A method for predicting key equipment failures in airport lighting stations based on digital twins

Abstract

The present invention relates to the technical field of equipment failure prediction, and in particular to a method for predicting key equipment failures of airport lighting stations based on digital twins, the method comprising: collecting real-time operation data and real-time physical data of power distribution equipment, and collecting real-time environmental data corresponding to the power distribution equipment; judging the operation failure of the power distribution equipment based on a number of real-time operation data, and judging the physical failure of the power distribution equipment based on a number of real-time physical data; correcting the physical failure judgment result based on a number of real-time environmental data, and then judging the actual failure degree of the power distribution equipment according to the operation failure of the power distribution equipment and the corrected physical failure result; determining the predicted failure degree based on real-time operation data, real-time physical data and a digital twin model of power distribution failure; respectively comparing the actual failure degree with the predicted failure degree to correct the digital twin model of power distribution failure. The present invention improves the accuracy of the fault prediction results of the digital twin model.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment failure prediction, and in particular to a method for predicting failure of key equipment of an airport lighting station based on digital twins. Background Art

[0002] As an important infrastructure to ensure flight safety, the stable operation of the power distribution equipment of the airport lighting station is crucial. However, traditional fault monitoring and diagnosis methods often rely on manual inspections and post-maintenance, which have problems such as delayed response and low efficiency. With the development of the Internet of Things, big data and artificial intelligence technologies, digital twin technology provides new ideas for fault prediction and maintenance of complex systems.

[0003] The patent document with the Chinese patent application publication number CN117371220A discloses a method for predicting faults based on digital twins, which relates to the field of fault prediction technology and includes the following steps: Step 1: Data acquisition, the data transmission on the device side is directly uploaded to the cloud through the communication interface, and the device management system on the cloud performs data analysis, processing and storage after receiving the data; Step 2: Data protocol check and analysis, before receiving the data, check the legality of the protocol used, and parse the protocol to confirm whether the data transmission is correct and effective; Step 3: Data reliability processing, de-duplicate values, process missing values, detect abnormal values, and convert data types based on valid data to obtain reliable and accurate data; Step 4: Establish digital twins and learning models, establish mathematical models and physical models according to the physical properties and characteristics of the equipment; Step 5: Digital twin simulation and real-time monitoring, integrate the digital twin model with entity information, continuously calculate and update the model, and collect and process the physical variables involved in monitoring and prediction in real time; Step 6: Fault diagnosis, compare the collected system data with the digital twin model, detect faults, and accurately locate the cause of the fault with the help of the fault diagnosis model.

[0004] The existing technology only relies on single-dimensional data such as equipment operating status parameters, ignoring the potential impact of environmental factors on equipment performance and the probability of failure, resulting in low accuracy of fault prediction results. Summary of the invention

[0005] To this end, the present invention provides a method for predicting key equipment faults of an airport lighting station based on digital twins, which can solve the problem of inaccurate fault prediction results.

[0006] To achieve the above objectives, the present invention provides a method for predicting key equipment failures of airport lighting stations based on digital twins, comprising:

[0007] Collect real-time operation data and real-time physical data of the power distribution equipment in the airport lighting station, as well as real-time environmental data corresponding to the power distribution equipment;

[0008] Determine the operation fault of the power distribution equipment based on some of the real-time operation data, and determine the physical fault of the power distribution equipment based on some of the real-time physical data;

[0009] Correcting the physical fault judgment result based on the real-time environmental data, so as to further judge the actual fault degree of the power distribution equipment according to the operation fault of the power distribution equipment and the corrected physical fault result;

[0010] Determining a predicted fault degree based on the real-time operation data, the real-time physical data, and the power distribution fault digital twin model;

[0011] The actual fault degree is compared with the predicted fault degree respectively, and the power distribution fault digital twin model is corrected according to the comparison result.

[0012] Furthermore, the step of determining the operating fault of the power distribution equipment based on the real-time operating data includes:

[0013] Collecting several real-time current values, real-time voltage values ​​and real-time power factor values ​​of the power distribution equipment;

[0014] Calculating a plurality of real-time power values ​​based on the plurality of real-time current values ​​and the plurality of real-time voltage values ​​corresponding thereto;

[0015] Draw a real-time power change curve based on several real-time power values, compare it with a preset power change curve, and determine power anomalies;

[0016] Based on a number of real-time power factor values, a power factor change curve is drawn, and the fluctuation of the power factor change curve is judged, so as to determine the real-time power factor abnormality according to the result of the fluctuation judgment;

[0017] The operation fault is determined based on the real-time power abnormality and the power factor abnormality.

