Intelligent stretching machine control analysis system for tension stringing construction

Abstract

The invention provides an intelligent stretching machine control analysis system for tension stringing construction, and relates to the field of power transmission line stringing construction and automatic control. According to the invention, the data acquisition module is used for acquiring the multi-dimensional data of the operation of the stretching machine in real time, the data transmission module transmits the multi-dimensional data to the data terminal and the data processing module, the data processing module processes the received data, and a Markov chain model is used for carrying out depth feature analysis, so that the accuracy of the deep feature analysis is improved. According to the method, the fault risk prediction is carried out, the corresponding early warning operation is carried out according to the prediction result, an accurate braking scheme is given, the wiring construction progress is prevented from being influenced by blind braking or delayed braking, and by integrating various technologies and combining real-time data acquisition, data processing and visual fault analysis, the wiring construction progress is ensured. Comprehensive monitoring and intelligent management of the construction process of the stretching machine are achieved, the operation state of equipment can be monitored in real time, potential faults can be warned in advance, and construction efficiency and safety are improved.

Description

Technical Field

[0001] The invention relates to the field of transmission line stringing construction and automatic control, and in particular to an intelligent tensioning machine control and analysis system for tension stringing construction. Background Art

[0002] Economic development is inseparable from electric energy. Electric energy needs to be transmitted over long distances via high-voltage overhead lines from the power plant to the household. The construction of overhead lines is an important means to support long-distance power transmission. However, the actual line construction process is complex and the construction environment is harsh, and construction safety accidents often occur. The traditional intelligent monitoring system fails to accurately detect the root cause of the tensioner failure. When the tensioner operation is abnormal, the tensioner is blindly braked, or the potential problems of the tensioner are not found, resulting in serious failure of the tensioner, thereby delaying the construction period and hindering the construction progress. This patent builds a dynamic fault analysis system for the tensioner based on the dynamic fault tree analysis of the Discrete Time Markov Chain (DTMC) model, deeply analyzes the real-time dynamic data of the tensioner, accurately grasps the root cause of the tensioner failure, and provides an accurate braking plan to avoid affecting the progress of the line construction due to blind braking or delayed braking. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide an intelligent tensioning machine control and analysis system for tension wire construction, build a dynamic fault analysis system for the tensioning machine based on the dynamic fault tree analysis of the Markov chain model, deeply analyze the real-time dynamic data of the tensioning machine, and provide an accurate braking plan to avoid blind braking of the tensioning machine and greatly delay the construction progress.

[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is: an intelligent tensioning machine control and analysis system for tension wire construction, comprising: The data acquisition module is used to collect multi-dimensional data of the operation of the tensioning machine in real time, and the multi-dimensional data includes multi-sensor data and relevant data of the traction machine; wherein the multi-sensor data includes speed, tension, pulling force, temperature and pressure; the relevant data of the traction machine includes the current of the tensioning machine and the operation status data of the traction machine; A data transmission module, connected to the data acquisition module, for transmitting multi-dimensional data to the data terminal and the data processing module; A data processing module, connected to the data transmission module, for processing the received data; Fault analysis module: builds a dynamic fault analysis model of the tensioner based on the dynamic fault tree of the Markov chain model, and deeply analyzes the real-time dynamic data of the tensioner; The electromagnetic braking module is used to brake according to the braking information transmitted by the fault analysis module. The electromagnetic braking module includes a rotating device and a braking device. The electromagnetic braking module uses the braking force of the braking device to generate resistance, and restricts the rotational force of the motor in the rotating device through the resistance to achieve precise braking of the motor.

[0005] In the preferred embodiment, among the multi-sensor data, a speed sensor is used to collect the wire-laying speed of the traction machine during on-site construction, a tension sensor is used to collect the traction tension of the traction machine, a tension sensor collects the tail tension of the traction machine, a temperature sensor collects the temperature of each key component of the tensioning machine, and a pressure sensor collects the pressure state data of the tensioning machine.

[0006] In the preferred solution, the data transmission module combines cloud computing technology to track and analyze multi-dimensional data, and schedules the monitoring data processed by the data processing module and transmits it to the fault analysis module. The formula for the specific scheduling planning process is: ; In the formula, For the current The scheduling status, is the i-th virtual machine, For the i tasks, is the number of instructions executed by the CPU per second, is the memory usage in GB, The unit is the storage usage. is the monitoring data set of the traction machine, k is the scheduling strategy used, q is the number of scheduling strategies, is the number of samples under each strategy, Respectively The task set, the feature vector of the virtual machine and the allocation status of the task in the virtual machine at the scheduling state, is the model prediction value, is the actual monitoring value.

