Intelligent traffic system and method for operation and maintenance of wind power plant

Abstract

The invention relates to the technical field of wind power plant operation and maintenance, and discloses an intelligent traffic system and method for wind power plant operation and maintenance, and the system comprises a receiving module which is used for receiving a plurality of maintenance requests and extracting key information in each maintenance request; the scheduling module is used for carrying out vehicle screening based on the key information and calibrating an optimal vehicle corresponding to the maintenance request according to a screening result; the planning module is used for determining a plurality of to-be-determined paths of the optimal vehicle of the maintenance request, constructing a simulation to-be-determined path environment, calculating a simulation driving evaluation value, and planning an optimal path according to the simulation driving evaluation value; the execution module is used for generating an execution instruction corresponding to the optimal vehicle according to the optimal path and triggering a real-time monitoring instruction of the optimal vehicle; and the judgment module is used for acquiring the real-time monitoring information according to the preset feedback node, and judging whether an adjustment instruction corresponding to the optimal vehicle is generated or not according to the real-time monitoring information, so that the vehicle scheduling efficiency and the maintenance efficiency during unit maintenance are improved.

Description

Technical Field

[0001] The present application relates to the technical field of wind farm operation and maintenance, and in particular to an intelligent transportation system and method for wind farm operation and maintenance. Background Art

[0002] New energy station wind farms have the problem of wide distribution of wind turbines and complex road conditions, and low traffic efficiency of traditional vehicles. As a result, during maintenance operations, vehicles cannot reach the generators or return to the station in time, affecting the timeliness of fault handling. Therefore, there is an urgent need for an intelligent transportation system and method for wind farm operation and maintenance to improve the vehicle dispatch efficiency and maintenance efficiency during unit maintenance. Summary of the Invention

[0003] In order to solve the above technical problems, the present application provides an intelligent transportation system and method for wind farm operation and maintenance, which receives multiple maintenance requests and determines the corresponding optimal vehicle, plans the preferred path according to the simulated driving evaluation values ​​of several pending paths of each optimal vehicle, generates execution instructions and real-time monitoring instructions according to the preferred path, obtains real-time monitoring information, and determines whether to make adjustments based on the real-time monitoring information, thereby improving the vehicle scheduling efficiency and maintenance efficiency during unit maintenance.

[0004] In some embodiments of the present application, an intelligent transportation system for wind farm operation and maintenance is provided, including: A receiving module, used for receiving several maintenance requests and extracting key information from each maintenance request; The scheduling module is used to screen vehicles based on key information and calibrate the optimal vehicle corresponding to the maintenance request based on the screening results; A planning module is used to determine several undetermined routes for the optimal vehicle for the maintenance request and construct a simulated undetermined route environment, calculate a simulated driving evaluation value of the simulated undetermined route environment, and plan an optimal route based on the simulated driving evaluation value; An execution module is used to generate an execution instruction corresponding to the optimal vehicle according to the preferred path and trigger a real-time monitoring instruction for the optimal vehicle; The judgment module is used to obtain real-time monitoring information according to the preset feedback node and determine whether to generate an adjustment instruction corresponding to the optimal vehicle based on the real-time monitoring information.

[0005] In some embodiments of the present application, vehicle screening is performed based on key information, and the optimal vehicle corresponding to the maintenance request is calibrated according to the screening results, including: The key information includes the location information of the unit to be repaired corresponding to the repair request, the unit fault level and the unit importance coefficient; Obtaining basic information of several vehicles, including vehicle location information, cargo space, and remaining battery power; Performing vehicle screening based on key information of each maintenance request and basic information of several vehicles to obtain screening results, wherein the screening results include a position matching coefficient, a cargo space matching coefficient, and a remaining power matching coefficient; Generate a comprehensive matching coefficient between each maintenance request and each vehicle based on the screening results; The vehicle with the largest comprehensive matching coefficient is set as the optimal vehicle to be determined corresponding to the maintenance request; Obtain all maintenance requests corresponding to each pending optimal vehicle, and set the priority coefficient of the corresponding maintenance request based on the unit fault level and unit importance coefficient in the maintenance request; The undetermined optimal vehicle is set as the optimal vehicle for the maintenance request with the largest priority coefficient, and the optimal vehicles for the remaining maintenance instructions are re-matched.

[0006] In some embodiments of the present application, determining a plurality of undetermined routes for optimal vehicles for a maintenance request and constructing a simulated undetermined route environment includes: Determine a plurality of pending routes based on the location information of the unit to be repaired in the repair request and the vehicle location information of the corresponding optimal vehicle; Obtaining geographic data of each undetermined path based on GIS, wherein the geographic data includes road data, terrain data, and obstacle data; Preprocessing the geographic data, and constructing a three-dimensional path model corresponding to the undetermined path based on the preprocessed terrain data; Obtain the power generation plan of the unit to be repaired that is subject to the maintenance request, and determine the maintenance time interval of the unit to be repaired based on the power generation plan; The departure time node and the predicted arrival time node of the optimal vehicle corresponding to the maintenance request are set according to the maintenance time interval and the historical driving log of the optimal vehicle corresponding to the maintenance request; Predict the weather conditions between the departure time node and the predicted arrival time node of the optimal vehicle to obtain some predicted weather information; The predicted driving impact characteristics of the optimal vehicle are generated based on the vehicle driving impact characteristics of the historical weather information, and the three-dimensional path model of the corresponding optimal vehicle is rendered to obtain the simulated undetermined path environment of the optimal vehicle.