[0018] Furthermore, the step of determining the physical fault of the power distribution equipment based on the real-time physical data includes:

[0019] Collecting several real-time device temperature values ​​of the power distribution equipment;

[0020] Collecting several real-time vibration values ​​of the power distribution equipment;

[0021] Draw a real-time device temperature change curve based on the real-time device temperature values, compare it with a preset device temperature change curve, and determine device temperature abnormality according to the comparison result;

[0022] Draw a real-time vibration change curve based on the real-time vibration values, compare it with a preset vibration change curve, and judge the vibration abnormality of the equipment according to the comparison result;

[0023] The physical fault is determined according to the abnormal temperature of the device and the abnormal vibration of the device.

[0024] Furthermore, the step of correcting the physical fault judgment result based on the real-time environmental data includes:

[0025] Collect several real-time ambient temperature values ​​and real-time wind strength values;

[0026] Draw a real-time ambient temperature change curve based on a number of real-time ambient temperature values;

[0027] Draw a real-time wind force change curve based on the real-time wind force intensity value;

[0028] Comparing the real-time environment temperature change curve with the real-time device temperature change curve, and correcting the device temperature anomaly according to the comparison result;

[0029] The real-time wind force change curve is compared with the real-time vibration change curve, and the abnormal vibration of the equipment is corrected according to the comparison result.

[0030] Furthermore, the step of determining the fluctuation of the power factor variation curve includes:

[0031] Identify whether the power factor variation curve is a periodic fluctuation;

[0032] When the power factor variation curve fluctuates periodically, the actual fluctuation period of the power factor variation curve, the actual fluctuation range within the period, and the actual fluctuation frequency are determined.

[0033] Further, determining the real-time power factor abnormality according to the fluctuation situation judgment result includes:

[0034] When the power factor variation curve is a periodic fluctuation, analyzing the fluctuation pattern within the period of the power factor variation curve;

[0035] If the fluctuation mode is abnormal, the real-time power factor is abnormal;

[0036] If the fluctuation mode is normal, the comparison result between the actual fluctuation range and the preset fluctuation range is determined, and the comparison result between the actual fluctuation frequency and the preset fluctuation frequency is determined, and then whether the real-time power factor is abnormal is determined based on the fluctuation range comparison result and the fluctuation frequency comparison result.

[0037] Further, the step of analyzing the fluctuation pattern within the power factor variation curve period includes:

[0038] Identifying a plurality of peak values ​​and a plurality of trough values ​​in the power factor variation curve;

[0039] The distribution of the peak values ​​and the trough values ​​is determined respectively, so as to further determine the fluctuation mode according to the distribution.

[0040] Furthermore, the step of judging the actual fault degree of the power distribution equipment according to the operation fault of the power distribution equipment and the corrected physical fault result includes:

[0041] Calculating a real-time fault index of the power distribution equipment according to the operational fault of the power distribution equipment and the corrected physical fault result, wherein the real-time fault index includes the frequency, duration and severity of the fault;

[0042] The real-time fault index is compared and analyzed with the historical fault data to determine the actual fault extent according to the comparison and analysis result.

[0043] Further, the step of determining the predicted fault degree based on the real-time operation data, the real-time physical data and the power distribution fault digital twin model includes:

[0044] Inputting the real-time operation data and the real-time physical data into a power distribution fault digital twin model;

[0045] The distribution fault digital twin model simulates the operating status and fault development process of the distribution equipment based on the input data;

[0046] The fault degree of the power distribution equipment is predicted according to the simulation result to obtain the predicted fault degree.

[0047] Furthermore, the step of correcting the power distribution fault digital twin model according to the comparison result includes:

[0048] calculating the difference between the actual fault degree and the predicted fault degree, and analyzing the difference;

[0049] According to the difference analysis results, adjust the relevant parameters in the distribution fault digital twin model;

[0050] The above process is repeated until the difference between the predicted fault degree and the actual fault degree is less than a preset threshold, thereby obtaining a target power distribution fault digital twin model.

[0051] Compared with the prior art, the beneficial effect of the present invention lies in that, by collecting real-time operation data, real-time physical data and real-time environmental data of the power distribution equipment, a comprehensive understanding of the equipment status is ensured. The collection of real-time data enables fault prediction to be based on the latest equipment status, improving the accuracy and timeliness of the prediction. Based on the real-time operation data and physical data, it is possible to quickly determine whether the power distribution equipment has an operation fault or a physical fault, providing a basis for subsequent fault degree judgment and prediction. Through preliminary analysis of the data, equipment that may have faults is screened out, reducing the focus on normal equipment and improving work efficiency. By considering environmental data, the physical fault judgment results are corrected to improve the accuracy of the judgment. The digital twin model can simulate the operating status of the power distribution equipment and predict the degree of equipment failure based on real-time data, providing a scientific basis for fault prevention and maintenance. By comparing the actual fault degree with the predicted fault degree, the accuracy of the digital twin model is evaluated, and the model is corrected according to the comparison results to make it more in line with the actual situation. After continuous correction and optimization, the prediction ability of the digital twin model will continue to improve, providing more reliable support for fault prediction of the power distribution equipment of the airport lighting station.

