A fault determination method, device and equipment for a crushing and screening integrated machine

Abstract

The application provides a fault determination method, device and equipment for a crushing and screening integrated machine, which comprises the following steps: obtaining real-time operation parameter data and current preset operation parameters of a target crushing and screening integrated machine; preprocessing the real-time operation parameter data to obtain target real-time operation parameter data; determining a dynamic threshold corresponding to each real-time operation parameter according to the current preset operation parameters, a preset basic threshold library and the cumulative running time of the target crushing and screening integrated machine; performing time sequence feature extraction and multi-time window trend analysis on the target real-time operation parameter data to obtain a parameter change trend of each real-time operation parameter; and obtaining a basic fault determination result according to the target real-time operation parameter data, the dynamic threshold, the parameter change trend of each real-time operation parameter and a preset fault determination rule. The scheme of the application can efficiently and accurately determine the fault of the crushing and screening integrated machine, and meet the requirements of soil tests on soil samples.

Description

Technical Field

[0001] This invention relates to the field of engineering survey technology, and in particular to a method, device and equipment for diagnosing faults in an integrated crushing and vibrating screen machine. Background Technology

[0002] In the field of soil testing, the integrated crushing and sieving machine is the core equipment for realizing soil sample crushing, sieving, and coarse material reprocessing. Its operational stability directly determines the soil sample processing efficiency and the accuracy of test data, while fault diagnosis is a key link to ensure stable operation of the equipment. Currently, the fault diagnosis technology for existing integrated crushing and sieving machines still has many defects and shortcomings, making it difficult to adapt to the actual needs of multi-component collaboration, dynamic changes in operating conditions, and complex fault types in soil processing. Specific technical problems are as follows: Fault determination relies on a single dimension and static judgment based on fixed thresholds. Existing equipment often uses fixed thresholds for a single electrical or mechanical parameter as the basis for fault determination. For example, overload is judged only by fixed values ​​of motor current and load torque, and overcurrent is judged only by circuit current threshold. It does not integrate multi-dimensional information such as temperature, speed, time trend, and component linkage status. It is easy to make misjudgments or omissions due to changes in soil material characteristics and adjustments to equipment operating conditions.

[0003] Without multi-level time window time series analysis, there is a lack of ability to predict fault precursors; existing fault judgment only performs instantaneous static detection of real-time parameters, which cannot capture the characteristics of gradual and sudden changes in parameters before the fault occurs. It can only respond passively after the fault becomes apparent, without the ability to provide early warning. As a result, when the fault occurs, it has already caused wear and tear on equipment parts, accumulation of materials, and even triggered subsequent chain failures, increasing equipment maintenance costs and soil sample processing losses.

[0004] Complex faults lack causal relationship determination, making root cause location difficult. During equipment operation, complex fault scenarios involving multiple interconnected faults are prone to occur, such as material jamming in the crushing chamber causing motor overload, which in turn leads to overcurrent in the branch circuit. However, existing technologies cannot determine the causal relationship between individual faults, treating root cause faults and derivative faults equally, making it impossible to accurately locate the source of the fault. Maintenance personnel need to check all fault points one by one, significantly extending the fault diagnosis time, and the failure to resolve the root cause fault can easily lead to repeated faults.

[0005] The aforementioned problems result in low accuracy, timeliness, and intelligence in fault diagnosis of existing integrated crushing and vibrating screen machines, limiting the stability of equipment operation and the efficiency of automated operation, making it difficult to meet the needs of soil testing for continuous, efficient, and precise soil sample processing. Summary of the Invention

[0006] This invention provides a method, device, and equipment for fault diagnosis of an integrated crushing and vibrating screen machine, which can efficiently and accurately diagnose faults in the integrated crushing and vibrating screen machine and meet the requirements of soil tests for soil samples.

[0007] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows: A fault diagnosis method for an integrated crushing and vibrating screen machine includes: Obtain real-time operating parameter data and current preset operating parameters of the target crushing and vibrating screen integrated machine; The real-time operating parameter data is preprocessed to obtain the target real-time operating parameter data; Based on the current preset operating parameters and the preset basic threshold library, as well as the cumulative running time of the target crushing and vibrating screen integrated machine, determine the dynamic threshold corresponding to each real-time operating parameter; The time-series features of the target real-time operating parameter data are extracted and multi-time window trend analysis is performed to obtain the parameter change trend of each real-time operating parameter in different time windows; Based on the target's real-time operating parameter data, dynamic thresholds, and the parameter change trend of each real-time operating parameter in different time windows, as well as the preset fault judgment rules, the target crushing and vibrating screen integrated machine is subjected to various basic fault judgments to obtain the basic fault judgment results. Based on the basic fault determination results, perform composite fault correlation reasoning to determine the composite fault level and root cause fault. The basic fault determination results and composite faults are filtered for false faults to obtain the fault determination results of the target crushing and vibrating screen integrated machine.

[0008] Optionally, based on the current preset operating parameters, the preset basic threshold library, and the cumulative running time of the target crushing and vibrating screen integrated machine, a dynamic threshold corresponding to each real-time operating parameter is determined, including: Based on the current preset operating parameters, the real-time operating conditions are determined, and the baseline thresholds of each real-time operating parameter in the basic threshold database are corrected according to the real-time operating conditions to obtain the preliminary corrected thresholds. Based on the cumulative running time of the target crushing and vibrating screen integrated machine, the preliminary correction threshold is compensated to obtain the dynamic threshold corresponding to each real-time operating parameter.

[0009] Optionally, time-series feature extraction and multi-time-window trend analysis are performed on the target real-time operating parameter data to obtain the parameter change trend of each real-time operating parameter in different time windows, including: Based on the changing characteristics of the real-time operating parameters, time windows of the first, second, and third levels are determined, and the lengths of the time windows of the first, second, and third levels are different. Temporal features are extracted from the real-time operating parameter data of the target within the time windows of the first, second and third levels, respectively. The temporal features include: mean, dispersion, rate of change, degree of abrupt change and deviation duration. Based on the time-series features extracted within the time windows of the first, second, and third levels, parameter change trend analysis is performed to obtain the parameter change trend of each real-time operating parameter in different time windows.

[0010] Optionally, based on the target's real-time operating parameter data, dynamic thresholds, and the parameter change trends of each real-time operating parameter in different time windows, as well as preset fault judgment rules, various basic fault judgments are performed on the target crushing and vibrating screen integrated machine to obtain basic fault judgment results, including: The real-time operating parameter data of the target is compared with the dynamic threshold. The parameter change trend of the real-time operating parameters within the time window of the first, second or third level, and the preset fault judgment rules are combined to make fault judgments on the target crushing and vibrating screen integrated machine in different dimensions, and obtain fault judgment results in different dimensions. Based on the fault judgment results of different dimensions, confidence level calculation is performed to obtain the overload fault judgment results, material jamming fault judgment results, and overcurrent fault judgment results of the target crushing and vibrating screen integrated machine.

[0011] Optionally, confidence levels are calculated based on the fault determination results from different dimensions to obtain the overload fault determination results, material jamming fault determination results, and overcurrent fault determination results for the target crushing and vibrating screen integrated machine, including: Based on the fault determination results of different dimensions, the fault scores of different dimensions are multiplied by a preset weight value to obtain the confidence level; Based on the confidence level value, the overload fault determination results, material jamming fault determination results, and overcurrent fault determination results of the target crushing and vibrating screen integrated machine are obtained.

