming that the training dataset contains N sample points, each sample point is characterized by x i (i=1, 2, …, N) and the corresponding class label is y i ，y i E { -1,1}, defining a minimized objective function as:
wherein C is regularization parameter, and the regularization parameter control model is in the training processThe punishment force of the model to misclassification samples is smaller C.fwdarw.0, which causes the model to allow some misclassifications, while larger C.fwdarw. +. Infinity forces the model to emphasize classification accuracy more, and the invention defines C as C= [0.01,100 ]]Wherein C.fwdarw.0.01 denotes that certain misclassification is allowed, C.fwdarw.100 denotes that the forcing model is classified as correctly as possible, max (0, 1-y i (w T x i +b)) 2 Representing sample points (x i ,y i ) Is determined, if the sample points are correctly classified, max (0, 1-y i (w T x i +b)) 2 Is 0, max (0, 1-y i (w T x i +b)) 2 The invention introduces an adaptive weight alpha with a positive value i Multiplying the loss term for each sample point by a corresponding weight, namely:
Wherein alpha is i Representing adaptive weights, reflecting the importance of the sample points, determining the weight of each sample according to certain criteria,is a regularization term for controlling the complexity of the model, preventing the model from overfitting the training data, by limiting the weight vector, w i The i-th weight value of the weight vector w;
to pair withSearching an optimal sample point, and defining a searching strategy:
x g+1 ＝x g +γ g *d g *β g
where g is the number of iterations, x g+1 For g+1 iteration sample points, γ is the search step of g < th >, d g Search direction for the g-th iteration, beta g For the g-th search power, the search power decays with the deviation from the current iteration numberSatisfies the following conditionsA is peak intensity, sigma is attenuation coefficient, forAt x i ＝x g+1 And (3) expanding:
(x i -x g+1 )+o(x i -x g+1 ) 2
wherein o (x i -x g+1 ) 2 Is a loss factor, and o (x i -x g+1 ) 2 →0,Representing the objective function at x i ＝x g+1 Defining H g+1 The method comprises the following steps:
the inverse matrix of (2) is present: />Adding a proof compensation operator Q g With H g+1 ＝H g +Q g Hold, let->Wherein a is g ，b g The size of (2) is N1, theta 1 And theta 1 The super parameters are:the establishment is found by mathematical derivation:
preferably, the self-adaptive weight is introduced to be applied to the data analysis and diagnosis module to help identify the critical power supply system state and fault condition, thereby improving the performance and reliability of the system, and the F1 score and the area under the curve are defined by the classification accuracy, the F1 score and the area under the curve, wherein the F1 score is defined as the F1 score, and the power supply system has the following characteristics that Define AUC as the area under the curve, with auc= ≡ 0 1 TRP (FRP) dFPRPR is the precision rate, call is the recall rate, TPR is the true positive rate, FPR is the false positive rate, and the ith sample feature X is defined i And a target variable Y satisfying length (N) =length (X i ) =length (Y), where length represents the length function, +.>Assuming that each sample contains Z features, there is i ε (0, Z]Defining an optimal information queue R (X; Y) as: /> Wherein p (x) i Y) is a feature X i And a target variable p (x i Y) probability of simultaneous occurrence, p (x) i ) And p (y) are each the respective marginal probabilities, x i Is a characteristic element, satisfies x i ∈{X 1 ,X 2 ,…,X Z Y is a target variable element, defining a margin value Γ, satisfying:
wherein,when N0 is satisfied, 1 is added to N0, N0 is the number of correctly classified samples, A is defined as the classification accuracy, and there is +.>Wherein N0 is the number of correctly classified samples, the classification accuracy directly measures the judgment accuracy of the model for different power supply states and fault types, the F1 score can ensure that the model can capture important power supply problems while maintaining high accuracy, in emergency treatment, the AUC helps to measure the overall classification performance of the model, is not influenced by classification threshold values, and in order to eliminate dimension, a normalized evaluation index matrix Z is constructed:
Wherein A is 1 Represents the classification accuracy of sample 1, A 2 Represents the classification accuracy of sample 2, A N Represents the classification accuracy of the Nth sample, F1 1 Represents the F1 fraction of sample 1, F1 2 Represents the F1 fraction, F1, of sample 2 N Represents the F1 fraction, AUC, of the Nth sample 1 Area under curve, AUC, representing sample 1 2 Area under curve, AUC, representing sample 2 N Area under curve, Z, representing the Nth sample A ,Z AUC And respectively defining a comprehensive overall function S for the normalized classification accuracy, the F1 fraction and the area under the curve:
wherein w is A ，w AUC The invention assumes +.A weight of classification accuracy, F1 fraction, area under curve, respectively, to obtain an optimal comprehensive overall function S>Wherein Gauss is a Gaussian function, μ i ,τ i The mean and standard deviation of the i-th weights, respectively, are combined linearly using weighted averages to generate a new combination of weights, with +.>Wherein (1)>Child weights for classification accuracy, +.>For parent weight, ε of classification accuracy A For cross parameters of classification accuracy, +.>Child weight for F1 score, +.>Parent weight for F1 score, +.>Cross parameter for F1 score, +.>Is the child weight of the area under the curve, +.>Is the parent weight of the area under the curve, epsilon AUC The present invention then uses a sine function to perform the mutation operation for the crossover parameter of the area under the curve:wherein eta is the variation amplitude and defines the maximum iteration number G * In the iterative process of each generation, the optimal comprehensive overall function S of the current generation is recorded best And the optimal comprehensive overall function S of the previous generation pbest Calculating the percentage change rate delta S of the comprehensive overall function change: />100%, increase of termination threshold DeltaS th And adjusting according to the mean value and standard deviation: />Wherein->For dynamically adjusted threshold value, l is the adjustment coefficient, delta ΔS Standard deviation of the overall function is integrated.