[0052] In particular, real-time collection of key parameters such as current, voltage and power factor provides a direct and reliable data source for subsequent fault judgment. Real-time data collection ensures the immediacy of fault judgment and helps to promptly discover and deal with potential problems. By calculating the real-time power value and monitoring the power output of the equipment in real time, it provides a basis for judging whether the equipment is overloaded or underpowered, thereby improving the accuracy of fault judgment. By drawing the power change curve and intuitively observing the power change trend, it helps to discover abnormal power fluctuations. By drawing the power factor change curve and monitoring its changes in real time, it helps to judge whether the equipment has faults. Combined with real-time power anomalies and power factor anomalies, a comprehensive judgment is made on the operating status of the equipment to improve the accuracy and reliability of fault judgment.

[0053] In particular, by collecting real-time ambient temperature values ​​and real-time wind intensity values, the key parameters of the equipment operating environment are obtained. By drawing the real-time ambient temperature change curve and the real-time wind force change curve, the dynamic changes of environmental factors can be intuitively observed. By comparing the real-time ambient temperature change curve with the equipment temperature change curve, the false alarm of equipment temperature anomaly caused by ambient temperature changes is eliminated, thereby improving the accuracy of fault prediction. Comparing the real-time wind force change curve with the equipment vibration change curve helps to distinguish between vibration anomalies caused by wind and vibration failures of the equipment itself, thereby more accurately locating the source of the fault. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1A flowchart of a method for predicting key equipment failures of an airport lighting station based on digital twins provided in an embodiment of the present invention;

[0055] Figure 2 A schematic diagram of a process for judging physical faults in a method for predicting key equipment faults of an airport lighting station based on digital twins provided in an embodiment of the present invention;

[0056] Figure 3 A schematic diagram of a process for correcting physical faults in a method for predicting key equipment faults of an airport lighting station based on digital twins provided in an embodiment of the present invention;

[0057] Figure 4 A schematic diagram of a process for determining the predicted degree of failure in a method for predicting failure of key equipment in an airport lighting station based on digital twins provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0058] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0059] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0060] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be understood as a limitation on the present invention.

[0061] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0062] See also Figure 1 As shown, an embodiment of the present invention provides a method for predicting key equipment failures of an airport lighting station based on digital twins, the method comprising:

[0063] Step S100, collecting real-time operation data and real-time physical data of the power distribution equipment in the airport lighting station, and collecting real-time environmental data corresponding to the power distribution equipment;

[0064] Step S200, judging an operation fault of the power distribution equipment based on some of the real-time operation data, and judging a physical fault of the power distribution equipment based on some of the real-time physical data;

[0065] Step S300, correcting the physical fault judgment result based on the real-time environmental data, so as to further judge the actual fault degree of the power distribution equipment according to the operation fault of the power distribution equipment and the corrected physical fault result;

[0066] Step S400, determining a predicted fault degree based on the real-time operation data, the real-time physical data and the power distribution fault digital twin model;

[0067] Step S500: compare the actual fault degree with the predicted fault degree respectively, and modify the power distribution fault digital twin model according to the comparison result.

[0068] Specifically, the embodiment of the present invention ensures a comprehensive understanding of the equipment status by collecting real-time operating data, real-time physical data and real-time environmental data of the distribution equipment. The collection of real-time data enables fault prediction to be based on the latest equipment status, thereby improving the accuracy and timeliness of the prediction. Based on the real-time operating data and physical data, it is quickly determined whether the distribution equipment has an operating fault or a physical fault, thereby providing a basis for subsequent fault degree judgment and prediction. Through preliminary analysis of the data, equipment that may have faults is screened out, reducing the focus on normal equipment and improving work efficiency. By considering environmental data, the physical fault judgment results are corrected to improve the accuracy of the judgment. The digital twin model can simulate the operating status of the distribution equipment and predict the degree of equipment failure based on real-time data, thereby providing a scientific basis for fault prevention and maintenance. By comparing the actual fault degree with the predicted fault degree, the accuracy of the digital twin model is evaluated, and the model is corrected according to the comparison results to make it more in line with the actual situation. After continuous correction and optimization, the prediction ability of the digital twin model will continue to improve, providing more reliable support for fault prediction of the airport lighting station distribution equipment.

