Power station equipment health state evaluation method, system and equipment under time sequence and storage medium

Abstract

The invention provides a power station equipment health state evaluation method and system under a time sequence, equipment and a medium. The method comprises the following steps: S1, collecting operation state data of power station equipment in real time and storing the data according to the time sequence; s2, carrying out preprocessing operation on the collected data; s3, according to the operation state data of the equipment, respectively processing to obtain an equipment predicted degradation trend coefficient and an equipment environment coefficient, calculating to obtain an equipment operation state variable quantity according to the change in the previous historical period, and judging whether to send out an equipment degradation trend early warning or not according to a comparison result; s4, marking the equipment which sends out the deterioration trend early warning, obtaining various health indexes of the marked equipment, synthesizing the various health indexes, calculating to obtain a health state evaluation value of the marked equipment, and performing health evaluation; and S5, comparing the health assessment value of the marked equipment with a preset health area assessment interval to realize assessment of the health state of the power station equipment.

Description

Technical Field

[0001] The present invention belongs to the technical field of power plant equipment health management, and specifically relates to a method, system, equipment and storage medium for evaluating the health status of power plant equipment under time series. Background Art

[0002] Pumped-storage power stations are a vital component of modern power systems, providing crucial functions such as peak-load shifting, frequency and phase regulation, and emergency standby. Their operational status directly impacts the safe and stable operation of power systems. Pump-turbines, the energy conversion devices within pumped-storage units, possess reversible operation capabilities, enabling flexible switching between pumping and power generation modes. Therefore, assessing the health of pump-turbines is crucial for ensuring stable unit operation and grid power quality.

[0003] However, the existing power plant equipment health status assessment system, although it detects pump-turbines through various sensors and detection instruments, ignores the impact of environmental parameters on pump-turbines, resulting in certain defects in the health assessment after single-direction monitoring. In addition, there is a problem of not distinguishing between the primary and secondary health assessments of each component or the entire pump-turbine, which leads to excessive waste of computing resources. Summary of the invention

[0004] The first object of the present invention is to provide a method for evaluating the health status of power plant equipment under time series in response to the above-mentioned problems.

[0005] To this end, the above-mentioned purpose of the present invention is achieved through the following technical solutions:

[0006] A method for evaluating the health status of power plant equipment under time series conditions comprises the following steps:

[0007] S1, collect the operating status data of power station equipment in real time and store the data in time series;

[0008] S2. Preprocessing the collected data;

[0009] S3. Based on the equipment's operating status data, the predicted equipment degradation trend coefficient and the equipment environmental coefficient are processed separately. Based on the changes in the predicted equipment degradation trend coefficient and the equipment environmental coefficient in the previous historical period, the change in the equipment's operating status is calculated. Based on the comparison results, it is determined whether to issue an equipment degradation trend warning.

[0010] S4. Mark the equipment that issues a degradation trend warning, obtain various health indicators of the marked equipment, calculate the health status assessment value of the marked equipment by integrating the various health indicators, and perform a health assessment based on the health assessment value of the marked equipment;

[0011] S5. Compare the health assessment value of the marking device with the preset health zone assessment range to achieve the assessment of the health status of the power station equipment.

[0012] While adopting the above technical solution, the present invention can also adopt or combine the following technical solutions:

[0013] As a preferred technical solution of the present invention: in step S1, the operating state data includes the operating state data of the equipment.

[0014] As a preferred technical solution of the present invention: in step S2, the preprocessing includes cleaning, denoising, and normalization.

[0015] As a preferred technical solution of the present invention: step S3 further includes the following sub-steps:

[0016] S31. Divide a historical period into multiple sub-periods at equal intervals;

[0017] Substitute the environmental parameter θ of the ψ item equipment υ into the formula to calculate the equipment environment coefficient Hh s :

[0018]

[0019] In the formula, θ υmax represents the maximum value of the υ-th environmental parameter, and θ υmin represents the minimum value of the υ-th environmental parameter;

[0020] S32. Fit and obtain the change curve Hh of the equipment environment coefficient over time for each sub-period s (t) and the reference change curve Hh sc (t), substitute them into the formula to calculate the change amount K of the equipment operating state in a historical period g :

[0021]

[0022] In the formula, K s represents the change amount of the equipment operating state in the s-th sub-period, tj and tj+1 represent the starting point and ending point of any sub-period, N represents the number of sub-periods, and e s (x) represents the judgment function of the equipment prediction deterioration trend coefficient in the s-th sub-period, and η s represents the preset weight factor.

