Control system and method of intelligent winch rope pressing safety device

Abstract

The invention discloses a control system and method of an intelligent winching rope pressing safety device, and relates to the technical field of winching safety devices.The system comprises a central processing unit module, a deep learning module, a pressure sensor array module and a driving motor control module.The intelligent control system and the self-adaptive rope pressing force adjusting method are used for controlling the winching rope pressing safety device. The device can analyze the state of a rope and winching working parameters in the winching operation process in real time, automatically adjust the pressure of the rope pressing device, and ensure that the rope pressing force is always in a safe and efficient state, so that the rope slipping accident caused by too loose rope pressing and the damage to the rope caused by too tight rope pressing are effectively avoided, and the working efficiency of the winching machine is improved. The safety and reliability of winching operation are greatly improved, meanwhile, a special pressure sensor array is adopted, the rope pressing force distribution condition is sensed in an all-dimensional mode, more accurate control is achieved, and the safety risk is further reduced.

Description

Technical Field

[0001] The invention relates to the technical field of capstan safety devices, and in particular to a control system and method for an intelligent capstan rope pressure safety device. Background Art

[0002] In today's engineering construction and industrial production fields, capstans, as an important lifting and traction equipment, are widely used in electricity, communications, construction and other industries. The safe operation of capstans is crucial to the smooth progress of the project and the safety of life and property of personnel. Among them, the capstan rope pressure safety device is a key component to ensure that the rope of the capstan is stable and does not slip during operation. With the continuous advancement of science and technology, the performance requirements for capstan rope pressure safety devices are becoming higher and higher. Intelligent, efficient, safe and reliable capstan rope pressure safety devices have become an urgent need for the development of the industry.

[0003] At present, in terms of the control of the rope-pressing safety device of the capstan, most of the existing rope-pressing safety devices adopt a fixed rope-pressing force setting and a simple mechanical adjustment method, and cannot be adjusted in real time according to the actual state of the rope and the working parameters of the capstan. This leads to the danger of the rope slipping due to the rope being too loose, or the rope being damaged due to the rope being too tight, thereby reducing the service life of the rope. In addition, traditional rope-pressing safety devices usually only use a single pressure sensor to monitor the rope-pressing force. This method cannot fully and accurately perceive the distribution of the rope-pressing force, and it is difficult to achieve precise rope-pressing control. In addition, the single pressure sensor is easily affected by external environmental factors, has a slow response speed, and cannot adjust the rope-pressing force in time, resulting in inaccurate measurement results, which brings potential safety hazards to the capstan operation.

[0004] In summary, the existing capstan rope pressure safety device has obvious defects in the adaptive rope pressure force adjustment, and cannot meet the high requirements of modern engineering construction and industrial production for the safe operation of the capstan. Therefore, the development of a control system and method for an intelligent capstan rope pressure safety device, especially an innovative technology with an adaptive rope pressure force adjustment function, has important practical significance and broad application prospects. Summary of the invention

[0005] The purpose of the present invention is to make up for the shortcomings of the prior art and to provide a control system and method for an intelligent capstan rope pressure safety device. It can monitor and analyze the state of the rope and the working parameters of the capstan during the capstan operation in real time by introducing a multi-point pressure sensor array and a deep learning algorithm based on artificial intelligence. The system can automatically adjust the rope pressure force according to these data to ensure that the rope pressure force is always in a safe and efficient state. This adaptive adjustment mechanism can effectively avoid rope slippage caused by too loose rope pressure and rope damage caused by too tight rope pressure, thereby significantly improving the safety and efficiency of the operation.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: On the one hand, a control system of an intelligent capstan rope pressure safety device includes a central processing unit module, a deep learning module, a pressure sensor array module, and a drive motor control module;

[0007] The central processing unit module receives and processes data information from each module, makes accurate judgments and control instructions based on different input information, and has self-monitoring and fault diagnosis functions, can monitor its own working status in real time, and take corresponding measures in abnormal situations;

[0008] The deep learning module is composed of a data preprocessing unit, a model structure and training unit, a model updating unit and a prediction output adjustment unit. The deep learning algorithm is used to perform real-time analysis and prediction of the rope state and the working parameters of the capstan during the capstan operation. The rope state includes the rope material, diameter and wear degree, and the working parameters of the capstan include the rotation speed and tension. By training and optimizing the data, the required rope pressure force under different conditions can be accurately predicted, and the results are transmitted to the central processing unit module and adjustment instructions are provided, wherein:

[0009] Analysis of rope material: Based on the rope material characteristics and historical data, combined with formula P mat =α mat F para Predict the required rope pressure force, where P mat is the predicted value of the rope compression force for a rope of a specific material, α mat is the influence coefficient of rope material, F para is the comprehensive influencing factor of the working parameters of the capstan, and the calculation formula is F para =β r R+β t T, where β r is the speed influence factor, β t is the tension influencing factor, R is the speed parameter, and T is the tension parameter;

[0010] For ropes of different diameters: According to the diameter size and the speed and tension parameters of the capstan, the formula Accurately calculate the lower limit of the rope pressure range, through Accurately calculate the upper limit of the rope pressure range, where P dmin is the lower limit of the rope compression force range for ropes of different diameters, P dmax is the upper limit of the rope compression force range for ropes of different diameters, γ dmin is the lower limit of the influence coefficient of rope diameter, γ dmax is the upper limit of the influence coefficient of rope diameter, It is the parameter that affects the speed of the capstan, and has a specific functional relationship with the speed. It is the parameter affecting the capstan tension;

[0011] For the degree of rope wear: through comprehensive analysis of sensor data, the rope wear is judged, and the formula P is used to wear =P 0 ×(1+∈ wear ) Adjust the pressure rope strength, where P wear P is the rope pressure adjustment value after considering the rope wear degree. 0 is the rope pressure value without considering wear, ∈ wear is the influencing factor of wear degree;

[0012] The pressure sensor array module is composed of a plurality of high-precision pressure sensors. The sensors are distributed to cover different positions of the rope pressing device to fully sense the distribution of the rope pressing force. Each sensor independently measures the pressure value at the position and transmits it to the central processing unit module in real time. The central processing unit module performs comprehensive analysis and fault detection on the data.

[0013] The drive motor control module accurately controls the speed and torque of the drive motor, thereby adjusting the pressure of the rope pressing device, and cooperates with the central processing unit and the deep learning module to adjust the working state of the drive motor in real time according to the instructions of the central processing unit and the prediction results of the deep learning module.

[0014] Furthermore, the central processing unit module also includes a data storage unit and a communication unit. The data storage unit is used to store data from each module as well as intermediate data and historical data during system operation for data analysis and fault diagnosis. The communication unit communicates with external devices through the drive motor control module for remote control.

[0015] Furthermore, the data preprocessing unit in the deep learning module preprocesses the collected rope state information, namely, rope material, diameter, degree of wear, and working parameters of the capstan speed and tension. For the rope material, it is hot-coded and converted into a numerical vector representation, that is, for a specific material m, its encoding vector The mth position is 1, and the other positions are 0. For the rope diameter D, normalization is performed to obtain Where D min is the minimum rope diameter, D max is the maximum rope diameter. The rope wear degree W is expressed in numerical levels, that is, it is divided into k levels, from 0 to k-1. The capstan speed R and tension T are also normalized to obtain

[0016] Furthermore, the model structure and training unit in the deep learning module adopt a multi-layer neural network structure, including an input layer, multiple hidden layers and an output layer. The input layer receives the rope state and capstan working parameter data after the preprocessing unit, that is, The hidden layer uses a nonlinear activation function f(x) = tanh(x), and the output layer outputs the predicted rope pressure P pred ,in:

[0017] During the training process, a loss function is used to measure the difference between the predicted value and the true value. The loss function is defined as Where N is the number of samples, P pred,i is the predicted rope pressure of the i-th sample, P true,i is the true rope pressure of the i-th sample, λ is the regularization parameter, M is the total number of model weights, W j is the jth weight;

[0018] And optimize the model parameters by gradient descent method. For the weight W j The update formula is Where η is the learning rate.

[0019] Furthermore, the model updating unit and the prediction output adjustment unit in the deep learning module adjust the output predicted rope pressure force in real time, that is, introduce a wear adjustment factor ∈ wear , the adjusted predicted rope pressure is P adjusted =P pred ×(1+∈ wear ), and at the same time, combined with the changes in the working parameters of the capstan, the speed adjustment factor is introduced and tension adjustment factor The adjusted predicted rope pressure is in and are the rotation speed and tension adjustment factors respectively, and the influence factor β of the rotation speed and tension on the rope pressure is r and β t Sure.