[0007] In the preferred solution, scheduling and transmitting the monitoring data includes the following steps: Obtain data transmitted by the channel and transmit it according to the preset scheduling path; Update the real-time status of the current channel and the preset target channel in real time; If it is detected that the transmitted data reaches the preset target channel, then one scheduling is completed; If the current channel is detected to be congested or the target channel is congested, the scheduling is stopped and a quantitative test is performed on the execution effect of the transmission task and the congestion of the channel; The quantitative test indicators are bit error rate and transmission data packet loss rate , the formula is: ; ; In the formula, and are the amount of transmission data sent to the channel and the amount of transmission data actually received, To receive error data in the transmitted data.

[0008] The preferred solution also includes using the data transmission rate as a test indicator of channel transmission efficiency, and the formula is: ; In the formula, and are the data transmission amount and data transmission time in the channel respectively.

[0009] In the preferred solution, the data processing module pre-processes the multi-dimensional data, specifically detecting abnormal points in the continuous data of the tractor and filtering out individual abnormal data in the multi-dimensional data, including the following steps: Step 1: Set each monitoring data set of the distraction machine as D, store m monitoring data in the set, and perform anomaly detection on any monitoring data d in the distraction machine monitoring data set based on the isolated tree detection principle. The formula is as follows: ; In the formula, n is the total number of samples, is the constant in the isolation forest, d is the depth of the data point, m is the total amount of data, and the isolated tree H represents the Euler constant of the isolated tree; Step 2: Calculate the anomaly score of the data based on the average path length of the device data in the isolated tree. The formula is as follows: ; In the formula, Represents the average value of all data path lengths in the monitoring data set; Step 3: If you calculate If the value of > the preset abnormal score threshold, it is abnormal data and the data is deleted; if not, the final decision is made, and the formula is: ; ; ; In the formula, is the radial basis kernel function parameter, Refers to the characteristic variable of the total amount of data sample 1, Refers to the characteristic variable 2 of the total amount of data samples, is the characteristic variable of the data sample i to be found, and are the characteristic variables of the data sample i and the reference data sample j, is the decision value of reference data sample j, is the decision value of the data sample to be determined, is the support vector coefficient, is the error coefficient, c is the data sample to be determined The maximum decision value is obtained when If the value of is greater than zero and less than c, the data sample is normal data, and if it is out of the range, it is abnormal data; Step 4: According to the data anomaly analysis results in step 3, filter the abnormal data in the data set and integrate the remaining normal data as the final result of preprocessing.

[0010] In the preferred solution, a series of dynamic logic gates are introduced to describe the timing rules and dynamic failure behaviors, including four typical dynamic logic gates: priority AND gate, function-related gate, sequence-related gate and spare gate, and the logic gates are transformed into a Markov chain model.

[0011] In the preferred embodiment, the fault analysis module deeply analyzes the real-time dynamic data of the tensioning machine according to the dynamic fault analysis model, and uses dynamic fault tree analysis to calculate the membership function of the fuzzy failure probability at time t when the tensioning machine is in an abnormal state, including the following steps: 1) According to the running state of the tensioner, each running data is analyzed to establish a fault tree analysis model, and then the Markov chain model is used to transform the dynamic fault tree with n states. In the transformed Markov chain model, fuzzy numbers are used to represent the transition rate between states, so that the state transition rate matrix of the model is transformed into a fuzzy state transition rate matrix. The formula is: ; In the formula, is the fuzzy state transition rate matrix, represents the failure rate of the input event; 2) According to the dynamic fault tree diagram of the tensioner, the differential equation corresponding to the Markov chain model is obtained as follows: ; In the formula, is the probability distribution over time, is the fuzzy failure rate of the input event, and It is a probability distribution over time; 3) Set initial conditions , using Laplace-Stieltjes transformation on the equations in 2), we get the following linear equations: ; In the formula, is the transformation function of the probability distribution of time with respect to s, is the s-transformation function of the probability distribution with respect to time, is the fuzzy failure rate of the input event; 4) Solve the equations in 3) to get the value of s Function, make Laplace-Stieltjes inverse transform, and solve the state of the tensioner with respect to time The probability distribution of is used to obtain the current fault status of the tensioner.

