Equipment maintenance method and system for smart power plant

Abstract

The invention relates to the technical field of smart power plants, in particular to an equipment maintenance method and system for a smart power plant, and the method comprises the following steps: obtaining the abnormality occurrence time of the operation parameters of smart power plant equipment; analyzing the abnormal data of the intelligent power plant equipment operation parameters, and outputting to obtain an intelligent power plant equipment operation abnormal total value; judging the total abnormal operation value of the intelligent power plant equipment and a corresponding threshold value, and evaluating the operation risk degree of the intelligent power plant equipment; starting abnormal parameter characteristics are determined, and a monitoring frequency adjustment coefficient is obtained through analysis; according to the invention, by determining the starting abnormal parameter characteristics, early warning can be carried out when the same starting abnormal parameter characteristics appear in the subsequent operation process of the intelligent power plant equipment; moreover, the abnormal condition of the intelligent power plant equipment is analyzed to obtain a monitoring frequency adjustment coefficient, the monitoring frequency of the starting abnormal parameter is adaptively regulated and controlled, and the key monitoring of the starting abnormal parameter is also improved.

Description

Technical Field

[0001] The present invention relates to the technical field of smart power plants, and in particular to an equipment maintenance method and system for smart power plants. Background Art

[0002] Chinese patent CN117217630A discloses a method for equipment reliability maintenance for smart power plants, which involves the technical field of equipment fault prediction and diagnosis, including: obtaining real-time equipment operation data, performing data quality analysis after cleaning the data; combining the cleaned data with equipment information to perform equipment digital modeling; the fault warning and diagnosis model determines and warns based on the equipment digital model and historical fault data;

[0003] In the prior art, the equipment reliability maintenance method provided for smart power plants monitors and warns the equipment, provides a scientific decision-making basis for the maintenance of key equipment, changes passive maintenance to predictive maintenance, and reduces the probability of human error; currently, it rarely monitors smart power plant equipment in abnormal and alarm states, analyzes the risk level of smart power plant equipment operation; and cannot perform feature analysis on operating abnormalities, resulting in subsequent smart power plant equipment encountering the same abnormal situation and being unable to perform maintenance in a timely manner. Summary of the invention

[0004] The purpose of the present invention is to provide an equipment maintenance method and system for a smart power plant. The technical problem solved by the present invention is: currently, smart power plant equipment is rarely monitored in abnormal and alarm states, and the risk level of the operation of smart power plant equipment is rarely analyzed; it is even more impossible to perform feature analysis on operating abnormalities, resulting in subsequent smart power plant equipment encountering the same abnormal situation and being unable to perform maintenance in a timely manner.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A method for equipment maintenance of a smart power plant, comprising the following steps:

[0007] Step 1: Obtain the abnormal occurrence time of the operating parameters of the smart power plant equipment;

[0008] Step 2: Analyze the abnormal occurrence time of the operating parameters of the smart power plant equipment, and output the total value of the abnormal operation of the smart power plant equipment;

[0009] Among them, the output process of the total abnormal value ZYZ of the smart power plant equipment operation is:

[0010] The total value of abnormal operation of smart power plant equipment ZYZ is calculated by the formula ZYZ=a1*ZBq+a2*ZBh, where a1 and a2 are weight ratio coefficients; ZBq is the triggering value of the front stage of the alarm and ZBh is the impact value of the back stage of the alarm;

[0011] Step 3: Determine the total value of the abnormal operation of the smart power plant equipment and the total threshold of the abnormal operation of the smart power plant equipment to assess the risk level of the operation of the smart power plant equipment;

[0012] Step 4: Based on the operational risk level of the smart power plant equipment, determine the originating abnormal parameter characteristics of the smart power plant equipment, and then analyze the monitoring frequency adjustment coefficient of the smart power plant equipment.