[0069] Specifically, the equipment in the airport lighting station may include power distribution equipment, lighting equipment and a central control device. The power distribution equipment is the core of the airport lighting station and is responsible for distributing electrical energy to various lighting equipment to ensure the stable operation of the lighting system. In the embodiment of the present invention, the power distribution equipment is selected as the key equipment. It can be understood that the power distribution equipment is a power distribution cabinet.

[0070] The digital twin model is a digital twin that makes full use of physical models, sensors, operation history and other data, integrates multi-disciplinary, multi-physical quantity, multi-scale, and multi-probability simulation processes, and completes mapping in virtual space, thereby reflecting the full life cycle of the corresponding physical equipment. The steps for constructing a digital twin model of power distribution faults in the embodiment of the present invention can be as follows: Step S1, comprehensively collect various types of data on the power distribution equipment of the airport lighting station, covering its design parameters, historical operation records, maintenance logs, etc., pre-process these data, and remove noise and outliers; Step S2, construct according to the actual physical structure and functional characteristics of the power distribution equipment Build a corresponding physical model, which should be able to accurately reflect the behavioral characteristics of the equipment under normal operation and fault conditions; step S3, use machine learning or deep learning algorithms, combine real-time operation data, physical data and environmental data, and train data-driven models. These models can capture the dynamic changes of equipment status and predict possible future failures; step S4, merge the physical model and the data-driven model to form a distribution fault digital twin model. The above steps are only an example of constructing a distribution fault digital twin model in an embodiment of the present invention. The construction of a distribution fault digital twin model belongs to the prior art and will not be repeated here.

[0071] It can be understood that in the embodiment of the present invention, "normal" and "abnormal" are defined based on the analysis results of the equipment operation data and environmental data. In the embodiment of the present invention, when the real-time operation data and real-time physical data of the power distribution equipment fluctuate within a preset range, the equipment can be considered to be in a "normal" state. For example, parameters such as current and voltage change within the specified threshold value, and there is no sudden change or exceeding the normal working range. On the contrary, if these parameters fluctuate abnormally, such as a sudden increase in current or a sharp drop in voltage, the equipment may be in an "abnormal" state, indicating that there may be a fault or an impending fault. In order to more accurately identify the "normal" and "abnormal" states, the embodiment of the present invention also considers the impact of real-time environmental data. For example, changes in environmental factors such as temperature and humidity may affect the operating state of the equipment, so when judging the equipment state, these environmental factors need to be taken into consideration. By comprehensively analyzing real-time operation data, real-time physical data and real-time environmental data, the operating state of the equipment can be more accurately identified, thereby improving the accuracy of fault prediction.

[0072] It can be understood that in the embodiment of the present invention, several real-time equipment parameters of the power distribution equipment and their corresponding real-time environmental parameters are all obtained by detection sensors corresponding to the parameters. For example, the real-time current value can be obtained by detection by a current sensor. The detection method of real-time data is the content of the existing technology and will not be repeated here.

[0073] See also Figure 2As shown, the step of judging the operation fault of the power distribution equipment based on the real-time operation data includes:

[0074] Step S210, collecting several real-time current values, real-time voltage values ​​and real-time power factor values ​​of the power distribution equipment;

[0075] Step S220, calculating a plurality of real-time power values ​​based on the plurality of real-time current values ​​and the plurality of real-time voltage values ​​corresponding thereto;

[0076] Step S230, drawing a real-time power change curve based on a number of real-time power values, comparing it with a preset power change curve, and determining power anomaly;

[0077] Step S240, drawing a power factor change curve based on a number of real-time power factor values, judging the fluctuation of the power factor change curve, and determining that the real-time power factor is abnormal according to the fluctuation judgment result;

[0078] Step S250: determining the operation fault based on the real-time power abnormality and the power factor abnormality.

[0079] Specifically, the preset power change curve described in the embodiment of the present invention is a curve drawn from several power values ​​obtained during the normal operation of the power distribution equipment within the same monitoring period.

[0080] Specifically, possible examples of operating failures in the embodiments of the present invention are:

[0081] Phenomenon description 1: The real-time current value of the power distribution equipment continues to exceed its rated current value, causing the equipment to overheat, which may cause serious consequences such as equipment damage or fire.

[0082] Judgment basis 1: If the real-time power value calculated by step S220 is continuously higher than the rated power of the equipment, and the real-time power change curve in step S230 shows a significant increase compared with the preset power change curve, and the power factor change curve in step S240 does not fluctuate much but is generally high (because when the power factor is close to 1, it means that the equipment is close to full load or overload), then it can be judged as an overload fault.

