A method and system for intelligent equipment management

Abstract

This invention relates to the field of control, and more specifically, to an intelligent equipment management method and system. The method includes: real-time acquisition of data during equipment performance testing, and preprocessing the acquired data; calculating a real-time time-series fault risk index for the equipment based on the preprocessed data; normalizing the time-series fault risk index and using it as an anomaly weight to improve the LOF anomaly detection algorithm; calculating a real-time anomaly score for the equipment based on the improved LOF anomaly detection algorithm; obtaining the equipment performance test results based on the anomaly score; and formulating equipment management strategies based on the equipment test results. This invention, through multi-dimensional data fusion and time-series analysis, can comprehensively and dynamically evaluate the operating status of equipment, promptly identify potential fault risks, and provide strong support for equipment quality control and reliability improvement.

Description

Technical Field

[0001] This invention relates to the field of control. More specifically, this invention relates to a method and system for intelligent equipment management. Background Technology

[0002] A smart mine refers to a mine that utilizes technologies such as the Internet of Things, big data, artificial intelligence, and automated control to achieve intelligent, information-based, and automated processes in mine production, management, and safety. Its goal is to improve mine production efficiency, reduce costs, enhance safety levels, reduce environmental pollution, and achieve sustainable development.

[0003] In the construction of smart mines, effective equipment management is one of the core elements to ensure the efficient and safe operation of the mine. By monitoring and analyzing the performance parameters of mining equipment in real time, not only can abnormal equipment conditions be detected in a timely manner and equipment failures be prevented, but also equipment maintenance strategies can be optimized, equipment lifespan extended, and operating costs reduced, thereby achieving full life-cycle management of the equipment.

[0004] The Local Outlier Factor (LOF) algorithm is an unsupervised anomaly detection method based on relative density. Its core idea is to identify anomalies by comparing the local density of a target object with that of its neighboring data points. In equipment condition monitoring scenarios, the performance parameters of equipment exhibit strong spatiotemporal correlation under normal operating conditions; that is, data points not only cluster spatially (in a multidimensional feature space) but also show certain regularities over time. The LOF algorithm primarily detects anomalies based on local density differences in space (multidimensional feature space), but it cannot capture the changing trends of data points over time. For gradual faults (such as insulation degradation), their characteristics may gradually appear over time, but they do not immediately show significant differences in spatial density, making it difficult for the LOF algorithm to detect such faults, thus reducing detection accuracy. Summary of the Invention

[0005] To address the limitations of the aforementioned LOF algorithm, which leads to insufficient accuracy in detecting device performance and even misjudging it as a normal state, this invention provides solutions in the following aspects.

[0006] In the first aspect, a method for intelligent equipment management includes:

[0007] Data is collected in real time during the equipment performance test, and the acquired data is preprocessed; the data includes the equipment's voltage and current data.

[0008] The real-time timing fault risk index of the equipment is calculated based on the preprocessed data; the timing fault risk index is positively correlated with the thermoelectric comprehensive fault index and positively correlated with the real-time voltage weight.

[0009] The timing fault risk index is normalized and used as an anomaly weight to improve the LOF anomaly detection algorithm. The real-time anomaly score of the device is calculated based on the improved LOF anomaly detection algorithm.

[0010] Based on the anomaly scores, the equipment performance test results are obtained, and equipment management strategies are formulated based on the equipment test results.

[0011] This invention collects real-time equipment performance data and calculates a time-series fault risk index based on preprocessed data. This index comprehensively considers a thermoelectric integrated fault index (combining temperature and current) and real-time voltage weighting. The thermoelectric integrated fault index reflects the impact of heat generated by current and the magnitude of the current itself on the equipment during operation. The voltage weighting considers the impact of voltage variations on equipment performance. By calculating this time-series fault risk index, the fault risk of the equipment at different time points can be dynamically assessed. Normalizing this index and using it as an anomaly weight enhances the sensitivity of the LOF algorithm to gradual faults, improving the accuracy and reliability of fault detection.

[0012] Preferably, the data also includes the device's temperature data.

