Management and control assistant system based on power grid resource business middle station and production management and control system

Abstract

The invention relates to the technical field of electric power systems and automation thereof, and discloses a management and control assistant system based on a power grid resource business middle station and a production management and control system, and the system comprises a collection module which is used for collecting the related data of a power grid; the anomaly analysis and positioning module is used for judging whether a fault exists in the power grid or not according to the power grid related data, and if yes, giving a fault type, a line where fault equipment is located and a coordinate position of the fault equipment; the operation and maintenance scheme compiling module is used for giving an optimal solution according to the fault type, the line where the fault equipment is located and the coordinate position of the fault equipment; the resource library is used for storing maintenance related data required during fault maintenance; the power failure monitoring module is used for monitoring the power grid in real time according to the fault power failure data of the service platform in combination with the output data of the anomaly analysis and positioning module; a display module; and a communication module. The method can improve the fault first-aid repair efficiency.

Description

Technical Field

[0001] The present invention relates to the field of power systems and automation technologies thereof, and in particular to a management and control assistant system based on a power grid resource business middle station and a production management and control system. Background Art

[0002] The production control center is a new model for the transformation of the State Grid Corporation's production organization system to digitalization and intelligence. Based on the existing information construction achievements of various provincial companies, the business, processes and data of the three application levels of the headquarters, provincial companies, ultra-high voltage and municipal companies are integrated, and the entire process of information control, process control, risk control, and command control is carried out. Through digitalization, productivity is effectively released, and a new form of company production control system with online collaboration, rapid response and efficient command is constructed. At present, the production control system of Sichuan Company is self-built by the province, and has achieved certain results in integrating operation and inspection business resources, strengthening production business control, strengthening risk operation supervision, and improving the level of lean management of operation and inspection. However, with the continuous improvement of the requirements of municipal companies for equipment safety foundation, power supply reliability, and lean production management, the existing production control system is not enough to fully support the production control decision-making and business closed-loop control of Luzhou Company, which is specifically manifested in the following four aspects:

[0003] First, when abnormalities such as heavy overload and low voltage occur in the substation, it is impossible to analyze and judge based on the switch position distribution of the line, the load changes of the feeder lines, the line length, the line diameter and other data;

[0004] Second, after a distribution network line fails, the repair team cannot view the line single-line diagram anytime and anywhere when carrying out on-site repairs, which prolongs the time for fault location. Inaccurate information may also lead to repair strategy errors, affecting repair efficiency and power supply restoration speed;

[0005] Third, after the power grid risk warning form is issued, the system cannot automatically compile the corresponding risk warning form, feedback form and operation and maintenance guarantee plan according to the warning equipment. Managers often have to spend a lot of time to compile power grid risk guarantee plans, which is time-consuming, labor-intensive and inefficient, and lacks data-driven decision-making;

[0006] Fourth, due to the diversified and differentiated characteristics of cross-departmental management, the reporting requirements for maintenance plans show significant heterogeneity among departments, but the content of maintenance plans tends to be consistent. Under the traditional model of manual intervention, the cumbersomeness of the work process has been aggravated, seriously restricting operation and maintenance efficiency and coordination capabilities.

[0007] Therefore, it is necessary to build personalized micro-applications for municipal companies based on the power grid resource business middle platform and production control system: "Control Assistant" to enhance the data analysis and automation processing capabilities, analysis and judgment, emergency response and coordination and command capabilities of the production control centers of municipal companies. Summary of the invention

[0008] The present invention provides a control assistant system based on a power grid resource business middle station and a production control system to solve the above problems.