Specifically, the emergency scheme generating module automatically generates an emergency treatment scheme suitable for various fault conditions according to the result of data analysis and the state of the power supply system, the schemes comprise switching, adjusting circuits and maintenance operation steps, so that normal operation of the power supply system is quickly and efficiently restored, the emergency scheme generating module obtains the result of fault diagnosis from the data analysis and diagnosis module, the result can serve as a basis for generating the emergency scheme, the emergency scheme generating module comprises a preset scheme library, the preset scheme library stores various common fault condition treatment schemes, the schemes are customized and adjusted according to different conditions, the emergency scheme generating module can automatically generate the emergency treatment scheme suitable for the current fault on the basis of obtaining the fault diagnosis result and real-time data, the generated emergency scheme comprises a series of steps, the operation steps of emergency treatment are described in detail, switching, adjusting and maintenance operation are required to be executed, the emergency scheme generating module determines which steps need to be executed firstly according to the priority and sequence of operation so as to minimize the power supply interruption time, the design of the scheme generating module allows operators to adjust and modify according to the actual conditions so as to adapt to different emergency conditions and different conditions and to the actual operation conditions and the optimal result and the generated actual operation conditions.
Specifically, the command and control module conveys the generated emergency scheme to operators, after the emergency scheme is confirmed, the operators need to confirm to execute the scheme after receiving the emergency scheme, the operators are ensured to understand the scheme content and are ready to execute the scheme, after the operators confirm the scheme, the command and control module automatically controls the equipment to switch, adjust and operate so as to resume the normal operation of the power supply system according to the steps in the scheme, according to the different schemes, the command and control module needs to adopt different control strategies, during the execution of the emergency scheme, the command and control module continuously monitors the state of the power supply system so as to ensure the execution effect of each step, and for equipment needing to be remotely operated, the command and control module needs to transmit an operation command to the equipment to realize remote control, if the problem occurs in the process of executing the emergency scheme, the operators can carry out emergency stop operation through the command and control module so as to avoid further damage.
Specifically, the real-time monitoring and optimizing module continuously monitors the state of the power supply system in the emergency treatment process, ensures the execution effect of the emergency scheme, and adjusts and optimizes the emergency scheme when necessary so as to ensure the stable operation of the power supply system.
Specifically, when an abnormal situation, a fault or an emergency is found, the alarm and notification module sends an alarm and a notification to related personnel so that the personnel can quickly take appropriate measures, the module acquires real-time data from the sensor acquisition module and the data analysis and diagnosis module, detects the abnormal situation in the power supply system, judges whether the power supply system has the fault or not according to the result of the fault diagnosis module, supports different types of alarms including an audio alarm, a visual alarm (such as a flashing light) and a notification of a text or an image, sets different alarm levels according to the emergency degree, so that the personnel can carry out corresponding processing according to the severity of the alarm, the alarm can be transmitted to the personnel in various modes including a mobile phone short message, an email, an App push and an audio alarm device, and when the abnormality or the fault is detected, the alarm and notification module can automatically trigger the alarm and the notification without manual intervention, and supports the manual triggering of the alarm by operators so as to notify other personnel to carry out emergency processing.
Specifically, the user interface module provides a platform for operators to interact with the system, so that the operators can monitor the state of the power supply system, execute emergency treatment and view alarm information, the user interface adopts a graphical interface, so that the operators can interact in the form of charts, images and buttons, the user interface module provides real-time monitoring data display, the operators can know the current state of the power supply system, the generated emergency treatment scheme and the detailed description of each step are displayed, the operators are guided to execute the steps in the emergency scheme, the user interface needs to display alarm and notification information, the operators can know the abnormal conditions in time, for the steps needing manual intervention, the user interface needs to provide buttons for operation confirmation, the operators can understand and confirm the operation, and the user interface has a user right management function, so that the operators with different levels can only access the functions within the right range.