[0013] Preferably, the process of obtaining the thermoelectric integrated failure index includes:

[0014] Obtain the device operating temperature data of the previous n time steps before the current time step, construct the nearest neighbor temperature monitoring sequence for the current time step, and obtain the device grounding current data of the previous n time steps before the current time step, construct the grounding current monitoring sequence for the current time step;

[0015] Calculate the thermal failure index and cable anomaly factor of the equipment at the current moment based on the nearest temperature monitoring sequence and the ground current monitoring sequence, respectively.

[0016] The product of the thermal failure index and the cable anomaly factor is used as the overall thermoelectric failure index of the equipment at the current moment.

[0017] Analyzing equipment operating temperature data can detect overheating. Overheating is often an early sign of problems such as insulation aging, poor contact, or overload. By analyzing temperature data from the previous n time points, abnormal temperature trends can be detected, allowing for early identification of potential thermal failure risks. Grounding current data reflects the insulation condition of cables and the integrity of the grounding system. Abnormal changes in grounding current may indicate problems such as cable insulation damage or poor grounding. Analyzing the grounding current monitoring sequence can promptly detect potential cable anomalies.

[0018] By integrating dual monitoring data of temperature and grounding current sequences, a joint analysis of thermal effects (equipment overheating) and electrical effects (current anomalies) can be achieved, which can more comprehensively reflect the complex failure risks of equipment compared with single parameter evaluation.

[0019] Preferably, the process of obtaining the voltage weight includes:

[0020] Obtain the voltage data of the device at each time point prior to the current time, as well as the breakdown voltage of the device under normal conditions. Use the ratio of the voltage data of the device at each time point to the breakdown voltage of the device under normal conditions as the voltage weight at the corresponding time point.

[0021] Using the ratio of voltage data at each moment to the breakdown voltage as a voltage weight, the approximation of the device's voltage state at that moment relative to its breakdown voltage can be quantified. A higher voltage weight indicates that the device's voltage state at that moment is closer to its breakdown voltage, and the greater the potential overvoltage risk.

[0022] Preferably, the timing failure risk index satisfies the following relationship:

[0023] ; For the current moment Equipment timing failure risk index Based on the current moment The former The overall thermal power failure index at a given moment. Based on the current moment The former Voltage weight at each moment, Based on the current moment The former Voltage data at each moment, This represents the breakdown voltage of the equipment under normal conditions. Indicates based on the current time The number of historical moments selected previously.

[0024] Preferably, the process of obtaining the anomaly score in the improved LOF anomaly detection algorithm is as follows:

[0025] The normalized time-series fault risk index at the current moment is used as a weight to multiply the original LOF anomaly score to obtain the anomaly score at the current moment after using the improved LOF anomaly detection algorithm.

[0026] Preferably, the step of obtaining equipment performance test results based on anomaly scores and formulating equipment management strategies based on the equipment test results includes:

[0027] If the anomaly score calculated based on the improved LOF anomaly detection algorithm is greater than the preset anomaly detection threshold, the performance test of the device at the current moment is deemed unqualified; otherwise, the performance test of the device at the current moment is deemed qualified.

[0028] Inspect and diagnose equipment that fails performance testing to identify the type and severity of the fault. For equipment with high severity, shut down for inspection or temporary repair.

[0029] Preferably, the process of obtaining the thermal failure index includes:

[0030] A trend detection was performed on the nearby temperature monitoring sequence to obtain a p-value;

[0031] The standard temperature of the preset equipment is used to calculate the temperature deviation of each element in the nearest temperature monitoring sequence from the standard temperature. This temperature deviation is used as the input of the hyperbolic tangent function, and its output is positively evaluated. Then, the results are summed over all elements in the nearest temperature monitoring sequence.

[0032] Multiplying the summation result by the value of p yields the thermal failure index.

[0033] Firstly, the p-value obtained through trend detection reflects the trend change of the temperature monitoring sequence. If the temperature shows an upward trend, the p-value may increase, indicating that the equipment may be heading towards failure. Furthermore, by calculating the temperature deviation and processing it using the hyperbolic tangent function, the degree of temperature anomaly can be quantified into a specific numerical value. The output range of the hyperbolic tangent function is 0 to 1, which can effectively suppress the influence of extreme temperature deviations, making the results more stable.

