Intelligent monitoring control method and system for conveying equipment based on chain tension

Abstract

The invention discloses an intelligent monitoring control method and system for conveying equipment based on chain tension, and relates to the technical field of conveying equipment.The intelligent monitoring control method for the conveying equipment based on the chain tension comprises the following steps that chain tension characteristic data are obtained; predicting the change of the chain tension at the future moment by using the tension prediction model to obtain the change trend of the chain tension; identifying a chain tension change mode; and operating parameters of the conveying equipment are adjusted based on the recognized key factors. By monitoring the tensioning force of the chain in real time and predicting the future change trend of the tensioning force, the tensioning state of the chain can be adjusted more accurately, it is ensured that the chain runs in the optimal state all the time, excessive abrasion and damage of the chain and a chain wheel are prevented, operation parameters can be automatically adjusted according to the recognized tensioning force change mode, and the working efficiency is improved. And therefore, the performance and the safety of the conveying equipment are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of conveying equipment, and in particular to an intelligent monitoring and control method and system for conveying equipment based on chain tensioning force. Background Art

[0002] Scraper conveyor equipment plays a vital role in the fully mechanized mining face of coal mines. It is mainly responsible for the continuous and efficient transportation of crushed coal in the mine. Due to the complexity of its operating environment, scraper conveyor equipment faces many challenges, especially the management of chain tension. In actual operation, the tension of the chain is affected by many factors, such as load fluctuations, position changes of hydraulic supports, etc. These factors may cause unstable chain tension, which in turn affects the operating efficiency and safety of the equipment. When the chain is too loose, it cannot effectively engage with the sprocket, which can easily cause the chain to accumulate or kink, thereby hindering the smooth transportation of coal and may cause equipment shutdown and maintenance. If the chain is too tight, it will increase friction and power consumption, accelerate the wear of key components such as chains and sprockets, and in severe cases, it will damage the equipment structure, shorten the equipment life, and increase maintenance costs.

[0003] In the prior art, it is not convenient to monitor the tension of the chain in real time and predict its future change trend, and it is not possible to accurately adjust the tension state of the chain, and it is not possible to ensure that it always runs in the best state. Not only does it increase the energy waste caused by the chain being too loose or too tight, but it also reduces the conveying efficiency, and it is not convenient to intelligently adjust the equipment failures and accidents caused by chain problems, especially in high-risk environments such as coal mines, which reduces work safety. At the same time, it is not convenient to identify the key factors that affect the tension of the chain, and it is not convenient for equipment managers to obtain detailed data and analysis reports on the tension of the chain, and managers cannot adopt corresponding adjustment measures in time, which reduces the performance and safety of the conveying equipment.

[0004] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0005] In view of the deficiencies of the prior art, the present invention proposes an intelligent monitoring and control method and system for conveying equipment based on chain tension, which solves the problems mentioned in the above background technology that it is inconvenient to monitor the tension of the chain in real time and predict its future change trend, the tension state of the chain cannot be accurately adjusted, and it cannot be guaranteed to always operate in the best state. It not only increases the energy waste caused by the chain being too loose or too tight, but also reduces the conveying efficiency, and is not convenient for intelligent adjustment of equipment failures and accidents caused by chain problems, especially in high-risk environments such as coal mines, which reduces work safety. At the same time, it is not convenient to identify the key factors affecting the tension of the chain, and thus it is not convenient for equipment managers to obtain detailed data and analysis reports on the tension of the chain, and managers cannot adopt corresponding adjustment measures in time, which reduces the performance and safety of the conveying equipment.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: According to one aspect of the present invention, a method for intelligent monitoring and control of a conveying equipment based on chain tension is provided, and the method for intelligent monitoring and control of a conveying equipment based on chain tension comprises the following steps: S1. Acquire real-time chain tension force data of the conveying equipment, and pre-process the real-time chain tension force data to obtain chain tension force characteristic data; S2. Based on the obtained chain tension force characteristic data, a tension force prediction model is established, and the chain tension force change at a future moment is predicted using the tension force prediction model to obtain a chain tension force change trend; S3, using the recognition analysis algorithm to analyze the obtained chain tension force change trend and identify the chain tension force change mode; S4. Use the efficiency evaluation algorithm to evaluate the identified chain tension change pattern to obtain the key factors affecting the efficiency and safety of the conveying equipment, and adjust the operating parameters of the conveying equipment based on the identified key factors.

[0007] Furthermore, obtaining the real-time chain tension force data of the conveying equipment and preprocessing the real-time chain tension force data to obtain the chain tension force characteristic data includes the following steps: S11. Deploy data collection nodes and use communication protocols to obtain real-time chain tension data of conveying equipment; S12, obtaining the original real-time chain tension force data transmitted from the data acquisition node, converting the original real-time chain tension force data from the time domain to the frequency domain using a wavelet transform method, and screening out wave field records of each frequency band affected by environmental interference; S13, in the converted frequency domain data, identifying and tracking the environmental interference waves in each frequency band, and obtaining the interference wave direction at the calculation sample point; S14, selecting a number of windows centered on the calculation sample point to perform median filtering, and restoring the environmental interference signal at the calculation sample point; S15, recovering the interference signals in the wave field records of each frequency band one by one, and converting the interference wave field back to the time domain by using inverse wavelet transform to obtain the entire wave field information of the interference wave; S16, removing the identified interference wave field from the original real-time chain tension force data to obtain a denoised effective signal wave field, and generating denoised chain tension force characteristic data based on the denoised effective signal wave field.

[0008] Furthermore, based on the obtained chain tension force characteristic data, a tension force prediction model is established, and the chain tension force change at a future moment is predicted using the tension force prediction model. Obtaining the chain tension force change trend includes the following steps: S21. Collect data related to chain tension in a historical period; S22, dividing the obtained chain tension force characteristic data and historical data into a training set and a test set; S23, constructing a tension prediction model, inputting the obtained chain tension characteristic data into the tension prediction model, and obtaining the chain tension change trend at a future moment.