[0020] Furthermore, the distribution of sensors in the pressure sensor array module follows a specific geometric layout. The sensors are distributed at key positions of the rope pressing device to form a three-dimensional pressure sensing network. The key positions of the sensors are determined by an optimization algorithm to make the measurement of pressure distribution more accurate and comprehensive. The optimization objective function is: Where N is the number of different rope states and capstan operating parameter combinations, M is the number of sensors, and P is the number of sensors. measured,i,j is the measured pressure value of the jth sensor under the ith combination, P true,i,jis the actual pressure value of the jth sensor under the i-th combination.

[0021] Furthermore, the drive motor control module has a variety of remote control and monitoring protection functions, among which the monitoring protection functions include overcurrent protection, overheating protection, and overload protection. The operator can monitor the working status of the drive motor and the changes in the rope pressure force in real time through the remote terminal device, and perform remote control and adjustment.

[0022] Furthermore, the remote control function in the drive motor control module is realized through network communication, and the control command sent by the remote terminal includes the target rope pressure force P target The CPU module calculates the actual rope pressure P according to the current actual rope pressure current Calculate the adjustment amount ΔP based on the target rope pressure force remote =P target -P current The adjustment command is sent to the drive motor control module, and the drive motor control module adjusts the motor speed and torque according to the adjustment amount. The adjustment formula is: N new =N current +θ×ΔP remote , T new =T current +μ×ΔP remote , where N new and T new are the adjusted motor speed and torque, N current and T current is the current motor speed and torque, θ and μ are the adjustment coefficients.

[0023] On the other hand, a control method of an intelligent capstan rope pressure safety device is provided, wherein the specific steps of the method are as follows:

[0024] Data collection: The pressure data of different positions of the rope pressing device are collected in real time and transmitted to the central processing unit module. At the same time, the deep learning module collects the rope status information and the working parameters of the capstan during the operation of the capstan.

[0025] Preliminary analysis and prediction: The deep learning module analyzes and predicts the rope status information and capstan working parameters collected, determines the initial rope pressure force prediction value, and transmits the result to the central processing unit module;

[0026] Initial rope pressing force adjustment: The central processing unit module controls the drive motor control module to adjust the pressure of the rope pressing device according to the rope pressing force prediction value provided by the deep learning module to make it close to the initial prediction value;

[0027] Real-time monitoring and dynamic adjustment: The pressure sensor array module continuously monitors the distribution of rope pressure and transmits real-time data to the central processing unit module. The deep learning module continuously receives updated rope status information and capstan working parameters, and dynamically adjusts the rope pressure according to these real-time data.

[0028] Abnormal situation handling: When the system detects abnormal situations such as sensor failure and motor failure, the central processing unit module immediately takes corresponding measures, i.e., sounds an alarm, starts the backup sensor and motor. If the rope pressure force predicted by the deep learning module for multiple consecutive times deviates greatly from the actual measured value, and multiple sensors in the pressure sensor array module show fault signs at the same time, the system is judged to have a fault, and comprehensive fault diagnosis and repair are carried out;

[0029] Remote control response: After receiving the control command sent by the remote terminal device, the central processing unit module calculates the adjustment amount according to the target rope pressing force and the current actual rope pressing force, and sends the adjustment command to the drive motor control module for adjustment.

[0030] Compared with the existing technology, this big data prediction system based on machine learning has the following beneficial effects:

[0031] 1. The present invention can analyze the state of the rope and the working parameters of the capstan in real time through an intelligent control system and an adaptive rope pressure force adjustment method during the capstan operation, automatically adjust the pressure of the rope pressure device, and ensure that the rope pressure force is always in a safe and efficient state. This effectively avoids rope slippage accidents caused by too loose rope pressure and damage to the rope caused by too tight rope pressure, greatly improving the safety and reliability of the capstan operation. At the same time, a special pressure sensor array is used to fully perceive the distribution of rope pressure force, achieve more precise control, and further reduce safety risks.

[0032] 2. The precise rope-pressing force control of the present invention can reduce excessive wear of the rope due to unreasonable pressure, extend the service life of the rope, and reduce equipment maintenance costs. The intelligent control system can quickly adapt to different working environments and changes in conditions, adjust the rope-pressing force in time, reduce work interruptions caused by untimely adjustment, and realize automatic adjustment of the rope-pressing force. At the same time, it provides remote control and monitoring functions, which is convenient for operators to manage and maintain, and can promptly detect and warn of potential faults, further improving the convenience and efficiency of operations.