[0034] In summary, using the hyperbolic tangent function to process temperature deviations and summing the results after taking positive values ​​avoids interference from negative deviations. Furthermore, multiplying by a p-value further enhances the sensitivity to trend changes, making the calculation of the thermal failure index more stable and reducing the possibility of false alarms and missed alarms.

[0035] Preferably, the process of obtaining the cable anomaly factor includes:

[0036] Obtain the mode of the ground current monitoring sequence, calculate the square of the difference between each element in the ground current monitoring sequence and the mode, and sum them up. Divide the sum by the mode to obtain the cable anomaly factor.

[0037] Choosing the mode (rather than the mean) avoids interference from extreme outliers and is more suitable for describing actual operating conditions. By calculating the sum of squares of the differences between each monitored value and the mode, the contribution of outliers can be amplified (the squaring operation is more sensitive to larger deviations), thereby highlighting atypical current fluctuations.

[0038] In a second aspect, an intelligent device management system includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the intelligent device management method described in any one of the claims is implemented.

[0039] The beneficial effects of this invention are:

[0040] This invention calculates a timing fault risk index by collecting real-time equipment performance data, combining multi-dimensional features and dynamic time-series analysis, and introduces anomaly weights to improve the LOF anomaly detection algorithm. This effectively solves the problem of insufficient accuracy in detecting gradual faults in traditional LOF algorithms. This method not only improves the detection capability for gradual faults but also enables real-time evaluation of equipment performance, providing strong support for equipment maintenance and management. Attached Figure Description

[0041] Figure 1 This is a flowchart of steps S1-S4 in an intelligent equipment management method according to an embodiment of the present invention. Detailed Implementation

[0042] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments.

[0043] Reference Figure 1 A method for intelligent equipment management includes steps S1-S4, as detailed below:

[0044] S1: Acquire data during the equipment performance test and preprocess the acquired data.

[0045] During equipment performance testing, data was collected using three types of sensors: a temperature sensor to collect temperature data during operation, a current sensor to collect grounding current data, and a voltage sensor to collect voltage data. The data was collected at one-second intervals, meaning data was collected once per second.

[0046] During data acquisition, the data may be affected by environmental interference (such as electromagnetic interference, temperature changes, etc.) or sensor errors (such as sensor accuracy issues, aging, etc.), resulting in noise and other anomalies in the acquired data. To eliminate the impact of this noise on subsequent analysis results, moving average filtering algorithms are used to denoise the acquired data.

[0047] In addition, the different data collected (temperature, current, voltage) have different dimensions (units). The data after noise reduction is further normalized (such as maximum value normalization). The value range of all data is normalized to between 0 and 1, eliminating the influence of different data dimensions.

[0048] After the above noise reduction and normalization preprocessing steps, the relevant monitoring data during the equipment performance testing process were obtained.

[0049] S2: Calculate the real-time equipment timing fault risk index based on the preprocessed data; the timing fault risk index is positively correlated with the thermoelectric comprehensive fault index and positively correlated with the real-time voltage weight.

[0050] When the equipment is working, it will generate heat due to the thermal effect of electric current. Normal temperature rise has a limited impact, but faults such as excessive load and poor contact can cause abnormal temperature rise, accelerate component aging, and cause other faults. Therefore, by analyzing the trend of equipment operating temperature change, the risk of equipment overheating can be assessed.

[0051] In one embodiment, the device operating temperature data of the previous n times (n is 20 in this embodiment) are obtained to construct the nearest neighbor temperature monitoring sequence at the current time. Then, the Cox-Stuart trend test is used to check whether the above nearest neighbor temperature monitoring sequence has an upward trend, and the p value is output. The smaller the p value, the more significant the upward trend of the sequence.

[0052] It is also necessary to consider that if the operating temperature of the equipment is within the normal range, even if the temperature fluctuates, it will not have a significant impact on the normal operation of the equipment. Therefore, such temperature rise is a normal phenomenon. Thus, it is also necessary to pay attention to abnormal temperature rises that exceed the normal range to avoid misjudging normal operating conditions as malfunctions.