[0083] Phenomenon description 2: The real-time voltage value of the power distribution equipment is continuously lower than its rated voltage value, causing the equipment to fail to work normally, which may cause problems such as insufficient lighting brightness and difficulty in starting the equipment.

[0084] Judgment basis 2: If the real-time power value calculated by step S220 is continuously lower than the rated power of the equipment, and the real-time power change curve in step S230 shows a significant decrease compared with the preset power change curve, and the power factor change curve in step S240 does not fluctuate much but is generally low (because a decrease in power factor may indicate that the equipment is in a light load or undervoltage state), then it can be judged as an undervoltage fault.

[0085] Phenomenon description 3: The real-time power factor value of the distribution equipment deviates from the normal range, resulting in an increase in the reactive power of the power grid, which may cause problems such as grid voltage fluctuations and increased equipment losses.

[0086] Judgment basis 3: directly observe the fluctuation of the power factor change curve in step S240. If the fluctuation is too large or continuously deviates from the normal range (such as lower than 0.9 or higher than 1.1, etc.), it can be judged as an abnormal power factor fault. This fault may be caused by a fault in the capacitor compensation device inside the equipment, a change in load characteristics, etc.

[0087] Specifically, the embodiments of the present invention provide a direct and reliable data source for subsequent fault judgment by real-time collection of key parameters such as current, voltage and power factor. The real-time collection of data ensures the immediacy of fault judgment, which helps to timely discover and deal with potential problems. By calculating the real-time power value and monitoring the power output of the equipment in real time, a basis is provided for judging whether the equipment is overloaded or underpowered, thereby improving the accuracy of fault judgment. By drawing the power change curve, the power change trend can be intuitively observed, which helps to discover abnormal power fluctuations. By drawing the power factor change curve and monitoring its changes in real time, it helps to judge whether the equipment has a fault. Combined with the real-time power anomaly and power factor anomaly, a comprehensive judgment is made on the operating status of the equipment, thereby improving the accuracy and reliability of fault judgment.

[0088] Specifically, the step of determining the physical fault of the power distribution equipment based on the real-time physical data includes:

[0089] Collecting several real-time device temperature values ​​of the power distribution equipment;

[0090] Collecting several real-time vibration values ​​of the power distribution equipment;

[0091] Draw a real-time device temperature change curve based on the real-time device temperature values, compare it with a preset device temperature change curve, and determine device temperature abnormality according to the comparison result;

[0092] Draw a real-time vibration change curve based on the real-time vibration values, compare it with a preset vibration change curve, and judge the vibration abnormality of the equipment according to the comparison result;

[0093] The physical fault is determined according to the abnormal temperature of the device and the abnormal vibration of the device.

[0094] Specifically, possible examples of physical failures described in the embodiments of the present invention are equipment overheating failures. For example, the circuit breaker in the distribution cabinet may be overloaded for a long time or have poor contact, resulting in a significant increase in the real-time equipment temperature value, exceeding the normal operating temperature range. Equipment overheating may cause accelerated aging of insulation materials, reduce equipment life, and even cause a fire. Bearing wear failures. For example, the fan or motor bearings in the distribution equipment are worn due to long-term operation, resulting in an increase in the real-time vibration value and a change in the vibration frequency characteristics. Bearing wear may cause unstable equipment operation, intensified vibration, and ultimately cause equipment damage.

[0095] Specifically, the preset equipment temperature change curve described in the embodiment of the present invention is a curve drawn from several temperature values ​​obtained during the normal operation of the power distribution equipment within the same monitoring period;

[0096] The preset vibration change curve is a curve drawn from several vibration values ​​obtained during the normal operation of the power distribution equipment within the same monitoring period.

[0097] It can be understood that the embodiment of the present invention can determine that the device temperature is abnormal by comparing the change trend and change range of the real-time device temperature change curve with the preset device temperature change curve, and marking the part of the real-time device temperature change curve that is different from the preset device temperature change curve to determine the device temperature abnormality.

[0098] It can be understood that the embodiment of the present invention can determine the abnormal vibration of the equipment by comparing the change trend and change range of the real-time equipment vibration change curve with the preset equipment vibration change curve, marking the part of the real-time equipment vibration change curve that is different from the preset equipment vibration change curve, so as to determine the abnormal vibration of the equipment.

[0099] It can be understood that, in the embodiment of the present invention, the physical fault may be determined by taking the union of the area corresponding to the abnormal temperature of the device and the area corresponding to the abnormal vibration of the device as the physical fault.