[0009] Furthermore, constructing a tension prediction model, inputting the obtained chain tension characteristic data into the tension prediction model, and obtaining the chain tension change trend at a future moment includes the following steps: S231, selecting a matching tension force prediction model, and determining the quantity of chain tension force feature data at the input level, hidden level, and output level of the tension force prediction model respectively; S232, calculating the input tension feature data of the hidden level according to the input tension feature data of the input level and in combination with the weight and bias of the tension prediction model; S233, calculating the input tension feature data of the output stage according to the output tension feature data of the hidden stage and in combination with the weight and bias of the tension prediction model; S234, importing the input tension force characteristic data of the output stage into the activation function for solving, obtaining the output tension force characteristic data of the output stage, and using the output tension force characteristic data of the output stage as the predicted value of the chain tension force change trend at a future moment; S235. Calculate the error between the predicted value of the chain tension force change trend at the future moment and the actual observed value through the propagation algorithm, and adjust the parameters of the tension force prediction model through the optimization algorithm.

[0010] Furthermore, the formula for calculating the hidden level input tension feature data is: ; in, represents input tension feature data of the hidden level; Represented as the weight of the input level; The input tension characteristic data represented as the input level; It is represented as the bias of the input stage; g The number of tension force characteristic data represented as input level; x The number of tension feature data represented as hidden level; c and b Respectively represent the input level c Tension feature data and hidden level b Tension characteristic data.

[0011] Furthermore, the formula for calculating the input tension characteristic data of the output stage is: ; in, Expressed as input tension force characteristic data of the output stage; denoted as the weight of the hidden level; The output tension feature data represented as hidden level; Represented as the bias of the hidden level; n The quantity represented as the characteristic data of the tension force of the output stage; x The number of tension feature data represented as hidden level; z and b Respectively represent the output stage z Tension feature data and hidden level b Tension characteristic data.

[0012] Further, the obtained chain tension force variation trend is analyzed using a recognition analysis algorithm, and identifying the chain tension force variation pattern includes the following steps: S31. Identify factors that affect the change of the chain tension force from the obtained change trend of the chain tension force; S32, determining the efficiency measurement method for chain tension force change analysis, and setting efficiency thresholds and adjustment techniques; S33, if the identified factors affecting the chain tension change cause the efficiency of the chain tension change analysis to be lower than a threshold, then improving the factors affecting the chain tension change by using a set improvement technique; S34, establishing an optimization model for analyzing chain tension force variation factors, and determining objective functions and constraints; S35. Apply the identification analysis algorithm to the optimization model to find the best solution that meets the constraints and use it as the chain tension force variation pattern.

[0013] Furthermore, the identification analysis algorithm is applied to the optimization model to find the best solution that meets the constraints, and the chain tension force variation mode includes the following steps: S351, processing the identified factors affecting the change of chain tension force to meet the preset conditions; S352, setting parameters of the identification and analysis algorithm, and initializing the improvement technology of factors affecting chain tension change; S353, using the established objective function, evaluating the impact of each improved technology on the efficiency of chain tension force change analysis, and updating the status of the improved technology according to the evaluation results; S354. Optimize, evaluate and adjust the improvement technology of factors affecting chain tension change according to preset conditions, and update the status of the improvement technology; S355. If the preset number of iterations is reached or the analysis efficiency reaches the preset threshold, the current improved technology is confirmed as the global optimal solution, which serves as the main basis for judging the chain tension change pattern. Otherwise, the improved technology of factors affecting the chain tension change is continuously optimized.

[0014] Further, the identified chain tension force variation pattern is evaluated using an efficiency evaluation algorithm to obtain key factors affecting the efficiency and safety of the conveying equipment, and the operating parameters of the conveying equipment are adjusted based on the identified key factors, including the following steps: S41, randomly initializing the value of the factor affecting the change of the chain tension force in the defined search space, and setting the parameters of the efficiency evaluation algorithm; S42, randomly assigning an initial value to each factor that affects the change of chain tension, and finding the current optimal solution according to the fitness value; S43, adjusting the value of each factor affecting the change of the chain tension force according to a preset update formula, and simulating the change frequency, change amount and set value change of each factor affecting the change of the chain tension force in actual operation; S44, generating a random number. If the random number is greater than the set frequency of change, performing random perturbations on the current optimal factor to generate a new factor solution; S45, generating other random numbers. If the other random numbers are smaller than the current frequency of change, the new factor solution generated in step S44 is accepted; S46, evaluating and ranking the fitness values ​​of all adjusted factors to determine the current optimal solution and optimal value; S47, repeating steps S42 to S45 until a preset maximum number of iterations is reached or other stop conditions are met; S48. Output the global optimal solution and optimal value as the key factors affecting the efficiency and safety of the conveying equipment, and adjust the operating parameters of the conveying equipment according to the key factors.

[0015] According to another aspect of the present invention, there is also provided an intelligent monitoring and control system for conveying equipment based on chain tension, the intelligent monitoring and control system for conveying equipment based on chain tension comprises: A data acquisition module is used to acquire real-time chain tension force data of the conveying equipment and pre-process the real-time chain tension force data to obtain chain tension force characteristic data; A model building module is used to build a tension prediction model based on the obtained chain tension characteristic data, and use the tension prediction model to predict the chain tension change at a future moment to obtain the chain tension change trend; An identification and analysis module is used to analyze the obtained chain tension force change trend by using an identification and analysis algorithm to identify the chain tension force change mode; An efficiency evaluation module is used to evaluate the identified chain tension force change pattern using an efficiency evaluation algorithm to obtain key factors affecting the efficiency and safety of the conveying equipment, and adjust the operating parameters of the conveying equipment based on the identified key factors; The data acquisition module is connected with the recognition and analysis module through the model building module, and the recognition and analysis module is connected with the efficiency evaluation module.

