Machine learning based coal preparation plant equipment health condition monitoring system

Abstract

This invention relates to the field of equipment monitoring technology, and more particularly to a machine learning-based health status monitoring system for coal preparation plant equipment. The system includes: a data acquisition module for collecting equipment operating data and raw material parameters; a coal slime characteristic analysis module for constructing a load coefficient and determining the coal slime load status based on the load coefficient; a structure monitoring module for constructing a structure status index and determining the equipment structure status based on the structure status index; a pressure monitoring module for jointly analyzing cylinder pressure, cylinder pressure standard deviation, and cylinder pressure average value to construct a pressure status index and update the equipment structure status assessment; an electrical safety monitoring module for determining electrical safety status and updating the pressure status index construction process based on the electrical safety status; and an equipment status monitoring module for determining the equipment health status and providing equipment maintenance prompts to the user. This invention effectively improves the efficiency of equipment monitoring in coal preparation plants.

Description

Technical Field

[0001] This invention relates to the field of equipment monitoring technology, and in particular to a machine learning-based equipment health status monitoring system for coal preparation plants. Background Technology

[0002] Coal preparation plant core equipment operates under high wear and high load conditions for extended periods. Traditional monitoring technologies, relying on manual inspections and single-sensor threshold alarms, have significant drawbacks: Static threshold limitations: Fixed thresholds cannot dynamically respond to the impact of changes in coal slime raw material characteristics (such as moisture content and particle size) on the equipment, leading to false alarms. For example, screen pressure differentials are often judged solely by fixed pressure thresholds, ignoring the nonlinear impact of sudden changes in coal slime particle size on the pressure differential; Insufficient fault coupling: The correlation between mechanical wear, electrical aging, and raw material load is not quantified. Drum wear and screen blockage are often analyzed in isolation, making it difficult to pinpoint the root cause of complex faults (such as wear causing material retention and resulting in pressure fluctuations); Lack of early warning: Traditional methods have low sensitivity to progressive faults (such as motor insulation degradation), typically triggering alarms only after the fault becomes severe. Dynamic parameters such as temperature gradients and wear rates are not incorporated into the model, missing maintenance windows.

[0003] Chinese Patent Publication No. CN114911206A discloses an intelligent predictive maintenance system for coal preparation plants based on the Internet of Things (IoT), comprising: IoT sensors for real-time data acquisition of equipment operation; IoT repeaters for transmitting real-time equipment operation data to a local server for storage and uploading; an intelligent cloud processing platform for analyzing various operational data of the equipment in the real-time operation data through AI machine learning algorithms and models embedded in the cloud, comprehensively evaluating the operating status of the equipment and pushing relevant information; a digital twin control platform for building a virtual coal preparation plant using 3D laser scanner field scanning technology, realizing intelligent interactive functions, monitoring functions, and early warning functions, and pushing early warning and alarm data; and an intelligent control client for receiving data, viewing the plant's operation status in real time, analyzing and realizing predictive maintenance and intelligent control. It is evident that this solution only achieves "3D display + alarm push" on the digital twin platform, but lacks multi-dimensional root cause analysis capabilities, resulting in low monitoring efficiency for coal preparation plant equipment. Summary of the Invention

[0004] The purpose of this invention is to provide a machine learning-based health status monitoring system for coal preparation plant equipment to solve at least one of the problems existing in the prior art.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] A machine learning-based health status monitoring system for coal preparation plant equipment includes:

[0007] The structural monitoring module is used to jointly analyze the thickness of the equipment drum lining and the screen pressure difference collected during the monitoring period in order to construct a structural status index and judge the structural status of the equipment based on the structural status index.

[0008] The pressure monitoring module is used to perform joint analysis on cylinder pressure, cylinder pressure standard deviation and cylinder pressure average value to construct a pressure state index and update the judgment of equipment structural status.

[0009] The equipment status monitoring module is used to determine the health status of the equipment based on the coal slime load status, equipment structure status, and electrical safety status within the management cycle, and to output equipment maintenance prompts to the user based on the determination results of the equipment health status.

[0010] Optionally, the structure monitoring module includes a wear analysis unit, which is used to calculate the wear rate Ms based on the equipment drum liner thickness m0 and reference thickness m1 collected during the monitoring period, and compare and analyze the wear rate Ms with the preset wear rate ms0 to determine the equipment wear status, and construct a wear index based on the equipment wear status.

[0011] Optionally, the structural monitoring module further includes a differential pressure analysis unit, used to compare and analyze the screen differential pressure ΔP collected during the monitoring period with the preset differential pressure p1 to determine the equipment differential pressure status, and to construct an equipment differential pressure index based on the equipment differential pressure status, wherein:

[0012] If △P is less than or equal to p1, the differential pressure analysis unit determines that the equipment differential pressure status is normal in the current monitoring cycle and sets the equipment differential pressure index to YC1, setting YC1=0. Otherwise, the differential pressure analysis unit sets the equipment differential pressure index to YC2, setting YC2=3×[(△P-p1) / (△P+p1)]2-2×[(△P-p1) / (△P+p1)]3.