[0053] In one embodiment, the normal temperature range of the device is set with reference to the device's technical manual and industry standards and specifications. In this embodiment of the invention, the maximum value of its normal temperature range is set to 40°C. For ease of analysis, the maximum value of this normal temperature range is recorded as the standard temperature. The thermal failure index of the device at each moment is calculated based on the above p-value and the standard temperature.

[0054] For example, a formula for calculating the thermal failure index is given:

[0055]

[0056] In the formula, For the current moment The thermal failure index of the equipment For the current moment The p-value obtained after trend detection of the corresponding nearest-neighbor temperature monitoring sequence. Standard temperature For the current moment The corresponding nearest neighbor temperature monitoring sequence The value of each element. Represents the hyperbolic tangent function. This represents the total number of elements contained in the nearest neighbor temperature monitoring sequence. In the formula, This indicates the temperature deviation between the current monitored temperature and the standard temperature.

[0057] Specifically, this applies when the equipment is within its normal operating temperature range, i.e., the temperature does not exceed the aforementioned 40°C. A value of 0 has no effect on equipment malfunction; conversely, when the equipment operating temperature exceeds the normal operating temperature range, i.e., greater than 40℃, a value of 0 is used. This indicates a significant impact on equipment failure. The more pronounced the upward trend in equipment operating temperature and the greater the deviation from the normal operating temperature range, the higher the thermal failure index. This suggests that the equipment may be overheating or experiencing abnormal temperature rises, potentially accelerating the aging of equipment components and causing other failures.

[0058] Furthermore, under normal circumstances, the sum of the currents flowing through the three cores of a three-core cable in an equipment should be zero, and there should be no induced current in the metal shielding layer. However, in reality, if the cores are bent, the sum of the electromotive force vectors will not be zero, thus generating a grounding current. The grounding current can reflect the degree of abnormality of the cable fault and the aging of the cable insulation layer.

[0059] In one embodiment, the ground current data of the device for the previous n time moments (n is 20 in this embodiment) are obtained, the ground current monitoring sequence for the current time moment is constructed, and then the cable anomaly factor of the device is calculated.

[0060] For example, a formula for calculating the cable anomaly factor is given:

[0061]

[0062] In the formula, For the current moment Cable abnormality factors of the equipment For the current moment The corresponding ground current monitoring sequence The value of each element. For the current moment The mode in the corresponding ground current monitoring sequence, This represents the total number of elements contained in the ground current monitoring sequence.

[0063] In the formula, when the monitored value with mode When the degree of deviation increases, the molecules Increase, leading to Increase.

[0064] It should be further noted that during operation, cables generate heat energy due to resistance losses from current flowing through the conductor and dielectric losses from the insulation material under the influence of electric and magnetic fields. If this heat cannot be dissipated in time, the cable temperature will continue to rise. Abnormal equipment temperatures may accelerate cable aging and damage, thereby increasing the risk of cable malfunctions. By considering the thermal failure index, the impact of temperature on cable malfunctions can be incorporated into the assessment.

[0065] In one embodiment, the current time calculated above is used as an example. thermal failure index of equipment With the current moment Equipment cable abnormality factor The product of these factors serves as the thermoelectric integrated failure index. .

[0066] The thermal failure index and cable anomaly factor reflect the equipment's failure risk from two different perspectives: temperature and grounding current, respectively. Combining the two can improve the accuracy of failure assessment.

[0067] However, considering only thermoelectric factors may not accurately reflect the true risk of equipment under high-voltage conditions. For example, even if the temperature and grounding current are within normal ranges, the equipment may still fail due to insufficient withstand voltage of the insulation material if the test voltage is close to the breakdown voltage. Voltages close to the breakdown voltage amplify the impact of thermoelectric factors on the equipment. By incorporating voltage factors into the calculations, this amplification effect can be reflected more accurately, thereby improving the accuracy of risk assessment.

[0068] In one embodiment, the voltage data of the device at each time point before the current time and the breakdown voltage of the device under normal conditions are obtained. The ratio of the voltage data of the device at each time point to the breakdown voltage of the device under normal conditions is used as the voltage weight at the corresponding time point. Based on the weight and the thermoelectric integrated fault index calculated above, the timing fault risk index of the device at the current time point is calculated.