[0100] See also Figure 3 As shown, the step of correcting the physical fault judgment result based on the real-time environmental data includes:

[0101] Step S310, collecting a number of real-time ambient temperature values ​​and real-time wind strength values;

[0102] Step S320, drawing a real-time ambient temperature change curve based on a number of real-time ambient temperature values;

[0103] Step S330, drawing a real-time wind force change curve based on the real-time wind force intensity value;

[0104] Step S340, comparing the real-time environment temperature change curve with the real-time device temperature change curve, and correcting the device temperature anomaly according to the comparison result;

[0105] Step S350, comparing the real-time wind force change curve with the real-time vibration change curve, and correcting the abnormal vibration of the equipment according to the comparison result.

[0106] Specifically, the embodiment of the present invention corrects the abnormal temperature of the device, which may include: if the device temperature change curve shows an abnormal increase or decrease, and the ambient temperature also changes accordingly, and the change trends of the two are consistent, the abnormal temperature of the device may be caused by the ambient temperature. At this time, the abnormal temperature of the device should be corrected to eliminate the influence of the ambient temperature factor. The correction method may include adjusting the change range threshold of the device temperature monitoring, etc.;

[0107] Correcting abnormal equipment vibration may include: if abnormal fluctuations appear in the vibration change curve, and at the same time the wind change curve also has corresponding fluctuations, and the fluctuation trends of the two are related, then the abnormal equipment vibration may be caused by wind. At this time, the abnormal equipment vibration should be corrected to eliminate the influence of wind factors. The correction method may include adjusting the change range threshold of vibration monitoring, etc.

[0108] Specifically, the embodiment of the present invention obtains key parameters of the equipment operating environment by collecting real-time ambient temperature values ​​and real-time wind intensity values, and intuitively observes the dynamic changes of environmental factors by drawing real-time ambient temperature change curves and real-time wind force change curves. By comparing the real-time ambient temperature change curve with the equipment temperature change curve, false alarms of equipment temperature anomalies caused by ambient temperature changes are eliminated, thereby improving the accuracy of fault prediction. Comparing the real-time wind force change curve with the equipment vibration change curve helps to distinguish between vibration anomalies caused by wind and vibration failures of the equipment itself, thereby more accurately locating the source of the fault.

[0109] Specifically, the step of determining the fluctuation of the power factor variation curve includes:

[0110] Identify whether the power factor variation curve is a periodic fluctuation;

[0111] When the power factor variation curve fluctuates periodically, the actual fluctuation period of the power factor variation curve, the actual fluctuation range within the period, and the actual fluctuation frequency are determined.

[0112] Specifically, in the embodiment of the present invention, when the power factor variation curve is a non-periodic fluctuation, it is determined that the power factor of the device is abnormal.

[0113] It can be understood that the embodiments of the present invention can identify whether the curve exhibits non-periodic fluctuations by observing the shape and trend of the power factor variation curve. This can be achieved by comparing whether the time intervals between adjacent peaks and troughs are consistent, and whether the curve lacks obvious periodic patterns. The actual fluctuation period of the power factor variation curve, the actual fluctuation range within the period, and the actual fluctuation frequency can be determined by any technology in the prior art for determining the fluctuation period, fluctuation range, and fluctuation frequency of a periodic curve, which will not be elaborated here.

[0114] Specifically, the real-time power factor abnormality is determined based on the fluctuation judgment results, including:

[0115] When the power factor variation curve is a periodic fluctuation, analyzing the fluctuation pattern within the period of the power factor variation curve;

[0116] If the fluctuation mode is abnormal, the real-time power factor is abnormal;

[0117] If the fluctuation mode is normal, the comparison result between the actual fluctuation range and the preset fluctuation range is determined, and the comparison result between the actual fluctuation frequency and the preset fluctuation frequency is determined, and then whether the real-time power factor is abnormal is determined based on the fluctuation range comparison result and the fluctuation frequency comparison result.

[0118] Specifically, the preset fluctuation range in the embodiment of the present invention is determined according to the minimum and maximum values ​​in the historical detection data of the normal operation of the power distribution equipment;

[0119] The preset fluctuation frequency is obtained by analyzing a curve drawn based on historical detection data of normal operation of the power distribution equipment.

[0120] Specifically, the steps of analyzing the fluctuation pattern within the power factor variation curve cycle include:

[0121] Identifying a plurality of peak values ​​and a plurality of trough values ​​in the power factor variation curve;

[0122] The distribution of the peak values ​​and the trough values ​​is determined respectively, so as to further determine the fluctuation mode according to the distribution.