[0013] As a further solution of the present invention: in step 1, the process of obtaining the abnormal occurrence time of the operating parameter is:

[0014] The alarm signal generation time of the smart power plant equipment is taken as the midpoint of the abnormal information collection cycle, and the generation time of all abnormal operating parameters within the abnormal information collection cycle is obtained;

[0015] If the operating parameters do not meet the standard operating parameters, the operating parameters are marked as abnormal operating parameters.

[0016] As a further solution of the present invention: in step 2, the process of obtaining the alarm front-stage triggering value ZBq is:

[0017] Mark the interval from the start time of the abnormal information collection cycle to the time when the alarm signal is generated as the first analysis period;

[0018] Acquire all abnormal operating parameters in the first analysis period, calculate the difference between each abnormal operating parameter and the standard operating parameter, and obtain the abnormal operating parameter difference;

[0019] Calculate the ratio of the abnormal operation parameter difference to the standard operation parameter to obtain each abnormal operation parameter deviation value ZPo i in the first analysis period;

[0020] Then, the time when all abnormal operating parameters are generated in the first analysis period is obtained, marked as the abnormal parameter generation time of the first analysis period, and the interval between the abnormal parameter generation time of the first analysis period and the alarm signal generation time is calculated, marked as the abnormal operating parameter triggering period;

[0021] Calculate the ratio of the abnormal operation parameter triggering period to the first analysis period to obtain the abnormal operation parameter triggering factor YFo i;

[0022] By formula The alarm front-end triggering value ZBq is calculated, where i represents the number of abnormal operating parameters in the first analysis period.

[0023] As a further solution of the present invention: in step 2, the process of obtaining the alarm post-stage impact value ZBh is:

[0024] Marking the interval from the time when the alarm signal is generated to the end time of the abnormal information collection cycle as the second analysis period;

[0025] Acquire all abnormal operating parameters in the second analysis period, calculate the difference between each abnormal operating parameter and the standard operating parameter, and obtain the abnormal operating parameter difference;

[0026] Calculate the ratio of the abnormal operating parameter difference to the standard operating parameter to obtain the deviation value ZPtj of each abnormal operating parameter in the second analysis period;

[0027] Then, the time when all abnormal operating parameters are generated in the second analysis period is obtained, marked as the abnormal parameter generation time of the second analysis period, and the interval between the abnormal parameter generation time of the second analysis period and the alarm signal generation time is calculated, marked as the abnormal operating parameter triggering period;

[0028] Calculate the ratio of the abnormal operation parameter triggering period to the second analysis period to obtain the abnormal operation parameter influencing factor YYtj;

[0029] The alarm post-stage impact value ZBh is calculated by the formula ZBh=ZPt1*YYt1+ZPt2*YYt2+...+ZPtj*YYtj, where j represents the number of abnormal operating parameters in the second analysis period.

[0030] As a further solution of the present invention: in step 3, if the total value of the abnormal operation of the smart power plant equipment is greater than or equal to the total threshold value of the abnormal operation of the smart power plant equipment, a high risk signal of the operation of the smart power plant equipment is generated.

[0031] As a further solution of the present invention: in step 3, if the total value of the abnormal operation of the smart power plant equipment is less than the total threshold value of the abnormal operation of the smart power plant equipment, a low risk signal of the operation of the smart power plant equipment is generated.

[0032] As a further solution of the present invention: in step 4, the process of determining the characteristics of the initial abnormal parameters is:

[0033] Sort all abnormal operation parameters from front to back according to time, obtain the abnormal operation parameter at the first position in the sorting, and mark it as the originating abnormal parameter;

[0034] The parameter name and parameter value of the originating abnormal parameter are extracted and marked as the originating abnormal parameter feature.

[0035] As a further solution of the present invention: in step 4, the analysis process of monitoring the frequency adjustment coefficient is:

[0036] On the premise of obtaining the characteristics of the initial abnormal parameters, the parameter abnormality range ratio BCf and the parameter abnormality degree ratio BCc are analyzed and obtained, and the parameter abnormality range ratio BCf and the parameter abnormality degree ratio BCc are summed and calculated to obtain the monitoring frequency adjustment coefficient.