[0007] In some embodiments of the present application, calculating a simulated driving evaluation value of a simulated undetermined path environment includes: Determining a first predicted driving period based on the departure time node and the predicted arrival time node of the optimal vehicle, and setting a plurality of simulation monitoring time nodes according to preset time intervals; Performing a dynamic simulation based on the simulated undetermined path environment and the optimal vehicle, and obtaining simulation monitoring data at each simulation monitoring time node, the simulation monitoring data including simulated driving speed, simulated remaining power, simulated driving vibration data, simulated energy consumption data, and simulated driving avoidance coefficient; The simulated driving speed, simulated remaining power, simulated driving vibration data, and simulated energy consumption data at multiple simulation monitoring time nodes are mapped onto the time reference line of the corresponding first predicted driving period to obtain a driving speed change curve, a power change curve, a vibration change curve, and an energy consumption change curve; Comparing each simulated driving speed in the driving speed change curve with the corresponding standard driving speed, and generating a first driving evaluation value according to the comparison result; generating a first compensation coefficient according to a curve change characteristic of the driving speed change curve; Comparing each simulated remaining power in the power change curve with the corresponding preset power threshold, and generating a second driving evaluation value according to the comparison result; generating a second compensation coefficient according to a curve change characteristic of the electric quantity change curve; comparing each simulated driving vibration data in the vibration change curve with a corresponding preset vibration threshold, and generating a third driving evaluation value according to the comparison result; generating a third compensation coefficient according to a curve change characteristic of the vibration change curve; comparing each simulated energy consumption data in the energy consumption change curve with a corresponding preset energy consumption threshold, and generating a fourth driving evaluation value according to the comparison result; generating a fourth compensation coefficient according to a curve change characteristic of the energy consumption change curve; Correcting the first driving evaluation value, the second driving evaluation value, the third driving evaluation value, and the fourth driving evaluation value according to the first compensation coefficient, the second compensation coefficient, the third compensation coefficient, and the fourth compensation coefficient, respectively, and generating a simulated driving evaluation value corresponding to the simulated undetermined path environment in combination with the simulated driving avoidance coefficient; The curve change characteristics include the curve fluctuation degree, change trend and change rate.

[0008] In some embodiments of the present application, the simulated driving avoidance coefficient includes: The optimal vehicle corresponding to each simulated undetermined path environment is set as the primary optimal vehicle, and the optimal vehicles corresponding to other maintenance requests are set as suboptimal vehicles; Determine whether there is a vehicle driving conflict at each simulation monitoring time node in the simulation undetermined path environment; If so, the priority coefficients of the primary optimal vehicle and the secondary optimal vehicle in which the vehicle conflict exists are calculated respectively. If the priority coefficient of the primary optimal vehicle is greater than the priority coefficient of the secondary optimal vehicle, it is determined to be a false driving conflict. If the priority coefficient of the primary optimal vehicle is not greater than the priority coefficient of the secondary optimal vehicle, it is determined to be a true driving conflict. Calculate the avoidance time of the main optimal vehicle for each real driving conflict and map it to the corresponding simulation monitoring time node to obtain the comprehensive avoidance time at the corresponding simulation monitoring time node; Generate a simulation travel avoidance coefficient according to the number of simulation monitoring time nodes with real travel conflicts in the same simulation undetermined path environment and the comprehensive avoidance time at the corresponding simulation monitoring time nodes; The calculation formula of the simulation driving avoidance coefficient is: ; Among them, R is the simulation driving avoidance coefficient, n1 is the number of simulation monitoring time nodes with real driving conflicts in the same simulation undetermined path environment, n2 is the total number of simulation monitoring time nodes, r0 is the driving avoidance conversion coefficient, is the comprehensive avoidance time at the ith simulation monitoring time node where there is a true driving conflict, The preset avoidance time threshold.

[0009] In some embodiments of the present application, planning an optimal route based on the simulated driving evaluation value includes: Comparing the simulated driving evaluation values ​​of several undetermined routes of the optimal vehicle for the same maintenance request, and selecting the largest simulated driving path evaluation value and the corresponding undetermined route based on the comparison results; Presetting a driving evaluation value threshold; If the simulated driving evaluation value is greater than the driving evaluation value threshold, the corresponding undetermined path is set as the preferred path of the optimal vehicle corresponding to the maintenance request; If the simulated driving evaluation value is not greater than the driving evaluation value threshold, several undetermined paths of the optimal vehicle for the same maintenance request are analyzed to determine the undetermined paths with a connection relationship; Splicing the pending paths with connection relationships to obtain several pending splicing paths of optimal vehicles corresponding to the maintenance request; A simulated pending splicing path environment of the pending splicing path is constructed and a corresponding simulated driving evaluation value is calculated until the simulated driving evaluation value is greater than a driving evaluation value threshold, and the corresponding pending splicing path is set as a preferred path of the optimal vehicle corresponding to the maintenance request.

[0010] In some embodiments of the present application, generating an execution instruction corresponding to the optimal vehicle according to the preferred path and triggering a real-time monitoring instruction for the optimal vehicle include: Generate execution path data based on the preferred path and encrypt and transmit it to the corresponding optimal vehicle, while triggering the self-test instruction of the corresponding optimal vehicle; Perform self-inspection on the optimal vehicle according to the self-inspection instruction, and calculate the health coefficient of the optimal vehicle based on the self-inspection results; If the health coefficient is greater than the preset health coefficient threshold, an execution instruction corresponding to the optimal vehicle is generated and a real-time monitoring instruction of the optimal vehicle is triggered. The real-time monitoring instruction includes collecting real-time monitoring information according to a preset feedback node, and the preset feedback node corresponds one-to-one to the simulation monitoring time node in the predicted driving period of the corresponding optimal vehicle.