[0009] The present invention is achieved through the following technical solutions:

[0010] A control assistant system based on a power grid resource business middle platform and a production control system, comprising:

[0011] A collection module is used to collect power grid related data;

[0012] An equipment abnormality analysis module is used to automatically determine the cause of equipment failure based on the power grid related data, and the cause of the failure includes the type of failure, the line where the faulty equipment is located, and the location of the faulty equipment;

[0013] An operation and maintenance plan preparation module is used to provide the best solution based on the fault type, the line where the faulty equipment is located, and the location of the faulty equipment;

[0014] Resource library, used to store relevant data required for automatic preparation of operation and maintenance plans;

[0015] A power outage monitoring module is used to monitor the power grid in real time based on the fault power outage data of the business middle station combined with the output data of the abnormal analysis and positioning module to provide whether there is a power outage in the area where the fault location is located, as well as details of the affected substations;

[0016] A display module, used to display the output data of the abnormality analysis and positioning module and the power outage detection module;

[0017] The communication module is used to send the optimal solution to the corresponding operation and maintenance unit.

[0018] As an optimization, the grid-related data includes all feeder data set in the grid, and each feeder data includes the switching status of all equipment set on the main feeder, the change in feeder load value, current data, feeder line length, feeder line diameter data, environmental meteorological data of the area where all equipment on the main feeder is located, and initial positioning data after equipment failure, wherein the main feeder is a feeder directly connected to the busbar.

[0019] As an optimization, the initial positioning data is obtained through a distributed traveling wave rangefinder, and each main feeder corresponds to a distributed traveling wave rangefinder. The distributed traveling wave rangefinder is arranged at the connection between the main feeder and the busbar, and is used to detect the specific location of the equipment after a device failure on the main feeder.

[0020] As an optimization, an extreme learning machine is provided in the abnormal analysis and positioning module, and the extreme learning machine is trained by an improved dung beetle algorithm to obtain an abnormal analysis and positioning model. The specific training process is as follows:

[0021] A1. Obtain historical fault data and use the historical fault data as training samples, wherein the historical fault data includes historical feeder data where the device is located when the device fails, the actual fault type when the device fails, the line where the faulty device is located, and the location of the faulty device;

[0022] A2, initializing algorithm parameters of the dung beetle algorithm, the algorithm parameters including the number of dung beetle populations, the maximum number of iterations, the proportion of dung beetle types, and the optimization range, wherein the individuals constituting the population all include relevant parameters of the ELM, the relevant parameters including the weights of hidden layer nodes and input layer nodes, and the thresholds of hidden layer nodes;

[0023] A3, initializing the population and calculating the fitness value of each individual, wherein the inverse of the sum of the errors between the predicted output of the training sample by the ELM and the actual result is used as the fitness function, and the actual result is the actual fault type, the line where the faulty device is located, and the location of the faulty device when the device fails;

[0024] A4, sorting the dung beetle population according to the size of the fitness value, so as to obtain the current best position and the current worst position;

[0025] A5. According to the sorted positions and the proportions of the dung beetle types, rolling behaviors, breeding behaviors, foraging behaviors, and stealing behaviors are performed to update the positions of the dung beetles;

[0026] A6. Obtain a first optimal value, a second optimal value, a third optimal value, and a fourth optimal value, wherein the first optimal value is the maximum fitness value of an individual performing a ball rolling behavior, the second optimal value is the maximum fitness value of an individual performing a breeding behavior, the third optimal value is the maximum fitness value of an individual performing a foraging behavior, and the fourth optimal value is the maximum fitness value of an individual performing a stealing behavior;

[0027] A7, sorting the first optimal value, the second optimal value, the third optimal value and the fourth optimal value, and adjusting the proportion of dung beetle types according to the sorted order;

[0028] A8, determining whether each updated dung beetle position exceeds the optimization range;

[0029] A9. Re-update the dung beetle population according to the ranking of fitness values;

[0030] A10, determine whether the maximum number of iterations has been reached;

[0031] A11. If yes, output the currently updated dung beetle population to obtain the optimal solution. Otherwise, repeat A4 to A10.

[0032] As an optimization, the total error includes a first error between the predicted fault type and the actual fault type, and a second error between the line where the predicted faulty device is located and the line where the actual faulty device is located. If the predicted fault type is consistent with the actual fault type, the first error value is 0, otherwise, the first error value is 1; if the line where the predicted faulty device is located is consistent with the line where the actual faulty device is located, the second error value is 0, otherwise, the second error value is 1.

