Operation method of high-voltage transformer substation tubular bus drainage wire disassembling and assembling robot

Abstract

The invention discloses an operation method of a high-voltage transformer substation tubular bus drainage wire detaching and erecting robot, and relates to the technical field of power construction. Comprising the steps of obtaining parameter data outside a tubular busbar drainage wire; a positioning model is constructed, the positioning model is based on the parameter data, an operation plan of the disassembly and assembly robot is output, and the operation plan comprises an operation position, an operation path and operation time; constructing a detection model, and obtaining environment data influencing the operation of the dismounting and building robot outside the tubular busbar drainage wire based on the detection model and the parameter data; obtaining attribute data of the disassembly and assembly robot; and constructing an influence discrimination model. According to the method, the attribute data and the environment data are efficiently matched through the feature tree diagram to form an accurate mapping relation, so that it is ensured that the disassembly and assembly robot can accurately recognize and understand the working environment in the working process, the data processing efficiency is improved, and the adaptability of the robot to the working environment is further enhanced.

Description

Technical Field

[0001] The invention relates to the technical field of electric power construction, and in particular to a robot operation method for dismantling and assembling a mother pipe drainage line of a high-voltage substation. Background Art

[0002] With the rapid development of modern industry and the improvement of people's living standards, power users' requirements for power supply reliability are also constantly increasing. In order to reduce power outage time or even avoid power outages, power supply companies in various places have accelerated the application and promotion of live working robots in substations. Substations are places where voltage and current are transformed, electric energy is received and distributed in the power system. Therefore, the robot operation method for dismantling and assembling the mother pipe drainage line of high-voltage substation is crucial for the application of robots in substations.

[0003] After searching, the Chinese invention patent with publication number "CN113708290 A" discloses "a method, device and robot terminal for controlling the threading of drainage wires of live working robots". The application obtains a state image before threading, identifies the posture information of the end of the drainage wire from the state image, takes the posture of the end of the drainage wire as a standard, adjusts the alignment of the wire clamp tool and the end of the drainage wire by adjusting the posture of the wire clamp arm, and allows the wire clamp arm equipped with the wire clamp tool to actively complete the threading action, thereby avoiding the occurrence of displacement of the posture of the drainage wire caused by arm movement, thereby improving the threading success rate;

[0004] In addition, the Chinese invention patent with publication number "CN113964720A" discloses "a distribution network live operation robot system and a method for connecting and disconnecting drainage lines". This application uses a unique robot structure design to enable the robot's main control to plan the overall task, and the slave control to be responsible for the motion control of each joint of the robot arm. The autonomous control uses the recognition information collected and processed by the visual device combined with the deep learning visual detection control method to identify the object to be operated and its position, and control the robot arm to complete the operation, thereby achieving short-distance high-precision displacement and positioning of the robot arm;

[0005] The Chinese invention patent with the last publication number "CN116787466A" discloses "a drainage line identification method, storage medium and robot based on an insulating sleeve". The application installs an insulating sleeve on the head of the cable drainage line while installing the cable drainage line; a fixing hole for installing the cable drainage line head is provided on the sleeve body of the insulating sleeve. During installation, the head of the current drainage line is inserted into the fixing hole on the sleeve body of the insulating sleeve for fixed installation; a feature code area consisting of multiple strong reflection areas and weak reflection areas is provided on the insulating sleeve; the current environment is scanned by a laser radar to obtain radar point cloud data, and the signal strength of the radar point cloud data is matched. Since the weak reflection area absorbs most of the laser beam, the laser beam can be used to identify the current drainage line. Light radar, and the strong reflection area will reflect most of the laser radar, so that when the laser radar scans the feature code area on the insulating sleeve, the data block corresponding to the signal feature code corresponding to the feature code area can be obtained according to the reflection intensity of the signal in the strong reflection area and the weak reflection area in the feature code area, and then the spatial information of the insulating sleeve can be obtained by parsing according to the obtained data block. The insulating sleeve is set on the drainage line, and the spatial position of the drainage line can be obtained according to the obtained spatial information of the insulating sleeve, and then the drainage line can be identified, and the insulating sleeve that is easily identified by the laser radar is set on the cable drainage line, so that the laser radar can easily identify the cable drainage line, which is convenient for subsequent live operations.