[0011] In some embodiments of the present application, determining whether to generate an adjustment instruction corresponding to an optimal vehicle based on real-time monitoring information includes: Presetting a test period and determining a number of preset feedback nodes in the test period; Acquiring real-time monitoring information at each preset feedback node, the real-time monitoring information including real-time driving speed, real-time remaining power, real-time driving vibration data, real-time energy consumption data, and real-time driving avoidance coefficient; Compare the real-time monitoring information at each preset feedback node with the simulated monitoring information at the corresponding simulation monitoring time node to obtain the deviation coefficients of the real-time driving speed, real-time remaining power, real-time driving vibration data, and real-time energy consumption data from the simulated driving speed, simulated remaining power, simulated driving vibration data, and simulated energy consumption data; Generate a comprehensive deviation coefficient at each preset feedback node based on the deviation coefficient, and construct a comprehensive deviation coefficient change curve during the inspection period; Predicting a second predicted driving period corresponding to the optimal vehicle according to the real-time monitoring information during the inspection period, and subtracting the predicted driving period from the first predicted driving period to obtain a predicted driving period difference; performing a curve trend extrapolation on a comprehensive deviation coefficient change curve during the inspection period to obtain a plurality of predicted comprehensive deviation coefficients during a second predicted driving period, and generating a plurality of predicted monitoring information based on the predicted comprehensive deviation coefficients, the predicted monitoring information including a predicted driving speed, a predicted remaining battery power, predicted driving vibration data, and predicted energy consumption data; generating a predicted driving evaluation value based on the real-time monitoring information of the inspection period and the predicted monitoring information of the second predicted driving period, and subtracting the predicted driving evaluation value from the simulated driving evaluation value to obtain a predicted driving evaluation value difference; Calculating a predicted driving avoidance coefficient based on the real-time monitoring information of the inspection period and the predicted monitoring information of the second predicted driving period, and subtracting the predicted driving avoidance coefficient from the simulated driving avoidance coefficient to obtain a predicted driving avoidance coefficient difference; Generate a first difference evaluation value according to the comprehensive deviation coefficient at each preset feedback node and the predicted comprehensive deviation coefficient; generating a second difference evaluation value according to the predicted travel period difference; generating a third difference evaluation value according to the predicted driving evaluation value difference; Generate a correction coefficient based on the difference in the predicted driving avoidance coefficient; generating a comprehensive difference evaluation value according to the first difference evaluation value, the second difference evaluation value, the third difference evaluation value, and the correction coefficient; If the comprehensive difference evaluation value is greater than the preset difference evaluation value threshold, it is determined that an adjustment instruction corresponding to the optimal vehicle is generated.

[0012] Some embodiments of the present application also include an intelligent transportation method for wind farm operation and maintenance: Receive several maintenance requests and extract key information from each maintenance request; Screen vehicles based on key information and calibrate the optimal vehicle for the corresponding maintenance request based on the screening results; Determine several undetermined routes for the optimal vehicle for the maintenance request and construct a simulated undetermined route environment, calculate a simulated driving evaluation value of the simulated undetermined route environment, and plan an optimal route based on the simulated driving evaluation value; Generate execution instructions for the optimal vehicle based on the preferred path and trigger real-time monitoring instructions for the optimal vehicle; Obtain real-time monitoring information according to the preset feedback node, and determine whether to generate adjustment instructions corresponding to the optimal vehicle based on the real-time monitoring information.

[0013] The intelligent transportation system and method for wind farm operation and maintenance according to the embodiments of the present application have the following advantages compared with the prior art: By receiving multiple maintenance requests and determining the corresponding optimal vehicle, the optimal path is planned according to the simulated driving evaluation values ​​of several pending paths of each optimal vehicle, execution instructions and real-time monitoring instructions are generated according to the optimal path, and real-time monitoring information is obtained. It is determined whether adjustments should be made based on the real-time monitoring information, thereby improving the vehicle scheduling efficiency and maintenance efficiency during unit maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 is a schematic diagram of an intelligent transportation system for wind farm operation and maintenance in an embodiment of the present application; Figure 2 It is a flow chart of an intelligent transportation method for wind farm operation and maintenance in an embodiment of the present application. DETAILED DESCRIPTION

[0015] The following embodiments are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0016] In the description of this application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application.

[0017] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of such features. Throughout this application, unless otherwise specified, "plurality" means two or more.

[0018] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on the specific circumstances.

[0019] like Figure 1 As shown, an intelligent transportation system for wind farm operation and maintenance according to an embodiment of the present application includes: A receiving module, used for receiving several maintenance requests and extracting key information from each maintenance request; The scheduling module is used to screen vehicles based on key information and calibrate the optimal vehicle corresponding to the maintenance request based on the screening results; A planning module is used to determine several undetermined routes for the optimal vehicle for the maintenance request and construct a simulated undetermined route environment, calculate a simulated driving evaluation value of the simulated undetermined route environment, and plan an optimal route based on the simulated driving evaluation value; An execution module is used to generate an execution instruction corresponding to the optimal vehicle according to the preferred path and trigger a real-time monitoring instruction for the optimal vehicle; The judgment module is used to obtain real-time monitoring information according to the preset feedback node and determine whether to generate an adjustment instruction corresponding to the optimal vehicle based on the real-time monitoring information.

[0020] In some embodiments of the present application, vehicle screening is performed based on key information, and the optimal vehicle corresponding to the maintenance request is calibrated according to the screening results, including: The key information includes the location information of the unit to be repaired corresponding to the repair request, the unit fault level and the unit importance coefficient; Obtaining basic information of several vehicles, including vehicle location information, cargo space, and remaining battery power; Performing vehicle screening based on key information of each maintenance request and basic information of several vehicles to obtain screening results, wherein the screening results include a position matching coefficient, a cargo space matching coefficient, and a remaining power matching coefficient; Generate a comprehensive matching coefficient between each maintenance request and each vehicle based on the screening results; The vehicle with the largest comprehensive matching coefficient is set as the optimal vehicle to be determined corresponding to the maintenance request; Obtain all maintenance requests corresponding to each pending optimal vehicle, and set the priority coefficient of the corresponding maintenance request based on the unit fault level and unit importance coefficient in the maintenance request; The undetermined optimal vehicle is set as the optimal vehicle for the maintenance request with the largest priority coefficient, and the optimal vehicles for the remaining maintenance instructions are re-matched.