Specifically, the log recording and analyzing module records operation, event and state information in the running process of the system and provides analysis functions for fault detection, performance evaluation and optimization, the module records various operations of operators in the system, including emergency treatment operation, configuration change and alarm response, records various events such as faults, alarms and notices occurring in the system, each log entry should contain a timestamp so as to trace the occurrence time of the event, and besides normal operation, the module should also record system abnormality, error and warning conditions so as to carry out fault detection, and record performance data such as response time and processing speed of the system so as to evaluate the running condition of the system.
Specifically, the maintenance and update module is responsible for daily maintenance, upgrading and updating of the system so as to ensure that the system is always in a good running state and keeps the latest functions and performances, continuously monitors the running state, performance indexes and resource utilization rate of the system, finds potential problems in time, regularly carries out health check on the system, checks whether a database, a storage and network connection are normally operated, and when the system needs to be added with a new function, loopholes are repaired or performance is improved, the maintenance and update module carries out system upgrading operation, and for the part related to hardware, the maintenance and update module coordinates maintenance and fault equipment replacement operation, and the maintenance and update module provides data backup and restoration functions so as to prevent data loss and restore the system.
The invention has the beneficial effects that: the intelligent command system for the medium-low voltage power supply emergency treatment provided by the invention can timely early warn before the occurrence of a fault by monitoring and analyzing the state of the power supply system in real time, and help operators to quickly take emergency measures, so that the occurrence of the accident is avoided. The automatic diagnosis and intelligent emergency scheme generation capability of the system can shorten the fault processing time, relieve the pressure of manual intervention and improve the running stability and reliability of the power supply system. The traditional power supply system fault diagnosis and recovery often need manual inspection and investigation, and is time-consuming and labor-consuming. The intelligent command system can rapidly identify the fault type and position through automatically analyzing the data and the state, help operators to rapidly locate and repair the fault, reduce the power failure time and improve the availability of power supply. In the emergency treatment process, the intelligent command system can recognize, check and guide the behaviors of operators in real time. This helps to reduce misjudgment and error of personnel operation, improves accuracy and security of operation flow. Operators can operate according to the guidance of the system, and the operation risk is reduced, so that accidents caused by human factors are avoided. The intelligent command system not only can monitor the running state of the power supply system in real time, but also can evaluate and optimize the performance and energy efficiency of the system. By analyzing historical data and trends, the system provides operation suggestions, helps to optimize the operation of the power supply system, reduces energy consumption and improves the power utilization efficiency. In special industries, such as coal mines, the safety and stability requirements for power supply are higher. The intelligent command system can realize the coal mine power supply system The rapid recovery of the barrier ensures the continuity and the safety of production and makes great contribution to the efficient production in special industries. In the data analysis and diagnosis module, the data are processed, diagnosed and analyzed by applying artificial intelligence and data analysis algorithm to realize accurate judgment and fault diagnosis of the state of the power supply system, the invention constructs an objective function, and constrains regularization parameter C, namely C is defined as C= [0.01,100 ]]Where C0.01 indicates that some misclassification is allowed, C100 indicates that the model is forced to classify as correctly as possible, since a smaller C0 would result in the model allowing some misclassification, while larger C →+++ is forced the model is more emphasis on the accuracy of the classification, to prevent under-fitting or over-fitting of the objective function, regularization parameters are constrained to [0.01,100 ]]Within the interval, by establishing a secondary interval loss max (0, 1-y i (w T x i +b)) 2 Amplifying the deviation result of data classification, and further, the invention adds the self-adaptive weight alpha i Reflecting the importance of sample points, determining the weight of each sample according to a specific standard, defining a search strategy, adding search power, attenuating the search power along with the deviation from the current iteration number, ensuring that the search power is most relevant to the latest iteration result, further expanding an objective function, further optimizing a correction algorithm, and approximating the inverse of an updated hessian matrix by utilizing the information of the previous iteration so as to gradually optimize parameters, wherein the approximation update can accelerate the convergence process of the optimization, ensure that the approximated hessian matrix keeps positive, keep positive, avoid the condition that the update direction is unstable or invalid, be more applicable to processing large-scale optimization problems, perform efficient search and parameter update in a high-dimensional space, and be insensitive to the initial point. Further, the invention defines the classification accuracy, the F1 fraction and the area under the curve, performs normalization processing for eliminating the dimension, defines the comprehensive overall function, performs Gaussian distribution on the initial samples of the classification accuracy, the F1 fraction and the weight of the area under the curve for obtaining the optimal comprehensive overall function value, and creates by utilizing the improved genetic algorithm provided by the invention The new weight combination is generated by using weighted average and linear combination in the cross operation link, the variation operation is carried out by adopting a sine function in the variation operation link, the variation and evolution process of the weight are controlled more finely, thereby optimizing the comprehensive overall function more effectively, and the termination threshold delta S is increased in the termination condition link th And the method adjusts according to the mean value and the standard deviation to dynamically and more robustly obtain the optimal solution of the comprehensive overall function. The data analysis module of the intelligent command system can process a large amount of real-time data and historical data, extract useful information from the data, and help a decision maker to make a more intelligent decision. This helps to optimize the operating strategy of the power supply system, improving the scientificity and accuracy of the decision. The introduction of the intelligent command system can promote the power industry to advance to an intelligent direction. The traditional power supply system is upgraded into an intelligent and automatic system through the integrated internet of things and artificial intelligence front technology, so that new power is brought to the development of the power industry.