[0023] As a preferred technical solution of the present invention: the expression of the judgment function e s (x) of the equipment prediction deterioration trend coefficient in the s-th sub-period in step S32 is:

[0024]

[0025] In the formula, n represents the number of samplings in the s-th sub-period, and x i represents the equipment predicted deterioration trend coefficient at the i-th sampling, and represents the preset equipment predicted deterioration trend warning value.

[0026] As a preferred technical solution of the present invention: Step S4 further includes the following sub-steps:

[0027] S41. Continuously obtain m water guide bearing pad temperatures at a predetermined time interval, input them into the bearing pad temperature analysis model, and output the water guide bearing pad temperature coefficient KW;

[0028] S42. Substitute the obtained water guide bearing pad temperature coefficient KW, water guide bearing vibration coefficient KB, and water guide bearing oil sump temperature coefficient BW into the formula group, and calculate the water guide bearing pad temperature health index F KW , water guide bearing vibration health index F KB , and water guide bearing oil sump temperature health index F BW respectively:

[0029]

[0030] S43. Then substitute into the formula to calculate the health status evaluation value JK of the marked equipment:

[0031] JK = (λ a F KW + λ b F KB + λ c F ΒW ) -1

[0032] In the formula, KW c , KB c , BW c respectively represent the water guide bearing pad temperature warning value, water guide bearing vibration warning value, and water guide bearing oil sump temperature warning value, and λ a , λ b , λ c represent preset proportionality coefficients.

[0033] As a preferred technical solution of the present invention: In step S42, the calculation formulas of the water guide bearing pad temperature coefficient KW, water guide bearing vibration coefficient KB, and water guide bearing oil sump temperature coefficient BW are as follows:

[0034]

[0035] In the formula, ω1, ω2, ω3 represent preset weight coefficients, and kw max, kw min represents the maximum and minimum values of the temperature of the water guide bearing pad, k'w ξ represents the difference between the temperatures of two adjacent water guide bearing pads at the ξth position, m represents the total number of times of collecting the temperature of the water guide bearing pad, represents the temperature of the water guide bearing pad collected at the time, and represents the average temperature of the water guide bearing pad;

[0036]

[0037] In the formula, t0 and t1 represent the starting point and the ending point of the detection period, Θ1 and Θ2 represent preset coefficients, kb X (t) represents the curve of the X-direction swing of the water guide bearing changing with time, kb Y (t) represents the curve of the Y-direction swing of the water guide bearing changing with time;

[0038]

[0039] In the formula, is the number of times of collecting the oil temperature of the water guide bearing oil sump, bw τ is the oil temperature of the water guide bearing oil sump collected at the τth time, is the average value of the oil temperature of the water guide bearing oil sump.

[0040] The second object of the present invention is to provide a power station equipment health status evaluation system under time series, including the following modules:

[0041] An equipment data acquisition module, which is used to collect the operation status data of power station equipment in real time and store the data in a time series;

[0042] A data preprocessing module, which is used to perform preprocessing operations such as cleaning, denoising, and normalization on the collected data;

[0043] An equipment status monitoring module, according to the operation status data of the equipment, respectively processes to obtain the equipment predicted deterioration trend coefficient and the equipment environment coefficient, calculates the equipment operation status change amount according to the changes of the equipment predicted deterioration trend coefficient and the equipment environment coefficient in the previous historical period; and compares the equipment operation status change amount with the preset equipment operation status warning value; if the equipment operation status change amount > the equipment operation status warning value, then issue an equipment deterioration trend warning, otherwise judge that the equipment deterioration trend is normal;

[0044] A health status evaluation module, which is used to mark the equipment that issues a deterioration trend warning, obtain various health indicators of the marked equipment, calculate the health status evaluation value of the marked equipment after comprehensively considering various health indicators, and perform a health evaluation according to the health evaluation value of the marked equipment.

