An intelligent cable operation load abnormality monitoring processing system in a well

Abstract

This invention relates to the field of data processing technology, and in particular to a system for monitoring and processing abnormal loads on underground intelligent cables. The system includes a processor and a memory. The processor executes a computer program in the memory to perform the following steps: acquiring real-time multi-dimensional monitoring data of the underground intelligent cable towing device at the current monitoring moment, as well as historical multi-dimensional monitoring data prior to the current monitoring moment; correcting the real-time traction force data at the current monitoring moment based on the real-time roadway slope data and real-time humidity data to obtain optimized traction force data; using the historical multi-dimensional monitoring data prior to the current monitoring moment, performing collaborative anomaly analysis of the optimized traction force data and the real-time multi-dimensional monitoring data to obtain a cable load anomaly coefficient; and using the cable load anomaly coefficient and the real-time multi-dimensional monitoring data to monitor the cable load anomaly at the current monitoring moment, thereby improving the accuracy of cable load anomaly monitoring.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a monitoring and processing system for abnormal operating loads of underground intelligent cables. Background Technology

[0002] In the complex and ever-changing underground tunnel environment of coal mines, real-time load monitoring of cable-dragging devices is a crucial link in ensuring continuous and efficient operation of the mining face and preventing cable breakage and equipment damage. Existing technologies mainly rely on multi-parameter alarm methods based on fixed thresholds for current, temperature, and traction force. By setting current overload settings, temperature safety thresholds, and maximum traction force limits, abnormal loads can be identified and warned of.

[0003] With the advancement of intelligent construction in coal mines, this type of threshold alarm technology has been combined with regular inspections and standardized maintenance processes, forming a standardized operation and maintenance system from data collection to anomaly handling. This lays an important foundation for the transformation of the operation and maintenance model from passive response to proactive early warning, and plays an important role in improving equipment reliability and reducing unplanned downtime.

[0004] Existing technologies have the advantages of intuitive monitoring principles, mature and cost-effective sensor technology, and simple implementation in scenarios with stable operating conditions and minimal environmental changes. However, in actual underground environments with dynamic changes in tunnel slope and complex coupling of mechanical and electrical states, traction force sensors are easily affected by both their own system (slope) and the external environment (humidity). They cannot effectively distinguish between real load anomalies and environmental interference, making it difficult for the traction force monitored by the traction force sensor to accurately reflect the actual traction force of the cable. As a result, the accuracy of traction force monitoring results is insufficient when there are environmental fluctuations or slope changes, leading to an increase in false alarm and missed alarm rates.

[0005] Therefore, how to accurately monitor abnormal cable loads based on the complex and ever-changing roadway environment in coal mines has become an urgent problem to be solved. Summary of the Invention

[0006] In view of this, embodiments of the present invention provide an intelligent underground cable operation load anomaly monitoring and processing system to solve the problem of how to accurately monitor cable load anomalies based on the complex and ever-changing roadway environment in coal mines.

[0007] This invention provides a system for monitoring and processing abnormal operating loads of underground intelligent cables, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it performs the following steps:

[0008] The system acquires multi-dimensional monitoring data at each monitoring moment during the operation of the intelligent cable dragging device in the mine, obtaining real-time multi-dimensional monitoring data at the current monitoring moment and historical multi-dimensional monitoring data before the current monitoring moment. The multi-dimensional monitoring data includes traction force data, current data, temperature data, humidity data and roadway slope data.

[0009] Based on the real-time roadway slope data at the current monitoring time, the real-time traction force data at the current monitoring time is initially corrected to obtain the initial optimized traction force data at the current monitoring time. Based on the real-time humidity data at the current monitoring time, the initial optimized traction force data at the current monitoring time is then corrected a second time to obtain the optimized traction force data at the current monitoring time.

[0010] The historical multidimensional monitoring data prior to the current monitoring time are combined into a historical multidimensional monitoring data sequence. The historical optimized traction force data prior to the current monitoring time are also combined into a historical optimized traction force data sequence. Using the historical multidimensional monitoring data sequence and the historical optimized traction force data sequence, a multi-source collaborative anomaly analysis is performed on the optimized traction force data, real-time current data, and real-time temperature data at the current monitoring time to obtain the cable load anomaly coefficient at the current monitoring time.

[0011] By utilizing the cable load anomaly coefficient at the current monitoring time and real-time multidimensional monitoring data, the cable load anomaly at the current monitoring time can be monitored.

[0012] Preferably, the step of performing initial correction on the real-time traction force data at the current monitoring time based on the real-time roadway slope data at the current monitoring time to obtain the initial optimized traction force data at the current monitoring time includes:

[0013] Obtain the cable gravity data at the current monitoring time, calculate the product of the sine value of the real-time roadway slope data at the current monitoring time and the cable gravity data to obtain gravity component data, obtain the difference between the real-time traction force data at the current monitoring time and the gravity component data to obtain the initial optimized traction force data at the current monitoring time.