[0012] Optionally, based on the basic fault determination results, composite fault correlation reasoning is performed to determine the composite fault level and root cause fault, including: Based on the basic fault determination results, when the number of basic faults is greater than or equal to 2, the causal relationship of each basic fault is determined based on the typical compound fault causal relationship pre-stored in the preset fault association rule base, as well as the occurrence time and parameter abnormal start time of each basic fault. Based on the causal relationships of the aforementioned basic faults, suspected root cause faults are preliminarily identified; The root cause confidence of the suspected root cause failure is calculated to obtain the root cause confidence of the suspected root cause failure. Based on the root cause confidence level, determine the composite fault level and the root cause fault.

[0013] Optionally, false fault filtering is performed on the basic fault determination results and composite faults to obtain the fault determination results of the target crushing and vibrating screen integrated machine, including: Based on the target's real-time operating parameter data, when the data of consecutive target frames in the target's real-time operating parameter data recovers to the normal range and no derivative fault characteristics occur, the basic fault determination result is determined to be a false fault. Based on the root cause confidence of the root cause fault in the composite fault, when the root cause confidence drops to the target value, the composite fault is determined to be a false composite fault. Based on the filtering results that eliminate false faults and false compound faults, the fault determination results of the target crushing and vibrating screen integrated machine are obtained.

[0014] The present invention also provides a fault determination device for an integrated crushing and vibrating screen machine, comprising: The acquisition module is used to acquire real-time operating parameter data and current preset operating parameters of the target crushing and vibrating screen integrated machine; The processing module is used to preprocess the real-time operating parameter data to obtain target real-time operating parameter data; determine the dynamic threshold corresponding to each real-time operating parameter based on the current preset operating parameters, the preset basic threshold library, and the cumulative running time of the target crushing and vibrating screen integrated machine; perform time-series feature extraction and multi-time-window trend analysis on the target real-time operating parameter data to obtain the parameter change trend of each real-time operating parameter in different time windows; perform various basic fault judgments on the target crushing and vibrating screen integrated machine based on the target real-time operating parameter data, dynamic thresholds, and parameter change trends of each real-time operating parameter in different time windows, as well as preset fault judgment rules, to obtain basic fault judgment results; perform composite fault association reasoning based on the basic fault judgment results to determine the composite fault level and root cause fault; and perform false fault filtering on the basic fault judgment results and composite faults to obtain the fault judgment result of the target crushing and vibrating screen integrated machine.

[0015] The present invention also provides a computing device, comprising: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method described above.

[0016] The present invention also provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the method described above.

[0017] The above-described solution of the present invention has at least the following beneficial effects: The above-described solution of the present invention acquires real-time operating parameter data and current preset operating parameters of the target crushing and vibrating screen integrated machine; preprocesses the real-time operating parameter data to obtain target real-time operating parameter data; determines the dynamic threshold corresponding to each real-time operating parameter based on the current preset operating parameters, a preset basic threshold library, and the cumulative running time of the target crushing and vibrating screen integrated machine; performs time-series feature extraction and multi-time-window trend analysis on the target real-time operating parameter data to obtain the parameter change trend of each real-time operating parameter in different time windows; performs multiple basic fault judgments on the target crushing and vibrating screen integrated machine based on the target real-time operating parameter data, dynamic thresholds, parameter change trends of each real-time operating parameter in different time windows, and preset fault judgment rules to obtain basic fault judgment results; performs composite fault association reasoning based on the basic fault judgment results to determine the composite fault level and root cause fault; and filters false faults from the basic fault judgment results and composite faults to obtain the fault judgment result of the target crushing and vibrating screen integrated machine. This allows for efficient and accurate fault judgment of the crushing and vibrating screen integrated machine, meeting the requirements of soil tests for soil samples. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating the fault determination method for the integrated crushing and vibrating screen machine according to an embodiment of the present invention. Figure 2 This is a structural diagram of the fault determination device for the integrated crushing and vibrating screen machine according to an embodiment of the present invention. Detailed Implementation

[0019] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0020] like Figure 1 As shown, an embodiment of the present invention proposes a fault determination method for an integrated crushing and vibrating screen machine, including: Step 11: Obtain the real-time operating parameter data and current preset operating parameters of the target crushing and vibrating screen integrated machine; Here, during equipment operation, the signal acquisition module collects real-time operating parameter data of each core component of the equipment at a high-frequency acquisition cycle. This real-time operating parameter data includes mechanical operating parameter data and electrical operating parameter data. The mechanical operating parameter data includes: real-time load torque of the crushing roller motor, fluctuation rate of the feeding roller speed of the feeding assembly, operating current of the vibrating screen assembly exciter, speed of the return assembly conveyor motor, and vibration amplitude of each transmission part. The electrical operating parameter data includes: real-time operating current, voltage, and power factor of the control circuits of the crushing assembly, feeding assembly, vibrating screen assembly, and return assembly, as well as the main circuit of the equipment; winding temperature of each motor; and inverter output frequency. The currently preset operating parameters are the operating parameters of the target crushing and vibrating screen integrated machine set by the operator for the current working condition, including feeding speed, crushing roller speed, and vibration frequency.

[0021] Step 12: Preprocess the real-time operating parameter data to obtain the target real-time operating parameter data; Here, the real-time operating parameter data acquired by the signal acquisition module is uploaded to the control module via the communication module. It first enters the parameter preprocessing unit for noise reduction, normalization, and completion processing to eliminate signal interference and data errors during the acquisition process, providing accurate basic data for subsequent judgment. The preprocessing process includes: Noise filtering: The Kalman filter algorithm is used to filter dynamic fluctuation parameters such as motor speed, load torque, and circuit current, eliminating random noise caused by electromagnetic interference and mechanical vibration, and retaining the true trend of parameter changes. Normalization processing normalizes parameters with different dimensions and numerical ranges to the 0 to 1 interval, enabling multi-parameter fusion and comparative analysis. Missing data completion: For single-frame data loss caused by momentary interference during data acquisition, adjacent frame data interpolation is used to complete the data, thus avoiding interruption or misjudgment caused by missing data. Outlier removal: Based on the preset reasonable threshold for parameter mutation, extreme outliers that exceed the reasonable mutation range (such as the current momentarily dropping to 0 due to a data acquisition failure) are marked and removed, and are determined to be data acquisition failures rather than equipment operation failures.

[0022] Step 13: Based on the current preset operating parameters, the preset basic threshold library, and the cumulative running time of the target crushing and vibrating screen integrated machine, determine the dynamic threshold corresponding to each real-time operating parameter; Here, based on the real-time operating status of the equipment, the characteristics of the processed soil sample, and historical operation data, dynamic thresholds for the parameters of each component are generated by fitting and correcting the historical data. These dynamic thresholds are dynamically adjusted as the equipment operates to adapt to the fault determination requirements under different working conditions, thus avoiding the problem of "false alarms under low working conditions and missed determinations under high working conditions" caused by fixed thresholds.