[0033] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0035] Figure 1 This is a flow chart of the control system of an intelligent capstan rope pressure safety device;

[0036] Figure 2 The present invention is an operation flow chart of a control method of an intelligent capstan rope pressure safety device. DETAILED DESCRIPTION

[0037] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. 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.

[0038] Embodiment 1

[0039] This embodiment describes the application of a control system of an intelligent capstan rope pressure safety device in the construction of electric power projects. Through the intelligent control and adaptive rope pressure force adjustment functions of the system, the stability and safety of the rope of the capstan during the construction of the electric power project are effectively guaranteed, thereby improving the construction efficiency and safety.

[0040] In the specific implementation, first, the control system of the intelligent capstan rope pressure safety device is installed at the power engineering construction site to ensure that the central processing unit module, deep learning module, pressure sensor array module and drive motor control module are connected correctly, and a power-on test is performed to start the system and each module performs a self-check. The central processing unit module checks whether its own processing capabilities and internal functions are normal, the deep learning module checks the operating status of the data preprocessing unit, model structure and training unit, model update unit and prediction output adjustment unit, the pressure sensor array module detects whether each sensor is working properly, and the drive motor control module checks whether the motor's driving capability and protection function are normal.

[0041] Then, when the capstan starts to pull cables and perform other operations in the construction of power projects, the pressure sensor array module collects pressure data at different positions of the rope pressing device in real time. These sensors are distributed in key positions to form a three-dimensional pressure sensing network, which can fully sense the distribution of rope pressing force. Each sensor independently measures the pressure value at its location and transmits the data to the central processing unit module. At the same time, the deep learning module collects rope status information and working parameters of the capstan during the operation of the capstan. The rope status information includes the material of the cable (such as steel-core aluminum stranded wire), diameter (determined according to engineering design requirements), and wear degree (the initial wear degree can be preliminarily judged by appearance inspection). The working parameters of the capstan include speed (set according to the traction speed requirements) and tension (determined according to factors such as cable weight and traction resistance). The deep learning module pre-processes the collected rope status information and capstan working parameters. For the rope material, it is uniquely encoded, such as the steel-core aluminum stranded wire is encoded as the corresponding vector, and the rope diameter and capstan speed and tension are normalized.

[0042] Based on the preprocessed data, the deep learning module uses formulas to analyze and predict the rope material based on its characteristics and historical data, combined with formula P mat =α mat F para Predict the required rope pressure force, where P mat is the predicted value of the rope compression force for a rope of a specific material, α mat is the influence coefficient of rope material, F para is the comprehensive influencing factor of the working parameters of the capstan, and the calculation formula is F para =β r R+β t T, where β r is the speed influence factor, β t is the tension influencing factor, R is the speed parameter, T is the tension parameter, for ropes of different diameters, according to the diameter size, the speed and tension parameters of the capstan, the formula is Accurately calculate the lower limit of the rope pressure range, through Accurately calculate the upper limit of the rope pressure range, where P dmin is the lower limit of the rope compression force range for ropes of different diameters, P dmax is the upper limit of the rope compression force range for ropes of different diameters, γ dmin is the lower limit of the influence coefficient of rope diameter, γ dmax is the upper limit of the influence coefficient of rope diameter, It is the parameter that affects the speed of the capstan, and has a specific functional relationship with the speed. The wear degree of the rope is determined by comprehensive analysis of the sensor data and the formula P is used to calculate the wear degree of the rope.wear =P 0 ×(1+∈ wear ) Adjust the pressure rope strength, where P wear P is the rope pressure adjustment value after considering the rope wear degree. 0 is the rope pressure value without considering wear, ∈ wear The wear degree influencing factor is determined and the result is transmitted to the central processing unit module.