[0006] However, the above-mentioned disclosed methods and similar methods, in actual operation, focus on the operation and recognition technology of the robotic arm, but lack the comprehensive collection and fusion processing of the environmental data of the working area, resulting in changes in environmental parameters affecting the working efficiency and safety when the robot works in a complex environment. Summary of the invention

[0007] The object of the present invention is to provide a robot operation method for dismantling and assembling a mother pipe drainage line in a high-voltage substation, so as to solve the problems raised in the above-mentioned background technology.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] A robot operation method for dismantling and assembling a mother pipe drainage line in a high-voltage substation, comprising:

[0010] Obtain parameter data outside the mother tube drainage line;

[0011] Build a positioning model. The positioning model outputs the operation plan of the disassembly and assembly robot based on the parameter data. The operation plan includes: operation location, operation path and operation time;

[0012] Construct a detection model, and obtain environmental data outside the mother pipe drainage line that affects the operation of the disassembly and assembly robot based on the detection model and parameter data;

[0013] Obtain the attribute data of the disassembly robot;

[0014] Construct an impact discrimination model, which outputs discrimination results based on attribute data and environmental data. The discrimination results are used to display factors that affect the operation of the disassembly and assembly robot.

[0015] Construct an instruction control model. The instruction control model outputs dynamic adjustment instructions based on the judgment results, and the dynamic adjustment instructions act on the operation plan;

[0016] Construct a monitoring feedback model, which is used to track the operating status of the disassembly and assembly robot in real time, and generate adjustment data based on the comparison between the real-time operating status of the disassembly and assembly robot and the preset target. The adjustment data acts on the instruction control model and affects the dynamic adjustment instructions.

[0017] The influence discrimination model includes:

[0018] Acquire feature data of attribute data and environmental data respectively, select feature data matching the attribute data and environmental data and build a mapping relationship, and integrate the attribute data and environmental data into several feature-based fusion data sets based on the mapping relationship;

[0019] Obtain the features in the disassembly and assembly robot's operation plan, and assign a high weight to the fusion data that matches the features in the disassembly and assembly robot's operation plan;

[0020] A preset discrimination threshold is set manually based on the historical operation plan of the disassembly and assembly robot and safety regulations. The discrimination threshold is compared with the data value in the high-weight fusion data, and the discrimination result is output.

[0021] As a further preferred embodiment of the present technical solution, the characteristic data in the attribute data include: the length of the mechanical arm of the disassembly robot, the rotation range of the mechanical arm, the type of tools assembled by the disassembly robot, and the specifications of the disassembly tools assembled by the disassembly robot;

[0022] The characteristic data of the environmental data include: temperature, humidity, wind speed, light intensity, electromagnetic interference level, and material and specification of the mother pipe drainage line in the operation area.

[0023] As a further preferred embodiment of the present technical solution, a method for constructing a mapping relationship includes:

[0024] Construct a feature tree diagram, wherein the feature tree diagram constructs a number of branch nodes according to the types of feature data in the attribute data and the environment data, each branch node has a number of child nodes, and the number of child nodes represents the specific feature data value;

[0025] The real-time operation data of the disassembly and assembly robot is obtained. Based on the real-time operation data, the feature data values ​​that match the attribute data and the environmental data are retrieved in the feature tree diagram. The child nodes corresponding to the matching feature data values ​​are connected to form a mapping path, which is the mapping relationship.

[0026] As a further preferred embodiment of the present technical solution, the comparison method of the discrimination threshold and the data value in the high-weight fusion data set includes:

[0027] Retrieve data values ​​of matching features within the discrimination threshold based on features in the high-weight fusion data set;

[0028] If the data value of the matching feature is retrieved, the data value comparison is directly performed;

[0029] If no data value of a matching feature is found, then the data value of a similar feature is retrieved for interpolation calculation, and the approximate value is obtained before comparison;

[0030] When the data value in the high-weight fusion data set exceeds the discrimination threshold, the discrimination result is that there is a risk in the disassembly and assembly robot operation;

[0031] When the data value in the high-weight fusion data set is lower than or equal to the discrimination threshold, the discrimination result is that the disassembly and assembly robot operation is safe.

[0032] As a further preferred embodiment of the present technical solution, the method for distinguishing similar feature data values ​​includes:

[0033] The characteristics of the feature data in the attribute data and the environmental data are obtained respectively, and a superordinate feature summary table is constructed. The superordinate feature summary table integrates and summarizes the obtained features based on physical, environmental and temporal aspects to form feature classifications at different levels.

[0034] As a further preferred embodiment of the present technical solution, the method for obtaining parameter data includes:

[0035] Construct a number of parameter collection nodes, which are based on lidar technology. The nodes are evenly distributed around the mother pipe drainage line. Set a data encryption and cleaning method. During the data collection process, redundant data is cleaned in real time and the cleaned data is output. A data shielding enhancement model is constructed. Multiple groups of cleaned data in adjacent time periods are acquired in real time to extract the middle value or the average value in any way to obtain parameter data. A mid-end storage node is created to acquire the parameter data and back it up. A feedback rule is constructed between the mid-end storage node and the data shielding enhancement model. The feedback rule presets a critical threshold. The critical threshold is dynamically set based on the historical parameter data. When the parameter data exceeds the critical threshold, the feedback rule will trigger the data replacement of the mid-end storage node with the latest acquired parameter data.