[0016] The beneficial effects of the present invention are: 1. The present invention can more accurately adjust the tension state of the chain by real-time monitoring of the tension of the chain and predicting its future change trend, ensuring that it always operates in the best state, not only reducing the energy waste caused by the chain being too loose or too tight, but also optimizing the conveying efficiency. Proper adjustment of the tension can reduce the wear of the chain and related components, and prevent excessive wear and damage of the chain and sprocket. This helps to reduce maintenance costs and extend the service life of the equipment, and reduce production stagnation caused by equipment failure. By analyzing the change trend of the chain tension, it is possible to accurately understand and predict future tension changes. According to the identified tension change pattern, the operating parameters, such as the tension of the chain, can be automatically adjusted to adapt to the current working conditions, thereby improving the performance and safety of the conveying equipment.

[0017] 2. The tension prediction model constructed by the present invention through the analysis of historical data and the input of characteristic data can accurately predict the chain tension change trend at future moments, making the equipment operation more reliable and reducing failures and downtime caused by prediction errors. By identifying potential failures and maintenance needs in advance, the prediction model helps to achieve preventive maintenance, thereby avoiding the occurrence of sudden failures, which not only reduces the cost of emergency repairs, but also extends the overall life of the equipment. Through precise tension control and timely prediction and adjustment, the system can effectively avoid safety accidents caused by improper chain tensioning, such as chain breakage or equipment overload, thereby ensuring the safety of operators and equipment.

[0018] 3. The present invention identifies and optimizes the key factors that affect the tension force. This method can improve the system's analysis accuracy of changes in the chain tension state, thereby responding and adjusting more quickly and ensuring that the equipment operates in the best state. The optimization model and objective function are used to automatically find the best solution, which reduces human intervention, improves the level of automation and intelligence in decision-making, and makes operation and maintenance management more efficient and scientific. The improved technology of continuously adjusting and optimizing the influencing factors through an iterative process can continuously improve equipment performance and operating efficiency, ensure long-term stable operation, and avoid safety problems caused by improper tension by effectively controlling and optimizing the tension force.

[0019] 4. The present invention ensures that the conveying equipment operates in the best condition, reduces energy consumption and improves material conveying efficiency by continuously optimizing and adjusting key influencing factors. It reduces equipment failure rate and prevents accidents caused by equipment failure by identifying and adjusting key factors that may affect equipment safety, ensures the safety of the production environment, and uses efficiency evaluation algorithms to simulate and test factors under different operating conditions, so that the equipment can quickly adapt to changes in production conditions and respond to different production needs more flexibly. By analyzing and arranging the pros and cons of influencing factors, equipment maintenance and update plans can be made more scientifically, thereby reducing unplanned maintenance costs and downtime. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] 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 will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 is a flow chart of a method for intelligent monitoring and controlling a conveying equipment based on chain tensioning force according to an embodiment of the present invention; Figure 2The invention is a block diagram of a chain tensioning force-based intelligent monitoring and control system for conveying equipment according to an embodiment of the invention.

[0022] In the figure: 1. Data acquisition module; 2. Model building module; 3. Identification and analysis module; 4. Efficiency evaluation module. DETAILED DESCRIPTION

[0023] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0024] In the description of the present invention, unless otherwise specified, "plurality" means two or more. In addition, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0025] According to an embodiment of the present invention, a method and system for intelligent monitoring and control of conveying equipment based on chain tensioning force are provided.

[0026] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to an intelligent monitoring and control method for conveying equipment based on chain tensioning force of an embodiment of the present invention, the intelligent monitoring and control method for conveying equipment based on chain tensioning force comprises the following steps: S1. Acquire real-time chain tension force data of the conveying equipment, and pre-process the real-time chain tension force data to obtain chain tension force characteristic data; It should be explained that real-time chain tension force data is obtained by installing a sensor on a scraper conveyor or other related conveying equipment.

[0027] Specifically, the sensors include: Tension Sensors: These sensors are specifically designed to measure tension in a chain or wire rope etc. They are usually mounted near the fixing point of the chain or the fastening device to measure the pulling force transmitted to the sensor.

[0028] Load Cell: Load Cells are commonly used devices for measuring force, and they determine chain tension by sensing pressure, tension or torque. They can be installed at the anchor point of the chain, the supporting structure, etc.

[0029] Torque Sensor: In some conveying equipment, torque sensors are used to measure the torque on the motor or drive shaft to infer the tension of the chain. These sensors are often used in more complex systems to monitor the condition of the entire drive system.

[0030] Accelerometer: used to monitor the vibration and turbulence of the chain to infer the tension of the chain. Accelerometer can help identify abnormal vibration or shock caused by improper tension.

[0031] Displacement sensors: These sensors measure the stretch and expansion of the chain, indirectly reflecting the tension of the chain. Displacement sensors are usually installed on the chain adjustment device or tensioner.

[0032] Pressure sensor: When chain tension is related to the hydraulic system, the pressure sensor can measure the pressure changes in the hydraulic system and infer the chain tension.

[0033] Magnetic sensors: Used to monitor chain position or motion to infer tension. These sensors are often used to detect chain skipping or irregular movement.

[0034] Specifically, the chain tension data includes: Tension value: This is the actual tension on the chain at a specific point in time, usually measured in Newtons (N). This is the most direct tension parameter and is critical for monitoring and adjusting chain tension.

[0035] Chain location information: This refers to the specific location of the chain in the conveyor system, which helps to identify the distribution of tension along the length of the chain. Position information can help determine if there are areas of over-tension or slack.

[0036] Movement speed: The speed of the chain during operation, which affects the stability and change of tension. Speed ​​data helps analyze the performance of chain tension at different operating speeds.

[0037] Timestamp: Recording the specific time point of data collection is very important for tracking the changing trends and periodic fluctuations of chain tension.

[0038] Temperature Data: The temperature of the chain and surrounding environment may also affect the tension readings, as temperature changes affect the physical properties of the material, such as elasticity and expansion.

[0039] S2. Based on the obtained chain tension force characteristic data, a tension force prediction model is established, and the chain tension force change at a future moment is predicted using the tension force prediction model to obtain a chain tension force change trend; It should be explained that the chain tension change trend refers to the change pattern or law of the chain tension over time.

