A method and system for monitoring operating parameters of generator sets based on information fusion

Abstract

The present invention discloses a method and system for monitoring the operating parameters of a generator set based on information fusion, including: collecting historical data of each operating parameter of the generator set and performing preprocessing to determine the characteristic parameters that affect the monitored target parameters; obtaining the operating data information of the target parameters and characteristic parameters within the sliding time series of the set sliding window, and substituting them into the regression formula of a linear function for regression calculation to obtain the corresponding regression coefficient; constructing the coefficient deviation monitoring index of the target parameter in the current sliding window according to the regression coefficient; based on the coefficient deviation monitoring index of the current sliding window, using the AR autoregression prediction method to calculate the threshold of the next sliding window; when the coefficient deviation monitoring index of the next sliding window is monitored to exceed the threshold, it is determined that the monitored target parameter is abnormal and an early warning signal is issued. The present invention can effectively improve the sensitivity and effectiveness of operating parameter monitoring and ensure the safety and reliability of unit operation.

Description

Technical Field

[0001] The present invention relates to the technical field of generator set operation monitoring, and in particular to a generator set operation parameter monitoring method and system based on information fusion. Background Art

[0002] Under the current "dual carbon" goal and power grid peak load situation, generator sets participate in deep peak load load, and the real-time status and energy efficiency of the unit operation have become the key factors determining the operation effect of the power plant. At present, the fault monitoring of generator sets is mainly carried out through the photon alarm screen, and the monitoring of the unit operating parameters is judged by fixed upper and lower limits. Due to the interference of the on-site measurement environment and other reasons, the monitoring of the generator set operating parameters is uncertain; the method of judging whether there is a fault in the generator set by fixed upper and lower limits has problems such as low sensitivity and low timeliness, which is not conducive to the safe operation of the unit. Summary of the invention

[0003] The purpose of the present invention is to overcome the deficiencies in the prior art and to provide a method and system for monitoring operating parameters of a generator set based on information fusion, so as to improve the sensitivity and effectiveness of monitoring.

[0004] To achieve the above object, the present invention is implemented by adopting the following technical solutions:

[0005] In a first aspect, the present invention provides a method for monitoring operating parameters of a generator set based on information fusion, the method comprising:

[0006] Collect historical data of various operating parameters of the generator set and pre-process them to determine the characteristic parameters that affect the monitored target parameters;

[0007] Obtaining the operating data information of the target parameter and the characteristic parameter within the sliding time series of the set sliding window, and substituting them into the regression formula of the linear function to perform regression calculation to obtain the corresponding regression coefficient;

[0008] Constructing a coefficient deviation monitoring index of the target parameter in the current sliding window according to the regression coefficient;

[0009] Based on the coefficient deviation monitoring index of the current sliding window, the threshold of the next sliding window is calculated using the AR autoregressive prediction method;

[0010] When it is monitored that the coefficient deviation monitoring index of the next sliding window exceeds the threshold, it is determined that the monitored target parameter is abnormal and an early warning signal is issued.

[0011] In combination with the first aspect, preferably, collecting historical data of various operating parameters of the generator set and preprocessing them to determine characteristic parameters that affect the monitored target parameters includes the following steps:

[0012] A set of historical operation data is collected within a variation range of 50% to 100% of the rated load of the unit, and another set of historical operation data is collected within a variation range of 50% to 100% of the rated value of the monitored target parameter, and the two sets of historical operation data are merged to obtain a historical data set;

[0013] Eliminate abnormal data of each operating parameter in the historical data set to obtain an initial data set;

[0014] Perform vector deduplication operation on the initial data set to obtain a new data set;

[0015] Based on the new data set, the correlation between each operating parameter and the monitored target parameter is analyzed using the PCA principal component analysis method, and the operating parameters with a correlation higher than a set threshold are determined as characteristic parameters that affect the monitored target parameter.

[0016] In combination with the first aspect, preferably, the step of performing a vector deduplication operation on the initial data set includes:

[0017] The average relative deviation between the corresponding elements in the two data vectors is calculated by formula (1):

[0018]

[0019] In the formula, abs represents the absolute value, Indicates the i-th operating parameter in the initial data set at t 1 The value of the moment, Indicates the i-th operating parameter in the initial data set at t 2 The value at the time, i = 1, 2, ... n, n represents the total number of operating parameters in the initial data set;

[0020] If the average relative deviation value of more than one-third of the elements in the two calculated data vectors is less than 2%, the two calculated data vectors are determined to be in the same state, and one of the two calculated data vectors is removed.