[0036] As a further preferred embodiment of the present technical solution, the parameter data includes: the length, diameter, curvature, position coordinates, distance from surrounding objects, and current and voltage of the mother tube drainage line;

[0037] The positioning model includes:

[0038] Construct three-dimensional space modeling. The three-dimensional space modeling takes the mother tube drainage line as the benchmark, establishes a three-dimensional coordinate system, converts the parameter data of the mother tube drainage line into coordinate points and vectors in the three-dimensional space, and constructs a three-dimensional space model of the mother tube drainage line based on the coordinate points and vectors. In addition, the three-dimensional space modeling takes the mother tube drainage line as the center, simulates the space environment around the mother tube drainage line, and divides the simulation space into different operation areas based on the position coordinates in the parameter data and the distance to the surrounding objects. Each operation area corresponds to the possible operation position and operation path of the disassembly and assembly robot;

[0039] The working position and working path of the dismantling robot in each working area are obtained and combined with the length of the mother pipe drainage line, the working time of the dismantling robot in each working area is calculated, the working time, working position and working path are summarized, and integrated into an operation plan for the dismantling robot.

[0040] As a further preferred embodiment of the present technical solution, the detection model includes:

[0041] Construct an environmental perception system. The environmental perception system is constructed based on a cross-combination of several different sensor units. It is used to collect real-time environmental data of the operating area, obtain parameter data features, mark sensor units based on feature types, build a fusion algorithm, assign high weights to the marked sensor units, assign equal weights to the remaining sensor units in different sensor units, and fuse the data of the marked sensor units with the data of the remaining sensor units to obtain environmental data;

[0042] The operating formula of the fusion algorithm is: where d m represents the environmental data value collected by the sensor unit m marked as high-weight, α represents the weight coefficient assigned to the high-weight sensor unit m, d i represents the sum of the environmental data values ​​collected by all other sensor units, i.e. n-1, except the high-weight sensor unit m. is a normalization factor used to distribute the sum of data from other sensor units to each sensor unit.

[0043] As a further preferred embodiment of the present technical solution, the instruction control model includes:

[0044] Obtain the characteristics of the discrimination results, including the operation risk level, operation safety area, and operation priority, and build an instruction generation system. The instruction generation system dynamically generates control instructions based on the characteristics of the discrimination results, combined with the operation plan and operation capability of the disassembly and assembly robot, and based on the adaptive control strategy of machine learning;

[0045] The operation plan includes: operation area selection, operation tool selection, operation path planning and operation time allocation.

[0046] As a further preferred embodiment of the present technical solution, the monitoring feedback model includes:

[0047] Acquire the real-time operation data of the disassembly and assembly robot, extract the features in the real-time operation data, and build an operation status database based on the features in the operation data. The operation status database is used to update the operation data of the disassembly and assembly robot in real time.

[0048] Associating the operation status database with the time axis, intercepting multiple groups of operation data parameters in adjacent time periods, analyzing the variation range of the operation data parameters, and predicting the operation status of the disassembly and assembly robot in the future time period based on the variation range, and setting the operation status parameter value in the future time period as a preset target;

[0049] Compare preset targets and real-time operating data, and generate adjustment data based on deviations.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] The high-voltage substation mother drain line disassembly and assembly robot operation method efficiently matches attribute data and environmental data through a feature tree diagram to form an accurate mapping relationship, thereby ensuring that the disassembly and assembly robot can accurately identify and understand the operating environment during the operation process, improving the efficiency of data processing, and enhancing the robot's adaptability to the operating environment;

[0052] Secondly, the present invention can accurately judge the risk level of the dismantling robot operation in real time through the comparison method of the data value in the high-weight fusion data set and the discrimination threshold, so that the robot can fully evaluate the working environment before the operation, thereby avoiding potential safety risks;

[0053] In addition, the present invention can acquire and clean parameter data in real time by constructing parameter collection nodes and data shielding enhancement models, ensuring the accuracy and reliability of the data. At the same time, by constructing a three-dimensional space model and a detection model, the robot can better understand the working environment and improve the accuracy of the operation.

[0054] Finally, the present invention realizes comprehensive monitoring and dynamic regulation of the dismantling robot operation through the command control model and the monitoring feedback model. By acquiring the operation data of the dismantling robot in real time, predicting its future operation status, and generating adjustment data based on the deviation, the robot can make adaptive adjustments during the operation process, ensuring the smooth progress of the operation.