Finally, it should be noted that the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the scope of the present invention, 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 or equivalent substitutions can 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. The intelligent command system for the medium-low voltage power supply emergency treatment is characterized by comprising a sensor acquisition module, a data transmission module, a data analysis and diagnosis module, a fault diagnosis module, an emergency scheme generation module, a command and control module, a real-time monitoring and optimization module, a communication module, an alarm and notification module, a user interface module, a log recording and analysis module and a maintenance and update module, wherein the sensor acquisition module is used for deploying a sensor in a power supply system and monitoring electrical parameters and environmental information in real time so as to acquire data of the running state of the power supply system; the data transmission module transmits real-time data acquired by the sensor from the site to a server or a central control unit of the system so as to perform data analysis, processing and emergency command; the data analysis and diagnosis module processes the real-time data transmitted from the sensor acquisition module, and processes, diagnoses and analyzes the data by applying artificial intelligence and a data analysis algorithm so as to realize accurate judgment and fault diagnosis of the state of the power supply system; the fault diagnosis module detects, analyzes and diagnoses abnormal conditions and faults in the power supply system to help operators accurately judge the cause of the problem, so that proper emergency treatment measures are adopted; the emergency scheme generating module automatically generates an emergency treatment scheme suitable for various fault conditions according to the data analysis result and the state of the power supply system; the command and control module transmits the generated emergency scheme to operators, and after the emergency scheme is confirmed, the real-time monitoring and optimizing module continuously monitors the state of the power supply system in the emergency treatment process, ensures the execution effect of the emergency scheme, adjusts and optimizes the emergency scheme when necessary to ensure the stable operation of the power supply system, and the communication module is connected with each module in the system to realize the transmission of data, the issuing of instructions and the coordination and communication among the modules; when an abnormal situation, fault or emergency is found, the alarm and notification module sends an alarm and notification to the relevant personnel so that they can take appropriate action quickly; the user interface module provides a platform for operators to interact with the system, so that the operators can monitor the state of the power supply system, execute emergency treatment and check alarm information; the log record and analysis module records operation, event and state information in the running process of the system and provides analysis functions so as to carry out fault investigation, performance evaluation and optimization work, the module records various operations of operators in the system, including emergency treatment operation, configuration change and alarm response, records various events such as faults, alarms and notices occurring in the system, each log entry should contain a time stamp so as to trace the occurrence time of the event, and besides normal operation, the module should also record system abnormality, error and warning conditions so as to carry out fault investigation and record performance data such as response time and processing speed of the system so as to evaluate the running condition of the system; the maintenance and update module is responsible for daily maintenance, upgrading and updating of the system to ensure that the system is always in a good running state and keeps the latest functions and performances, continuously monitors the running state, performance indexes and resource utilization rate of the system, discovers potential problems in time, regularly performs health check on the system to check whether the database, the storage and the network connection are in normal operation, and when the system needs to be added with new functions, loopholes are repaired or performance is improved, the maintenance and update module performs system upgrading operation, and for the part related to hardware, the maintenance and update module coordinates maintenance and replacement of fault equipment operation, and the maintenance and update module provides data backup and restoration functions to prevent data loss and restore the system.
2. The intelligent command system for medium-low voltage power supply emergency treatment according to claim 1, wherein the sensor acquisition module is responsible for deploying sensors in a power supply system, monitoring electrical parameters and environmental information in real time to acquire data of the running state of the power supply system, selecting proper sensor types according to the characteristics and requirements of the power supply system, including a current sensor, a voltage sensor and a temperature sensor, capable of sensing changes of the electrical parameters and changes of the environmental temperature, arranging the selected sensors at key positions of the power supply system, including circuit branches, equipment connection points and inside a control box, so as to ensure that various electrical parameters and environmental information can be accurately monitored, acquiring data of the electrical parameters and the environmental information in real time, including current values, voltage values, temperature and humidity data transmitted by the current sensor, the voltage sensor and the temperature sensor, transmitting the data to a server or a central control unit of the system for processing, and performing real-time analysis, storage and recording.