[0043] The CPU module controls the drive motor control module to adjust the pressure of the rope pressing device according to the predicted value of the rope pressing force provided by the deep learning module, so that it is close to the initial predicted value, and the adjustment range is ΔP = P predicted -P current , where P predicted is the rope pressure value predicted by the deep learning module, P current is the average rope pressure value measured by the current pressure sensor array module. If it exceeds the preset safe adjustment range, a step-by-step adjustment strategy is adopted, and the adjustment amount each time is Where n is the preset number of adjustments. During the capstan operation, the pressure sensor array module continuously monitors the distribution of the rope pressure and transmits real-time data to the central processing unit module. The central processing unit module conducts a comprehensive analysis of the data to obtain a pressure distribution map, and the deep learning module continuously receives updated rope status information and capstan working parameters. For example, as the cable pulling process proceeds, the cable may increase in wear due to friction with the ground or other objects, and the speed and tension of the capstan may also change due to changes in the construction progress. The deep learning module dynamically adjusts the rope pressure based on these real-time data. If it is found that the rope pressure is too loose and may cause the rope to slip, the deep learning module will issue an instruction to increase the pressure. According to this instruction, the central processing unit module controls the drive motor control module to increase the speed and torque of the drive motor to increase the pressure of the rope pressing device. At the same time, the system will monitor the changes in the rope pressing force in real time through the pressure sensor array to ensure the accuracy and stability of the adjustment. When the rope pressing force reaches the appropriate range, the system will stop increasing the pressure and enter a stable state. On the contrary, if it is found that the rope pressing force is too tight and may damage the rope, the deep learning module will issue an instruction to reduce the pressure. According to this instruction, the central processing unit module controls the drive motor control module to reduce the speed and torque of the drive motor to reduce the pressure of the rope pressing device. Similarly, the system will monitor the changes in the rope pressing force in real time through the pressure sensor array to ensure the accuracy and stability of the adjustment. When the rope pressing force reaches the appropriate range, the system will stop reducing the pressure and enter a stable state.

[0044] When the system detects a sensor failure, the fault detection function in the pressure sensor array module will be activated. If the measured value of a sensor deviates from the average value of other sensors by more than the preset threshold value Z, that is, Where P i is the measurement value of the i-th sensor, is the average of all sensor measurement values, the sensor is judged to be faulty, and the system starts the backup sensor to measure the pressure value at that position to ensure the normal operation of the system; when the system detects a motor failure, the drive motor control module will immediately stop the operation of the drive motor and issue an alarm, and the system will start the backup motor or take other emergency measures to ensure the normal operation of the winch rope pressure safety device; if the rope pressure force predicted by the deep learning module for multiple consecutive times deviates greatly from the actual measurement value, or if fault signs appear on multiple sensors in the pressure sensor array module at the same time, the system may be judged to be faulty, the central processing unit module will issue an alarm, start the fault diagnosis process, analyze the possible causes of the fault, and take corresponding repair measures.

[0045] To sum up, this embodiment demonstrates the effective application of the control system of the intelligent capstan rope pressure safety device in the construction of power projects. Through the coordinated work of various modules of the system, adaptive rope pressure force adjustment is achieved, ensuring the safety and stability of the rope during the capstan operation, and improving the efficiency and safety of power project construction. At the same time, it also reflects the system's remote control and abnormal situation handling capabilities, providing reliable protection for power project construction.

[0046] Embodiment 2

[0047] This embodiment describes in detail the application process of a control system of an intelligent capstan rope pressure safety device in mining operations. By introducing the working principles and coordination methods of each module of the system, it demonstrates how to achieve adaptive rope pressure force adjustment in a complex mining environment to ensure the safety and efficiency of capstan operations.

[0048] When the capstan in mining starts to work, for example, when it is used to lift and transport ore, the pressure sensor array module starts to collect pressure data at different positions of the rope pressing device in real time. These sensors are distributed at key positions of the rope pressing device according to a specific geometric layout, forming a three-dimensional pressure sensing network to fully perceive the distribution of the rope pressing force. Assume that a total of 20 high-precision pressure sensors (M=20) are installed on the rope pressing device of a mine capstan. Each sensor independently measures the pressure value at its location and transmits the data to the central processor module. At the same time, the deep learning module collects the rope status information and the working parameters of the capstan during the operation of the capstan. The rope status information includes the rope material (such as the steel wire rope commonly used in mines), diameter (assuming that the diameter of the steel wire rope used here is 20mm), and wear degree (the wear condition can be initially judged by appearance inspection at the beginning). The working parameters of the capstan include the rotation speed (set to 10 revolutions per minute according to the ore lifting speed requirement, that is, R=10) and the tension (determined to be 5000N according to factors such as ore weight and lifting resistance, that is, T=5000).