[0033] As an optimization, the specific process of A7 is:

[0034] The first optimal value, the second optimal value, the third optimal value and the fourth optimal value are sorted in descending order, and then the dung beetle types are proportionally allocated according to the sorted order, wherein the dung beetle type allocation ratio corresponding to the first optimal value is a, the dung beetle type allocation ratio corresponding to the second optimal value is b, the dung beetle type allocation ratio corresponding to the third optimal value is c, and the dung beetle type allocation ratio corresponding to the last optimal value is d, and a+b+c+d=N, N is the number of individuals in the population.

[0035] As an optimization, the resource library includes an emergency material library, an emergency material address library, a solution library and a guarantee team library, wherein the emergency material library stores several material details required for repairing faulty equipment, the emergency material address library stores several address details where emergency materials are stored, the solution library stores solutions corresponding to different equipment failures, and the guarantee team library stores operation and maintenance units that repair faulty equipment.

[0036] As an optimization, the operation and maintenance plan preparation module is used to find the corresponding solution from the solution library and the required materials from the emergency material library according to the fault type given by the abnormal analysis and positioning module. At the same time, according to the line where the faulty equipment is located and the coordinate position of the faulty equipment given by the abnormal analysis and positioning module, the emergency material location closest to the faulty equipment is found from the emergency material address library and the corresponding operation and maintenance unit is found from the support team library, and the best path between the emergency material location closest to the faulty equipment and the coordinate position of the faulty equipment is matched, and the solution, required materials, emergency material location, operation and maintenance unit, and best path are filled in the preset table to obtain the best solution.

[0037] As an optimization, a method for obtaining the best path between the emergency material location closest to the faulty device and the coordinate position of the faulty device can be obtained through an optimal path algorithm.

[0038] As an optimization, the communication module mainly uses SMS notification.

[0039] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0040] (1) Improve data analysis capabilities: By integrating multi-source data, accurate analysis and judgment of equipment anomalies and power outages can be achieved, providing strong data support for production control.

[0041] (2) Improve fault repair efficiency: monitor equipment status in real time, quickly locate fault points, shorten fault handling time, and increase power supply restoration speed.

[0042] (3) Simplify the risk warning sheet preparation process: Automatically generate power grid risk warning sheets and operation and maintenance guarantee plans to reduce the workload of management personnel and improve work efficiency.

[0043] (4) Optimize the maintenance plan management process: reduce manual intervention, realize automatic summary, analysis and reminder of maintenance plans, and improve operation and maintenance efficiency and coordination capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0045] Figure 1 A module connection diagram of a control assistant system based on a power grid resource business middle station and a production control system according to the present invention;

[0046] Figure 2 This is a schematic diagram of the structure of one of the feeders in the embodiment;

[0047] Figure 3 This is a schematic diagram of a power grid fault event displayed by the display module. DETAILED DESCRIPTION

[0048] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0049] The present invention aims to solve the four major technical problems existing in the existing production control system of State Grid Power Supply Company, so as to improve the intelligentization and automation level of production control and the closed-loop control capability of business. The specific technical problems include:

[0050] (1) Insufficient data analysis capabilities: The existing system is unable to accurately analyze and judge abnormalities such as heavy overload and low voltage in the substation based on data such as equipment switch position and feeder load changes.

[0051] (2) Low efficiency of fault repair: After a distribution network line fails, it is difficult for repair personnel to quickly view line information, resulting in a long time to locate the fault, affecting the repair efficiency and power supply restoration speed.

[0052] (3) The preparation of risk warning forms is cumbersome: The system cannot automatically prepare power grid risk warning forms and operation and maintenance guarantee plans. Management personnel need to operate manually, which is time-consuming, labor-intensive and inefficient.

[0053] (4) Complex maintenance plan management: The diversification and differentiation of cross-departmental management leads to a cumbersome maintenance plan submission process, which restricts operation and maintenance efficiency and coordination capabilities.

