Electric power inspection method and system based on digital twinning

Abstract

The invention relates to an electric power inspection method and system based on digital twinning, and belongs to the field of electric power system risk monitoring. According to the invention, the collected equipment state data, power load data, environment data and life data of the power equipment are input into the pre-trained digital twin model to obtain the equipment characteristic quantized value related to the power risk, and then the characteristic index of the power equipment is obtained according to the equipment characteristic quantized value. And then a comprehensive risk value is obtained according to the power index, and when the comprehensive risk value is greater than a preset risk threshold, an early warning signal is generated. According to the collected multi-dimensional data of the power equipment, the power equipment is inspected, and the operation state of the power equipment is comprehensively and accurately reflected.

Description

Technical Field

[0001] The present invention relates to a digital twin-based electric power inspection method and system, and belongs to the field of electric power system risk monitoring. Background Art

[0002] With the continuous development and expansion of the power system, the stable operation of power equipment is crucial to ensure the reliability and safety of power supply. In the complex power operation environment, power equipment faces the combined effects of multiple factors such as voltage and current changes, load fluctuations, ambient temperature and humidity, wind speed, and its own aging and fault history.

[0003] However, due to the lack of effective data integration and analysis methods, traditional power inspection methods are unable to accurately quantify the operating risks of equipment, resulting in the inability to carry out targeted maintenance and management in a timely manner, increasing the possibility of equipment failure and affecting the normal operation of the power system.

[0004] For example, the Chinese patent application publication document with publication number CN118611260A discloses a substation equipment monitoring method based on digital twins, which includes obtaining real-time operating data corresponding to the substation equipment, performing feature extraction on the real-time operating data, and then inputting the extracted data into the digital twin model to determine the operating status of the substation equipment.

[0005] However, when analyzing the operating status of the substation equipment, this method does not take into account the load of the substation equipment and the fact that the performance of the substation equipment will decrease as the time of commissioning of the substation equipment increases. Summary of the invention

[0006] The purpose of the present invention is to provide a power inspection method and system based on digital twins to solve the problem of being unable to conduct a comprehensive analysis of the many factors that affect the power supply of power equipment.

[0007] To achieve the above object, the solution of the present invention includes:

[0008] A digital twin-based power inspection method of the present invention comprises the following steps:

[0009] Obtain the equipment status data and power load data of each preset time node of the power equipment, and obtain the environmental data and life data of the current time node of the power equipment; the equipment status data includes voltage value and current value, the power load data includes load value, the environmental data includes temperature value, humidity value and wind speed value, and the life data includes current usage time and expected usage time; after marking the corresponding categories of the equipment status data, power load data, environmental data and life data, input them into the corresponding feature extraction algorithm in the pre-established digital twin model, and obtain the corresponding equipment feature quantification value related to power risk; the equipment feature quantification value includes power feature coefficient, load fluctuation coefficient, temperature influence coefficient, humidity influence coefficient, wind speed influence coefficient, etc. speed influence coefficient and aging characteristic coefficient; weighted sum of characteristic indicators corresponding to the quantified values ​​of equipment characteristics is performed to obtain a comprehensive risk value, and when the comprehensive risk value is greater than a first preset comprehensive risk threshold, a warning signal is generated; the feature extraction algorithm includes a power characteristic coefficient extraction algorithm, a load fluctuation coefficient extraction algorithm, a temperature influence coefficient extraction algorithm, a humidity influence coefficient extraction algorithm, a wind speed influence coefficient extraction algorithm and an aging characteristic coefficient extraction algorithm; the characteristic indicators include a power error indicator obtained according to the power characteristic coefficient, a load stability indicator obtained according to the power load data, an environmental impact indicator obtained according to the temperature influence coefficient, the humidity influence coefficient and the wind speed influence coefficient, and a performance indicator obtained according to the aging characteristic coefficient.

[0010] Furthermore, the power error index is obtained by the following formula:

[0011]

[0012] Among them, Z P is the power error index, n is the number of preset time nodes, The corresponding result is the power characteristic coefficient, Vi and Yi are the voltage value and current value corresponding to each preset time node, and PY is the power reference value preset for the power equipment.