3. The intelligent command system for emergency treatment of medium and low voltage power supply according to claim 1, wherein the data transmission module transmits real-time data acquired by the sensor from the site to a server or a central control unit of the system so as to perform data analysis, processing and emergency command, the data transmission module compresses and encrypts the data in order to reduce the bandwidth occupation of data transmission and improve the safety of the data, the data transmission module needs to ensure the real-time monitoring and emergency processing of the power supply system, the data transmission module ensures the timely transmission of the data so as to ensure the system to quickly respond to any abnormal situation, the data transmission module controls the transmitted data amount according to the requirement so as to avoid data congestion and resource waste, supports remote access, enables operators to acquire real-time data from any place and perform remote monitoring and command, and in the transmission process, if network interruption or abnormality occurs, the data transmission module has a data caching and retransmission mechanism so as to ensure that the data cannot be lost, can cope with an unstable network environment with a certain adaptability so as to ensure the stability of the data transmission, and can be well integrated with other modules of the system and compatible with the existing power supply equipment and network.
4. The intelligent command system for emergency treatment of medium and low voltage power supply according to claim 1, wherein the data analysis and diagnosis module processes the real-time data transmitted from the sensor acquisition module, and processes, diagnoses and analyzes the data by applying artificial intelligence and data analysis algorithm to realize accurate judgment and fault diagnosis of the state of the power supply system, and the data analysis and diagnosis module is specifically as follows:
assuming that the training dataset contains N sample points, each sample point is characterized by x i (i=1, 2, …, N) and the corresponding class label is y i ，y i E { -1,1}, defining a minimized objective function as:
wherein C is regularization parameter, regularization parameter controls punishment force of model to misclassification sample in training process, smaller C.fwdarw.0 can lead to model to allow some misclassification, larger C.fwdarw. +.infinity can force model to emphasize classification accuracy more, the invention defines C as C= [0.01, 100]Wherein C.fwdarw.0.01 denotes that certain misclassification is allowed, C.fwdarw.100 denotes that the forcing model classifies as correctly as possible，max(0，1-y i (w T x i +b)) 2 Representing sample points (x i ，y i ) Is determined, if the sample points are correctly classified, max (0, 1-y i (w T x i +n)) 2 Is 0, max (0, 1-y i (w T x i +n)) 2 The invention introduces an adaptive weight alpha with a positive value i Multiplying the loss term for each sample point by a corresponding weight, namely:
wherein alpha is i Representing adaptive weights, reflecting the importance of the sample points, determining the weight of each sample according to certain criteria,is a regularization term for controlling the complexity of the model, preventing the model from overfitting the training data, by limiting the weight vector, w i The i-th weight value of the weight vector w;
to pair withSearching an optimal sample point, and defining a searching strategy:
x g+1 ＝x g +γ g *d g *β g
where g is the number of iterations, x g+1 For g+1 iteration sample points, γ is the search step of g < th >, d g Search direction for the g-th iteration, beta g For the searching power of the g time, the searching power is attenuated along with the deviation from the current iteration number, thereby meeting the requirements ofA is peak intensity, sigma is attenuation coefficient, forAt x i ＝x g+1 And (3) expanding:
(x i -x g+1 )+o(x i -x g+1 ) 2
wherein o (x i -x g+1 ) 2 Is a loss factor, and o (x i -x g+1 ) 2 →0，Representing the objective function at x i ＝x g+1 Defining H g+1 The method comprises the following steps:
the inverse matrix of (2) is present:adding a proof compensation operator Q g With H g+1 ＝H g +Q g Hold, let->Wherein a is g ，b g The size of (2) is N1, theta 1 And theta 1 The super parameters are:the establishment is found by mathematical derivation:
5. the intelligent command system for emergency treatment of medium and low voltage power supply according to claim 4, wherein the self-adaptive weight is introduced to be applied in the data analysis and diagnosis module to help identify the state and fault condition of the key power supply system, thereby improving the performance and reliability of the system, and the F1 score and the area under the curve are defined by the classification accuracy, the F1 score and the area under the curve, wherein the F1 score is defined as the F1 score, and the data analysis and diagnosis module comprises Define AUC as area under curve, with +.>Wherein PR is the precision rate, call is the recall rate, TPR is the true positive rate, FPR is the false positive rate, and the ith sample feature X is defined i And a target variable Y satisfying length (N) =length (X i ) =length (Y), where length represents the length function, +.>Assuming that each sample contains Z features, there is i ε (0, Z]Defining an optimal information queue R (X; Y) as: /> Wherein p (x) i Y) is a feature X i And a target variable p (x i Y) probability of simultaneous occurrence, p (x) i ) And p (y) are each the respective marginal probabilities, x i Is a characteristic element, satisfies x i ∈{X 1 ，X 2 ，...，X Z Y is a target variable element, and a margin value Γ is defined to satisfy：