[0021] In combination with the first aspect, preferably, the regression formula of the linear function is:

[0022] y=a k x+b k (2)

[0023] Where y and x represent the operating data information of the target parameter and characteristic parameter of the kth sliding window respectively; k represents the number of the sliding window, k = 1, 2, ...; a k and b k They respectively represent the regression coefficient and constant term of the kth sliding window operation data information.

[0024] In combination with the first aspect, preferably, the step of constructing a coefficient deviation monitoring indicator of the target parameter in the current sliding window according to the regression coefficient includes:

[0025] The number of the current sliding window is set to r, and the operation data information of the target parameters and characteristic parameters of the first q sliding windows including the current sliding window r is intercepted, and regression calculations are performed respectively using formula (2) to obtain the regression coefficients of the first q sliding windows, that is, a r 、a r-1 、a r-2 …a r-q+2 、a r-q+1 ;

[0026] According to the regression coefficients of the first q sliding windows, the coefficient deviation monitoring index dis of the current sliding window r is calculated. r :

[0027]

[0028] In combination with the first aspect, preferably, the step of calculating the threshold of the next sliding window by using an AR autoregressive prediction method based on the coefficient deviation monitoring indicator of the current sliding window includes:

[0029] The target parameters and characteristic parameters of the first g sliding windows of the current sliding window r are intercepted, and the coefficient deviation monitoring index of the first g sliding windows is calculated by using the calculation method of formula (3), that is, dis r-g+1 , β 2 dis r-g+2 、…dis r-1 、dis r ;

[0030] According to the coefficient deviation monitoring index of the first g sliding windows, the deviation coefficient of the next sliding window is calculated using the AR autoregressive prediction method

[0031]

[0032] In the formula, β 1 , β 2 , …, β g-1 , β g Respectively represent the time series coefficients of the corresponding items, and satisfy

[0033] Combine the coefficient deviation monitoring index of the current sliding window and the difference coefficient of the next sliding window deviation to calculate the threshold of the next sliding window.

[0034]

[0035] Where α represents the scaling factor, and the value of α is determined by the speed at which the current operating conditions of the generator set change.

[0036] In combination with the first aspect, preferably, it is characterized in that when the monitored target parameter is the main steam pressure, the characteristic parameters affecting the monitored main steam pressure include unit load, feed water pressure, feed water flow, reheat steam pressure, main steam flow and extraction pressures of each stage.

[0037] In a second aspect, the present invention provides a generator set operating parameter monitoring system based on information fusion, the system comprising:

[0038] The data acquisition module is used to collect historical data of various operating parameters of the generator set and perform preprocessing to determine the characteristic parameters that affect the monitored target parameters;

[0039] A regression calculation module is used to obtain the operating data information of the target parameter and the characteristic parameter within the sliding time series of the set sliding window, and substitute it into the regression formula of the linear function to perform regression calculation to obtain the corresponding regression coefficient;

[0040] Constructing a coefficient deviation monitoring indicator module, used to construct a coefficient deviation monitoring indicator of the target parameter in the current sliding window according to the regression coefficient;

[0041] The threshold calculation module is used to calculate the threshold of the next sliding window based on the coefficient deviation monitoring index of the current sliding window using the AR autoregressive prediction method;

[0042] The abnormality monitoring module is used to determine that the monitored target parameter is abnormal and issue a warning signal when it is monitored that the coefficient deviation monitoring index of the next sliding window exceeds the threshold.

[0043] In a third aspect, the present invention provides a generator set operating parameter monitoring device based on information fusion, including a processor and a storage medium;

[0044] The storage medium is used to store instructions;

[0045] The processor is used to operate according to the instructions to execute the steps of the generator set operating parameter monitoring method based on information fusion as described in any one of the first aspects.

[0046] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the generator set operating parameter monitoring method based on information fusion as described in any one of the first aspects.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] The present invention obtains the operating data information of the target parameters and characteristic parameters within the sliding time series of the set sliding window for regression calculation, and constructs the coefficient deviation monitoring index as the monitoring data of the target parameters. At the same time, the threshold of the monitored data is dynamically calculated by using the AR autoregressive prediction method, so that the abnormal parameters can be accurately identified in the shortest time, so as to take countermeasures for different faults as soon as possible, thereby improving the safety and reliability of the unit operation.