[0054] Specifically, Figure 1 As shown, this embodiment 1 provides a control assistant system based on a power grid resource business middle station and a production control system, including:

[0055] A collection module is used to collect power grid related data;

[0056] In some embodiments, the grid-related data includes all feeder data set in the grid, and each feeder data includes the switching status of all devices set on the main feeder, the change in feeder load value, current data, feeder line length, feeder line diameter data, environmental meteorological data of the area where all devices on the main feeder are located, and initial positioning data after equipment failure, wherein the main feeder is a feeder directly connected to the busbar.

[0057] In some embodiments, the initial positioning data is obtained by a distributed traveling wave rangefinder, and each of the main feeders corresponds to a distributed traveling wave rangefinder. The distributed traveling wave rangefinder is arranged at the connection between the main feeder and the busbar, and is used to detect the position of the equipment after a failure of the equipment on the main feeder.

[0058] It should be noted that a main feeder can be in a tree structure, and the switch state of the equipment on the main feeder is a switch state set composed of the switch states of all equipment, and when the switch is in an open state, the switch state is 1, and when the switch is in a closed state, the switch state is 0. Alternatively, it can also be defined that when the switch is in an open state, the switch state is 0, and when the switch is in a closed state, the switch state is 1.

[0059] For example, if the main feeder has 3 branches and 4 devices, such as Figure 2 As shown, F is the connection end between the main feeder and the busbar.

[0060] If there are 4 devices A, B, C, and D, A is closed, B is open, C is closed, and D is open, then the switch state is {0,1,0,1} or {1,0,1,0}.

[0061] The feeder load value variation is also a set of load value variation composed of the load value variation corresponding to all branches of the tree structure.

[0062] For example, the feeder load value change is {x,y,z}, where x is Figure 2 The load value change on the feeder of FA, y, is Figure 2 The load value change on the feeder of FB is Figure 2 The load value change on the feeder of FD.

[0063] The current data is the current size at the connection with the busbar, that is, the current size of F.

[0064] The feeder line length is also a set of lengths consisting of the lengths from the ends of all branches of the tree structure to the busbar, namely, the feeder length a of FA, the feeder length b of FB, and the feeder length c of FD. The feeder line length is expressed as {a, b, c}.

[0065] The feeder wire diameters of the same main feeder are the same, and the feeder wire diameters of different main feeders may be the same or different.

[0066] The environmental meteorological data of the area where all the equipment on the main feeder is located includes a meteorological data set composed of the environmental meteorological data of the area where all the equipment is located. The environmental meteorological data specifically includes one or more of rainfall, temperature, humidity and wind speed.

[0067] Similarly, if only temperature is included, the ambient meteorological data on the feeder can be expressed as {37.5, 37.2, 37.6, 37.1}.

[0068] If both temperature and humidity are included, the ambient meteorological data on the feeder can be expressed as {37.5|42%, 37.2|42%, 37.6|43%, 37.1|42%}.

[0069] If the device is fault-free, the initial positioning data is {0,0,0,0}. If device A is faulty, the initial positioning data is {1000,0,0,0}, where 1000 is the distance between FAs measured by the distributed traveling wave rangefinder. Since the distributed traveling wave rangefinder has a certain error, the initial positioning data is used as one of the input data of the abnormal analysis and positioning module to train the abnormal analysis and positioning module, which can make the positioning of the abnormal analysis and positioning module more accurate.

[0070] It should be noted that the position order of each corresponding element in each set will not change.

[0071] The abnormality analysis and positioning module is used to determine whether there is a fault in the power grid based on the power grid related data. If so, it gives the fault type, the line where the faulty equipment is located, and the coordinate position of the faulty equipment.

[0072] It should be noted that the fault types include line fault types and equipment fault types.

[0073] Line fault types mainly include whole line tripping, branch line tripping, etc., and equipment fault types mainly include heavy load, overload, low voltage, etc.