Wherein,when N0 is satisfied, 1 is added to N0, N0 is the number of correctly classified samples, A is defined as the classification accuracy, and there is +.>N0 is the number of correctly classified samples, the classification accuracy directly measures the judgment accuracy of the model for different power supply states and fault types, the F1 fraction can ensure that the model can capture important power supply problems while maintaining high accuracy, in emergency treatment, the AUC helps to measure the overall classification performance of the model, the influence of classification threshold values is avoided, and in order to eliminate dimension, a normalized evaluation index matrix Z is constructed:
Wherein A is 1 Represents the classification accuracy of sample 1, A 2 Represents the classification accuracy of sample 2, A N Represents the classification accuracy of the Nth sample, F1 1 Represents the F1 fraction of sample 1, F1 2 Represents the F1 fraction, F1, of sample 2 N Represents the F1 fraction, AUC, of the Nth sample 1 Area under curve, AUC, representing sample 1 2 Area under curve, AUC, representing sample 2 N Area under curve, Z, representing the Nth sample A ，Z AUC And respectively defining a comprehensive overall function S for the normalized classification accuracy, the F1 fraction and the area under the curve:
wherein w is A ，w AUC The invention assumes +.A weight of classification accuracy, F1 fraction, area under curve, respectively, to obtain an optimal comprehensive overall function S>Wherein Gauss is a Gaussian function, μ i ，τ i The mean and standard deviation of the f weight are respectively used for generating a new weight combination by using weighted average and linear combination, and the new weight combination is provided withWherein (1)>Child weights for classification accuracy, +.>For parent weight, ε of classification accuracy A For cross parameters of classification accuracy, +.>Child weight for F1 score, +.>Parent weight for F1 score, +.>Cross parameter for F1 score, +.>Is the child weight of the area under the curve, +.>Is the parent weight of the area under the curve, epsilon AUC The present invention then uses a sine function to perform the mutation operation for the crossover parameter of the area under the curve:wherein eta is the variation amplitude and defines the maximum iteration number G * In the iterative process of each generation, the optimal comprehensive overall function S of the current generation is recorded best And the optimal comprehensive overall function S of the previous generation pbest Calculating the percentage change rate delta S of the comprehensive overall function change: /> Increasing the termination threshold Δs th And adjusting according to the mean value and standard deviation: />Wherein->For dynamically adjusted threshold value, l is the adjustment coefficient, delta ΔS Standard deviation of the overall function is integrated.
6. The intelligent command system for emergency treatment of medium and low voltage power supply according to claim 1, wherein the emergency plan generating module automatically generates emergency treatment plans suitable for various fault conditions according to the result of data analysis and the state of the power supply system, the plans comprise switching, adjusting circuits and maintenance operation steps to quickly and efficiently restore the normal operation of the power supply system, the emergency plan generating module obtains the result of fault diagnosis from the data analysis and diagnosis module, the result can be used as the basis for generating the emergency plan, the emergency plan generating module comprises a preset plan library, the preset plan library stores the treatment plans of various common fault conditions, the plans are customized and adjusted according to different conditions, the emergency plan generating module can automatically generate the emergency treatment plan suitable for the current fault on the basis of obtaining the fault diagnosis result and real-time data, the generated emergency plan comprises a series of steps, the operation steps of emergency treatment are described in detail, the switching, the adjustment and the maintenance operation are required to be executed, the steps are required to be executed first according to the priority and the sequence of operation, the emergency plan generating module determines which steps are required to be executed first, the emergency power supply time is required to be minimized, the emergency plan generating module is required to be modified according to the actual condition and the optimal condition is not allowed to be continuously adjusted according to the actual condition and the actual condition.
7. The intelligent command system for emergency treatment of medium and low voltage power supply according to claim 1, wherein the command and control module transmits the generated emergency solution to operators, and after confirming the emergency solution, the operators need to confirm to execute the solution after receiving the emergency solution, ensure that the operators understand the solution content and are ready to execute, after confirming the solution, the command and control module automatically controls the equipment to switch, adjust and operate so as to resume the normal operation of the power supply system according to the steps in the solution, the command and control module needs to adopt different control strategies according to the different schemes, the command and control module continuously monitors the state of the power supply system during the execution of the emergency solution so as to ensure the execution effect of each step, and for the equipment needing to be remotely operated, the command and control module needs to transmit an operation command to the equipment to realize remote control, if problems occur in the process of executing the emergency solution, the operators can carry out emergency stop operation through the command and control module so as to avoid further damage.