[0040] Specifically, the chain tension change trends include: Increasing or decreasing trend: This refers to the tendency for chain tension to continue to increase or decrease over time. For example, as the chain wears or stretches, tension may gradually decrease.

[0041] Cyclic Variations: Chains may exhibit cyclical tension variations during operation, which are usually related to mechanical cyclic motion (such as cyclical load changes caused by rotating parts) or operating conditions (such as changes in production cycle).

[0042] Random fluctuations: This includes random fluctuations in tension caused by external disturbances or non-periodic changes in operating conditions. Such fluctuations may be caused by random events such as environmental factors, operating errors or equipment failures.

[0043] Stability and variability: Describes the stability and range of variation of the tension over a period of time. Analysis of stability and variability helps identify possible equipment problems or operating parameters that need to be adjusted.

[0044] S3, using the recognition analysis algorithm to analyze the obtained chain tension force change trend and identify the chain tension force change mode; It should be explained that the chain tension variation pattern refers to a specific law that describes how the chain tension changes over time or conditions.

[0045] Specifically, the strip tension change modes include: Regular Patterns: These are common, predictable trends, such as a gradual decrease in tension due to equipment aging, or periodic tension fluctuations due to cyclical load changes.

[0046] Abnormal Patterns: These patterns indicate that the change in tension is not consistent with what is expected under normal operating conditions and may be caused by equipment failure, installation error or external environmental factors. Identifying these patterns is critical for early fault detection and preventive maintenance.

[0047] Critical Modes: In these modes, the tension approaches or exceeds the design limit, which may cause safety risks to the equipment. Identifying and handling these situations is key to ensuring safe operation of the equipment.

[0048] Stable mode: In this mode, the tension remains in a relatively stable range, indicating that the equipment is operating normally with no obvious signs of wear or failure.

[0049] Trending Changes: These patterns refer to tension forces showing a gradual increase or decrease over a long period of time, usually related to long-term wear of equipment, material fatigue, or continuous load changes.

[0050] S4. Use the efficiency evaluation algorithm to evaluate the identified chain tension change pattern to obtain the key factors affecting the efficiency and safety of the conveying equipment, and adjust the operating parameters of the conveying equipment based on the identified key factors.

[0051] Specifically, the key factors include: Tension level: Whether the chain tension is appropriate, too tight or too loose may cause equipment wear or failure.

[0052] Chain Wear Condition: The age or degree of wear of the chain, which may affect its performance and lifespan.

[0053] Load changes: Changes in material load during conveying may affect the tension of the chain.

[0054] Environmental factors: Environmental factors such as temperature and humidity can affect the tension and material properties of the chain.

[0055] Equipment alignment and balance: The alignment and balance of the equipment. Poor alignment or balance will increase mechanical stress and wear.

[0056] Specifically, the adjusted operating parameters include: Tension setting: Adjust the tensioner settings based on the evaluation results to ensure the chain runs at optimal tension.

[0057] Speed ​​Control: Adjust conveying speed to optimize operating efficiency and reduce wear.

[0058] Load management: Adjust operating parameters such as start and stop speed, load distribution, etc. according to changes in material load.

[0059] Maintenance plan: adjust the maintenance and replacement cycle according to the wear and aging of the chain.

[0060] Environmental Conditioning: When environmental conditions have a significant impact, consider adjusting the environment around the equipment (such as heating or dehumidification) to maintain equipment performance.

[0061] Preferably, obtaining the real-time chain tension force data of the conveying equipment and preprocessing the real-time chain tension force data to obtain the chain tension force characteristic data comprises the following steps: S11. Deploy data collection nodes and use communication protocols to obtain real-time chain tension data of conveying equipment; S12, obtaining the original real-time chain tension force data transmitted from the data acquisition node, converting the original real-time chain tension force data from the time domain to the frequency domain using a wavelet transform method, and screening out wave field records of each frequency band affected by environmental interference; S13, in the converted frequency domain data, identifying and tracking the environmental interference waves in each frequency band, and obtaining the interference wave direction at the calculation sample point; S14, selecting a number of windows centered on the calculation sample point to perform median filtering, and restoring the environmental interference signal at the calculation sample point; S15, recovering the interference signals in the wave field records of each frequency band one by one, and converting the interference wave field back to the time domain by using inverse wavelet transform to obtain the entire wave field information of the interference wave; S16, removing the identified interference wave field from the original real-time chain tension force data to obtain a denoised effective signal wave field, and generating denoised chain tension force characteristic data based on the denoised effective signal wave field.

[0062] It is important to explain that, for example, the conveyor is used to transport coal, where the chain tension data is critical to the healthy operation of the equipment. First, we install multiple tension sensors (data acquisition nodes) on the conveyor. These sensors send data to the central monitoring system in real time via wireless communication protocols (such as ZigBee or Wi-Fi). The raw tension data collected contains interference caused by mechanical vibration and electrical noise. Using wavelet transform, a transformation method that provides both time and frequency information, the data is converted from the time domain to the frequency domain. This allows engineers to clearly see the signal strength at different frequencies and then distinguish between real signals and noise. By analyzing the data in the frequency domain, specific frequency interference caused by the movement of surrounding mechanical equipment can be identified. For example, if the vibration in a certain frequency band is found to be consistent with the operating frequency of a nearby pump, it can be marked as interference. After confirming the interference signal, a median filter can be applied on these frequency bands to reduce the impact of the interference. This filter replaces the median of each point in the signal with the median of the midpoint of its neighborhood, thereby reducing the occasional extreme values ​​or prominent interference. After the filtering process is completed, the cleaned frequency domain data is converted back to the time domain using the inverse wavelet transform. This not only restores the valid signal in the data, but also preserves the structural integrity of the denoised data. Finally, the chain tension data with interference removed can now be used for further analysis, such as establishing a tension prediction model. These denoised data provide a more accurate basis for equipment health monitoring and preventive maintenance.