[0074] In some embodiments, an extreme learning machine is provided in the abnormal analysis and positioning module, and the extreme learning machine is trained by an improved dung beetle algorithm to obtain an abnormal analysis and positioning model. The specific training process is:

[0075] A1. Obtain historical fault data and use the historical fault data as training samples, wherein the historical fault data includes historical feeder data where the device is located when the device fails, the actual fault type when the device fails, the line where the faulty device is located, and the location of the faulty device;

[0076] A2, initializing algorithm parameters of the dung beetle algorithm, the algorithm parameters including the number of dung beetle populations, the maximum number of iterations, the proportion of dung beetle types, and the optimization range, wherein the individuals constituting the population all include relevant parameters of the ELM, the relevant parameters including the weights of hidden layer nodes and input layer nodes, and the thresholds of hidden layer nodes;

[0077] A3, initializing the population and calculating the fitness value of each individual, wherein the inverse of the sum of the errors between the predicted output of the training sample by the ELM and the actual result is used as the fitness function, and the actual result is the actual fault type, the line where the faulty device is located, and the location of the faulty device when the device fails;

[0078] In some embodiments, the error sum includes a first error between the predicted fault type and the actual fault type, and a second error between the line where the predicted fault device is located and the line where the actual fault device is located, and if the predicted fault type is consistent with the actual fault type, the first error value is 0, otherwise, the first error value is 1; if the line where the predicted fault device is located is consistent with the line where the actual fault device is located, the second error value is 0, otherwise, the second error value is 1.

[0079] Since there are two types of faults, if the two faults are consistent, the first error value is 0, otherwise, the first error value is 1.

[0080] A4, sorting the dung beetle population according to the size of the fitness value, so as to obtain the current best position and the current worst position;

[0081] A5. According to the sorted positions and the proportions of the dung beetle types, rolling behaviors, breeding behaviors, foraging behaviors, and stealing behaviors are performed to update the positions of the dung beetles;

[0082] A6. Obtain a first optimal value, a second optimal value, a third optimal value, and a fourth optimal value, wherein the first optimal value is the maximum fitness value of an individual performing a ball rolling behavior, the second optimal value is the maximum fitness value of an individual performing a breeding behavior, the third optimal value is the maximum fitness value of an individual performing a foraging behavior, and the fourth optimal value is the maximum fitness value of an individual performing a stealing behavior;

[0083] A7, sorting the first optimal value, the second optimal value, the third optimal value and the fourth optimal value, and adjusting the proportion of dung beetle types according to the sorted order;

[0084] The specific process is:

[0085] The first optimal value, the second optimal value, the third optimal value and the fourth optimal value are sorted in descending order, and then the dung beetle types are proportionally allocated according to the sorted order, wherein the dung beetle type allocation ratio corresponding to the first optimal value is a, the dung beetle type allocation ratio corresponding to the second optimal value is b, the dung beetle type allocation ratio corresponding to the third optimal value is c, and the dung beetle type allocation ratio corresponding to the last optimal value is d, and a+b+c+d=N, N is the number of individuals in the population.

[0086] Here, if N is 30, then a, b, c, and d can be 6, 6, 11, and 7 respectively. If the first best value, the second best value, the third best value, and the fourth best value are sorted in descending order as follows: fourth best value, first best value, second best value, and third best value, then the fourth best value corresponds to a (6), the first best value corresponds to b (6), the second best value corresponds to c (11), and the third best value corresponds to d (7), then the corresponding dung beetle type ratio is:

[0087] Rolling behavior / dancing behavior: breeding behavior: foraging behavior: stealing behavior = 6:11:7:6.

[0088] If the first best value, the second best value, the third best value and the fourth best value are sorted in descending order as follows: the second best value, the fourth best value, the first best value, the third best value, then the second best value corresponds to a(6), the fourth best value corresponds to b(6), the first best value corresponds to c(11), and the third best value corresponds to d(7), and the corresponding dung beetle type ratio is:

[0089] Rolling behavior / dancing behavior: breeding behavior: foraging behavior: stealing behavior = 11:6:7:6.

