A side-based power transmission equipment monitoring method and system

Abstract

The embodiment of the application discloses a kind of based on side's power transmission equipment monitoring method and system.The method comprises: the index of target power transmission equipment is monitored by sensor, and the operating data of target power transmission equipment is acquired;Determine the standardization score of operating data, according to the standard score of operating data, the adaptive deviation correction term of operating data and proportional coefficient, determine the comprehensive health score of target power transmission equipment;According to the comprehensive health score of target power transmission equipment, standardization score and trend factor, determine the comprehensive score index of target power transmission equipment;According to the comprehensive score index of target power transmission equipment, the equipment operating state of target power transmission equipment is determined.The above-mentioned scheme can accurately evaluate the equipment operating state of target power transmission equipment based on the operating data of target power transmission equipment, accurately evaluate considering the relevance of operating data between different sampling periods, improve the accuracy and reliability of target power transmission equipment operating state evaluation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power equipment monitoring, in particular to a power transmission equipment monitoring method and system based on edge side. BACKGROUND

[0002] Power transmission equipment refers to equipment responsible for power transmission, protection, control and other functions in a power transmission system, mainly including substations, power transmission lines, transformers, circuit breakers, disconnectors and the like. Power transmission equipment plays a crucial role in the power system. They carry the transmission of electric power, protect the power system and control the flow of electric current. Substations convert high-voltage power into low-voltage power suitable for the power supply system, power transmission lines transport electric current from power plants to different places, transformers adjust voltage and current size, circuit breakers protect equipment and personnel safety, and disconnectors cut off power line transmission equipment during maintenance. The state monitoring of power transmission equipment is crucial for the safe operation of the power system. Power transmission equipment monitoring based on edge side refers to real-time monitoring and data analysis of power transmission equipment to assess its operating state and potential faults, ensuring stable operation and safety of the equipment.

[0003] In the current power transmission equipment monitoring scheme based on edge side, whether the operating state of the power transmission equipment is normal is only determined according to whether the voltage and current of the power transmission equipment exceed a certain threshold, which is one-sided and cannot accurately and comprehensively evaluate the operating state of the power transmission equipment, resulting in low accuracy. SUMMARY

[0004] The embodiments of the present application provide a power transmission equipment monitoring method and system based on edge side to comprehensively determine the operating state of the target power transmission equipment.

[0005] According to an aspect of the present application, a power transmission equipment monitoring method based on edge side is provided, which comprises:

[0006] The sensor monitors the indicators of the target power transmission equipment to obtain the operating data of the target power transmission equipment; wherein the operating data includes at least one of the current, voltage, temperature and vibration amount of the target power transmission equipment;

[0007] The standardized score of the operating data is determined, and the comprehensive health score of the target power transmission equipment is determined according to the standardized score of the operating data, the adaptive bias correction term of the operating data and the proportional coefficient; wherein the standardized score reflects the deviation degree of the operating data of each sampling period relative to the average value; the adaptive bias correction term reflects the deviation degree of the operating data of the current sampling period relative to the operating data of the previous sampling periods;

[0008] The comprehensive score index of the target power transmission equipment is determined according to the comprehensive health score, the standardized score and the trend factor of the target power transmission equipment.

[0009] determine the equipment operation state of the target power transmission equipment according to the comprehensive score index of the target power transmission equipment.

[0010] According to an aspect of the present application, a side-based power transmission equipment monitoring system is provided, which comprises:

[0011] a server, a data acquisition module, a side processing module, and an evaluation response module; the data acquisition module, the side processing module, and the evaluation response module are connected with the server respectively;

[0012] The data acquisition module acquires operation data of a target power transmission equipment, the side processing module performs localized processing on the operation data transmitted by the data acquisition module to analyze the operation state of the target power transmission equipment in real time and generate a health state report of the target power transmission equipment, the evaluation response module evaluates the health state report of the target power transmission equipment to form an evaluation result, and generates a maintenance strategy for the target power transmission equipment according to the evaluation result:

[0013] The side processing module comprises a data receiving unit, a state analysis unit, and a local alarm unit, the data receiving unit receives operation data from the data acquisition module, the state analysis unit processes and analyzes the received operation data to form an analysis result to obtain the health state report of the target power transmission equipment, and the local alarm unit triggers a warning according to the health state report and prompts maintenance personnel to handle.

[0014] The technical scheme of the embodiment of the present application monitors the indexes of a target power transmission equipment through a sensor to acquire operation data of the target power transmission equipment; wherein the operation data comprises at least one of current, voltage, temperature, and vibration amount of the target power transmission equipment; a standardized score of the operation data is determined, a comprehensive health score of the target power transmission equipment is determined according to the standardized score of the operation data, an adaptive bias correction term of the operation data, and a proportional coefficient; wherein the standardized score reflects the deviation degree of the operation data of each sampling period relative to the average value; the adaptive bias correction term reflects the deviation degree of the operation data of the current sampling period relative to the operation data of each previous sampling period; a comprehensive score index of the target power transmission equipment is determined according to the comprehensive health score of the target power transmission equipment, the standardized score, and a trend factor; and the equipment operation state of the target power transmission equipment is determined according to the comprehensive score index of the target power transmission equipment. The above scheme can accurately evaluate the equipment operation state of the target power transmission equipment based on the operation data of the target power transmission equipment, accurately evaluate considering the correlation between different sampling periods, and improve the accuracy and reliability of the evaluation of the operation state of the target power transmission equipment.

[0015] It should be understood that the contents described in this part are not intended to identify key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0017] Figure 1 A flow chart of a power transmission equipment monitoring method based on edge side provided by an embodiment of the present application;

[0018] Figure 2 A structural schematic diagram of a power transmission equipment monitoring system based on edge side provided by an embodiment of the present application;

[0019] Figure 3 A local alarm unit connection schematic diagram provided by an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to make the person skilled in the art better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0021] It should be noted that the terms "first", "second", "third", "fourth", "actual", "preset" and the like in the specification and claims of the present application and the above drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0022] Figure 1A flowchart of a power transmission equipment monitoring method based on edge side is provided for an embodiment of the present application. The embodiment of the present application can be applicable to the case of determining the running state of the power transmission equipment. The method can be executed by an edge side-based power transmission equipment monitoring device, which can be realized in the form of hardware and / or software and can be configured in an electronic device. As shown in Figure 1 the method includes the following steps.

[0023] S110, monitoring the indicators of the target power transmission equipment by the sensor to obtain the running data of the target power transmission equipment; wherein the running data includes at least one of the current, voltage, temperature and vibration amount of the target power transmission equipment.

[0024] The sensor is a sensor corresponding to the running data. For example, when the running data is voltage, the sensor is a voltage sensor; when the running data is current, the sensor is a current sensor; when the running data is temperature, the sensor is a temperature sensor; and when the running data is vibration amount, the sensor is a vibration sensor. The target power transmission equipment is the power transmission equipment that needs to be monitored, and the running data includes at least one of the current, voltage, temperature and vibration amount.

[0025] For example, during the running of the target power transmission equipment, the indicators of the target power transmission equipment can be monitored by the sensor to obtain the running data of the target power transmission equipment, so as to evaluate the running state of the target power transmission equipment based on the running data.

[0026] S120, determining the standardized score of the running data, and determining the comprehensive health score of the target power transmission equipment according to the standardized score of the running data, the adaptive deviation correction term of the running data and the proportional coefficient; wherein the standardized score reflects the deviation degree of the running data of each sampling period relative to the average value; and the adaptive deviation correction term reflects the deviation degree of the running data of the current sampling period relative to the running data of the previous sampling periods.

[0027] The standardized score of the running data reflects the deviation degree of the running data of each sampling period relative to the average value, which can be determined by the average value of the running data obtained in the current sampling period and the running data obtained in the historical sampling periods. The adaptive deviation correction term reflects the deviation degree of the running data of the current sampling period relative to the running data of the previous sampling periods, which can be determined by the running data obtained in the current sampling period and the running data obtained in the previous sampling periods. The proportional coefficient can be a coefficient for adjustment, which is a constant term.

[0028] In the present application, for the operation data obtained in the current sampling period, a standardization score of the operation data can be determined, and according to the standardization score of the operation data, an adaptive deviation correction term and a proportional coefficient, a comprehensive health score of the target power transmission equipment is determined, reflecting the operation of the target power transmission equipment.

[0029] In the present application, for the operation data obtained in the current sampling period, a standardization score of the operation data can be determined, and according to the standardization score of the operation data, an adaptive deviation correction term and a proportional coefficient, a comprehensive health score of the target power transmission equipment is determined, reflecting the operation of the target power transmission equipment.

[0030] In the present application, for the operation data obtained in the current sampling period, a standardization score of the operation data can be determined, and according to the standardization score of the operation data, an adaptive deviation correction term and a proportional coefficient, a comprehensive health score of the target power transmission equipment is determined, reflecting the operation of the target power transmission equipment.

[0031] In the present application, for the operation data obtained in the current sampling period, a standardization score of the operation data can be determined, and according to the standardization score of the operation data, an adaptive deviation correction term and a proportional coefficient, a comprehensive health score of the target power transmission equipment is determined, reflecting the operation of the target power transmission equipment.

[0032] In the present application, for the operation data obtained in the current sampling period, a standardization score of the operation data can be determined, and according to the standardization score of the operation data, an adaptive deviation correction term and a proportional coefficient, a comprehensive health score of the target power transmission equipment is determined, reflecting the operation of the target power transmission equipment.

[0033] In the present application, for the operation data obtained in the current sampling period, a standardization score of the operation data can be determined, and according to the standardization score of the operation data, an adaptive deviation correction term and a proportional coefficient, a comprehensive health score of the target power transmission equipment is determined, reflecting the operation of the target power transmission equipment.

[0034] As a non-limiting implementation, the method further comprises:

[0035] For each existing power transmission device, determining criticality data of each existing power transmission device according to a device type and / or a use scenario of the existing power transmission device;

[0036] Dividing the criticality data into different data intervals and determining a corresponding relationship between the data intervals and the proportionality coefficients; wherein the criticality data of different data intervals is positively correlated with the proportionality coefficients;

[0037] The determination process of the proportionality coefficients comprises:

[0038] Determining the criticality data of the target power transmission device, and determining, from the corresponding relationship, a proportionality coefficient corresponding to a data interval in which the criticality data of the target power transmission device is located, as the proportionality coefficient of the target power transmission device.