[0021] In this embodiment, the comprehensive matching coefficient is calculated based on the position matching coefficient, the cargo space matching coefficient, and the remaining power matching coefficient.

[0022] In this embodiment, when the unit fault level is higher and the unit importance coefficient is larger, the priority coefficient of the corresponding maintenance request is larger, and vice versa.

[0023] In this embodiment, by determining the optimal vehicle for each maintenance instruction, the fault handling timeliness of each maintenance instruction is guaranteed, laying the foundation for subsequent planning of the optimal path and improving maintenance efficiency.

[0024] In some embodiments of the present application, determining a plurality of undetermined routes for optimal vehicles for a maintenance request and constructing a simulated undetermined route environment includes: Determine a plurality of pending routes based on the location information of the unit to be repaired in the repair request and the vehicle location information of the corresponding optimal vehicle; Obtaining geographic data of each undetermined path based on GIS, wherein the geographic data includes road data, terrain data, and obstacle data; Preprocessing the geographic data, and constructing a three-dimensional path model corresponding to the undetermined path based on the preprocessed terrain data; Obtain the power generation plan of the unit to be repaired that is subject to the maintenance request, and determine the maintenance time interval of the unit to be repaired based on the power generation plan; The departure time node and the predicted arrival time node of the optimal vehicle corresponding to the maintenance request are set according to the maintenance time interval and the historical driving log of the optimal vehicle corresponding to the maintenance request; Predict the weather conditions between the departure time node and the predicted arrival time node of the optimal vehicle to obtain some predicted weather information; The predicted driving impact characteristics of the optimal vehicle are generated based on the vehicle driving impact characteristics of the historical weather information, and the three-dimensional path model of the corresponding optimal vehicle is rendered to obtain the simulated undetermined path environment of the optimal vehicle.

[0025] In this embodiment, if the unit to be repaired in the maintenance request is still in operation, the minimum output period in the power generation plan is set as the maintenance time interval; if the unit to be repaired is not in operation, the current time node is set as the departure time node corresponding to the optimal vehicle.

[0026] In this embodiment, the vehicle driving impact characteristics of historical weather information refer to the impact characteristics of historical weather information on the vehicle driving process.

[0027] In this embodiment, by constructing several simulated pending path environments for the optimal vehicle, accurate simulation of the driving process of different pending paths is achieved, laying the foundation for the subsequent calculation of simulated driving evaluation values ​​and planning of preferred paths, ensuring the planning accuracy of the preferred paths, and thus improving maintenance efficiency and scheduling efficiency.

[0028] In some embodiments of the present application, calculating a simulated driving evaluation value of a simulated undetermined path environment includes: Determining a first predicted driving period based on the departure time node and the predicted arrival time node of the optimal vehicle, and setting a plurality of simulation monitoring time nodes according to preset time intervals; Performing a dynamic simulation based on the simulated undetermined path environment and the optimal vehicle, and obtaining simulation monitoring data at each simulation monitoring time node, the simulation monitoring data including simulated driving speed, simulated remaining power, simulated driving vibration data, simulated energy consumption data, and simulated driving avoidance coefficient; The simulated driving speed, simulated remaining power, simulated driving vibration data, and simulated energy consumption data at multiple simulation monitoring time nodes are mapped onto the time reference line of the corresponding first predicted driving period to obtain a driving speed change curve, a power change curve, a vibration change curve, and an energy consumption change curve; Comparing each simulated driving speed in the driving speed change curve with the corresponding standard driving speed, and generating a first driving evaluation value according to the comparison result; generating a first compensation coefficient according to a curve change characteristic of the driving speed change curve; Comparing each simulated remaining power in the power change curve with the corresponding preset power threshold, and generating a second driving evaluation value according to the comparison result; generating a second compensation coefficient according to a curve change characteristic of the electric quantity change curve; comparing each simulated driving vibration data in the vibration change curve with a corresponding preset vibration threshold, and generating a third driving evaluation value according to the comparison result; generating a third compensation coefficient according to a curve change characteristic of the vibration change curve; comparing each simulated energy consumption data in the energy consumption change curve with a corresponding preset energy consumption threshold, and generating a fourth driving evaluation value according to the comparison result; generating a fourth compensation coefficient according to a curve change characteristic of the energy consumption change curve; Correcting the first driving evaluation value, the second driving evaluation value, the third driving evaluation value, and the fourth driving evaluation value according to the first compensation coefficient, the second compensation coefficient, the third compensation coefficient, and the fourth compensation coefficient, respectively, and generating a simulated driving evaluation value corresponding to the simulated undetermined path environment in combination with the simulated driving avoidance coefficient; The curve change characteristics include the curve fluctuation degree, change trend and change rate.

[0029] In this embodiment, when the curve fluctuation degree in the curve change characteristics of the driving speed change curve is smaller, the change trend tends to no change, and the change rate is smaller, the corresponding first compensation coefficient is larger, and vice versa, the smaller; when the curve fluctuation degree in the curve change characteristics of the electric power change curve is smaller, the change trend tends to a normal downward trend, and the change rate is smaller, the corresponding second compensation coefficient is larger, and vice versa, the smaller; when the curve fluctuation degree in the curve change characteristics of the vibration change curve is smaller, the change trend tends to no change, and the change rate is smaller, the corresponding third compensation coefficient is larger, and vice versa, the smaller; when the curve fluctuation degree in the curve change characteristics of the energy consumption change curve is smaller, the change trend tends to a normal downward trend, and the change rate is smaller, the corresponding fourth compensation coefficient is larger, and vice versa, the smaller, and the value range is (0,1).