[0090] By dynamically allocating the proportion of dung beetle types, the dung beetle algorithm can avoid local convergence too quickly, resulting in failure of global convergence.

[0091] A8. Determine whether each updated dung beetle position exceeds the optimization range; the optimization range here refers to the upper and lower limits in the dung beetle algorithm.

[0092] A9. Re-update the dung beetle population according to the ranking of fitness values;

[0093] A10, determine whether the maximum number of iterations has been reached;

[0094] A11. If yes, output the currently updated dung beetle population to obtain the optimal solution. Otherwise, repeat A4 to A10.

[0095] The optimal solution here is the optimal weights of the hidden layer nodes and input layer nodes and the threshold of the hidden layer nodes.

[0096] After the training is completed, an abnormal analysis and positioning model is obtained. The input of the abnormal analysis and positioning model is the feeder data, and the output is the fault type, the line where the faulty equipment is located, and the coordinate position of the faulty equipment.

[0097] The measurement data and online monitoring data before and after the equipment failure are called up, combined with the environmental meteorological data, and the abnormal analysis and positioning module is used to assist in judging the authenticity of the fault event, and provide query and analysis of abnormal information such as equipment heavy load, overload, low voltage, etc., combined with the load change, line length, wire diameter and other data of the feeder, the cause of the abnormality is automatically analyzed.

[0098] At the same time, the abnormal analysis and positioning module can automatically analyze the causes of heavy overload and low voltage areas, and the operation and maintenance plan preparation module can formulate control measures, making the entire maintenance work quick and standardized.

[0099] An operation and maintenance plan preparation module is used to provide the best solution based on the fault type, the line where the faulty equipment is located, and the coordinates of the faulty equipment;

[0100] Resource library, used to store maintenance-related data required for fault repair;

[0101] In some embodiments, the resource library includes an emergency material library, an emergency material address library, a solution library and a guarantee team library, wherein the emergency material library stores a number of material details required for repairing faulty equipment, the emergency material address library stores a number of address details where emergency materials are stored, the solution library stores solutions corresponding to different equipment failures, and the guarantee team library stores operation and maintenance units that repair faulty equipment.

[0102] In some embodiments, the operation and maintenance plan preparation module is used to find the corresponding solution from the solution library and the required materials from the emergency material library according to the fault type given by the abnormal analysis and positioning module. At the same time, according to the line where the faulty equipment is located and the coordinate position of the faulty equipment given by the abnormal analysis and positioning module, the emergency material location closest to the faulty equipment is found from the emergency material address library and the corresponding operation and maintenance unit is found from the support team library, and the best path between the emergency material location closest to the faulty equipment and the coordinate position of the faulty equipment is matched, and the solution, required materials, emergency material location, operation and maintenance unit, and best path are filled in the preset table to obtain the best solution.

[0103] In some embodiments, the method for obtaining the best path between the emergency material location closest to the faulty device and the coordinate position of the faulty device can be obtained through an optimal path algorithm. That is, the following functions can be achieved through the operation and maintenance plan compilation module:

[0104] Equipment emergency repair auxiliary management:

[0105] (1) Spare parts and supplies association: Automatically calculate the nearest spare parts and emergency supplies storage location based on the location of the faulty equipment and display it on a power grid map.

[0106] (2) Path planning: Based on the road network information of a power grid map, the shortest path from the material warehouse to the faulty equipment is planned to improve the efficiency of emergency repairs.

[0107] (3) Single-line diagram push: Automatically associate the single-line diagram based on the fault line to assist in emergency repair decision-making.

[0108] Grid risk protection:

[0109] Automatic compilation of power grid risk warning sheets and operation and maintenance guarantee plans: Establish an intermediate sample library to automatically generate risk prevention measures and operation and maintenance guarantee plans (including guarantee teams, guarantee priorities, guarantee measures, emergency response, operation control priorities, etc.) based on faulty equipment.