[0063] Preferably, based on the obtained chain tension force characteristic data, a tension force prediction model is established, and the chain tension force change at a future moment is predicted using the tension force prediction model, and obtaining the chain tension force change trend includes the following steps: S21. Collect data related to chain tension in a historical period; S22, dividing the obtained chain tension force characteristic data and historical data into a training set and a test set; S23, constructing a tension prediction model, inputting the obtained chain tension characteristic data into the tension prediction model, and obtaining the chain tension change trend at a future moment.

[0064] Preferably, constructing a tension prediction model, inputting the obtained chain tension characteristic data into the tension prediction model, and obtaining the chain tension change trend at a future moment includes the following steps: S231, selecting a matching tension force prediction model, and respectively determining the quantity of chain tension force feature data of the input level (i.e., input layer), hidden level (i.e., hidden layer), and output level (i.e., output layer) of the tension force prediction model; S232, calculating the input tension feature data of the hidden level according to the input tension feature data of the input level and in combination with the weight and bias of the tension prediction model; S233, calculating the input tension feature data of the output stage according to the output tension feature data of the hidden stage and in combination with the weight and bias of the tension prediction model; S234, importing the input tension force characteristic data of the output stage into the activation function for solving, obtaining the output tension force characteristic data of the output stage, and using the output tension force characteristic data of the output stage as the predicted value of the chain tension force change trend at a future moment; S235. Calculate the error between the predicted value of the chain tension force change trend at the future moment and the actual observed value through the propagation algorithm, and adjust the parameters of the tension force prediction model through the optimization algorithm.

[0065] It should be explained that, for example, in the transportation of coal, chain tension data recorded in the past year are collected. These data include the size of the tension, the position of the chain, the running speed, and the ambient temperature, etc., which are recorded every 15 minutes, and the collected data are divided into 70% training set and 30% test set. The training set is used to train the tension prediction model, while the test set is used to evaluate the performance and accuracy of the tension prediction model, and an artificial neural network is used to establish the tension prediction model. The input level (i.e., input layer) receives feature data, processes it through several hidden levels (i.e., hidden layers), and finally generates a prediction of future tension in the output layer. A three-layer neural network is selected, in which the input layer has 10 neurons (corresponding to 10 types of feature data), two hidden levels (i.e., hidden layers) each have 20 neurons, and the output level (i.e., output layer) has 1 neuron (predicting the value of future tension). The feature data passes from the input level (i.e., input layer) through two hidden levels (i.e., hidden layers), where the ReLU activation function is used to increase the nonlinear processing capability, and finally the predicted tension value is obtained through the Sigmoid activation function of the output layer. During the training process, the back propagation algorithm is used to update the weights and bias parameters of the neural network. The error between the predicted value and the actual observed value (such as the mean square error MSE) is calculated, and the parameters are adjusted to minimize this error.

[0066] Preferably, the formula for calculating the input tension force characteristic data of the hidden level is: ; in, represents input tension feature data of the hidden level; Represented as the weight of the input level; The input tension characteristic data represented as the input level; It is represented as the bias of the input stage; g The number of tension force characteristic data represented as input level; x The number of tension feature data represented as hidden level; c and b Respectively represent the input level c Tension feature data and hidden level b Tension characteristic data.

[0067] Preferably, the formula for calculating the input tension force characteristic data of the output stage is: ; in, Expressed as input tension force characteristic data of the output stage; denoted as the weight of the hidden level; The output tension feature data represented as hidden level; Represented as the bias of the hidden level; n The quantity represented as the characteristic data of the tension force of the output stage; x The number of tension feature data represented as hidden level; z and b Respectively represent the output stage z Tension feature data and hidden level b Tension characteristic data.

[0068] Preferably, using an identification and analysis algorithm to analyze the obtained chain tension force variation trend, identifying the chain tension force variation pattern includes the following steps: S31. Identify factors that affect the change of the chain tension force from the obtained change trend of the chain tension force; S32, determining the efficiency measurement method for chain tension force change analysis, and setting efficiency thresholds and adjustment techniques; S33, if the identified factors affecting the chain tension change cause the efficiency of the chain tension change analysis to be lower than a threshold, then improving the factors affecting the chain tension change by using a set improvement technique; S34, establishing an optimization model for analyzing chain tension force variation factors, and determining objective functions and constraints; S35. Apply the identification analysis algorithm to the optimization model to find the best solution that meets the constraints and use it as the chain tension force variation pattern.

[0069] Specifically, the identification and analysis algorithm is the fish school algorithm, which is an optimization algorithm based on swarm intelligence. It is inspired by the foraging, clustering and following behaviors of fish schools in nature. The algorithm imitates the collective behavior of fish schools in finding food and avoiding danger.

[0070] It should be explained that, for example, in the transportation of coal, the chain tension of the coal conveyor is analyzed using historical and real-time tension data, and the recognition analysis algorithm is used to identify the main factors that affect the change of tension, such as ambient temperature and humidity, chain wear and operating speed. First, the efficiency metric is defined as the accuracy and response time of the prediction model. For example, the efficiency threshold is set to 85% accuracy and a maximum response time of 2 seconds. If the analysis is below this threshold, consider taking improvement measures, such as optimizing the recognition analysis algorithm or upgrading the hardware. The efficiency metric usually involves multiple aspects, including but not limited to performance, cost and speed. By setting specific thresholds, it can be ensured that the system operation meets the predetermined performance standards. Then, if it is found that temperature fluctuations have a greater impact on the prediction accuracy of tension, an environmental control system can be introduced to stabilize the temperature of the mine. Construct a linear programming model with the objective function of maximizing production efficiency while satisfying the following constraints: keeping the chain tension within a safe range and controlling the production cost not to exceed the budget. Use the recognition analysis algorithm to find the optimal setting parameters to keep the chain tension within the ideal range while improving overall production efficiency. The recognition analysis algorithm gradually finds the best solution that satisfies all constraints in multiple iterations.

[0071] Preferably, the identification analysis algorithm is applied to the optimization model to find the best solution that meets the constraints, and the chain tension force variation mode includes the following steps: S351, processing (whitening) the identified factors affecting the change of chain tension force to meet the preset conditions; Specifically, whitening is a signal processing technique used to eliminate redundant information in data and reduce the correlation between features. In the present invention, the purpose of whitening is to prepare the factors that affect the change of chain tension so that they meet the input requirements of the recognition analysis algorithm.