[0013] Furthermore, the load stability index is obtained by the following formula:

[0014]

[0015] Among them, Z FH is the load stability index, n is the number of preset time nodes, The corresponding result is the load fluctuation coefficient, Li is the load value corresponding to each preset time node, L P It is the average value of the sum of the load values ​​at each preset time node.

[0016] Furthermore, the environmental impact index is obtained by including the following steps:

[0017] The temperature influence coefficient is obtained by the following formula:

[0018]

[0019] Among them, X T is the temperature influence coefficient, T e is the temperature value, T min and T max They are respectively the lower limit and upper limit of the suitable temperature range preset for the power equipment during operation;

[0020] The humidity influence coefficient is obtained by the following formula:

[0021]

[0022] Among them, X H is the humidity influence coefficient, H u is the humidity value, H0 is the appropriate humidity threshold preset during the operation of the power equipment;

[0023] The wind speed influence coefficient is obtained by the following formula:

[0024]

[0025] Among them, X W is the wind speed influence coefficient, W s is the wind speed value, W0 is the appropriate wind speed threshold preset during the operation of the power equipment;

[0026] Then the environmental impact index is obtained by the following formula:

[0027] Z HJ =X T ×β1+X H ×β2+X W ×β3

[0028] Among them, β1, β2, and β3 are corresponding pre-set weight coefficients respectively.

[0029] Furthermore, the performance index is obtained by the following formula:

[0030]

[0031] Among them, Z LH is the performance indicator, The corresponding result is the aging characteristic coefficient, DS is the current usage time, YS is the expected usage time, R is the number of maintenance times of the power equipment, F is the maintenance frequency of the power equipment, and α1, α2, and α3 are the corresponding pre-set weight coefficients.

[0032] Furthermore, the comprehensive risk value is obtained by the following formula:

[0033]

[0034] Among them, C is the comprehensive risk value, and γ1, γ2, γ3, and γ4 are the corresponding pre-set weight values.

[0035] Furthermore, the warning signals are graded. When the comprehensive risk value is greater than or equal to a first preset comprehensive risk threshold and less than a second preset comprehensive risk threshold, a first warning signal is generated; when the comprehensive risk value is greater than or equal to the second preset comprehensive risk threshold and less than a third preset comprehensive risk threshold, a second warning signal is generated; when the comprehensive risk value is greater than or equal to the third preset comprehensive risk threshold, a third warning signal is generated.

[0036] A digital twin-based power inspection system of the present invention includes a processor, which is used to execute a computer program to implement the steps of a digital twin-based power inspection method.

[0037] The beneficial effects of the present invention are as follows: the present invention is a pioneering invention. The present invention obtains the quantified value of equipment characteristics related to power risk based on the collected equipment status data, power load data, environmental data and life data of the power equipment into the pre-trained digital twin model, and then obtains the characteristic index of the power equipment based on the equipment characteristic quantified value, and then obtains the comprehensive risk value based on the power index. When the comprehensive risk value is greater than the preset risk threshold, an early warning signal is generated. The present invention inspects the power equipment based on the collected multi-dimensional data of the power equipment, and comprehensively and accurately reflects the operating status of the power equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a flow chart of a power inspection method based on digital twins of the present invention;

[0039] Figure 2 It is a flow chart of a data analysis unit in a power inspection method based on digital twins of the present invention. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments.

[0041] The idea of ​​the present invention is to input the equipment status data, power load data, environmental data and historical fault data of the power equipment into a pre-trained digital twin model, obtain the corresponding indicators of the power equipment, and obtain the comprehensive risk value of the power equipment based on the indicators, and then evaluate whether the power equipment has abnormalities based on the comprehensive risk value.

[0042] Method Example:

[0043] This embodiment provides a power inspection method based on digital twins, such as Figure 1 As shown, it includes a data acquisition module, a feature extraction unit, a data analysis unit, a risk assessment unit and a result display unit. The data acquisition module is used to collect the equipment status data, power load data, environmental data and life data of each power equipment at a specified time node within the standard cycle; the feature extraction unit is used to mark the equipment status data, power load data, environmental data and life data with corresponding categories and import them into the corresponding feature extraction algorithm in the pre-established digital twin model, so as to obtain the equipment characteristic quantification values ​​corresponding to the equipment status data, power load data, environmental data and historical fault data, and the equipment characteristic quantification values ​​include power characteristic coefficient, load fluctuation coefficient, temperature influence coefficient, humidity influence coefficient, wind speed influence coefficient and aging characteristic coefficient; the data analysis unit is used to analyze the comprehensive risk value of the power equipment according to the equipment characteristic quantification value; the result display unit is used to display the warning signal of the power equipment to the use level to the relevant management personnel in an intuitive display method, so as to realize risk warnings of different levels.

[0044] The collected data is marked in the following ways:

[0045] The attribute parameters corresponding to the voltage and current in the device status data are extracted and imported into the pre-established voltage attribute set and current attribute set respectively.

[0046] The marking processing methods corresponding to the power load data, environmental data and historical fault data are the same as the marking processing method of the equipment status data.

[0047] Then, the corresponding attribute parameters in the classified attribute set are matched to the corresponding feature extraction algorithm. Specifically, the voltage and current of the power equipment at each specified time node in the standard cycle are obtained, and the voltage and current marked with the corresponding category are input into the pre-established digital twin model, and then the power feature coefficient X is obtained through the power feature extraction algorithm. p ,Right now:

[0048]

[0049] Among them, Yi is the voltage of the power equipment at each specified time node in the standard cycle, Vi is the current of the power equipment at each specified time node in the standard cycle, and n is the number of all specified time nodes in the standard cycle.

[0050] The power characteristic coefficient X p Input into the data analysis unit, and then obtain the power error index Z of the power equipment through the following formula p :

[0051] Z P =X P -PY (2)

[0052] Among them, PY is a pre-defined power reference value corresponding to the power equipment. The power reference value is information provided by the power equipment manufacturer, which represents the energy consumption of the power equipment under ideal working conditions.

[0053] Specifically, the power load data of the power equipment at each specified time node within the standard cycle is obtained, and the power load data marked with the corresponding category is input into the pre-established digital twin model, and then the mean value L of the power load data at each specified time node is obtained by the following formula p :

[0054]

[0055] Among them, Li is the power load data of the power equipment at each specified time node within the standard period.

[0056] Furthermore, the load fluctuation coefficient X is obtained through the load feature extraction algorithm. FH ,Right now:

[0057]

[0058] The power characteristic coefficient X p Input into the data analysis unit, and then obtain the load stability index Z of the power equipment through the following formula FH :

[0059] Z FH =1-X FH (5)

[0060] Specifically, the environmental data of the power equipment at the specified time node within the standard cycle is obtained. The environmental data includes the ambient temperature value Te, the ambient humidity value Hu and the ambient wind speed value Ws of the current time node of the power equipment. The ambient temperature value Te, the ambient humidity value Hu and the ambient wind speed value Ws marked with the corresponding category are input into the pre-established digital twin model, and then the temperature influence coefficient X is obtained through the temperature, humidity and wind speed feature extraction algorithm. T , Humidity influence coefficient X H And the wind speed influence coefficient X W ,Right now:

[0061]

[0062] Wherein, [Tmin, Tmax] is a preset suitable temperature range when the power equipment is in operation, Tmin represents the minimum value of the suitable temperature range, and Tmax represents the maximum value of the suitable temperature range.

[0063]

[0064] Among them, H0 is a pre-set appropriate temperature threshold when the power equipment is running.

[0065]

[0066] Wherein, W0 is the pre-set appropriate wind speed threshold when the power equipment is in operation.

[0067] The obtained temperature influence coefficient X T , Humidity influence coefficient X H And the wind speed influence coefficient X W Input into the data analysis unit, and then obtain the environmental impact index Z of the power equipment through the following formula HJ :

[0068] Z HJ =X T ×β1+X H ×β2+X W ×β3 (9)

[0069] Among them, β1, β2, and β3 are corresponding preset weight coefficients, and it is ensured that the sum of β1, β2, and β3 is 1.

[0070] Specifically, the life data and historical fault data of the power equipment at the specified time node within the standard cycle are obtained. The life data includes the usage time DS and the expected usage time YS of the corresponding power equipment to the current time node. The historical fault data includes the number of maintenance times R and the fault frequency F. The current usage time DS and the expected usage time YS marked with the corresponding category are input into the pre-established digital twin model, and then the aging characteristic coefficient LH is obtained by the following formula:

[0071]

[0072] Furthermore, the performance index Z of the power equipment is obtained through the performance extraction algorithm. LH ,Right now:

[0073]

[0074] Among them, α1, α2, and α3 are corresponding preset weight coefficients, and it is ensured that the sum of α1, α2, and α3 is 1.

[0075] Considering that the power error index Z of the power equipment should be obtained p , Load stability index Z FH 、Environmental impact index Z HJ And performance index Z LH Comprehensively judge whether the power equipment is abnormal, such as Figure 2 As shown, in the data analysis unit, according to the power error indicator Z p , Load stability index Z FH 、Environmental impact index Z HJ And performance index Z LH At least any two indicators in the above formula can obtain the comprehensive risk value of power equipment, but then use the load stability index Z FH and performance index Z LH When calculating, take the inverse of these two indicators. The above process is explained with three specific examples below.

[0076] When any two indicators are used to obtain the comprehensive risk value, the power error indicator Z p and load stability index Z FH For example, the comprehensive risk value C1 is obtained by the following formula:

[0077]

[0078] Among them, γ11 and γ12 are the power error index Z when calculating the comprehensive risk value C1. p and load stability index Z FH Corresponding to the pre-set weight value, when obtaining the comprehensive risk value through any two indicators, it is only necessary to set the corresponding weight value and ensure that the sum of γ11 and γ12 is 1.

[0079] When any three indicators are used to obtain the comprehensive risk value, the power error indicator Z p , Load stability index Z FH and environmental impact indicator Z HJ For example, the comprehensive risk value C2 is obtained by the following formula:

[0080]

[0081] Among them, γ21, γ22, and γ23 are the power error index Z when calculating the comprehensive risk value C2. p , Load stability index Z FH and environmental impact indicator Z HJ Corresponding to the pre-set weight values, when obtaining the comprehensive risk value through any three indicators, it is only necessary to set the corresponding weight values ​​and ensure that the sum of γ21, γ22, and γ23 is 1.

[0082] The power error indicator Z is used by the following formulap , Load stability index Z FH 、Environmental impact index Z HJ And performance index Z LH Get the comprehensive risk value C3:

[0083]

[0084] Among them, γ31, γ32, γ33, and γ34 are the power error index Z when calculating the comprehensive risk value C3. p , Load stability index Z FH 、Environmental impact index Z HJ And performance index Z LH Corresponding to the preset weight values, the sum of γ31, γ32, γ33, and γ34 is 1.

[0085] Furthermore, the obtained comprehensive risk value is input into the risk assessment unit, which performs a comprehensive risk assessment on the power equipment according to a preset comprehensive risk threshold D1, and generates a corresponding signal according to the assessment result. The comprehensive risk threshold D1 is set according to the obtained comprehensive risk value.

[0086] When the corresponding comprehensive risk value is less than the corresponding comprehensive risk threshold D1, it is judged that the comprehensive state of the power equipment is relatively stable and a normal signal is generated; when the corresponding comprehensive risk value is greater than or equal to the corresponding comprehensive risk threshold D1, it is judged that the comprehensive state of the power equipment is abnormal and an early warning signal is generated.

[0087] Furthermore, the obtained signal is output to the result display unit, and the result display unit displays the comprehensive evaluation result of the power equipment on the display screen by means of a breathing light. For example, when a normal signal is obtained, the breathing light is green; when a warning signal is obtained, the breathing light is other colors.

[0088] As another embodiment, when the comprehensive risk value is greater than or equal to the comprehensive risk threshold D1, the comprehensive risk value is further judged, that is, when the comprehensive risk value is greater than or equal to the comprehensive risk threshold D1 and less than the comprehensive risk threshold D2, it is determined that the comprehensive state of the power equipment has a low abnormality, and a warning signal one is generated; when the comprehensive risk value is greater than or equal to the comprehensive risk threshold D2 and less than the comprehensive risk threshold D3, it is determined that the comprehensive state of the power equipment has a moderate abnormality, and a warning signal two is generated; when the comprehensive risk value is greater than or equal to the comprehensive risk threshold D3, it is determined that the comprehensive state of the power equipment has a high abnormality, and a warning signal three is generated.

[0089] Furthermore, the result display unit also displays on the display screen according to different warning signals. For example, when warning signal one is obtained, the breathing light is yellow; when warning signal two is obtained, the breathing light is orange; when warning signal three is obtained, the breathing light is red.

[0090] As another embodiment, the power error indicator Z P The data is input to the risk assessment unit, which evaluates the operating status of the power equipment according to the preset power error threshold and generates a corresponding signal according to the evaluation result. When the power error index is less than or equal to the power error threshold, the operating status of the power equipment is judged to be relatively stable and a normal signal is generated; when the power error index is greater than the power error threshold, the operating status of the power equipment is judged to be abnormal and a reminder signal 1 is generated. When the reminder signal 1 is obtained, the breathing light is gray.

[0091] The load stability index Z FH The data is input to the risk assessment unit, which evaluates the load condition of the power equipment according to the preset load stability threshold and generates a corresponding signal according to the evaluation result. When the load stability index is greater than the load stability threshold, the operating state of the power equipment is judged to be relatively stable and a normal signal is generated; when the load stability index is less than or equal to the load stability threshold, the load condition of the power equipment is judged to be abnormal and a reminder signal 2 is generated. When the reminder signal 2 is obtained, the breathing light is blue.

[0092] The environmental impact index Z HJ The data is input to the risk assessment unit, which evaluates the environment in which the power equipment is located according to the preset environmental impact threshold and generates a corresponding signal based on the evaluation result. When the environmental impact index is less than or equal to the environmental impact threshold, it is determined that the environment in which the power equipment is located is relatively stable and a normal signal is generated; when the environmental impact index is greater than the environmental impact threshold, it is determined that the environment in which the power equipment is located is abnormal and a reminder signal three is generated. When the reminder signal three is obtained, the breathing light is purple.

[0093] The performance index Z LH The data is input to the risk assessment unit, which evaluates the performance of the power equipment according to the pre-set performance threshold and generates a corresponding signal according to the evaluation result. When the performance index is greater than the performance threshold, the performance of the power equipment is judged to be relatively stable and a normal signal is generated; when the performance index is less than or equal to the performance threshold, the performance of the power equipment is judged to be abnormal and a reminder signal 4 is generated. When the reminder signal 4 is obtained, the breathing light is black.

[0094] The formulas of the present invention are dimensionless and numerically calculated. The digital twin model is trained by pre-collecting a large amount of actual data on site, and then outputs data that is closest to the actual conditions of the power equipment. The preset parameters and thresholds in the formula are set according to different actual conditions on site. The intuitive display of the result display unit includes but is not limited to breathing lights, voice broadcasts, generated text, etc.

[0095] System Example:

[0096] In this embodiment, a power inspection system based on digital twin is provided. When inspecting power equipment, the system adopts a power inspection method based on digital twin as introduced in the method embodiment. Since the introduction of this method is clear enough, it will not be repeated here.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A power inspection method based on digital twins, characterized in that: The steps include: Obtain equipment status data and power load data at each preset time node of the power equipment, and obtain environmental data and life data of the current time node of the power equipment; the equipment status data includes voltage value and current value, the power load data includes load value, the environmental data includes temperature value, humidity value and wind speed value, and the life data includes current usage time and expected usage time; after marking the equipment status data, power load data, environmental data and life data with corresponding categories, input them into the corresponding feature extraction algorithm in the pre-established digital twin model, and obtain corresponding equipment feature quantification values ​​related to power risks; the equipment feature quantification values ​​include power feature coefficient, load fluctuation coefficient, temperature influence coefficient, humidity influence coefficient, wind speed influence coefficient and aging feature coefficient; perform weighted summation on the feature indicators obtained according to the equipment feature quantification values ​​to obtain a comprehensive risk value, and generate a warning signal when the comprehensive risk value is greater than a first preset comprehensive risk threshold; the feature extraction algorithm includes a power feature coefficient extraction algorithm, a load fluctuation coefficient extraction algorithm, a temperature influence coefficient extraction algorithm, a humidity influence coefficient extraction algorithm, a wind speed influence coefficient extraction algorithm and an aging feature coefficient extraction algorithm; The characteristic indicators include a power error indicator obtained according to a power characteristic coefficient, a load stability indicator obtained according to power load data, an environmental impact indicator obtained according to a temperature impact coefficient, a humidity impact coefficient, and a wind speed impact coefficient, and a performance indicator obtained according to an aging characteristic coefficient.

2. The power inspection method based on digital twin according to claim 1 is characterized in that: The power error index is obtained by the following formula: Among them, Z P is the power error index, n is the number of preset time nodes, The corresponding result is the power characteristic coefficient, Vi and Yi are the voltage value and current value corresponding to each preset time node, and PY is the power reference value preset for the power equipment.

3. The power inspection method based on digital twin according to claim 2 is characterized in that: The load stability index is obtained by the following formula: Among them, Z FH is the load stability index, n is the number of preset time nodes, The corresponding result is the load fluctuation coefficient, Li is the load value corresponding to each preset time node, L P It is the average value of the sum of the load values ​​at each preset time node.

4. The power inspection method based on digital twin according to claim 3 is characterized in that: The environmental impact index is obtained by including the following steps: The temperature influence coefficient is obtained by the following formula: Among them, X T is the temperature influence coefficient, T e is the temperature value, T min and T max They are respectively the lower limit and upper limit of the suitable temperature range preset for the power equipment during operation; The humidity influence coefficient is obtained by the following formula: Among them, X H is the humidity influence coefficient, H u is the humidity value, H0 is the appropriate humidity threshold preset during operation of the power equipment; The wind speed influence coefficient is obtained by the following formula: Among them, X W is the wind speed influence coefficient, W s is the wind speed value, W0 is the appropriate wind speed threshold preset during operation of the power equipment; Then the environmental impact index is obtained by the following formula: Z HJ =X T ×β1+X H ×β2+X W ×β3 Among them, β1, β2, and β3 are corresponding pre-set weight coefficients respectively.

5. The power inspection method based on digital twin according to claim 4 is characterized in that: The performance index is obtained by the following formula: Among them, Z LH is the performance index, The corresponding result is the aging characteristic coefficient, DS is the current usage time, YS is the expected usage time, R is the number of maintenance times of the power equipment, F is the maintenance frequency of the power equipment, and α1, α2, and α3 are the corresponding pre-set weight coefficients respectively.

6. The power inspection method based on digital twin according to claim 5 is characterized in that: The comprehensive risk value is obtained by the following formula: Among them, C is the comprehensive risk value, and γ1, γ2, γ3, and γ4 are corresponding pre-set weight values.

7. The power inspection method based on digital twin according to claim 1 is characterized in that: The warning signals are also graded, and a first warning signal is generated when the comprehensive risk value is greater than or equal to a first preset comprehensive risk threshold and less than a second preset comprehensive risk threshold; When the comprehensive risk value is greater than or equal to the second preset comprehensive risk threshold and less than the third preset comprehensive risk threshold, a second warning signal is generated; When the comprehensive risk value is greater than or equal to a third preset comprehensive risk threshold, a third warning signal is generated.

8. A power inspection system based on digital twins, comprising a processor, characterized in that: The processor is used to execute a computer program to implement the steps of the digital twin-based power inspection method according to any one of claims 1 to 7.

Images