A method and system for intelligent monitoring of power system based on artificial intelligence

Abstract

The present invention relates to the technical field of power system monitoring, and specifically discloses an artificial intelligence-based intelligent monitoring method and system for a power system, comprising the following steps: Step S1: Acquire historical data of power equipment, obtain a standard usage cycle according to the historical data, and establish a standard load curve and a standard temperature curve; Step S2: Establish a temperature curve of the power equipment, and select monitoring points; if there are two power equipment whose temperature curves meet certain conditions, they belong to quasi-environmental equipment; establish a load curve, obtain a climbing interval, and calculate a load factor; Step S3: Establish a load curve of the power equipment, and select monitoring points; if there are two power equipment whose load curves meet certain conditions, they belong to quasi-load equipment; establish a temperature curve of the quasi-load equipment, obtain extreme temperature points, and calculate an environmental factor; Step S4: Calculate the predicted usage cycle of the current power equipment according to the load factor and the environmental factor.

Description

Technical Field

[0001] The present invention relates to the technical field of power system monitoring, and in particular to an artificial intelligence-based power system intelligent monitoring method and system. Background Art

[0002] The power system is a complex system for producing and consuming electric energy, which mainly includes power generation systems, transmission systems, substation systems, distribution systems, control and protection systems, energy management systems, etc.; accordingly, these parts are all operated by different power equipment, including power generation equipment, transmission equipment, distribution equipment and power-consuming equipment, etc., to ensure the smooth production, transmission and distribution of electricity, and to ensure the normal operation of society.

[0003] Power system monitoring is an important part of ensuring stable, safe and efficient power supply; its main monitoring contents include voltage monitoring, current monitoring, equipment status monitoring, safety monitoring, data recording and analysis, etc.

[0004] After the power equipment of the power system is put into use, it will inevitably age. In the prior art, the aging monitoring method for power equipment mainly involves regular manual inspection of the aging of the power equipment, so as to promptly detect and replace the power equipment that has reached the end of its service life. However, due to the complex installation environment of the power equipment, which may be underground or in the air, the manual regular inspection method is relatively cumbersome and costly. In addition, the aging of the power equipment is not only affected by external environmental factors, but also by the pressure and load on the power system. Therefore, the regular inspection method cannot promptly detect the power equipment that has reached the end of its service life, resulting in the failure to replace the power equipment in time, thereby affecting the normal operation of the power system. Summary of the invention

[0005] The purpose of the present invention is to provide an artificial intelligence-based power system intelligent monitoring method and system to solve the above technical problems.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] An artificial intelligence-based intelligent monitoring method for a power system comprises the following steps:

[0008] Step S1: Acquire historical data of the power equipment, the historical data including the use period of the power equipment, and load time series data and temperature time series data within the use period; obtain a standard use period T0 according to the historical data, and establish a standard load curve and a standard temperature curve;

[0009] Step S2: Establish a temperature curve of the power equipment, and select m monitoring points at equal intervals on the temperature curve; if there are two temperature curves that match, record the power equipment class environment corresponding to the two temperature curves; select a number of power equipment whose any two temperature curves are class environment, and record them as class environment equipment;

[0010] Establish a load curve for environmental equipment; obtain a climbing interval on the load curve, where the climbing interval is an interval in which the average slope between two timestamps exceeds a preset slope threshold; obtain a load factor K based on the standard load curve and the climbing interval on the load curve f ;

[0011] Step S3: Establish a load curve of the power equipment, and select m monitoring points at equal intervals on the load curve; if there are two load curves that match, record the power equipment class loads corresponding to the two load curves; select a number of power equipment with any two load curves that are class loads, and record them as class load equipment;

[0012] Establish a temperature curve for load-like equipment, obtain the extreme temperature point on the temperature curve, where the temperature corresponding to the timestamp does not belong to the preset temperature range threshold [Tem1, Tem2]; obtain the environmental factor K according to the standard temperature curve and the extreme temperature point on the temperature curve h ;

[0013] Step S4: Obtain the current power equipment's input cycle in real time, where the input cycle is the time period between the time it is put into use and the current time; and obtain the current load curve and current temperature curve of the current power equipment during the input cycle; and obtain the predicted use cycle Ty of the current power equipment based on the load factor and environmental factor.