[0049] The deep learning module preprocesses the collected rope status information and capstan working parameters. For the rope material, it is encoded by one-hot encoding. For the rope diameter D = 20 mm, the minimum rope diameter D is known. min =10mm, maximum rope diameter D max =30mm, normalized to D=0.5, the rope wear degree is divided into 5 levels (k=5), the initial judgment is level 2 (W=2), and the minimum speed R is known for the capstan speed. min , maximum speed R max , normalized to R = 0.5, for tension T = 5000, the minimum tension T is known min =2000, maximum tension T max =8000, normalized to T=0.5. Based on the preprocessed data, the deep learning module uses the formula for analysis and prediction. For the rope material, assume that the rope material influence coefficient α of the wire rope mat =0.8, speed influence factor β r =0.3, tension influence factor β t =0.5, according to the formula F para =β r R+β i T, we can get F para =0.4, then according to the formula P mat =α mat F para , predict the required rope pressure P mat =0.32; For ropes of different diameters, assume that the lower limit of the rope diameter influence coefficient is γ dmin =0.2, upper limit value γdmax =0.4, parameters affected by the grinding speed Tension influence parameters According to the formula P dmin =0.1, according to the formula P dmax =0.2; For the degree of rope wear, it is assumed that the rope pressure value P when wear is not considered 0 =0.25, wear degree influence factor∈ wear =0.2, according to the formula P wear =P 0 ×(1+∈ wear ), we can get P wear =0.3, the deep learning module comprehensively considers the above factors, determines the initial rope pressure force prediction value, and transmits the result to the central processing unit module.

[0050] The central processing unit module controls the drive motor control module to adjust the pressure of the rope pressing device according to the predicted value of the rope pressing force provided by the deep learning module, so that it is close to the initial predicted value. During the operation of the winch, the pressure sensor array module continuously monitors the distribution of the rope pressing force and transmits real-time data to the central processing unit module. For example, as the ore is lifted and transported, the rope may increase in wear due to friction and collision with the ore, and the speed and tension of the winch may also change due to changes in the weight of the ore and the difficulty of lifting. The deep learning module dynamically adjusts the rope pressing force according to these real-time data. If it is found that the rope pressing force is too loose and may cause the rope to slip, the central processing unit module controls the drive motor control module to increase the speed and torque of the drive motor according to this instruction, so as to increase the pressure of the rope pressing device. At the same time, the system will monitor the changes in the rope pressing force in real time through the pressure sensor array to ensure the accuracy and stability of the adjustment. When the rope pressing force reaches the appropriate range, the system will stop increasing the pressure and enter a stable state; on the contrary, if it is found that the rope pressing force is too tight and may damage the rope, the deep learning module will issue an instruction to reduce the pressure. According to this instruction, the CPU module controls the drive motor control module to reduce the speed and torque of the drive motor, so as to reduce the pressure of the rope pressing device. Similarly, the system will monitor the changes in the rope pressing force in real time through the pressure sensor array to ensure the accuracy and stability of the adjustment. When the rope pressing force reaches the appropriate range, the system will stop reducing the pressure and enter a stable state.

[0051] When the system detects a sensor failure, the fault detection function in the pressure sensor array module will be activated, that is, if the measured value of a certain sensor deviates from the average value of other sensors by more than the preset threshold, the sensor is judged to be likely to be faulty. At the same time, the system starts the backup sensor or uses the interpolation algorithm to estimate the pressure value at that position to ensure the normal operation of the system; when the system detects a motor failure, the drive motor control module will immediately stop the operation of the drive motor and issue an alarm. At the same time, the system will start the backup motor or take other emergency measures to ensure the normal operation of the winch rope pressure safety device; if the rope pressure force predicted by the deep learning module for multiple consecutive times deviates greatly from the actual measured value, or if multiple sensors in the pressure sensor array module show fault signs at the same time, the system is judged to be likely to be faulty. The central processing unit module will issue an alarm and start the fault diagnosis process to analyze possible causes of the failure, such as sensor failure, motor failure, algorithm abnormality, etc., and take corresponding repair measures.

[0052] In summary, this embodiment shows in detail the application of the control system of the intelligent capstan rope pressure safety device in mining operations. Through the close cooperation of various modules of the system, real-time monitoring and analysis of rope status and capstan working parameters, as well as adaptive rope pressure force adjustment are realized. In complex and harsh mining environments, the system effectively ensures the safety and efficiency of capstan operations, and at the same time has remote control and abnormal situation processing capabilities, providing reliable technical support for mining operations.