[0012] The present invention provides an intelligent tension machine control and analysis system for tension line construction, which uses a data acquisition module to collect multi-dimensional data of the tension machine operation, a data transmission module to transmit multi-dimensional data, a data processing module to process the received data, and transmits the fault analysis module to perform in-depth analysis and fault risk prediction. The root cause of the tension machine failure is accurately grasped, and an accurate braking solution is given to avoid affecting the progress of the line construction due to blind braking or delayed braking. By integrating multiple technologies and combining real-time data acquisition, data processing and fault analysis, comprehensive monitoring and intelligent management of the tension machine construction process are realized, the equipment operation status is monitored in real time, and potential faults are warned in advance, which improves construction efficiency and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The present invention will be further described below in conjunction with the accompanying drawings and embodiments: Figure 1 It is a schematic diagram of the system module of the present invention; Figure 2 It is a schematic diagram of the installation position of multiple sensors of the present invention; Figure 3 It is a logic diagram of the tensioning machine fault analysis system of the present invention; Figure 4 It is a processing flow chart of monitoring data of the present invention; Figure 5 It is a diagram of a braking device provided by the present invention; Figure 6 It is a schematic diagram of a dynamic fault analysis diagram of the stretching machine of the present invention; Figure 7 It is a schematic diagram of converting the fault tree model of the present invention into a fuzzy Markov chain model; Figure 8is a membership function diagram of the real-time fuzzy failure probability of the traction machine of the present invention; Fig. 9 is a state diagram of the cold spare part conversion Markov model of the present invention; Fig.10 It is a state diagram of the warm spare part conversion Markov model of the present invention; Fig.11 It is a state diagram of the hot spare part conversion Markov model of the present invention.

[0014] In the figure: pressure sensor 1, tension sensor 2, monitoring system 3, braking system 4, data transmission system 5, speed sensor 6, tension sensor 7, temperature sensor 8, signal receiving device 9, brake lining 10, brake disc 11, mounting screws 12, brake housing 13, brake stator 14. DETAILED DESCRIPTION

[0015] Example 1 like Figure 1-9 As shown, an intelligent tensioning machine control and analysis system for tension wire construction includes: The data acquisition module is used to collect multi-dimensional data of the operation of the tensioning machine in real time. The multi-dimensional data includes multi-sensor data and relevant data of the traction machine; wherein the multi-sensor data includes speed, tension, pulling force, temperature and pressure; the relevant data of the traction machine includes the tensioning machine current and the operating status data of the traction machine.

[0016] The data transmission module is connected to the data acquisition module and is used to transmit the multi-dimensional data to the data terminal and the data processing module.

[0017] The data processing module is connected to the data transmission module and is used to process the received data.

[0018] The fault analysis module builds a dynamic fault analysis model of the tensioning machine based on the dynamic fault tree of the Markov chain model, deeply analyzes the real-time dynamic data of the tensioning machine, accurately grasps the root cause of the tensioning machine failure, and provides an accurate braking plan to avoid affecting the progress of the line construction due to blind braking or delayed braking.

[0019] The electromagnetic braking module is used to brake according to the braking information transmitted by the fault analysis module. The electromagnetic braking module includes a rotating device and a braking device. The electromagnetic braking module uses the braking force of the braking device to generate resistance, and restricts the rotational force of the motor in the rotating device through the resistance to achieve precise braking of the motor.

[0020] like Figure 5 As shown, a braking device that can be used in an electromagnetic braking module is provided, and the braking device is composed of a signal receiver 9, a brake lining 10, a brake disc 11, a mounting screw 12, a brake housing 13 and a brake stator 14.

[0021] The automatic fault analysis system sends a braking signal which is received by a signal receiver 9. The control system of the braking device accurately controls the brake disc 11 according to the braking scheme given by the fault analysis system, that is, the control signal received by the braking device. The brake body on the brake disc 11 receives the braking force and generates resistance, and the rotational force of the motor is restricted by this resistance to achieve accurate braking of the motor.

[0022] like Figure 1 As shown, this embodiment utilizes the data acquisition module to collect multi-dimensional data of the tensioning machine operation in real time, and the data transmission module transmits the multi-dimensional data to the data terminal and the data processing module. The data processing module processes the received data and uses the Markov chain model to perform in-depth feature analysis and predict fault risks. According to the prediction results, corresponding early warning operations are performed and accurate braking plans are given to avoid affecting the progress of the line construction due to blind braking or delayed braking. By integrating multiple technologies and combining real-time data acquisition, data processing and visual fault analysis, comprehensive monitoring and intelligent management of the tensioning machine construction process are realized, the equipment operation status is monitored in real time, and potential faults are warned in advance, which greatly improves the construction efficiency and safety.