[0037] As a further solution of the present invention: the analysis process of the parameter abnormal range ratio BCf is:

[0038] Obtain the number of all abnormal operating parameters within the abnormal information collection cycle, and the total number of operating parameters monitored by the smart power plant equipment controller, respectively marked as the number of abnormal operating parameters and the total number of monitored operating parameters, and calculate the ratio of the number of abnormal operating parameters to the total number of monitored operating parameters to obtain the parameter abnormal range ratio BCY;

[0039] The analysis process of parameter abnormality ratio BCc is as follows:

[0040] Obtain each abnormal operating parameter deviation value ZPo i in the first analysis period and each abnormal operating parameter deviation value ZPtj in the second analysis period, and use the formula The parameter abnormality degree ratio BCc was calculated.

[0041] An equipment maintenance system for a smart power plant, the system comprising:

[0042] Monitoring module: obtains the abnormal occurrence time of the operating parameters of the smart power plant equipment;

[0043] Analysis module: Analyzes the abnormal data of the operating parameters of the smart power plant equipment and outputs the total value of the abnormal operation of the smart power plant equipment;

[0044] Among them, the output process of the total abnormal value ZYZ of the smart power plant equipment operation is:

[0045] The total value of abnormal operation of smart power plant equipment ZYZ is calculated by the formula ZYZ=a1*ZBq+a2*ZBh, where a1 and a2 are weight ratio coefficients; ZBq is the triggering value of the front stage of the alarm and ZBh is the impact value of the back stage of the alarm;

[0046] Evaluation module: judge the total value of abnormal operation of smart power plant equipment against the corresponding threshold value to evaluate the risk level of smart power plant equipment operation;

[0047] Maintenance module: Based on the risk level of smart power plant equipment operation, determine the characteristics of the originating abnormal parameters, and then analyze to obtain the monitoring frequency adjustment coefficient.

[0048] Beneficial effects of the present invention:

[0049] (1) The present invention obtains abnormal data of operating parameters of smart power plant equipment; analyzes the abnormal data of operating parameters of smart power plant equipment, and outputs the total abnormal value of operating parameters of smart power plant equipment; judges the total abnormal value of operating parameters of smart power plant equipment with the corresponding threshold value, and evaluates the operating risk level of smart power plant equipment; The present invention monitors and analyzes the alarm time generated by smart power plant equipment during operation, and analyzes the abnormal time of abnormal operating parameters with reference to the alarm time, and analyzes the abnormal degree of abnormal operating parameters, and uses the time deviation degree from the alarm time and the numerical deviation degree of abnormal operating parameters to comprehensively monitor the risk level of smart power plant equipment at the time of alarm, which is not only convenient for analyzing the operating status of smart power plant equipment, but also convenient for more accurate early warning of the subsequent operation of smart power plant equipment;

[0050] (2) The present invention determines the characteristics of the initial abnormal parameters based on the abnormal information collection cycle, and then analyzes to obtain the monitoring frequency adjustment coefficient. By determining the characteristics of the initial abnormal parameters, the present invention can provide early warning when the same initial abnormal parameter characteristics appear during the subsequent operation of the smart power plant equipment; and by analyzing the abnormal conditions of the smart power plant equipment to obtain the monitoring frequency adjustment coefficient, the monitoring frequency of the initial abnormal parameters is adaptively adjusted, which will also improve the focus on monitoring the initial abnormal parameters, effectively perform timely fault handling during the operation of the smart power plant equipment, and provide maintenance timeliness. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The present invention will be further described below in conjunction with the accompanying drawings.