[0013] Optionally, the structure monitoring module further includes a structure state judgment unit, which is used to construct a structure state index ZY based on the wear index and the equipment differential pressure index, and set ZY=lg(3×wear index+1) / lg4×equipment differential pressure index;

[0014] The structural state judgment unit compares and analyzes the structural state index ZY and the preset state index zy to determine the structural state of the equipment. If ZY is less than or equal to zy, the structural state judgment unit determines that the structural state of the equipment in the current monitoring period is healthy and does not issue a structural health status warning to the user. Conversely, the structural state judgment unit determines that the structural state of the equipment in the current monitoring period is abnormal and issues a structural health status warning to the user.

[0015] Optionally, the pressure monitoring module compares and analyzes the i-th cylinder pressure Pi collected within the monitoring period with the preset cylinder pressure threshold p0 to determine whether the cylinder pressure exceeds the limit. If Pi is less than or equal to p0, the pressure monitoring module determines that the i-th cylinder pressure does not exceed the limit; otherwise, the pressure monitoring module determines that the i-th cylinder pressure exceeds the limit, and counts the number of cylinder pressure exceeding the limit Pn. The proportion of cylinder pressure exceeding the limit is set as β, where β is the ratio of Pn to Pu, and Pu is the number of cylinder pressures collected within the monitoring period.

[0016] The pressure monitoring module performs joint analysis on the percentage of cylinder pressure exceeding the limit β, the standard deviation of cylinder pressure σP, and the average cylinder pressure Pavg to construct the pressure state index PC, which is set as: PC = σP / Pavg × β;

[0017] If the equipment structure is in a healthy state during the current monitoring period, and the pressure state index PC is greater than or equal to the preset pressure state index pc0, then the equipment structure is determined to be in an abnormal state during the current monitoring period, and a structural health status warning is issued to the user.

[0018] Optionally, the system further includes: an electrical safety monitoring module, used to fuse the motor insulation resistance and winding temperature collected during the monitoring period to construct an insulation degradation index, and to determine the electrical safety status based on the insulation degradation index, and also used to update the construction process of the pressure status index based on the electrical safety status.

[0019] Optionally, the electrical safety monitoring module includes a construction unit for calculating the winding temperature gradient ΔT based on the winding temperature collected during the monitoring period, wherein the winding temperature gradient ΔT is the difference between the maximum and minimum winding temperature collected during the monitoring period.

[0020] The construction unit fuses the winding temperature gradient ΔT and the motor insulation resistance RI to construct the insulation degradation index HI.

[0021] Optionally, the electrical safety monitoring module includes an electrical safety monitoring unit, which compares and analyzes the insulation degradation index HI and the electrical safety threshold IDI to determine the electrical safety status. If HI is less than or equal to IDI, the electrical safety monitoring unit determines that the electrical safety status is normal; otherwise, the electrical safety monitoring unit determines that the electrical safety status is an insulation aging risk status. The unit updates the construction process of the pressure status index by updating the preset pressure status index, setting the updated preset pressure status index as pc1, and setting the calculation formula of pc1 as pc1=pc0×exp[-(HI-IDI)].

[0022] Optionally, the equipment status monitoring module includes a status monitoring unit. When the coal slime load is normal, if L1×j1 / J+L2×j2 / J is less than or equal to the first equipment status threshold u1, the status monitoring unit determines that the equipment health status of the current management cycle is normal; otherwise, the status monitoring unit determines that the equipment health status of the current management cycle is abnormal. L1 is the structural weight, L2 is the electrical safety weight, L1+L2=1, j1 is the number of monitoring cycles in the management cycle where the equipment structural status is abnormal, j2 is the number of monitoring cycles where the electrical safety status is in the insulation aging risk state, and J is the number of monitoring cycles in the management cycle.

[0023] When the coal slime load is abnormal, if L1×j1 / J+L2×j2 / J is less than or equal to the second equipment status threshold u2, the status monitoring unit determines that the equipment health status of the current management cycle is normal; otherwise, the status monitoring unit determines that the equipment health status of the current management cycle is abnormal.

[0024] Optionally, the system further includes: a data acquisition module for acquiring equipment operating data and raw material parameters;

[0025] The coal slime characteristic analysis module is used to perform data fusion analysis on coal slime moisture content and particle size to construct a loading coefficient and determine the coal slime loading state based on the loading coefficient. The module constructs a loading coefficient LC based on the collected coal slime moisture content s0 and coal slime particle size d0, and compares the loading coefficient LC with a preset loading threshold LC0 to determine the coal slime loading state.