[0014] Preferably, the step of performing a secondary correction on the initial optimized traction force data at the current monitoring time based on the real-time humidity data at the current monitoring time to obtain the optimized traction force data at the current monitoring time includes:

[0015] Substitute the product of the real-time humidity data at the current monitoring time and the preset humidity sensitivity coefficient into the hyperbolic tangent function to obtain the humidity influence index. Obtain the product of the humidity influence index and the preset maximum humidity attenuation coefficient to obtain the friction coefficient attenuation value. Calculate the difference between the constant 1 and the friction coefficient attenuation value to obtain the remaining proportion of the friction coefficient. Obtain the reference friction coefficient. Calculate the product of the reference friction coefficient and the remaining proportion of the friction coefficient to obtain the real-time friction coefficient. Obtain the ratio of the reference friction coefficient to the real-time friction coefficient to obtain the friction compensation coefficient.

[0016] The optimized traction force data for the current monitoring time is obtained by multiplying the initial optimized traction force data at the current monitoring time with the friction compensation coefficient.

[0017] Preferably, the step of using the historical multi-dimensional monitoring data sequence and the historical optimized traction force data sequence to perform multi-source data collaborative anomaly analysis on the optimized traction force data, real-time current data, and real-time temperature data at the current monitoring time to obtain the cable load anomaly coefficient at the current monitoring time includes:

[0018] At least one normal historical multidimensional monitoring data is selected from the historical multidimensional monitoring data sequence to form a normal historical multidimensional monitoring data sequence. The normal historical multidimensional monitoring data sequence is then divided into a normal historical current monitoring data sequence and a normal historical temperature monitoring data sequence according to the dimensions.

[0019] At least one normal historical optimized traction force data point is selected from the historical optimized traction force data sequence to form a normal historical optimized traction force data sequence;

[0020] Based on the data differences between the optimized traction force data at the current monitoring time and the normal historical optimized traction force data sequence, the data differences between the real-time current data at the current monitoring time and the normal historical current monitoring data sequence, and the data differences between the real-time temperature data at the current monitoring time and the normal historical temperature monitoring data sequence, the cable load anomaly coefficient at the current monitoring time is obtained.

[0021] Preferably, the step of obtaining the cable load anomaly coefficient at the current monitoring time based on the data differences between the optimized traction force data at the current monitoring time and the normal historical optimized traction force data sequence, the data differences between the real-time current data at the current monitoring time and the normal historical current monitoring data sequence, and the data differences between the real-time temperature data at the current monitoring time and the normal historical temperature monitoring data sequence includes:

[0022] The average value of the normal historical optimized traction force data sequence is obtained and recorded as the baseline traction force data. The absolute value of the difference between the optimized traction force data at the current monitoring time and the baseline traction force data is calculated to obtain the traction force difference value. The standard deviation of the normal historical optimized traction force data sequence is obtained and recorded as the traction force standard deviation. The ratio of the traction force difference value to the traction force standard deviation is calculated to obtain the traction force anomaly index.

[0023] The average value of the normal historical current monitoring data sequence is obtained and recorded as the reference current data. The absolute value of the difference between the real-time current data at the current monitoring time and the reference current data is calculated to obtain the current difference value. The standard deviation of the normal historical current monitoring data sequence is obtained and recorded as the current standard deviation. The ratio of the current difference value to the current standard deviation is calculated to obtain the current anomaly index.

[0024] The average value of the normal historical temperature monitoring data sequence is obtained and recorded as the reference temperature data. The absolute value of the difference between the real-time temperature data at the current monitoring time and the reference temperature data is calculated to obtain the temperature difference value. The standard deviation of the normal historical temperature monitoring data sequence is obtained and recorded as the temperature standard deviation. The ratio of the temperature difference value to the temperature standard deviation is calculated to obtain the temperature anomaly index.

[0025] The average value between the current anomaly index and the temperature anomaly index is obtained to obtain the lateral traction force anomaly index. The traction force anomaly index and the lateral traction force anomaly index are weighted and summed to obtain the cable load anomaly coefficient at the current monitoring time.

[0026] Preferably, the tunnel slope data in the multidimensional monitoring data is obtained by a stroke encoder installed in the cable dragging device.