[0030] In this embodiment, the closer each simulated driving speed is to the corresponding standard driving speed, the larger the first driving evaluation value is, and vice versa. The greater the remaining power of each simulation is than the corresponding preset power threshold, the larger the second driving evaluation value is, and vice versa. The smaller the vibration data of each simulation driving is than the corresponding preset vibration threshold, the larger the third driving evaluation value is, and vice versa. The smaller the energy consumption data of each simulation is than the corresponding preset energy consumption threshold, the larger the fourth driving evaluation value is, and vice versa. The preset power threshold refers to the minimum power of the vehicle, the preset vibration threshold refers to the maximum vibration value corresponding to the vehicle on a normal road surface, and the preset energy consumption threshold refers to the maximum energy consumption value under normal driving conditions.

[0031] In this embodiment, the larger the simulated driving avoidance coefficient is, the less avoidance situations the optimal vehicle has to make when corresponding to the simulated undetermined path environment, that is, the smoother the optimal vehicle is and the less conflicts there are with other optimal vehicles.

[0032] In this embodiment, by constructing a simulated pending path environment and calculating the simulated driving evaluation value of the optimal vehicle in each simulated pending path environment, the driving performance of the optimal vehicle in each pending path is accurately evaluated, thereby determining the preferred path, improving the maintenance scheduling efficiency, and ensuring the timeliness of fault handling.

[0033] In some embodiments of the present application, the simulated driving avoidance coefficient includes: The optimal vehicle corresponding to each simulated undetermined path environment is set as the primary optimal vehicle, and the optimal vehicles corresponding to other maintenance requests are set as suboptimal vehicles; Determine whether there is a vehicle driving conflict at each simulation monitoring time node in the simulation undetermined path environment; If so, the priority coefficients of the primary optimal vehicle and the secondary optimal vehicle in which the vehicle conflict exists are calculated respectively. If the priority coefficient of the primary optimal vehicle is greater than the priority coefficient of the secondary optimal vehicle, it is determined to be a false driving conflict. If the priority coefficient of the primary optimal vehicle is not greater than the priority coefficient of the secondary optimal vehicle, it is determined to be a true driving conflict. Calculate the avoidance time of the main optimal vehicle for each real driving conflict and map it to the corresponding simulation monitoring time node to obtain the comprehensive avoidance time at the corresponding simulation monitoring time node; Generate a simulation travel avoidance coefficient according to the number of simulation monitoring time nodes with real travel conflicts in the same simulation undetermined path environment and the comprehensive avoidance time at the corresponding simulation monitoring time nodes; The calculation formula of the simulation driving avoidance coefficient is: ; Among them, R is the simulation driving avoidance coefficient, n1 is the number of simulation monitoring time nodes with real driving conflicts in the same simulation undetermined path environment, n2 is the total number of simulation monitoring time nodes, r0 is the driving avoidance conversion coefficient, is the comprehensive avoidance time at the ith simulation monitoring time node where there is a true driving conflict, The preset avoidance time threshold.

[0034] In this embodiment, the driving avoidance conversion coefficient refers to converting the comprehensive avoidance time into a value of the same dimension as the simulated driving avoidance coefficient. When the difference between the comprehensive avoidance time and the preset avoidance time threshold is smaller, the corresponding simulated driving avoidance coefficient is larger, and vice versa. The value range of the simulated driving avoidance coefficient is (0.8, 1.2).

[0035] In some embodiments of the present application, planning an optimal route based on the simulated driving evaluation value includes: Comparing the simulated driving evaluation values ​​of several undetermined routes of the optimal vehicle for the same maintenance request, and selecting the largest simulated driving path evaluation value and the corresponding undetermined route based on the comparison results; Presetting a driving evaluation value threshold; If the simulated driving evaluation value is greater than the driving evaluation value threshold, the corresponding undetermined path is set as the preferred path of the optimal vehicle corresponding to the maintenance request; If the simulated driving evaluation value is not greater than the driving evaluation value threshold, several undetermined paths of the optimal vehicle for the same maintenance request are analyzed to determine the undetermined paths with a connection relationship; Splicing the pending paths with connection relationships to obtain several pending splicing paths of optimal vehicles corresponding to the maintenance request; A simulated pending splicing path environment of the pending splicing path is constructed and a corresponding simulated driving evaluation value is calculated until the simulated driving evaluation value is greater than a driving evaluation value threshold, and the corresponding pending splicing path is set as a preferred path of the optimal vehicle corresponding to the maintenance request.

[0036] In this embodiment, the pending paths with a connection relationship refer to paths with overlapping sections or points, and the pending splicing path refers to a path different from the pending path that is constructed on the premise of ensuring that the optimal vehicle arrives at the unit to be repaired.

[0037] In this embodiment, the optimal route is planned by calculating the simulated driving evaluation value, thereby improving the operation and maintenance traffic efficiency of the new energy wind farm station. The optimal vehicle and the corresponding optimal route can be configured for multiple maintenance instructions to ensure the timeliness of fault handling of the units to be maintained, and improve the scheduling efficiency and maintenance efficiency.

[0038] In some embodiments of the present application, generating an execution instruction corresponding to the optimal vehicle according to the preferred path and triggering a real-time monitoring instruction for the optimal vehicle include: Generate execution path data based on the preferred path and encrypt and transmit it to the corresponding optimal vehicle, while triggering the self-test instruction of the corresponding optimal vehicle; Perform self-inspection on the optimal vehicle according to the self-inspection instruction, and calculate the health coefficient of the optimal vehicle based on the self-inspection results; If the health coefficient is greater than the preset health coefficient threshold, an execution instruction corresponding to the optimal vehicle is generated and a real-time monitoring instruction of the optimal vehicle is triggered. The real-time monitoring instruction includes collecting real-time monitoring information according to a preset feedback node, and the preset feedback node corresponds one-to-one to the simulation monitoring time node in the predicted driving period of the corresponding optimal vehicle.

[0039] In this embodiment, the self-inspection includes a brake system pressure check, a power mode switching check, a positioning accuracy check, etc., and a health factor is obtained based on the inspection results.