[0023] In the preferred embodiment, among the multi-sensor data, a speed sensor is used to collect the wire-laying speed of the traction machine during on-site construction, a tension sensor is used to collect the traction tension of the traction machine, a tension sensor collects the tail tension of the traction machine, a temperature sensor collects the temperature of each key component of the tensioning machine, and a pressure sensor collects the pressure state data of the tensioning machine.

[0024] Among the multi-sensor data, the speed sensor is used to measure the wire-laying speed of the traction machine during the construction process to ensure the accuracy of the construction progress; the tension sensor measures the traction tension of the traction machine to ensure that the tension is within a safe range; the tension sensor monitors the tension at the tail of the traction machine to prevent overload; the temperature sensor monitors the temperature of each key component of the tensioning machine to prevent failures caused by overheating; the pressure sensor records the pressure state of the tensioning machine to ensure the normal operation of the system.

[0025] Multiple sensors need to be set at their respective optimal detection positions to ensure the accuracy of the data obtained. In this embodiment, the actual reference setting position is given as Figure 2 As shown: the pressure sensor 1 is arranged on the hydraulic system of the tensioning machine and is responsible for determining the pressure state of the tensioning machine; the tension sensor 2 is arranged on the rear end of the tensioning machine to monitor the tail tension exerted on the traction machine when laying out the line during on-site construction; the speed sensor 6 is arranged on the tensioning machine shaft wheel to monitor the laying-out speed of the traction machine during on-site construction; the tension sensor 7 is arranged on the tensioning machine shaft wheel to monitor the traction tension of the traction machine; the temperature sensor 8 is arranged near the tensioning machine engine to monitor the engine temperature of the traction machine.

[0026] According to Figure 3 and 4 The various sensors of the tensioning machine shown in the figure collect relevant data of the line construction, and the data transmission module built by cloud computing transmits the relevant data to the data terminal over a long distance. The data terminal transmits the data to the dynamic fault analysis module to discover potential problems, provide accurate braking solutions and transmit the braking signal to the electromagnetic braking module, thereby realizing autonomous discovery and control of potential faults of the tensioning machine.

[0027] like Figure 4 As shown, the data push component communicates with the real-time fault analysis component through websocket to transmit data, analyze the current data in real time after receiving the data, perform fault analysis, store the data and feed it back to the terminal of the analysis system for display or corresponding warning.

[0028] Specific description: Taking the monitoring data of the wire construction as an example, the fault analysis module is used to analyze the real-time data of the tensioning machine, which is specifically divided into the temperature of key components of the equipment, tail tension, wire release speed, pressure state and other data, such as Figure 6 As shown, X1, X2...X8 respectively represent abnormal traction line speed, abnormal tail pulling force of the traction machine, abnormal traction tension of the traction machine, abnormal engine temperature of the tensioning machine, abnormal hydraulic pressure of the tensioning machine, oil circuit failure of the tensioning machine, and abnormal internal pressure of the tensioning machine; among them, M1 represents abnormal external construction status of the tensioning machine, and M2 represents abnormal internal system status of the tensioning machine.

[0029] like Figure 7 As shown, the fault tree model is then transformed into a fuzzy Markov chain model, including five states S1-S5.

[0030] S1: Normal working state of the tensioning machine; S2: Partial failure state caused by abnormal external construction of the tensioning machine; S3: Partial failure state caused by abnormal internal state of the tensioning machine; S4: Partial failure state caused by abnormal internal state of the tensioning machine; S5: Complete failure state.

[0031] And calculate the probability of state S5 as a function of time t, the fuzzy failure probability function, the formula is: ; Given the task time t, the upper and lower limits of the fuzzy probability of the system being in state S5 are calculated, which is the membership function of the fuzzy failure probability of the system at the time t. The fault hazard level is set to three levels: A, B, and C. When the failure probability of the tensioning machine is lower than 0.1, it is level C. At this time, the electromagnetic braking system can temporarily stop working and continue to monitor. When the failure probability of the tensioning machine is higher than 0.1 and lower than 0.5, it is level B. At this time, the electromagnetic braking system needs to act to reduce the wire release speed of the tensioning machine or take other measures to reduce the risk. When the failure probability of the tensioning machine is higher than 0.5, it is level A. At this time, the tensioning machine needs to be stopped immediately, and the construction personnel take measures to troubleshoot the fault.