[0039] In the embodiments of the present application, the proportion coefficient can be adaptively selected according to actual conditions. Specifically, the proportion coefficient can be determined according to the actual type and application scenario of the target power transmission equipment. The key data of each existing power transmission equipment can be determined in advance according to the equipment type and / or use scenario of the existing power transmission equipment, reflecting the key degree of the operating state of the existing power transmission equipment. The key data is divided into different data intervals, and the corresponding relationship between each data interval and the proportion coefficient is determined, so that the key data in each data interval is positively correlated with the proportion coefficient. Specifically, assuming that the existing power transmission equipment is a transformer of a transformer substation, and / or the existing power transmission equipment is used in a scenario with high fault risk, the key data of the existing power transmission equipment is large. Assuming that the existing power transmission equipment is a regional power transmission line, and / or is used in a scenario with moderate fault risk, the key data of the existing power transmission equipment is moderate. Assuming that the existing power transmission equipment is an indoor power transformation equipment or a standby equipment, and / or is used in an environment with stable environment and stable state, the key data of the existing power transmission equipment is minimum. Different proportion coefficients are set for different key data intervals. For example, for the data interval with the largest key data, the proportion coefficient can be set to be the largest. In this scenario, the stability of the existing power transmission equipment is crucial to the operation of the entire system, and the comprehensive health score needs to be highly sensitive, so as to detect deviations in time and respond to maintenance, for example, the proportion coefficient is set to 18-20. A higher proportion coefficient makes the comprehensive health score more sensitive to the fluctuation of each deviation, and can quickly reflect the state change of the existing power transmission equipment. For example, if the vibration or current fluctuates slightly, the comprehensive health score will decrease significantly, reminding the monitoring personnel to take inspection measures quickly to prevent fault risk. For the data interval with moderate key data, the proportion coefficient can be set to be moderate. For the power transmission line monitored daily, the operating environment of the existing power transmission equipment is relatively stable, but it still needs to maintain moderate sensitivity to detect abnormalities as soon as possible without being too sensitive to short-term fluctuations. For example, the proportion coefficient is set to 14-17. The moderate proportion coefficient can ensure a certain sensitivity without frequent fluctuations. The comprehensive health score of the existing power transmission equipment will not change frequently due to short-term small fluctuations, but when the temperature, current and other parameters deviate significantly, the comprehensive health score will decrease significantly, reminding the maintenance personnel to pay attention. For the data interval with the smallest key data, the proportion coefficient can be set to be the smallest. In this case, the operating environment of the existing power transmission equipment is basically not affected by external factors, and the fluctuation is small, so the sensitivity of the comprehensive health score is low, and the focus is on the long-term change of the overall state of the existing power transmission equipment. For example, the proportion coefficient is set to 10-13. A smaller proportion coefficient makes the comprehensive health score less sensitive to small deviations, which helps to maintain the stability of the score.When the long-term data changes little, the score will not change frequently due to short-term fluctuations, but when the existing power transmission equipment state deviates greatly, the comprehensive health score can still reflect the changes.

[0040] In addition, in the scenario where seasonal load fluctuation is obvious, such as the existing power transmission equipment with large seasonal load fluctuation, in this scenario, the load of the existing power transmission equipment changes with the season, and the comprehensive health score needs to adapt to the periodic fluctuation of the load, while avoiding frequent fluctuations due to seasonal small fluctuations. The proportion coefficient is set to 15-18. The value of the proportion coefficient can take into account the load fluctuation and the stability requirement of the equipment. The comprehensive health score of the existing power transmission equipment during the load peak period will not be too obvious, but it can still maintain high sensitivity to serious fluctuations.

[0041] For example, for the target power transmission equipment, the criticality data of the target power transmission equipment can be determined, for example, the device type and / or application environment of the target power transmission equipment are determined, the criticality data of the target power transmission equipment is determined according to the device type and / or application environment, and then the proportion coefficient corresponding to the criticality data of the target power transmission equipment is determined from the corresponding relationship as the proportion coefficient of the target power transmission equipment.

[0042] As a non-limiting implementation, the standardized score of the operation data is determined, and the comprehensive health score of the target power transmission equipment is determined according to the standardized score of the operation data, the adaptive deviation correction term of the operation data, and the proportion coefficient, comprising:

[0043] The comprehensive health score of the target power transmission equipment is determined based on the following formula:

[0044] H score (t)=a-K·ln(1+Z V (t) 2 +Z I (t) 2 +Z T (t) 2 +Z Vib (t) 2 )-A(t);

[0045] Wherein, H score (t) is the comprehensive health score of the target power transmission equipment; Z V (t) is the standardized score of the voltage in the tth sampling period, Z I (t) is the standardized score of the current in the tth sampling period, Z T (t) is the standardized score of the temperature in the tth sampling period, Z Vib (t) is the standardized score of the vibration in the tth sampling period, A(t) is the adaptive deviation correction term in the tth sampling period, K is the proportion coefficient, and a is the constant term.

[0046] In the above formula, a can be 100, that is, the full score is set as 100, and the quantified value of the deviation of the running data in the current sampling period from the average value is subtracted from the full score, and the quantified value of the deviation of the running data in the current sampling period from the running data in the previous sampling periods is subtracted from the full score, so as to reflect the comprehensive health score of the target power transmission device at present.

[0047] The normalized score Z of the voltage in the tth sampling period V (t) is calculated according to the following formula:

[0048]

[0049] In the formula, V smooth (t) is the smoothed voltage value in the tth sampling period, is the historical average value of the voltage in the preset sampling period, and σ V is the historical standard deviation of the voltage in the preset sampling period.

[0050] The historical average value of the voltage in the preset sampling period is calculated according to the following formula:

[0051]

[0052] In the formula, N is the number of sampling periods used to calculate the average value, for example, the average value of the past 50 sampling periods, and N is 50. V smooth (t) is the smoothed voltage value in the tth sampling period,

[0053] The historical standard deviation of the voltage in the preset sampling period σ V is calculated according to the following formula:

[0054]

[0055] In the formula, N is the number of sampling periods used to calculate the average value, for example, the average value of the past 50 sampling periods, and N is 50. V smooth (t) is the smoothed voltage value in the tth sampling period, is the historical average value of the voltage.

[0056] The normalized score Z of the current deviation in the tth sampling period I (t) is calculated according to the following formula:

[0057]

[0058] In the formula, I smooth (t) is the smoothed current value in the tth sampling period, is the historical average of the current in the preset sampling period, σ I is the historical standard deviation of the current in the preset sampling period.

[0059] is the historical average of the current in the preset sampling period, σ is calculated according to the following formula:

[0060]

[0061] wherein N is the number of sampling periods used to calculate the average, for example, the average of the past 50 sampling periods, then N is 50. I smooth (t) is the smoothed current value in the tth sampling period, is the historical average of the current in the preset sampling period, σ

[0062] is the historical standard deviation of the current in the preset sampling period. I is calculated according to the following formula:

[0063]

[0064] wherein N is the number of sampling periods used to calculate the average, for example, the average of the past 50 sampling periods, then N is 50. I smooth (t) is the smoothed current value in the tth sampling period, is the historical average of the current in the preset sampling period, σ

[0065] is the normalized score Z of the temperature deviation in the tth sampling period T (t) is calculated according to the following formula:

[0066]

[0067] wherein T smooth (t) is the smoothed temperature value in the tth sampling period, is the historical average of the temperature in the preset sampling period, σ T is the historical standard deviation of the temperature in the preset sampling period.

[0068] is the historical average of the temperature in the preset sampling period, σ is calculated according to the following formula:

[0069]

[0070] wherein N is the number of sampling periods used to calculate the average, for example, the average of the past 50 sampling periods, then N is 50. T smooth (t) is the smoothed temperature value in the tth sampling period, is the historical average of the temperature in the preset sampling period, σ

[0071] Historical standard deviation σ of temperature in preset sampling period T is calculated according to the following formula:

[0072]

[0073] wherein N is the number of sampling periods used to calculate the average value, for example, the average value of the past 50 sampling periods, then N is 50. T smooth (t) is the smoothed temperature value of the tth sampling period, is the historical average value of temperature.

[0074] Standardized score Z of vibration amount deviation of the tth sampling period Vib (t) is calculated according to the following formula:

[0075]

[0076] wherein Vib smooth (t) is the smoothed vibration amount data of the tth sampling period, is the historical average value of vibration amount in preset sampling period, σ Vib (t) is the historical standard deviation of vibration amount in preset sampling period.

[0077] Historical average value of vibration amount in preset sampling period is calculated according to the following formula:

[0078]

[0079] wherein N is the number of sampling periods used to calculate the average value, for example, the average value of the past 50 sampling periods, then N is 50. Vib smooth (t) is the smoothed vibration amount value of the tth sampling period, is the historical average value of vibration amount.

[0080] Historical standard deviation σ of vibration amount in preset sampling period T is calculated according to the following formula:

[0081]

[0082] wherein N is the number of sampling periods used to calculate the average value, for example, the average value of the past 50 sampling periods, then N is 50. Vib smooth (t) is the smoothed vibration amount value of the tth sampling period, is the historical average value of vibration amount.

[0083] As a non-limiting implementation, the determination process of the tth sampling period smoothed operation data used to determine the standardized score of the operation data of the tth sampling period comprises:

[0084] determining the operation data collected in the current sampling period and the operation data smoothed in the last sampling period;

[0085] performing weighted summation on the operation data collected in the current sampling period and the operation data smoothed in the last sampling period to obtain the operation data smoothed in the current sampling period; wherein the operation data comprises at least one of voltage, current, temperature and vibration.

[0086] For example, the operation data is vibration, and the operation data smoothed in the current sampling period is illustrated.

[0087] Vib smooth (t) is the vibration smoothed in the tth sampling period, which is calculated according to the following formula:

[0088] Vib smooth (t) = a · Vib(t) + (1-a) · Vib smooth (t-1);

[0089] In the formula, a is the weight value corresponding to the vibration in the tth sampling period (usually 0 smooth (t-1) is the vibration smoothed in the last sampling period.

[0090] As a non-limiting implementation, the process for determining the weight value for weighted summation comprises:

[0091] determining the monitoring timeliness data of the target power transmission equipment;

[0092] making the weight value of the operation data collected in the current sampling period positively correlated with the monitoring timeliness data;

[0093] taking the difference between the weight value of the operation data collected in the current sampling period and the weight value of the operation data smoothed in the last sampling period as the operation data smoothed in the last sampling period;

[0094] wherein the monitoring timeliness data is positively correlated with the monitoring timeliness of the target power transmission equipment.

[0095] Exemplarily, the monitoring timeliness of the target power transmission equipment can be quantitatively represented, and the monitoring timeliness data is represented. The weight value of the operation data collected in the current sampling period is positively correlated with the detection timeliness data, so that in the scene with strong timeliness, the operation data of the current sampling period is mainly focused on, and the weight value of the operation data collected in the current sampling period is subtracted as the operation data of the previous sampling period after smoothing processing. In the scene with weak timeliness, more consideration is given to the influence of the operation data of the past sampling period.

[0096] Specifically, the specific value of the weight value a in the following scene can be:

[0097] 1) The target power transmission equipment for quickly detecting mechanical faults

[0098] In some scenes with high sensitivity requirements, such as mechanical state monitoring of high-voltage switches or transformers, quickly detecting changes in vibration data helps to identify equipment abnormalities in a timely manner. At this time, the smoothing processing of the vibration quantity data needs to respond more quickly to changes in the latest data, and then: a = 0.3 to 0.5;

[0099] Among them, a higher a value can more quickly respond to changes in the vibration quantity, which helps to discover mechanical faults in a timely manner and avoid potential risks.

[0100] 2) The target power transmission equipment for daily monitoring, such as medium-frequency fluctuation:

[0101] For the target power transmission equipment for daily monitoring, such as transformers or circuit breakers, the vibration quantity data has certain fluctuations, but the fluctuation frequency is low. At this time, the smoothing processing needs to moderately pay attention to the latest data, while not being too sensitive to avoid the influence of short-term fluctuations on the judgment, and then a = 0.15 to 0.25;

[0102] Among them, a moderate a value can balance the influence of the latest data and the historical data, and is suitable for data with moderate fluctuation amplitude, so that the comprehensive health score does not change dramatically due to short-term fluctuations.

[0103] 3) Stable equipment environment, such as low fluctuation monitoring:

[0104] In some scenes where the equipment operating environment is very stable, such as indoor power transmission transformer equipment, the vibration quantity changes very little, and the health state is relatively stable. At this time, the purpose of data smoothing is to keep the score stable, and more emphasis is placed on historical trends, and then a = 0.05 to 0.1;

[0105] Among them, a lower a value makes the smoothing result more dependent on historical data, which is suitable for devices running stably, and reduces the situation that the score is unstable due to short-term slight fluctuations.

[0106] 4) Special monitoring tasks, such as seasonal load changes:

[0107] If the environment or load condition of the device has periodic fluctuations (such as seasonal load changes), the smoothing coefficient can be selected in a moderate range to smooth small fluctuations and capture larger changes, and a = 0.2 to 0.3.

[0108] Among them, selecting a moderate to high smoothing coefficient can adapt to seasonal change trends while avoiding short-term fluctuations, making the device state more in line with the true situation of periodic load.

[0109] As a non-limiting implementation, the determination process of the adaptive bias correction term of the operation data includes:

[0110] For each sampling period, the difference between the operation data in the sampling period and the average value of the operation data of each sampling period before the sampling period is determined respectively;

[0111] The product of the difference value and the time weighting function corresponding to the sampling period is determined, and the average value of the product corresponding to each sampling period is determined as the adaptive bias correction term of the operation data; wherein the operation data includes at least one of voltage, current, temperature and vibration amount;

[0112] The determination process of the adaptive bias correction term of the target power transmission device includes:

[0113] The sum of the adaptive bias correction terms of each operation data is taken as the adaptive bias correction term of the target power transmission device.

[0114] In the embodiments of the present application, the operation data includes current, voltage, temperature, vibration amount, comprehensive health score, and bias information of each operation data (including current, voltage, temperature, vibration amount) of the target power transmission device;

[0115] The adaptive bias correction term A(t) of the tth sampling period is calculated according to the following formula:

[0116] A(t) = V adjust (t) + I adjust (t) + T adjust (t);

[0117] In the formula, V adjust (t) is the voltage bias correction term, I adjust (t) is the current bias correction term, and T adjust (t) is the temperature bias correction term;

[0118] Among them, the voltage bias correction term V adjust (t) is calculated according to the following formula:

[0119]

[0120] where V(t) is the voltage value at the current sampling period t, μ V (t) is the voltage average value before the current sampling period t (i.e., the average value of the historical voltage), W(t-(t-M)) = W(M) is the time weighting function of the Mth sampling period before the current sampling period t, V(t-M) is the voltage value of the Mth sampling period before the current sampling period t, μ V (t-M) is the voltage average value before the Mth sampling period before the current sampling period t (i.e., the average value of the voltage values before the Mth sampling period before the current sampling period t), V(t-(M-l)) is the voltage value of the (M-l)th sampling period before the current sampling period t, μ V (t-(M-l)) is the voltage average value before the (M-l)th sampling period before the current sampling period t (i.e., the average value of the voltage values before the (M-l)th sampling period before the current sampling period t), W(t-(t-(M-l))) is the time weighting function of the (M-l)th sampling period before the current sampling period t, W(t-t) is the time weighting function of the current sampling period t, W(t-t) = W(0) = e -λ*0 = 1, and M represents the number of past sampling periods used for the calculation, for example, 3 to 5 past periods.

[0121] In addition, the current deviation correction term I adjust (t) is calculated according to the following equation:

[0122]

[0123] where I(t) is the current value at the current sampling period t, μ I (t) is the current average value before the current sampling period t (i.e., the average value of the historical current), W(t-(t-M)) = W(M) is the time weighting function of the Mth sampling period before the current sampling period t, I(t-M) is the current value of the Mth sampling period before the current sampling period t, μ I (t-M) is the current average value before the Mth sampling period before the current sampling period t, I(t-(M-l)) is the current value of the (M-l)th sampling period before the current sampling period t, μ I (t-(M-l)) is the current average value before the (M-l)th sampling period before the current sampling period t, W(t-(t-(M-l))) is the time weighting function of the (M-l)th sampling period before the current sampling period t, W(t-t) is the time weighting function of the current sampling period t, W(t-t) = W(0) = e -λ*0 = 1, and M represents the number of past sampling periods used for the calculation, for example, 3 to 5 past periods.

[0124] Similarly, the temperature deviation correction term T adjust (t) is calculated according to the following formula:

[0125]

[0126] wherein T(t) is the temperature value of the current sampling period t, μ T (t) is the average temperature value before the current sampling period t (i.e. the average value of the historical temperature), W(t-(t-M))=W(M) is the time weighting function of the Mth sampling period before the current sampling period t, T(t-M) is the temperature of the Mth sampling period before the current sampling period t, μ T (t-M) is the average temperature value before the M-1th sampling period before the current sampling period t, T(t-(M-1)) is the temperature value of the M-1th sampling period before the current sampling period t, μ T (t-(M-1)) is the average temperature value before the M-1th sampling period before the current sampling period t, W(t-(t-(M-1))) is the time weighting function of the M-1th sampling period before the current sampling period t, W(t-t) is the time weighting function of the current sampling period t, W(t-t)=W(0)=e -λ*0 =1, and M represents the number of past sampling periods used for calculation, for example, 3 to 5 past periods.

[0127] In calculating the voltage deviation correction term V adjust (t), the current deviation correction term I adjust (t), and the temperature deviation correction term T adjust (t), if there is not enough data for M periods, the initial value or the initial historical average value set by the system or the initial value measured under normal operating conditions is used by default.

[0128] As a non-limiting implementation, the determination process of the time weighting function includes:

[0129] determining the product of the time decay coefficient and the number of sampling periods before the current sampling period, and taking the inverse to obtain the decay index;

[0130] taking the decay index as the independent variable of the natural exponential function, and calculating the time weighting function corresponding to the sampling period.

[0131] The time weighting function W(t-(t-M))=W(M) of the sampling period at the current time point t is calculated according to the following formula:

[0132] W(t-(t-M))=W(M)=e -λM ;

[0133] In the formula, M represents the number of past sampling periods for calculation, for example, 3 to 5 periods, and λ is a time decay coefficient, usually taking a value between 0.1 and 0.3; in this embodiment, a larger value of λ makes the weight of a more recent period higher.

[0134] Specifically, when λ takes a larger value (close to 0.3), the decay speed of the time weighting function is faster, which means that a sampling period closer to the current time t is given a higher weight, and the weight of a sampling period farther away decreases rapidly. Therefore, a larger value of λ makes the formula more sensitive to recent data and less sensitive to historical data.

[0135] When λ takes a smaller value (close to 0.1), the decay speed is slower, and the data of a sampling period farther away still has a relatively large influence in weighting. Therefore, a smaller value of λ makes the formula more smooth and stable in response to the entire historical data. Assuming that M = 3 (3 sampling periods in the past), taking voltage as an example, the voltage data of the past 3 sampling periods are 220V, 230V, and 225V, and the current sampling period is t.

[0136] The historical average value μ V (t) is calculated as follows:

[0137] 1) Calculate μ V (t-3): Since t-3 is the earliest sampling period, there is no enough sampling period data to refer to. By default, an initial value or an initial historical average value set by the system or an initial value measured under normal operating conditions is used to fill in, as μ V (t-3) = 220.

[0138] 2) Calculate μ V (t-2): The historical average value of t-2 can refer to the data of t-3,

[0139] Therefore, μ V (t-2) = 220 / 1 = 220.

[0140] 3) Calculate μ V (t-1): The historical average value of t-1 can refer to the data of t-3 and t-2,

[0141] μ V (t-1) = (220 + 230) / 2 = 225.

[0142] 4) Calculate μ V (t): The historical average value of t can refer to the data of t-3, t-2, and t-1,

[0143] μ V (t) = (220 + 230 + 225) / 3 = 225.

[0144] Calculate the absolute value of the deviation for each sampling period:

[0145] Substituting these historical averages, we calculate the absolute value of the deviation for each sampling period:

[0146] First sampling period (time point t-3) (voltage value: 220):

[0147] Absolute value of deviation |220-μ V (t-3)∣=∣220-220∣=0;

[0148] Second sampling period (time point t-2) (voltage value: 230):

[0149] Absolute value of deviation |230-μ V (t-2)∣=∣230-220∣=10;

[0150] Third sampling period (time point t-1) (voltage value: 225):

[0151] Absolute value of deviation |225-μ V (t-1)∣=∣225-225∣=0;

[0152] Calculate the time-weighted function: Assuming λ = 0.1 (λ is the time decay coefficient, and the system sets this value to λ = 0.1 after 3 sampling periods), then:

[0153] For M = 3: W(t - 3) = e 0.1*3 =e -0.3 ;

[0154] For M = 2: W(t-2) = e 0.1*2 =e -0.2 ;

[0155] For M=1: W(t-1)=e 0.1*1 =e -0.1 ;

[0156] Calculate the adaptive deviation correction term V adjust (t): Substituting the absolute value of the deviation and the time-weighted function into the formula:

[0157] V adjust (t)=1 / 3(0*W(t-3)+10*W(t-2)+0*W(t-1))=1 / 3(0*e -0.3 +10*e -0.2 +0*

[0158] e -0.1 );

[0159] Based on the example steps above, calculate the voltage deviation correction term V respectively.adjust (t), a current deviation correction term I adjust (t) and a temperature deviation correction term T adjust (t), which are summed up to obtain A(t).

[0160] As a non-limiting implementation, a comprehensive score index of the target power transmission equipment is determined according to the comprehensive health score, the standardized score and the trend factor of the target power transmission equipment, comprising:

[0161] The comprehensive score index of the target power transmission equipment is determined according to the following formula:

[0162]

[0163] Wherein, ER(t) is the comprehensive score index of the target power transmission equipment, H score (t) is the comprehensive health score of the target power transmission equipment, Z V (t) is the standardized score of voltage in the tth sampling period, Z I (t) is the standardized score of current in the tth sampling period, Z T (t) is the standardized score of temperature in the tth sampling period, Z Vib (t) is the standardized score of vibration in the tth sampling period, δ is an adjustment coefficient, and TF(t) is a trend factor in the tth sampling period.

[0164]

[0165] Wherein, σ TF is the historical standard deviation of the trend factor TF(t), μ TF is the historical average value of the trend factor TF(t).

[0166] Wherein, the historical average value μ TF of the trend factor TF(t) is calculated according to the following formula:

[0167]

[0168] N is the number of sampling periods for calculating the average value, TF(t) is the trend factor in the tth sampling period, and the formula is:

[0169]

[0170] In the formula, H score (t) is the comprehensive health score in the tth sampling period, H score (t-1) is the comprehensive health score in the previous sampling period.

[0171] In the embodiments of the present application, in the embodiments, the trend factor can be calculated starting from i = 1, and the first data point is usually used to initialize the system state, so skipping the calculation thereof will not affect the subsequent trend analysis and comprehensive health score. The calculation of the historical average value starts from the second data point and accumulates.

[0172] wherein, TF(t) > 0: indicates that the comprehensive health score is improved compared with the last sampling period, and the device state is improving;

[0173] TF(t) < 0: indicates that the comprehensive health score is decreased compared with the last sampling period, and the device state is possibly deteriorating;

[0174] TF(t) = 0: indicates that the comprehensive health score does not change, and the device state remains stable;

[0175] The historical standard deviation σ of the trend factor TF(t) TF is calculated according to the following formula:

[0176]

[0177] wherein, N is the number of sampling periods for calculating the average value, for example, the average value of the past 50 sampling periods, and N is 50. TF(t) is the trend factor of the t th sampling period, μ TF is the historical average value of the trend factor TF(t).

[0178] As a non-limiting implementation manner, the method further comprises:

[0179] in the case where the device running state of the power transmission device does not reach the preset state, notifying the maintenance personnel of the target power transmission device for maintenance through the terminal, and determining a trend evaluation index of the maintenance personnel;

[0180] wherein, the trend evaluation index of the maintenance personnel is determined based on the following formula:

[0181]

[0182] wherein, Completeness is the current completion degree of the assigned maintenance personnel, Completeness history is the historical average completion degree of the assigned maintenance personnel, and a is a trend influence coefficient.

[0183] the current completion degree

[0184] Time spent is the time consumed by the maintenance personnel for executing the maintenance work order; and Total time is the theoretical time consumption of the maintenance personnel for executing the maintenance work order.

[0185] Historical average completion rate

[0186] Completeness j M represents the completion rate of the assigned maintenance personnel in the j-th cycle, where M is the selected historical task cycle number.

[0187] Figure 2 A schematic diagram of a side-side-based power transmission equipment monitoring system provided in this application embodiment is shown below. Figure 2 As shown in the figure, an embodiment of this application provides a power transmission equipment monitoring system including:

[0188] Server 210, data acquisition module 220, side-side processing module 230, and evaluation response module 240; the data acquisition module 220, the side-side processing module 230, and the evaluation response module 240 are respectively connected to the server 210;

[0189] The data acquisition module 220 collects the operating data of the target power transmission equipment. The side-side processing module 230 performs localized processing on the operating data transmitted by the data acquisition module 220 to analyze the operating status of the target power transmission equipment in real time and generate a health status report. The evaluation and response module 240 evaluates the power transmission equipment based on the health status report to form an evaluation result, and generates the maintenance strategy for the target power transmission equipment based on the evaluation result.

[0190] The side-side processing module 230 includes a data receiving unit, a status analysis unit, and a local alarm unit, such as... Figure 3 As shown, the data receiving unit receives operating data from the data acquisition module, the status analysis unit processes and analyzes the received operating data to form an analysis result, thereby obtaining a health status report of the target power transmission equipment, and the local alarm unit triggers an early warning based on the health status report and prompts maintenance personnel to handle the situation.

[0191] The real-time monitoring system for the target power transmission equipment also includes a central processing unit (CPU). The CPU is connected to the data acquisition module, the side-side processing module, and the evaluation and response module. The CPU provides centralized control over the data acquisition module, the side-side processing module, and the evaluation and response module, and stores the control data of the CPU in a database, thereby improving the monitoring accuracy and reliability of the entire system for the target power transmission equipment.

[0192] Optionally, the data acquisition module comprises a sensor unit, a data transmission unit and a memory, the sensor unit acquires the operation data of the target power transmission equipment, the data transmission unit transmits the operation data acquired by the sensor unit to the memory, and the memory stores the operation data transmitted by the data transmission unit.

[0193] The sensor unit comprises a current sensor, a voltage sensor, a temperature sensor and a vibration sensor,

[0194] The current sensor is used to monitor the current of the target power transmission equipment, the voltage sensor is used to monitor the voltage fluctuation of the target power transmission equipment, the temperature sensor detects the temperature data of the target power transmission equipment, and the vibration sensor acquires the vibration data of the monitoring equipment.

[0195] The data transmission unit comprises a data acquisition interface, a data transmission controller and a communicator, the data acquisition interface is responsible for receiving data from the sensor unit and collecting different types of sensor data, the data transmission controller manages and controls the transmission of each sensor data, formats, packages and transmits the data transmitted by the acquisition interface to the memory, and the communicator transmits the packaged data in the data transmission controller to the memory.

[0196] The data transmission unit realizes data transmission according to the following steps:

[0197] S1, data acquisition and preprocessing: the data acquisition interface obtains current, voltage, temperature and vibration data from the sensor and performs preliminary signal conversion (such as ADC analog-digital conversion).

[0198] S2, data formatting and packaging: the data transmission controller receives the data of the acquisition interface, formats the data (such as adding time stamp, device ID, etc.) and packages the data for subsequent processing and storage.

[0199] S3, data transmission: the communicator selects a suitable transmission mode (such as RS-485, CAN, Ethernet, Wi-Fi) to send the formatted data to the memory. If it is wired transmission, the data will be directly sent to the memory address; if it is wireless transmission, the data transmission controller will perform short-term buffering in the wireless module to ensure data integrity.

[0200] S4, data storage: after receiving the data, the memory saves the data to the local storage area, so that the subsequent modules can read and process the data from the memory.

[0201] The side processing module comprises a data receiving unit, a state analyzing unit and a local alarm unit, the data receiving unit receives operation data from the data collecting module, the state analyzing unit processes and analyzes the received operation data to form an analysis result, so as to obtain the target power transmission equipment health state report, and the local alarm unit triggers a pre-warning according to the health state report and prompts on-site personnel to process.

[0202] Optionally, the data receiving unit comprises a scheduling requester, a receiver, a buffer and a data verifier, the scheduling requester sends a data request to the data collecting module, coordinates the time and frequency of data collection, the receiver receives operation data transmitted from the data collecting module, the buffer temporarily stores the operation data during data receiving, and the data verifier verifies the received operation data.

[0203] The verification step of the data verifier comprises:

[0204] S11, preset verification standard:

[0205] Selecting a verification algorithm: according to system requirements and data characteristics, a suitable verification algorithm is selected, for example, CRC-16 or CRC-32 (suitable for longer data and providing higher error detection capability), or simple checksum (suitable for short data or resource-limited applications).

[0206] Generating a polynomial: for CRC verification, a suitable polynomial generator is selected. For example, the commonly used generating polynomial of CRC-16 is 0x8005, and the commonly used generating polynomial of CRC-32 is 0x04C11DB7.

[0207] S12, data verification code generation

[0208] Calculating the verification code of the sending end: when sending the operation data, the data collecting module calculates the verification code of the operation data according to the set verification algorithm, and appends it to the end of the operation data frame and sends it to the data receiving unit.

[0209] Verification code transmission: after generating and packaging the verification code, the data collecting module sends the operation data and the verification code as a complete transmission frame to the receiving unit.

[0210] S13, receiving data and extracting verification code:

[0211] Receiving data frame: after receiving the operation data frame, the receiver in the data receiving unit transmits the operation data frame to the data verifier.

[0212] Extracting the verification code: the data verifier separates the original operation data and the appended verification code from the received operation data frame.

[0213] Assuming the data frame structure is [running data | check code], the checker separates the "running data part" and the "check code part".

[0214] S14, Recalculate the check code at the receiving end:

[0215] Calculate the check code at the receiving end: the data checker recalculates the check code using the same check algorithm according to the received running data content.

[0216] For CRC check, the checker will operate the data bit by bit and recalculate the check value using the generating polynomial.

[0217] For example, for CRC-16, the check code can be calculated in the following steps:

[0218] Initialize the CRC register to 0xFFFF.

[0219] XOR each byte of the running data bit by bit, and shift according to the generating polynomial until all data bits are processed.

[0220] The value obtained after calculation is the check code at the receiving end.

[0221] S15, Compare the check code

[0222] Check code comparison: the data checker compares the check code calculated at the receiving end with the check code in the data frame:

[0223] If they are consistent, the data check is passed, and the data is complete and accurate;

[0224] If they are not consistent, it indicates that the running data may have errors during transmission.

[0225] S16, Error handling:

[0226] Error marking or retransmission request:

[0227] If the check is passed, the running data is passed to the buffer and stored, and the subsequent module can normally use the data.

[0228] If the check is not passed, the data checker can mark the running data as error and send a retransmission request to the scheduling requester or data acquisition module.

[0229] Record error information during the check process to facilitate system monitoring of data receiving quality, or trigger an alarm according to system requirements.

[0230] Optionally, the state analysis unit obtains the operation data collected by the data receiving unit, and processes the operation data, the processing including removing outliers and smoothing, and calculates the comprehensive health score Hscore(t) of the t-th sampling period according to the following formula:

[0231] H score (t) = 100 - K ln(1 + Z V (t) 2 + Z I (t) 2 + Z T (t) 2 + Z Vib (t) 2 - A(t).

[0232] The higher the comprehensive health score H score (t) is, the better the working condition of the equipment is, and the lower score usually means that there may be problems or performance degradation. Therefore, when the comprehensive health score H score (t) is lower than a preset threshold, the local alarm unit triggers a warning. In the formula, Z V (t) is the standardized score of the pressure deviation of the t-th sampling period, Z I (t) is the standardized score of the current deviation of the t-th sampling period, Z T (t) is the standardized score of the temperature deviation of the t-th sampling period, Z Vib (t) is the standardized score of the vibration amount deviation of the t-th sampling period, A(t) is the adaptive deviation correction term of the t-th sampling period, and K is a proportional coefficient, the value of which is in the range of [10, 20], wherein the value of the proportional coefficient K should be adjusted according to the stability of the equipment operating environment and the sensitivity requirement of the comprehensive health score, specifically:

[0233] High sensitivity scenario: a higher K value (such as 18-20) is selected to make the comprehensive health score more sensitive and quickly respond to small deviations.

[0234] Medium sensitivity scenario: a medium K value (such as 14-17) is selected to ensure a certain sensitivity while not fluctuating too frequently, which is suitable for most scenarios.

[0235] Low sensitivity scenario: a lower K value (such as 10-13) is selected, which is suitable for high-stability environments to avoid frequent changes in the comprehensive health score due to small fluctuations.

[0236] Meanwhile, in this embodiment, an example of the value of the proportional coefficient K is given:

[0237] 1) Key target power transmission equipment or high-fault-risk scenario (such as substation main transformer):

[0238] In this scenario, the stability of the equipment is crucial to the operation of the entire system, and the comprehensive health score needs to be highly sensitive to detect deviations in time and respond to maintenance. The K value range is 18-20.

[0239] A higher K value makes the comprehensive health score more sensitive to fluctuations in each deviation, allowing it to quickly reflect changes in the state of the equipment. For example, if there is a slight fluctuation in vibration or current, the comprehensive health score will drop significantly, prompting monitoring personnel to take inspection measures quickly to prevent failure risks.

[0240] 2) Target power transmission equipment for daily monitoring (such as regional power transmission lines):

[0241] For daily monitoring of power transmission lines, the operating environment of the equipment is relatively stable, but it still needs to maintain appropriate sensitivity to detect abnormalities early without being overly sensitive to short-term fluctuations. The K value range is 14-17.

[0242] A moderate K value can ensure a certain degree of sensitivity while not fluctuating too frequently. The comprehensive health score of the target power transmission equipment will not change frequently due to short-term small fluctuations, but when there are significant deviations in temperature, current, etc., the comprehensive health score will decrease significantly, prompting maintenance personnel to pay attention.

[0243] 3) Target power transmission equipment with stable environment and stable state (such as indoor power transformation equipment or standby equipment):

[0244] In this case, the operating environment of the equipment is not affected by external factors, and the fluctuations are small, so the sensitivity of the comprehensive health score is relatively low, and more attention is paid to long-term changes in the overall state of the equipment. The K value range is 10-13.

[0245] A lower K value makes the comprehensive health score less responsive to small deviations, which helps maintain the stability of the score. When there are small fluctuations in the short term, the score will not change frequently, but when there are significant deviations in the state of the target power transmission equipment, the comprehensive health score can still reflect the changes significantly.

[0246] 4) Scenario with significant seasonal load fluctuations (such as target power transmission equipment with significant seasonal load fluctuations):

[0247] In this scenario, the load of the equipment changes with the seasons, and the comprehensive health score needs to adapt to the periodic fluctuations in the load while avoiding frequent fluctuations due to seasonal small fluctuations. The K value range is 15-18.

[0248] A moderately high K value can balance the needs of load fluctuations and equipment stability. The score of the target power transmission equipment during the load peak period will not decrease too significantly, but it can still maintain high sensitivity to severe fluctuations.

[0249] In summary, the value of the specific proportion coefficient K needs to be combined with the specific scene and the actual situation for value taking, and is input from the human-computer interaction interface, which is a technical means familiar to those skilled in the art, so in the embodiment, it will not be described one by one;

[0250] When the comprehensive health score H score After (t) is derived, the current state of the comprehensive operation data generates the health state analysis report of the tth sampling period.

[0251] The normalized score Z V (t) of the voltage of the tth sampling period is calculated according to the following formula:

[0252]

[0253] In the formula, V smooth (t) is the smoothed voltage value in the tth sampling period, is the historical average value of the voltage in the preset sampling period, and σ V is the historical standard deviation of the voltage in the preset sampling period.

[0254] The historical average value of the voltage in the preset sampling period is calculated according to the following formula:

[0255]

[0256] In the formula, N is the number of sampling periods for calculating the average value, for example, the average value of the past 50 sampling periods, then N is 50. V smooth (t) is the smoothed voltage value in the tth sampling period;

[0257] The historical standard deviation σ V of the voltage in the preset sampling period is calculated according to the following formula:

[0258]

[0259] In the formula, N is the number of sampling periods for calculating the average value, for example, the average value of the past 50 sampling periods, then N is 50. V smooth (t) is the smoothed voltage value in the tth sampling period, is the historical average value of the voltage.

[0260] The normalized score Z I (t) of the current deviation of the tth sampling period is calculated according to the following formula:

[0261]

[0262] In the formula, Ismooth (t) is the smoothed current value in the tth sampling period, is the historical average of the current in the preset sampling period, σ I is the historical standard deviation of the current in the preset sampling period.

[0263] is the historical average of the current in the preset sampling period. is calculated according to the following formula:

[0264]

[0265] In the formula, N is the number of sampling periods used to calculate the average value, for example, the average value of the past 50 sampling periods, then N is 50. smooth (t) is the smoothed current value in the tth sampling period, is the historical average of the current in the preset sampling period.

[0266] is the historical standard deviation of the current in the preset sampling period. I is calculated according to the following formula:

[0267]

[0268] In the formula, N is the number of sampling periods used to calculate the average value, for example, the average value of the past 50 sampling periods, then N is 50. smooth (t) is the smoothed current value in the tth sampling period, is the historical average of the current in the preset sampling period.

[0269] is the normalized score Z of the temperature deviation in the tth sampling period. T (t) is calculated according to the following formula:

[0270]

[0271] In the formula, T smooth (t) is the smoothed temperature value in the tth sampling period, is the historical average of the temperature in the preset sampling period, σ T is the historical standard deviation of the temperature in the preset sampling period.

[0272] is the historical average of the temperature in the preset sampling period. is calculated according to the following formula:

[0273]

[0274] In the formula, N is the number of sampling periods used to calculate the average value, for example, the average value of the past 50 sampling periods, then N is 50. smooth (t) is the smoothed temperature value in the tth sampling period, is the historical average of temperature.

[0275] is the historical standard deviation of temperature σ T is calculated according to the following formula:

[0276]

[0277] where N is the number of sampling periods used to calculate the average, for example, the average of the past 50 sampling periods, then N is 50. T smooth (t) is the smoothed temperature value of the tth sampling period, is the historical average of temperature.

[0278] is the normalized fraction of the vibration amount deviation of the tth sampling period Z Vib (t) is calculated according to the following formula:

[0279]

[0280] where N is the number of sampling periods used to calculate the average, for example, the average of the past 50 sampling periods, then N is 50. Vib smooth (t) is the smoothed vibration amount data of the tth sampling period, is the historical average of vibration amount σ Vib (t) is the historical standard deviation of vibration amount.

[0281] is the historical average of vibration amount is calculated according to the following formula:

[0282]

[0283] where N is the number of sampling periods used to calculate the average, for example, the average of the past 50 sampling periods, then N is 50. Vib smooth (t) is the smoothed vibration amount value of the tth sampling period, is the historical average of vibration amount.

[0284] is the historical standard deviation of vibration amount σ T is calculated according to the following formula:

[0285]

[0286] where N is the number of sampling periods used to calculate the average, for example, the average of the past 50 sampling periods, then N is 50. Vib smooth (t) is the smoothed vibration amount value of the tth sampling period, is the historical average of vibration amount.

[0287] Exemplary, the running data of the current sampling period is smoothed and the vibration quantity is taken as an example for illustration.

[0288] Vib smooth (t) is calculated according to the following formula:

[0289] Vib smooth (t) = a · Vib(t) + (1-a) · Vib smooth (t-1) ;

[0290] In the formula, a is the weight value corresponding to the vibration quantity of the tth sampling period (usually 0 < a < 1), Vib(t) is the vibration quantity collected in the current sampling period, the value of which is collected by a vibration sensor, and Vib smooth (t-1) is the vibration quantity smoothed in the last period.

[0291] Specifically, in the following scenarios, the specific value of the weight value a can be:

[0292] 1) The target power transmission equipment for rapid detection of mechanical failure

[0293] In some scenarios with high sensitivity requirements, such as mechanical state monitoring of high-voltage switches or transformers, rapid detection of changes in vibration data helps to identify device abnormalities in a timely manner. At this time, the smoothing of the vibration quantity data needs to respond more quickly to changes in the latest data, and then a = 0.3 to 0.5.

[0294] Among them, a higher a value can respond more quickly to changes in the vibration quantity, which helps to discover mechanical failures in a timely manner and avoid potential risks.

[0295] 2) The target power transmission equipment for daily monitoring, such as medium frequency fluctuation:

[0296] For the target power transmission equipment for daily monitoring, such as transformers or circuit breakers, the vibration quantity data has certain fluctuations, but the fluctuation frequency is low. At this time, the smoothing needs to moderately pay attention to the latest data, while not being too sensitive to avoid the influence of short-term fluctuations on the judgment, and then a = 0.15 to 0.25.

[0297] Among them, a moderate a value can balance the influence of the latest data and historical data, and is suitable for data with moderate fluctuation amplitude, so that the comprehensive health score does not change dramatically due to short-term fluctuations.

[0298] 3) Stable device environment, such as low fluctuation monitoring:

[0299] In some device running environment very stable scenarios, such as indoor power transmission equipment, the vibration amount changes very little, and the health status is relatively stable. At this time, the purpose of data smoothing is to keep the score stable, and more emphasis is placed on historical trends, and α=0.05 to 0.1;

[0300] Wherein, the lower α value makes the smoothing result more dependent on historical data, suitable for stable running equipment, and reduces the situation that the score is unstable due to short-term small fluctuations.

[0301] 4) Special monitoring tasks, such as seasonal load changes:

[0302] If the environment or load conditions of the device will appear periodic fluctuations (such as seasonal load changes), the smoothing coefficient can be selected in a moderate range, which can smooth small fluctuations and capture larger changes, and α=0.2 to 0.3;

[0303] Among them, the selection of a moderately high smoothing coefficient can adapt to seasonal change trends, while avoiding short-term fluctuations, so that the device state is more in line with the true situation of periodic load.

[0304] In the embodiment of the application, the running data includes current, voltage, temperature, vibration amount, comprehensive health score of the target power transmission device, and deviation information of each running data (including current, voltage, temperature, vibration amount);

[0305] The adaptive deviation correction term A(t) of the tth sampling period is calculated according to the following formula:

[0306] A(t) = V adjust (t) + I adjust (t) + T adjust (t);

[0307] In the formula, V adjust (t) is a voltage deviation correction term, I adjust (t) is a current deviation correction term, and T adjust (t) is a temperature deviation correction term;

[0308] Wherein, the voltage deviation correction term V adjust (t) is calculated according to the following formula:

[0309]

[0310] In the formula, V(t) is the voltage value of the current sampling period t, μ V (t) is the average value of the voltage before the current sampling period t (that is, the average value of the historical voltage), W(t-(t-M))=W(M) is the time weighting function of the Mth sampling period before the current sampling period t, and V(t-M) is the voltage value of the Mth sampling period before the current sampling period t.V (t - M) is the average value of the voltage before the Mth sampling period before the current sampling period t (i.e., the average value of the voltage before the Mth sampling period before the current sampling period t), V(t - (M - 1)) is the voltage value of the (M - 1)th sampling period before the current sampling period t, μ V (t - (M - 1)) is the average value of the voltage before the (M - 1)th sampling period before the current sampling period t (i.e., the average value of the voltage before the (M - 1)th sampling period before the current sampling period t), W(t - (t - (M - 1))) is the time weighting function of the (M - 1)th sampling period before the current sampling period t, W(t - t) is the time weighting function of the current sampling period t, W(t - t) = W(0) = e -λ*0 = 1, M represents the number of past sampling periods used for calculation, for example, 3 to 5 past periods.

[0311] In addition, the current deviation correction term I adjust (t) is calculated according to the following formula:

[0312]

[0313] In the formula, I(t) is the current value of the current sampling period t, μ I (t) is the average value of the current before the current sampling period t (i.e., the average value of the historical current), W(t - (t - M)) = W(M) is the time weighting function of the Mth sampling period before the current sampling period t, I(t - M) is the current value of the Mth sampling period before the current sampling period t, μ I (t - M) is the average value of the current before the Mth sampling period before the current sampling period t, I(t - (M - 1)) is the current value of the (M - 1)th sampling period before the current sampling period t, μ I (t - (M - 1)) is the average value of the current before the (M - 1)th sampling period before the current sampling period t, W(t - (t - (M - 1))) is the time weighting function of the (M - 1)th sampling period before the current sampling period t, W(t - t) is the time weighting function of the current sampling period t, W(t - t) = W(0) = e -λ*0 = 1, M represents the number of past sampling periods used for calculation, for example, 3 to 5 past periods.

[0314] Similarly, the temperature deviation correction term T adjust (t) is calculated according to the following formula:

[0315]

[0316] In the formula, T(t) is the temperature value of the current sampling period t, μ T(t) is the average value of temperature before the current sampling period t (i.e. the average value of historical temperature), W(t-(t-M)) = W(M) is the time weighting function of the Mth sampling period before the current sampling period t, T(t-M) is the temperature of the Mth sampling period before the current sampling period t, μ T (t-M) is the average value of temperature before the Mth sampling period before the current sampling period t, T(t-(M-1)) is the temperature value of the M-1th sampling period before the current sampling period t, μ T (t-(M-1)) is the average value of temperature before the M-1th sampling period before the current sampling period t, W(t-(t-(M-1))) is the time weighting function of the M-1th sampling period before the current sampling period t, W(t-t) is the time weighting function of the current sampling period t, W(t-t) = W(0) = e -λ*0 = 1, and M represents the number of past sampling periods used for calculation, for example, 3 to 5 past periods.

[0317] In calculating the voltage deviation correction term V adjust (t), the current deviation correction term I adjust (t), and the temperature deviation correction term T adjust (t), if there is not enough data for M periods, the initial value or the initial historical average value set by the system or the initial value measured under normal operating conditions is used by default.

[0318] The time weighting function W(t-(t-M)) = W(M) of the sampling period at the current time point t is calculated according to the following formula:

[0319] W(t-(t-M)) = W(M) = e -λM ;

[0320] In the formula, M represents the number of past sampling periods used for calculation, for example, 3 to 5 past periods, and λ is the time decay coefficient, which is usually in the range of 0.1 to 0.3; in this embodiment, a larger λ makes the weight of the more recent period higher.

[0321] Specifically, when λ takes a larger value (close to 0.3), the decay speed of the time weighting function is faster, which means that the sampling period closer to the current time t is given a higher weight, and the weight of the sampling period farther away decreases rapidly. Therefore, a larger λ makes the formula more sensitive to recent data and less affected by historical data.

[0322] When λ takes a smaller value (close to 0.1), the decay speed is slower, and the data of the far sampling period still has a relatively large influence when weighted. Therefore, a smaller value of λ makes the formula more smooth and stable in response to the entire historical data. Assuming M = 3 (the past 3 sampling periods), taking voltage as an example, the voltage data of the past 3 sampling periods is 220V, 230V, and 225V, and the current sampling period is t.

[0323] Historical average value μ V (t):

[0324] 1) Calculate μ V (t-3): Since t-3 is the earliest sampling period, there is no enough sampling period data to refer to. By default, the initial value of the historical average value or the initial value measured under normal operating conditions is used to fill in as μ V (t-3) = 220.

[0325] 2) Calculate μ V (t-2): The historical average value of t-2 can refer to the data of t-3,

[0326] Therefore, μ V (t-2) = 220 / 1 = 220.

[0327] 3) Calculate μ V (t-1): The historical average value of t-1 can refer to the data of t-3 and t-2,

[0328] μ V (t-1) = (220+230) / 2 = 225.

[0329] 4) Calculate μ V (t): The historical average value of t can refer to the data of t-3, t-2, t-1,

[0330] μ V (t) = (220+230+225) / 3 = 225.

[0331] Calculate the absolute value of the deviation of each sampling period:

[0332] Substitute these historical average values into the formula to calculate the absolute value of the deviation of each sampling period one by one:

[0333] The first sampling period (time point t-3) (voltage value: 220):

[0334] The absolute value of the deviation |220-μ V (t-3)| = |220-220| = 0;

[0335] Second sampling period (time point t-2) (voltage value: 230):

[0336] Absolute value of deviation |230 - μ V (t-2) | = |230 - 220| = 10;

[0337] Third sampling period (time point t-1) (voltage value: 225):

[0338] Absolute value of deviation |225 - μ V (t-1) | = |225 - 225| = 0;

[0339] Calculating time weighting function: assuming λ = 0.1 (λ is a time decay coefficient, interval 3 sampling periods, thus the system sets this value λ = 0.1), then:

[0340] For M = 3: W(t-3) = e 0.1*3 = e -0.3 ;

[0341] For M = 2: W(t-2) = e 0.1*2 = e -0.2 ;

[0342] For M = 1: W(t-1) = e 0.1*1 = e -0.1 ;

[0343] Calculating adaptive deviation correction term V adjust (t): substituting absolute value of deviation and time weighting function into formula:

[0344] V adjust (t) = 1 / 3(0*W(t-3) + 10*W(t-2) + 0*W(t-1)) = 1 / 3(0*e -0.3 + 10*e -0.2 + 0*

[0345] e -0.1 );

[0346] According to the above example steps, voltage deviation correction term V adjust (t), current deviation correction term I adjust (t) and temperature deviation correction term T adjust (t) are calculated respectively, and are added up to obtain A(t).

[0347] The local alarm unit includes an alarm trigger, a signal controller and an alarm output device. The alarm trigger receives and analyzes the key state information in the health status report, and determines whether an alarm needs to be sent. The signal controller converts the alarm trigger signal into a visual or audible alarm signal to ensure that the on-site personnel can pay attention in time. The alarm output device is used to provide alarm prompts to the on-site personnel, which include visual, audible and text reminders.

[0348] The alarm output device includes an alarm, a buzzer and a display screen. The alarm light flashes red or yellow light to visually prompt the fault level. The buzzer emits a buzzing sound or other audio alarm to remind the on-site personnel to pay attention. The display screen (LCD and / or OLED) displays detailed health status reports, including current values and deviations of operating data, to help the on-site personnel understand the fault cause.

[0349] The specific process is as follows:

[0350] The local alarm unit receives the health status report from the state analysis unit. The alarm trigger reads the comprehensive health score, each standardized score (such as Z V , Z I , Z T , Z Vib ) and trend information in the report.

[0351] The operating data is compared with the preset alarm threshold to determine whether the current state of the device meets the alarm condition. For example:

[0352] Mild alarm: the comprehensive health score is less than 80, or any parameter deviation exceeds a certain set range;

[0353] Moderate alarm: the comprehensive health score is less than 60, or any parameter deviation is significantly beyond the set range;

[0354] Severe alarm: the comprehensive health score is less than 40, indicating that the device is in a high-risk state.

[0355] If the alarm trigger determines that the current state exceeds the threshold, an alarm signal is sent, and the signal controller controls the alarm light, buzzer and display screen to start accordingly.

[0356] Different levels of alarms can have different prompt methods. For example, only the alarm light flashes for a mild alarm, the buzzer is added for a moderate alarm, and a detailed report is displayed on the display screen for a severe alarm.

[0357] When the alarm is triggered, the display screen can display the current comprehensive health score, the parameters exceeding the threshold and their specific values, so that the on-site personnel can understand the detailed device state.

[0358] The display screen can also provide maintenance suggestions, such as "check the device temperature and current sensor", to help the on-site personnel respond in time.

[0359] Through the cooperation of the side processing module and the data acquisition module, the state of the target power transmission equipment is accurately collected, and the entire system has the advantages of strong processing capability, high data processing efficiency, good real-time performance, strong monitoring capability, reliable evaluation means, and high intelligence.

[0360] In addition, through the cooperation of the side processing module and the data acquisition module, the state data of the target power transmission equipment is accurately collected and locally processed in real time, ensuring that the system has strong data processing capability, high data processing efficiency, and excellent real-time monitoring capability, further improving the accuracy of sensing the operating state of the target power transmission equipment.

[0361] Optionally, the evaluation response module includes a health state analysis unit, a state evaluation unit, and a maintenance strategy generation unit. The health state analysis unit extracts and analyzes the comprehensive health score of the tth sampling period, the voltage deviation value of the tth sampling period, the current deviation value of the tth sampling period, the temperature deviation value of the tth sampling period, and the vibration amount deviation value of the tth sampling period from the health state report. The state evaluation unit performs comprehensive evaluation on the current state of the equipment based on the comprehensive health score, the standardized scores, and the trend analysis results, generates an evaluation result, and the maintenance strategy generation unit formulates a corresponding maintenance strategy according to the evaluation result.

[0362] Optionally, the health state analysis unit includes a data receiver, an analysis processor, and a data buffer. The data receiver is responsible for receiving health state report data. The analysis processor analyzes the received raw health state report data, extracts the values of each field, formats the analysis results into structured data, and stores the analyzed data for calling by the state evaluation unit.

[0363] The state evaluation unit calculates the comprehensive score index ER based on the comprehensive health score, the standardized scores, and the trend analysis results according to the following formula:

[0364]

[0365] Wherein, ER(t) is the comprehensive score index of the target power transmission equipment, H score (t) is the comprehensive health score of the target power transmission equipment, Z V (t) is the standardized score of the voltage of the tth sampling period, Z I (t) is the standardized score of the current of the tth sampling period, Z T (t) is the standardized score of the temperature of the tth sampling period, Z Vib(t) is the normalized score of the vibration quantity of the tth sampling period, δ is an adjustment coefficient, and TF(t) is a trend factor of the tth sampling period;

[0366]

[0367] wherein σ TF is the historical standard deviation of the trend factor TF(t), and μ TF is the historical average value of the trend factor TF(t).

[0368] wherein the historical average value μ TF of the trend factor TF(t) is calculated according to the following formula:

[0369]

[0370] N is the number of sampling periods used to calculate the average value, TF(t) is the trend factor of the tth sampling period, and the formula is:

[0371]

[0372] wherein H score (t) is the comprehensive health score of the tth sampling period, H score (t-1) is the comprehensive health score of the previous sampling period.

[0373] In the embodiments of the present application, the trend factor can be calculated starting from i = 1 in the embodiments, and the first data point is usually used to initialize the system state, so skipping the calculation thereof will not affect the subsequent trend analysis and comprehensive health score. The calculation of the historical average value starts from the second data point.

[0374] wherein TF(t) > 0: indicates that the comprehensive health score is improved compared with the previous sampling period, and the device state is improving;

[0375] TF(t) < 0: indicates that the comprehensive health score is decreased compared with the previous sampling period, and the device state is possibly deteriorating;

[0376] TF(t) = 0: indicates that the comprehensive health score does not change, and the device state remains stable;

[0377] The historical standard deviation σ TF of the trend factor TF(t) is calculated according to the following formula:

[0378]

[0379] wherein N is the number of sampling periods used to calculate the average value, for example, the average value of the past 50 sampling periods, and N is 50. TF(t) is the trend factor of the tth sampling period, and μ TFis the historical average value of the trend factor TF(t).

[0380] Optionally, the maintenance type generated by the maintenance strategy generation unit includes: regular monitoring, preventive maintenance, corrective maintenance, and emergency maintenance.

[0381] The maintenance strategy generation unit obtains the evaluation results of the state evaluation unit and formulates the following maintenance strategy:

[0382] Regular monitoring (ER(t)>80): The equipment is in good condition.

[0383] Preventive maintenance (60<ER(t)≤80): The equipment state is slightly abnormal, with potential risks.

[0384] Corrective maintenance (40<ER(t)≤60): The equipment state deviates significantly, and needs to be checked and maintained as soon as possible.

[0385] Emergency maintenance (ER(t)≤40): The equipment state is severely deteriorated or failed, and needs to be immediately shut down for repair.

[0386] According to the above maintenance strategy division, the maintenance strategy generation unit can formulate the following specific maintenance strategy:

[0387] 1) Regular monitoring (ER(t)>80) The equipment is in good condition, no additional maintenance is needed, only regular monitoring is needed:

[0388] Maintenance measures:

[0389] Routine monitoring: Keep the original monitoring frequency (such as monitoring once a month or once a quarter), and record the changes in health status.

[0390] Data recording: Regularly record health status reports and changes in various parameters for subsequent trend analysis.

[0391] Analysis report: After the monitoring period ends, generate a state analysis report as a reference for equipment management and maintenance.

[0392] Execution frequency: Keep the regular monitoring frequency, do not increase the inspection and maintenance burden.

[0393] 2) Preventive maintenance (60<ER(t)≤80)

[0394] Strategy description: The equipment state is slightly abnormal, and preventive maintenance is needed to prevent further development of potential risks.

[0395] Maintenance measures:

[0396] Operation data inspection: Increase the inspection and recording of large deviation operation data, such as temperature and current, etc., to ensure that the operation data is within the normal range.

[0397] Periodic review: Shorten the monitoring period (e.g., weekly monitoring) to timely track the equipment status.

[0398] Environmental adjustment: If the deviation is related to environmental factors, adjust the equipment operating environment or parameters as needed (e.g., increase cooling or reduce load).

[0399] Execution frequency: Appropriately shorten the monitoring period and focus on relevant parameters in the next routine inspection.

[0400] 3) Repair maintenance (40 < ER(t) ≤ 60) The equipment status deviates significantly, the operation stability is poor, and repair maintenance measures need to be taken as soon as possible:

[0401] Maintenance measures:

[0402] Troubleshooting: Detailed inspection of operation data (such as vibration, voltage) beyond the normal range to identify possible abnormalities inside the equipment.

[0403] Key component maintenance: Check high-risk components (such as temperature regulation module or current regulation module), clean or replace components with wear or failure risk.

[0404] Health status review: Re-evaluate the equipment health status after repair to ensure the repair effect.

[0405] Execution frequency: Schedule on-site inspection within 1 week, then review equipment status every week until it returns to normal.

[0406] 4) Emergency maintenance (ER(t) ≤ 40) The equipment status deteriorates severely, there are serious faults or failure risks, and immediate shutdown and emergency maintenance measures are required:

[0407] Maintenance measures:

[0408] Emergency shutdown: Immediately stop the equipment operation to prevent the expansion of faults or cause safety accidents.

[0409] Comprehensive overhaul: Arrange professional maintenance team to conduct comprehensive inspection of the equipment, focusing on checking all parameters deviating beyond the threshold.

[0410] Replace or repair critical components: If critical components are found to be severely damaged, replace damaged components or perform maintenance to ensure equipment safety.

[0411] Fault analysis and improvement: After emergency maintenance is completed, conduct fault analysis and generate detailed fault report to identify and analyze fault causes and provide improvement measures for subsequent maintenance.

[0412] Execution frequency: Immediately perform maintenance, and the equipment can be put into use after complete recovery.

[0413] In this embodiment, the process of formulating the maintenance strategy of the maintenance strategy generation unit includes:

[0414] Obtain evaluation results: obtain comprehensive evaluation results ER(t) from the state evaluation unit;

[0415] Determine the type of maintenance: according to the value of ER(t), select the corresponding type of maintenance;

[0416] Formulate maintenance measures: according to the requirements of the measures in the maintenance type, formulate specific maintenance tasks, including inspection period, key components, execution frequency, etc.

[0417] Generate maintenance plan: organize maintenance measures to form maintenance plan, allocate tasks and set priority;

[0418] Execute maintenance and feedback: after the completion of maintenance, feedback the results to the system, track the recovery of the equipment, and adjust the monitoring frequency or maintenance measures according to the recovery situation;

[0419] Through the cooperation of the evaluation response module and the edge processing module, the generation and evaluation of the target power transmission equipment health status report are more efficient and accurate. The evaluation response module can respond quickly based on real-time analysis of health status data, effectively improving the monitoring accuracy of the system and the reliability of maintenance decision-making, ensuring that the system can generate reasonable maintenance strategies in time when an abnormality occurs.

[0420] Through the cooperation of the evaluation response module and the data acquisition module, it is ensured that the collected target power transmission equipment state data can be continuously used for health status monitoring and maintenance strategy generation. The real-time data provided by the data acquisition module provides an accurate basis for evaluation response, effectively supporting the scientific nature of maintenance strategies, enabling the system to have reliable state tracking capabilities and dynamic evaluation advantages.

[0421] In this embodiment, through the comprehensive cooperation of the data acquisition module, the edge processing module and the evaluation response module, a complete closed loop is formed from data acquisition, state analysis to evaluation response. The system can realize intelligent monitoring and adaptive maintenance of the target power transmission equipment, has the advantages of strong processing capacity, timely data feedback, accurate real-time monitoring, flexible maintenance response, and greatly improves the reliability and intelligent level of the system.

[0422] On the basis of the above-mentioned embodiments, the evaluation response module further comprises a maintenance dispatching unit, a maintenance state analysis unit and a feedback unit, the maintenance dispatching unit dispatches a maintenance work order according to the maintenance type of the maintenance strategy generation unit, the maintenance state analysis unit collects the maintenance state of the maintenance work order, analyzes the real-time state of the maintenance work order according to the collected maintenance state data to form a maintenance result, and triggers the feedback unit to feedback to the control center, and the feedback unit feeds back the maintenance result to the control center;

[0423] The maintenance dispatching unit comprises a work order generator, a personnel matcher, a task scheduler and a data dispatcher, the work order generator generates a detailed maintenance work order according to the maintenance type and equipment state information provided by the maintenance strategy generation unit, the personnel matcher selects the most suitable maintenance personnel (considering technical level, geographical location, current working state, etc.) according to the work order requirements, and the data dispatcher is responsible for distributing the work order to the selected maintenance personnel and sending the work order information to the terminal equipment (such as mobile phone, tablet or smart watch, etc.) of the maintenance personnel.

[0424] The maintenance state analysis unit comprises a task collection subunit and a task analysis subunit, the task collection subunit collects real-time state data of the maintenance work order of the maintenance personnel, and the task analysis subunit analyzes the real-time state of the maintenance work order according to the collected real-time state data to form a maintenance result;

[0425] The task collection subunit comprises a state collector and a state data buffer, the state collector collects the maintenance state data uploaded by the maintenance personnel through the terminal equipment, such as "task start", "pause", "resume", "task completion" and the like, and the progress information of the maintenance operation (such as the percentage of completed tasks, the details of the current operation). The state data buffer buffers the collected state data to ensure that the data will not be lost in the case of unstable network, and provides data support for the task analysis subunit.

[0426] The real-time state data comprises time-consuming data and the current completion degree of the assigned maintenance worker; the task analysis subunit obtains the real-time state data, and calculates a trend evaluation index TEI according to the following formula:

[0427]

[0428] In the formula, Completeness historyThe historical average completion degree of the assigned maintenance personnel, a is a trend influence coefficient, the value of which is determined according to the type of the maintenance order, specifically, the emergency task takes a = 0.4, the general task takes a = 0.2, and the ample task takes a = 0.1, and Δt is a time interval, that is, the time difference between the current sampling time and the time point for calculating the historical average progress;

[0429] The current completion degree Completeness of the assigned maintenance worker is calculated according to the following formula

[0430]

[0431] Times spent The time consumed for executing the maintenance order, the value of which is directly collected by the state collector, Total time The theoretical time consumption for executing the maintenance order, the value of which is set by the system according to the type of the maintenance strategy;

[0432] The historical average completion degree Completeness of the assigned maintenance worker history is calculated according to the following formula:

[0433]

[0434] Completeness j is the completion degree of the assigned maintenance worker in the jth period task, and M is the number of selected historical task periods, for example, the past 3 or 5 period tasks.

[0435] If the trend evaluation index TEI is greater than the system set warning threshold Worn, the feedback unit triggers feedback to the control center;

[0436] If the value evaluation index TEI is less than or equal to the system set warning threshold Worn, immediate feedback to the control center is not required;

[0437] The system set warning threshold Worn is set by the system or the manager according to the type of the executed maintenance order or the maintenance type, and is input from the human-computer interaction interface, which is a technical means familiar to those skilled in the art, and those skilled in the art can consult relevant technical manuals to learn the technology, so it is not repeated here.

[0438] The feedback unit includes a data collector and an information transmitter, the data collector collects and summarizes the data of the maintenance state analysis unit (including task state, task completion degree, abnormal event, etc.), and the information transmitter transmits feedback information to the control center, ensuring the real-time and reliability of information transmission;

[0439] The information transmitter transmits data through a wireless network (such as Wi-Fi, 4G, 5G) or a wired network (such as Ethernet), and can set a feedback frequency of periodic or event-driven.

[0440] Through the mutual cooperation between the maintenance sending unit, the maintenance state analysis unit and the feedback unit, the whole maintenance process is more clear and transparent, and the real-time monitoring ability, monitoring efficiency, overall operation and maintenance efficiency of the whole system on the target power transmission equipment are more accurate, automatic and intelligent.

[0441] It should be understood that the various forms of flow shown above can be used to reorder, add or delete steps. For example, the steps described in this application can be executed in parallel, sequentially or in a different order, as long as the desired information of the technical solution of this application can be achieved, which is not limited herein.

[0442] The above detailed description does not constitute a limitation on the scope of protection of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for monitoring power transmission equipment based on edge side, characterized in that, The method comprises: monitoring indicators of a target power transmission device through a sensor to obtain operation data of the target power transmission device; wherein the operation data comprises at least one of current, voltage, temperature and vibration amount of the target power transmission device; determining a standardized score of the operation data, and determining a comprehensive health score of the target power transmission device according to the standardized score of the operation data, an adaptive deviation correction term of the operation data and a proportional coefficient; wherein the standardized score reflects the deviation degree of the operation data of each sampling period relative to the average value; the adaptive deviation correction term reflects the deviation degree of the operation data of the current sampling period relative to the operation data of each previous sampling period; determining a comprehensive score index of the target power transmission device according to the comprehensive health score, the standardized score and a trend factor of the target power transmission device; determining a device operation state of the target power transmission device according to the comprehensive score index of the target power transmission device; determining a standardized score of the operation data, and determining a comprehensive health score of the target power transmission device according to the standardized score of the operation data, an adaptive deviation correction term of the operation data and a proportional coefficient, comprises: determining the comprehensive health score of the target power transmission device based on the following formula: ； wherein H score (t) is the comprehensive health score of the target power transmission equipment; Z V (t) is the normalized score of voltage in the tth sampling period, Z I (t) is the normalized score of current in the tth sampling period, Z T (t) is the normalized score of temperature in the tth sampling period, Z Vib (t) is the normalized score of vibration in the tth sampling period, A(t) is the adaptive deviation correction term in the tth sampling period, K is a proportional coefficient, and a is a constant term. determining a comprehensive score index of the target power transmission device according to the comprehensive health score, the standardized score and a trend factor of the target power transmission device, comprises: determining the comprehensive score index of the target power transmission device according to the following formula: ； wherein, H is the overall score index of the target power transmission equipment score (t) is the overall health score of the target power transmission equipment, Z V (t) is the normalized score of voltage in the tth sampling period, Z I (t) is the normalized score of current in the tth sampling period, Z T (t) is the normalized score of temperature in the tth sampling period, Z Vib (t) is the normalized score of vibration in the tth sampling period, and δ is an adjustment coefficient, and TF(t) is a trend factor in the tth sampling period. ； where σ TF is the historical standard deviation of the trend factor TF(t), μ TF is the historical average of the trend factor TF(t); where the historical average of the trend factor TF(t) is μ TF is calculated according to the following formula: ； N is the number of sampling periods for calculating the average value, TF(t) is the trend factor of the tth sampling period, and the formula is: ； In the formula, H score (t) is the comprehensive health score of the tth sampling period, H score (t−1) is the comprehensive health score of the previous sampling period.

2. The method of claim 1, wherein, The method further comprises: for each existing power transmission device, determining key data of each existing power transmission device according to the device type and / or use scenario of the existing power transmission device; dividing the key data into different data intervals, and determining the correspondence between the data intervals and the proportional coefficient; wherein the key data of different data intervals is positively correlated with the proportional coefficient; The determination process of the proportional coefficient comprises: determining the key data of the target power transmission device, and determining the proportional coefficient corresponding to the data interval where the key data of the target power transmission device is located from the correspondence as the proportional coefficient of the target power transmission device.

3. The method of claim 1, wherein, The determination process of the tth sampling period smoothed operation data for determining the standardized score of the tth sampling period operation data comprises: determining the operation data collected in the current sampling period and the operation data smoothed in the previous sampling period; performing weighted summation on the operation data collected in the current sampling period and the operation data smoothed in the previous sampling period to obtain the operation data smoothed in the current sampling period; wherein the operation data comprises at least one of voltage, current, temperature and vibration amount.

4. The method of claim 3, wherein, The determination process of the weight value for weighted summation comprises: determining monitoring timeliness data of the target power transmission device; making the weight value of the operation data collected in the current sampling period positively correlated with the monitoring timeliness data; a difference between a weight value of the operation data collected in the current sampling period and a weight value of the operation data collected in the previous sampling period is taken as the operation data of the previous sampling period after smoothing processing; The monitoring timeliness data is positively correlated with the monitoring timeliness of the target power transmission equipment.

5. The method of claim 1, wherein, The determination process of the adaptive bias correction term of the operation data includes: For each sampling period, a difference between the operation data in the sampling period and an average value of the operation data in each sampling period before the sampling period is determined; The product of the difference and a time weighting function corresponding to the sampling period is determined, and an average value of the products corresponding to each sampling period is determined as the adaptive bias correction term of the operation data; wherein the operation data includes at least one of voltage, current, temperature and vibration quantity; The determination process of the adaptive bias correction term of the target power transmission equipment includes: The sum of the adaptive bias correction terms of each operation data is taken as the adaptive bias correction term of the target power transmission equipment.

6. The method of claim 5, wherein, The determination process of the time weighting function includes: The product of a time decay coefficient and the number of sampling periods before the current sampling period is determined, and the reciprocal of the product is taken as a decay index; The decay index is taken as the independent variable of the natural exponential function, and the time weighting function corresponding to the sampling period is calculated.

7. The method of claim 1, wherein, The method further includes: In the case where the device operating state of the power transmission equipment does not reach a preset state, the terminal notifies the maintenance personnel to maintain the target power transmission equipment, and determines a trend evaluation index of the maintenance personnel; The trend evaluation index of the maintenance personnel is determined based on the following formula: ； Wherein, Completeness is the current completion degree of the assigned maintenance personnel, Completenesshistory is the historical average completion degree of the assigned maintenance personnel, and a is a trend influence coefficient; Current completion ; Time spent Time spent by maintenance personnel to perform maintenance work orders already consumed; Total time Theoretical time spent by maintenance personnel to perform maintenance work orders historical average completion ; Completeness j The completeness of the jth period task for the assigned maintainer is M, and the selected number of historical task periods is M.

8. A side-of-line power delivery equipment monitoring system, comprising: The edge-based power transmission equipment monitoring system is used to execute the method according to any one of claims 1-7, and the system includes a server, a data acquisition module, an edge processing module, and an evaluation response module; the data acquisition module, the edge processing module, and the evaluation response module are connected with the server respectively; The data acquisition module acquires operation data of the target power transmission equipment, the edge processing module locally processes the operation data transmitted by the data acquisition module to analyze the operation state of the target power transmission equipment in real time and generate a target power transmission equipment health state report, and the evaluation response module evaluates according to the power transmission equipment health state report to form an evaluation result, and generates a target power transmission equipment maintenance strategy according to the evaluation result: The edge processing module includes a data receiving unit, a state analysis unit, and a local alarm unit; the data receiving unit receives operation data from the data acquisition module, the state analysis unit processes and analyzes the received operation data to form an analysis result to obtain the target power transmission equipment health state report, and the local alarm unit triggers a warning according to the health state report and prompts the maintenance personnel to process.

Images