[0027] The beneficial effects of the embodiments of the present invention compared with the prior art are as follows:

[0028] In this invention, based on the real-time roadway slope data at the current monitoring time, the real-time traction force data at the current monitoring time is initially corrected to obtain the initially optimized traction force data for the current monitoring time. This process removes the gravity component caused by roadway undulations from the real-time traction force data, ensuring that the corrected initially optimized traction force data retains only frictional resistance and abnormal resistance, thus more directly reflecting the mechanical load level of the equipment. Based on the real-time humidity data at the current monitoring time, the initially optimized traction force data is then further corrected to obtain the optimized traction force data for the current monitoring time, achieving [further refinement / correction]. Precise compensation for friction coefficient fluctuations caused by changes in ambient humidity eliminates the interference of ambient humidity in traction force readings, providing a purer reflection of the equipment's true mechanical load. By utilizing historical multidimensional monitoring data sequences and historical optimized traction force data sequences, collaborative anomaly analysis of optimized traction force data, real-time current data, and real-time temperature data at the current monitoring moment is performed. This overcomes the limitations of poor robustness and susceptibility to misjudgment in single-parameter threshold detection, and supplements overall anomalies that cannot be detected by single data thresholds. By fusing features and single data features, load anomalies can be monitored more comprehensively, achieving higher accuracy monitoring. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This is a flowchart of a method for monitoring and handling abnormal operating loads of an intelligent underground cable, provided in Embodiment 1 of the present invention. Detailed Implementation

[0031] Embodiments of this disclosure are described in detail below, with examples of these embodiments illustrated in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting it.

[0032] It should be noted that the terms "first," "second," etc., used in this disclosure and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure.

[0033] To illustrate the technical solution of the present invention, specific embodiments are described below.

[0034] This invention provides a system for monitoring and processing abnormal operating loads of downhole intelligent cables, including a processor and a memory. The processor executes a computer program in the memory to implement a method for monitoring and processing abnormal operating loads of downhole intelligent cables. Figure 1 As shown, the method may include:

[0035] Step S101: Real-time acquisition of multi-dimensional monitoring data at each monitoring moment during the operation of the underground intelligent cable towing device, obtaining real-time multi-dimensional monitoring data at the current monitoring moment and historical multi-dimensional monitoring data before the current monitoring moment. The multi-dimensional monitoring data includes traction force data, current data, temperature data, humidity data and roadway slope data.

[0036] In the complex and ever-changing tunnel environment of coal mines, real-time load monitoring of cable dragging devices is a key link to ensure continuous and efficient operation of mining faces and to prevent cable breakage and equipment damage.

[0037] In this implementation case, multiple types of sensors installed on the cable towing device acquire multi-dimensional monitoring data at a data acquisition frequency of 10 times per second. This is not limited here and can be set according to the specific implementation scenario. The system can acquire multi-dimensional monitoring data at each monitoring moment during the operation of the underground intelligent cable towing device in real time, and obtain the real-time multi-dimensional monitoring data at the current monitoring moment as well as the historical multi-dimensional monitoring data before the current monitoring moment. This data is used to monitor the load anomaly of the underground intelligent cable towing device.

[0038] Multidimensional monitoring data includes traction force data, current data, temperature data, humidity data, and roadway slope data. The specific operations for obtaining multidimensional monitoring data are as follows: (1) Synchronous acquisition of multi-source data: Through the traction force sensor, current transformer, temperature and humidity sensor, and stroke encoder set on the cable towing device, the real-time output of each sensor is read in parallel, and a unified timestamp is added to all data to ensure the time consistency of subsequent fusion analysis; (2) Data quality cleaning and anomaly handling: Threshold range (such as physical possible range) and mutation rate constraints are applied to the obtained real-time output data to identify and remove obvious outliers; For the missing data caused by brief communication interruption, linear interpolation or rolling mean of the nearest time is used to fill in the gaps smoothly; (3) Traction force self Adaptive filtering: Apply Kalman filtering algorithm to the real-time traction force data output by the traction force sensor to separate the real load signal from the instantaneous noise caused by underground vibration and impact; (4) Slope dynamic mapping: Based on the running mileage of the cable towing device obtained in real time by the stroke encoder, obtain the angle of the cable towing device's location on the coordinate axis, automatically match and output the roadway slope data corresponding to the location of the cable towing device; (5) Current and temperature reference compensation: Perform phase correction on the real-time current data output by the current transformer to eliminate harmonic effects, and perform ambient temperature compensation on the real-time temperature data of the cable surface output by the temperature and humidity sensor to more accurately reflect the temperature rise caused by load heat generation; finally, obtain multi-dimensional monitoring data for each monitoring moment.

[0039] Existing technologies primarily rely on multi-parameter alarm methods based on fixed thresholds for current, temperature, and traction force. These methods identify and warn of load anomalies by setting overload current settings, temperature safety thresholds, and maximum traction force limits. However, in the dynamic changes of tunnel slope and the complex coupling of mechanical and electrical conditions in actual underground environments, traction force sensors are susceptible to both system-specific (slope) and external environmental (humidity) influences. This makes it difficult to effectively distinguish between actual load anomalies and environmental interference. Consequently, the traction force detected by the sensor fails to accurately reflect the actual traction force of the cable, resulting in insufficient accuracy of traction force monitoring results during environmental fluctuations or slope changes, leading to increased false alarm and missed alarm rates.