[0072] S352, setting parameters of the recognition and analysis algorithm (i.e., initializing parameters of the fish school algorithm), and initializing the improvement technology of factors affecting the change of chain tension force (i.e., the artificial fish in the fish school algorithm); S353, using the established objective function, evaluating the impact of each improved technology on the efficiency of chain tension force change analysis, and updating the status of the improved technology according to the evaluation results; S354, optimizing the improved technology of factors affecting the change of chain tension force according to preset conditions (i.e., foraging behavior in the fish school algorithm), evaluating and adjusting (i.e., clustering behavior in the fish school algorithm), and updating the status of the improved technology (i.e., tail-chasing behavior in the fish school algorithm); S355. If the preset number of iterations is reached or the analysis efficiency reaches the preset threshold, the current improved technology is confirmed as the global optimal solution, which serves as the main basis for judging the chain tension change pattern. Otherwise, the improved technology of factors affecting the chain tension change is continuously optimized.

[0073] It is necessary to explain that, for example, in the transportation of coal, the influence of important factors such as the change in the load of coal, chain wear and temperature change on the tensioning force is identified. Based on these factors, the tensioning device is adjusted to ensure constant tension under different load and environmental conditions, appropriate parameters such as learning rate and number of iterations are selected for the optimization model, and a series of predetermined improvement techniques (i.e., improvement measures) are initialized, such as adjusting the automatic tensioning device, evaluating the performance of the automatic tensioning regulator under different load conditions, using objective functions such as minimizing wear and failure rate, making real-time adjustments based on model predictive control (MPC) theory, periodically running the simulation model, testing the response of the automatic tensioning device under different environments, and adjusting the control of the conveying equipment based on feedback. After a certain period of time, if the performance of the automatic tensioning device meets the preset efficiency threshold (such as reducing maintenance costs by 10% and improving operating efficiency by 5%), the technology setting is confirmed to be optimal. If not, continue to improve through iterative optimization.

[0074] Preferably, using an efficiency evaluation algorithm to evaluate the identified chain tension force change pattern to obtain key factors affecting the efficiency and safety of the conveying equipment, and adjusting the operating parameters of the conveying equipment based on the identified key factors includes the following steps: S41, randomly initializing the value of the factor affecting the change of the chain tension force in the defined search space, and setting the parameters of the efficiency evaluation algorithm; S42, randomly assigning an initial value to each factor that affects the change of chain tension, and finding the current optimal solution according to the fitness value; S43, adjusting the value of each factor affecting the change of the chain tension force according to a preset update formula, and simulating the change frequency (i.e., the pulse frequency in the bat algorithm), the change amount (i.e., the speed in the bat algorithm), and the change of the set value (i.e., the position of the bat in the bat algorithm) of each factor affecting the change of the chain tension force (i.e., the bat in the bat algorithm) in actual operation; S44, generating a random number. If the random number is greater than the set frequency of change, performing random perturbations on the current optimal factor to generate a new factor solution; S45, generating other random numbers. If the other random numbers are smaller than the current frequency of change, the new factor solution generated in step S44 is accepted; S46, evaluating and ranking the fitness values ​​of all adjusted factors to determine the current optimal solution and optimal value; S47, repeating steps S42 to S45 until a preset maximum number of iterations is reached or other stop conditions are met; S48. Output the global optimal solution and optimal value as the key factors affecting the efficiency and safety of the conveying equipment, and adjust the operating parameters of the conveying equipment according to the key factors.

[0075] Specifically, the efficiency evaluation algorithm is the bat algorithm, which is an optimization algorithm based on swarm intelligence and is inspired by the echolocation behavior of bats. Bats emit sound waves when flying and hunting, and locate obstacles and prey by receiving the reflected sound waves. The key to the bat algorithm is that it can find the optimal solution by simulating the hunting behavior of bats in nature (using sound waves to locate and adjust flight patterns). The key components of the bat algorithm include: 1) Sound wave emission frequency: Each bat uses different frequencies, speeds, and loudness to detect targets and obstacles during the search process, which helps to dynamically adjust the search range and refine the potential solution area.

[0076] 2) Echo loudness and pulse emission rate: The initial loudness value is usually high, and as a better solution is found, the loudness decreases to reduce the search range and focus around the optimal solution.

[0077] The pulse firing rate increases as the target is approached, which helps to update the position more frequently to approach the global optimal solution.

[0078] 4) Speed ​​and position update: Bats adjust their flight speed and direction based on their frequency, and the position and velocity update formulas in the bat algorithm are used to simulate this behavior.

[0079] It should be explained that, for example, at the beginning of the optimization of transporting coal, various factors that may affect the tension of the chain, such as load weight, belt speed, ambient temperature, etc., are initialized. At the same time, the parameters of the efficiency evaluation algorithm are set, such as the goal is to maximize the transmission efficiency and minimize energy consumption. Then, after assigning initial values ​​to each factor, the simulation program is run to evaluate the effect of these values, such as simulating the reaction of the chain under different loads. Based on the results (such as reducing downtime and failure rate), it is determined which combination of factors produces the best transportation efficiency. Then, using an optimization algorithm, such as simulated annealing or genetic algorithm, the values ​​of the influencing factors are adjusted according to the fitness evaluation results, and the performance of each factor in actual operation is simulated to find a better setting. If the random number is greater than the set change frequency, the current optimal factor setting is slightly changed to explore new possibilities; if other random numbers are less than the set frequency, this new solution is retained as the current optimal solution. The updated factor values ​​are tested by simulation to test their impact on the performance of the conveying equipment, evaluate the new fitness values, and re-rank them according to these values ​​to select the best performing configuration. Finally, the optimization is stopped after reaching the preset number of iterations or the efficiency reaches the preset threshold. The optimal solution finally determined is used to adjust the operating parameters of the conveyor belt, such as changing the tension setting, optimizing the load distribution, and adjusting the belt speed to improve the overall conveying efficiency and safety.