[0052] Figure 1 is a flowchart of Embodiment 1 of the present invention;

[0053] Figure 2 is a flowchart of Embodiment 2 of the present invention;

[0054] Figure 3 It is a system block diagram of embodiment 3 of the present invention. DETAILED DESCRIPTION

[0055] 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.

[0056] Example 1

[0057] See also Figure 1 As shown, the present invention is a method for equipment maintenance for a smart power plant, comprising the following steps:

[0058] Step 1: Obtain abnormal data of operating parameters of smart power plant equipment;

[0059] Among them, the abnormal data includes the time when the abnormality occurs;

[0060] In some embodiments, during the operation of the smart power plant equipment, when the smart power plant equipment generates an alarm signal, the generation time of the alarm signal is taken as the midpoint of the abnormal information collection cycle, and the generation time of all abnormal operation parameters within the abnormal information collection cycle is obtained; for example, the abnormal operation parameters include temperature, current, voltage, etc.;

[0061] The process of obtaining abnormal operation parameters is as follows:

[0062] Collect all the operating parameters of the smart power plant equipment and compare each operating parameter with the corresponding standard operating parameter;

[0063] If the operating parameters meet the standard operating parameters, the operating parameters are marked as normal operating parameters;

[0064] If the operating parameters do not meet the standard operating parameters, the operating parameters are marked as abnormal operating parameters;

[0065] It should be noted that: the selection of abnormal information collection cycle: the start time of the abnormal information collection cycle should be before the abnormal operation parameter mark, and the end time of the abnormal information collection cycle can be selected as the stop time of the smart power plant equipment;

[0066] Step 2: Analyze the abnormal data of the operating parameters of the smart power plant equipment, and output the total value of the abnormal operation of the smart power plant equipment;

[0067] In some embodiments, the interval from the start time of the abnormal information collection cycle to the time when the alarm signal is generated is marked as the first analysis period;

[0068] Marking the interval from the time when the alarm signal is generated to the end time of the abnormal information collection cycle as the second analysis period;

[0069] The first analysis period and the second analysis period are analyzed respectively to obtain the alarm pre-stage triggering value ZBq and the alarm post-stage impact value ZBh. The total value ZYZ of the abnormal operation of the smart power plant equipment is calculated by the formula ZYZ=a1*ZBq+a2*ZBh, where a1 and a2 are weight ratio coefficients, a1+a2=1, a1 is 0.52, and a2 is 0.48;

[0070] First, specifically, the analysis is conducted for the first analysis period:

[0071] Acquire all abnormal operating parameters in the first analysis period, calculate the difference between each abnormal operating parameter and the standard operating parameter, and obtain the abnormal operating parameter difference;

[0072] Calculate the ratio of the abnormal operating parameter difference to the standard operating parameter to obtain the deviation value of each abnormal operating parameter in the first analysis period;

[0073] Then, the time when all abnormal operating parameters are generated in the first analysis period is obtained, marked as the abnormal parameter generation time of the first analysis period, and the interval between the abnormal parameter generation time of the first analysis period and the alarm signal generation time is calculated, marked as the abnormal operating parameter triggering period;

[0074] Calculate the ratio of the abnormal operation parameter triggering period to the first analysis period to obtain the abnormal operation parameter triggering factor;

[0075] Each abnormal operating parameter deviation value and abnormal operating parameter triggering factor in the first analysis period are marked as ZPo i and YFo i, respectively; through the formula The alarm pre-stage triggering value ZBq is calculated, where i represents the number of abnormal operating parameters in the first analysis period;

[0076] The second specific analysis is conducted for the second analysis period:

[0077] Acquire all abnormal operating parameters in the second analysis period, calculate the difference between each abnormal operating parameter and the standard operating parameter, and obtain the abnormal operating parameter difference;

[0078] Calculate the ratio of the abnormal operating parameter difference to the standard operating parameter to obtain the deviation value of each abnormal operating parameter in the second analysis period;