[0045] The third object of the present invention is to provide an electronic device, which includes a processor, a communication interface, a memory, and a communication bus. The processor, the communication interface, and the memory communicate with each other through the communication bus. The characteristics are as follows:

[0046] A memory for storing a computer program;

[0047] A processor for executing the computer program stored on the memory to implement the steps of the power station equipment health status evaluation method under the time series as described above.

[0048] Another object of the present invention is to provide a non-volatile storage medium, in which an executable program is stored. When the executable program is executed by a processor, the steps of the power station equipment health status evaluation method under the time series as described above are implemented.

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] 1) The operation status data of power station equipment, including equipment body status parameters and environmental parameters, are collected in real time through the equipment data acquisition module, ensuring comprehensive and immediate monitoring of the equipment status. The data preprocessing module further improves the accuracy and reliability of the data, providing a solid foundation for subsequent monitoring and evaluation. Through the equipment status monitoring module, the system can timely detect the deterioration trend of the equipment. Once the change amount of the equipment operation status exceeds the preset warning value, a warning is immediately issued, effectively improving the maintenance efficiency and safety of power station equipment;

[0051] 2) By monitoring the equipment status in real time, warning potential problems, and accurately evaluating the equipment health status, the risk of power station equipment failure is effectively reduced, not only improving the operation stability of the power station, but also ensuring the safety of power station staff and the surrounding environment;

[0052] 3) Through early warning analysis and judgment of the overall predicted deterioration trend of the pump-turbine, equipment with early warning of predicted deterioration areas is marked with emphasis, and then the health assessment of the marked equipment is carried out. Since the water guide bearing is the core component of the pump-turbine and its operation status directly affects the stability and safety of the entire unit, the health assessment of various indicators of the water guide bearing of the marked equipment is carried out, and after comprehensive processing, it is used as the health assessment value of the marked equipment. On the premise of saving computing power resources, it can also take into account the need to comprehensively reflect the overall health status of the marked equipment. At the same time, it not only helps the operation and maintenance personnel to timely understand the health status of the equipment, but also provides strong support for formulating scientific and reasonable maintenance plans and overhaul strategies. Description of the Drawings

[0053] Figure 1It is a flowchart of the method for evaluating the health status of power station equipment under time series provided by the present invention.

[0054] Figure 2 It is a schematic diagram for monitoring the predicted deterioration trend of equipment with vibration parameters.

[0055] Figure 3 It is a schematic diagram of the deep long short-term memory neural network model. Specific implementation manners

[0056] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0057] As Figure 1 shown, a method for evaluating the health status of power station equipment under time series specifically includes the following steps:

[0058] S1. Real-time collect the operation status data of power station equipment and store the data in time series;

[0059] The operation status data includes the operation status data of the equipment, the equipment body status parameters include the vibration, temperature, and oil level of the equipment, and the environmental parameters where the equipment is located include humidity, temperature, and pressure; the above various parameters are all monitored by sensors or special detection instruments.

[0060] S2. Perform preprocessing operations on the collected data;

[0061] The preprocessing includes cleaning, denoising, and normalization. The data preprocessing adopts existing technologies, and it is only necessary to achieve the purpose of data preprocessing.