[0040] Therefore, in this implementation case, the real-time traction force data at the current monitoring time is corrected based on the real-time roadway slope data and real-time humidity data at the current monitoring time to obtain optimized traction force data. This reduces the interference of friction caused by gravity components and changes in environmental humidity, and the traction force data can more purely reflect the true mechanical load of the equipment. Then, multi-source data collaborative anomaly analysis is performed on the real-time multi-dimensional monitoring data at the current monitoring time, overcoming the limitations of poor robustness and easy misjudgment of single parameter threshold detection, and thus more comprehensively and accurately monitoring the load anomaly of the cable dragging device.

[0041] Step S102: Based on the real-time roadway slope data at the current monitoring time, perform initial correction on the real-time traction force data at the current monitoring time to obtain the initial optimized traction force data at the current monitoring time. Based on the real-time humidity data at the current monitoring time, perform secondary correction on the initial optimized traction force data at the current monitoring time to obtain the optimized traction force data at the current monitoring time.

[0042] Because of the slope changes in the underground mining face of a coal mine, the traction force sensor cannot distinguish between the drag resistance and the gravity component caused by the inclination angle of the roadway when measuring, so the obtained traction force data will deviate significantly from the actual load under uphill and downhill conditions.

[0043] Therefore, in this implementation case, the real-time traction force data at the current monitoring time is initially corrected based on the real-time roadway slope data at the current monitoring time to obtain the initial optimized traction force data at the current monitoring time. This solves the problem of inaccurate traction force data caused by different slopes, and ensures that the corrected initial optimized traction force data only retains frictional resistance and abnormal resistance, thus more directly reflecting the mechanical load level of the equipment.

[0044] The method for initially correcting the real-time traction force data based on the real-time roadway slope data at the current monitoring time to obtain the initially optimized traction force data at the current monitoring time is as follows:

[0045] Obtain the unit length mass of the cable from the cable product standard or specification (e.g., approximately 15 kg / m for MYP-3×95 cable). Obtain the length of the cable being dragged in a suspended state or on a slope at the current monitoring time (i.e., the length of the cable being "suspended under tension" between the cable dragging device and the nearest fixed point), and record it as the cable dragging length at the current monitoring time. Calculate the product of the cable's unit length mass, gravitational acceleration, and the cable dragging length at the current monitoring time to obtain the cable gravity data at the current monitoring time. Calculate the product of the sine value of the real-time roadway slope data at the current monitoring time and the cable gravity data to obtain the gravity component data. Obtain the difference between the real-time traction force data at the current monitoring time and the gravity component data to obtain the initial optimized traction force data at the current monitoring time.

[0046] In one embodiment, the formula for calculating the initial optimized traction force data at the current monitoring time is:

[0047]

[0048] in, Optimize traction force data for the current monitoring time. This represents the real-time traction force data at the current monitoring moment; m is the mass per unit length of the cable; g is the acceleration due to gravity; and L is the cable drag length at the current monitoring moment. This provides real-time tunnel slope data at the current monitoring moment. This represents the sine value of the real-time roadway slope data at the current monitoring moment.

[0049] It should be noted that if the device is in the downhole state, gravity acts as the driving force, which will reduce the traction force. In this case, the obtained θ is less than 0, meaning that the real-time traction force data at the current monitoring moment becomes larger after correction. If the device is in the uphole state, gravity acts as the resistance, which will increase the traction force. In this case, the obtained θ is greater than 0, meaning that the real-time traction force data at the current monitoring moment becomes smaller after correction.

[0050] During the operation of cable dragging devices, humidity levels can vary, and the corresponding coefficient of friction will change accordingly, presenting a constantly changing quantity. The coefficient of friction summarized solely from historical data is not applicable.

[0051] Therefore, after obtaining the initial optimized traction force data at the current monitoring time, this implementation case performs a secondary correction on the initial optimized traction force data at the current monitoring time based on the real-time humidity data at the current monitoring time, thereby obtaining the optimized traction force data at the current monitoring time. This achieves accurate compensation for the fluctuation of the friction coefficient caused by changes in environmental humidity, reduces the interference of humidity fluctuations on the traction force data, and makes it more realistic and stable in reflecting the actual mechanical load state in the complex humidity environment downhole.