[0040] In some embodiments of the present application, determining whether to generate an adjustment instruction corresponding to an optimal vehicle based on real-time monitoring information includes: Presetting a test period and determining a number of preset feedback nodes in the test period; Acquiring real-time monitoring information at each preset feedback node, the real-time monitoring information including real-time driving speed, real-time remaining power, real-time driving vibration data, real-time energy consumption data, and real-time driving avoidance coefficient; Compare the real-time monitoring information at each preset feedback node with the simulated monitoring information at the corresponding simulation monitoring time node to obtain the deviation coefficients of the real-time driving speed, real-time remaining power, real-time driving vibration data, and real-time energy consumption data from the simulated driving speed, simulated remaining power, simulated driving vibration data, and simulated energy consumption data; Generate a comprehensive deviation coefficient at each preset feedback node based on the deviation coefficient, and construct a comprehensive deviation coefficient change curve during the inspection period; Predicting a second predicted driving period corresponding to the optimal vehicle according to the real-time monitoring information during the inspection period, and subtracting the predicted driving period from the first predicted driving period to obtain a predicted driving period difference; performing a curve trend extrapolation on a comprehensive deviation coefficient change curve during the inspection period to obtain a plurality of predicted comprehensive deviation coefficients during a second predicted driving period, and generating a plurality of predicted monitoring information based on the predicted comprehensive deviation coefficients, the predicted monitoring information including a predicted driving speed, a predicted remaining battery power, predicted driving vibration data, and predicted energy consumption data; generating a predicted driving evaluation value based on the real-time monitoring information of the inspection period and the predicted monitoring information of the second predicted driving period, and subtracting the predicted driving evaluation value from the simulated driving evaluation value to obtain a predicted driving evaluation value difference; Calculating a predicted driving avoidance coefficient based on the real-time monitoring information of the inspection period and the predicted monitoring information of the second predicted driving period, and subtracting the predicted driving avoidance coefficient from the simulated driving avoidance coefficient to obtain a predicted driving avoidance coefficient difference; Generate a first difference evaluation value according to the comprehensive deviation coefficient at each preset feedback node and the predicted comprehensive deviation coefficient; generating a second difference evaluation value according to the predicted travel period difference; generating a third difference evaluation value according to the predicted driving evaluation value difference; Generate a correction coefficient based on the difference in the predicted driving avoidance coefficient; generating a comprehensive difference evaluation value according to the first difference evaluation value, the second difference evaluation value, the third difference evaluation value, and the correction coefficient; If the comprehensive difference evaluation value is greater than the preset difference evaluation value threshold, it is determined that an adjustment instruction corresponding to the optimal vehicle is generated.

[0041] In this embodiment, the adjustment instructions include but are not limited to dynamic route correction, re-planning or replacement of vehicles, etc., and actual adjustments are made according to actual conditions.

[0042] In this embodiment, the larger the comprehensive deviation coefficient and the predicted comprehensive deviation coefficient at each preset feedback node, the larger the corresponding first difference evaluation value, and vice versa. When the difference in the predicted driving period is larger, the larger the corresponding second difference evaluation value, and vice versa. When the difference in the predicted driving evaluation value is larger, the larger the corresponding third difference evaluation value, and vice versa.

[0043] In this embodiment, when the predicted driving avoidance coefficient is greater than the simulated driving avoidance coefficient, that is, when the difference between the predicted driving avoidance coefficients is greater, the correction coefficient is greater, and vice versa. The value range of the correction coefficient is (0, 1).

[0044] In this embodiment, by calculating the comprehensive difference evaluation value, the degree of similarity between the actual driving process of the optimal vehicle and the simulated driving process is accurately evaluated, and the preferred path of the optimal vehicle or the shortcomings of the vehicle itself are discovered and adjusted in a timely manner, so as to ensure the timeliness of fault handling of the unit to be repaired and improve the maintenance efficiency.

[0045] In some embodiments of the present application, Figure 2 As shown, it also includes an intelligent transportation method for wind farm operation and maintenance: Step S201: receiving several maintenance requests and extracting key information from each maintenance request; Step S202: screening vehicles based on key information, and calibrating the optimal vehicle corresponding to the maintenance request according to the screening results; Step S203: determining a number of undetermined routes for the optimal vehicle for the maintenance request and constructing a simulated undetermined route environment, calculating a simulated driving evaluation value of the simulated undetermined route environment, and planning an optimal route based on the simulated driving evaluation value; Step S204: generating an execution instruction corresponding to the optimal vehicle according to the preferred path, and triggering a real-time monitoring instruction for the optimal vehicle; Step S205: obtaining real-time monitoring information according to a preset feedback node, and determining whether to generate an adjustment instruction corresponding to the optimal vehicle based on the real-time monitoring information.

[0046] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and replacements can be made without departing from the technical principles of the present application. These improvements and replacements should also be regarded as the scope of protection of the present application.

Claims

1. An intelligent transportation system for wind farm operation and maintenance, characterized in that: include: A receiving module, used for receiving a number of maintenance requests and extracting key information from each maintenance request; The scheduling module is used to screen vehicles based on key information and calibrate the optimal vehicle corresponding to the maintenance request based on the screening results; A planning module is used to determine several undetermined routes for the optimal vehicle for the maintenance request and construct a simulated undetermined route environment, calculate a simulated driving evaluation value of the simulated undetermined route environment, and plan an optimal route based on the simulated driving evaluation value; An execution module is used to generate an execution instruction corresponding to the optimal vehicle according to the preferred path and trigger a real-time monitoring instruction for the optimal vehicle; The judgment module is used to obtain real-time monitoring information according to the preset feedback node and determine whether to generate an adjustment instruction corresponding to the optimal vehicle based on the real-time monitoring information.