[0032] like Figure 8 As shown in the figure, when the wire-releasing speed of the traction machine is abnormal, the membership function of the fuzzy failure probability of the tensioning machine at the moment t=50h is obtained by calculation.

[0033] Depend on Figure 8 It can be seen from the content that the median value of the fuzzy probability is 0.166. This indicates that when the operation reaches 50 hours, the maximum possible value of the failure probability is 0.166. When the maximum possible value of the tensioner failure probability reaches 0.166, the electromagnetic brake module needs to act to reduce the tensioner pay-off speed or take other measures to reduce the risk.

[0034] In the preferred solution, the data transmission module combines cloud computing technology to track and analyze multi-dimensional data, and schedules the monitoring data processed by the data processing module and transmits it to the fault analysis module. The formula for the specific scheduling planning process is: ; In the formula, For the current The scheduling status, is the i-th virtual machine, For the i tasks, is the number of instructions executed by the CPU per second, is the memory usage in GB, The unit is the storage usage. is the monitoring data set of the traction machine, k is the scheduling strategy used, q is the number of scheduling strategies, is the number of samples under each strategy, Respectively The task set, the feature vector of the virtual machine and the allocation status of the task in the virtual machine at the scheduling state, is the model prediction value, is the actual monitoring value.

[0035] Furthermore, it is possible to set To initialize the zero matrix, Initialize to an empty graph.

[0036] Using cloud computing technology to schedule channel transmission during data transmission can effectively reduce channel congestion and improve the efficiency of the data transmission system in receiving monitoring data. Preprocess the data transmitted by the data transmission system, detect abnormal points in the continuous data of the traction machine, filter out individual abnormal data in the entire transmission data, set the data set to be represented by D, store n equipment data in the set, select data segmentation points and cutting planes, and perform spatial cutting processing on the data set. Based on the principle of isolated tree detection, perform abnormal detection on any equipment data d in the data set, and use the decision model to make the final decision on the data with hidden dangers.

[0037] In this embodiment, data transmission effectively utilizes cloud computing resources to improve the efficiency of data processing and transmission.

[0038] Compared with traditional data transmission, data transmission based on cloud computing does not require a large amount of complex hardware infrastructure, thereby reducing energy waste and lowering costs. In addition, due to the advanced data encryption technology of cloud computing, it is more protective.

[0039] In the preferred solution, scheduling and transmitting the monitoring data includes the following steps: Obtain the data transmitted by the channel and transmit it according to the preset scheduling path.

[0040] Update the real-time status of the current channel and the preset target channel in real time.

[0041] If it is detected that the transmitted data reaches the preset target channel, then one scheduling is completed.

[0042] If the current channel is detected to be congested or the target channel is congested, the scheduling is stopped and a quantitative test is performed on the execution effect of the transmission task and the congestion of the channel.

[0043] The quantitative test indicators are bit error rate and transmission data packet loss rate , the formula is: ; ; In the formula, and are the amount of transmission data sent to the channel and the amount of transmission data actually received, To receive error data in the transmitted data.

[0044] The monitoring data is scheduled and transmitted, and its data acquisition and preliminary processing include acquiring the data transmitted by the channel and transmitting it according to the preset scheduling path, so as to transmit the data through the specified channel according to the set scheduling strategy.

[0045] Update the current channel status in real time, including monitoring and updating the real-time status of the current channel.

[0046] In the preferred solution, the data transmission rate is used as the test index of the channel transmission efficiency, and the formula is: ; In the formula, and are the data transmission amount and data transmission time in the channel respectively.

[0047] In the preferred solution, the data processing module pre-processes the multi-dimensional data, specifically detecting abnormal points in the continuous data of the tractor and filtering out individual abnormal data in the multi-dimensional data, including the following steps: Step 1: Set each monitoring data set of the distraction machine as D, store m monitoring data in the set, and perform anomaly detection on any monitoring data d in the distraction machine monitoring data set based on the isolated tree detection principle. The formula is as follows: ; In the formula, n is the total number of samples, is a constant in the isolation forest, d is the depth of the data point, m is the total amount of data, and the isolated tree H represents the Euler constant of the isolation tree.

[0048] Step 2: Calculate the anomaly score of the data based on the average path length of the device data in the isolated tree. The formula is as follows: ; In the formula, It represents the average value of all data path lengths in the monitoring data set.