[0026] If LC is less than or equal to LC0, the coal slime characteristic analysis module determines that the coal slime load state is normal; otherwise, the coal slime characteristic analysis module determines that the coal slime load state is abnormal.

[0027] The beneficial effects of this invention are as follows: This system significantly improves the accuracy and reliability of health monitoring of coal preparation plant equipment through multi-source data fusion and dynamic threshold adjustment mechanisms. First, based on a load coefficient model of coal slime moisture content and particle size, it overcomes the limitations of traditional single-parameter threshold methods, enabling early identification of raw material overload risks and preventing equipment wear aggravation or efficiency decline due to abnormal loads. Second, the structural monitoring module employs joint analysis of wear rate and differential pressure, combining logarithmic functions and exponential formulas to enhance anomaly sensitivity and achieve early warning. The pressure monitoring module introduces dynamic calculation of over-limit ratios and fluctuation values, effectively identifying cylinder deformation or sealing failures, filling the blind spots of traditional structural monitoring. The electrical safety module, through the fusion analysis of insulation resistance and temperature gradient, can warn of potential aging risks through temperature surges when the motor insulation resistance has not reached a critical value, and adjust the pressure threshold accordingly, forming cross-module collaborative protection. Attached Figure Description

[0028] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0029] Figure 1 This is a schematic diagram of the structure of the machine learning-based coal preparation plant equipment health status monitoring system in this embodiment.

[0030] Figure 2 This is a schematic diagram of the structure monitoring module in this embodiment.

[0031] Figure 3 This is a schematic diagram of the electrical safety monitoring module in this embodiment.

[0032] Figure 4 This is a schematic diagram of the device status monitoring module in this embodiment. Detailed Implementation

[0033] To more clearly illustrate the present invention, the following description, in conjunction with preferred embodiments and accompanying drawings, further explains the invention. Similar components in the drawings are indicated by the same reference numerals. Those skilled in the art should understand that the specific description below is illustrative rather than restrictive and should not be construed as limiting the scope of protection of the present invention.

[0034] It should be noted that although the terms first, second, third, etc., may be used in the embodiments of this application for description, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of this application, first can also be referred to as second, and similarly, second can also be referred to as first.

[0035] Please see Figure 1 As shown, this is a schematic diagram of the structure of the machine learning-based coal preparation plant equipment health status monitoring system of this embodiment. The system includes,

[0036] The data acquisition module is used to collect equipment operating data and raw material parameters. The equipment operating data includes the thickness of the drum lining, screen pressure difference, cylinder pressure, motor insulation resistance, and winding temperature. The raw material parameters include the moisture content and particle size of the coal slime. It is understood that this embodiment does not specifically limit the acquisition method of equipment operating data and raw material parameters. Those skilled in the art can freely set it, as long as it meets the acquisition requirements of equipment operating data and raw material parameters. Specifically, a laser rangefinder or ultrasonic sensor can be installed on the inner wall of the drum to measure the lining wear thickness in real time. Differential pressure sensors can be installed at both ends of the screen to monitor the pressure difference before and after the screen. Pressure sensors can be deployed at key positions in the cylinder to collect pressure data in real time. An insulation resistance tester can be used to periodically or online monitor the insulation performance of the motor windings. A thermocouple or infrared temperature sensor can be embedded in the motor windings to collect temperature data in real time. A microwave moisture meter or drying method can be used in combination with online sensors to detect the moisture content of the coal slime in real time. A laser particle size analyzer or sieving method can be used to analyze the particle size of the coal slime sample.

[0037] Please continue reading. Figure 1 As shown, the system also includes:

[0038] The coal slime characteristic analysis module is connected to the data acquisition module to perform data fusion analysis on the coal slime moisture content and coal slime particle size in order to construct a load coefficient and determine the coal slime load status based on the load coefficient.

[0039] Specifically, the coal slime characteristic analysis module constructs the loading coefficient LC based on the collected coal slime moisture content s0 and coal slime particle size d0, and sets LC=w1×ln(s0 / s1+1)+w2×(d0 / d1) 1.5 w1 is the moisture content weight, w2 is the particle size weight, w1+w2=1, s1 is the preset moisture content, and d1 is the preset particle size.

[0040] The coal slime characteristic analysis module compares the load coefficient LC with the preset load threshold LC0 to determine the coal slime load status, wherein:

[0041] If LC is less than or equal to LC0, the coal slime characteristic analysis module determines that the coal slime load state is normal; otherwise, the coal slime characteristic analysis module determines that the coal slime load state is abnormal. By fusing multi-source data of moisture content and particle size, a load coefficient LC is constructed to realize dynamic load assessment. A logarithmic function is used to handle the nonlinear influence of moisture content, and an exponential function is used to enhance the abnormal response of particle size. Compared with the traditional single-parameter threshold method, the accuracy of coal slime load state analysis is improved.