[0049] In addition, when determining the characteristic parameters that affect the monitored target parameters, the present invention collects a large amount of historical operating data, and after eliminating abnormal data and performing vector deduplication operations, uses the PCA principal component analysis method to determine the operating parameters with a correlation degree higher than a set threshold as the characteristic parameters that affect the monitored target parameters, so that the constructed coefficient deviation monitoring indicator can more accurately reflect the data status of the target parameter, further improving the monitoring sensitivity. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is a flow chart of a method for monitoring operating parameters of a generator set based on information fusion provided by an embodiment of the present invention;

[0051] Figure 2 It is a monitoring process diagram of the coefficient deviation index of the main steam pressure by the method provided in the embodiment of the present invention;

[0052] Figure 3 The present invention provides a block diagram of the structure of a generator set operating parameter monitoring system based on information fusion. DETAILED DESCRIPTION

[0053] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations on the technical solution of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0054] The term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0055] Embodiment 1:

[0056] like Figure 1 As shown, this embodiment introduces a method for monitoring operating parameters of a generator set based on information fusion, which specifically includes the following steps:

[0057] Step S1: Collect historical data of each operating parameter of the generator set and perform preprocessing to determine characteristic parameters that affect the monitored target parameter;

[0058] Step S2: Obtain the operating data information of the target parameter and characteristic parameters within the sliding time series of the set sliding window, and substitute them into the regression formula of a linear function for regression calculation to obtain corresponding regression coefficients;

[0059] Step S3: Construct a coefficient deviation monitoring index of the target parameter for the current sliding window according to the regression coefficients;

[0060] Step S4: Based on the coefficient deviation monitoring index of the current sliding window, use the AR autoregressive prediction method to calculate the threshold of the next sliding window;

[0061] Step S5: When it is monitored that the coefficient deviation monitoring index of the next sliding window exceeds the threshold, it is determined that the monitored target parameter is abnormal and a warning signal is issued.

[0062] As an embodiment of the present invention, in step S1, it specifically includes the following processes:

[0063] Step S1.1: Collect a set of historical operating data within the range of 50% - 100% of the rated load of the unit, and collect another set of historical operating data within the range of 50% - 100% of the rated value of the monitored target parameter, and merge the two sets of historical operating data to obtain a historical data set;

[0064] Step S1.2: Eliminate abnormal data of each operating parameter in the historical data set to obtain an initial data set;

[0065] Specifically, in step S1.2, conventional threshold judgment and change rate are used to eliminate outliers in the historical data set, and the data that meets the outlier judgment conditions is eliminated; the conditions for threshold judgment are x t > h1 or x t < h2, where h1 and h2 are the upper and lower limit values of the corresponding parameter in the normal operating range respectively. The formula used for change rate judgment is abs(x t - x t-1 ) < s, x t is the measured value of the parameter at time t, x t-1 is the measured value of the parameter at time t - 1, abs represents the absolute value, and s is the upper limit value of the normal fluctuation of the change rate of this parameter during the normal operation of the unit.

[0066] Step S1.3: Perform a vector deduplication operation on the initial data set to obtain a new data set;

[0067] Step S1.3 provided in the embodiment of the present invention specifically includes: calculating the average relative deviation between corresponding elements in two data vectors by formula (1):

[0068]

[0069] In the formula, abs represents the absolute value, Indicates the i-th operating parameter in the initial data set at t 1 The value of the moment, Indicates the i-th operating parameter in the initial data set at t 2 The value at the time, i = 1, 2, ... n, n represents the total number of operating parameters in the initial data set;

[0070] If the average relative deviation value of more than one-third of the elements in the two calculated data vectors is less than 2%, the two calculated data vectors are determined to be in the same state, and one of the two calculated data vectors is removed.

[0071] Step S1.4: Based on the new data set, the correlation between each operating parameter and the monitored target parameter is analyzed using the PCA principal component analysis method, and the operating parameters with a correlation higher than a set threshold are determined as characteristic parameters that affect the monitored target parameter.