8. The intelligent command system for emergency treatment of medium and low voltage power supply according to claim 1, wherein the real-time monitoring and optimizing module continuously monitors the state of the power supply system during the emergency treatment process, ensures the execution effect of the emergency scheme, and adjusts and optimizes the power supply system when necessary to ensure the stable operation of the power supply system.
9. An intelligent command system for emergency treatment of medium and low voltage power supply according to claim 1, characterized in that the alarm and notification module sends alarms and notifications to related personnel when abnormal conditions, faults or emergency events are found so that they can take appropriate measures quickly, the module obtains real-time data from the sensor acquisition module and the data analysis and diagnosis module, detects abnormal conditions in the power supply system, judges whether the power supply system has faults and the type and position of the faults according to the result of the fault diagnosis module, supports different types of alarms, including acoustic alarms, visual alarms and notifications of texts or images, the alarm and notification module sets different alarm levels according to the emergency level so that personnel can carry out corresponding treatment according to the severity of the alarms, the alarms are transmitted to the personnel in various manners, including mobile phone short messages, mails, app pushes and acoustic alarm devices, and when the abnormality or fault is detected, the alarm and notification module can trigger the alarms automatically without manual intervention, and supports the manual triggering of the alarms by operators so that other personnel are notified to carry out emergency treatment.
10. The intelligent command system for emergency treatment of medium and low voltage power supply according to claim 1, wherein the user interface module provides a platform for operators to interact with the system, so that the operators can monitor the state of the power supply system, execute emergency treatment and view alarm information, the user interface adopts a graphical interface so that the operators can interact in the form of charts, images and buttons, the user interface module provides real-time monitoring data display, the operators can know the current state of the power supply system, the generated emergency treatment scheme and the detailed description of each step are displayed, the operators are guided to execute the steps in the emergency scheme, the user interface needs to display alarm and notification information, the operators can know the abnormal conditions in time, the user interface needs to provide operation confirmation buttons for the steps needing manual intervention, the operators can understand and confirm the operation, and the user interface has user authority management functions so as to ensure that the personnel with different levels can only access the functions within the authority range.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311395151.7A CN117411184B (en) | 2023-10-26 | Intelligent command system for emergency treatment of medium-low voltage power supply |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311395151.7A CN117411184B (en) | 2023-10-26 | Intelligent command system for emergency treatment of medium-low voltage power supply |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117411184A true CN117411184A (en) | 2024-01-16 |
| CN117411184B CN117411184B (en) | 2024-05-03 |
Family
ID=
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100169030A1 (en) * | 2007-05-24 | 2010-07-01 | Alexander George Parlos | Machine condition assessment through power distribution networks |
| CN102607643A (en) * | 2012-01-18 | 2012-07-25 | 西安交通大学 | Overheat fault diagnosis and early warning system and method for electrical equipment of traction substation of electrified railway |
| CN111476299A (en) * | 2020-04-07 | 2020-07-31 | 国家电网有限公司华东分部 | Improved convolutional neural network and power grid intelligent alarm system based on same |
| US20200327206A1 (en) * | 2019-04-12 | 2020-10-15 | General Electric Company | Systems and methods for distributed power system model calibration |
| US20220357729A1 (en) * | 2021-04-23 | 2022-11-10 | General Electric Company | Systems and methods for global cyber-attack or fault detection model |
| CN115640698A (en) * | 2022-11-09 | 2023-01-24 | 浙江水利水电学院 | Fault early warning system for hydropower station operation equipment |
| CN115693911A (en) * | 2022-06-27 | 2023-02-03 | 国网浙江省电力有限公司嘉兴供电公司 | Equipment state sensing system of power distribution network |
| US20230162123A1 (en) * | 2018-02-17 | 2023-05-25 | Electro Industries/Gauge Tech | Devices, systems and methods for cost management and risk mitigation in power distribution systems |
| CN116545123A (en) * | 2023-07-06 | 2023-08-04 | 七星电气股份有限公司 | Comprehensive monitoring system for ring main unit |
| CN116739562A (en) * | 2023-06-15 | 2023-09-12 | 国网安徽省电力有限公司宿州供电公司 | LSTM-based power distribution network stability operation and maintenance method |