[0110] The power outage monitoring module is used to monitor the power grid in real time based on the fault power outage data of the business middle station combined with the output data of the abnormal analysis and positioning module to provide whether there is a power outage in the area where the fault location is located, and the details of the affected substations; specifically, the power outage monitoring module has the following functions:

[0111] (1) Main grid power outage event: Access the main grid fault power outage data through the business middle office service call, combine the equipment's telemetering data, monitor the main grid operation status in real time, and build a module on the i State Grid APP to display the operation flow chart and real-time monitoring of unplanned shutdown equipment.

[0112] (2) Distribution network power outage events: Using the data provided by distribution automation and calling the data interface between systems, real-time query and recovery status monitoring of distribution network power outage events are achieved, and the automatic work order supervision and issuance process is supported for power outages that have timed out and have not been maintained.

[0113] (3) Main and distribution network topology analysis: Establish a main and distribution network tripping correlation and user correlation analysis model, screen outages of more than 100 or 1,000 households, and display and notify them in a grid map.

[0114] The display module is used to display the output data of the abnormality analysis and positioning module and the power outage detection module; specifically, Figure 3 It should be noted that the name of the faulty device can be obtained according to the location coordinate information of the faulty device, and different location coordinate information corresponds to different device names.

[0115] The communication module is used to send the optimal solution to the corresponding operation and maintenance unit.

[0116] In some embodiments, the communication module mainly uses SMS notification.

[0117] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A control assistant system based on a power grid resource business middle platform and a production control system, characterized in that: include: A collection module is used to collect power grid related data; An equipment abnormality analysis module is used to automatically determine the cause of equipment failure based on the power grid related data, and the cause of the failure includes the type of failure, the line where the faulty equipment is located, and the location of the faulty equipment; An operation and maintenance plan preparation module is used to provide the best solution based on the fault type, the line where the faulty equipment is located, and the location of the faulty equipment; Resource library, used to store relevant data required for automatic preparation of operation and maintenance plans; A power outage monitoring module is used to monitor the power grid in real time based on the fault power outage data of the business middle station combined with the output data of the abnormal analysis and positioning module to provide whether there is a power outage in the area where the fault location is located, as well as details of the affected substations; A display module, used to display the output data of the abnormality analysis and positioning module and the power outage detection module; The communication module is used to send the optimal solution to the corresponding operation and maintenance unit.

2. A control assistant system based on a power grid resource business middle platform and a production control system according to claim 1, characterized in that: The grid-related data includes all feeder data set in the grid, and each feeder data includes the switch status of all equipment set on the main feeder, the change in feeder load value, current data, feeder line length, feeder line diameter data, environmental meteorological data of the area where all equipment on the main feeder is located, and initial positioning data after equipment failure, wherein the main feeder is a feeder directly connected to the busbar.

3. A control assistant system based on a power grid resource business middle platform and a production control system according to claim 2, characterized in that: The initial positioning data is obtained through a distributed traveling wave rangefinder, and each main feeder corresponds to a distributed traveling wave rangefinder. The distributed traveling wave rangefinder is arranged at the connection between the main feeder and the busbar, and is used to detect the specific position of the equipment after a device failure on the main feeder.