[0072] As an embodiment of the present invention, the regression formula of the linear function in step S2 is:

[0073] y=a k x+b k (2)

[0074] Where y and x represent the operating data information of the target parameter and characteristic parameter of the kth sliding window respectively; k represents the number of the sliding window, k = 1, 2, ...; a k and b k They respectively represent the regression coefficient and constant term of the kth sliding window operation data information.

[0075] As an embodiment of the present invention, in step S3, the step of constructing a coefficient deviation monitoring index of the target parameter in the current sliding window according to the regression coefficient includes:

[0076] The number of the current sliding window is set to r, and the operation data information of the target parameters and characteristic parameters of the first q sliding windows including the current sliding window r is intercepted, and regression calculations are performed respectively using formula (2) to obtain the regression coefficients of the first q sliding windows, that is, a r 、a r-1 、a r-2 …a r-q+2 、a r-q+1 ;

[0077] According to the regression coefficients of the first q sliding windows, the coefficient deviation monitoring index dis of the current sliding window r is calculated. r :

[0078]

[0079] Step S4 provided in the embodiment of the present invention specifically includes the following process:

[0080] The target parameters and characteristic parameters of the first g sliding windows of the current sliding window r are intercepted, and the coefficient deviation monitoring index of the first g sliding windows is calculated by using the calculation method of formula (3), that is, dis r-g+1 , β 2 dis r-g+2 、…dis r-1 、dis r ;

[0081] According to the coefficient deviation monitoring index of the first g sliding windows, the deviation coefficient of the next sliding window is calculated using the AR autoregressive prediction method

[0082]

[0083] In the formula, β 1 , β 2 , …, β g-1 , β g Respectively represent the time series coefficients of the corresponding items, and satisfy

[0084] Combine the coefficient deviation monitoring index of the current sliding window and the difference coefficient of the next sliding window deviation to calculate the threshold of the next sliding window.

[0085]

[0086] Where α represents the scaling factor;

[0087] It should be noted that the value of α is determined by the speed of change of the current operating condition of the generator set, and its size is automatically adjusted according to the actual situation. The adjustment rules are: if it is a period of rapid change of the unit's operating condition, take 0.3-0.5; if it is a period of slow change of the unit's operating condition, take 0.5-0.6; if it is in a period of relatively stable operating condition, take 0.6-0.8; wherein, the judgment rule of the unit load change is set: the two parameters of unit load and main feed water flow are selected for comprehensive judgment. If the load change rate exceeds 2%*rated load / min, and the main feed water flow rate exceeds 5% of the rated evaporation, it is considered to be in a period of rapid change of operating condition; if one of the two parameters has a change rate exceeding the limit and the other has not exceeded the limit, it is considered to be in a period of slow change of operating condition; if the change rates of both parameters are within the limit, it is considered to be in a relatively stable period of operating condition. It can be seen that the coefficient deviation monitoring index and threshold value of the target parameter detection of the present invention are dynamically adjusted according to the real-time operation data of the generator set, so that the monitored results are more timely and accurate.

[0088] The embodiment of the present invention uses the monitored target parameter as the main steam pressure to conduct a simulation test, and determines through the method provided by the present invention that the characteristic parameters affecting the monitored main steam pressure are unit load, feed water pressure, feed water flow, reheat steam pressure, main steam flow and extraction pressures at all levels; Figure 2 This is the monitoring process for abnormal changes in the main steam pressure caused by leakage of the four pipes of the unit. The coefficient deviation monitoring index of the main steam pressure is monitored. Figure 2 The trend curve in the figure is the calculated value of the coefficient deviation monitoring indicator, the rectangle represents the sliding window, and the dotted line is the threshold limit. Figure 2 It can be seen that the method of the present invention detects the abnormal main steam pressure and issues a fault abnormality signal warning from 1100s. It can be seen that the coefficient deviation index calculated before 1100s is stable at about 0.45. When the leakage occurs, the calculated index shows an abnormal upward trend and exceeds the limit in time, while the main steam pressure alarm of the DCS system exceeds the limit after 1200s, which verifies that the method of the present invention has high sensitivity and more accurate monitoring results of operating parameters.