[0049] Step 3: If you calculate If the value of > the preset abnormal score threshold, it is abnormal data and the data is deleted; if not, the final decision is made, and the formula is: ; ; ; In the formula, is the radial basis kernel function parameter. The value is a constant 1. Refers to the characteristic variable of the total amount of data sample 1, Refers to the characteristic variable 2 of the total amount of data samples, is the characteristic variable of the data sample i to be found, and are the characteristic variables of the data sample i and the reference data sample j, is the decision value of reference data sample j, is the decision value of the data sample to be determined, is the support vector coefficient, is the error coefficient, c is the data sample to be determined The maximum decision value is obtained when If the value of is greater than zero and less than c, the data sample is normal data; if it is out of the range, it is abnormal data.

[0050] Step 4: According to the data anomaly analysis results in step 3, filter the abnormal data in the data set and integrate the remaining normal data as the final result of preprocessing.

[0051] In the preferred solution, a series of dynamic logic gates are introduced into the fault analysis module to describe the timing rules and dynamic failure behaviors of the system. It mainly includes four typical dynamic logic gates: priority AND gate, function-related gate, sequence-related gate and spare part gate, and the Markov chain model of these logic gates is transformed to calculate the fuzzy failure rate of the tensioner, realize the dynamic fault analysis of the real-time data of the tensioner, timely discover the tensioner fault, and ensure the smooth progress of the line construction.

[0052] In the preferred embodiment, the fault analysis module deeply analyzes the real-time dynamic data of the tensioning machine according to the dynamic fault analysis model, and uses the dynamic fault tree analysis to calculate the membership function of the fuzzy failure probability at time t when the tensioning machine is in an abnormal state, including the following steps: 1) According to the running state of the tensioner, each running data is analyzed to establish a fault tree analysis model, and then the Markov chain model is used to transform the dynamic fault tree with n states. In the transformed Markov chain model, fuzzy numbers are used to represent the transition rate between states, so that the state transition rate matrix of the model is transformed into a fuzzy state transition rate matrix. The formula is: ; In the formula, is the fuzzy state transition rate matrix, Indicates the failure rate of the input event.

[0053] 2) According to the dynamic fault tree diagram of the tensioner, the differential equation corresponding to the Markov chain model is obtained as follows: ; In the formula, is the probability distribution over time, is the fuzzy failure rate of the input event, and is a probability distribution over time.

[0054] 3) Set initial conditions , using Laplace-Stieltjes transformation on the equations in 2), we get the following linear equations: ; In the formula, is the transformation function of the probability distribution of time with respect to s, is the s-transformation function of the probability distribution with respect to time, is the fuzzy failure rate of the input event.

[0055] 4) Solve the equations in 3) to get the value of s Function, make Laplace-Stieltjes inverse transform, and solve the state of the tensioner with respect to time The probability distribution of is used to obtain the current fault status of the tensioner.

[0056] The specific description of the TREE-NEURAL NETWORK (TNN) technology in this embodiment is: by introducing a series of dynamic logic gates to describe the timing rules and dynamic failure behaviors of the system. It mainly includes four typical dynamic logic gates, namely, Priority-AND Gate (PAND), Functional Dependency Gate (FDEP), Sequence Enforcing Gate (SEQ) and Spare Gate (SP). And transform these logic gates into Markov chain models. The four typical dynamic logic gates are all commonly used forms and will not be repeated here.

[0057] like Fig. 9 As shown, according to the working mechanism of the above three spare parts doors, assuming that the failure rate of the component is λ, when used as a spare part, its failure rate can be described as βλ.

[0058] Analysis shows: Fig. 9 The figure shows the state diagram of the cold spare part converted into a Markov model. When β=0, the part is a cold spare part. The state diagram consists of three state nodes (00, 10, Fail) and state transition lines. A represents the basic part, S represents the spare part. Starting from the 00 node, there is a state line pointing to the 10 node, which means that the condition is met. When the state jumps from 00 to 10, it means that component A fails; similarly, if the condition is met , the status jumps from 10 to Fail, indicating the failure of the entire system.

[0059] 1. Status definition: 00: Indicates the system status in which both basic component A and spare component S are working 10: Indicates the system status when component A fails.

[0060] Fail: Indicates system failure status.

[0061] condition Represents the failure probability of component A when it is in working condition.

[0062] condition Represents the failure probability of spare part S when it is in working condition.

[0063] 2. State transfer: 1. 00→10: It means that the two components change from the normal working state to the failure state of component A. Since the spare part S can still work, the whole system has not failed.

[0064] 2. 10→Fail: It indicates that the state of component A changes to the state of both components failing. The whole system fails.