[0062] S3. According to the operation status data of the equipment, respectively process to obtain the equipment predicted deterioration trend coefficient and the equipment environment coefficient, input the preprocessed equipment body status parameters into the pre-trained deep long short-term memory neural network model, output the equipment predicted deterioration trend coefficient, calculate the equipment operation status change amount according to the changes of the equipment predicted deterioration trend coefficient and the equipment environment coefficient in the previous historical cycle, and judge whether to issue an equipment deterioration trend warning according to the comparison result;

[0063] The deep long short-term memory neural network model in the present invention, that is, the DLSTM model can accurately capture the time series changes of equipment status parameters, realize the accurate prediction of the deterioration trend, and the model has strong adaptive learning ability, without the need for manual setting of complex rules; at the same time, it has high real-time performance and flexibility, can quickly respond to equipment status changes, provide effective support for the intelligent operation and maintenance of power station equipment, and can also reduce the downtime and maintenance costs, playing a role in improving the operation efficiency and safety of the power station;

[0064] Step S3 further includes the following sub-steps:

[0065] S31. Divide a historical period into multiple sub-periods at equal intervals;

[0066] Substitute the environmental parameter θ of the ψ-term device υ into the formula to calculate the device environmental coefficient Hh s :

[0067]

[0068] In the formula, θ υmax represents the maximum value of the υ-th environmental parameter, and θ υmin represents the minimum value of the υ-th environmental parameter;

[0069] S32. Fit and obtain the change curve of the device environmental coefficient over time Hh s (t) and the reference change curve Hh sc (t), substitute them into the formula to calculate the change amount K of the device operating state in a historical period g :

[0070]

[0071] In the formula, K s represents the change amount of the device operating state in the s-th sub-period, tj and tj+1 represent the starting point and ending point of any sub-period, N represents the number of sub-periods, and e s (x) represents the judgment function for the device predicted deterioration trend coefficient in the s-th sub-period, and η s represents the preset weight factor.

[0072] If the deviation between the device environmental coefficient and the reference environmental coefficient in each sub-period is larger, it means that the cumulative change amount of the device environmental coefficient is larger, so the device environment is more unstable.

[0073] The expression of the judgment function e s (x) for the device predicted deterioration trend coefficient in the s-th sub-period in step S32 is:

[0074]

[0075] In the formula, n represents the number of samples in the s-th sub-period, and x i represents the device predicted deterioration trend coefficient at the i-th sampling, represents the preset device predicted deterioration trend warning value. If there is at least one then Otherwise, e s (x) = 1.

[0076] If the volatility of the equipment's predicted deterioration trend coefficient is greater, it indicates that there are more problems with the equipment's deterioration trend. Therefore, the impact on K g is greater. Thus Otherwise, e s (x) = 1. Therefore, through the above technical solution, the change in the operating state of each device, i.e., the pump-turbine, within a historical period can be accurately calculated. Then, the change in the device's operating state is compared with the preset early warning value of the device's operating state. If the change in the device's operating state > the early warning value of the device's operating state, an early warning of the equipment deterioration trend is issued; otherwise, it is determined that the equipment deterioration trend is normal.

[0077] S4. Mark the devices for which the deterioration trend warning is issued, and obtain the various health indicators of the marked devices. After synthesizing the various health indicators, calculate the health status evaluation value of the marked devices, and conduct a health assessment based on the health evaluation value of the marked devices;

[0078] Step S4 also includes the following sub-steps:

[0079] S41. Continuously obtain the temperatures of m water guide bearing pads at predetermined time intervals and input them into the bearing pad temperature analysis model to output the water guide bearing pad temperature coefficient KW;

[0080] S42. Substitute the obtained water guide bearing pad temperature coefficient KW, water guide bearing vibration coefficient KB, and water guide bearing oil sump temperature coefficient BW into the formula group to calculate the water guide bearing pad temperature health indicator F KW , water guide bearing vibration health indicator F KB , and water guide bearing oil sump temperature health indicator F BW as follows: :

[0081]

[0082] The calculation formulas for the water guide bearing pad temperature coefficient KW, water guide bearing vibration coefficient KB, and water guide bearing oil sump temperature coefficient BW are as follows:

[0083]

[0084] In the formula, ω1, ω2, ω3 represent preset weight coefficients determined based on historical data, kw max , kw min represent the maximum and minimum values of the water guide bearing pad temperature, represents the difference between the ξ-th adjacent two water guide bearing pad temperatures, m represents the total number of water guide bearing pad temperature acquisitions, kw ζ represents the water guide bearing pad temperature at the ζ-th acquisition, represents the average value of the water guide bearing pad temperature;

