Scraper chain tension dynamic optimization method based on real-time load feedback

Abstract

The invention relates to a scraper chain tension dynamic optimization method based on real-time load feedback, and belongs to the technical field of scraper chain control. The method comprises the following steps: acquiring load data of a scraper chain in various operation states; carrying out standardization processing on the load data of various operation states and then extracting features to obtain load time sequence features; carrying out time attention mechanism processing on the load time sequence characteristics and the load data of the multiple operation states to obtain importance weights; a tension value is calculated according to the load data of each operation state and the importance weight of the load data; calculating a real-time working condition coefficient of the current time node, and dynamically adjusting a preset safety tension range to obtain a real-time safety tension range of the current time node; comparing the tension value with a real-time safe tension range, and generating a control instruction according to a comparison result; and executing the control instruction. The tension control method of the scraper chain is optimized, and the control precision of the tension of the scraper chain is improved.

Description

Technical Field

[0001] This invention relates to the field of scraper conveyor chain control technology, and in particular to a method for dynamic optimization of scraper conveyor chain tension based on real-time load feedback. Background Technology

[0002] As a key piece of equipment for material conveying in industries such as coal mining and metallurgy, the stability of the scraper conveyor chain directly affects the overall operating efficiency and safety performance. Chain tension, as a core parameter reflecting the chain's operating status, often fluctuates dynamically under complex working conditions, leading to excessive tension or slackness, causing malfunctions, increasing equipment maintenance costs, and potentially causing production interruptions. Currently, static control is often used to control the tension of scraper conveyor chains. This involves setting a fixed tension value based on the scraper conveyor's design parameters and maintaining that tension through a hydraulic system. However, scraper conveyors face complex and variable operating conditions in actual operation. Controlling the chain tension solely based on a fixed value is insufficient to adapt to these changing conditions, resulting in inadequate control precision. Summary of the Invention

[0003] To address the aforementioned technical problems, this invention provides a method for dynamic optimization of scraper conveyor chain tension based on real-time load feedback. The technical solution of this invention is as follows: A method for dynamic optimization of scraper conveyor chain tension based on real-time load feedback includes: S1, acquire various operating state load data of the scraper conveyor chain, including multiple time nodes aligned to the current time node; S2, after standardizing the load data of various operating states at all time points, extract features to obtain load time series features; S3, the time series characteristics of the load and the load data of multiple operating states at each time node are processed by the time attention mechanism to obtain the importance weight of each type of load data at each time node. S4, calculate the tension value of the scraper conveyor chain at the current time node based on the load data of each operating state at all time nodes and their importance weights; S5. Calculate the real-time operating condition coefficient of the current time node based on the load data of each operating state at the current time node and its importance weight, and dynamically adjust the preset safety tension range based on the real-time operating condition coefficient of the current time node to obtain the real-time safety tension range of the current time node. S6, compare the tension value of the scraper conveyor chain at the current time node with its real-time safe tension range, and generate control commands based on the comparison results; S7 adjusts the scraper conveyor chain according to the control command so that the tension value of the scraper conveyor chain at future time nodes is always within its corresponding real-time safe tension range.

[0004] Preferably, S2 includes: S21, standardize the load data of various operating states at all time points to obtain various standard operating state load data of all time points; S22, calculate the statistical characteristics of the load data of each standard operating state at all time points, and generate the first feature of the load data of each standard operating state at each time point based on the statistical characteristics of the load data of each standard operating state. The statistical characteristics include the mean, standard deviation and extreme values. S23, convert each standard operating state load data into frequency domain operating state load data through Fourier transform, and obtain the instantaneous frequency characteristics of each frequency domain operating state load data at each time node, and use the instantaneous frequency characteristics of each time node as the second feature. S24, take each time node, the first feature and the second feature as the elements corresponding to each time node, and combine the elements corresponding to all time nodes to obtain the load time series features.

[0005] Preferably, when generating the first feature of the load data for each standard operating state at each time point based on the statistical characteristics of the load data for each standard operating state, step S22 includes: S221, Construct the matching relationship between the maximum and minimum values ​​of load data for each standard operating state and the time nodes corresponding to the maximum and minimum values; S222, construct the matching relationship between the mean and standard deviation of the load data for each standard operating state and all time points; S223, combine the extreme values ​​of each standard operating state load data and their corresponding time node matching relationships, mean and standard deviation matching relationships with all time nodes to obtain the first feature of each time node.

[0006] Preferably, S3 includes: S31, construct a load matrix based on the load data of multiple operating states at each time point, wherein each row of the matrix load represents a load data of one operating state, and each column represents the load data of multiple operating states at a time point. S32, input the load matrix and load time series features into the channel attention module, and generate query vector, key vector and value vector of load data for each time step and each running state according to the channel attention module; S33, calculate the attention score for each type of runtime state load data at each time step based on the query vector, key vector, and value vector of each type of runtime state load data at each time step; S34. Normalize the attention scores of each type of runtime load data at all time steps to obtain the attention weights of each type of runtime load data at each time step, which serve as the importance weights of each type of runtime load data at each time node.

[0007] Preferably, when S33 calculates the attention score 'a' of the operating state load data at the i-th time step based on the query vector, key vector, and value vector of any operating state load data at each time step, it is achieved through formula (1): (1); In formula (1), exp() represents the exponential function, Qi represents the query vector of the running state load data at the i-th time step, Kj represents the key vector of the running state load data at the j-th time step, Ki represents the key vector of the running state load data at the i-th time step, d represents the sum of the dimensions of the query vector and the key vector of the running state load data, and T represents the number of time steps.

[0008] Preferably, S4 includes: S41, fit the load data of each operating state at all time points and its importance weight to obtain the chain tension curve; S42, Obtain the predicted chain tension corresponding to the current time node based on the chain tension curve; S43, calculate the tension value of the scraper conveyor chain at the current time node based on the importance weight of the predicted chain tension and the various operating state load data at the current time node.

[0009] Preferably, when S43 calculates the tension value P of the scraper conveyor chain at the current time node based on the importance weights of the predicted chain tension and the various operating state load data at the current time node, it is achieved through formula (2): (2); In formula (2), max(a) represents the maximum value of the importance weight of all operating state load data at the current time node, min(a) represents the minimum value of the importance weight of all operating state load data at the current time node, and P0 represents the predicted chain tension.

[0010] Preferably, S5 includes: S51, weight all the running status load data of the current time node and their importance weights, and sum them up by adding the preset load coefficient to obtain the load value of the current time node; S52, determine the preset amplification factor corresponding to the load value at the current time node according to the load value-preset amplification factor mapping table, and multiply the load value at the current time node with the corresponding preset amplification factor to obtain the real-time operating condition factor at the current time node. S53, multiply the left and right values ​​of the preset safe tension range by the real-time operating condition coefficient of the current time node to obtain the real-time left and right values, and construct the real-time safe tension range of the current time node based on the real-time left and right values.

[0011] Preferably, S6 includes: S61, if the tension value of the scraper conveyor chain at the current time node is within its real-time safe tension range, then the tension of the scraper conveyor chain at the current time node is determined to be normal, and it is determined that there is no warning level. S62, if the tension value of the scraper conveyor chain at the current time node is not within its real-time safe tension range, and the minimum absolute value of the difference between the real-time left end value and the real-time right end value of the real-time safe tension range is less than or equal to the critical threshold, then it is determined that there is a risk in the tension of the scraper conveyor chain at the current time node, and a warning level is determined to be medium. S63, if the tension value of the scraper conveyor chain at the current time node is not within its real-time safe tension range, and the minimum absolute value of the difference between the real-time left end value and the real-time right end value of the real-time safe tension range is greater than the critical threshold, then it is determined that the tension of the scraper conveyor chain at the current time node has a significant risk, and a warning level is determined to exist and the warning level is high. S64, when a warning level is determined, a control strategy for the scraper conveyor chain is generated based on the minimum absolute value of the difference, and the control strategy is combined with the warning level to generate control commands.

[0012] All of the above-mentioned optional technical solutions can be combined arbitrarily, and the present invention will not provide a detailed description of the structure after each combination.

[0013] By means of the above solution, the beneficial effects of the present invention are as follows: By processing the load time series characteristics and load data of various operating states using a time attention mechanism, the importance weight of each type of load data at each time node is obtained. Based on this, the tension value of the scraper conveyor chain at the current time node is calculated. By utilizing the load time series characteristics and the time attention mechanism, different weights are assigned to the load data of different operating states at each time node. This allows for dynamic determination of tension based on the complex and variable working conditions of the scraper conveyor in actual operation, and enables more accurate calculation of the tension value of the scraper conveyor chain at the current time node.

[0014] By calculating the real-time operating condition coefficient at the current time node based on the load data and importance weight of each operating state, and dynamically adjusting the preset safe tension range according to the real-time operating condition coefficient, the real-time safe tension range at the current time node is obtained. The tension value is compared with the real-time safe tension range, and control commands are generated based on the comparison results. This establishes the relationship between the tension adjustment of the scraper conveyor chain and its real-time operating condition, thereby optimizing the tension control method of the scraper conveyor chain and improving the control accuracy of the scraper conveyor chain tension.

[0015] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, the preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating the dynamic optimization method for scraper conveyor chain tension based on real-time load feedback provided in an embodiment of the present invention. Detailed Implementation

[0017] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and are not intended to limit the scope of the invention.

[0018] like Figure 1 As shown, the method for dynamic optimization of scraper conveyor chain tension based on real-time load feedback provided in this embodiment of the invention includes steps S1-S7, specifically: S1, acquire various operating state load data of the scraper conveyor chain, including multiple time nodes aligned to the current time node.

[0019] In this embodiment of the invention, various types of sensors with the same acquisition frequency and time alignment, pre-configured on the scraper conveyor, collect multiple operational load data in real time. These operational load data include chain speed data, chain load data, chain strain data, and chain vibration data. The sensor types include speed sensors, load sensors, strain sensors, and vibration sensors. The multiple time nodes, including the current time node, are generally taken from within 30 minutes prior to the current moment.

[0020] S2 extracts features from the load data of various operating states at all time points after standardization processing, thus obtaining the load time series features.

[0021] Specifically, standardization is achieved by standardizing the load data for multiple operating states to their maximum and minimum values. Feature extraction in this embodiment refers to extracting the mean, standard deviation, maximum and minimum values, and instantaneous frequency features of the load data for each operating state after standardization. Then, load time series features are constructed based on these features of the load data for multiple operating states at each time point.

[0022] In one specific embodiment, S2 includes S21 to S24: S21, standardize the load data of various operating states at all time points to obtain various standard operating state load data of all time points.

[0023] Specifically, load data for various standard operating states are all standardized within [0,1].

[0024] S22, calculate the statistical characteristics of the load data of each standard operating state at all time points, and generate the first feature of the load data of each standard operating state at each time point based on the statistical characteristics of the load data of each standard operating state. The statistical characteristics include the mean, standard deviation and extreme values.

[0025] Specifically, the mean and variance are obtained by calculating the mean and variance of the load data for each standard operating state at all time points; for any standard operating state load data, its maximum and minimum values ​​are found by searching for the maximum and minimum values ​​of that standard operating state load data at all time points.

[0026] In a specific embodiment, when S22 generates the first feature of each standard operating state load data at each time point based on the statistical characteristics of each standard operating state load data, it includes: S221, construct the matching relationship between the maximum and minimum values ​​of the load data for each standard operating state and the time nodes corresponding to the maximum and minimum values.

[0027] Specifically, for any standard operating state load data, since its maximum and minimum values ​​can only exist at two time points, when constructing the matching relationship between the maximum and minimum values ​​of any standard operating state load data and the time points corresponding to the maximum and minimum values, it is to construct the relationship between the maximum and minimum values ​​of the standard operating state load data and the corresponding time points.

[0028] S222, construct the matching relationship between the mean and standard deviation of the load data for each standard operating state and all time points.

[0029] Specifically, for any standard operating state load data, after calculating the mean and standard deviation of the standard operating state load data, a matching relationship is established between the mean and standard deviation and each time node, so that the mean and standard deviation are one of the first features of the standard operating state load data at each time node.

[0030] S223, combine the extreme values ​​of each standard operating state load data and their corresponding time node matching relationships, mean and standard deviation matching relationships with all time nodes to obtain the first feature of each time node.

[0031] Specifically, the mean, variance, and extreme values ​​of each standard operating state load data at each time node are sorted and combined according to the time node to obtain the first feature of each time node. For example, the first feature of standard chain running speed data and standard chain load data at the 5th time node can be represented as [5,(0.6,0.06,0.01,0.08),(0.5,0.05,0.01,0.09)]; where 5 represents the 5th time node, and 0.6, 0.06, 0.01, and 0.08 represent the mean, variance, minimum, and maximum values ​​of the standard chain running speed data, respectively. The first feature of the standard chain load data is similar. It should be noted that if there is no extreme value for a certain standard operating state load data at a certain time node, the element corresponding to the extreme value in the first feature of that standard operating state load data at that time node is empty, and the elements after the extreme value are filled in.

[0032] S23, convert each standard operating state load data into frequency domain operating state load data through Fourier transform, and obtain the instantaneous frequency characteristics of each frequency domain operating state load data at each time node, and use the instantaneous frequency characteristics of each time node as the second feature.

[0033] Specifically, the frequency domain operating state load data X(f) is obtained by performing a Fourier transform on the load data x(y) of a certain standard operating state, and is achieved through formula (3): (3); In formula (3), f represents the preset frequency, x(y) represents the data of the y-th time node of the load data of the standard operating state, m represents the number of time nodes, and π represents pi.

[0034] Instantaneous frequency characteristics refer to the instantaneous frequency changes of load data in each frequency domain operating state at each time point, including instantaneous frequency and instantaneous phase.

[0035] S24, take each time node, the first feature and the second feature as the elements corresponding to each time node, and combine the elements corresponding to all time nodes to obtain the load time series features.

[0036] Specifically, taking the example in S223 as an example, if the instantaneous frequency is 20 and the instantaneous phase is 2π in the second feature corresponding to the standard chain running speed data, then the element corresponding to the 5th time node of the standard chain running speed data is [5,(0.6,0.06,0.01,0.08,20,2π)].

[0037] Furthermore, by sequentially combining the elements corresponding to all time nodes according to their chronological order, the load time series characteristics are obtained.

[0038] S3 processes the load time series features and the load data of various operating states at each time node using a time attention mechanism to obtain the importance weight of each type of load data at each time node.

[0039] Specifically, the attention mechanism is used to assign different importance weights to each type of operational load data at each time point, in order to improve the accuracy of subsequent tension value calculations.

[0040] In one specific embodiment, S3 includes: S31. Construct a load matrix based on the load data of multiple operating states at each time point. Each row of the matrix load represents a load data of one operating state, and each column represents the load data of multiple operating states at a time point.

[0041] Specifically, the number of rows in the load matrix represents the number of types of operational status load data, and the number of columns represents the number of time nodes.

[0042] S32, input the load matrix and load time series features into the channel attention module, and generate query vector, key vector and value vector of load data for each time step and each running state according to the channel attention module.

[0043] Specifically, the channel attention module is a module used to assign different importance weights to different types of operational state load data. In this embodiment of the invention, the channel attention module can refer to the channel mechanism in a convolutional neural network. The query vector is a vector obtained by multiplying the load matrix by the load time series features after a linear transformation, used to compare the degree of correlation between load data of each operational state at each time point; each key vector is generated by passing each element in the load time series features through the channel attention module; each value vector is generated by passing each element in each row and column of the load matrix through the channel attention module.

[0044] S33, calculate the attention score for each type of runtime state load data at each time step based on the query vector, key vector, and value vector of each type of runtime state load data at each time step.

[0045] Specifically, the attention score refers to the contribution of each value vector when calculating the importance weight of each type of runtime load data at each time point. In this embodiment of the invention, one time step corresponds to one time point.

[0046] In a specific embodiment, when S33 calculates the attention score a of the operating state load data at the i-th time step based on the query vector, key vector, and value vector of any operating state load data at each time step, it does so through formula (1): (1); In formula (1), exp() represents the exponential function, Qi represents the query vector of the running state load data at the i-th time step, Kj represents the key vector of the running state load data at the j-th time step, Ki represents the key vector of the running state load data at the i-th time step, d represents the sum of the dimensions of the query vector and the key vector of the running state load data, and T represents the number of time steps.

[0047] S34. Normalize the attention scores of each type of runtime load data at all time steps to obtain the attention weights of each type of runtime load data at each time step, which serve as the importance weights of each type of runtime load data at each time node.

[0048] Specifically, the importance weight of each type of operating state load data at each time point is not necessarily the same, and the sum of the importance weights of all operating state load data at each time point is 1.

[0049] S4, calculate the tension value of the scraper conveyor chain at the current time node based on the load data of each operating state at all time nodes and their importance weights.

[0050] Specifically, the tension value refers to the sum of the forces applied to the scraper conveyor chain.

[0051] In one specific embodiment, S4 includes: S41, fit the load data of each operating state at all time points and its importance weight to obtain the chain tension curve.

[0052] Specifically, the chain tension value at a given time point is obtained by weighted summation of all operational load data at a specific time point and their respective importance weights. Then, a linear regression is performed on the chain tension values ​​at all time points to obtain the chain tension curve. The horizontal axis of the chain tension curve represents the time point, and the vertical axis represents the chain tension value.

[0053] S42, obtain the predicted chain tension corresponding to the current time node based on the chain tension curve.

[0054] Specifically, the chain tension value corresponding to the current time node in the chain tension curve is obtained as the predicted chain tension.

[0055] S43, calculate the tension value of the scraper conveyor chain at the current time node based on the importance weight of the predicted chain tension and the various operating state load data at the current time node.

[0056] Specifically, since the chain tension curve obtains predicted data, in order to more accurately calculate the tension value of the scraper conveyor chain at the current time node, this embodiment of the invention adjusts the predicted chain tension by weighting the importance of various operating state load data at the current time node.

[0057] In a specific embodiment, when S43 calculates the tension value P of the scraper conveyor chain at the current time node based on the importance weights of the predicted chain tension and the various operating state load data at the current time node, it does so through formula (2): (2); In formula (2), max(a) represents the maximum value of the importance weight of all operating state load data at the current time node, min(a) represents the minimum value of the importance weight of all operating state load data at the current time node, and P0 represents the predicted chain tension.

[0058] Specifically, formula (2) corrects the predicted chain tension by taking the maximum and minimum values ​​of the importance weights of all running state load data at the current time node, thus obtaining a more accurate tension value of the scraper conveyor chain at the current time node.

[0059] S5 calculates the real-time operating condition coefficient of the current time node based on the load data of each operating state at the current time node and its importance weight, and dynamically adjusts the preset safety tension range based on the real-time operating condition coefficient of the current time node to obtain the real-time safety tension range of the current time node.

[0060] Specifically, the real-time operating condition coefficient refers to a coefficient dynamically calculated at a certain point in time based on the load data of each operating state and its importance weight at that point in time, representing the working state of the scraper conveyor chain at that point in time. The preset safe tension range is a safe operating range of tension values ​​obtained based on historical experience data of the scraper conveyor chain.

[0061] In one specific embodiment, S5 includes: S51, weighted summation of all operating status load data at the current time node and their importance weights, and accumulation of preset load coefficients to obtain the load value at the current time node.

[0062] Specifically, the preset load factor is a coefficient that is pre-set according to standard operating conditions, representing the load capacity of the scraper conveyor chain under specific conditions.

[0063] S52, determine the preset amplification factor corresponding to the load value at the current time node according to the load value-preset amplification factor mapping table, and multiply the load value at the current time node with the corresponding preset amplification factor to obtain the real-time operating condition factor at the current time node.

[0064] Specifically, the load value-preset amplification factor mapping table is a pre-defined table that represents the relationship between load values ​​and preset amplification factors, as shown in Table 1. The preset amplification factor is a pre-set coefficient used to adjust the preset safety tension range based on a specific load value.

[0065]

[0066] S53, multiply the left and right values ​​of the preset safe tension range by the real-time operating condition coefficient of the current time node to obtain the real-time left and right values, and construct the real-time safe tension range of the current time node based on the real-time left and right values.

[0067] Specifically, the range of values ​​between the real-time left-hand value and the real-time right-hand value constitutes the real-time safety tension range.

[0068] It should be noted that, in the embodiments of the present invention, the real-time operating condition coefficients at different time points change in real time according to the load data of each operating state at different time points and their importance weights. Therefore, the real-time operating condition coefficients corresponding to different time points are dynamically changing, which in turn makes the real-time safety tension range corresponding to different time points also dynamically changing.

[0069] S6 compares the tension value of the scraper conveyor chain at the current time node with its real-time safe tension range, and generates control commands based on the comparison results.

[0070] Specifically, the control command is generated by comparing the tension value of the scraper conveyor chain at the current time node with its real-time safe tension range, and then adjusting the parameters of the scraper conveyor chain, such as intermediate warning, increasing chain running speed, advanced warning, increasing motor load, etc.

[0071] In one specific embodiment, S6 includes: S61, if the tension value of the scraper conveyor chain at the current time node is within its real-time safe tension range, then the tension of the scraper conveyor chain at the current time node is determined to be normal, and it is determined that there is no warning level.

[0072] S62, if the tension value of the scraper conveyor chain at the current time node is not within its real-time safe tension range, and the minimum absolute value of the difference between the real-time left end value and the real-time right end value of the real-time safe tension range is less than or equal to the critical threshold, then it is determined that there is a risk in the tension of the scraper conveyor chain at the current time node, and a warning level is determined to be medium.

[0073] Specifically, the critical threshold is preset based on empirical values ​​and is used to determine whether the tension value of the scraper conveyor chain at the current time point is far from the real-time safe tension range and whether it is at a significant risk. The minimum absolute value of the difference refers to the smaller of the absolute values ​​of the differences between the tension value of the scraper conveyor chain at the current time point and the real-time left and right ends of the real-time safe tension range.

[0074] S63, if the tension value of the scraper conveyor chain at the current time node is not within its real-time safe tension range, and the minimum absolute value of the difference between the real-time left end value and the real-time right end value of the real-time safe tension range is greater than the critical threshold, then it is determined that there is a significant risk to the tension of the scraper conveyor chain at the current time node, and a warning level is determined to be high.

[0075] S64, when a warning level is determined, a control strategy for the scraper conveyor chain is generated based on the minimum absolute value of the difference, and the control strategy is combined with the warning level to generate control commands.

[0076] Specifically, if the tension value of the scraper conveyor chain at the current time point is less than the real-time left end of the real-time safe tension range and the warning level is medium, the control strategy is to increase the scraper conveyor chain speed. If the tension value of the scraper conveyor chain at the current time point is greater than the real-time right end of the real-time safe tension range and the warning level is high, the control strategy is to reduce the scraper conveyor chain speed and reduce the motor load. The control command is obtained by combining the control strategy with the warning level.

[0077] S7 adjusts the scraper conveyor chain according to the control command so that the tension value of the scraper conveyor chain at future time nodes is always within its corresponding real-time safe tension range.

[0078] Based on all the above embodiments, the scraper conveyor chain tension dynamic optimization method based on real-time load feedback provided by the present invention has the following beneficial effects: First, by acquiring load data of various operating states of the scraper conveyor chain and extracting features, load time series features are obtained, providing an accurate data foundation for subsequent analysis of scraper conveyor chain tension values.

[0079] Then, the load time series features and load data of various operating states are processed by a time attention mechanism to obtain the importance weight of each type of load data of each operating state at each time node. Based on the load data of each operating state at all time nodes and their importance weights, the tension value of the scraper conveyor chain at the current time node is calculated. By utilizing the load time series features and the time attention mechanism, different weights are assigned to the load data of different operating states at each time node. This allows for dynamic adjustment of tension according to the complex and ever-changing working conditions of the scraper conveyor in actual operation. It can also more accurately calculate the tension value of the scraper conveyor chain at the current time node, providing high-quality data for subsequent optimization control of the scraper conveyor chain. Finally, the real-time operating condition coefficient for the current time node is calculated based on the load data of each operating state and its importance weight. The preset safe tension range is dynamically adjusted according to the real-time operating condition coefficient to obtain the real-time safe tension range for the current time node. The tension value is compared with the real-time safe tension range, and control commands are generated and executed based on the comparison results. This optimizes the tension control method of the scraper conveyor chain and improves the control accuracy of the scraper conveyor chain tension.

[0080] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for dynamic optimization of scraper conveyor chain tension based on real-time load feedback, characterized in that, include: S1, acquire various operating state load data of the scraper conveyor chain, including multiple time nodes aligned to the current time node; S2, after standardizing the load data of various operating states at all time points, extract features to obtain load time series features; S3, the time series characteristics of the load and the load data of multiple operating states at each time node are processed by the time attention mechanism to obtain the importance weight of each type of load data at each time node. S4, calculate the tension value of the scraper conveyor chain at the current time node based on the load data of each operating state at all time nodes and their importance weights; S5. Calculate the real-time operating condition coefficient of the current time node based on the load data of each operating state at the current time node and its importance weight, and dynamically adjust the preset safety tension range based on the real-time operating condition coefficient of the current time node to obtain the real-time safety tension range of the current time node. S6, compare the tension value of the scraper conveyor chain at the current time node with its real-time safe tension range, and generate control commands based on the comparison results; S7 adjusts the scraper conveyor chain according to the control command so that the tension value of the scraper conveyor chain at future time nodes is always within its corresponding real-time safe tension range.

2. The method for dynamic optimization of scraper conveyor chain tension based on real-time load feedback according to claim 1, characterized in that, S2 includes: S21, standardize the load data of various operating states at all time points to obtain various standard operating state load data of all time points; S22, calculate the statistical characteristics of the load data of each standard operating state at all time points, and generate the first feature of the load data of each standard operating state at each time point based on the statistical characteristics of the load data of each standard operating state. The statistical characteristics include the mean, standard deviation and extreme values. S23, convert each standard operating state load data into frequency domain operating state load data through Fourier transform, and obtain the instantaneous frequency characteristics of each frequency domain operating state load data at each time node, and use the instantaneous frequency characteristics of each time node as the second feature. S24, take each time node, the first feature and the second feature as the elements corresponding to each time node, and combine the elements corresponding to all time nodes to obtain the load time series features.

3. The method for dynamic optimization of scraper conveyor chain tension based on real-time load feedback according to claim 2, characterized in that, When S22 generates the first feature of the load data for each standard operating state at each time point based on the statistical characteristics of the load data for each standard operating state, it includes: S221, Construct the matching relationship between the maximum and minimum values ​​of load data for each standard operating state and the time nodes corresponding to the maximum and minimum values; S222, construct the matching relationship between the mean and standard deviation of the load data for each standard operating state and all time points; S223, combine the extreme values ​​of each standard operating state load data and their corresponding time node matching relationships, mean and standard deviation matching relationships with all time nodes to obtain the first feature of each time node.

4. The method for dynamic optimization of scraper conveyor chain tension based on real-time load feedback according to claim 1, characterized in that, S3 includes: S31, construct a load matrix based on the load data of multiple operating states at each time point, wherein each row of the matrix load represents a load data of one operating state, and each column represents the load data of multiple operating states at a time point. S32, input the load matrix and load time series features into the channel attention module, and generate query vector, key vector and value vector of load data for each time step and each running state according to the channel attention module; S33, calculate the attention score for each type of runtime state load data at each time step based on the query vector, key vector, and value vector of each type of runtime state load data at each time step; S34. Normalize the attention scores of each type of runtime load data at all time steps to obtain the attention weights of each type of runtime load data at each time step, which serve as the importance weights of each type of runtime load data at each time node.

5. The method for dynamic optimization of scraper conveyor chain tension based on real-time load feedback according to claim 4, characterized in that, When S33 calculates the attention score 'a' of the operating state load data at the i-th time step based on the query vector, key vector, and value vector of any operating state load data at each time step, it does so through formula (1): （1）； In formula (1), exp() represents the exponential function, Qi represents the query vector of the running state load data at the i-th time step, Kj represents the key vector of the running state load data at the j-th time step, Ki represents the key vector of the running state load data at the i-th time step, d represents the sum of the dimensions of the query vector and the key vector of the running state load data, and T represents the number of time steps.

6. The method for dynamic optimization of scraper conveyor chain tension based on real-time load feedback according to claim 1, characterized in that, S4 includes: S41, fit the load data of each operating state at all time points and its importance weight to obtain the chain tension curve; S42, Obtain the predicted chain tension corresponding to the current time node based on the chain tension curve; S43, calculate the tension value of the scraper conveyor chain at the current time node based on the importance weight of the predicted chain tension and the various operating state load data at the current time node.

7. The method for dynamic optimization of scraper conveyor chain tension based on real-time load feedback according to claim 6, characterized in that, When S43 calculates the tension value P of the scraper conveyor chain at the current time node based on the importance weights of the predicted chain tension and the various operating state load data at the current time node, it does so through formula (2): （2）； In formula (2), max(a) represents the maximum value of the importance weight of all operating state load data at the current time node, min(a) represents the minimum value of the importance weight of all operating state load data at the current time node, and P0 represents the predicted chain tension.

8. The method for dynamic optimization of scraper conveyor chain tension based on real-time load feedback according to claim 1, characterized in that, S5 includes: S51, weight all the running status load data of the current time node and their importance weights, and sum them up by adding the preset load coefficient to obtain the load value of the current time node; S52, determine the preset amplification factor corresponding to the load value at the current time node according to the load value-preset amplification factor mapping table, and multiply the load value at the current time node with the corresponding preset amplification factor to obtain the real-time operating condition factor at the current time node. S53, multiply the left and right values ​​of the preset safe tension range by the real-time operating condition coefficient of the current time node to obtain the real-time left and right values, and construct the real-time safe tension range of the current time node based on the real-time left and right values.

9. The method for dynamic optimization of scraper conveyor chain tension based on real-time load feedback according to claim 8, characterized in that, S6 includes: S61, if the tension value of the scraper conveyor chain at the current time node is within its real-time safe tension range, then the tension of the scraper conveyor chain at the current time node is determined to be normal, and it is determined that there is no warning level. S62, if the tension value of the scraper conveyor chain at the current time node is not within its real-time safe tension range, and the minimum absolute value of the difference between the real-time left end value and the real-time right end value of the real-time safe tension range is less than or equal to the critical threshold, then it is determined that there is a risk in the tension of the scraper conveyor chain at the current time node, and a warning level is determined to be medium. S63, if the tension value of the scraper conveyor chain at the current time node is not within its real-time safe tension range, and the minimum absolute value of the difference between the real-time left end value and the real-time right end value of the real-time safe tension range is greater than the critical threshold, then it is determined that the tension of the scraper conveyor chain at the current time node has a significant risk, and a warning level is determined to exist and the warning level is high. S64, when a warning level is determined, a control strategy for the scraper conveyor chain is generated based on the minimum absolute value of the difference, and the control strategy is combined with the warning level to generate control commands.

Images