[0065] like Fig.10 and 11 As shown in FIG. 1 , they are state diagrams of warm spare parts and hot spare parts converted into Markov models. When β=1, the component is a hot spare part; when 0<β<1, the component is a warm spare part.

[0066] It consists of four state nodes (00, 01, 10, 00) and a state transfer line.

[0067] 1. Status definition: 00: Indicates that the warm / hot spare parts and input component A are both in normal working state. In this state, the spare parts are used as standby and are not actually involved in the work, but they are ready to take over the host at any time.

[0068] 10: Input component fails, spare part works normally. At this time, the spare part changes from standby state to working state, while input component A is in failure state.

[0069] 01: Warm / hot spare part failure. After taking over the work of input component A, the spare part may fail for various reasons. At this time, the system is in a state without effective working parts.

[0070] Fail: Indicates that both spare part S and component A have failed, and the system has completely failed.

[0071] condition Represents the failure probability of component A when it is in working condition.

[0072] condition Represents the failure probability of spare part S when it is in working condition.

[0073] 2. State transfer: 1. 00→01: It means that the two components change from the normal working state to the failure state of spare part S. Since component A can still work, the whole system has not failed.

[0074] 2. 00→10: It means that the two components change from the normal working state to the failure state of component A. Since the spare part S can still work, the whole system has not failed.

[0075] 3. 10 / 01→Fail: indicates that the state of component A / spare part S changes to the state of both components failing. The entire system fails.

[0076] In Markov models, these intermediate states are often simplified into a single transition process.

[0077] This embodiment uses a deep analysis virtual model to accurately grasp the root cause of the tensioning machine failure based on the deep characteristics of the data, and provides an accurate braking plan to avoid affecting the progress of the line construction due to blind braking or delayed braking. By integrating multiple technologies and combining real-time data collection, data processing and visual fault analysis, comprehensive monitoring and intelligent management of the tensioning machine construction process are achieved.

[0078] The above embodiments are only preferred technical solutions of the present invention and should not be regarded as limiting the present invention. The protection scope of the present invention shall be the technical solutions recorded in the claims, including equivalent replacement solutions of the technical features in the technical solutions recorded in the claims. That is, equivalent replacement improvements within this scope are also within the protection scope of the present invention.

Claims

1. An intelligent tensioning machine control and analysis system for tension wire construction, characterized in that: include: The data acquisition module is used to collect multi-dimensional data of the operation of the tensioning machine in real time, and the multi-dimensional data includes multi-sensor data and relevant data of the traction machine; wherein the multi-sensor data includes speed, tension, pulling force, temperature and pressure; the relevant data of the traction machine includes the current of the tensioning machine and the operation status data of the traction machine; A data transmission module, connected to the data acquisition module, for transmitting multi-dimensional data to the data terminal and the data processing module; A data processing module, connected to the data transmission module, for processing the received data; Fault analysis module: builds a dynamic fault analysis model of the tensioner based on the dynamic fault tree of the Markov chain model, and deeply analyzes the real-time dynamic data of the tensioner; The electromagnetic braking module is used to brake according to the braking information transmitted by the fault analysis module. The electromagnetic braking module includes a rotating device and a braking device. The electromagnetic braking module uses the braking force of the braking device to generate resistance, and restricts the rotational force of the motor in the rotating device through the resistance to achieve precise braking of the motor.

2. The intelligent tensioning machine control and analysis system for tension wire construction according to claim 1 is characterized in that: Among the multi-sensor data, a speed sensor is used to collect the wire-laying speed of the traction machine during on-site construction, a tension sensor is used to collect the traction tension of the traction machine, a tension sensor collects the tail tension of the traction machine, a temperature sensor collects the temperature of each key component of the tensioning machine, and a pressure sensor collects the pressure state data of the tensioning machine.

3. The intelligent tensioning machine control and analysis system for tension wire construction according to claim 1 is characterized in that: The data transmission module combines cloud computing technology to track and analyze multi-dimensional data, and schedules the monitoring data processed by the data processing module and transmits it to the fault analysis module. The formula for the specific scheduling planning process is: ； In the formula, For the current The scheduling status, is the i-th virtual machine, For the i tasks, is the number of instructions executed by the CPU per second, is the memory usage in GB, The unit is the storage usage. is the monitoring data set of the traction machine, k is the scheduling strategy used, q is the number of scheduling strategies, is the number of samples under each strategy, Respectively The task set, the feature vector of the virtual machine and the allocation status of the task in the virtual machine at the scheduling state, is the model prediction value, is the actual monitoring value.