[0052] The method for obtaining the optimized traction force data for the current monitoring time by performing a secondary correction on the initial optimized traction force data based on the real-time humidity data at the current monitoring time is as follows:

[0053] Substituting the product of the real-time humidity data at the current monitoring moment and the preset humidity sensitivity coefficient into the hyperbolic tangent function yields the humidity influence index. The product of this humidity influence index and the preset maximum humidity attenuation coefficient is then obtained to determine the friction coefficient attenuation value. The difference between the constant 1 and the friction coefficient attenuation value is calculated to obtain the remaining friction coefficient ratio. The friction coefficient of the cable at the coal mine entrance is obtained using a friction coefficient meter as a reference friction coefficient. The product of the reference friction coefficient and the remaining friction coefficient ratio is calculated to obtain the real-time friction coefficient. Finally, the ratio of the reference friction coefficient to the real-time friction coefficient is obtained to determine the friction compensation. The compensation coefficient; among which, the preset humidity sensitivity coefficient controls the sensitivity of the effect of humidity on the friction coefficient. The larger the preset humidity sensitivity coefficient, the more sensitive the friction coefficient is to changes in humidity. In this embodiment, the preset humidity sensitivity coefficient is set to 3. There is no limitation here, and it can be set according to the specific implementation scenario. The preset maximum humidity attenuation coefficient represents the maximum friction coefficient attenuation ratio that humidity can cause (for example, when the preset maximum humidity attenuation coefficient is 0.3, it means that the friction coefficient can be reduced by up to 30%). The value range is (0, 1). In this embodiment, the preset maximum humidity attenuation coefficient is set to 0.3. There is no limitation here, and it can be set according to the specific implementation scenario.

[0054] The optimized traction force data for the current monitoring time is obtained by multiplying the initial optimized traction force data at the current monitoring time with the friction compensation coefficient.

[0055] In one embodiment, the formula for calculating the optimized traction force data at the current monitoring time is:

[0056]

[0057] in, Optimize traction force data for the current monitoring moment; Optimize traction force data for the current monitoring time. The reference friction coefficient; The preset maximum humidity attenuation coefficient; H represents the preset humidity sensitivity coefficient; H is the real-time humidity data at the current monitoring time. It is the hyperbolic tangent function.

[0058] It should be noted that, This indicates the percentage by which the coefficient of friction decreases from the baseline coefficient of friction at the current humidity data H. Increasing H leads to a decrease in the actual coefficient of friction. In other words, under the same actual mechanical load, the downhole environment causes the traction force measured by the traction force sensor to be lower than expected. Therefore, it is necessary to compensate for the monitored traction force data. It will become larger after correction; It is the reference friction coefficient. In mathematical formulas, the reference friction coefficient can be simplified, but it is retained here for ease of understanding.

[0059] At this point, optimized traction force data for the current monitoring moment is obtained.

[0060] Step S103: The historical multidimensional monitoring data before the current monitoring time is used to form a historical multidimensional monitoring data sequence. The historical optimized traction force data before the current monitoring time is used to form a historical optimized traction force data sequence. Using the historical multidimensional monitoring data sequence and the historical optimized traction force data sequence, a multi-source collaborative anomaly analysis is performed on the optimized traction force data, real-time current data and real-time temperature data at the current monitoring time to obtain the cable load anomaly coefficient at the current monitoring time.

[0061] While optimized traction force data can more realistically and stably reflect the actual mechanical load status in the complex humidity environment downhole, using only optimized traction force data for load anomaly monitoring still carries the risk of misjudgment due to accidental sensor errors, localized momentary jamming, or atypical faults. For example, sensors may occasionally experience sudden spikes due to noise; cables may briefly rub against the tunnel wall or run over small foreign objects during dragging, generating a short-duration, high-amplitude resistance pulse; force sensors may fail to detect minor short circuits in motors (abnormal current data) or minor lubrication problems in gearboxes (abnormal temperature data).

[0062] To address the limitations of single-data monitoring, this implementation case combines historical multi-dimensional monitoring data prior to the current monitoring time into a historical multi-dimensional monitoring data sequence, and historical optimized traction force data prior to the current monitoring time into a historical optimized traction force data sequence. It also integrates current and temperature data—two electrical and thermal parameters strongly correlated with load status—and uses these historical multi-dimensional monitoring data sequences and the historical optimized traction force data sequence to perform collaborative anomaly analysis on the optimized traction force data, real-time current data, and real-time temperature data at the current monitoring time. This yields the cable load anomaly coefficient at the current monitoring time. This approach not only integrates multi-dimensional mechanical, electrical, and thermal state information but also effectively suppresses single-point interference through consistency verification of multi-source signals. It overcomes the limitations of poor robustness and susceptibility to misjudgment associated with single-parameter threshold detection, thereby achieving accurate diagnosis of real load anomalies.