[0055] It should also be noted that the present invention constructs an impact judgment model so that the dismantling and assembly robot can comprehensively consider various influencing factors when conducting operation risk judgment, thereby obtaining a more comprehensive and accurate judgment result, thereby improving the safety and stability of the dismantling and assembly robot in the dismantling and assembly operations of the mother pipe drainage line of the high-voltage substation, and also provides more reliable technical support for the operation and maintenance management of the substation. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is the operation logic diagram of the method of the present invention;

[0057] Figure 2 It is the operation logic diagram of the impact discrimination model of the present invention;

[0058] Figure 3 A diagram of a method for constructing a mapping relationship of the present invention;

[0059] Figure 4 A diagram showing a method for obtaining parameter data of the present invention;

[0060] Figure 5 An operating logic diagram for the invention positioning model;

[0061] Figure 6 It is the operation logic diagram of the detection model of the present invention;

[0062] Figure 7 This is the operation logic diagram of the monitoring feedback model of the present invention. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] The application of the present invention in the scenario of dismantling and installing pipe mother drainage lines in high-voltage substations. It should be noted that in this scenario, the present application proposes a robot operation method for dismantling and installing pipe mother drainage lines in high-voltage substations. Before the robot operation of dismantling and installing pipe mother drainage lines in high-voltage substations, it is necessary to ensure the stability and safety of the robot system. First, a comprehensive system inspection is required to ensure that all components of the robot, such as robotic arms, sensors, control systems, etc., are in good working condition. Secondly, a detailed survey of the operating area is required to clarify the position, height, angle and other information of the pipe mother drainage lines to provide accurate data support for the robot operation.

[0065] like Figure 1-Figure 7 As shown, this solution includes: obtaining parameter data outside the mother tube drainage line, building a positioning model, the positioning model outputs the operation plan of the disassembly and assembly robot based on the parameter data, the operation plan includes: operation position, operation path and operation time, building a detection model, the detection model obtains environmental data outside the mother tube drainage line that affects the operation of the disassembly and assembly robot based on the parameter data, obtains the attribute data of the disassembly and assembly robot, builds an influence discrimination model, the influence discrimination model outputs discrimination results based on the attribute data and the environmental data, the discrimination results are used to display the factors affecting the operation of the disassembly and assembly robot, builds an instruction control model, the instruction control model outputs dynamic adjustment instructions based on the discrimination results, the dynamic adjustment instructions act on the operation plan, builds a monitoring feedback model, the monitoring feedback model is used to track the operation status of the disassembly and assembly robot in real time, and generates adjustment data based on the comparison between the real-time operation status of the disassembly and assembly robot and the preset target, the adjustment data acts on the instruction control model and affects the dynamic adjustment instructions.

[0066] It should be noted that, in this embodiment, the parameter data include: the length, diameter, curvature, position coordinates, distance from surrounding objects, and current and voltage of the mother pipe drainage line; the operation plan includes: operation area selection, operation tool selection, operation path planning, and operation time allocation; the characteristic data in the attribute data include: the length of the robotic arm of the disassembly robot, the rotation range of the robotic arm, the type of tools assembled by the disassembly robot, and the specifications of the disassembly tools assembled by the disassembly robot; the characteristic data of the environmental data include: the temperature, humidity, wind speed, light intensity, degree of electromagnetic interference, and the material and specifications of the mother pipe drainage line in the operation area.

[0067] It should be added that in the actual operation process of the disassembly and assembly robot, due to the complex and changeable working environment, the real-time acquired data will contain noise or interference. In order to ensure the accuracy and stability of the acquired data, the present invention further introduces a data cleaning and verification mechanism. Specifically, after obtaining the real-time operation data of the disassembly and assembly robot, the monitoring feedback model will first clean the data to remove outliers and noise to ensure the accuracy and reliability of the data. Then, the cleaned data will be verified through the data verification mechanism to ensure that it meets the preset data range and format requirements.

[0068] As a preferred embodiment, refer to Figure 2 It can be seen that in the present application, the impact discrimination model includes: respectively obtaining feature data of attribute data and environmental data, selecting feature data that matches the attribute data and environmental data and constructing a mapping relationship, based on the mapping relationship, integrating the attribute data and environmental data into several feature-based fusion data sets, obtaining features in the disassembly and assembly robot's work plan, giving high weights to the fusion data that matches the features in the disassembly and assembly robot's work plan, presetting a discrimination threshold, the discrimination threshold is manually set based on the disassembly and assembly robot's historical work plan and safety regulations, comparing the discrimination threshold with the data values ​​in the high-weight fusion data set, and outputting the discrimination result.