[0085] By comprehensive analysis of the deviation between the maximum and minimum values of the water-guided bearing pad temperature kw max -kw min , the temperature deviation between two adjacent water guide bearing pads And the fluctuation of water-guide bearing pad temperature A comprehensive bearing temperature analysis model is established to accurately calculate the water-guide bearing temperature coefficient KW, thereby improving the accuracy of the health assessment of the pump-turbine. Therefore, the larger the water-guide bearing temperature coefficient KW, the worse the safety of the pump-turbine, the higher the probability of failure, and the smaller the health status assessment value JK reflected in the marked equipment.

[0086]

[0087] Where t0 and t1 represent the starting and ending points of the detection period, Θ1 and Θ2 represent the preset coefficients, which are comprehensively formulated based on historical data and experimental data, and kb X (t) represents the curve of the water-guided bearing's X-axis runout varying with time, kb Y (t) represents the curve of the water guide bearing Y-axis swing changing with time;

[0088] First, obtain the changes in the X-direction swing and Y-direction swing of the water-guide bearing during the detection period, and then calculate the water-guide bearing vibration coefficient KB through the integral formula. Obviously, the greater the cumulative change in the X-direction swing and Y-direction swing of the water-guide bearing, the more severe the vibration of the water-guide bearing, and therefore the larger the water-guide bearing vibration coefficient KB, the worse the safety of the pump-turbine, the higher the probability of failure, and the smaller the health status assessment value JK reflected in the marked equipment.

[0089]

[0090] Where, bw is the number of times the oil temperature of the water-guided bearing oil tank is collected, τ is the oil temperature of the water-guided bearing oil tank collected for the τth time, is the average oil temperature of the water-guided bearing oil tank;

[0091] First obtain the oil temperature of the water guide bearing oil tank at different time points, and then calculate the standard deviation using the formula The deviation of the water-guide bearing oil tank oil temperature is analyzed. Obviously, the greater the fluctuation of the water-guide bearing oil tank oil temperature, the greater the deviation of the water-guide bearing oil tank oil temperature. Therefore, the larger the calculated water-guide bearing oil tank oil temperature coefficient BW is, the worse the safety of the pump-turbine is, the more likely it is to fail, and the smaller the health status assessment value JK reflected in the marked equipment is.

[0092] If the temperature coefficient KW of the water guide bearing, the vibration coefficient KB of the water guide bearing, and the oil sump temperature coefficient BW of the water guide bearing are larger, then the health index F of the water guide bearing bush temperature KW 、the health index F of the water guide bearing vibration KB and the health index F of the oil sump temperature of the water guide bearing BW are larger, indicating that there are more problems with the health indicators of the marked equipment, namely the pump-turbine.

[0093] S43. Then substitute into the formula to calculate the health status evaluation value JK of the marked equipment:

[0094] JK = (λ a F KW + λ b F KB + λ c F ΒW ) -1

[0095] In the formula, KW c , KB c , BW c respectively represent the early warning value of the water guide bearing bush temperature, the early warning value of the water guide bearing vibration, and the early warning value of the oil sump temperature of the water guide bearing. λ a , λ b , λ c represent the preset proportionality coefficients, which are determined comprehensively based on historical data and empirical data. If the health status evaluation value is larger, it indicates that the pump-turbine is healthier; otherwise, it indicates that the pump-turbine is less healthy.

[0096] S5. Compare the health evaluation value of the marked equipment with the preset health area evaluation interval to achieve the evaluation of the health status of the power station equipment:

[0097] If the health evaluation value of the marked equipment is lower than the health area evaluation interval, it is judged that the marked equipment is in a serious state;

[0098] If the health evaluation value of the marked equipment falls within the health area evaluation interval, it is judged that the marked equipment is in an abnormal state;

[0099] If the health evaluation value of the marked equipment exceeds the health area evaluation interval, it is judged that the marked equipment is in a state of attention;

[0100] The equipment without a deterioration trend warning is judged to be in a normal state;

[0101] The health degree increases in the order of serious > abnormal > attention > normal.