[0123] Specifically, the step of judging the actual fault degree of the power distribution equipment according to the operation fault of the power distribution equipment and the corrected physical fault result includes:

[0124] Calculating a real-time fault index of the power distribution equipment according to the operational fault of the power distribution equipment and the corrected physical fault result, wherein the real-time fault index includes the frequency, duration and severity of the fault;

[0125] The real-time fault index is compared and analyzed with the historical fault data to determine the actual fault extent according to the comparison and analysis result.

[0126] See also Figure 4 As shown, the step of determining the predicted fault degree based on the real-time operation data, the real-time physical data and the power distribution fault digital twin model includes:

[0127] Step S410, inputting the real-time operation data and the real-time physical data into a power distribution fault digital twin model;

[0128] Step S420, the power distribution fault digital twin model simulates the operating status and fault development process of the power distribution equipment according to the input data;

[0129] Step S430: predicting the fault degree of the power distribution equipment according to the simulation result to obtain the predicted fault degree.

[0130] Specifically, the embodiment of the present invention inputs real-time operating data and real-time physical data into the digital twin model of power distribution faults. The model can simulate the operating status and fault development process of the power distribution equipment based on these data, and more accurately predict the degree of equipment failure.

[0131] Specifically, the step of correcting the power distribution fault digital twin model according to the comparison result includes:

[0132] calculating the difference between the actual fault degree and the predicted fault degree, and analyzing the difference;

[0133] According to the difference analysis results, adjust the relevant parameters in the distribution fault digital twin model;

[0134] The above process is repeated until the difference between the predicted fault degree and the actual fault degree is less than a preset threshold, thereby obtaining a target power distribution fault digital twin model.

[0135] Specifically, a possible example of correction in the digital twin model of power distribution fault in an embodiment of the present invention is that a circuit breaker in the distribution cabinet is damaged due to overheating, and the actual fault degree is evaluated as "serious". The digital twin model predicts that the fault degree of the distribution cabinet is "minor", and it is considered that the distribution cabinet is operating normally. There is a significant difference between the actual fault degree and the predicted fault degree. Analysis shows that the model fails to accurately simulate the heat accumulation effect of the circuit breaker in a high temperature environment. The model does not take into account the impact of frequent fluctuations in the circuit breaker load on the failure probability. The thermal model is updated to better reflect the thermal behavior of the circuit breaker under high temperature conditions, and the impact of load fluctuations on fault prediction is increased. The corrected model is re-run, and the new prediction results show that the fault degree of the distribution cabinet is "serious", which is consistent with the actual fault degree. After multiple iterations, the difference between the predicted fault degree and the actual fault degree drops below the preset threshold, and finally the target power distribution fault digital twin model is obtained.

[0136] Specifically, in the embodiments of the present invention, when the actual fault degree reaches the following degrees, it may cause abnormal operation: Severe: The equipment fails completely and needs to be shut down for maintenance immediately. For example, the circuit breaker in the power distribution cabinet is damaged due to overheating, causing the entire power distribution cabinet to fail to work normally, affecting the normal operation of the airport lighting system;

[0137] Moderate: Equipment performance has significantly degraded and a planned shutdown may be required for repair. For example, if the insulation material inside the transformer is partially damaged, the equipment can still operate but there is a high risk of failure, which may cause a power outage at any time.

[0138] Minor: Equipment performance has slightly decreased but is still within the safe operating range. Immediate shutdown may not be required, but enhanced monitoring and regular inspections are required to prevent further development of the fault.

[0139] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0140] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for predicting key equipment failures of airport lighting stations based on digital twins, characterized in that: include: Collecting real-time operation data and real-time physical data of the power distribution equipment in the airport lighting station, as well as real-time environmental data corresponding to the power distribution equipment, wherein the real-time operation data includes real-time current value, real-time voltage value and real-time power factor value; Determine the operation fault of the power distribution equipment based on some of the real-time operation data, and determine the physical fault of the power distribution equipment based on some of the real-time physical data; Correcting the physical fault judgment result based on the real-time environmental data, so as to further judge the actual fault degree of the power distribution equipment according to the operation fault of the power distribution equipment and the corrected physical fault result; Determining a predicted fault degree based on the real-time operation data, the real-time physical data, and the power distribution fault digital twin model; Respectively comparing the actual fault degree with the predicted fault degree, and modifying the power distribution fault digital twin model according to the comparison result; The step of determining the physical fault of the power distribution equipment based on the real-time physical data comprises: Collecting several real-time device temperature values ​​of the power distribution equipment; Collecting several real-time vibration values ​​of the power distribution equipment; Draw a real-time device temperature change curve based on the real-time device temperature values, compare it with a preset device temperature change curve, and determine device temperature abnormality according to the comparison result; Draw a real-time vibration change curve based on the real-time vibration values, compare it with a preset vibration change curve, and judge the vibration abnormality of the equipment according to the comparison result; Determining the physical fault according to the abnormal temperature of the device and the abnormal vibration of the device; The step of correcting the physical fault judgment result based on the real-time environmental data comprises: Collect several real-time ambient temperature values ​​and real-time wind strength values; Draw a real-time ambient temperature change curve based on a number of real-time ambient temperature values; Draw a real-time wind force change curve based on the real-time wind force intensity value; Comparing the real-time environment temperature change curve with the real-time device temperature change curve, and correcting the device temperature anomaly according to the comparison result; The real-time wind force change curve is compared with the real-time vibration change curve, and the abnormal vibration of the equipment is corrected according to the comparison result.