[0080] According to another embodiment of the present invention, Figure 2 As shown, a conveying equipment intelligent monitoring and control system based on chain tensioning force is also provided, and the conveying equipment intelligent monitoring and control system based on chain tensioning force includes: The data acquisition module 1 is used to acquire the real-time chain tension force data of the conveying equipment and pre-process the real-time chain tension force data to obtain the chain tension force characteristic data; Model building module 2 is used to build a tension prediction model based on the obtained chain tension characteristic data, and use the tension prediction model to predict the chain tension change at a future moment to obtain the chain tension change trend; Identification and analysis module 3, used to analyze the obtained chain tension force change trend by using the identification and analysis algorithm, and identify the chain tension force change mode; The efficiency evaluation module 4 is used to evaluate the identified chain tension force change pattern using an efficiency evaluation algorithm to obtain key factors affecting the efficiency and safety of the conveying equipment, and adjust the operating parameters of the conveying equipment based on the identified key factors; The data acquisition module 1 is connected to the recognition and analysis module 3 via the model building module 2 , and the recognition and analysis module 3 is connected to the efficiency evaluation module 4 .

[0081] To sum up, with the help of the above-mentioned technical scheme of the present invention, the tension prediction model constructed by the present invention through the analysis of historical data and the input of characteristic data can accurately predict the chain tension change trend at future moments, making the equipment operation more reliable and reducing failures and shutdowns caused by prediction errors. By identifying potential failures and maintenance needs in advance, the prediction model helps to achieve preventive maintenance, thereby avoiding the occurrence of sudden failures, which not only reduces the cost of emergency repairs, but also extends the overall life of the equipment. Through precise tension control and timely prediction and adjustment, the system can effectively avoid safety accidents caused by improper chain tensioning, such as chain breakage or equipment overload, thereby ensuring the safety of operators and equipment. The present invention identifies and optimizes the key factors that affect the tensioning force. This method can improve the system's analysis accuracy of changes in the chain tensioning state, thereby responding and adjusting more quickly and ensuring that the equipment operates in the best state. The optimization model and objective function are used to automatically find the best solution, which reduces human intervention, improves the level of automation and intelligence in decision-making, and makes operation and maintenance management more efficient and scientific. The improved technology of continuously adjusting and optimizing the influencing factors through an iterative process can continuously improve equipment performance and operating efficiency, ensure long-term stable operation, and avoid safety problems caused by improper tensioning by effectively controlling and optimizing the tensioning force. The present invention ensures that the conveying equipment operates in the best condition, reduces energy consumption and improves material conveying efficiency by continuously optimizing and adjusting key influencing factors. It reduces equipment failure rate and prevents accidents caused by equipment failure by identifying and adjusting key factors that may affect equipment safety, ensures the safety of the production environment, and uses efficiency evaluation algorithms to simulate and test factors under different operating conditions, so that the equipment can quickly adapt to changes in production conditions and thus respond more flexibly to different production needs. By analyzing and arranging the pros and cons of influencing factors, equipment maintenance and update plans can be made more scientifically, thereby reducing unplanned maintenance costs and downtime.

[0082] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent monitoring and control method for conveying equipment based on chain tension, characterized in that: The intelligent monitoring and control method for conveying equipment based on chain tension force comprises the following steps: S1. Acquire real-time chain tension force data of the conveying equipment, and pre-process the real-time chain tension force data to obtain chain tension force characteristic data; S2. Based on the obtained chain tension force characteristic data, a tension force prediction model is established, and the chain tension force change at a future moment is predicted using the tension force prediction model to obtain a chain tension force change trend; S3, using the recognition analysis algorithm to analyze the obtained chain tension force change trend and identify the chain tension force change mode; S4. Use the efficiency evaluation algorithm to evaluate the identified chain tension change pattern to obtain the key factors affecting the efficiency and safety of the conveying equipment, and adjust the operating parameters of the conveying equipment based on the identified key factors.

2. The intelligent monitoring and control method for conveying equipment based on chain tension according to claim 1 is characterized in that: The method of obtaining the real-time chain tension force data of the conveying equipment and preprocessing the real-time chain tension force data to obtain the chain tension force characteristic data includes the following steps: S11. Deploy data collection nodes and use communication protocols to obtain real-time chain tension data of conveying equipment; S12, obtaining the original real-time chain tension force data transmitted from the data acquisition node, converting the original real-time chain tension force data from the time domain to the frequency domain using a wavelet transform method, and screening out wave field records of each frequency band affected by environmental interference; S13, in the converted frequency domain data, identifying and tracking the environmental interference waves in each frequency band, and obtaining the interference wave direction at the calculation sample point; S14, selecting a number of windows centered on the calculation sample point to perform median filtering, and restoring the environmental interference signal at the calculation sample point; S15, recovering the interference signals in the wave field records of each frequency band one by one, and converting the interference wave field back to the time domain by using inverse wavelet transform to obtain the entire wave field information of the interference wave; S16, removing the identified interference wave field from the original real-time chain tension force data to obtain a denoised effective signal wave field, and generating denoised chain tension force characteristic data based on the denoised effective signal wave field.

3. The intelligent monitoring and control method for conveying equipment based on chain tension according to claim 1 is characterized in that: The method of establishing a tension prediction model based on the obtained chain tension characteristic data, and using the tension prediction model to predict the chain tension change at a future moment, and obtaining the chain tension change trend includes the following steps: S21. Collect data related to chain tension in a historical period; S22, dividing the obtained chain tension force characteristic data and historical data into a training set and a test set; S23, constructing a tension prediction model, inputting the obtained chain tension characteristic data into the tension prediction model, and obtaining the chain tension change trend at a future moment.

4. The intelligent monitoring and control method for conveying equipment based on chain tension according to claim 3 is characterized in that: The construction of the tension prediction model, inputting the obtained chain tension characteristic data into the tension prediction model, and obtaining the chain tension change trend at a future moment comprises the following steps: S231, selecting a matching tension force prediction model, and determining the quantity of chain tension force feature data at the input level, hidden level, and output level of the tension force prediction model respectively; S232, calculating the input tension feature data of the hidden level according to the input tension feature data of the input level and in combination with the weight and bias of the tension prediction model; S233, calculating the input tension feature data of the output stage according to the output tension feature data of the hidden stage and in combination with the weight and bias of the tension prediction model; S234, importing the input tension force characteristic data of the output stage into the activation function for solving, obtaining the output tension force characteristic data of the output stage, and using the output tension force characteristic data of the output stage as the predicted value of the chain tension force change trend at a future moment; S235. Calculate the error between the predicted value of the chain tension force change trend at the future moment and the actual observed value through the propagation algorithm, and adjust the parameters of the tension force prediction model through the optimization algorithm.

5. The intelligent monitoring and control method for conveying equipment based on chain tension according to claim 4 is characterized in that: The formula for calculating the hidden level input tension force characteristic data is: ； in, represents input tension feature data of the hidden level; Represented as the weight of the input level; The input tension characteristic data represented as the input level; It is represented as the bias of the input stage; g The number of tension force characteristic data represented as input level; x The number of tension feature data represented as hidden level; c and b Respectively represent the input level c Tension feature data and hidden level b Tension characteristic data.

6. The intelligent monitoring and control method for conveying equipment based on chain tension according to claim 4 is characterized in that: The formula for calculating the input tension force characteristic data of the output stage is: ； in, Expressed as input tension force characteristic data of the output stage; denoted as the weight of the hidden level; The output tension feature data represented as hidden level; Represented as the bias of the hidden level; n The quantity represented as the characteristic data of the tension force of the output stage; x The number of tension feature data represented as hidden level; z and b Respectively represent the output stage z Tension feature data and hidden level b Tension characteristic data.

7. The intelligent monitoring and control method for conveying equipment based on chain tension according to claim 1 is characterized in that: The method of analyzing the obtained chain tension force variation trend by using the recognition analysis algorithm to identify the chain tension force variation pattern comprises the following steps: S31. Identify factors that affect the change of the chain tension force from the obtained change trend of the chain tension force; S32, determining the efficiency measurement method for chain tension force change analysis, and setting efficiency thresholds and adjustment techniques; S33, if the identified factors affecting the chain tension change cause the efficiency of the chain tension change analysis to be lower than a threshold, then improving the factors affecting the chain tension change by using a set improvement technique; S34, establishing an optimization model for analyzing chain tension force variation factors, and determining objective functions and constraints; S35. Apply the identification analysis algorithm to the optimization model to find the best solution that meets the constraints and use it as the chain tension force variation pattern.

8. The intelligent monitoring and control method for conveying equipment based on chain tension according to claim 7 is characterized in that: The method of applying the identification analysis algorithm to the optimization model to find the best solution that meets the constraint conditions and use it as the chain tension force variation mode includes the following steps: S351, processing the identified factors affecting the change of chain tension force to meet the preset conditions; S352, setting parameters of the identification and analysis algorithm, and initializing the improvement technology of factors affecting chain tension change; S353, using the established objective function, evaluating the impact of each improved technology on the efficiency of chain tension force change analysis, and updating the status of the improved technology according to the evaluation results; S354. Optimize, evaluate and adjust the improvement technology of factors affecting chain tension change according to preset conditions, and update the status of the improvement technology; S355. If the preset number of iterations is reached or the analysis efficiency reaches the preset threshold, the current improved technology is confirmed as the global optimal solution, which serves as the main basis for judging the chain tension change pattern. Otherwise, the improved technology of factors affecting the chain tension change is continuously optimized.

9. The intelligent monitoring and control method for conveying equipment based on chain tension according to claim 1 is characterized in that: The method of evaluating the identified chain tension force variation pattern using an efficiency evaluation algorithm to obtain key factors affecting the efficiency and safety of the conveying equipment, and adjusting the operating parameters of the conveying equipment based on the identified key factors includes the following steps: S41, randomly initializing the value of the factor affecting the change of the chain tension force in the defined search space, and setting the parameters of the efficiency evaluation algorithm; S42, randomly assigning an initial value to each factor that affects the change of chain tension, and finding the current optimal solution according to the fitness value; S43, adjusting the value of each factor affecting the change of the chain tension force according to a preset update formula, and simulating the change frequency, change amount and set value change of each factor affecting the change of the chain tension force in actual operation; S44, generating a random number. If the random number is greater than the set frequency of change, performing random perturbations on the current optimal factor to generate a new factor solution; S45, generating other random numbers. If the other random numbers are smaller than the current frequency of change, the new factor solution generated in step S44 is accepted; S46, evaluating and ranking the fitness values ​​of all adjusted factors to determine the current optimal solution and optimal value; S47, repeating steps S42 to S45 until a preset maximum number of iterations is reached or other stop conditions are met; S48. Output the global optimal solution and optimal value as the key factors affecting the efficiency and safety of the conveying equipment, and adjust the operating parameters of the conveying equipment according to the key factors.

10. An intelligent monitoring and control system for conveying equipment based on chain tension, used to implement the intelligent monitoring and control method for conveying equipment based on chain tension as described in any one of claims 1 to 9, characterized in that: The intelligent monitoring and control system for conveying equipment based on chain tension force includes: A data acquisition module is used to acquire real-time chain tension force data of the conveying equipment and pre-process the real-time chain tension force data to obtain chain tension force characteristic data; A model building module is used to build a tension prediction model based on the obtained chain tension characteristic data, and use the tension prediction model to predict the chain tension change at a future moment to obtain the chain tension change trend; An identification and analysis module is used to analyze the obtained chain tension force change trend by using an identification and analysis algorithm to identify the chain tension force change mode; An efficiency evaluation module is used to evaluate the identified chain tension force change pattern using an efficiency evaluation algorithm to obtain key factors affecting the efficiency and safety of the conveying equipment, and adjust the operating parameters of the conveying equipment based on the identified key factors; The data acquisition module is connected with the recognition and analysis module through the model building module, and the recognition and analysis module is connected with the efficiency evaluation module.

Images