[0023] Step 14: Extract time-series features and perform multi-time-window trend analysis on the target real-time operating parameter data to obtain the parameter change trend of each real-time operating parameter in different time windows; Here, since there are time-series characteristics of gradual or sudden parameter changes before equipment failure occurs, the control module extracts time-series features from the preprocessed target real-time operating parameter data, analyzes the changing trends of parameters within multiple time windows, captures fault precursor features, and achieves advanced fault prediction, rather than just making static judgments on the current parameters.

[0024] Step 15: Based on the target real-time operating parameter data, dynamic thresholds, and parameter change trends of each real-time operating parameter in different time windows, as well as the preset fault judgment rules, perform various basic fault judgments on the target crushing and vibrating screen integrated machine to obtain the basic fault judgment results. Here, the control module uses preprocessed target real-time operating parameter data, dynamic thresholds, and extracted parameter change trends, combined with preset fault judgment rules, to perform multi-dimensional judgment on three basic faults: overload, material jamming, and overcurrent. At the same time, a fault judgment confidence assessment is introduced. Only when the confidence is greater than or equal to 90% is it initially judged as a real fault, and if it is less than 90%, it is marked as a "suspected fault" and monitoring is strengthened.

[0025] Step 16: Based on the basic fault determination results, perform composite fault correlation reasoning to determine the composite fault level and root cause fault; Here, when the control module detects that the confidence level of two or more basic faults is greater than or equal to 70%, it activates the composite fault association reasoning unit. Based on the built-in fault association rule base (built from equipment operating mechanisms and historical fault data), it analyzes the causal relationship between each individual fault, realizes the root cause localization of composite faults, avoids confusion between "root cause faults" and "derived faults," and provides accurate basis for subsequent targeted shutdowns and fault troubleshooting. Step 17: Perform false fault filtering on the basic fault determination results and composite faults to obtain the fault determination results of the target crushing and vibrating screen integrated machine.

[0026] Here, to avoid false fault determinations caused by sudden changes in material properties, brief power supply fluctuations, or instantaneous sensor interference, the control module is equipped with a false fault filtering unit and a suspected fault continuous monitoring unit to achieve accurate triggering of real faults, effective filtering of false faults, and focused tracking of suspected faults.

[0027] The fault determination method for the integrated crushing and vibrating screen machine in this embodiment is based on multi-dimensional parameter fusion perception, dynamic threshold self-adaptation, temporal feature analysis, and fault correlation reasoning. It breaks through the limitations of traditional fixed threshold single determination. It is executed by the fault intelligent determination unit built into the control module. It integrates four dimensions of information: real-time collected parameters, equipment operation sequence, historical operation data, and soil material characteristics. It achieves high-level determination effects such as accurate identification of single faults, advanced prediction of fault precursors, root cause location of compound faults, and effective elimination of false faults. The determination process is divided into basic parameter preprocessing, dynamic threshold generation, temporal feature extraction, multi-dimensional fusion determination, fault root cause tracing, and false fault filtering. Each step is executed in conjunction with the other. It also has a built-in fault determination confidence assessment mechanism. Only when the confidence level is greater than or equal to 90% will subsequent alarm and shutdown actions be triggered to ensure the accuracy and reliability of the determination results.

[0028] In an optional embodiment of the present invention, step 13, determining the dynamic threshold corresponding to each real-time operating parameter based on the current preset operating parameters, the preset basic threshold library, and the cumulative running time of the target crushing and vibrating screen integrated machine, may include: Step 131: Determine the real-time operating conditions based on the current preset operating parameters, and correct the baseline threshold of each real-time operating parameter in the basic threshold database based on the real-time operating conditions to obtain the preliminary corrected threshold. Here, the basic threshold database pre-stores benchmark thresholds for various component parameters corresponding to different soil types (clay, sandy soil, silt, etc.) and different processing particle size requirements. After the test personnel set the soil sample type, the control module automatically retrieves the corresponding benchmark threshold. Based on the current preset operating parameters of the equipment, the benchmark threshold is linearly corrected. For example, if the feed speed is increased by 20% in the preset operating parameters, the initial correction threshold for the load torque of the crushing roller motor will be increased by 15% simultaneously.

[0029] Step 132: Based on the cumulative running time of the target crushing and vibrating screen integrated machine, compensate the preliminary correction threshold to obtain the dynamic threshold corresponding to each real-time operating parameter.

[0030] Here, the initial correction threshold is compensated in real time for factors such as mechanical wear and temperature rise during equipment operation. For example, after the equipment has been running for 1 hour, the initial correction threshold for motor winding temperature is dynamically adjusted upward with the ambient temperature and motor temperature rise to avoid triggering false alarms due to normal temperature rise.

[0031] In an optional embodiment of the present invention, step 14, which involves extracting time-series features and performing multi-time-window trend analysis on the target real-time operating parameter data to obtain the parameter change trend of each real-time operating parameter in different time windows, may include: Step 141: Based on the change characteristics of the real-time operating parameters, determine the time windows of the first level, the second level, and the third level, wherein the lengths of the time windows of the first level, the second level, and the third level are different. Here, the first-level time window corresponds to a short window with a duration of 1 second and contains 10 frames of acquired data; the second-level time window corresponds to a medium window with a duration of 5 seconds and contains 50 frames of acquired data; and the third-level time window corresponds to a long window with a duration of 30 seconds and contains 300 frames of acquired data. The first, second, and third-level time windows respectively correspond to the instantaneous changes, short-term trends, and long-term trends of the parameters.

[0032] Step 142: Extract time series features from the real-time target operation parameter data within the time windows of the first, second, and third levels, respectively. The time series features include: mean, dispersion, rate of change, degree of abrupt change, and deviation duration. Here, the control module precisely extracts five core time-series features from the preprocessed parameters within each time window. It quantifies parameter change characteristics from multiple dimensions—mean, dispersion, rate of change, degree of abrupt change, and duration of deviation—providing a quantitative basis for trend determination. By extracting the mean, it characterizes the overall operational level of the parameters within the window; by extracting dispersion, it characterizes the degree of discrete fluctuation of the parameters within the window; by extracting the rate of change, it characterizes the continuous rate of change of the parameters within the window; by extracting the degree of abrupt change, it characterizes the instantaneous magnitude of abrupt changes of the parameters within the window; and by extracting the duration of deviation, it characterizes the proportion of time the parameters within the window exceed the normal threshold range.

[0033] Step 143: Based on the time series features extracted within the time windows of the first, second, and third levels, perform parameter change trend analysis to obtain the parameter change trend of each real-time running parameter in different time windows.

[0034] Here, the control module, based on the time-series features extracted within each time window and combined with preset feature thresholds, uniformly categorizes the changing trends of all parameters into four levels: stable, slow deviation, rapid deviation, and abrupt change. For example, if the slope of the load torque of the crushing roller motor in the second-level time window is greater than a preset value, it can be determined as "torque showing a rapid deviation trend"; if the change rate of the circuit current in the first-level time window is greater than a preset value, it can be determined as "current abrupt change".