[0069] It should be noted that, in the present embodiment, the mapping relationship is the correspondence between the characteristic data such as the length of the robotic arm, the rotation range of the robotic arm, the type and specification of the tools assembled by the disassembly and assembly robot in the attribute data, and the characteristic data such as the temperature, humidity, wind force, light intensity, and electromagnetic interference degree of the working area in the environmental data. This mapping relationship is used to help the disassembly and assembly robot better understand the working environment, so as to make more accurate judgment results. In addition, during the actual operation of the influence discrimination model, the setting of the discrimination threshold is not static, but will be dynamically adjusted according to the real-time feedback data and historical operation data during the operation of the disassembly and assembly robot to adapt to the needs of different working environments and work tasks. For example: when the disassembly and assembly robot is performing disassembly and assembly operations, if it is found that the temperature or humidity of the working area exceeds the preset discrimination threshold, the influence discrimination model will respond immediately, output the corresponding discrimination result, and send a dynamic adjustment instruction to the disassembly and assembly robot through the instruction control model, requiring the robot to adjust the operation plan, such as changing the operation path, adjusting the operation time, etc., to ensure the safety and stability of the operation.

[0070] Furthermore, it should be added that, in actual operation, the job plan output by the positioning model constructed in this embodiment may include any one or more of the job location, job path, and job time. When only one feature exists, a high weight is given to the fused dataset that matches the feature in the job plan of the disassembly and assembly robot. When multiple features exist, the weights of the fused datasets that match the features in the job plan of the disassembly and assembly robot are evenly divided.

[0071] As a preferred embodiment, refer to Figure 3 It can be seen that in the present application, the method for constructing a mapping relationship includes: constructing a feature tree diagram, the feature tree diagram constructs a number of branch nodes according to the types of feature data in the attribute data and the environmental data, each branch node is provided with a number of child nodes, the number of child nodes represents the specific feature data value, the real-time operation data of the disassembly and assembly robot is obtained, based on the real-time operation data, the feature data values ​​that match the attribute data and the environmental data are retrieved in the feature tree diagram, the child nodes corresponding to the matching feature data values ​​are connected to form a mapping path, and the mapping path is the mapping relationship.

[0072] It should be noted that during the actual operation of this embodiment, the mapping relationship needs to be verified and optimized to ensure its accuracy and effectiveness. Specifically, when the disassembly robot generates new operating data during the actual operation process, these new data will be used to verify the mapping relationship. If the verification result shows that the mapping relationship can accurately reflect the relationship between the working environment and attributes of the disassembly robot, then the mapping relationship is considered to be valid and can continue to be used. However, if the verification result shows that there are deviations or errors in the mapping relationship, the mapping relationship needs to be optimized. The optimization methods include: adjusting the branch nodes and sub-nodes of the feature tree diagram based on the new operating data, adding or deleting certain feature data values, and adjusting the mapping path, etc.

[0073] As a preferred embodiment, in the present application, the comparison method of the discrimination threshold and the data value in the high-weight fusion data set includes: retrieving the data value of the matching feature within the discrimination threshold based on the feature in the high-weight fusion data set; if the data value of the matching feature is retrieved, the data value comparison is directly performed; if the data value of the matching feature is not retrieved, the data value of the similar feature is retrieved for interpolation calculation, and the approximate value of the feature is obtained before comparison; when the data value in the high-weight fusion data set exceeds the discrimination threshold, the judgment result is that there is a risk in the operation of the disassembly and assembly robot; when the data value in the high-weight fusion data set is lower than or equal to the discrimination threshold, the judgment result is that the operation of the disassembly and assembly robot is safe.

[0074] As a preferred embodiment, in the present application, the method for distinguishing similar feature data values ​​includes: respectively obtaining the features of the feature data in the attribute data and the environmental data, constructing a superordinate feature summary table, and integrating and summarizing the acquired features based on physical, environmental and temporal aspects to form feature classifications at different levels.

[0075] It should be noted that, in this embodiment, the construction of the upper-level feature summary table aims to provide a systematic framework to help the disassembly and assembly robot better understand and analyze the complexity of the working environment. By integrating and summarizing physical, environmental, and temporal features, the upper-level feature summary table can form a multi-level feature classification system, thereby achieving a more comprehensive and detailed description of the working environment. In the actual operation process, the disassembly and assembly robot retrieves the corresponding feature classification in the upper-level feature summary table according to the operating data obtained in real time, and performs more accurate operation risk assessment and judgment based on these feature classifications.

[0076] As a preferred embodiment, refer to Figure 4 It can be seen that in the present application, the method for obtaining parameter data includes: constructing a number of parameter collection nodes, the parameter collection nodes are based on lidar technology, and the number of parameter collection nodes are evenly distributed around the mother pipe drainage line, setting a data encryption and cleaning method, cleaning redundant data in real time during the data collection process, and outputting the cleaned data, constructing a data shielding enhancement model, real-time acquisition of multiple groups of cleaned data in adjacent time periods, and extracting the middle value or the average value in any one of the ways to obtain parameter data, creating a mid-end storage node, obtaining parameter data and backing it up, and constructing feedback rules between the mid-end storage node and the data shielding enhancement model. The feedback rule presets a critical threshold, and the critical threshold is dynamically set based on the historical parameter data as the standard. When the parameter data exceeds the critical threshold, the feedback rule will trigger the data replacement of the mid-end storage node and replace it with the latest acquired parameter data.