4. A control assistant system based on a power grid resource business middle station and a production control system according to claim 2 or 3, characterized in that: The abnormal analysis and positioning module is provided with an extreme learning machine, and the extreme learning machine is trained by the improved dung beetle algorithm to obtain an abnormal cause analysis model. The specific training process is as follows: A1. Obtain historical fault data and use the historical fault data as training samples, wherein the historical fault data includes historical feeder data where the device is located when the device fails, the actual fault type when the device fails, the line where the faulty device is located, and the location of the faulty device; A2, initializing algorithm parameters of the dung beetle algorithm, the algorithm parameters including the number of dung beetle populations, the maximum number of iterations, the proportion of dung beetle types, and the optimization range, wherein the individuals constituting the population all include relevant parameters of the ELM, the relevant parameters including the weights of hidden layer nodes and input layer nodes, and the thresholds of hidden layer nodes; A3, initializing the population and calculating the fitness value of each individual, wherein the inverse of the sum of the errors between the predicted output of the training sample by the ELM and the actual result is used as the fitness function, and the actual result is the actual fault type, the line where the faulty device is located, and the location of the faulty device when the device fails; A4, sorting the dung beetle population according to the size of the fitness value, so as to obtain the current best position and the current worst position; A5. According to the sorted positions and the proportions of the dung beetle types, rolling behaviors, breeding behaviors, foraging behaviors, and stealing behaviors are performed to update the positions of the dung beetles; A6. Obtain a first optimal value, a second optimal value, a third optimal value, and a fourth optimal value, wherein the first optimal value is the maximum fitness value of an individual performing a ball rolling behavior, the second optimal value is the maximum fitness value of an individual performing a breeding behavior, the third optimal value is the maximum fitness value of an individual performing a foraging behavior, and the fourth optimal value is the maximum fitness value of an individual performing a stealing behavior; A7, sorting the first optimal value, the second optimal value, the third optimal value and the fourth optimal value, and adjusting the proportion of dung beetle types according to the sorted order; A8, determining whether each updated dung beetle position exceeds the optimization range; A9. Re-update the dung beetle population according to the ranking of fitness values; A10, determine whether the maximum number of iterations has been reached; A11. If yes, output the currently updated dung beetle population to obtain the optimal solution. Otherwise, repeat A4 to A10.

5. A control assistant system based on a power grid resource business middle platform and a production control system according to claim 4, characterized in that: The error sum includes a first error between the predicted fault type and the actual fault type, and a second error between the line where the predicted faulty device is located and the line where the actual faulty device is located. If the predicted fault type is consistent with the actual fault type, the first error value is 0, otherwise, the first error value is 1; if the line where the predicted faulty device is located is consistent with the line where the actual faulty device is located, the second error value is 0, otherwise, the second error value is 1.

6. A control assistant system based on a power grid resource business middle platform and a production control system according to claim 4, characterized in that: The specific process of A7 is as follows: The first optimal value, the second optimal value, the third optimal value and the fourth optimal value are sorted in descending order, and then the dung beetle types are proportionally allocated according to the sorted order, wherein the dung beetle type allocation ratio corresponding to the first optimal value is a, the dung beetle type allocation ratio corresponding to the second optimal value is b, the dung beetle type allocation ratio corresponding to the third optimal value is c, and the dung beetle type allocation ratio corresponding to the last optimal value is d, and a+b+c+d=N, N is the number of individuals in the population.

7. A control assistant system based on a power grid resource business middle platform and a production control system according to claim 1, characterized in that: The resource library includes an emergency material library, an emergency material address library, a solution library and a guarantee team library, wherein the emergency material library stores a number of material details required for repairing faulty equipment, the emergency material address library stores a number of address details where emergency materials are stored, the solution library stores solutions corresponding to different equipment failures, and the guarantee team library stores operation and maintenance units that repair faulty equipment.

8. A control assistant system based on a power grid resource business middle platform and a production control system according to claim 7, characterized in that: The operation and maintenance solution preparation module is used to find the corresponding solution from the solution library and the required materials from the emergency material library according to the fault type given by the abnormal analysis and positioning module. At the same time, according to the line where the faulty equipment is located and the coordinate position of the faulty equipment given by the abnormal analysis and positioning module, the emergency material location closest to the faulty equipment is found from the emergency material address library and the corresponding operation and maintenance unit is found from the support team library, and the best path between the emergency material location closest to the faulty equipment and the coordinate position of the faulty equipment is matched, and the solution, required materials, emergency material location, operation and maintenance unit, and best path are filled in a preset table to obtain the best solution.

9. A control assistant system based on a power grid resource business middle platform and a production control system according to claim 8, characterized in that: The method for obtaining the best path between the emergency material location closest to the faulty device and the coordinate position of the faulty device can be obtained through an optimal path algorithm.

10. A control assistant system based on a power grid resource business middle platform and a production control system according to claim 1, characterized in that: The notification method of the communication module includes a text message notification method.

Images