[0035] Furthermore, a direct correlation is established between trend levels and fault precursor warning levels, as well as the determination of explicit faults, to achieve seamless integration between trend determination and fault response. When the parameter change trend is stable, it is determined that the equipment has no fault precursors and monitoring continues under normal operating conditions; when the parameter change trend deviates slowly, it is determined that the equipment has minor fault precursors, triggering a Level 1 precursor warning and initiating high-frequency parameter monitoring; when the parameter change trend deviates rapidly, it is determined that the equipment has obvious fault precursors, triggering a Level 2 precursor warning, strengthening parameter trend tracking and preparing for fault response; when the parameter change trend changes abruptly, it is determined that the equipment has exhibited direct characteristics of an explicit fault, bypassing the precursor warning stage and directly entering the explicit fault determination stage, simultaneously triggering subsequent alarm and shutdown actions.

[0036] In an optional embodiment of the present invention, in step 15, based on the target real-time operating parameter data, dynamic thresholds, and parameter change trends of each real-time operating parameter in different time windows, as well as preset fault judgment rules, various basic fault judgments are performed on the target crushing and vibrating screen integrated machine to obtain basic fault judgment results, which may include: Step 151: Compare the real-time operating parameter data of the target with the dynamic threshold, and combine the parameter change trend of the real-time operating parameters within the time window of the first, second or third level, as well as the preset fault judgment rules, to perform fault judgment on the target crushing and vibrating screen integrated machine in different dimensions and obtain fault judgment results in different dimensions. Here, the real-time operating parameter data of the target is compared with a dynamic threshold to observe the current state of the data and determine whether the threshold has been exceeded. Combining this with the parameter change trend, the focus is on the parameter trend within a certain time window while considering the current state, to identify any precursors to a fault. The preset fault determination rules, specifically for the integrated crushing and vibrating screen machine, specify which judgment dimensions need to be considered for a particular type of fault, and how fault scoring is performed within each judgment dimension.

[0037] For example, taking overload fault determination as an example, overload fault determination needs to consider four dimensions: load parameters, temperature parameters, speed parameters, and timing trends. Each dimension is assigned a different weight (load torque: 40%, winding temperature: 25%, speed fluctuation rate: 20%, timing trend: 15%), and the confidence level of overload fault is calculated.

[0038] For the load parameter dimension, the real-time load torque of the component drive motor is used as the criterion, and the score is based on the parameter change trend of the second-level time window (5s): when the current value of the real-time load torque exceeds the upper limit of the dynamic threshold, and the parameter change trend of the second-level time window is "rapid deviation or abrupt change", then 100 points are awarded; when the current value of the real-time load torque does not exceed the upper limit of the dynamic threshold, but the parameter change trend of the second-level time window is "slow deviation", then 50 points are awarded; when the current value of the real-time load torque is within the dynamic threshold range, and the parameter change trend of the second-level time window is "stable", then 0 points are awarded.

[0039] For the temperature parameter dimension, the real-time temperature of the winding of the component-driven motor is used as the judgment basis, and the score is combined with the parameter change trend of the third-level time window (30s): when the current value of the real-time temperature of the winding exceeds the upper limit of the dynamic threshold, and the parameter change trend of the third-level time window is "rapid deviation", then 100 points are awarded; when the current value of the real-time temperature of the winding does not exceed the upper limit of the dynamic threshold, but the parameter change trend of the third-level time window is "slow deviation", then 40 points are awarded; when the current value of the real-time temperature of the winding is within the dynamic threshold range, and the parameter change trend of the third-level time window is "stable", then 0 points are awarded.

[0040] For the speed parameter dimension, the real-time speed fluctuation rate of the component-driven motor is used as the criterion, combined with the parameter change trend of the first-level time window (1s) for scoring: when the current value of the real-time speed fluctuation rate exceeds the upper limit of the dynamic threshold, and the parameter change trend of the first-level time window is "sharp change", then 100 points are awarded; when the current value of the real-time speed fluctuation rate does not exceed the upper limit of the dynamic threshold, but the parameter change trend of the first-level time window is "slow deviation", then 30 points are awarded; when the current value of the real-time speed fluctuation rate is within the dynamic threshold range, and the parameter change trend of the first-level time window is "stable", then 0 points are awarded.

[0041] For the time-series trend dimension, the comprehensive performance of parameter change trends in the three dimensions of load, temperature, and speed is used as the judgment basis, and scores are assigned according to the severity gradient of the trend: "stable, slow deviation, rapid deviation, and abrupt change". When the parameter change trend of at least two of the three dimensions is "rapid deviation or abrupt change", 100 points are awarded; when the parameter change trend of only one of the three dimensions is "rapid deviation or abrupt change", or when at least two of the three dimensions are "slow deviation", 50 points are awarded; when only one of the three dimensions is "slow deviation" and the rest are "stable", 30 points are awarded; when the parameter change trend of all three dimensions is "stable", 0 points are awarded.

[0042] Step 152: Calculate the confidence level based on the fault judgment results of different dimensions to obtain the overload fault judgment results, material jamming fault judgment results, and overcurrent fault judgment results of the target crushing and vibrating screen integrated machine.

[0043] Specifically, step 152 may include: Step 1521: Based on the fault determination results of different dimensions, multiply the fault scores of different dimensions by a preset weight value to obtain the confidence level. Step 1522: Based on the confidence level value, obtain the overload fault determination result, material jamming fault determination result, and overcurrent fault determination result of the target crushing and vibrating screen integrated machine.

[0044] Here, taking overload fault determination as an example, after scoring each dimension through step 151 above, the overload fault confidence score is calculated using the formula "Overload Fault Confidence = (Load Parameter Dimension Score × 40% + Temperature Parameter Dimension Score × 25% + Speed ​​Parameter Dimension Score × 20% + Time Series Trend Dimension Score × 15%) ÷ 100" to obtain the overload fault determination result. When the overload fault confidence score is greater than or equal to 90%, it is determined to be an explicit overload fault, indicating that the component of the equipment has experienced substantial overload, and the corresponding fault response action must be triggered immediately. When the overload fault confidence score is greater than or equal to 70% and less than 90%, it is determined to be a Level II overload precursor warning, indicating that the component of the equipment shows a significant overload trend, and an early warning must be triggered and real-time monitoring strengthened. When the overload fault confidence score is greater than or equal to 50% and less than 70%, it is determined to be a Level I overload precursor warning, indicating that the component of the equipment shows a slight overload tendency, and high-frequency monitoring and parameter changes must be initiated. When the overload fault confidence level is less than 50%, it is determined to be normal operation. The component of the equipment has no overload-related abnormalities and continues to operate according to the preset parameters.

[0045] In this embodiment, the overload fault determination method is applicable to the crushing component, feeding component, reflux component, and vibration component of the integrated crushing and vibrating screen machine. The determination logic of each component is completely consistent, and each component is independently configured with its own dynamic determination threshold, so they do not interfere with each other.

[0046] For determining material jamming faults, the judgment rules vary depending on the specific part of the machine, as follows: For material jamming at the feed end, the fault diagnosis includes four dimensions: feed roller speed fluctuation rate, feed motor load torque, feed inlet material level sensor (infrared or ultrasonic) signal, and the linkage matching degree between feed roller speed and crushing roller speed.