2. The intelligent transportation system for wind farm operation and maintenance according to claim 1, characterized in that: Vehicle screening is performed based on key information, and the optimal vehicle corresponding to the maintenance request is determined based on the screening results, including: The key information includes the location information of the unit to be repaired corresponding to the repair request, the unit fault level and the unit importance coefficient; Obtaining basic information of several vehicles, including vehicle location information, cargo space, and remaining battery power; Performing vehicle screening based on key information of each maintenance request and basic information of several vehicles to obtain screening results, wherein the screening results include a position matching coefficient, a cargo space matching coefficient, and a remaining power matching coefficient; Generate a comprehensive matching coefficient between each maintenance request and each vehicle based on the screening results; The vehicle with the largest comprehensive matching coefficient is set as the optimal vehicle to be determined corresponding to the maintenance request; Obtain all maintenance requests corresponding to each pending optimal vehicle, and set the priority coefficient of the corresponding maintenance request based on the unit fault level and unit importance coefficient in the maintenance request; The undetermined optimal vehicle is set as the optimal vehicle for the maintenance request with the largest priority coefficient, and the optimal vehicles for the remaining maintenance instructions are re-matched.

3. The intelligent transportation system for wind farm operation and maintenance according to claim 2, characterized in that: Determine several potential routes for the optimal vehicle for the maintenance request and build a simulation environment for the potential routes, including: Determine a plurality of pending routes based on the location information of the unit to be repaired in the repair request and the vehicle location information of the corresponding optimal vehicle; Obtaining geographic data of each undetermined path based on GIS, wherein the geographic data includes road data, terrain data, and obstacle data; Preprocessing the geographic data, and constructing a three-dimensional path model corresponding to the undetermined path based on the preprocessed terrain data; Obtain the power generation plan of the unit to be repaired that is subject to the maintenance request, and determine the maintenance time interval of the unit to be repaired based on the power generation plan; The departure time node and the predicted arrival time node of the optimal vehicle corresponding to the maintenance request are set according to the maintenance time interval and the historical driving log of the optimal vehicle corresponding to the maintenance request; Predict the weather conditions between the departure time node and the predicted arrival time node of the optimal vehicle to obtain some predicted weather information; The predicted driving impact characteristics of the optimal vehicle are generated based on the vehicle driving impact characteristics of the historical weather information, and the three-dimensional path model of the corresponding optimal vehicle is rendered to obtain the simulated undetermined path environment of the optimal vehicle.

4. The intelligent transportation system for wind farm operation and maintenance according to claim 3, characterized in that: Calculate the simulated driving evaluation value of the simulated undetermined path environment, including: Determining a first predicted driving period based on the departure time node and the predicted arrival time node of the optimal vehicle, and setting a plurality of simulation monitoring time nodes according to preset time intervals; Performing a dynamic simulation based on the simulated undetermined path environment and the optimal vehicle, and obtaining simulation monitoring data at each simulation monitoring time node, the simulation monitoring data including simulated driving speed, simulated remaining power, simulated driving vibration data, simulated energy consumption data, and simulated driving avoidance coefficient; The simulated driving speed, simulated remaining power, simulated driving vibration data, and simulated energy consumption data at multiple simulation monitoring time nodes are mapped onto the time reference line of the corresponding first predicted driving period to obtain a driving speed change curve, a power change curve, a vibration change curve, and an energy consumption change curve; Comparing each simulated driving speed in the driving speed change curve with the corresponding standard driving speed, and generating a first driving evaluation value according to the comparison result; generating a first compensation coefficient according to a curve change characteristic of the driving speed change curve; Comparing each simulated remaining power in the power change curve with the corresponding preset power threshold, and generating a second driving evaluation value according to the comparison result; generating a second compensation coefficient according to a curve change characteristic of the electric quantity change curve; comparing each simulated driving vibration data in the vibration change curve with a corresponding preset vibration threshold, and generating a third driving evaluation value according to the comparison result; generating a third compensation coefficient according to a curve change characteristic of the vibration change curve; comparing each simulated energy consumption data in the energy consumption change curve with a corresponding preset energy consumption threshold, and generating a fourth driving evaluation value according to the comparison result; generating a fourth compensation coefficient according to a curve change characteristic of the energy consumption change curve; Correcting the first driving evaluation value, the second driving evaluation value, the third driving evaluation value, and the fourth driving evaluation value according to the first compensation coefficient, the second compensation coefficient, the third compensation coefficient, and the fourth compensation coefficient, respectively, and generating a simulated driving evaluation value corresponding to the simulated undetermined path environment in combination with the simulated driving avoidance coefficient; The curve change characteristics include the curve fluctuation degree, change trend and change rate.

5. The intelligent transportation system for wind farm operation and maintenance according to claim 4, characterized in that: The simulation driving avoidance coefficient includes: The optimal vehicle corresponding to each simulated undetermined path environment is set as the primary optimal vehicle, and the optimal vehicles corresponding to other maintenance requests are set as suboptimal vehicles; Determine whether there is a vehicle driving conflict at each simulation monitoring time node in the simulation undetermined path environment; If so, the priority coefficients of the primary optimal vehicle and the secondary optimal vehicle in which the vehicle conflict exists are calculated respectively. If the priority coefficient of the primary optimal vehicle is greater than the priority coefficient of the secondary optimal vehicle, it is determined to be a false driving conflict. If the priority coefficient of the primary optimal vehicle is not greater than the priority coefficient of the secondary optimal vehicle, it is determined to be a true driving conflict. Calculate the avoidance time of the main optimal vehicle for each real driving conflict and map it to the corresponding simulation monitoring time node to obtain the comprehensive avoidance time at the corresponding simulation monitoring time node; Generate a simulation travel avoidance coefficient according to the number of simulation monitoring time nodes with real travel conflicts in the same simulation undetermined path environment and the comprehensive avoidance time at the corresponding simulation monitoring time nodes; The calculation formula of the simulation driving avoidance coefficient is: ； Among them, R is the simulation driving avoidance coefficient, n1 is the number of simulation monitoring time nodes with real driving conflicts in the same simulation undetermined path environment, n2 is the total number of simulation monitoring time nodes, r0 is the driving avoidance conversion coefficient, is the comprehensive avoidance time at the ith simulation monitoring time node where there is a true driving conflict, The preset avoidance time threshold.