[0077] It should be noted that in this embodiment, when the method of extracting the middle value is selected to obtain parameter data, if the data fluctuation is small and the overall trend is stable, then the middle value effectively represents the overall state of the current parameter data, reducing the impact of extreme values ​​or noise data. At the same time, the method of obtaining the middle value can also reduce the system's demand for data processing speed, thereby improving the stability and reliability of the system to a certain extent. When the method of extracting the average value is selected to obtain parameter data, the average value can more comprehensively reflect the overall situation of the data. Especially when the data fluctuates greatly or there are extreme values, the average value can weaken the impact of extreme values ​​on the overall data through the "averaging" effect, providing more robust and accurate parameter data.

[0078] As a preferred embodiment, refer to Figure 5It can be seen that the positioning model includes: constructing three-dimensional space modeling, the three-dimensional space modeling takes the mother tube drainage line as the benchmark, establishes a three-dimensional coordinate system, converts the parameter data of the mother tube drainage line into coordinate points and vectors in the three-dimensional space, and constructs a three-dimensional space model of the mother tube drainage line based on the coordinate points and vectors. In addition, the three-dimensional space modeling takes the mother tube drainage line as the center, simulates the spatial environment around the mother tube drainage line, and divides the simulation space into different work areas based on the position coordinates in the parameter data and the distance to the surrounding objects. Each work area corresponds to the possible work position and work path of the disassembly and assembly robot. The work position and work path of the disassembly and assembly robot in each work area are obtained and combined with the length of the mother tube drainage line. The operation time of the disassembly and assembly robot in each work area is calculated, the operation time, operation position and operation path are summarized, and integrated to form an operation plan for the disassembly and assembly robot.

[0079] It should be added that based on the content of this implementation mode and Figure 5 It can be seen that the content of the integrated calculation is to obtain the working position and working path of the disassembly and assembly robot in each working area and combine them with the length of the mother pipe drainage line, calculate the working time of the disassembly and assembly robot in each working area, summarize the working time, working position and working path, and integrate them to form the working plan of the disassembly and assembly robot. It should be further explained that the method of integrated calculation is to use computer vision and machine learning algorithms to conduct in-depth analysis of coordinate points, vectors and working areas in three-dimensional space modeling. First, according to the working position and working path of the disassembly and assembly robot in each working area, combined with the length and shape of the mother pipe drainage line, the moving distance and working complexity required for the robot to perform the operation are evaluated. Then, the historical operation data and time series analysis are used to predict the time required for the disassembly and assembly robot to complete the operation in each working area. Then, the predicted working time is combined with the actual working position and working path to generate a detailed work plan.

[0080] As a preferred embodiment, refer to Figure 6 It can be seen that in this embodiment, the detection model includes: constructing an environmental perception system, which is constructed based on a cross-combination of several different sensor units, and is used for real-time collection of environmental data of the working area, obtaining parameter data characteristics, marking sensor units based on feature types, and constructing a fusion algorithm, giving high weights to marked sensor units, giving equal weights to the remaining sensor units in different sensor units, and fusing the data of the marked sensor units with the data of the remaining sensor units to obtain environmental data.

[0081] It should be noted that the fusion algorithm is: where d m represents the environmental data value collected by the sensor unit m marked as high-weight, α represents the weight coefficient assigned to the high-weight sensor unit m, di represents the sum of the environmental data values ​​collected by all other sensor units, i.e. n-1, except the high-weight sensor unit m. is a normalization factor used to distribute the sum of data from other sensor units to each sensor unit.

[0082] It should be noted that when the fusion algorithm is actually running, for example, when the high-weight sensor unit is a voltage sensor unit, the collected environmental data value is a voltage value, for example, assuming it is 100kv (just as an example, the actual value may vary depending on the environment and the sensor unit), and then, the total data of other sensor units, 100kv, is evenly distributed to the remaining n-1 sensor units. Assuming there are 3 sensor units (n=4), there are 2 sensor units in addition to the high-weight sensor unit, so each sensor unit gets 100kv / 2=50kv. Finally, these values ​​are substituted into the operating formula of the fusion algorithm to calculate the fused environmental data value.

[0083] R=5*215kv+2*(50kv / 2)=1075kv+50kv=1125kv (Note: the unit kv here is only used for example, other units or dimensionless values ​​may be used in actual calculations).

[0084] As a preferred embodiment, in this embodiment, the instruction control model includes: obtaining the characteristics of the judgment result, the judgment result characteristics include the operation risk level, the operation safety area, and the operation priority, and constructing an instruction generation system. The instruction generation system is based on the judgment result characteristics, combined with the operation plan and operation capability of the disassembly and assembly robot, and based on the adaptive control strategy of machine learning to dynamically generate control instructions.