[0079] Then, the time when all abnormal operating parameters are generated in the second analysis period is obtained, marked as the abnormal parameter generation time of the second analysis period, and the interval between the abnormal parameter generation time of the second analysis period and the alarm signal generation time is calculated, marked as the abnormal operating parameter triggering period;

[0080] Calculate the ratio of the abnormal operation parameter triggering period to the second analysis period to obtain the abnormal operation parameter impact factor;

[0081] Each abnormal operating parameter deviation value and abnormal operating parameter impact factor in the second analysis period are marked as ZPtj and YYtj respectively; the alarm post-segment impact value ZBh is calculated by the formula ZBh=ZPt1*YYt1+ZPt2*YYt2+...+ZPtj*YYtj, where j represents the number of abnormal operating parameters in the second analysis period;

[0082] It should be explained that: if the standard operating parameter is a specific parameter value, the difference between the abnormal operating parameter and the standard operating parameter is calculated to obtain the abnormal operating parameter difference;

[0083] Calculate the ratio of the abnormal operating parameter difference to the standard operating parameter to obtain the deviation value of each abnormal operating parameter;

[0084] If the standard operating parameter is within the parameter range, the difference between the abnormal operating parameter and the midpoint value of the parameter range is calculated to obtain the abnormal operating parameter difference;

[0085] Calculate the ratio of the abnormal operation parameter difference to the midpoint value of the parameter range to obtain the deviation value of each abnormal operation parameter;

[0086] Step 3: Compare the total value of the abnormal operation of the smart power plant equipment with the corresponding threshold value to assess the risk level of the operation of the smart power plant equipment;

[0087] Among them, the degree of risk of smart power plant equipment operation includes a high signal of smart power plant equipment operation risk or a low signal of smart power plant equipment operation risk;

[0088] In some embodiments, the total value of abnormal operation of the smart power plant equipment is obtained and compared with the total threshold value of abnormal operation of the smart power plant equipment;

[0089] If the total value of the abnormal operation of the smart power plant equipment is greater than or equal to the total threshold of the abnormal operation of the smart power plant equipment, a high risk signal of the operation of the smart power plant equipment is generated;

[0090] If the total value of the abnormal operation of the smart power plant equipment is less than the total threshold of the abnormal operation of the smart power plant equipment, a low risk signal of the operation of the smart power plant equipment is generated;

[0091] It should be noted that the high risk signal of the operation of the smart power plant equipment indicates that the operation risk of the smart power plant equipment is evaluated by the triggering value before the alarm and the impact value after the alarm before and after the alarm is generated.

[0092] The alarm pre-stage triggering value reflects: the abnormal degree of each abnormal operating parameter before the alarm and the time urgency between the abnormal operating parameter and the alarm. The larger the alarm pre-stage triggering value, the greater the abnormality and the more urgent the alarm.

[0093] The impact value of the post-alarm period reflects: the abnormal degree of each abnormal operating parameter after the alarm and the time influence degree between the abnormal operating parameter and the alarm. The larger the impact value of the post-alarm period, the greater and longer the impact of the smart power plant equipment after the alarm.

[0094] The technical solution of the embodiment of the present invention: obtaining abnormal data of operating parameters of smart power plant equipment; analyzing the abnormal data of operating parameters of smart power plant equipment, and outputting the total value of abnormal operation of smart power plant equipment; judging the total value of abnormal operation of smart power plant equipment with the corresponding threshold value, and evaluating the degree of risk of operation of smart power plant equipment; the present invention monitors and analyzes the alarm time generated by smart power plant equipment during operation, and analyzes the abnormal time of abnormal operating parameters with reference to the alarm time, and analyzes the abnormal degree of abnormal operating parameters, and uses the degree of time deviation from the alarm time and the degree of numerical deviation of abnormal operating parameters to comprehensively monitor the risk degree of smart power plant equipment at the time of alarm, which is not only convenient for analyzing the operation status of smart power plant equipment, but also convenient for more accurate early warning of the subsequent operation of smart power plant equipment.