[0063] The method for obtaining the cable load anomaly coefficient at the current monitoring time by performing multi-source collaborative anomaly analysis on the optimized traction force data, real-time current data, and real-time temperature data at the current monitoring time using the historical multi-dimensional monitoring data sequence and the historical optimized traction force data sequence is as follows:

[0064] At least one normal historical multidimensional monitoring data (i.e., historical multidimensional monitoring data in which the historical current data does not exceed the preset current data warning threshold and the historical temperature data does not exceed the preset temperature data warning threshold) is selected from the historical multidimensional monitoring data sequence. The current data warning threshold and the temperature data warning threshold need to be set according to the specific specifications of the cable dragging device. In this embodiment, the rated current is obtained from the product manual and other product specifications of the cable dragging device as the preset current data warning threshold and the maximum operating temperature is obtained as the preset temperature data warning threshold. There is no restriction here, and it can be set according to the specific implementation scenario. The normal historical multidimensional monitoring data sequence is divided into a normal historical current monitoring data sequence and a normal historical temperature monitoring data sequence according to the dimensions.

[0065] At least one normal historical optimized traction force data (i.e., the historical optimized traction force data does not exceed the preset warning threshold of the load anomaly coefficient of the third-level cable in this embodiment) is selected from the historical optimized traction force data sequence to form a normal historical optimized traction force data sequence;

[0066] The average value of the normal historical optimized traction force data sequence is obtained and recorded as the baseline traction force data. The absolute value of the difference between the optimized traction force data at the current monitoring time and the baseline traction force data is calculated to obtain the traction force difference value. The standard deviation of the normal historical optimized traction force data sequence is obtained and recorded as the traction force standard deviation. The ratio of the traction force difference value to the traction force standard deviation is calculated to obtain the traction force anomaly index.

[0067] The average value of the normal historical current monitoring data sequence is obtained and recorded as the reference current data. The absolute value of the difference between the real-time current data at the current monitoring time and the reference current data is calculated to obtain the current difference value. The standard deviation of the normal historical current monitoring data sequence is obtained and recorded as the current standard deviation. The ratio of the current difference value to the current standard deviation is calculated to obtain the current anomaly index.

[0068] The average value of the normal historical temperature monitoring data sequence is obtained and recorded as the reference temperature data. The absolute value of the difference between the real-time temperature data at the current monitoring time and the reference temperature data is calculated to obtain the temperature difference value. The standard deviation of the normal historical temperature monitoring data sequence is obtained and recorded as the temperature standard deviation. The ratio of the temperature difference value to the temperature standard deviation is calculated to obtain the temperature anomaly index.

[0069] The average value between the current anomaly index and the temperature anomaly index is obtained to obtain the lateral traction force anomaly index. The traction force anomaly index and the lateral traction force anomaly index are weighted and summed to obtain the cable load anomaly coefficient at the current monitoring time.

[0070] In one embodiment, the formula for calculating the cable load anomaly coefficient at the current monitoring time is:

[0071]

[0072] Where K is the cable load anomaly coefficient at the current monitoring time; Optimize traction force data for the current monitoring moment; This is the baseline traction force data; is the standard deviation of the traction force; I is the real-time current data at the current monitoring moment; Reference current data; is the standard deviation of the current; T is the real-time temperature data at the current monitoring moment; Reference temperature data; This represents the standard deviation of temperature. It is the absolute value symbol; The first weighting coefficient, i.e. Weighting coefficients; This is the second weighting coefficient, i.e. The weighting coefficients.

[0073] It should be noted that, This is an abnormal indicator of traction force. The larger the value, the greater the difference between the optimized traction force data and the baseline traction force data at the current monitoring time, and the more likely the cable load at the current monitoring time is to be abnormal; the larger K is. This is an indicator of abnormal lateral traction. This is an indicator of abnormal current. As an indicator of temperature anomalies, this is because there is an inherent physical coupling relationship between traction force data, current data, and temperature data: "increased load → increased traction force → increased current → accelerated temperature rise." or The larger the value, the more likely an anomaly is to occur in the cable load at the current monitoring moment. The larger the value, the larger K becomes; since traction force data is the most direct and instantaneous representation of load, its abnormal changes are large, while current and temperature data reflect abnormal load conditions from the side, i.e., as a side load representation, their overall abnormal changes are small. Therefore, in this implementation case, K is set... , There are no restrictions here; settings can be made according to the specific implementation scenario.

[0074] Since the calculation of the cable load anomaly coefficient needs to be compared with the normal data under historical operating conditions, this implementation case performs anomaly monitoring 1 minute after the cable dragging device starts running. There is no restriction here, and it can be set according to the specific implementation scenario.

[0075] Thus, the cable load anomaly coefficient at the current monitoring time is obtained.

[0076] Step S104: Using the cable load anomaly coefficient at the current monitoring time and real-time multidimensional monitoring data, the cable load anomaly at the current monitoring time is monitored.