6. The intelligent transportation system for wind farm operation and maintenance according to claim 5, characterized in that: Planning the optimal path based on the simulated driving evaluation value, including: Comparing the simulated driving evaluation values ​​of several undetermined routes of the optimal vehicle for the same maintenance request, and selecting the largest simulated driving path evaluation value and the corresponding undetermined route based on the comparison results; Presetting a driving evaluation value threshold; If the simulated driving evaluation value is greater than the driving evaluation value threshold, the corresponding undetermined path is set as the preferred path of the optimal vehicle corresponding to the maintenance request; If the simulated driving evaluation value is not greater than the driving evaluation value threshold, several undetermined paths of the optimal vehicle for the same maintenance request are analyzed to determine the undetermined paths with a connection relationship; Splicing the pending paths with connection relationships to obtain several pending splicing paths of optimal vehicles corresponding to the maintenance request; A simulated pending splicing path environment of the pending splicing path is constructed and a corresponding simulated driving evaluation value is calculated until the simulated driving evaluation value is greater than a driving evaluation value threshold, and the corresponding pending splicing path is set as a preferred path of the optimal vehicle corresponding to the maintenance request.

7. The intelligent transportation system for wind farm operation and maintenance according to claim 6, characterized in that: Generate execution instructions for the optimal vehicle based on the preferred path and trigger real-time monitoring instructions for the optimal vehicle, including: Generate execution path data based on the preferred path and encrypt and transmit it to the corresponding optimal vehicle, while triggering the self-test instruction of the corresponding optimal vehicle; Perform self-inspection on the optimal vehicle according to the self-inspection instruction, and calculate the health coefficient of the optimal vehicle based on the self-inspection results; If the health coefficient is greater than the preset health coefficient threshold, an execution instruction corresponding to the optimal vehicle is generated and a real-time monitoring instruction of the optimal vehicle is triggered. The real-time monitoring instruction includes collecting real-time monitoring information according to a preset feedback node, and the preset feedback node corresponds one-to-one to the simulation monitoring time node in the predicted driving period of the corresponding optimal vehicle.

8. The intelligent transportation system for wind farm operation and maintenance according to claim 7, characterized in that: Determine whether to generate adjustment instructions corresponding to the optimal vehicle based on real-time monitoring information, including: Presetting a test period and determining a number of preset feedback nodes in the test period; Acquiring real-time monitoring information at each preset feedback node, the real-time monitoring information including real-time driving speed, real-time remaining power, real-time driving vibration data, real-time energy consumption data, and real-time driving avoidance coefficient; Compare the real-time monitoring information at each preset feedback node with the simulated monitoring information at the corresponding simulation monitoring time node to obtain the deviation coefficients of the real-time driving speed, real-time remaining power, real-time driving vibration data, and real-time energy consumption data from the simulated driving speed, simulated remaining power, simulated driving vibration data, and simulated energy consumption data; Generate a comprehensive deviation coefficient at each preset feedback node based on the deviation coefficient, and construct a comprehensive deviation coefficient change curve during the inspection period; Predicting a second predicted driving period corresponding to the optimal vehicle according to the real-time monitoring information during the inspection period, and subtracting the predicted driving period from the first predicted driving period to obtain a predicted driving period difference; performing a curve trend extrapolation on a comprehensive deviation coefficient change curve during the inspection period to obtain a plurality of predicted comprehensive deviation coefficients during a second predicted driving period, and generating a plurality of predicted monitoring information based on the predicted comprehensive deviation coefficients, the predicted monitoring information including a predicted driving speed, a predicted remaining battery power, predicted driving vibration data, and predicted energy consumption data; generating a predicted driving evaluation value based on the real-time monitoring information of the inspection period and the predicted monitoring information of the second predicted driving period, and subtracting the predicted driving evaluation value from the simulated driving evaluation value to obtain a predicted driving evaluation value difference; Calculating a predicted driving avoidance coefficient based on the real-time monitoring information of the inspection period and the predicted monitoring information of the second predicted driving period, and subtracting the predicted driving avoidance coefficient from the simulated driving avoidance coefficient to obtain a predicted driving avoidance coefficient difference; Generate a first difference evaluation value according to the comprehensive deviation coefficient at each preset feedback node and the predicted comprehensive deviation coefficient; generating a second difference evaluation value according to the predicted travel period difference; generating a third difference evaluation value according to the predicted driving evaluation value difference; Generate a correction coefficient based on the difference in predicted driving avoidance coefficients; generating a comprehensive difference evaluation value according to the first difference evaluation value, the second difference evaluation value, the third difference evaluation value, and the correction coefficient; If the comprehensive difference evaluation value is greater than the preset difference evaluation value threshold, it is determined that an adjustment instruction corresponding to the optimal vehicle is generated.

9. An intelligent transportation method for wind farm operation and maintenance, characterized in that: include: Receive several maintenance requests and extract key information from each maintenance request; Screen vehicles based on key information and calibrate the optimal vehicle for the corresponding maintenance request based on the screening results; Determine several undetermined routes for the optimal vehicle for the maintenance request and construct a simulated undetermined route environment, calculate a simulated driving evaluation value of the simulated undetermined route environment, and plan an optimal route based on the simulated driving evaluation value; Generate execution instructions for the optimal vehicle based on the preferred path and trigger real-time monitoring instructions for the optimal vehicle; Obtain real-time monitoring information according to the preset feedback node, and determine whether to generate adjustment instructions corresponding to the optimal vehicle based on the real-time monitoring information.

Images