[0085] As a preferred embodiment, refer to Figure 7 It can be seen that, in this embodiment, the monitoring feedback model includes: obtaining real-time operation data of the disassembly and construction robot, and extracting features in the real-time operation data, constructing an operation status database based on the features in the operation data, the operation status database is used to update the operation data of the disassembly and construction robot in real time, associating the operation status database and the time axis, intercepting multiple groups of operation data parameters in adjacent time periods, analyzing the change range of the operation data parameters, and predicting the operation status of the disassembly and construction robot in the future time period based on the change range, setting the operation status parameter value of the future time period as a preset target, comparing the preset target and the real-time operation data, and generating adjustment data based on the deviation.

[0086] It should be noted that, in this embodiment, the comparison between the preset target and the real-time operation data and the generation of adjustment data based on the deviation are achieved by the deviation analysis algorithm in the prior art. The deviation analysis algorithm is an algorithm widely used in data monitoring and prediction adjustment. It compares the preset target and the real-time data to calculate the deviation between the two and generates corresponding adjustment data based on the deviation. These adjustment data can be used to guide the operation of the disassembly robot to ensure that it can operate according to the preset target.

[0087] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is limited by the attached embodiments and their equivalents.

Claims

1. A robot operation method for dismantling and assembling a mother pipe drainage line in a high-voltage substation, characterized in that: include: Obtain parameter data outside the mother tube drainage line; Build a positioning model. The positioning model outputs the operation plan of the disassembly and assembly robot based on the parameter data. The operation plan includes: operation location, operation path and operation time; Construct a detection model, and obtain environmental data outside the mother pipe drainage line that affects the operation of the disassembly and assembly robot based on the detection model and parameter data; Obtain the attribute data of the disassembly robot; Construct an impact discrimination model, which outputs discrimination results based on attribute data and environmental data. The discrimination results are used to display factors that affect the operation of the disassembly and assembly robot. Construct an instruction control model. The instruction control model outputs dynamic adjustment instructions based on the judgment results, and the dynamic adjustment instructions act on the operation plan; Construct a monitoring feedback model, which is used to track the operating status of the disassembly and assembly robot in real time, and generate adjustment data based on the comparison between the real-time operating status of the disassembly and assembly robot and the preset target. The adjustment data acts on the instruction control model and affects the dynamic adjustment instructions. The influence discrimination model includes: Acquire feature data of attribute data and environmental data respectively, select feature data matching the attribute data and environmental data and build a mapping relationship, and integrate the attribute data and environmental data into several feature-based fusion data sets based on the mapping relationship; Obtain the features in the disassembly and assembly robot's operation plan, and assign a high weight to the fusion data that matches the features in the disassembly and assembly robot's operation plan; A discrimination threshold is preset, and the discrimination threshold is manually set based on the historical operation plan of the disassembly and assembly robot and safety regulations. The discrimination threshold is compared with the data value in the high-weight fusion data, and the discrimination result is output.

2. A robot operation method for dismantling and assembling a mother pipe drainage line in a high-voltage substation according to claim 1, characterized in that: The characteristic data in the attribute data include: the length of the mechanical arm of the disassembly robot, the rotation range of the mechanical arm, the type of tools assembled by the disassembly robot, and the specifications of the disassembly tools assembled by the disassembly robot; The characteristic data of the environmental data include: temperature, humidity, wind speed, light intensity, electromagnetic interference level, and material and specification of the mother pipe drainage line in the operation area.

3. A robot operation method for dismantling and assembling a mother pipe drainage line in a high-voltage substation according to claim 2, characterized in that: The methods for constructing mapping relationships include: Construct a feature tree diagram, wherein the feature tree diagram constructs a number of branch nodes according to the types of feature data in the attribute data and the environment data, each branch node has a number of child nodes, and the number of child nodes represents the specific feature data value; The real-time operation data of the disassembly and assembly robot is obtained. Based on the real-time operation data, the feature data values ​​that match the attribute data and the environmental data are retrieved in the feature tree diagram. The child nodes corresponding to the matching feature data values ​​are connected to form a mapping path, which is the mapping relationship.

4. A robot operation method for dismantling and assembling a mother pipe drainage line in a high-voltage substation according to claim 1, characterized in that: The comparison method of the discrimination threshold and the data value in the high-weight fusion data set includes: Retrieve data values ​​of matching features within the discrimination threshold based on features in the high-weight fusion data set; If the data value of the matching feature is retrieved, the data value comparison is directly performed; If no data value of a matching feature is found, then the data value of a similar feature is retrieved for interpolation calculation, and the approximate value is obtained before comparison; When the data value in the high-weight fusion data set exceeds the discrimination threshold, the discrimination result is that there is a risk in the disassembly and assembly robot operation; When the data value in the high-weight fusion data set is lower than or equal to the discrimination threshold, the discrimination result is that the disassembly and assembly robot operation is safe.