[0095] Example 2

[0096] See also Figure 2 As shown, the present invention is a method for equipment maintenance for a smart power plant, further comprising the following steps:

[0097] Step 4: Based on the abnormal information collection cycle, determine the characteristics of the originating abnormal parameters, and then analyze to obtain the monitoring frequency adjustment coefficient;

[0098] In some embodiments, when a high risk signal of the operation of the smart power plant equipment or a low risk signal of the operation of the smart power plant equipment is received, all abnormal operation parameters are sorted from front to back according to time, and the abnormal operation parameter at the first position in the sorting is obtained and marked as the originating abnormal parameter;

[0099] Extract the parameter name and parameter value of the originating abnormal parameter and mark them as the originating abnormal parameter feature; for example, the parameter name of the originating abnormal parameter may be temperature, and the parameter value may be A;

[0100] On the premise of obtaining the characteristics of the initial abnormal parameters, the parameter abnormal range ratio BCf and the parameter abnormal degree ratio BCc are analyzed and obtained, and the parameter abnormal range ratio BCf and the parameter abnormal degree ratio BCc are summed and calculated to obtain the monitoring frequency adjustment coefficient KJ;

[0101] Obtain the monitoring frequency of the originating abnormal parameter in the current abnormal information collection cycle (i.e., the frequency at which the smart power plant equipment controller collects data on the originating abnormal parameter), perform a multiplication operation on the monitoring frequency of the originating abnormal parameter and the monitoring frequency adjustment coefficient, and obtain the upper adjustment value of the monitoring frequency of the originating abnormal parameter;

[0102] Among them, the analysis process of parameter abnormal range ratio BCf is:

[0103] Obtain the number of all abnormal operating parameters within the abnormal information collection cycle, and the total number of operating parameters monitored by the smart power plant equipment controller, respectively marked as the number of abnormal operating parameters and the total number of monitored operating parameters, and calculate the ratio of the number of abnormal operating parameters to the total number of monitored operating parameters to obtain the parameter abnormal range ratio BCY;

[0104] The analysis process of parameter abnormality ratio BCc is as follows:

[0105] Obtain the abnormal operation parameter deviation value (each abnormal operation parameter deviation value ZPo i in the first analysis period and each abnormal operation parameter deviation value ZPtj in the second analysis period) during the abnormal information collection period, and use the formula The parameter abnormality degree ratio BCc is calculated;

[0106] The technical solution of the embodiment of the present invention is as follows: based on the abnormal information collection cycle, the characteristics of the initial abnormal parameters are determined, and then the monitoring frequency adjustment coefficient is obtained by analysis. By determining the characteristics of the initial abnormal parameters, the present invention can provide early warning when the same initial abnormal parameter characteristics appear during the subsequent operation of smart power plant equipment; and by analyzing the abnormal conditions of the smart power plant equipment to obtain the monitoring frequency adjustment coefficient, the monitoring frequency of the initial abnormal parameters is adaptively adjusted, which will also improve the key monitoring of the initial abnormal parameters, effectively perform timely fault handling during the operation of the smart power plant equipment, and provide maintenance timeliness.

[0107] Example 3

[0108] See also Figure 3 As shown, the present invention is an equipment maintenance system for a smart power plant, the system comprising:

[0109] Monitoring module: obtains the abnormal occurrence time of the operating parameters of the smart power plant equipment;

[0110] Analysis module: Analyzes the abnormal data of the operating parameters of the smart power plant equipment and outputs the total value of the abnormal operation of the smart power plant equipment;

[0111] Among them, the output process of the total abnormal value ZYZ of the smart power plant equipment operation is:

[0112] The total value of abnormal operation of smart power plant equipment ZYZ is calculated by the formula ZYZ=a1*ZBq+a2*ZBh, where a1 and a2 are weight ratio coefficients; ZBq is the triggering value of the front stage of the alarm and ZBh is the impact value of the back stage of the alarm;

[0113] Evaluation module: judge the total value of abnormal operation of smart power plant equipment against the corresponding threshold value to evaluate the risk level of smart power plant equipment operation;

[0114] Maintenance module: Based on the abnormal information collection cycle, determine the characteristics of the originating abnormal parameters, and then analyze to obtain the monitoring frequency adjustment coefficient.