[0102] The present invention also provides a power station equipment health status evaluation system under a time series, including the following modules:

[0103] The device data acquisition module is used to collect the operation status data of power station devices in real time and store the data in a time series.

[0104] The data preprocessing module is used to perform preprocessing operations such as cleaning, denoising, and normalization on the collected data.

[0105] The device status monitoring module processes the operation status data of the device to obtain the device predicted deterioration trend coefficient and the device environment coefficient respectively. According to the changes of the device predicted deterioration trend coefficient and the device environment coefficient in the previous historical cycle, the device operation status change amount is calculated; and the device operation status change amount is compared with the preset device operation status warning value; if the device operation status change amount > the device operation status warning value, a device deterioration trend warning is issued, otherwise it is judged that the device deterioration trend is normal.

[0106] The health status evaluation module is used to mark the devices that issue deterioration trend warnings, obtain various health indicators of the marked devices, calculate the health status evaluation value of the marked devices after integrating various health indicators, and perform health evaluation according to the health evaluation value of the marked devices.

[0107] The present invention also provides an electronic device, which includes a processor, a communication interface, a memory, and a communication bus. The processor, the communication interface, and the memory complete mutual communication through the communication bus.

[0108] The memory is used to store computer programs.

[0109] The processor is used to execute the computer programs stored on the memory to implement the steps of the method for evaluating the health status of power station devices in the time series as described above.

[0110] The present invention also provides a non-transitory readable storage medium, which provides a non-volatile storage medium. The non-volatile storage medium stores an executable program. When the executable program is executed by a processor, the steps of the method for evaluating the health status of power station devices in the time series as described above are implemented.

[0111] So far, the technical solution of the present invention has been described in combination with the specific experimental process shown in the drawings. However, the protection scope of the present invention is not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A method for evaluating the health status of power station equipment under a time series, characterized in that It includes the following steps: S1. Collect the operation status data of power station equipment in real time and store the data in time series; S2. Perform preprocessing operations on the collected data; S3. According to the operation status data of the equipment, respectively obtain the equipment predicted deterioration trend coefficient and the equipment environment coefficient. According to the changes of the equipment predicted deterioration trend coefficient and the equipment environment coefficient in the previous historical cycle, calculate the equipment operation status change amount, and judge whether to issue an equipment deterioration trend warning according to the comparison result; S4. Mark the equipment that issues a deterioration trend warning, obtain various health indicators of the marked equipment, calculate the health status evaluation value of the marked equipment after synthesizing various health indicators, and perform a health assessment according to the health evaluation value of the marked equipment; S5. Compare the health evaluation value of the marked equipment with the preset health area evaluation interval to realize the evaluation of the health status of power station equipment.

2. The method according to claim 1, wherein: In step S1, the operation status data includes the operation status data of the equipment.

3. The method according to claim 1, wherein: In step S2, the preprocessing includes cleaning, denoising, and normalization.

4. The method according to claim 1, wherein: Step S3 further includes the following sub-steps: S31. Divide a historical cycle into multiple sub-cycles at equal intervals; Substitute the environmental parameter θ of the ψ-term device υ into the formula to calculate the device environmental coefficient Hh s : where θ υmax represents the maximum value of the υ-th environmental parameter, and θ υmin represents the minimum value of the υ-th environmental parameter; S32. Respectively fit and obtain the change curve Hh s (t) of the device environment coefficient with time in each sub-cycle and the reference change curve Hh sc (t), substitute them into the formula to calculate the change amount K of the device operation state in a historical cycle g : Where, K s represents the change in the operating state of the device in the s-th sub-cycle, tj and tj+1 represent the starting point and ending point of any sub-cycle, N represents the number of sub-cycles, e s (x) represents a judgment function regarding the predicted deterioration trend coefficient of the device in the s-th sub-cycle, η s represents a preset weight factor.