[0047] Among them, the feed roller speed fluctuation dimension is based on the comparison between the real-time speed fluctuation of the feed roller and the preset dynamic threshold. If the fluctuation exceeds the upper limit of the threshold and does not recover for three consecutive collection cycles, it is scored as 100 points; if the fluctuation does not exceed the threshold but shows a continuous upward trend (slow deviation), it is scored as 50 points; if the fluctuation is within the threshold range and remains stable, it is scored as 0 points.

[0048] The load torque dimension of the feeding motor is based on the comparison between the real-time load torque of the feeding motor and the preset dynamic threshold. If the torque exceeds the upper limit of the threshold and the parameter change trend of the second-level time window (5s) is rapid deviation or abrupt change, it is scored as 100 points; if the torque does not exceed the threshold but shows a slow upward trend, it is scored as 40 points; if the torque is within the threshold range and remains stable, it is scored as 0 points.

[0049] The signal dimension of the feed inlet level sensor (infrared or ultrasonic) is based on the real-time material detection signal of the level sensor. A high level signal is triggered, scoring 100 points; a medium level signal is triggered or the signal shows a continuous upward trend, scoring 50 points; a low level signal is triggered and remains stable, scoring 0 points.

[0050] The linkage matching degree between the feed roller speed and the crushing roller speed is judged based on the positive correlation logic of the two component speeds. If the linkage matching degree is less than the preset threshold (positive correlation under normal working conditions) and has not recovered for 5 consecutive collection cycles, it is scored as 100 points; if the matching degree does not reach the threshold but shows a continuous downward trend, it is scored as 40 points; if the matching degree is within the preset threshold range and remains stable, it is scored as 0 points.

[0051] The basic confidence level for a material jamming fault at the feed end is calculated as follows: (Feed roller speed fluctuation rate score × 30% + Feed motor load torque score × 25% + Material level sensor signal score × 25% + Speed ​​linkage matching score × 20%) ÷ 100. It should be noted that if the material level sensor at the feed inlet triggers a high material level signal for a duration greater than or equal to 3 seconds, the confidence level will be directly increased by 20% based on the basic confidence level calculation. If the increased confidence level exceeds 100%, it will be calculated as 100%.

[0052] For determining the fault of material jamming in the crushing chamber, the determination dimensions include the crushing roller motor speed or load torque, the material level sensor signal inside the crushing chamber, the vibration amplitude of the bearings at both ends of the crushing roller, and the linkage matching degree between the crushing roller speed and the feeding speed. The confidence level of material jamming fault in the crushing chamber = (speed or torque × 35% + material level sensor signal × 25% + bearing vibration amplitude × 20% + linkage matching degree × 20%) ÷ 100.

[0053] For determining the material jamming fault at the return end, the determination dimensions include the return conveyor motor speed or load torque, the return channel material level sensor signal, the coarse material outlet flow rate signal of the vibrating screen component, and the linkage matching degree between the return motor speed and vibration frequency. The confidence level for the return end material jamming fault is calculated as follows: (Speed ​​or torque × 30% + Material level sensor signal × 30% + Coarse material outlet flow rate × 20% + Linkage matching degree × 20%) ÷ 100.

[0054] For overcurrent fault determination, the determination rules differ depending on whether the overcurrent is in the branch circuit or the main circuit.

[0055] For branch circuit overcurrent, the first step is to perform time-domain timing analysis on the collected current data to identify the specific type of overcurrent. The judgment logic and confidence calculation rules differ for different types. If, within the first-level time window, the branch operating current momentarily exceeds the dynamic threshold upper limit but quickly falls back to the normal threshold range within one acquisition cycle, it is judged as a momentary overcurrent. Only the fluctuation data is recorded; no confidence calculation is performed, and no alarm is triggered—it is not considered a fault. If, within the second-level time window, the branch operating current continuously exceeds the dynamic threshold upper limit without a significant downward trend, it is judged as a continuous overcurrent, and branch circuit overcurrent fault confidence calculation needs to be initiated. If, within the third-level time window, the branch operating current exceeds the dynamic threshold more than or equal to three times, even if each exceedance is short, the frequency is excessive, it is judged as a cumulative overcurrent, and branch circuit overcurrent fault confidence calculation needs to be initiated.

[0056] The confidence level of overcurrent fault in the branch circuit is calculated as follows: (Real-time current score × 35% + Current trend score × 25% + Load rate score × 20% + Winding temperature score × 10% + Power factor score × 10%) ÷ 100.

[0057] The real-time current score is based on the real-time operating current of the branch. When the current value exceeds the dynamic threshold by 150% or more, 100 points are awarded; when the current value exceeds the dynamic threshold but is between 100% and 150%, 70 points are awarded; when the current value is normal but close to the upper limit of the threshold, 30 points are awarded; and when the current value is within the normal range, 0 points are awarded.

[0058] The current trend score is based on the current time series trend. When the trend rises sharply or changes abruptly, it scores 100 points; when the trend rises slowly or deviates continuously, it scores 70 points; when the trend fluctuates but returns to normal (applicable to cumulative overcurrent), it scores 40 points; when the trend is stable and has no fluctuations, it scores 0 points.

[0059] The load rate score is based on the motor load rate. When the motor load rate is greater than or equal to 90%, 100 points are awarded. When the motor load rate is between 70% and 89%, 60 points are awarded. When the motor load rate is less than 70%, 20 points are awarded. When the motor load rate is normal, 0 points are awarded.

[0060] The winding temperature score is based on the motor winding temperature. When the temperature exceeds the rated temperature rise value, 100 points are awarded; when the temperature is close to the rated temperature rise value, 50 points are awarded; and when the temperature is normal and stable, 0 points are awarded.

[0061] The power factor score is based on the circuit's power factor: 100 points for a power factor less than 0.7; 50 points for a power factor between 0.7 and 0.85; and 0 points for a power factor greater than 0.85.

[0062] For determining the overcurrent fault in the main circuit, the confidence level of the overcurrent fault in the main circuit is calculated as follows: (Real-time operating current score of the main circuit × 30% + total matching score of branch currents × 25% + voltage stability score of the main circuit × 20% + total power factor score of the main circuit × 15% + total load rate score of each component × 10%) ÷ 100.

[0063] 100 points are awarded if the real-time operating current of the main circuit exceeds the upper limit of the dynamic threshold and shows no downward trend within the second-level time window; 60 points are awarded if the real-time operating current of the main circuit does not exceed the threshold but is close to the upper limit and shows a slow upward trend; and 0 points are awarded if the real-time operating current of the main circuit operates stably within the dynamic threshold range.

[0064] The score for the matching degree of the total branch current is based on the matching degree between the main circuit current and the total branch current. When the matching degree deviation is greater than 10%, 100 points are awarded; when the deviation is between 5% and 10%, 70 points are awarded; when the deviation is between 0% and 5% (normal linkage range), 0 points are awarded.

[0065] The main circuit voltage stability score is based on the main circuit voltage fluctuation rate within the second-level time window. When the voltage fluctuation rate exceeds the upper limit of the dynamic threshold, 100 points are awarded; when the voltage fluctuation rate does not exceed the threshold but shows a continuous fluctuation trend, 50 points are awarded; when the voltage fluctuation rate is within the threshold range and operates stably, 0 points are awarded.