[0053] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A control system for an intelligent capstan rope pressure safety device, characterized in that: The system includes a central processing unit module, a deep learning module, a pressure sensor array module, and a drive motor control module; The central processing unit module receives and processes data information from each module, makes accurate judgments and control instructions based on different input information, and has self-monitoring and fault diagnosis functions, can monitor its own working status in real time, and take corresponding measures in abnormal situations; The deep learning module is composed of a data preprocessing unit, a model structure and training unit, a model updating unit and a prediction output adjustment unit. The deep learning algorithm is used to perform real-time analysis and prediction of the rope state and the working parameters of the capstan during the capstan operation. The rope state includes the rope material, diameter and wear degree, and the working parameters of the capstan include the rotation speed and tension. By training and optimizing the data, the required rope pressure force under different conditions can be accurately predicted, and the results are transmitted to the central processing unit module and adjustment instructions are provided, wherein: Analysis of rope material: Based on the rope material characteristics and historical data, combined with formula P mat =α mat F para Predict the required rope pressure force, where P mat is the predicted value of the rope compression force for a rope of a specific material, α mat is the influence coefficient of rope material, F para is the comprehensive influencing factor of the working parameters of the capstan, and the calculation formula is F para =β r R+β t T, where β r is the speed influence factor, β t is the tension influencing factor, R is the speed parameter, and T is the tension parameter; For ropes of different diameters: According to the diameter size and the speed and tension parameters of the capstan, the formula Accurately calculate the lower limit of the rope pressure range, through Accurately calculate the upper limit of the rope pressure range, where P dmin is the lower limit of the rope compression force range for ropes of different diameters, P dmax is the upper limit of the rope compression force range for ropes of different diameters, γ dmin is the lower limit of the influence coefficient of rope diameter, γ dmax is the upper limit of the influence coefficient of rope diameter, It is the parameter that affects the speed of the capstan, and has a specific functional relationship with the speed. It is the parameter affecting the capstan tension; For the degree of rope wear: through comprehensive analysis of sensor data, the rope wear is judged, and the formula P is used to wear =P0×(1+∈ wear ) Adjust the pressure rope strength, where P wear is the rope pressure adjustment value after considering the rope wear degree, P0 is the rope pressure value without considering the wear, ∈ wear is the influencing factor of wear degree; The pressure sensor array module is composed of a plurality of high-precision pressure sensors. The sensors are distributed to cover different positions of the rope pressing device to fully sense the distribution of the rope pressing force. Each sensor independently measures the pressure value at the position and transmits it to the central processing unit module in real time. The central processing unit module performs comprehensive analysis and fault detection on the data. The drive motor control module accurately controls the speed and torque of the drive motor, thereby adjusting the pressure of the rope pressing device, and cooperates with the central processing unit and the deep learning module to adjust the working state of the drive motor in real time according to the instructions of the central processing unit and the prediction results of the deep learning module.

2. The control system of the intelligent capstan rope pressure safety device according to claim 1 is characterized in that: The central processing unit module also includes a data storage unit and a communication unit. The data storage unit is used to store data from various modules as well as intermediate data and historical data during system operation for data analysis and fault diagnosis. The communication unit communicates with external devices through the drive motor control module for remote control.

3. The control system of the intelligent capstan rope pressure safety device according to claim 1 is characterized in that: The data preprocessing unit in the deep learning module preprocesses the collected rope status information, namely, rope material, diameter, wear degree, and working parameters of the capstan speed and tension. For the rope material, it is hot-coded and converted into a numerical vector representation, that is, for a specific material m, its encoding vector The mth position is 1, and the other positions are 0. For the rope diameter D, normalization is performed to obtain Where D min is the minimum rope diameter, D max is the maximum rope diameter. The rope wear degree W is expressed in numerical levels, that is, it is divided into k levels, from 0 to k-1. The capstan speed R and tension T are also normalized to obtain 4. The control system of the intelligent capstan rope pressure safety device according to claim 1 is characterized in that: The model structure and training unit in the deep learning module adopt a multi-layer neural network structure, including an input layer, multiple hidden layers and an output layer. The input layer receives the rope state and capstan working parameter data after the preprocessing unit, that is, The hidden layer uses a nonlinear activation function f(x) = tanh(x), and the output layer outputs the predicted rope pressure P pred ,in: During the training process, a loss function is used to measure the difference between the predicted value and the true value. The loss function is defined as Where N is the number of samples, P pred,i is the predicted rope pressure of the i-th sample, P true,i is the true rope pressure of the i-th sample, λ is the regularization parameter, M is the total number of model weights, W j is the jth weight; And optimize the model parameters by gradient descent method. For the weight W j The update formula is Where η is the learning rate.