[0069] The above-mentioned timing failure risk index satisfies the following relationship:

[0070]

[0071] For the current moment Equipment timing failure risk index Based on the current moment The former The overall thermal power failure index at a given moment. Based on the current moment The former Voltage weight at each moment, Based on the current moment The former Voltage data at each moment, This represents the breakdown voltage of the equipment under normal conditions. Indicates based on the current time The number of historical moments selected previously.

[0072] in, Historical voltage This is converted to a ratio relative to the breakdown voltage. If this value is close to or exceeds 1, it indicates that the voltage is approaching the device's tolerance limit, and the risk is increased.

[0073] Representing historical moments The product of the thermoelectric comprehensive failure index and the ratio of the voltage is significant if the thermoelectric comprehensive failure index is high and the voltage is close to the breakdown value at a certain moment.

[0074] Integrating the equipment in the past The fault trend and voltage state at each moment are normalized and averaged to quantify the timing fault risk at the current moment. If... A high level indicates a high risk of equipment failure in the near future, requiring early warning or maintenance measures.

[0075] Similarly, the timing fault risk index of real-time devices can be obtained based on the above operations.

[0076] By calculating the time-series fault risk index at each moment, the degree of anomaly in the equipment performance test data at each moment in the time series can be reflected.

[0077] S3: Normalize the timing fault risk index and use it as an anomaly weight to improve the LOF anomaly detection algorithm. Calculate the real-time anomaly score of the device based on the improved LOF anomaly detection algorithm.

[0078] While traditional LOF (Local Outlier Factor) anomaly detection algorithms can detect outliers in data, they may not be able to fully consider the actual operating status and failure risks of the equipment.

[0079] By multiplying the normalized timing failure risk index by the traditional LOF anomaly score as a weight, the targeting of anomaly detection can be enhanced. If the device itself has a high failure risk (i.e., a large normalized timing failure risk index), then even if the traditional LOF score is not high, the improved score may increase, making it easier to detect potential problems.

[0080] The improved outlier scores described above can be expressed as follows:

[0081]

[0082] In the formula, For the current moment Abnormal scores after equipment improvement The current moment after normalization Equipment timing failure risk index The current time is calculated using the traditional LOF anomaly detection algorithm. The device's anomaly score.

[0083] S4: Obtain equipment performance test results based on anomaly scores, and formulate equipment management strategies based on the equipment test results.

[0084] In one embodiment, the anomaly detection threshold is set to 1.2. If at the current time... If the anomaly score of the improved equipment exceeds the anomaly detection threshold, it indicates a problem with the equipment's performance test results, potentially posing a risk in practical applications. In such cases, quality inspectors need to address the issue promptly, performing further inspection, repair, or adjustments to ensure equipment quality and safety. For example, in a smart mine power system, based on real-time collected equipment performance data and calculated anomaly scores, operating parameters can be adjusted in real time to keep the equipment in optimal operating condition. Similarly, based on real-time load, temperature, and other performance data of the transformer, combined with its anomaly score, the transformer's cooling system operation mode can be dynamically adjusted (e.g., increasing cooling fan speed or activating auxiliary cooling equipment) to ensure the transformer operates within a safe and efficient temperature range, improving power transmission efficiency and reducing energy loss.

[0085] In addition, equipment with an abnormal score greater than the quality inspection threshold should be inspected and diagnosed to confirm the type and severity of the fault. For faults that may affect production safety or cause major shutdowns, emergency measures should be taken immediately, such as shutdown inspection and temporary repair.

[0086] If the improved anomaly score is less than the quality inspection threshold, it indicates that the equipment performance test results are satisfactory.

[0087] The system includes a processor and a memory, the memory storing computer program instructions, which, when executed by the processor, implement the intelligent device management method according to the first aspect of the present invention.

[0088] The system also includes other components well known to those skilled in the art, such as communication buses and communication interfaces, the settings and functions of which are known in the art and will not be described in detail here.