[0014] As a further solution of the present invention: the usage cycle is the time period between the time of commissioning and the time of aging, the usage time is the timestamp corresponding to when the power equipment is put into use, and the aging time is the timestamp corresponding to when the power equipment is replaced or repaired; the load time series data is the power consumption at each timestamp.

[0015] As a further solution of the present invention: the process of obtaining the standard use cycle, the standard load curve and the standard temperature curve includes:

[0016] According to the use cycle of each power device in the historical data, an average value of the use cycle of each power device is obtained, which is recorded as a standard use cycle T0;

[0017] Obtain the load curves of each power device and stretch or shrink each load curve horizontally so that T i = T0, where i∈[1,All] and i∈N + , where N+ is a positive integer set, All is the total number of power equipment; the load curve after horizontal stretching or reduction is called the telescopic load curve; the power consumption at each monitoring point on the telescopic load curve is obtained, and the power consumption of each telescopic load curve at the same monitoring point is obtained, and the average power consumption of each telescopic load curve at the same monitoring point is obtained; according to the average power consumption at each monitoring point, a standard load curve is established;

[0018] Obtain the temperature curve of each power device, and stretch or shrink each temperature curve horizontally so that T i =T0, the load curve after transverse stretching or reduction is recorded as the expansion and contraction temperature curve; the temperature at each monitoring point on the expansion and contraction temperature curve is obtained, and the temperature of each expansion and contraction temperature curve at the same monitoring point is obtained, and the average temperature of each expansion and contraction temperature curve at the same monitoring point is obtained; according to the average temperature at each monitoring point, a standard temperature curve is established.

[0019] As a further solution of the present invention: the selection of the monitoring points includes points corresponding to the time of commissioning and the time of aging on the temperature curve.

[0020] As a further solution of the present invention: the process of determining that the two temperature curves are consistent includes:

[0021] Let the two temperature curves be F1 and F2. If F1 and F2 satisfy , where F1 t is the value corresponding to the tth monitoring point on F1, F2 t is the value corresponding to the tth monitoring point on F2; then the two temperature curves are consistent.

[0022] As a further solution of the present invention: the process of determining the slope threshold is as follows:

[0023] The slope threshold is denoted as kst, and kst=tanθ, wherein θ is the angle between the corresponding tangent and the x-axis, and the setting range of the angle is (45°, 90°), then the setting range of the slope threshold is kst∈(tan45°, tan90°).

[0024] As a further solution of the present invention: the load factor K f The process of obtaining includes:

[0025] ;

[0026] Where N0 is the number of rising intervals on the standard load curve, k 0x is the mean slope of the xth climbing interval on the standard load curve, k ix is the mean slope of the xth climbing interval on the ith load curve, T i is the use cycle of the i-th type of environmental equipment, Ni is the number of climbing intervals on the i-th load curve, and μ is the preset first correction coefficient.

[0027] As a further solution of the present invention: during the setting process of the preset temperature range threshold [Tem1, Tem2], Tem1≤0°C, Tem2≥40°C.

[0028] As a further solution of the present invention: the environmental factor K h The process of obtaining includes:

[0029] ;

[0030] in , num is the total number of load-type devices, T e is the service life of the e-th type of load equipment, M e is the number of extreme temperature points on the e-th temperature curve, M0 is the number of extreme temperature points on the standard temperature curve, tem eq is the temperature corresponding to the qth extreme temperature point on the eth temperature curve, tem 0q is the temperature corresponding to the qth extreme temperature point on the standard temperature curve, and λ is the preset second correction coefficient.

[0031] As a further solution of the present invention: the process of obtaining the predicted usage period Ty includes:

[0032] ;

[0033] in , , M' is the total number of extreme temperature points on the current temperature curve, tem' q is the temperature corresponding to the qth extreme temperature point on the current temperature curve, N' is the total number of climbing intervals on the current load curve, k' x It is the mean slope of the xth climbing interval on the current load curve.

[0034] As a further solution of the present invention: an intelligent monitoring system for a power system based on artificial intelligence, comprising:

[0035] Historical data processing module: obtain historical data of power equipment, the historical data includes the use cycle of the power equipment, and load time series data and temperature time series data within the use cycle; obtain the standard use cycle T0 according to the historical data, and establish a standard load curve and a standard temperature curve;

[0036] Load factor analysis module: establish the temperature curve of the power equipment, and select m monitoring points at equal intervals on the temperature curve; if there are two temperature curves that match, record the power equipment class environment corresponding to the two temperature curves; select a number of power equipment whose any two temperature curves are class environment, and record them as class environment equipment;

[0037] Establish a load curve for environmental equipment; obtain a climbing interval on the load curve, where the climbing interval is an interval in which the average slope between two timestamps exceeds a preset slope threshold; obtain a load factor K based on the standard load curve and the climbing interval on the load curve f ;

[0038] Environmental factor analysis module: establish the load curve of the power equipment, and select m monitoring points at equal intervals on the load curve; if there are two load curves that match, record the power equipment class loads corresponding to the two load curves; select a number of power equipment with any two load curves that are class loads, and record them as class load equipment;

[0039] Establish a temperature curve for load-like equipment, obtain the extreme temperature point on the temperature curve, where the temperature corresponding to the timestamp does not belong to the preset temperature range threshold [Tem1, Tem2]; obtain the environmental factor K according to the standard temperature curve and the extreme temperature point on the temperature curve h ;

[0040] Usage cycle prediction module: obtain the current power equipment's input cycle in real time, the input cycle being the time period between the time it is put into use and the current time; and obtain the current load curve and current temperature curve of the current power equipment within the input cycle; obtain the predicted usage cycle Ty of the current power equipment based on the load factor and environmental factor.

[0041] Beneficial effects of the present invention:

[0042] After the power equipment of the power system is put into use, it will inevitably age. In the prior art, the aging monitoring method for power equipment mainly involves regular manual inspection of the aging of the power equipment, so as to promptly detect and replace the power equipment that has reached the end of its service life. However, due to the complex installation environment of the power equipment, which may be underground or in the air, the manual regular inspection method is relatively cumbersome and costly. In addition, the aging of the power equipment is not only affected by external environmental factors, but also by the pressure and load on the power system. Therefore, the regular inspection method cannot promptly detect the power equipment that has reached the end of its service life, resulting in the failure to replace the power equipment in time, thereby affecting the normal operation of the power system.

[0043] Compared with the prior art, the present invention can obtain the operating data of power equipment in real time, and conduct in-depth analysis in combination with historical data, so as to achieve accurate prediction of the use cycle of power equipment; this not only helps to discover potential problems in advance, but also provides strong support for the maintenance and optimization of the power system; the present invention not only takes into account the load curve of the power equipment, but also introduces environmental factors such as temperature, so that the prediction results are more comprehensive and accurate; the present invention calculates the load factor and environmental factor, and uses a multi-dimensional analysis method to help better understand the operating conditions and influencing factors of the power equipment; through the feedback of real-time data, the scheme can dynamically adjust the prediction model to make it more in line with the actual operating conditions; this dynamic adjustment mechanism enhances the adaptability and flexibility of the scheme and improves the accuracy of the prediction; the evaluation of the use cycle helps the power system operation and maintenance personnel to reasonably arrange the maintenance plan and avoid sudden failures, thereby improving the overall reliability and stability of the power system; by reducing unexpected power outages and maintenance costs, and optimizing the use efficiency of power equipment, the present invention can bring significant economic benefits to power companies, realize the intelligence and automation of power monitoring, reduce the need for manual intervention, and improve monitoring efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The present invention will be further described below in conjunction with the accompanying drawings.

[0045] Figure 1 The present invention is a flowchart of an artificial intelligence-based power system intelligent monitoring method and system. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] See also Figure 1 As shown, the present invention is an intelligent monitoring method for a power system based on artificial intelligence, comprising the following steps:

[0048] Step S1: Acquire historical data of the power equipment, the historical data including the use period of the power equipment, and load time series data and temperature time series data within the use period; obtain a standard use period T0 according to the historical data, and establish a standard load curve and a standard temperature curve;

[0049] It is understood that, based on the collected historical data, a standard usage cycle is calculated, the standard cycle represents the average usage time of the equipment under normal operating conditions, and the historical data is used to establish a standard load curve and a standard temperature curve, which reflect the load and temperature change trends of the equipment under normal operating conditions;

[0050] As a preferred embodiment of the present invention, the use cycle is a time period between the time of being put into use and the time of aging, the use time is a timestamp corresponding to when the power equipment is put into use, and the aging time is a timestamp corresponding to when the power equipment is replaced or repaired; the load time series data is the power consumption at each timestamp;

[0051] The process of obtaining the standard use cycle, standard load curve and standard temperature curve includes:

[0052] According to the use cycle of each power device in the historical data, an average value of the use cycle of each power device is obtained, which is recorded as a standard use cycle T0;

[0053] Obtain the load curves of each power device and stretch or shrink each load curve horizontally so that T i = T0, where i∈[1,All] and i∈N + , where N + is a positive integer set, All is the total number of power equipment; the load curve after horizontal stretching or reduction is called the telescopic load curve; the power consumption at each monitoring point on the telescopic load curve is obtained, and the power consumption of each telescopic load curve at the same monitoring point is obtained, and the average power consumption of each telescopic load curve at the same monitoring point is obtained; according to the average power consumption at each monitoring point, a standard load curve is established;

[0054] Obtain the temperature curve of each power device, and stretch or shrink each temperature curve horizontally so that T i =T0, the load curve after transverse stretching or reduction is recorded as the stretching temperature curve; the temperature at each monitoring point on the stretching temperature curve is obtained, and the temperature of each stretching temperature curve at the same monitoring point is obtained, and then the average temperature of each stretching temperature curve at the same monitoring point is obtained; according to the average temperature at each monitoring point, a standard temperature curve is established;

[0055] It should be noted that the process of establishing the standard load curve includes:

[0056] A rectangular coordinate system is established with power as the ordinate and the monitoring point number as the abscissa; the number of each monitoring point and its corresponding average power consumption are converted into coordinate points of corresponding positions on the rectangular coordinate system; each coordinate point is connected with a smooth curve, and the curve is recorded as a standard load curve;

[0057] It can be understood that the use cycle specifically refers to the time period from the time when the power equipment is put into use until the time when the equipment needs to be replaced or repaired due to aging; it is used to clarify the time range of monitoring, that is, from the brand new state to the state that needs maintenance or replacement; the total use time refers to the time point when the power equipment starts to operate and is officially put into use, and the time point usually corresponds to the moment when the equipment is installed and starts to perform its intended function; in contrast, the aging time refers to the time point when the performance of the equipment deteriorates due to long-term operation, so that it needs to be repaired or completely replaced; these two time points provide a clear starting point and end point for the use cycle; the load time series data refers to a series of power consumption data recorded in chronological order during the use cycle of the power equipment; each set of data corresponds to a specific timestamp, reflecting the power consumption at that point in time;

[0058] It can be understood that the standard use cycle is obtained by calculating the average value of the use cycles of all power equipment; the standard cycle can be used as a benchmark for comparing and evaluating the performance of individual equipment; the standard load curve is established by horizontally stretching or reducing the load curves of each power equipment to align them with the standard use cycle, and calculating the average power consumption at each monitoring point; the standard temperature curve is similar to the method of establishing the standard load curve, and is established by adjusting the temperature curve and calculating the average temperature at each monitoring point;

[0059] Step S2: Establish a temperature curve of the power equipment, and select m monitoring points at equal intervals on the temperature curve; if there are two temperature curves that match, record the power equipment class environment corresponding to the two temperature curves; select a number of power equipment whose any two temperature curves are class environment, and record them as class environment equipment;

[0060] Establish a load curve for environmental equipment; obtain a rising interval on the load curve, where the slope average between two timestamps exceeds a preset slope threshold; and obtain a load factor K f :

[0061] ;

[0062] Where N0 is the number of rising intervals on the standard load curve, k 0x is the mean slope of the xth climbing interval on the standard load curve, k ix is the mean slope of the xth climbing interval on the ith load curve, T i is the use cycle of the i-th type of environmental equipment, N i is the number of climbing intervals on the i-th load curve, and μ is the preset first correction coefficient;

[0063] It should be noted that the derivative value at each monitoring point on the temperature curve is the temperature change rate; the sum of the absolute values ​​of the derivative values ​​at each monitoring point is obtained. If the sum of the absolute values ​​is less than or equal to the preset temperature difference threshold R, it is considered that the temperature curves of the two devices are consistent, that is, they are under similar environmental conditions;

[0064] It can be understood that if the temperature curves corresponding to two power devices match, the two power devices are identified as being in similar environments and recorded as similar environment devices, and the load curves of similar environment devices are further analyzed; by comparing the load factors of different devices, the impact of power load on the aging of power devices can be evaluated;

[0065] As a preferred embodiment of the present invention, the selection of the monitoring points includes points corresponding to the time of commissioning and the time of aging on the temperature curve;

[0066] As a preferred embodiment of the present invention, the process of determining whether two temperature curves are consistent includes:

[0067] Let the two temperature curves be F1 and F2. If F1 and F2 satisfy , where F1 t is the value corresponding to the tth monitoring point on F1, F2 t is the value corresponding to the tth monitoring point on F2; then the two temperature curves are consistent;

[0068] If F1 and F2 do not satisfy , then the two temperature curves do not match;

[0069] It can be understood that setting the temperature difference threshold to be greater than or equal to the average value plus one standard deviation can ensure that most normal fluctuations are covered while reducing the impact of extreme values;

[0070] As a preferred embodiment of the present invention, the slope threshold is determined as follows:

[0071] The slope threshold is denoted as kst, and kst=tanθ, where θ is the angle between the corresponding tangent and the x-axis, and the setting range of the angle is (45°, 90°), then the setting range of the slope threshold is kst∈(tan45°, tan90°);

[0072] It is understandable that the climbing interval indicates a sharp increase in power demand, which may be caused by various factors such as increased industrial production and peak power consumption in residential areas; operations such as starting and stopping of large-capacity equipment will cause power fluctuations and flickers, which will impact the stable operation of the equipment. Frequent impact loads will significantly reduce the life of the equipment and accelerate equipment aging;

[0073] Step S3: Establish a load curve of the power equipment, and select m monitoring points at equal intervals on the load curve; if there are two load curves that match, record the power equipment class loads corresponding to the two load curves; select a number of power equipment with any two load curves that are class loads, and record them as class load equipment;

[0074] Establish a temperature curve for load-like equipment and obtain the extreme temperature point on the temperature curve. The extreme temperature point is a point where the temperature corresponding to the timestamp does not belong to the preset temperature range threshold [Tem1, Tem2]; then obtain the environmental factor K h :

[0075] ;

[0076] in , num is the total number of load-type devices, T e is the service life of the e-th type of load equipment, M e is the number of extreme temperature points on the e-th temperature curve, M0 is the number of extreme temperature points on the standard temperature curve, tem eq is the temperature corresponding to the qth extreme temperature point on the eth temperature curve, tem 0q is the temperature corresponding to the qth extreme temperature point on the standard temperature curve, and λ is the preset second correction coefficient;

[0077] It should be noted that the process of determining whether the two load curves are consistent includes:

[0078] Let the two load curves be f1 and f2. If f1 and f2 satisfy , where f1 t is the value corresponding to the tth monitoring point on f1, f2 t is the value corresponding to the tth monitoring point on f2; then the two load curves are consistent;

[0079] If f1 and f2 do not satisfy , then the two load curves do not match;

[0080] It can be understood that the preset load difference threshold is used to screen out power equipment with similar loads during the use period, by judging whether the values ​​corresponding to the load curves at various monitoring points are similar, that is, whether the shapes and changing trends of the curves are close;

[0081] It should be noted that Td(tem) indicates the degree to which the extreme temperature point exceeds the threshold of the preset temperature range; the environmental factor is obtained according to the number of extreme temperature points on the temperature curve, the degree to which each extreme temperature point exceeds the threshold of the preset temperature range, and the periodic change compared with the standard use cycle; the environmental factor is used to evaluate the impact of load on the aging of power equipment under different environmental conditions;

[0082] As a preferred embodiment of the present invention, in the process of setting the preset temperature range threshold [Tem1, Tem2], Tem1≤0°C, Tem2≥40°C;

[0083] It should be noted that, generally speaking, the normal operating temperature range of power equipment is between 0℃ and 40℃. This range is considered to be the normal temperature for most common environmental conditions. Exceeding this range may cause the power equipment to overheat, affecting its performance and life. Therefore, it is set that Tem1≤0℃, Tem2≥40℃;

[0084] Step S4: obtaining the current power equipment input cycle in real time, the input cycle being the time period from the time of input to the current time; and obtaining the current load curve and current temperature curve of the current power equipment within the input cycle;

[0085] According to the load factor and environmental factor, the predicted use period Ty of the current power equipment is obtained:

[0086] ;

[0087] in , , M' is the total number of extreme temperature points on the current temperature curve, tem' q is the temperature corresponding to the qth extreme temperature point on the current temperature curve, N' is the total number of climbing intervals on the current load curve, k' x is the mean slope of the xth climbing interval on the current load curve;

[0088] It can be understood that based on the obtained load factors and environmental factors, as well as the load curve and temperature curve of the power equipment, the load conditions and ambient temperature changes experienced by the current power equipment during the investment cycle are obtained, and then the standard usage cycle is corrected to predict the predicted usage cycle of the current power equipment.

[0089] An artificial intelligence-based intelligent monitoring system for a power system, characterized by comprising:

[0090] Historical data processing module: obtain historical data of power equipment, the historical data includes the use cycle of the power equipment, and load time series data and temperature time series data within the use cycle; obtain the standard use cycle T0 according to the historical data, and establish a standard load curve and a standard temperature curve;

[0091] Load factor analysis module: establish the temperature curve of the power equipment, and select m monitoring points at equal intervals on the temperature curve; if there are two temperature curves that match, record the power equipment class environment corresponding to the two temperature curves; select a number of power equipment whose any two temperature curves are class environment, and record them as class environment equipment;

[0092] Establish a load curve for environmental equipment; obtain a rising interval on the load curve, where the slope average between two timestamps exceeds a preset slope threshold; and obtain a load factor K f :

[0093] ;

[0094] Where N0 is the number of rising intervals on the standard load curve, k 0x is the mean slope of the xth climbing interval on the standard load curve, k ix is the mean slope of the xth climbing interval on the ith load curve, T i is the use cycle of the i-th type of environmental equipment, N i is the number of climbing intervals on the i-th load curve, and μ is the preset first correction coefficient;

[0095] Environmental factor analysis module: establish the load curve of the power equipment, and select m monitoring points at equal intervals on the load curve; if there are two load curves that match, record the power equipment class loads corresponding to the two load curves; select a number of power equipment with any two load curves that are class loads, and record them as class load equipment;

[0096] Establish a temperature curve for load-like equipment and obtain the extreme temperature point on the temperature curve. The extreme temperature point is a point where the temperature corresponding to the timestamp does not belong to the preset temperature range threshold [Tem1, Tem2]; then obtain the environmental factor K h :

[0097] ;

[0098] in , num is the total number of load-type devices, T e is the service life of the e-th type of load equipment, M e is the number of extreme temperature points on the e-th temperature curve, M0 is the number of extreme temperature points on the standard temperature curve, tem eq is the temperature corresponding to the qth extreme temperature point on the eth temperature curve, tem 0q is the temperature corresponding to the qth extreme temperature point on the standard temperature curve, and λ is the preset second correction coefficient;

[0099] Use cycle prediction module: obtain the current power equipment input cycle in real time, the input cycle is the time period between the time of input and the current time; and obtain the current load curve and current temperature curve of the current power equipment within the input cycle;

[0100] According to the load factor and environmental factor, the predicted use period Ty of the current power equipment is obtained:

[0101] ;

[0102] in , , M' is the total number of extreme temperature points on the current temperature curve, tem' q is the temperature corresponding to the qth extreme temperature point on the current temperature curve, N' is the total number of climbing intervals on the current load curve, k' x It is the mean slope of the xth climbing interval on the current load curve.

[0103] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. An intelligent monitoring method for power system based on artificial intelligence, characterized in that: The following steps are involved: Step S1: Acquire historical data of the power equipment, wherein the historical data includes the use cycle of the power equipment, and load time series data and temperature time series data within the use cycle; Obtaining a standard usage period T0 according to the historical data, and establishing a standard load curve and a standard temperature curve; Step S2: Establish a temperature curve of the power equipment, and determine whether the power equipment is an environmental-type equipment according to the temperature curve; obtain a rising interval on the load curve of the environmental-type equipment, where the rising interval is an interval in which the average slope between two timestamps exceeds a preset slope threshold; The load factor K is obtained according to the standard load curve and the climbing interval on the load curve. f ; Step S3: Establish a load curve of the power equipment, and determine whether the power equipment is a load-like device according to the load curve; obtain the extreme temperature point on the temperature curve of the load-like device, where the extreme temperature point is a point where the temperature corresponding to the timestamp does not belong to the preset temperature range threshold [Tem1, Tem2]; obtain the environmental factor K according to the standard temperature curve and the extreme temperature point on the temperature curve h ; Step S4: obtaining the current power equipment input cycle in real time, the input cycle being the time period between the time of input and the current time; and obtaining the current load curve and the current temperature curve of the current power equipment within the input cycle; and obtaining the predicted use cycle Ty of the current power equipment according to the load factor and the environmental factor; Establish a temperature curve for the power equipment, and select m monitoring points at equal intervals on the temperature curve; if there are two temperature curves that match, record the power equipment class environment corresponding to the two temperature curves; select a number of power equipment whose any two temperature curves are class environment, and record them as class environment equipment; In step S2, the load factor K f The process of obtaining includes: Where N0 is the number of climbing intervals on the standard load curve, k 0x is the mean slope of the xth climbing interval on the standard load curve, k ix is the mean slope of the xth climbing interval on the ith load curve, T i is the use cycle of the i-th type of environmental equipment, N i is the number of climbing intervals on the i-th load curve, μ is the preset first correction coefficient; Establish a load curve for the power equipment, and select m monitoring points at equal intervals on the load curve; if there are two load curves that match, record the power equipment class loads corresponding to the two load curves; select a number of power equipment with any two load curves that are class loads, and record them as class load equipment; In step S3, the environmental factor K h The process of obtaining includes: in num is the total number of load-type devices, T e is the service life of the e-th type of load equipment, M e is the number of extreme temperature points on the e-th temperature curve, M0 is the number of extreme temperature points on the standard temperature curve, tem eq is the temperature corresponding to the qth extreme temperature point on the eth temperature curve, tem 0q is the temperature corresponding to the qth extreme temperature point on the standard temperature curve, and λ is the preset second correction coefficient; In step S4, the process of obtaining the predicted usage period Ty includes: in M′ is the total number of extreme temperature points on the current temperature curve, tem′ q is the temperature corresponding to the qth extreme temperature point on the current temperature curve, N′ is the total number of climbing intervals on the current load curve, k′ x It is the mean slope of the xth climbing interval on the current load curve.

2. The method for intelligent monitoring of a power system based on artificial intelligence according to claim 1, characterized in that: In step S1, the usage cycle is the time period between the time of commissioning and the time of aging, the usage time is the timestamp corresponding to when the power equipment is put into use, and the aging time is the timestamp corresponding to when the power equipment is replaced or repaired; the load time series data is the power consumption at each timestamp.

3. The method for intelligent monitoring of a power system based on artificial intelligence according to claim 2, characterized in that: In step S1, the process of obtaining the standard use cycle, the standard load curve and the standard temperature curve includes: According to the use cycle of each power device in the historical data, an average value of the use cycle of each power device is obtained, which is recorded as a standard use cycle T0; Obtain the load curve of each power device and select m monitoring points at equal intervals on the temperature curve; stretch or shrink each load curve horizontally so that T i = T0, where i∈[1,All] and i∈N + , where N + is a positive integer set, All is the total number of power equipment; the load curve after horizontal stretching or reduction is called the telescopic load curve; the power consumption at each monitoring point on the telescopic load curve is obtained, and the power consumption of each telescopic load curve at the same monitoring point is obtained, and the average power consumption of each telescopic load curve at the same monitoring point is obtained; according to the average power consumption at each monitoring point, a standard load curve is established; Obtain the temperature curve of each power equipment and select m monitoring points at equal intervals on the load curve; stretch or shrink each temperature curve horizontally so that T i =T0, the load curve after transverse stretching or reduction is recorded as the expansion and contraction temperature curve; the temperature at each monitoring point on the expansion and contraction temperature curve is obtained, and the temperature of each expansion and contraction temperature curve at the same monitoring point is obtained, and then the average temperature of each expansion and contraction temperature curve at the same monitoring point is obtained; according to the average temperature at each monitoring point, a standard temperature curve is established.

4. The method for intelligent monitoring of a power system based on artificial intelligence according to claim 1, characterized in that: In step S2, the process of determining whether the power equipment is an environmental-type equipment according to the temperature curve includes: If there are two temperature curves that match, the power equipment corresponding to the two temperature curves are recorded as class environments; select a number of power equipment whose any two temperature curves are class environments and record them as class environment equipment.

5. The method for intelligent monitoring of a power system based on artificial intelligence according to claim 4, characterized in that: In step S2, the process of determining whether the two temperature curves are consistent includes: Let the two temperature curves be F1 and F2. If F1 and F2 satisfy Among them, F1 t is the value corresponding to the tth monitoring point on F1, F2 t is the value corresponding to the tth monitoring point on F2; then the two temperature curves are consistent.

6. The method for intelligent monitoring of a power system based on artificial intelligence according to claim 1, characterized in that: In step S2, the slope threshold is determined as follows: The slope threshold is denoted as kst, and kst=tanθ, wherein θ is the angle between the corresponding tangent and the x-axis, and the setting range of the angle is (45°, 90°), then the setting range of the slope threshold is kst∈(tan45°, tan90°).

7. The method for intelligent monitoring of a power system based on artificial intelligence according to claim 1, characterized in that: In step S3, during the setting process of the preset temperature range threshold [Tem1, Tem2], Tem1≤0°C, Tem2≥40°C.

8. An artificial intelligence-based intelligent monitoring system for power systems, characterized in that: include: Historical data processing module: acquiring historical data of the power equipment, the historical data including the use cycle of the power equipment, and load time series data and temperature time series data within the use cycle; Obtaining a standard usage period T0 according to the historical data, and establishing a standard load curve and a standard temperature curve; Load factor analysis module: establish a temperature curve of the power equipment, and determine whether the power equipment is an environmental-type equipment according to the temperature curve; obtain a climbing interval on the load curve of the environmental-type equipment, where the climbing interval is an interval in which the average slope between two timestamps exceeds a preset slope threshold; The load factor K is obtained according to the standard load curve and the climbing interval on the load curve. f ; Environmental factor analysis module: establish a load curve of the power equipment, determine whether the power equipment is a load-like device based on the load curve; obtain the extreme temperature point on the temperature curve of the load-like device, the extreme temperature point is a point where the temperature corresponding to the timestamp does not belong to the preset temperature range threshold [Tem1, Tem2]; obtain the environmental factor K based on the standard temperature curve and the extreme temperature point on the temperature curve h ; Use cycle prediction module: obtain the current power equipment input cycle in real time, the input cycle is the time period between the time of input and the current time; and obtain the current load curve and current temperature curve of the current power equipment within the input cycle; obtain the predicted use cycle Ty of the current power equipment according to the load factor and environmental factor; Establish a temperature curve for the power equipment, and select m monitoring points at equal intervals on the temperature curve; if there are two temperature curves that match, record the power equipment class environment corresponding to the two temperature curves; select a number of power equipment whose any two temperature curves are class environment, and record them as class environment equipment; The load factor K f The process of obtaining includes: Where N0 is the number of climbing intervals on the standard load curve, k 0x is the mean slope of the xth climbing interval on the standard load curve, k ix is the mean slope of the xth climbing interval on the ith load curve, T i is the use cycle of the i-th type of environmental equipment, N i is the number of climbing intervals on the i-th load curve, μ is the preset first correction coefficient; Establish a load curve for the power equipment, and select m monitoring points at equal intervals on the load curve; if there are two load curves that match, record the power equipment class loads corresponding to the two load curves; select a number of power equipment with any two load curves that are class loads, and record them as class load equipment; The environmental factor K h The process of obtaining includes: in num is the total number of load-type devices, T e is the service life of the e-th type of load equipment, M e is the number of extreme temperature points on the e-th temperature curve, M0 is the number of extreme temperature points on the standard temperature curve, tem eq is the temperature corresponding to the qth extreme temperature point on the eth temperature curve, tem 0q is the temperature corresponding to the qth extreme temperature point on the standard temperature curve, and λ is the preset second correction coefficient; The process of obtaining the predicted usage period Ty includes: in M′ is the total number of extreme temperature points on the current temperature curve, tem′ q is the temperature corresponding to the qth extreme temperature point on the current temperature curve, N′ is the total number of climbing intervals on the current load curve, k′ x It is the mean slope of the xth climbing interval on the current load curve.

Images