[0077] Once the cable load anomaly coefficient at the current monitoring time is obtained, the cable load anomaly can be monitored at the current monitoring time using the cable load anomaly coefficient at the current monitoring time and real-time multidimensional monitoring data.

[0078] Monitoring cable load anomalies at the current monitoring moment using the cable load anomaly coefficient and real-time multidimensional monitoring data is an existing technology, which will be briefly described here:

[0079] (1) Multi-parameter fixed threshold early warning: The optimized traction force data, real-time temperature data and real-time current data at the current monitoring time are compared with the preset traction force data early warning threshold, temperature data early warning threshold and current data early warning threshold respectively. If any of the optimized traction force data, real-time temperature data and real-time current data at the current monitoring time exceeds its early warning threshold, an alarm is triggered. In this implementation case, the maximum safe traction force is obtained from the product specifications such as the product manual of the cable dragging device, and 90% of the maximum safe traction force is set as the optimized traction force data threshold. There is no restriction here, and it can be set according to the specific implementation scenario.

[0080] (2) Graded early warning matching based on cable load abnormality coefficient: It is carried out in sync with multi-parameter fixed threshold early warning. The cable load abnormality coefficient at the current monitoring time is compared with the preset three-level cable load abnormality coefficient early warning threshold. Even if a single data does not alarm, if the cable load abnormality coefficient at the current monitoring time meets the conditions, the preset response program will be automatically triggered: Level 1 early warning (reminder recording), Level 2 early warning (speed limit check) or Level 3 early warning (emergency shutdown), and corresponding sound and light and remote notification will be issued.

[0081] (3) Multi-dimensional data backtracking and anomaly pattern self-verification: When an early warning is triggered, the standardized deviation of traction force data, real-time temperature data and real-time current data is automatically backtracked and optimized. By analyzing the magnitude relationship and change sequence of the three (such as whether they rise synchronously), cross-validation is performed to determine whether the dominant factor of the anomaly is mechanical jamming, electrical overload or local overheating, and the preliminary anomaly type confidence and diagnostic clues are output.

[0082] In summary, in this embodiment of the invention, the real-time traction force data at the current monitoring time is initially corrected based on the real-time roadway slope data to obtain the initial optimized traction force data. This process removes the gravity component caused by roadway undulations from the real-time traction force data, ensuring that the corrected initial optimized traction force data retains only frictional resistance and abnormal resistance, thus more directly reflecting the mechanical load level of the equipment. A second correction is then performed based on the real-time humidity data at the current monitoring time to obtain the optimized traction force data for the current monitoring time. It achieves precise compensation for friction coefficient fluctuations caused by changes in ambient humidity, eliminating the interference of ambient humidity in traction force readings and reflecting the true mechanical load of the equipment more purely. By utilizing historical multidimensional monitoring data sequences and historical optimized traction force data sequences, it performs collaborative anomaly analysis of optimized traction force data, real-time current data, and real-time temperature data at the current monitoring moment. This overcomes the limitations of poor robustness and easy misjudgment of single parameter threshold detection, and supplements the overall anomalies that cannot be detected by single data thresholds. By fusing features and single data features, it can more comprehensively monitor load anomalies and achieve higher accuracy monitoring.

[0083] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A downhole intelligent cable operational load anomaly monitoring and processing system comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized by, When the processor executes the computer program, it performs the following steps: The system acquires multi-dimensional monitoring data at each monitoring moment during the operation of the intelligent cable dragging device in the mine, obtaining real-time multi-dimensional monitoring data at the current monitoring moment and historical multi-dimensional monitoring data before the current monitoring moment. The multi-dimensional monitoring data includes traction force data, current data, temperature data, humidity data and roadway slope data. Based on the real-time roadway slope data at the current monitoring time, the real-time traction force data at the current monitoring time is initially corrected to obtain the initial optimized traction force data at the current monitoring time. Based on the real-time humidity data at the current monitoring time, the initial optimized traction force data at the current monitoring time is then corrected a second time to obtain the optimized traction force data at the current monitoring time. The historical multidimensional monitoring data prior to the current monitoring time are combined into a historical multidimensional monitoring data sequence. The historical optimized traction force data prior to the current monitoring time are also combined into a historical optimized traction force data sequence. Using the historical multidimensional monitoring data sequence and the historical optimized traction force data sequence, a multi-source collaborative anomaly analysis is performed on the optimized traction force data, real-time current data, and real-time temperature data at the current monitoring time to obtain the cable load anomaly coefficient at the current monitoring time. By utilizing the cable load anomaly coefficient at the current monitoring time and real-time multidimensional monitoring data, the cable load anomaly at the current monitoring time can be monitored.