[0042] Specifically, this embodiment does not impose specific limitations on the settings of each weight, preset moisture content, and preset particle size. Those skilled in the art can set them freely, as long as the setting requirements of each weight, preset moisture content, preset load threshold, and preset particle size are met. Among them, the optimal value of s1 is 0.2, the optimal value of d1 is 0.5mm, the optimal value of w1 is 0.6, the optimal value of w2 is 0.4, and the optimal value of LC0 is 0.8.

[0043] Please continue reading. Figure 1 As shown, the system also includes:

[0044] The structural monitoring module, connected to the coal slime characteristic analysis module, is used to jointly analyze the thickness of the equipment drum lining and the screen pressure difference collected during the monitoring period in order to construct a structural state index and determine the structural state of the equipment based on the structural state index.

[0045] Specifically, this embodiment does not impose specific limitations on the setting of the monitoring period. Those skilled in the art can set it freely, as long as the requirements for setting the monitoring period are met. The monitoring period can be set to 5 minutes.

[0046] Please see Figure 2 As shown, this is a schematic diagram of the structure monitoring module in this embodiment, including:

[0047] The wear analysis unit is used to calculate the wear rate Ms based on the drum liner thickness m0 and reference thickness m1 collected during the monitoring period. Ms is set to (m1-m0) / m1. The wear rate Ms is compared with the preset wear rate ms0 to determine the equipment wear status. A wear index is then constructed based on the equipment wear status, where:

[0048] If Ms is less than or equal to ms0, the wear analysis unit determines that the wear status of the equipment in the current monitoring cycle is normal and sets the wear index to MZ1, with MZ1=0. Conversely, if Ms is less than or equal to ms0, the wear analysis unit determines that the wear status of the equipment in the current monitoring cycle is abnormal and sets the wear index to MZ2, with MZ2=lg[(Ms-ms0)+1] / lg2. The wear rate calculation based on the change in lining thickness uses an indexation formula to enhance the sensitivity of abnormal wear. When the wear rate exceeds the threshold, the degree of abnormal wear is quantified, thereby improving the accuracy of structural health status monitoring.

[0049] Specifically, the reference thickness mentioned in this embodiment is the initial thickness of the inner lining of the equipment drum. This embodiment does not specifically limit the setting of the preset wear rate. Those skilled in the art can set it freely, as long as the setting requirements of the preset wear rate are met. The optimal value of ms0 is 0.05.

[0050] Please continue reading. Figure 2As shown, the structure monitoring module also includes:

[0051] The differential pressure analysis unit, connected to the wear analysis unit, compares and analyzes the screen differential pressure ΔP collected during the monitoring period with the preset differential pressure p1 to determine the equipment differential pressure status and constructs an equipment differential pressure index based on the equipment differential pressure status, wherein:

[0052] If ΔP is less than or equal to p1, the differential pressure analysis unit determines that the equipment differential pressure status is normal in the current monitoring cycle and sets the equipment differential pressure index to YC1, with YC1=0. Otherwise, the differential pressure analysis unit sets the equipment differential pressure index to YC2, with YC2=3×[(ΔP-p1) / (ΔP+p1)]. 2 -2×[(△P-p1) / (△P+p1)] 3 By combining preset thresholds with a nonlinear differential pressure response function, the system can accurately identify screen clogging trends. For example, when the screen is slightly clogged, the system can trigger an early warning to avoid sudden shutdown caused by complete clogging.

[0053] Specifically, this embodiment does not impose specific limitations on the setting of the preset pressure difference. Those skilled in the art can set it freely, as long as the setting requirements of the preset pressure difference are met. The optimal value of p1 is 0.2 MPa.

[0054] Please continue reading. Figure 2 As shown, the structure monitoring module also includes:

[0055] A structural condition determination unit, connected to the differential pressure analysis unit, is used to construct a structural condition index based on the wear index and the equipment differential pressure index, and to determine the structural condition of the equipment based on the structural condition index, wherein:

[0056] The structural state judgment unit sets the structural state index to ZY, and sets ZY=lg(3×wear index+1) / lg4×equipment pressure difference index;

[0057] The structural state judgment unit compares and analyzes the structural state index ZY and the preset state index zy to determine the structural state of the equipment. If ZY is less than or equal to zy, the structural state judgment unit determines that the structural state of the equipment in the current monitoring period is healthy and does not issue a structural health status warning to the user. Conversely, if ZY is less than or equal to zy, the structural state judgment unit determines that the structural state of the equipment in the current monitoring period is abnormal and issues a structural health status warning to the user. Through the joint analysis of the wear index and the differential pressure index, the health of the mechanical structure is comprehensively evaluated, resulting in higher detection efficiency for complex faults such as bearing damage and screen breakage.

[0058] Specifically, this embodiment does not impose specific limitations on the setting of the preset state index. Those skilled in the art can set it freely, as long as the setting requirements of the preset state index are met. The optimal value of zy is 0.342.

[0059] Please continue reading. Figure 1 As shown, the system also includes:

[0060] The pressure monitoring module, which is connected to the structure monitoring module, is used to compare and analyze the cylinder pressure collected during the monitoring period to determine the proportion of cylinder pressure exceeding the limit. The proportion of cylinder pressure exceeding the limit, the standard deviation of cylinder pressure, and the average value of cylinder pressure are jointly analyzed to construct a pressure state index and update the judgment of the equipment structure state.

[0061] Specifically, the pressure monitoring module compares and analyzes the i-th cylinder pressure Pi collected within the monitoring period with the preset cylinder pressure threshold p0 to determine whether the cylinder pressure exceeds the limit. If Pi is less than or equal to p0, the pressure monitoring module determines that the i-th cylinder pressure does not exceed the limit; otherwise, the pressure monitoring module determines that the i-th cylinder pressure exceeds the limit. The module also counts the number of cylinder pressures exceeding the limit, Pn, and sets the percentage of cylinder pressures exceeding the limit as β, where β is the ratio of Pn to Pu, and Pu is the number of cylinder pressures collected within the monitoring period.

[0062] The pressure monitoring module performs joint analysis on the percentage of cylinder pressure exceeding the limit β, the standard deviation of cylinder pressure σP, and the average cylinder pressure Pavg to construct the pressure state index PC, which is set as: PC = σP / Pavg × β;

[0063] If the equipment structure is in a healthy state during the current monitoring cycle, and the pressure state index PC is greater than or equal to the preset pressure state index pc0, then the equipment structure is determined to be in an abnormal state during the current monitoring cycle, and a structural health status warning is issued to the user. By introducing the joint calculation of the pressure over-limit ratio, average value and fluctuation value, the risk of abnormal cylinder pressure is quantified, which can effectively identify cylinder deformation or sealing failure and supplement the blind spots of structural status monitoring.

[0064] Specifically, this embodiment does not impose specific limitations on the setting of the preset cylinder pressure threshold and the preset pressure state index. Those skilled in the art can set them freely, as long as the setting requirements of the preset cylinder pressure threshold and the preset pressure state index are met. The optimal value of p0 is 1.1 times the rated cylinder pressure, and the optimal value of pc0 is 0.2.

[0065] Please continue reading. Figure 1 As shown, the system also includes:

[0066] An electrical safety monitoring module, connected to the pressure monitoring module, is used to fuse data of motor insulation resistance and winding temperature collected during the monitoring period to construct an insulation degradation index, and to determine the electrical safety status based on the insulation degradation index. It is also used to update the construction process of the pressure status index based on the electrical safety status.

[0067] Please see Figure 3 As shown, the electrical safety monitoring module includes:

[0068] A construction unit is used to calculate the winding temperature gradient ΔT based on the winding temperature collected during the monitoring period. The winding temperature gradient ΔT is the difference between the maximum and minimum winding temperature collected during the monitoring period.

[0069] The construction unit fuses winding temperature gradient ΔT and motor insulation resistance RI to construct an insulation degradation index HI. The formula for HI is HI=(RI / RM)×(1+0.05×ΔT / TY), where RM is the motor insulation resistance threshold and TY is the temperature difference threshold. The insulation degradation index (HI) is constructed through real-time calculation and analysis of the fusion of winding temperature gradient (ΔT) and insulation resistance (RI). This model overcomes the limitations of traditional single-threshold judgments. For example, when intermittent overload of the motor causes a sudden temperature rise, even if the insulation resistance has not reached the critical value, the HI index can still provide early warning through changes in the temperature gradient, avoiding accelerated insulation aging caused by temperature fluctuations.

[0070] Specifically, this embodiment does not impose specific limitations on the setting of the motor insulation resistance threshold and temperature difference threshold. Those skilled in the art can set them freely, as long as the setting requirements of the motor insulation resistance threshold and temperature difference threshold are met. The optimal value of RM is 1MΩ / kV, and the optimal value of TY is 50℃.

[0071] Please continue reading. Figure 3 As shown, the electrical safety monitoring module includes:

[0072] An electrical safety monitoring unit, connected to the building unit, compares and analyzes the insulation degradation index HI and the electrical safety threshold IDI to determine the electrical safety status. If HI is less than or equal to IDI, the electrical safety monitoring unit determines the electrical safety status to be normal; otherwise, it determines the electrical safety status to be at risk of insulation aging. The unit updates the construction process of the pressure status index by updating the preset pressure status index, setting the updated preset pressure status index as pc1, and setting the calculation formula of pc1 as pc1=pc0×exp[-(HI-IDI)]. By linking the HI index with the pressure monitoring module, the pressure status threshold is dynamically adjusted when insulation degradation is detected, avoiding the risk of mechanical overload indirectly caused by electrical abnormalities.

[0073] Specifically, this embodiment does not impose specific limitations on the setting of the electrical safety threshold. Those skilled in the art can set it freely, as long as the setting requirements of the electrical safety threshold are met. The optimal value of IDI is 0.8.

[0074] Please continue reading. Figure 1 As shown, the system also includes:

[0075] The equipment status monitoring module is connected to the electrical safety monitoring module. It is used to determine the health status of the equipment based on the coal slime load status, equipment structure status and electrical safety status within the management cycle, and output equipment maintenance prompts to the user based on the determination results of the equipment health status.

[0076] Specifically, this embodiment does not impose specific limitations on the setting of the management cycle. Those skilled in the art can set it freely, as long as the setting requirements of the management cycle are met. The management cycle can be set to 2 hours.

[0077] Please see Figure 4 As shown, the equipment status monitoring module includes:

[0078] The condition monitoring unit is used to determine the health status of the equipment based on the coal slime load status, equipment structure status, and electrical safety status during the management cycle.

[0079] Specifically, when the coal slime load is normal, if L1×j1 / J+L2×j2 / J is less than or equal to the first equipment status threshold u1, the status monitoring unit determines that the equipment health status of the current management cycle is normal; otherwise, the status monitoring unit determines that the equipment health status of the current management cycle is abnormal. L1 is the structural weight, L2 is the electrical safety weight, L1+L2=1, j1 is the number of monitoring cycles in the management cycle where the equipment structural status is abnormal, j2 is the number of monitoring cycles where the electrical safety status is insulation aging risk, and J is the number of monitoring cycles in the management cycle.

[0080] When the coal slime load condition is abnormal, if L1×j1 / J+L2×j2 / J is less than or equal to the second equipment status threshold u2, the status monitoring unit determines that the equipment health status of the current management cycle is normal; otherwise, the status monitoring unit determines that the equipment health status of the current management cycle is abnormal. By integrating real-time data from multiple dimensions such as mechanical load, structural wear, and electrical parameters (e.g., vibration, temperature, insulation index), a comprehensive health assessment model is established to improve the efficiency of equipment health status monitoring.

[0081] Specifically, this embodiment does not impose specific limitations on the settings of each weight and each state threshold. Those skilled in the art can set them freely, as long as the setting requirements of each weight and each state threshold are met. Among them, the optimal value of L1 is 0.7, the optimal value of L2 is 0.3, the optimal value of u1 is 0.3, and the optimal value of u2 is 0.26.

[0082] Please continue reading. Figure 4 As shown, the equipment status monitoring module also includes,

[0083] An output unit, connected to the status monitoring unit, is used to output a device maintenance prompt to the user when the device's health status is abnormal.

[0084] Specifically, in an exemplary application scenario, during equipment monitoring at a coal preparation plant, the data acquisition module collects equipment operating data: the current thickness is measured to be 47 mm (initial thickness is 50 mm) by an ultrasonic sensor; the differential pressure sensor displays a real-time pressure difference of 0.3 MPa across the screen; data collected by five pressure sensors are 0.9 MPa, 1.2 MPa, 1.3 MPa, 0.8 MPa, and 1.1 MPa (rated pressure is 1.0 MPa, trigger threshold is 1.1 times the rated value); motor parameters: the insulation resistance tester displays an insulation resistance of 0.9 MΩ / kV (rated threshold 1 MΩ / kV), and the thermocouple measures a winding temperature that rises from 35℃ to 90℃ within 5 minutes; raw material parameters are collected: the online microwave moisture meter detects a moisture content of 30% (preset threshold 20%); the laser particle size analyzer detects a particle size of 0.8 mm (preset threshold 0.5 mm).

[0085] The coal slime characteristic analysis module inputs the coal slime moisture content (30%) and particle size (0.8 mm) into the load model. Through weighted fusion analysis (moisture content weight 60%, particle size weight 40%), the load coefficient is calculated to be 1.358, which is significantly higher than the preset threshold of 0.8, and the coal slime load is determined to be abnormal.

[0086] The structural monitoring module assesses drum wear: the current lining thickness (47 mm) has decreased by 6% compared to the initial value (50 mm), exceeding the preset wear rate threshold of 5%. The system confirms an abnormal wear trend through wear index calculation.

[0087] Screen pressure differential risk assessment: When the screen pressure differential (0.3 MPa) exceeds the safety threshold (0.2 MPa), the pressure differential index formula analysis is triggered, and it is determined that there is a risk of screen blockage (the index is biased towards the warning range).

[0088] Structural health assessment: Based on the combined wear index and differential pressure index, the structural condition index is 0.003, which is far below the health threshold (0.342). The system maintains the "normal structural condition" assessment.

[0089] The pressure monitoring module analyzed the pressure exceeding limits: three pressure exceeding limits (1.2 MPa, 1.3 MPa, 1.1 MPa) occurred within 5 minutes, accounting for 60% of the total, with a pressure fluctuation standard deviation of 0.18 MPa, and generated a pressure state index of 0.101 (threshold 0.2), without triggering an alarm.

[0090] Correction for linked electrical safety: Due to insulation degradation detected by the electrical module, the system dynamically adjusted the pressure warning threshold to 0.171. After the update, the pressure index remains below the threshold, maintaining normal judgment.

[0091] The electrical safety module performs a combined analysis of temperature and insulation. The winding temperature spiked by 55°C within 5 minutes, and the insulation resistance (0.9 MΩ / kV) did not reach the safety threshold.

[0092] The system generates an insulation degradation index of 0.949 (threshold 0.8), which indicates the risk of insulation aging.

[0093] Global impact: Dynamically lowers the pressure warning threshold, enhancing sensitivity to the pressure-bearing state of the cylinder;

[0094] Summary of the comprehensive health decision management cycle (2 hours) of the equipment status monitoring module:

[0095] Coal slime load status: 20 load anomalies (83%) within 24 monitoring cycles; structural anomalies: 8 instances of wear or differential pressure exceeding the standard (33%); electrical anomalies: 15 insulation degradation warnings (62%).

[0096] Health assessment logic:

[0097] Weighting: Structural health 70%, electrical safety 30%.

[0098] Overall score: 0.421 (threshold 0.26), significantly exceeding the safe range;

[0099] System output: Push maintenance command: "Equipment health status is abnormal, priority suggestions: ① Coal slime dewatering treatment; ② Check screen blockage and drum wear; ③ Retest motor insulation."

[0100] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the implementation of the present invention. For those skilled in the art, other variations or modifications can be made based on the above description. It is impossible to exhaustively list all the implementation methods here. All obvious variations or modifications derived from the technical solutions of the present invention are still within the protection scope of the present invention.

Claims

1. A machine learning-based health status monitoring system for coal preparation plant equipment, characterized in that, include: The structural monitoring module is used to jointly analyze the thickness of the equipment drum lining and the screen pressure difference collected during the monitoring period in order to construct a structural status index and judge the structural status of the equipment based on the structural status index. The pressure monitoring module is used to perform joint analysis on cylinder pressure, cylinder pressure standard deviation and cylinder pressure average value to construct a pressure state index and update the judgment of equipment structural status. The equipment status monitoring module is used to determine the health status of the equipment based on the coal slime load status, equipment structure status, and electrical safety status within the management cycle, and to output equipment maintenance prompts to the user based on the determination results of the equipment health status.

2. The machine learning-based coal preparation plant equipment health status monitoring system according to claim 1, characterized in that, The structural monitoring module includes a wear analysis unit, which is used to calculate the wear rate Ms based on the equipment drum liner thickness m0 and reference thickness m1 collected during the monitoring period, and compare the wear rate Ms with the preset wear rate ms0 to determine the equipment wear status, and construct a wear index based on the equipment wear status.

3. The machine learning-based coal preparation plant equipment health status monitoring system according to claim 2, characterized in that, The structural monitoring module also includes a differential pressure analysis unit, used to compare and analyze the screen differential pressure ΔP collected during the monitoring period with the preset differential pressure p1 to determine the equipment differential pressure status, and to construct an equipment differential pressure index based on the equipment differential pressure status, wherein: If ΔP is less than or equal to p1, the differential pressure analysis unit determines that the equipment differential pressure status is normal in the current monitoring cycle and sets the equipment differential pressure index to YC1, with YC1=0. Otherwise, the differential pressure analysis unit sets the equipment differential pressure index to YC2, with YC2=3×[(ΔP-p1) / (ΔP+p1)]. 2 -2×[(△P-p1) / (△P+p1)] 3 .

4. The machine learning-based coal preparation plant equipment health status monitoring system according to claim 3, characterized in that, The structural monitoring module also includes a structural state judgment unit, which is used to construct a structural state index ZY based on the wear index and the equipment pressure difference index, and set ZY=lg(3×wear index+1) / lg4×equipment pressure difference index; The structural state judgment unit compares and analyzes the structural state index ZY and the preset state index zy to determine the structural state of the equipment. If ZY is less than or equal to zy, the structural state judgment unit determines that the structural state of the equipment in the current monitoring period is healthy and does not issue a structural health status warning to the user. Conversely, the structural state judgment unit determines that the structural state of the equipment in the current monitoring period is abnormal and issues a structural health status warning to the user.

5. The machine learning-based coal preparation plant equipment health status monitoring system according to claim 4, characterized in that, The pressure monitoring module compares and analyzes the i-th cylinder pressure Pi collected within the monitoring period with the preset cylinder pressure threshold p0 to determine whether the cylinder pressure exceeds the limit. If Pi is less than or equal to p0, the pressure monitoring module determines that the i-th cylinder pressure does not exceed the limit; otherwise, the pressure monitoring module determines that the i-th cylinder pressure exceeds the limit. The module also counts the number of cylinder pressure exceeding the limit, Pn, and sets the proportion of cylinder pressure exceeding the limit as β, where β is the ratio of Pn to Pu, and Pu is the number of cylinder pressures collected within the monitoring period. The pressure monitoring module performs joint analysis on the percentage of cylinder pressure exceeding the limit β, the standard deviation of cylinder pressure σP, and the average cylinder pressure Pavg to construct the pressure state index PC, which is set as: PC = σP / Pavg × β; If the equipment structure is in a healthy state during the current monitoring period, and the pressure state index PC is greater than or equal to the preset pressure state index pc0, then the equipment structure is determined to be in an abnormal state during the current monitoring period, and a structural health status warning is issued to the user.

6. The machine learning-based coal preparation plant equipment health status monitoring system according to claim 5, characterized in that, The system also includes an electrical safety monitoring module, which is used to fuse the motor insulation resistance and winding temperature collected during the monitoring period to construct an insulation degradation index, and to determine the electrical safety status based on the insulation degradation index. It is also used to update the construction process of the pressure status index based on the electrical safety status.

7. The machine learning-based health status monitoring system for coal preparation plant equipment according to claim 6, characterized in that, The electrical safety monitoring module includes a construction unit for calculating the winding temperature gradient ΔT based on the winding temperature collected during the monitoring period. The winding temperature gradient ΔT is the difference between the maximum and minimum winding temperature collected during the monitoring period. The construction unit fuses the winding temperature gradient ΔT and the motor insulation resistance RI to construct the insulation degradation index HI.

8. The machine learning-based health status monitoring system for coal preparation plant equipment according to claim 7, characterized in that, The electrical safety monitoring module includes an electrical safety monitoring unit, which compares and analyzes the insulation degradation index HI and the electrical safety threshold IDI to determine the electrical safety status. If HI is less than or equal to IDI, the electrical safety monitoring unit determines that the electrical safety status is normal; otherwise, the electrical safety monitoring unit determines that the electrical safety status is an insulation aging risk state. The module also updates the construction process of the pressure status index by updating the preset pressure status index. The updated preset pressure status index is set as pc1, and the calculation formula of pc1 is set as pc1=pc0×exp[-(HI-IDI)].

9. The machine learning-based health status monitoring system for coal preparation plant equipment according to claim 8, characterized in that, The equipment status monitoring module includes a status monitoring unit. When the coal slime load is normal, if L1×j1 / J+L2×j2 / J is less than or equal to the first equipment status threshold u1, the status monitoring unit determines that the equipment health status of the current management cycle is normal. Otherwise, the status monitoring unit determines that the equipment health status of the current management cycle is abnormal. L1 is the structural weight, L2 is the electrical safety weight, L1+L2=1, j1 is the number of monitoring cycles in the management cycle where the equipment structural status is abnormal, j2 is the number of monitoring cycles where the electrical safety status is insulation aging risk, and J is the number of monitoring cycles in the management cycle. When the coal slime load is abnormal, if L1×j1 / J+L2×j2 / J is less than or equal to the second equipment status threshold u2, the status monitoring unit determines that the equipment health status of the current management cycle is normal; otherwise, the status monitoring unit determines that the equipment health status of the current management cycle is abnormal.

10. The machine learning-based health status monitoring system for coal preparation plant equipment according to claim 9, characterized in that, The system also includes: a data acquisition module for collecting equipment operating data and raw material parameters; The coal slime characteristic analysis module is used to perform data fusion analysis on coal slime moisture content and particle size to construct a loading coefficient and determine the coal slime loading state based on the loading coefficient. The module constructs a loading coefficient LC based on the collected coal slime moisture content s0 and coal slime particle size d0, and compares the loading coefficient LC with a preset loading threshold LC0 to determine the coal slime loading state. If LC is less than or equal to LC0, the coal slime characteristic analysis module determines that the coal slime load state is normal; otherwise, the coal slime characteristic analysis module determines that the coal slime load state is abnormal.

Images