| CN116881083A (en) * | 2023-07-21 | 2023-10-13 | 国网河北省电力有限公司邢台供电分公司 | Information resource sharable distribution network equipment management system |
| CN116914917A (en) * | 2023-05-31 | 2023-10-20 | 深圳市宝安爱德电气有限公司 | Big data-based monitoring and management system for operation state of power distribution cabinet |
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100169030A1 (en) * | 2007-05-24 | 2010-07-01 | Alexander George Parlos | Machine condition assessment through power distribution networks |
| CN102607643A (en) * | 2012-01-18 | 2012-07-25 | 西安交通大学 | Overheat fault diagnosis and early warning system and method for electrical equipment of traction substation of electrified railway |
| US20230162123A1 (en) * | 2018-02-17 | 2023-05-25 | Electro Industries/Gauge Tech | Devices, systems and methods for cost management and risk mitigation in power distribution systems |
| US20200327206A1 (en) * | 2019-04-12 | 2020-10-15 | General Electric Company | Systems and methods for distributed power system model calibration |
| CN111476299A (en) * | 2020-04-07 | 2020-07-31 | 国家电网有限公司华东分部 | Improved convolutional neural network and power grid intelligent alarm system based on same |
| US20220357729A1 (en) * | 2021-04-23 | 2022-11-10 | General Electric Company | Systems and methods for global cyber-attack or fault detection model |
| CN115693911A (en) * | 2022-06-27 | 2023-02-03 | 国网浙江省电力有限公司嘉兴供电公司 | Equipment state sensing system of power distribution network |
| CN115640698A (en) * | 2022-11-09 | 2023-01-24 | 浙江水利水电学院 | Fault early warning system for hydropower station operation equipment |
| CN116914917A (en) * | 2023-05-31 | 2023-10-20 | 深圳市宝安爱德电气有限公司 | Big data-based monitoring and management system for operation state of power distribution cabinet |
| CN116739562A (en) * | 2023-06-15 | 2023-09-12 | 国网安徽省电力有限公司宿州供电公司 | LSTM-based power distribution network stability operation and maintenance method |
| CN116545123A (en) * | 2023-07-06 | 2023-08-04 | 七星电气股份有限公司 | Comprehensive monitoring system for ring main unit |
| CN116881083A (en) * | 2023-07-21 | 2023-10-13 | 国网河北省电力有限公司邢台供电分公司 | Information resource sharable distribution network equipment management system |
Non-Patent Citations (3)
| Title |
|---|
| 夏洪刚;郭红兵;肖金超;: "基于CNN的电力变压器故障诊断方法", 电子设计工程, no. 13, 5 July 2020 (2020-07-05) * |
| 张雷;: "基于PSO-LSSVM的牵引供电系统故障诊断研究", 机车电传动, no. 03, 10 May 2019 (2019-05-10), pages 51 - 59 * |
| 王运通;徐斌;: "中频供电微机自动监测系统的研究与实现", 中国核科技报告, no. 01, 15 June 2007 (2007-06-15), pages 174 - 184 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101713985B1 (en) | Method and apparatus for prediction maintenance | |
| CN113298278A (en) | Power equipment with self-health state prediction function, self-health state prediction method thereof and cloud server | |
| US20210232104A1 (en) | Method and system for identifying and forecasting the development of faults in equipment | |
| CN110991799A (en) | Comprehensive early warning method for power distribution network production | |
| WO2024065988A1 (en) | Device monitoring method and system, electronic device, and storage medium | |
| CN117055502A (en) | Intelligent control system based on Internet of things and big data analysis | |
| CN115826469A (en) | Automatic valve control method and system | |
| KR102296568B1 (en) | Swithchboard Management And Control System based on Machine Learning | |
| KR102296561B1 (en) | Integrated Management And Control System for Swithchboard based on Artificial Intelligence using Zigbee | |
| CN117411184B (en) | Intelligent command system for emergency treatment of medium-low voltage power supply | |
| CN117411184A (en) | Intelligent command system for emergency treatment of medium-low voltage power supply | |
| CN116683648B (en) | Intelligent power distribution cabinet and control system thereof | |
| CN116071902B (en) | Method, equipment and medium for monitoring power equipment of machine room | |
| Brown et al. | Learning models of plant behavior for anomaly detection and condition monitoring | |
| CN116596322A (en) | Property equipment management method and system based on big data visualization | |
| CN115456041A (en) | Equipment fault early warning method and device, computing equipment and storage medium | |
| CN114970950A (en) | Fan fault alarm method and device, storage medium and electronic equipment | |
| CN115409100A (en) | Method, device, medium and equipment for generating power accident emergency scheme | |
| JP2022134340A (en) | Peripheral apparatus, monitoring system, monitoring method, and program | |
| CN113983446B (en) | Control method and control device of gas steam equipment | |
| CN117376108B (en) | Intelligent operation and maintenance method and system for Internet of things equipment | |
| CN111832832B (en) | District self-inspection system based on thing networking | |
| CN116502156B (en) | Intelligent identification method and system for light CT abnormal state of converter station | |
| CN112034355B (en) | Method and device for evaluating state of storage battery | |
| CN117474357A (en) | Power distribution room operation and maintenance management method and system based on deep learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |