A method for early warning of faults in a tailings paste filling system

Abstract

The present invention relates to the field of fault early warning, and particularly to a fault early warning method for a tailings paste filling system. It includes: monitoring and storing parameters in real time to form a parameter matrix; introducing a sliding time window technique to standardize the parameters at each moment to obtain the standardized parameter values; based on the standardized parameter values, using a dynamic feature extraction algorithm to process and obtain feature values; based on the feature values, calculating a fault probability value through a dynamic gain adjustment fault probability calculation algorithm, comparing the fault probability value with a fault threshold to obtain a fault determination result; according to the feature values and the fault determination result, calculating a significance score through a fault location algorithm, and determining the fault source according to the significance score; based on the fault source, carrying out fault early warning. It solves the technical problem that in the tailings paste filling system, there are multiple monitoring points, making the real-time data processing complex and difficult to conduct unified comparison and analysis.

Description

Technical Field

[0001] The present invention relates to the field of fault warning, and particularly to a method for fault warning of a tailings paste filling system. Background Art

[0002] The tailings paste filling technology is an important means applied to the treatment of mine waste, aiming to reduce the environmental pollution caused by tailings and realize the reuse of mine resources. However, with the increasingly wide application of the tailings paste filling technology, the importance of the tailings paste filling system in mine production has become increasingly prominent. The faults of the tailings paste filling system not only affect the filling efficiency of the tailings paste, but also may pose a threat to the safety of the mine, and may even trigger mine accidents. Traditional fault warnings for tailings paste filling systems mostly rely on manual inspections and simple equipment monitoring, which have disadvantages such as monitoring delays and poor accuracy, and it is difficult to detect the potential risks of faults in the tailings paste filling system in real time. Therefore, timely detection and warning of potential faults in the tailings paste filling system can effectively prevent the spread of faults, reduce losses, and ensure the safe production of the mine.

[0003] However, the existing methods for fault warning of tailings paste filling systems have the following technical problems: In the tailings paste filling system, there are multiple monitoring points, which makes real-time data processing complicated and difficult to conduct unified comparison and analysis. Simple static standardization processing will result in the inability to effectively integrate the parameters of different monitoring points, thereby affecting the accuracy of fault warning; Traditional fault detection methods are difficult to effectively capture the sudden changes or non-periodic fluctuations of the tailings paste filling system, especially in the case of multiple monitoring points and multiple parameters. Existing feature extraction methods are difficult to accurately reflect the change patterns of the tailings paste filling system, resulting in a lag in fault judgment; When calculating the fault probability, traditional fault detection methods often use fixed weights or linear weighting methods, which are not sensitive enough to rapidly changing monitoring points and are prone to ignoring sudden events, affecting the accuracy of fault determination; The fault location method relies on static parameter differences or simple threshold judgments and cannot accurately locate the fault source. Especially in the case of drastic changes in the parameters of multiple monitoring points, misjudgment is likely to occur; Traditional methods for fault warning of tailings paste filling systems lack comprehensive evaluation of faults and cannot display the positions of abnormal monitoring points and abnormal parameters in real time, resulting in the inability of management personnel to quickly locate and handle problems when faults occur in the tailings paste filling system. Summary of the Invention

[0004] The present invention provides a method for fault early warning of a tailings paste filling system, aiming to solve the following technical problems in the tailings paste filling system: there are various monitoring points, making real-time data processing complex and difficult to conduct unified comparison and analysis. Simple static standardization processing will result in ineffective integration of parameters at different monitoring points, thus affecting the accuracy of fault early warning; traditional fault detection methods are difficult to effectively capture sudden changes or non-periodic fluctuations in the tailings paste filling system, especially in the case of multiple monitoring points and multiple parameters, and existing feature extraction methods are difficult to accurately reflect the change pattern of the tailings paste filling system, leading to a lag in fault judgment; when calculating the fault probability, traditional fault detection methods often adopt a fixed weight or linear weighting method, which is not sensitive enough to rapidly changing monitoring points and is prone to ignoring sudden events, affecting the accuracy of fault determination; the fault location method relies on static parameter differences or simple threshold judgments and cannot accurately locate the fault source, especially when the parameters of multiple monitoring points change violently, resulting in misjudgment; traditional fault early warning methods for tailings paste filling systems lack comprehensive evaluation of faults and cannot display the positions of abnormal monitoring points and abnormal parameters in real time, resulting in the inability of management personnel to quickly locate and handle problems when a fault occurs in the tailings paste filling system.

[0005] A method for fault early warning of a tailings paste filling system according to the present invention specifically includes the following technical solutions:

[0006] A method for fault early warning of a tailings paste filling system includes the following steps:

[0007] S1: Monitor and store parameters in real time to form a parameter matrix; introduce a sliding time window technology to perform standardization processing on the parameters at each moment to obtain standardized parameter values;

[0008] S2: Based on the standardized parameter values, use a dynamic feature extraction algorithm to process and obtain feature values;

[0009] S3: Based on the feature values, calculate the fault probability value through a dynamic gain adjustment fault probability calculation algorithm, compare the fault probability value with the fault threshold to obtain a fault determination result;

[0010] S4: According to the feature values and the fault determination result, calculate the significance score through a fault location algorithm, determine the fault source based on the significance score; based on the fault source, conduct fault early warning.

[0011] Preferably, the S1 specifically includes:

[0012] The sliding time window technology analyzes the parameters monitored in real time by dividing the sliding window into different time periods. By sliding a fixed step size, as time progresses, new parameters will automatically enter the sliding time window, while outdated parameters will be removed, so that each sliding time window covers the parameters of the current and the next time periods.

[0013] Preferably, S1 specifically includes:

[0014] Based on the parameters monitored and stored in real time, through the real-time calculation of the mean value and the standard deviation, the parameters at each moment are normalized to obtain the normalized parameter values. The normalization formula is:

[0015]

[0016] Where, represents the th normalized parameter value of the th monitoring point at time represents the th parameter value of the th monitoring point at time represents the mean value of the th parameters of the th monitoring point at time represents the standard deviation of the th parameters of the th monitoring point at time

[0017] Preferably, S2 specifically includes:

[0018] The core of the dynamic feature extraction algorithm includes two aspects: dynamic energy characteristics and dynamic change enhancement term; the dynamic energy characteristics are obtained by integrating the squared normalized parameter values of the monitoring points and normalizing the dynamic energy characteristics of the parameters; the dynamic change enhancement term is obtained by integrating the absolute values of the normalized parameter values of the parameters of the monitoring points within the sliding time window to adjust the sensitivity to non-periodic fluctuations.

[0019] Preferably, S2 specifically includes:

[0020] The calculation formula for the eigenvalue is:

[0021]

[0022] Where, represents the th The eigenvalue of the th parameter of the th monitoring point; at time the th normalized parameter value of the th monitoring point; represents the dynamic energy characteristic of the th parameter of the th monitoring point within the th sliding time window; represents the normalization term; represents the square root operation; represents the dynamic change enhancement term;

[0023] Preferably, the S3 specifically includes:

[0024] The dynamic gain adjustment fault probability calculation algorithm obtains the fault probability value by multiplying the eigenvalue of the monitoring point parameter by the gain adjustment factor and then performing cumulative summation, and combining with a non-linear activation function. The specific calculation formula is:

[0025]

[0026] where represents the fault probability value within the th sliding time window; represents the activation function; represents the weighted summation of the eigenvalues of all parameters of all monitoring points; represents at the th sliding time window, the th monitoring point, the th parameter eigenvalue; represents at the th sliding time window, the th monitoring point, the th parameter gain adjustment factor.

[0027] Preferably, the S4 specifically includes:

[0028] In the implementation process of the fault location algorithm, calculate the absolute difference between the eigenvalue of the monitoring point parameter and the expected value, and obtain the significance score by introducing the standard deviation of the eigenvalue of the monitoring point parameter and the dynamic adaptive coupling factor, and combining with the sine function.

[0029] Preferably, the S4 specifically includes:

[0030] The calculation formula of the significance score is:

[0031]

[0032] in, Indicated in The first sliding time window The monitoring point The significance score of each parameter; Indicated in The first sliding time window The monitoring point The characteristic value of the parameter; Indicates expected value; represents the parameter deviation, that is, The first sliding time window The monitoring point The absolute difference between the characteristic value and the expected value of a parameter; Indicated in The first sliding time window The monitoring point The standard deviation of the eigenvalues ​​of the parameters; represents a very small constant; represents the normalization term; represents the dynamic adaptive coupling factor.

[0033] Preferably, the S4 specifically includes:

[0034] A significance score threshold is set and compared with the significance score to determine the fault source; when the significance score exceeds the significance score threshold, the parameter at the monitoring point is considered to be the source of the fault; an early warning is issued based on the fault source, and the location of the abnormal monitoring point and the abnormal parameters are displayed.

[0035] The beneficial effects of the technical solution of the present invention are:

[0036] 1. By installing sensors at key monitoring points of the tailings paste filling system and monitoring parameters in real time, such as pressure, flow rate, and concentration, and combining the sliding time window technology to process the real-time monitored parameters in real time, the real-time monitoring of the tailings paste filling system can be ensured. It can not only ensure that the tailings paste filling system can obtain timely and accurate monitoring data at all times, but also standardize the various parameters to eliminate the problems of dimensional differences and different numerical ranges, thereby providing a reliable data basis for subsequent dynamic analysis, ensuring that the tailings paste filling system can obtain and process the parameters of each monitoring point in real time, reduce the analysis errors caused by dimensional differences, and improve the accuracy and efficiency of data processing.

[0037] 2. By introducing a dynamic feature extraction algorithm, it is possible to effectively evaluate the fluctuation intensity and sudden changes in the state of the tailings paste filling system. The dynamic energy characteristics reflect the fluctuation intensity of each parameter in the tailings paste filling system within a sliding time window, while the dynamic change enhancement term can sensitively capture non-periodic fluctuations, providing multi-dimensional data support for fault detection, thereby enhancing the early warning ability of faults in the tailings paste filling system. Through the extraction of eigenvalues, the fluctuation intensity and sudden changes in the tailings paste filling system can be accurately identified, improving the sensitivity and accuracy of fault diagnosis.

[0038] 3. The dynamic gain adjustment fault probability calculation algorithm is adopted. By weighted summing the eigenvalues and combining with a non-linear activation function to calculate the fault probability value of the tailings paste filling system, it can quickly respond to the dynamic changes of the tailings paste filling system. Especially when a sudden fault occurs, it can sensitively detect and respond, improving the real-time performance of fault detection, being able to quickly detect potential risks at the initial stage of fault occurrence, and ensuring the efficient operation and safety of the tailings paste filling system.

[0039] 4. After fault determination, the significance score is calculated through the fault location algorithm, and the abnormality degree of each monitoring point is further analyzed. Through accurate fault location, the fault source can be effectively determined, reducing the possibility of misjudgment, thereby reducing the downtime and maintenance cost of the tailings paste filling system. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a flowchart of a method for fault early warning of a tailings paste filling system according to the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0041] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0042] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0043] The following specifically describes the specific solution of a method for fault early warning of a tailings paste filling system provided by the present invention in conjunction with the drawings.

[0044] Refer to the attached Figure 1, which shows a flowchart of a method for early warning of faults in a tailings paste filling system provided by an embodiment of the present invention. The method includes the following steps:

[0045] S1. Monitor and store parameters in real time to form a parameter matrix; introduce the sliding time window technology to standardize the parameters at each moment to obtain the standardized parameter values;

[0046] According to the key processes and monitoring requirements of the tailings paste filling system, select key monitoring points and determine the parameters to be monitored, such as pressure, flow rate, and concentration; install sensors at each monitoring point position to monitor and store parameters in real time to form a parameter matrix, and the representation form is as follows:

[0047]

[0048] Among them, represents the th parameter value of the th monitoring point at time , such as pressure, flow rate, and concentration; represents the number of monitoring points; represents the number of parameters monitored at each monitoring point;

[0049] In order to effectively process the parameters monitored in real time and perform dynamic analysis, the sliding time window technology is introduced. The sliding time window technology analyzes the parameters monitored in real time by dividing the sliding time window into multiple time periods. Each sliding time window contains data within a certain time range, which is defined as:

[0050]

[0051] Among them, represents the start time of the th sliding time window; represents the length of the sliding time window; represents the end time of the th sliding time window;

[0052] In the sliding time window technology, the sliding process of the time window is also real-time. By sliding a fixed step length each time, the fixed step length , as time progresses, new parameters will automatically enter the sliding time window, while outdated parameters will be removed, so that each sliding time window can cover the parameters of the current and the next time periods, ensuring that the tailings paste filling system can process the monitored parameters in real time and guarantee the timeliness of dynamic analysis;

[0053] Based on the parameters monitored and stored in real time, through the real-time calculation of the mean and standard deviation, the parameters at each moment can be standardized to obtain the standardized parameter values, so as to eliminate the problems of dimensional differences and different numerical ranges of the parameters;

[0054] The standardization formula is as follows:

[0055]

[0056] Wherein, represents the th standardized parameter value of the th monitoring point at time ; represents the th parameter value of the th monitoring point at time such as pressure, flow rate, concentration; represents the mean value of the th parameter of the th monitoring point at time , and the calculation formula is: , represents the sliding window length; represents the th parameter value of the th monitoring point at time ; represents the sum and average of the parameters from time to time ; represents the standard deviation of the th parameter of the th monitoring point at time , that is, within the time range from time to time , the square root of the sum of the squares of the differences between the parameter values and the mean value is taken and averaged, and the calculation formula is:

[0057] ;

[0058] By calculating the mean and standard deviation in a recursive update manner, real-time data processing can be achieved. Only by updating the current mean and standard deviation according to the parameters within the sliding time window and then performing standardization processing, not only can the changes in the data stream be responded to in real time, but also the computational complexity can be reduced, which is suitable for fault warning with extremely high requirements for real-time performance;

[0059] S2. Based on the standardized parameter values, use the dynamic feature extraction algorithm to process and obtain the feature values;

[0060] Based on the standardized parameter values, the eigenvalue is obtained by processing with the dynamic feature extraction algorithm;

[0061] The core of the dynamic feature extraction algorithm lies in two aspects: dynamic energy characteristics and dynamic change enhancement term;

[0062] The dynamic energy characteristics are evaluated by assessing the fluctuation amplitude of each parameter within a sliding time window to measure the energy characteristics. Specifically, by integrating the squared standardized parameter values of the monitoring points, the total energy characteristics within the current sliding time window are calculated. To make the measurement comparable, the dynamic energy characteristics of all parameters are also normalized. The normalized dynamic energy characteristics can reflect the fluctuation intensity of each parameter within a specific sliding time window. The stronger the fluctuation, the more it reflects the instability or potential faults of the tailings paste filling system;

[0063] The dynamic change enhancement term integrates the absolute values of the standardized parameter values of each parameter value of each monitoring point within a sliding time window to enhance the sensitivity to non-periodic fluctuations, and is used to capture sudden changes or abnormal phenomena in the tailings paste filling system;

[0064] The calculation formula of the eigenvalue is:

[0065]

[0066] Where, represents the eigenvalue of the th parameter of the th monitoring point within the th sliding time window; represents the th standardized parameter value of the th monitoring point at time ; represents the dynamic energy characteristics of the th parameter of the th monitoring point within the th sliding time window. By integrating the squared standardized parameter values, the energy distribution of the monitoring point and the parameter within the time window can be calculated, which can reflect the fluctuation degree or the "intensity" of the change of the parameter; represents the normalization term, which is used to calculate the squared integral of all standardized parameter values of all monitoring points within the th sliding time window, ensuring that the energy measurement of each eigenvalue is not affected by the overall fluctuation; represents the square root operation, which is used for scale adjustment to keep within a suitable proportion range; Represents the dynamic change enhancement term, that is, the integral of the absolute value of the standardized parameter values within the sliding time window, used to capture the non-periodic changes or abnormal fluctuations in the tailings paste filling system; Represents the weight factor, used to balance the relative importance of the normalized dynamic energy characteristics and the dynamic change enhancement term;

[0067] S3. Based on the eigenvalues, calculate the fault probability value through the dynamic gain adjustment fault probability calculation algorithm, and compare the fault probability value with the fault threshold to obtain the fault determination result;

[0068] Based on the eigenvalues, calculate the fault probability through the dynamic gain adjustment fault probability calculation algorithm;

[0069] The dynamic gain adjustment fault probability calculation algorithm obtains the fault probability value by weighted summing the eigenvalues of all parameters at all monitoring points and combining a non-linear activation function, which is used to reflect whether there is a fault in the tailings paste filling system. Specifically, multiply the eigenvalue of each parameter at each monitoring point by the gain adjustment factor and perform cumulative summation, and input it into the activation function to obtain a value between and which represents the occurrence probability of the fault, that is, the fault probability value;

[0070] The gain adjustment factor normalizes the dynamic change rates of all eigenvalues by calculating the dynamic change rate of the eigenvalues within the sliding time window, ensuring the response consistency to the changes at all monitoring points. By enhancing the sensitivity of the eigenvalues to rapid changes, it can make a rapid response to emergencies in the tailings paste filling system;

[0071] The calculation formula for the fault probability value is:

[0072]

[0073] Where, represents the fault probability value in the th sliding time window, and the value range is ; represents the activation function, used to smooth the weighted sum and convert the weighted sum into a value between and to ensure that the output fault probability value is always within a reasonable range; represents the weighted sum of the eigenvalues of all parameters at all monitoring points. The weighted sum reflects the overall dynamic change situation of the tailings paste filling system within the sliding time window and is the core of fault judgment; represents at the The eigenvalue of the th monitoring point for the th parameter within a sliding time window; Indicates that within the th sliding time window, for the th monitoring point, the th parameter's gain adjustment factor, which is used to weight the fault discrimination according to the characteristic change rate of the monitoring point parameter. The calculation formula is:

[0074]

[0075] Where, Represents the exponential function, which magnifies the influence of the eigenvalue change by exponentiating the dynamic change rate of the eigenvalue; Represents the adjustment coefficient that controls the sensitivity of the gain adjustment factor, determines the magnification factor of the dynamic change rate of the eigenvalue on the gain adjustment factor, and can be specifically set according to the specific implementation scenario, which is not limited here; Indicates that within the th sliding time window, for the th monitoring point, the th parameter's absolute integral of the dynamic change rate of the eigenvalue. By taking the absolute value, the direction of the characteristic change is ignored, emphasizing the amplitude of the characteristic change. The integral reflects the change amount of the eigenvalue within the time window and can evaluate the dynamic change degree of the eigenvalue; Represents the th monitoring point's th parameter's dynamic change rate of the eigenvalue; Represents calculating the maximum value of the characteristic change rates of all parameters of all monitoring points to ensure that all gain adjustment factors are normalized according to the maximum characteristic change rate, preventing the stability of the entire tailings paste filling system from being affected by some violently changing characteristics;

[0076] Set the fault threshold , which can be specifically set according to the specific implementation scenario and is not limited here; Compare the fault probability value with the fault threshold to obtain the fault determination result; Based on the fault determination result, determine whether there is a fault in the tailings paste filling system. When the fault probability value is greater than the fault threshold, it is considered that there is a fault in the tailings paste filling system within the th sliding time window, otherwise, there is no fault;

[0077] S4. According to the eigenvalue and the fault determination result, calculate the significance score through the fault location algorithm, and determine the fault source based on the significance score; Based on the fault source, conduct fault early warning;

[0078] According to the eigenvalue and the fault determination result, calculate the significance score through the fault location algorithm;

[0079] The fault location algorithm calculates the absolute difference between the eigenvalue of each parameter at each monitoring point and the expected value. This absolute difference reflects the difference between the current state and the normal state of the monitoring point. The greater the difference, the higher the degree of abnormality.

[0080] To further improve the calculation accuracy, the standard deviation of the eigenvalue of the monitoring point parameter is introduced to measure the fluctuation range of the eigenvalue, which can give more attention when the eigenvalue changes violently, thereby improving the sensitivity of fault detection.

[0081] A dynamic adaptive coupling factor is further introduced. Based on the change amount of the eigenvalue of the monitoring point parameter between adjacent time windows, it reflects the fluctuation of the state of the tailings paste filling system. Nonlinear processing is performed through a sine function, so that when the eigenvalue changes extremely, the response is sensitive, which helps to accurately capture the abnormal behavior of the tailings paste filling system.

[0082] The calculation formula for the significance score is:

[0083]

[0084] where, represents the significance score of the -th parameter of the -th monitoring point in the -th sliding time window; represents the eigenvalue of the -th parameter of the -th monitoring point in the -th sliding time window; represents the expected value, which can be calculated through predefined normal values and is a well-known technical means for those skilled in the art, so it will not be elaborated here; represents the parameter deviation, that is, the absolute difference between the eigenvalue of the -th parameter of the -th monitoring point and the expected value in the -th sliding time window; represents the standard deviation of the eigenvalue of the -th parameter of the -th monitoring point in the -th sliding time window, which is used to measure the volatility of the eigenvalue of the monitoring point parameter and is a well-known technical means for those skilled in the art, so it will not be elaborated here; represents a very small constant, which is used to prevent the denominator from being zero and ensure the calculation stability. It can be specifically set according to the specific implementation scenario and is not limited here; represents the normalization term, which is used to normalize the significance scores of all parameters of all monitoring points; It represents the dynamic adaptive coupling factor, and the calculation formula is as follows:

[0085]

[0086] Wherein, represents the change amount of the eigenvalue of the th parameter at the th monitoring point between adjacent time windows, and the calculation formula is: ; represents the eigenvalue of the th parameter at the th monitoring point within the th sliding time window; represents the eigenvalue of the th parameter at the th monitoring point within the th sliding time window; represents the mathematical constant, approximately equal to 3.14159; represents non - linear processing through the sine function, so that when the eigenvalue changes greatly, the response is sensitive, which helps to accurately capture the abnormal behavior of the tailings paste filling system; represents the coupling coefficient, reflecting the correlation between the th parameter at the th monitoring point, which can be specifically set according to the specific implementation scenario and is not limited here;

[0087] Set the significance score threshold, and compare it with the significance score to determine the fault source; specifically, when the significance score exceeds the significance score threshold, it is considered that the parameter at the monitored point is the source of the fault; the significance score threshold can be specifically set according to the specific implementation scenario and is not limited here;

[0088] Give an early warning according to the fault source, and display the location of the abnormal monitoring point and the abnormal parameter.

[0089] In summary, a fault early - warning method for a tailings paste filling system is completed.

[0090] The sequence of the invention embodiments is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multi - tasking and parallel processing are also possible or may be advantageous.

[0091] Each embodiment in this specification is described in a progressive manner. For the same or similar parts between each embodiment, reference can be made to each other. Each embodiment focuses on the differences from other embodiments.

[0092] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A tailings paste filling system fault early warning method, characterized in that: The following steps are involved: S1: Monitor and store parameters in real time to form a parameter matrix; introduce sliding time window technology to standardize the parameters at each moment to obtain the standardized parameter values; S2: Based on the standardized parameter values, the dynamic feature extraction algorithm is used to obtain the feature values; S3: Based on the eigenvalue, a dynamic gain adjustment fault probability calculation algorithm is introduced. The algorithm multiplies the eigenvalue of the monitoring point parameter by the gain adjustment factor and then adds them up. It is combined with a nonlinear activation function to obtain the fault probability value. The calculation formula is: ； in, Indicated in Failure probability value within a sliding time window; express Activation function; Indicated in The first sliding time window The monitoring point The characteristic value of the parameter; Indicated in The first sliding time window The monitoring point Gain adjustment factor for each parameter; Indicates the number of monitoring points; Indicates the number of parameters monitored at each monitoring point; Compare the fault probability value with the fault threshold to obtain a fault determination result; S4: According to the characteristic value and fault judgment result, the fault location algorithm is introduced to calculate the absolute difference between the characteristic value and the expected value of the monitoring point parameter. By combining the standard deviation of the characteristic value of the monitoring point parameter and the dynamic adaptive coupling factor, the significance score is obtained. The calculation formula is: ； in, Indicated in The first sliding time window The monitoring point The significance score of each parameter; Indicates expected value; Indicated in The first sliding time window The monitoring point The standard deviation of the eigenvalues ​​of the parameters; represents a very small constant; represents the dynamic adaptive coupling factor; Determine the fault source based on the significance score; and issue a fault warning based on the fault source.

2. A tailings paste filling system fault early warning method according to claim 1, characterized in that: The S1 specifically includes: The sliding time window technology analyzes the parameters monitored in real time by dividing the sliding window into different time periods. By sliding a fixed step, as time goes by, new parameters will automatically enter the sliding time window, and outdated parameters will be removed, so that each sliding time window covers the parameters of the current and next time periods.

3. A tailings paste filling system fault early warning method according to claim 2, characterized in that: The S1 specifically includes: Based on the real-time monitored and stored parameters, the parameters at each moment are standardized through real-time calculation of the mean and standard deviation to obtain the standardized parameter value. The standardization formula is: ； in, Indicates at time Time The monitoring point The standardized parameter values; Indicates at time Time The monitoring point parameter values; Indicates at time Time The monitoring point The mean of the parameters; Indicates at time Time The monitoring point The standard deviation of the parameter.

4. A tailings paste filling system fault early warning method according to claim 1, characterized in that: The S2 specifically includes: The core of the dynamic feature extraction algorithm includes two aspects: dynamic energy characteristics and dynamic change enhancement items; the dynamic energy characteristics are obtained by squaring and integrating the standardized parameter values ​​of the monitoring points, and normalizing the dynamic energy characteristics of the parameters; the dynamic change enhancement items adjust the sensitivity of non-periodic fluctuations by integrating the absolute values ​​of the standardized parameter values ​​of the monitoring points within the sliding time window.

5. A tailings paste filling system fault early warning method according to claim 4, characterized in that: The S2 specifically includes: The calculation formula of the eigenvalue is: ； in, Indicated in The first sliding time window The monitoring point The characteristic value of the parameter; Indicates at time Time The monitoring point The standardized parameter values; Indicated in The first sliding time window The monitoring point Dynamic energy characteristics of parameters; represents the normalization term; Represents the square root operation; Indicates dynamically changing enhancement items; Represents the weight factor.

6. A tailings paste filling system fault early warning method according to claim 1, characterized in that: The S4 specifically includes: A significance score threshold is set and compared with the significance score to determine the fault source; when the significance score exceeds the significance score threshold, the parameter at the monitoring point is considered to be the source of the fault; an early warning is issued based on the fault source, and the location of the abnormal monitoring point and the abnormal parameters are displayed.

Images