5. A robot operation method for dismantling and assembling a mother pipe drainage line in a high-voltage substation according to claim 4, characterized in that: Methods for determining similar feature data values ​​include: The characteristics of the feature data in the attribute data and the environmental data are obtained respectively, and a superordinate feature summary table is constructed. The superordinate feature summary table integrates and summarizes the obtained features based on physical, environmental and temporal aspects to form feature classifications at different levels.

6. A robot operation method for dismantling and assembling a mother pipe drainage line in a high-voltage substation according to claim 1, characterized in that: Methods for obtaining parameter data include: Construct a number of parameter collection nodes, which are based on lidar technology. The nodes are evenly distributed around the mother pipe drainage line. Set a data encryption and cleaning method. During the data collection process, redundant data is cleaned in real time and the cleaned data is output. A data shielding enhancement model is constructed. Multiple groups of cleaned data in adjacent time periods are acquired in real time to extract the middle value or the average value in any way to obtain parameter data. A mid-end storage node is created to acquire the parameter data and back it up. A feedback rule is constructed between the mid-end storage node and the data shielding enhancement model. The feedback rule presets a critical threshold. The critical threshold is dynamically set based on the historical parameter data. When the parameter data exceeds the critical threshold, the feedback rule will trigger the data replacement of the mid-end storage node with the latest acquired parameter data.

7. A robot operation method for dismantling and assembling a mother pipe drainage line in a high-voltage substation according to claim 6, characterized in that: The parameter data include: the length, diameter, curvature, position coordinates, distance from surrounding objects, and current and voltage of the mother tube drainage line; The positioning model includes: Construct three-dimensional space modeling. The three-dimensional space modeling takes the mother tube drainage line as the benchmark, establishes a three-dimensional coordinate system, converts the parameter data of the mother tube drainage line into coordinate points and vectors in the three-dimensional space, and constructs a three-dimensional space model of the mother tube drainage line based on the coordinate points and vectors. In addition, the three-dimensional space modeling takes the mother tube drainage line as the center, simulates the space environment around the mother tube drainage line, and divides the simulation space into different operation areas based on the position coordinates in the parameter data and the distance to the surrounding objects. Each operation area corresponds to the possible operation position and operation path of the disassembly and assembly robot; The working position and working path of the dismantling robot in each working area are obtained and combined with the length of the mother pipe drainage line, the working time of the dismantling robot in each working area is calculated, the working time, working position and working path are summarized, and integrated into an operation plan for the dismantling robot.

8. A robot operation method for dismantling and installing a mother pipe drainage line in a high-voltage substation according to claim 6, characterized in that: The detection model includes: Construct an environmental perception system. The environmental perception system is constructed based on a cross-combination of several different sensor units. It is used to collect real-time environmental data of the operating area, obtain parameter data features, mark sensor units based on feature types, build a fusion algorithm, assign high weights to the marked sensor units, assign equal weights to the remaining sensor units in different sensor units, and fuse the data of the marked sensor units with the data of the remaining sensor units to obtain environmental data; The operating formula of the fusion algorithm is: where d m represents the environmental data value collected by the sensor unit m marked as high-weight, α represents the weight coefficient assigned to the high-weight sensor unit m, represents the sum of the environmental data values ​​collected by all other sensor units, i.e. n-1, except the high-weight sensor unit m. is a normalization factor used to distribute the sum of data from other sensor units to each sensor unit.

9. A robot operation method for dismantling and assembling a mother pipe drainage line in a high-voltage substation according to claim 1, characterized in that: The instruction control model includes: Obtain the characteristics of the discrimination results, including the operation risk level, operation safety area, and operation priority, and build an instruction generation system. The instruction generation system dynamically generates control instructions based on the characteristics of the discrimination results, combined with the operation plan and operation capability of the disassembly and assembly robot, and based on the adaptive control strategy of machine learning; The operation plan includes: operation area selection, operation tool selection, operation path planning and operation time allocation.

10. A robot operation method for dismantling and assembling a mother pipe drainage line in a high-voltage substation according to claim 1, characterized in that: The monitoring feedback model includes: Acquire the real-time operation data of the disassembly and assembly robot, extract the features in the real-time operation data, and build an operation status database based on the features in the operation data. The operation status database is used to update the operation data of the disassembly and assembly robot in real time. Associating the operation status database with the time axis, intercepting multiple groups of operation data parameters in adjacent time periods, analyzing the variation range of the operation data parameters, and predicting the operation status of the disassembly and assembly robot in the future time period based on the variation range, and setting the operation status parameter value in the future time period as a preset target; Compare preset targets and real-time operating data, and generate adjustment data based on deviations.

Images