[0115] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0116] 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. A method for equipment maintenance in a smart power plant, characterized in that: The following steps are involved: Step 1: Obtain the abnormal occurrence time of the operating parameters of the smart power plant equipment; Step 2: Analyze the abnormal occurrence time of the operating parameters of the smart power plant equipment, and output the total value of the abnormal operation of the smart power plant equipment; Among them, the output process of the total abnormal value ZYZ of the smart power plant equipment operation is: The total value of abnormal operation of smart power plant equipment ZYZ is calculated by the formula ZYZ=a1*ZBq+a2*ZBh, where a1 and a2 are weight ratio coefficients; ZBq is the triggering value of the front stage of the alarm and ZBh is the impact value of the back stage of the alarm; Step 3: Determine the total value of the abnormal operation of the smart power plant equipment and the total threshold of the abnormal operation of the smart power plant equipment to assess the risk level of the operation of the smart power plant equipment; Step 4: Based on the operational risk level of the smart power plant equipment, determine the characteristics of the originating abnormal parameters of the smart power plant equipment, and then analyze the monitoring frequency adjustment coefficient of the smart power plant equipment.

2. The equipment maintenance method for a smart power plant according to claim 1 is characterized in that: In step 1, the process of obtaining the abnormal occurrence time of the operating parameters is as follows: The alarm signal generation time of the smart power plant equipment is taken as the midpoint of the abnormal information collection cycle, and the generation time of all abnormal operating parameters within the abnormal information collection cycle is obtained; If the operating parameters do not meet the standard operating parameters, the operating parameters are marked as abnormal operating parameters.

3. The equipment maintenance method for a smart power plant according to claim 1 is characterized in that: In step 2, the process of obtaining the alarm pre-stage triggering value ZBq is as follows: Mark the interval from the start time of the abnormal information collection cycle to the time when the alarm signal is generated as the first analysis period; Acquire all abnormal operating parameters in the first analysis period, calculate the difference between each abnormal operating parameter and the standard operating parameter, and obtain the abnormal operating parameter difference; Calculate the ratio of the abnormal operating parameter difference to the standard operating parameter to obtain each abnormal operating parameter deviation value ZPoi in the first analysis period; Then, the time when all abnormal operating parameters are generated in the first analysis period is obtained, marked as the abnormal parameter generation time of the first analysis period, and the interval between the abnormal parameter generation time of the first analysis period and the alarm signal generation time is calculated, marked as the abnormal operating parameter triggering period; Calculate the ratio of the abnormal operation parameter triggering period to the first analysis period to obtain the abnormal operation parameter triggering factor YFoi; By formula The alarm front-end triggering value ZBq is calculated, where i represents the number of abnormal operating parameters in the first analysis period.

4. The equipment maintenance method for a smart power plant according to claim 1 is characterized in that: In step 2, the process of obtaining the alarm post-stage impact value ZBh is as follows: Marking the interval from the time when the alarm signal is generated to the end time of the abnormal information collection cycle as the second analysis period; Acquire all abnormal operating parameters in the second analysis period, calculate the difference between each abnormal operating parameter and the standard operating parameter, and obtain the abnormal operating parameter difference; Calculate the ratio of the abnormal operating parameter difference to the standard operating parameter to obtain the deviation value ZPtj of each abnormal operating parameter in the second analysis period; Then, the time when all abnormal operating parameters are generated in the second analysis period is obtained, marked as the abnormal parameter generation time of the second analysis period, and the interval between the abnormal parameter generation time of the second analysis period and the alarm signal generation time is calculated, marked as the abnormal operating parameter triggering period; Calculate the ratio of the abnormal operation parameter triggering period to the second analysis period to obtain the abnormal operation parameter influencing factor YYtj; The alarm post-stage impact value ZBh is calculated by the formula ZBh=ZPt1*YYt1+ZPt2*YYt2+...+ZPtj*YYtj, where j represents the number of abnormal operating parameters in the second analysis period.