[0089] It should be noted that those skilled in the art can make various modifications and improvements without departing from the inventive concept, and these all fall within the scope of protection of this invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

Claims

1. A method for intelligent equipment management, characterized in that, include: Real-time acquisition of data during equipment performance testing, and preprocessing of the acquired data; The data includes the device's voltage, current, and temperature data; Calculate the real-time timing failure risk index of the equipment based on the preprocessed data; The timing fault risk index is positively correlated with the thermoelectric integrated fault index and with the real-time voltage weight; The process of obtaining the voltage weight includes: obtaining the voltage data of the device at each time point before the current time, as well as the breakdown voltage of the device under normal conditions, and using the ratio of the voltage data of the device at each time point to the breakdown voltage of the device under normal conditions as the voltage weight at the corresponding time point. The timing fault risk index is normalized and used as an anomaly weight to improve the LOF anomaly detection algorithm. The real-time anomaly score of the device is calculated based on the improved LOF anomaly detection algorithm. Equipment performance test results are obtained based on anomaly scores, and equipment management strategies are formulated based on these results; the process of obtaining the thermoelectric comprehensive failure index includes: Obtain the device operating temperature data of the previous n time steps before the current time step, construct the nearest neighbor temperature monitoring sequence for the current time step, and obtain the device grounding current data of the previous n time steps before the current time step, construct the grounding current monitoring sequence for the current time step; Calculate the thermal failure index and cable anomaly factor of the equipment at the current moment based on the nearest temperature monitoring sequence and the ground current monitoring sequence, respectively. The product of the thermal failure index and the cable anomaly factor is used as the current thermal-electric comprehensive failure index of the equipment; the process of obtaining the thermal failure index includes: A trend detection was performed on the nearby temperature monitoring sequence to obtain a p-value; The standard temperature of the preset equipment is used to calculate the temperature deviation of each element in the nearest temperature monitoring sequence from the standard temperature. This temperature deviation is used as the input of the hyperbolic tangent function, and its output is positively evaluated. Then, the results are summed over all elements in the nearest temperature monitoring sequence. Multiplying the summation result by the value of p yields the thermal failure index; The thermal failure index satisfies the formula: For the current moment The thermal failure index of the equipment For the current moment The p-value obtained after trend detection of the corresponding nearest-neighbor temperature monitoring sequence. Standard temperature For the current moment The corresponding nearest neighbor temperature monitoring sequence The value of each element. Represents the hyperbolic tangent function. This represents the total number of elements contained in the nearest neighbor temperature monitoring sequence. This indicates the temperature deviation between the current monitored temperature and the standard temperature.

2. The intelligent equipment management method according to claim 1, characterized in that, The timing failure risk index satisfies the following relationship: ; For the current moment Equipment timing failure risk index Based on the current moment The former The overall thermal power failure index at a given moment. Based on the current moment The former Voltage weight at each moment, Based on the current moment The former Voltage data at each moment, This represents the breakdown voltage of the equipment under normal conditions. Indicates based on the current time The number of historical moments selected previously.

3. The intelligent equipment management method according to claim 2, characterized in that, The process for obtaining the anomaly score in the improved LOF anomaly detection algorithm is as follows: The normalized time-series fault risk index at the current moment is used as a weight to multiply the original LOF anomaly score to obtain the anomaly score at the current moment after using the improved LOF anomaly detection algorithm.

4. The intelligent equipment management method according to claim 3, characterized in that, The process of obtaining equipment performance test results based on anomaly scores and formulating equipment management strategies based on these results includes: If the anomaly score calculated based on the improved LOF anomaly detection algorithm is greater than the preset anomaly detection threshold, the performance test of the device at the current moment is deemed unqualified; otherwise, the performance test of the device at the current moment is deemed qualified. Inspect and diagnose equipment that fails performance testing to identify the type and severity of the fault. For equipment with high severity, shut down for inspection or temporary repair.

5. The intelligent equipment management method according to claim 1, characterized in that, The process of obtaining the cable anomaly factor includes: Obtain the mode of the ground current monitoring sequence, calculate the square of the difference between each element in the ground current monitoring sequence and the mode, and sum them up. Divide the sum by the mode to obtain the cable anomaly factor.

6. An intelligent equipment management system, characterized in that, include: A processor and a memory, wherein the memory stores computer program instructions that, when executed by the processor, implement the intelligent device management method according to any one of claims 1-5.

Images