2. According to claim 1, the method for predicting key equipment failures of airport lighting stations based on digital twins is characterized in that: The step of judging the operation fault of the power distribution equipment based on the real-time operation data comprises: Collecting several real-time current values, real-time voltage values ​​and real-time power factor values ​​of the power distribution equipment; Calculating a plurality of real-time power values ​​based on the plurality of real-time current values ​​and the plurality of real-time voltage values ​​corresponding thereto; Draw a real-time power change curve based on several real-time power values, compare it with a preset power change curve, and determine power anomalies; Based on a number of real-time power factor values, a power factor change curve is drawn, and the fluctuation of the power factor change curve is judged, so as to determine the real-time power factor abnormality according to the result of the fluctuation judgment; The operation fault is determined based on the real-time power abnormality and the power factor abnormality.

3. The method for predicting key equipment failures of airport lighting stations based on digital twins according to claim 2 is characterized in that: The step of determining the fluctuation of the power factor variation curve comprises: Identify whether the power factor variation curve is a periodic fluctuation; When the power factor variation curve fluctuates periodically, the actual fluctuation period of the power factor variation curve, the actual fluctuation range within the period, and the actual fluctuation frequency are determined.

4. The method for predicting key equipment failures of airport lighting stations based on digital twins according to claim 3 is characterized in that: According to the fluctuation results, the real-time power factor abnormality is determined, including: When the power factor variation curve is a periodic fluctuation, analyzing the fluctuation pattern within the period of the power factor variation curve; If the fluctuation mode is abnormal, the real-time power factor is abnormal; If the fluctuation mode is normal, the comparison result between the actual fluctuation range and the preset fluctuation range is determined, and the comparison result between the actual fluctuation frequency and the preset fluctuation frequency is determined, and then whether the real-time power factor is abnormal is determined based on the fluctuation range comparison result and the fluctuation frequency comparison result.

5. The method for predicting key equipment failures of airport lighting stations based on digital twins according to claim 4 is characterized in that: The steps to analyze the fluctuation pattern within the power factor variation curve cycle include: Identifying a plurality of peak values ​​and a plurality of trough values ​​in the power factor variation curve; The distribution of the peak values ​​and the trough values ​​is determined respectively, so as to further determine the fluctuation mode according to the distribution.

6. The method for predicting key equipment failures of airport lighting stations based on digital twins according to claim 5 is characterized in that: The step of judging the actual fault degree of the power distribution equipment according to the operation fault of the power distribution equipment and the corrected physical fault result comprises: Calculating a real-time fault index of the power distribution equipment according to the operational fault of the power distribution equipment and the corrected physical fault result, wherein the real-time fault index includes the frequency, duration and severity of the fault; The real-time fault index is compared and analyzed with the historical fault data to determine the actual fault extent according to the comparison and analysis result.

7. The method for predicting key equipment failures of airport lighting stations based on digital twins according to claim 6 is characterized in that: The step of determining the predicted fault degree based on the real-time operation data, the real-time physical data and the power distribution fault digital twin model includes: Inputting the real-time operation data and the real-time physical data into a power distribution fault digital twin model; The distribution fault digital twin model simulates the operating status and fault development process of the distribution equipment based on the input data; The fault degree of the power distribution equipment is predicted according to the simulation result to obtain the predicted fault degree.

8. The method for predicting key equipment failures of airport lighting stations based on digital twins according to claim 7 is characterized in that: The step of correcting the power distribution fault digital twin model according to the comparison result includes: calculating the difference between the actual fault degree and the predicted fault degree, and analyzing the difference; According to the difference analysis results, adjust the relevant parameters in the distribution fault digital twin model; The above process is repeated until the difference between the predicted fault degree and the actual fault degree is less than a preset threshold, thereby obtaining a target power distribution fault digital twin model.

Images