[0066] For the total power factor score of the main circuit, 100 points are awarded when the total power factor is less than 0.7 (low quality operation, large reactive power loss); 40 points are awarded when the total power factor is between 0.7 and 0.85 (low); and 0 points are awarded when the total power factor is greater than 0.85 (normal operating range).

[0067] For the total score of the load rate of each component, when the total load rate of each component is greater than or equal to 90% (the system is fully loaded and the main circuit is under great load pressure), 100 points are awarded; when the total load rate is between 70% and 89% (the system is under high load), 50 points are awarded; when the total load rate is less than 70% (the system is under low load), 0 points are awarded.

[0068] It should be noted that when the control module determines that the main circuit exhibits overcurrent characteristics (confidence level ≥ 40%), it simultaneously initiates the fault root cause correlation determination logic. By calculating the deviation between the main circuit current and the sum of the currents in each branch, it accurately identifies the root cause of the overcurrent, providing a basis for subsequent targeted fault handling. Specific determination rules are as follows: Deviation value = |Real-time operating current of main circuit - Sum of operating currents of all branches| ÷ Real-time operating current of main circuit × 100%.

[0069] When the deviation value is ≤5%, it is determined that the main circuit overcurrent is caused by the superposition of the loads of each branch (not a fault of the main circuit itself, but caused by the linkage of the downstream component overload); when the deviation value is >5%, it is determined that the overcurrent is caused by the fault of the main circuit itself (such as a short circuit in the main circuit line, poor contact of the contactor, abnormal main fuse, and other faults of the main circuit itself).

[0070] The judgment results will be stored synchronously with the fault confidence level and abnormal data of various indicators. When a fault alarm is triggered, the root cause of the overcurrent will be displayed simultaneously, which will help testers to quickly locate the fault point.

[0071] In an optional embodiment of the present invention, step 16, based on the basic fault determination result, performing composite fault correlation reasoning to determine the composite fault level and root cause fault, may include: Step 161: Based on the basic fault determination results, when the number of basic faults is greater than or equal to 2, determine the causal relationship of each basic fault based on the typical compound fault causal relationship stored in the preset fault association rule library, as well as the occurrence time and parameter abnormal start time of each basic fault. Here, the pre-defined fault association rule base is constructed based on equipment operating mechanisms and statistical analysis results of historical fault data. Its core function is to pre-store the explicit causal relationships of various typical composite faults, forming a standardized causal association model to provide a reference for subsequent causal relationship determination. The typical composite fault causal relationships pre-stored in the rule base are as follows: Material jamming in the crushing chamber (root cause fault), overload of the crushing roller motor (primary derivative fault), overcurrent in the crushing branch (secondary derivative fault). Material jamming at the feed end (root cause fault), sudden drop in crushing roller speed (first-level derivative fault), insufficient material in the vibrating screen component (second-level derivative fault). Material jamming at the return end (root cause fault), overload of the return motor (first-level derivative fault), and fluctuation of the main circuit current (second-level derivative fault). Overload of the crushing roller motor (root cause fault), sudden rise in winding temperature (first-level derivative fault), and overcurrent in the crushing branch (second-level derivative fault).

[0072] When the control module detects that the confidence level of two or more basic faults is ≥70% (i.e., multiple suspected fault associations exist), it immediately initiates the causal relationship determination process. Through a dual logic of "time series analysis + rule matching," it accurately determines the causal relationship between the basic faults and locates the suspected root cause fault, specifically including: The control module synchronously extracts the occurrence time of each basic fault (accurate to the acquisition frame) and the start time of parameter abnormality, calculates the occurrence time difference between each fault, and clarifies the order of parameter abnormalities for each fault. The basic fault that "occurs earliest and whose abnormal parameters precede all other faults" is identified as a suspected root cause fault, and the remaining faults are tentatively identified as suspected derivative faults. The preliminary combination of "suspected root cause fault + suspected derivative fault" is compared and matched with the typical causal relationship model pre-stored in the fault association rule base. If the match is successful, the credibility of the suspected root cause fault is further improved. If the match fails, the temporal relationship and parameter association characteristics of each fault are re-examined to eliminate false associations and correct the suspected root cause fault judgment result.

[0073] Step 162: Based on the causal relationship of the aforementioned basic faults, preliminarily identify the suspected root cause faults; Step 163: Calculate the root cause confidence of the suspected root cause fault to obtain the root cause confidence of the suspected root cause fault. Here, the root cause confidence score = (suspected root cause failure self-confidence score × 50% + temporal correlation score × 30% + rule base matching score × 20%) × 100%.

[0074] Step 164: Determine the composite fault level and root cause fault based on the root cause confidence level.

[0075] Here, when the root cause confidence level is ≥90%, the suspected root cause fault is determined to be the core root cause fault, and the other related faults are all derived faults; when the root cause confidence level is <90%, the suspected root cause fault is re-determined. If the confidence level is still below 90% after multiple determinations, it is determined to be "multiple root causes coexisting", and subsequent management is carried out as a severe composite fault.

[0076] Based on the "level of the core root cause fault (precursor or explicit)" and the "number of derivative faults," complex faults are divided into three levels: mild, moderate, and severe. Different levels correspond to different alarm intensities and shutdown strategies, achieving graded control of complex faults. Specific grading standards are as follows: Mild composite fault: 1 core root cause fault (precursor level) + 1 derivative fault (precursor level), with no obvious fault characteristics; this level of fault has a low risk, only triggering a yellow warning, strengthening parameter monitoring, and does not require emergency shutdown. It is recommended that test personnel promptly investigate the precursors of the root cause fault. Intermediate composite fault: 1 core root cause fault (dominant level) + 2 or more derivative faults (can be mixed with precursor and dominant levels); this level of fault has a high risk, triggers an orange alarm, disconnects the component corresponding to the core root cause fault according to the directional shutdown rules, and restarts after the fault is cleared; Severe composite fault: Two or more core root cause faults (any one of which is dominant) + multiple derivative faults; this level of fault has an extremely high risk and is likely to cause the entire machine to fail, triggering a red emergency alarm, immediately cutting off the main power supply to the equipment's main circuit, and all components will shut down in an emergency according to a safe sequence. At the same time, a remote early warning system (optional) will be activated to prompt the test personnel to handle the situation immediately.

[0077] In an optional embodiment of the present invention, step 17, which involves filtering out false faults from the basic fault determination results and composite faults to obtain the fault determination results of the target crushing and vibrating screen integrated machine, may include: Step 171: Based on the target real-time operating parameter data, when the data of consecutive target frames in the target real-time operating parameter data recovers to the normal range and no derivative fault characteristics occur, the basic fault determination result is determined to be a false fault. Here, preferably, a false fault is identified when the target's real-time operating parameter data recovers to the normal range for three consecutive frames within the first-level time window, and no derivative faults occur. Fault identification is then canceled, and parameter fluctuations are only recorded locally.

[0078] Step 172: Based on the root cause confidence of the root cause fault in the composite fault, when the root cause confidence drops to the target value, the composite fault is determined to be a false composite fault. If the confidence level of the root cause fault in a composite fault drops rapidly to less than 50%, it is judged as a false composite fault, and all related fault judgments are cancelled. Step 173: Based on the filtering results of eliminating false faults and false composite faults, obtain the fault determination result of the target crushing and vibrating screen integrated machine.