5. The control system of the intelligent capstan rope pressure safety device according to claim 1 is characterized in that: The model updating unit and the prediction output adjustment unit in the deep learning module adjust the output prediction rope pressure force in real time, that is, introduce the wear adjustment factor ∈ wear , the adjusted predicted rope pressure force is P adjusted =P pred ×(1+∈ wear ), and at the same time, combined with the changes in the working parameters of the capstan, the speed adjustment factor is introduced and tension adjustment factor The adjusted predicted rope pressure is in and are the rotation speed and tension adjustment factors respectively, and the influence factor β of the rotation speed and tension on the rope pressure is r and β t Sure.

6. The control system of the intelligent capstan rope pressure safety device according to claim 1 is characterized in that: The distribution of sensors in the pressure sensor array module follows a specific geometric layout. The sensors are distributed at key positions of the rope pressing device to form a three-dimensional pressure sensing network. The key positions of the sensors are determined by an optimization algorithm to make the measurement of pressure distribution more accurate and comprehensive. The optimization objective function is: Where N is the number of different rope states and capstan operating parameter combinations, M is the number of sensors, and P is the number of sensors. measured,i,j is the measured pressure value of the jth sensor under the ith combination, P true,i,j is the actual pressure value of the jth sensor under the i-th combination.

7. The control system of the intelligent capstan rope pressure safety device according to claim 1 is characterized in that: The drive motor control module has a variety of remote control and monitoring protection functions, among which the monitoring protection functions include overcurrent protection, overheating protection, and overload protection. The operator can monitor the working status of the drive motor and the changes in the rope pressure force in real time through the remote terminal device, and perform remote control and adjustment.

8. The control system of the intelligent capstan rope pressure safety device according to claim 7 is characterized in that: The remote control function in the drive motor control module is realized through network communication. The control command sent by the remote terminal includes the target rope pressure force P target The CPU module calculates the actual rope pressure P according to the current actual rope pressure current Calculate the adjustment amount ΔP based on the target rope pressure force remote =P target -P current The adjustment command is sent to the drive motor control module, and the drive motor control module adjusts the motor speed and torque according to the adjustment amount. The adjustment formula is: N new =N current +θ×ΔP remote , T new =T current +μ×ΔP remote , where N new and T new are the adjusted motor speed and torque, N current and T current is the current motor speed and torque, θ and μ are the adjustment coefficients.

9. A control method for an intelligent capstan rope pressure safety device according to any one of claims 1 to 8, characterized in that: The specific steps of this method are: Data collection: The pressure data of different positions of the rope pressing device are collected in real time and transmitted to the central processing unit module. At the same time, the deep learning module collects the rope status information and the working parameters of the capstan during the operation of the capstan. Preliminary analysis and prediction: The deep learning module analyzes and predicts the rope status information and capstan working parameters collected, determines the initial rope pressure force prediction value, and transmits the result to the central processing unit module; Initial rope pressing force adjustment: The central processing unit module controls the drive motor control module to adjust the pressure of the rope pressing device according to the rope pressing force prediction value provided by the deep learning module to make it close to the initial prediction value; Real-time monitoring and dynamic adjustment: The pressure sensor array module continuously monitors the distribution of rope pressure and transmits real-time data to the central processing unit module. The deep learning module continuously receives updated rope status information and capstan working parameters, and dynamically adjusts the rope pressure according to these real-time data. Abnormal situation handling: When the system detects abnormal situations such as sensor failure and motor failure, the central processing unit module immediately takes corresponding measures, i.e., sounds an alarm, starts the backup sensor and motor. If the rope pressure force predicted by the deep learning module for multiple consecutive times deviates greatly from the actual measured value, and multiple sensors in the pressure sensor array module show fault signs at the same time, the system is judged to have a fault, and comprehensive fault diagnosis and repair are carried out; Remote control response: After receiving the control command sent by the remote terminal device, the central processing unit module calculates the adjustment amount according to the target rope pressing force and the current actual rope pressing force, and sends the adjustment command to the drive motor control module for adjustment.

Images