5. The equipment maintenance method for a smart power plant according to claim 1 is characterized in that: In step 3, if the total value of the abnormal operation of the smart power plant equipment is greater than or equal to the total threshold value of the abnormal operation of the smart power plant equipment, a high risk signal of the operation of the smart power plant equipment is generated.

6. The equipment maintenance method for a smart power plant according to claim 1 is characterized in that: In step 3, if the total value of the abnormal operation of the smart power plant equipment is less than the total threshold value of the abnormal operation of the smart power plant equipment, a low risk signal of the operation of the smart power plant equipment is generated.

7. The equipment maintenance method for a smart power plant according to claim 1 is characterized in that: In step 4, the process of determining the characteristics of the originating abnormal parameters is as follows: Sort all abnormal operation parameters from front to back according to time, obtain the abnormal operation parameter at the first position in the sorting, and mark it as the originating abnormal parameter; The parameter name and parameter value of the originating abnormal parameter are extracted and marked as the originating abnormal parameter feature.

8. The equipment maintenance method for a smart power plant according to claim 7 is characterized in that: In step 4, the analysis process of monitoring the frequency adjustment coefficient is: On the premise of obtaining the characteristics of the initial abnormal parameters, the parameter abnormality range ratio BCf and the parameter abnormality degree ratio BCc are analyzed and obtained, and the parameter abnormality range ratio BCf and the parameter abnormality degree ratio BCc are summed and calculated to obtain the monitoring frequency adjustment coefficient.

9. The equipment maintenance method for a smart power plant according to claim 8, characterized in that: The analysis process of parameter abnormal range ratio BCf is: Obtain the number of all abnormal operating parameters within the abnormal information collection cycle, and the total number of operating parameters monitored by the smart power plant equipment controller, respectively marked as the number of abnormal operating parameters and the total number of monitored operating parameters, and calculate the ratio of the number of abnormal operating parameters to the total number of monitored operating parameters to obtain the parameter abnormal range ratio BCY; The analysis process of parameter abnormality ratio BCc is as follows: Obtain each abnormal operating parameter deviation value ZPo i in the first analysis period and each abnormal operating parameter deviation value ZPtj in the second analysis period, and use the formula The parameter abnormality ratio BCc was calculated.

10. An equipment maintenance system for a smart power plant, characterized in that: The system is used to execute the method described in any one of claims 1 to 9, and the system comprises: Monitoring module: obtains the abnormal occurrence time of the operating parameters of smart power plant equipment; Analysis module: Analyzes the abnormal data of the operating parameters of the smart power plant equipment and outputs the total value of the abnormal operation of the smart power plant equipment; Among them, the output process of the total abnormal value ZYZ of the smart power plant equipment operation is: The total value of abnormal operation of smart power plant equipment ZYZ is calculated by the formula ZYZ=a1*ZBq+a2*ZBh, where a1 and a2 are weight ratio coefficients; ZBq is the triggering value of the front stage of the alarm and ZBh is the impact value of the back stage of the alarm; Evaluation module: judge the total value of abnormal operation of smart power plant equipment against the corresponding threshold value to evaluate the risk level of smart power plant equipment operation; Maintenance module: Based on the risk level of smart power plant equipment operation, determine the characteristics of the originating abnormal parameters, and then analyze to obtain the monitoring frequency adjustment coefficient.

Images