[0079] The embodiments of this invention abandon the traditional single fixed threshold judgment mode, integrate multi-dimensional information such as mechanical, electrical, temporal trends and component linkage, and dynamically generate adaptive thresholds based on operating conditions, significantly reducing the false judgment and missed judgment rates. By extracting temporal features through multi-level time windows, it achieves advanced prediction of fault precursors, capturing potential faults in advance and preventing fault escalation and equipment damage. Simultaneously, relying on a fault association rule base and causal relationship reasoning, it accurately locates the core root cause of complex faults, significantly shortening fault investigation time and preventing repeated faults. The addition of false fault filtering and self-learning mechanisms effectively solves the problem of frequent false alarms, ensuring continuous closed-loop operation of automated work. Furthermore, it establishes hierarchical control and differentiated judgment logic for main and branch overcurrent, achieving differentiated intelligent fault response, balancing equipment operation safety and operational efficiency, accurately tracing the root cause of overcurrent, and improving power supply stability. This significantly improves the accuracy and intelligence level of equipment fault judgment, enhances operational stability, reduces maintenance costs, increases operational efficiency, and ensures that the qualified rate of processed soil samples meets soil testing requirements. Its practicality and promotional value are outstanding, comprehensively compensating for the shortcomings of existing technologies.

[0080] like Figure 2 As shown, an embodiment of the present invention also provides a fault determination device 20 for a crushing and vibrating screen integrated machine, comprising: The acquisition module 21 is used to acquire the real-time operating parameter data and the current preset operating parameters of the target crushing and vibrating screen integrated machine; The processing module 22 is used to preprocess the real-time operating parameter data to obtain target real-time operating parameter data; determine the dynamic threshold corresponding to each real-time operating parameter based on the current preset operating parameters, the preset basic threshold library, and the cumulative running time of the target crushing and vibrating screen integrated machine; perform time-series feature extraction and multi-time-window trend analysis on the target real-time operating parameter data to obtain the parameter change trend of each real-time operating parameter in different time windows; perform various basic fault judgments on the target crushing and vibrating screen integrated machine based on the target real-time operating parameter data, dynamic thresholds, and parameter change trends of each real-time operating parameter in different time windows, as well as preset fault judgment rules, to obtain basic fault judgment results; perform composite fault association reasoning based on the basic fault judgment results to determine the composite fault level and root cause fault; and perform false fault filtering on the basic fault judgment results and composite faults to obtain the fault judgment result of the target crushing and vibrating screen integrated machine.

[0081] Optionally, based on the current preset operating parameters, the preset basic threshold library, and the cumulative running time of the target crushing and vibrating screen integrated machine, a dynamic threshold corresponding to each real-time operating parameter is determined, including: Based on the current preset operating parameters, the real-time operating conditions are determined, and the baseline thresholds of each real-time operating parameter in the basic threshold database are corrected according to the real-time operating conditions to obtain the preliminary corrected thresholds. Based on the cumulative running time of the target crushing and vibrating screen integrated machine, the preliminary correction threshold is compensated to obtain the dynamic threshold corresponding to each real-time operating parameter.

[0082] Optionally, time-series feature extraction and multi-time-window trend analysis are performed on the target real-time operating parameter data to obtain the parameter change trend of each real-time operating parameter in different time windows, including: Based on the changing characteristics of the real-time operating parameters, time windows of the first, second, and third levels are determined, and the lengths of the time windows of the first, second, and third levels are different. Temporal features are extracted from the real-time operating parameter data of the target within the time windows of the first, second and third levels, respectively. The temporal features include: mean, dispersion, rate of change, degree of abrupt change and deviation duration. Based on the time-series features extracted within the time windows of the first, second, and third levels, parameter change trend analysis is performed to obtain the parameter change trend of each real-time operating parameter in different time windows.

[0083] Optionally, based on the target's real-time operating parameter data, dynamic thresholds, and the parameter change trends of each real-time operating parameter in different time windows, as well as preset fault judgment rules, various basic fault judgments are performed on the target crushing and vibrating screen integrated machine to obtain basic fault judgment results, including: The real-time operating parameter data of the target is compared with the dynamic threshold. The parameter change trend of the real-time operating parameters within the time window of the first, second or third level, and the preset fault judgment rules are combined to make fault judgments on the target crushing and vibrating screen integrated machine in different dimensions, and obtain fault judgment results in different dimensions. Based on the fault judgment results of different dimensions, confidence level calculation is performed to obtain the overload fault judgment results, material jamming fault judgment results, and overcurrent fault judgment results of the target crushing and vibrating screen integrated machine.

[0084] Optionally, confidence levels are calculated based on the fault determination results from different dimensions to obtain the overload fault determination results, material jamming fault determination results, and overcurrent fault determination results for the target crushing and vibrating screen integrated machine, including: Based on the fault determination results of different dimensions, the fault scores of different dimensions are multiplied by a preset weight value to obtain the confidence level; Based on the confidence level value, the overload fault determination results, material jamming fault determination results, and overcurrent fault determination results of the target crushing and vibrating screen integrated machine are obtained.

[0085] Optionally, based on the basic fault determination results, composite fault correlation reasoning is performed to determine the composite fault level and root cause fault, including: Based on the basic fault determination results, when the number of basic faults is greater than or equal to 2, the causal relationship of each basic fault is determined based on the typical compound fault causal relationship pre-stored in the preset fault association rule base, as well as the occurrence time and parameter abnormal start time of each basic fault. Based on the causal relationships of the aforementioned basic faults, suspected root cause faults are preliminarily identified; The root cause confidence of the suspected root cause failure is calculated to obtain the root cause confidence of the suspected root cause failure. Based on the root cause confidence level, determine the composite fault level and the root cause fault.

[0086] Optionally, false fault filtering is performed on the basic fault determination results and composite faults to obtain the fault determination results of the target crushing and vibrating screen integrated machine, including: Based on the target's real-time operating parameter data, when the data of consecutive target frames in the target's real-time operating parameter data recovers to the normal range and no derivative fault characteristics occur, the basic fault determination result is determined to be a false fault. Based on the root cause confidence of the root cause fault in the composite fault, when the root cause confidence drops to the target value, the composite fault is determined to be a false composite fault. Based on the filtering results that eliminate false faults and false compound faults, the fault determination results of the target crushing and vibrating screen integrated machine are obtained.

[0087] It should be noted that this device is the same as the method described above. All implementations in the above method embodiments are applicable to the embodiments of this device and can achieve the same technical effect.

[0088] Embodiments of the present invention also provide a computing device, including: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method as described above. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0089] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0090] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0091] In the embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0092] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0093] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0094] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0095] Furthermore, it should be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent solutions of the present invention. Moreover, the steps performing the above series of processes can naturally be executed in the order described, but are not necessarily required to be executed in chronological order; some steps can be executed in parallel or independently of each other. Those skilled in the art will understand that all or any step or component of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or network of computing devices, in hardware, firmware, software, or a combination thereof. This is something that those skilled in the art can achieve by using their basic programming skills after reading the description of the present invention.