4. The intelligent tensioning machine control and analysis system for tension wire construction according to claim 3 is characterized in that: Scheduling and transmitting monitoring data includes the following steps: Obtain data transmitted by the channel and transmit it according to the preset scheduling path; Update the real-time status of the current channel and the preset target channel in real time; If it is detected that the transmitted data reaches the preset target channel, then one scheduling is completed; If the current channel is detected to be congested or the target channel is congested, the scheduling is stopped and a quantitative test is performed on the execution effect of the transmission task and the congestion of the channel; The quantitative test indicators are bit error rate and transmission data packet loss rate , the formula is: ； ； In the formula, and are the amount of transmission data sent to the channel and the amount of transmission data actually received, To receive error data in the transmitted data.

5. The intelligent tensioning machine control and analysis system for tension wire construction according to claim 4 is characterized in that: It also includes using the data transmission rate as a test indicator of channel transmission efficiency, and the formula is: ； In the formula, and are the data transmission amount and data transmission time in the channel respectively.

6. The intelligent tensioning machine control and analysis system for tension wire construction according to claim 1 is characterized in that: The data processing module pre-processes the multi-dimensional data, specifically detecting abnormal points in the continuous data of the tractor and filtering out individual abnormal data in the multi-dimensional data, including the following steps: Step 1: Set each monitoring data set of the distraction machine as D, store m monitoring data in the set, and perform anomaly detection on any monitoring data d in the distraction machine monitoring data set based on the isolated tree detection principle. The formula is as follows: ； In the formula, n is the total number of samples, is the constant in the isolation forest, d is the depth of the data point, m is the total amount of data, and the isolated tree H represents the Euler constant of the isolated tree; Step 2: Calculate the anomaly score of the data based on the average path length of the device data in the isolated tree. The formula is as follows: ； In the formula, Represents the average value of all data path lengths in the monitoring data set; Step 3: If you calculate If the value of > the preset abnormal score threshold, it is abnormal data and the data is deleted; if not, the final decision is made, and the formula is: ； ； ； In the formula, is the radial basis kernel function parameter, Refers to the characteristic variable of the total amount of data sample 1, Refers to the characteristic variable 2 of the total amount of data samples, is the characteristic variable of the data sample i to be found, and are the characteristic variables of the data sample i and the reference data sample j, is the decision value of reference data sample j, is the decision value of the data sample to be determined, is the support vector coefficient, is the error coefficient, c is the data sample to be determined The maximum decision value is obtained when If the value of is greater than zero and less than c, the data sample is normal data, and if it is out of the range, it is abnormal data; Step 4: According to the data anomaly analysis results in step 3, filter the abnormal data in the data set and integrate the remaining normal data as the final result of preprocessing.

7. The intelligent tensioning machine control and analysis system for tension wire construction according to claim 1 is characterized in that: A series of dynamic logic gates are introduced to describe the timing rules and dynamic failure behaviors, including four typical dynamic logic gates: priority AND gate, function-related gate, sequence-related gate and spare gate, and the logic gates are transformed into a Markov chain model.

8. The intelligent tensioning machine control and analysis system for tension wire construction according to claim 7 is characterized in that: The fault analysis module deeply analyzes the real-time dynamic data of the tensioning machine according to the dynamic fault analysis model, and uses dynamic fault tree analysis to calculate the membership function of the fuzzy failure probability at time t when the tensioning machine is in an abnormal state, including the following steps: 1) According to the running state of the tensioner, each running data is analyzed to establish a fault tree analysis model, and then the Markov chain model is used to transform the dynamic fault tree with n states. In the transformed Markov chain model, fuzzy numbers are used to represent the transition rate between states, so that the state transition rate matrix of the model is transformed into a fuzzy state transition rate matrix. The formula is: ； In the formula, is the fuzzy state transition rate matrix, represents the failure rate of the input event; 2) According to the dynamic fault tree diagram of the tensioner, the differential equation corresponding to the Markov chain model is obtained as follows: ； In the formula, is the probability distribution over time, is the fuzzy failure rate of the input event, and is a probability distribution over time; 3) Set initial conditions , using Laplace-Stieltjes transformation on the equations in 2), we get the following linear equations: ； In the formula, is the transformation function of the probability distribution of time with respect to s, is the s-transformation function of the probability distribution with respect to time, is the fuzzy failure rate of the input event; 4) Solve the equations in 3) to get the value of s Function, make Laplace-Stieltjes inverse transform, and solve the state of the tensioner with respect to time The probability distribution of is used to obtain the current fault status of the tensioner.

Images