5. The method according to claim 4, wherein: The judgment function e s (x) for predicting the deterioration trend coefficient of the device in the s-th sub-period in step S32 is expressed as: where n represents the number of samplings in the s-th sub-cycle, and x i represents the device predicted deterioration trend coefficient at the i-th sampling, and represents the preset warning value of the device predicted deterioration trend.

6. The method according to claim 1, characterized in that: Step S4 further includes the following sub-steps: S41. Continuously obtain the temperatures of m water guide bearing pads at a predetermined time interval, input them into the bearing pad temperature analysis model, and output the water guide bearing pad temperature coefficient KW; S42. Substitute the obtained water guide bearing pad temperature coefficient KW, water guide bearing vibration coefficient KB, and water guide bearing oil sump oil temperature coefficient BW into the formula group, and calculate to obtain the water guide bearing pad temperature health index F KW , the water guide bearing vibration health index F KB , and the water guide bearing oil sump oil temperature health index F BW : S43. Then substitute into the formula to calculate the health status evaluation value JK of the marked equipment: JK = (λ a F KW + λ b F KB + λ c F ΒW ) -1 Wherein, KW c 、KB c 、BW c respectively represent the warning value of the water guide bearing pad temperature, the warning value of the water guide bearing vibration, and the warning value of the oil sump temperature of the water guide bearing, and λ a 、λ b 、λ c represent preset proportionality coefficients.

7. The method according to claim 6, wherein: In step S42, the calculation formulas for the water guide bearing pad temperature coefficient KW, the water guide bearing vibration coefficient KB, and the water guide bearing oil sump oil temperature coefficient BW are as follows: where ω1, ω2, ω3 represent preset weight coefficients, kw max , kw min represent the maximum and minimum values of the water guide bearing pad temperature, represents the difference between the temperatures of two adjacent water guide bearing pads at the ξ-th position, m represents the total number of times the water guide bearing pad temperature is collected, represents the temperature of the water guide bearing pad collected at the -th time, and represents the average temperature of the water guide bearing pad; Where, t0 and t1 represent the start and end points of the detection period, Θ1 and Θ2 represent preset coefficients, and kb X (t) represents the curve of the X-direction swing of the water guide bearing changing with time, and kb Y (t) represents the curve of the Y-direction swing of the water guide bearing changing with time; In the formula, is the acquisition times of the oil sump oil temperature of the water guide bearing, bw τ is the oil sump oil temperature of the water guide bearing acquired at the τ-th time, is the average value of the oil sump oil temperature of the water guide bearing.

8. A power station equipment health status evaluation system under a time series, characterized in that, It includes the following modules: An equipment data acquisition module, which is used to collect the operation status data of power station equipment in real time and store the data in time series; A data preprocessing module, which is used to perform preprocessing operations of cleaning, denoising, and normalization on the collected data; An equipment status monitoring module, according to the operation status data of the equipment, respectively obtain the equipment predicted deterioration trend coefficient and the equipment environment coefficient, and calculate the equipment operation status change amount according to the changes of the equipment predicted deterioration trend coefficient and the equipment environment coefficient in the previous historical cycle; and compare the equipment operation status change amount with the preset equipment operation status warning value; If the equipment operation status change amount > the equipment operation status warning value, issue an equipment deterioration trend warning, otherwise judge that the equipment deterioration trend is normal; A health status evaluation module, which is used to mark the equipment that issues a deterioration trend warning, obtain various health indicators of the marked equipment, calculate the health status evaluation value of the marked equipment after synthesizing various health indicators, and perform a health assessment according to the health evaluation value of the marked equipment.

9. An electronic device, the electronic device includes a processor, a communication interface, a memory, and a communication bus, and the processor, the communication interface, and the memory complete mutual communication through the communication bus, and is characterized in that: A memory, the memory is used to store a computer program; A processor, which is used to execute a computer program stored in a memory to implement the steps of the method for evaluating the health state of power station equipment in a time series as described in any one of claims 1-6.

10. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores an executable program, which, when executed by a processor, implements the steps of the method for evaluating the health state of power station equipment in a time series as described in any one of claims 1-7.

Images