2. The downhole intelligent cable operational load anomaly monitoring and processing system of claim 1, wherein, The process of performing initial correction on the real-time traction force data based on the real-time roadway slope data at the current monitoring time to obtain the initial optimized traction force data at the current monitoring time includes: Obtain the cable gravity data at the current monitoring time, calculate the product of the sine value of the real-time roadway slope data at the current monitoring time and the cable gravity data to obtain gravity component data, obtain the difference between the real-time traction force data at the current monitoring time and the gravity component data to obtain the initial optimized traction force data at the current monitoring time.

3. The downhole intelligent cable operating load anomaly monitoring and processing system of claim 1, wherein, The process of performing a secondary correction on the initial optimized traction force data at the current monitoring time based on the real-time humidity data at the current monitoring time to obtain the optimized traction force data at the current monitoring time includes: Substitute the product of the real-time humidity data at the current monitoring time and the preset humidity sensitivity coefficient into the hyperbolic tangent function to obtain the humidity influence index. Obtain the product of the humidity influence index and the preset maximum humidity attenuation coefficient to obtain the friction coefficient attenuation value. Calculate the difference between the constant 1 and the friction coefficient attenuation value to obtain the remaining proportion of the friction coefficient. Obtain the reference friction coefficient. Calculate the product of the reference friction coefficient and the remaining proportion of the friction coefficient to obtain the real-time friction coefficient. Obtain the ratio of the reference friction coefficient to the real-time friction coefficient to obtain the friction compensation coefficient. The optimized traction force data for the current monitoring time is obtained by multiplying the initial optimized traction force data at the current monitoring time with the friction compensation coefficient.

4. The downhole intelligent cable operating load anomaly monitoring and processing system of claim 1, wherein, The method involves using the historical multidimensional monitoring data sequence and the historical optimized traction force data sequence to perform multi-source collaborative anomaly analysis on the optimized traction force data, real-time current data, and real-time temperature data at the current monitoring time, to obtain the cable load anomaly coefficient at the current monitoring time, including: At least one normal historical multidimensional monitoring data is selected from the historical multidimensional monitoring data sequence to form a normal historical multidimensional monitoring data sequence. The normal historical multidimensional monitoring data sequence is then divided into a normal historical current monitoring data sequence and a normal historical temperature monitoring data sequence according to the dimensions. At least one normal historical optimized traction force data point is selected from the historical optimized traction force data sequence to form a normal historical optimized traction force data sequence; Based on the data differences between the optimized traction force data at the current monitoring time and the normal historical optimized traction force data sequence, the data differences between the real-time current data at the current monitoring time and the normal historical current monitoring data sequence, and the data differences between the real-time temperature data at the current monitoring time and the normal historical temperature monitoring data sequence, the cable load anomaly coefficient at the current monitoring time is obtained.

5. A downhole intelligent cable operational load anomaly monitoring and processing system according to claim 4, characterized in that, The step of obtaining the cable load anomaly coefficient at the current monitoring time based on the data differences between the optimized traction force data at the current monitoring time and the normal historical optimized traction force data sequence, the data differences between the real-time current data at the current monitoring time and the normal historical current monitoring data sequence, and the data differences between the real-time temperature data at the current monitoring time and the normal historical temperature monitoring data sequence includes: The average value of the normal historical optimized traction force data sequence is obtained and recorded as the baseline traction force data. The absolute value of the difference between the optimized traction force data at the current monitoring time and the baseline traction force data is calculated to obtain the traction force difference value. The standard deviation of the normal historical optimized traction force data sequence is obtained and recorded as the traction force standard deviation. The ratio of the traction force difference value to the traction force standard deviation is calculated to obtain the traction force anomaly index. The average value of the normal historical current monitoring data sequence is obtained and recorded as the reference current data. The absolute value of the difference between the real-time current data at the current monitoring time and the reference current data is calculated to obtain the current difference value. The standard deviation of the normal historical current monitoring data sequence is obtained and recorded as the current standard deviation. The ratio of the current difference value to the current standard deviation is calculated to obtain the current anomaly index. The average value of the normal historical temperature monitoring data sequence is obtained and recorded as the reference temperature data. The absolute value of the difference between the real-time temperature data at the current monitoring time and the reference temperature data is calculated to obtain the temperature difference value. The standard deviation of the normal historical temperature monitoring data sequence is obtained and recorded as the temperature standard deviation. The ratio of the temperature difference value to the temperature standard deviation is calculated to obtain the temperature anomaly index. The average value between the current anomaly index and the temperature anomaly index is obtained to obtain the lateral traction force anomaly index. The traction force anomaly index and the lateral traction force anomaly index are weighted and summed to obtain the cable load anomaly coefficient at the current monitoring time.

6. The downhole intelligent cable operational load anomaly monitoring and processing system of claim 1, wherein, The tunnel slope data in the multidimensional monitoring data is obtained by a stroke encoder installed in the cable dragging device.

Images