[0096] Therefore, the object of the present invention can also be achieved by running a program or a set of programs on any computing device. The computing device can be a known general-purpose device. Therefore, the object of the present invention can also be achieved simply by providing a program product containing program code implementing the method or apparatus. That is, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any known storage medium or any storage medium developed in the future. It should also be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent to the present invention. Furthermore, the steps performing the above series of processes can naturally be performed in the order described, but are not necessarily required to be performed in chronological order. Some steps can be performed in parallel or independently of each other.

[0097] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for diagnosing faults in an integrated crushing and vibrating screen machine, characterized in that, include: Obtain real-time operating parameter data and current preset operating parameters of the target crushing and vibrating screen integrated machine; The real-time operating parameter data is preprocessed to obtain the target real-time operating parameter data; Based on the current preset operating parameters and the preset basic threshold library, as well as the cumulative running time of the target crushing and vibrating screen integrated machine, determine the dynamic threshold corresponding to each real-time operating parameter; The time-series features of the target real-time operating parameter data are extracted and multi-time window trend analysis is performed to obtain the parameter change trend of each real-time operating parameter in different time windows; Based on the target's real-time operating parameter data, dynamic thresholds, and the parameter change trend of each real-time operating parameter in different time windows, as well as the preset fault judgment rules, the target crushing and vibrating screen integrated machine is subjected to various basic fault judgments to obtain the basic fault judgment results. Based on the basic fault determination results, perform composite fault correlation reasoning to determine the composite fault level and root cause fault. The basic fault determination results and composite faults are filtered for false faults to obtain the fault determination results of the target crushing and vibrating screen integrated machine.

2. The fault determination method for the integrated crushing and vibrating screen machine according to claim 1, characterized in that, Based on the current preset operating parameters and the preset basic threshold library, as well as the cumulative running time of the target crushing and vibrating screen integrated machine, determine the dynamic threshold corresponding to each real-time operating parameter, including: Based on the current preset operating parameters, the real-time operating conditions are determined, and the baseline thresholds of each real-time operating parameter in the basic threshold database are corrected according to the real-time operating conditions to obtain the preliminary corrected thresholds. Based on the cumulative running time of the target crushing and vibrating screen integrated machine, the preliminary correction threshold is compensated to obtain the dynamic threshold corresponding to each real-time operating parameter.

3. The fault determination method for the integrated crushing and vibrating screen machine according to claim 1, characterized in that, The target real-time operating parameter data is subjected to time-series feature extraction and multi-time-window trend analysis to obtain the parameter change trend of each real-time operating parameter in different time windows, including: Based on the changing characteristics of the real-time operating parameters, time windows of the first, second, and third levels are determined, and the lengths of the time windows of the first, second, and third levels are different. Temporal features are extracted from the real-time operating parameter data of the target within the time windows of the first, second and third levels, respectively. The temporal features include: mean, dispersion, rate of change, degree of abrupt change and deviation duration. Based on the time-series features extracted within the time windows of the first, second, and third levels, parameter change trend analysis is performed to obtain the parameter change trend of each real-time operating parameter in different time windows.

4. The fault diagnosis method for the integrated crushing and vibrating screen machine according to claim 1, characterized in that, Based on the target's real-time operating parameter data, dynamic thresholds, and the parameter change trends of each real-time operating parameter in different time windows, as well as preset fault judgment rules, various basic fault judgments are performed on the target crushing and vibrating screen integrated machine to obtain basic fault judgment results, including: The real-time operating parameter data of the target is compared with the dynamic threshold. The parameter change trend of the real-time operating parameters within the time window of the first, second or third level, and the preset fault judgment rules are combined to make fault judgments on the target crushing and vibrating screen integrated machine in different dimensions, and obtain fault judgment results in different dimensions. Based on the fault judgment results of different dimensions, confidence level calculation is performed to obtain the overload fault judgment results, material jamming fault judgment results, and overcurrent fault judgment results of the target crushing and vibrating screen integrated machine.

5. The fault determination method for the integrated crushing and vibrating screen machine according to claim 4, characterized in that, Based on the confidence level calculation of the fault determination results from different dimensions, the overload fault determination results, material jamming fault determination results, and overcurrent fault determination results of the target crushing and vibrating screen integrated machine are obtained, including: Based on the fault determination results of different dimensions, the fault scores of different dimensions are multiplied by a preset weight value to obtain the confidence level; Based on the confidence level value, the overload fault determination results, material jamming fault determination results, and overcurrent fault determination results of the target crushing and vibrating screen integrated machine are obtained.

6. The fault determination method for the integrated crushing and vibrating screen machine according to claim 1, characterized in that, Based on the basic fault determination results, composite fault correlation reasoning is performed to determine the composite fault level and root cause fault, including: Based on the basic fault determination results, when the number of basic faults is greater than or equal to 2, the causal relationship of each basic fault is determined based on the typical compound fault causal relationship pre-stored in the preset fault association rule base, as well as the occurrence time and parameter abnormal start time of each basic fault. Based on the causal relationships of the aforementioned basic faults, suspected root cause faults are preliminarily identified; The root cause confidence of the suspected root cause failure is calculated to obtain the root cause confidence of the suspected root cause failure. Based on the root cause confidence level, determine the composite fault level and the root cause fault.

7. The fault determination method for the integrated crushing and vibrating screen machine according to claim 1, characterized in that, The basic fault determination results and composite faults are filtered for false faults to obtain the fault determination results of the target crushing and vibrating screen integrated machine, including: Based on the target's real-time operating parameter data, when the data of consecutive target frames in the target's real-time operating parameter data recovers to the normal range and no derivative fault characteristics occur, the basic fault determination result is determined to be a false fault. Based on the root cause confidence of the root cause fault in the composite fault, when the root cause confidence drops to the target value, the composite fault is determined to be a false composite fault. Based on the filtering results that eliminate false faults and false compound faults, the fault determination results of the target crushing and vibrating screen integrated machine are obtained.

8. A fault determination device for an integrated crushing and vibrating screen machine, characterized in that, include: The acquisition module is used to acquire real-time operating parameter data and current preset operating parameters of the target crushing and vibrating screen integrated machine; The processing module is used to preprocess the real-time operating parameter data to obtain the target real-time operating parameter data; Based on the current preset operating parameters and the preset basic threshold library, as well as the cumulative running time of the target crushing and vibrating screen integrated machine, determine the dynamic threshold corresponding to each real-time operating parameter; The time-series features of the target real-time operating parameter data are extracted and multi-time window trend analysis is performed to obtain the parameter change trend of each real-time operating parameter in different time windows; Based on the target's real-time operating parameter data, dynamic thresholds, and the parameter change trend of each real-time operating parameter in different time windows, as well as the preset fault judgment rules, the target crushing and vibrating screen integrated machine is subjected to various basic fault judgments to obtain the basic fault judgment results. Based on the basic fault determination results, perform composite fault correlation reasoning to determine the composite fault level and root cause fault. The basic fault determination results and composite faults are filtered for false faults to obtain the fault determination results of the target crushing and vibrating screen integrated machine.

9. A computing device, characterized in that, include: A processor, a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A storage instruction that, when executed on a computer, causes the computer to perform the method as described in any one of claims 1 to 7.

Images