[0089] Embodiment 2:

[0090] like Figure 2 As shown, the embodiment of the present invention provides a generator set operating parameter monitoring system based on information fusion, which can be used to implement the method described in the first embodiment, specifically including:

[0091] The data acquisition module is used to collect historical data of various operating parameters of the generator set and perform preprocessing to determine the characteristic parameters that affect the monitored target parameters;

[0092] A regression calculation module is used to obtain the operating data information of the target parameter and the characteristic parameter within the sliding time series of the set sliding window, and substitute it into the regression formula of the linear function to perform regression calculation to obtain the corresponding regression coefficient;

[0093] Constructing a coefficient deviation monitoring indicator module, used to construct a coefficient deviation monitoring indicator of the target parameter in the current sliding window according to the regression coefficient;

[0094] The threshold calculation module is used to calculate the threshold of the next sliding window based on the coefficient deviation monitoring index of the current sliding window using the AR autoregressive prediction method;

[0095] The abnormality monitoring module is used to determine that the monitored target parameter is abnormal and issue a warning signal when the coefficient deviation monitoring index of the next sliding window exceeds the threshold.

[0096] The generator set operating parameter monitoring system based on information fusion provided in the embodiment of the present invention and the generator set operating parameter monitoring method based on information fusion provided in Example 1 are based on the same technical concept, and can produce the beneficial effects as described in Example 1. For the contents not described in detail in this embodiment, please refer to Example 1.

[0097] Embodiment three:

[0098] An embodiment of the present invention provides a generator set operating parameter monitoring device based on information fusion, including a processor and a storage medium;

[0099] The storage medium is used to store instructions;

[0100] The processor is used to operate according to the instructions to execute the steps of any method in the first embodiment.

[0101] Embodiment 4:

[0102] An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any method in the first embodiment are implemented.

[0103] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0104] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0105] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0106] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0107] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for monitoring operating parameters of a generator set based on information fusion, characterized in that: The method comprises: Collect historical data of various operating parameters of the generator set and pre-process them to determine the characteristic parameters that affect the monitored target parameters; Obtaining the operating data information of the target parameter and the characteristic parameter within the sliding time series of the set sliding window, and substituting them into the regression formula of the linear function to perform regression calculation to obtain the corresponding regression coefficient; Constructing a coefficient deviation monitoring index of the target parameter in the current sliding window according to the regression coefficient; Based on the coefficient deviation monitoring index of the current sliding window, the threshold of the next sliding window is calculated using the AR autoregressive prediction method; When the coefficient deviation monitoring index of the next sliding window is monitored to exceed the threshold, it is determined that the monitored target parameter is abnormal and an early warning signal is issued; Among them, the regression formula of the linear function is: ； （2） In the formula, They represent the operating data information of the target parameter and characteristic parameter of the kth sliding window respectively; k represents the number of the sliding window, k= and They represent the regression coefficient and constant term of the k-th sliding window operation data information respectively; The step of constructing a coefficient deviation monitoring index of the target parameter in the current sliding window according to the regression coefficient includes: The number of the current sliding window is set to r, and the operating data information of the target parameters and characteristic parameters of the first q sliding windows including the current sliding window r is intercepted, and regression calculations are performed respectively using formula (2) to obtain the regression coefficients of the first q sliding windows, that is, , ; According to the regression coefficients of the first q sliding windows, the coefficient deviation monitoring index of the current sliding window r is calculated : ；（3） The step of calculating the threshold of the next sliding window by using the AR autoregressive prediction method based on the coefficient deviation monitoring index of the current sliding window includes: Intercept the front of the current sliding window r The target parameters and characteristic parameters of the sliding window are used to calculate the operation data information of the previous The coefficient deviation monitoring index of a sliding window is ; According to the previous The coefficient deviation monitoring indicator of the sliding window is used to calculate the deviation coefficient of the next sliding window using the AR autoregression prediction method. : ； （4） In the formula, , , …, , Respectively represent the time series coefficients of the corresponding items, and satisfy , j = ; Combine the coefficient deviation monitoring index of the current sliding window and the deviation coefficient of the next sliding window to calculate the threshold of the next sliding window : ； In the formula, represents the scaling factor, The value of is determined by the speed at which the current operating conditions of the generator set change.

2. The method for monitoring operating parameters of a generator set based on information fusion according to claim 1, characterized in that: The method of collecting historical data of various operating parameters of the generator set and preprocessing them to determine characteristic parameters that affect the monitored target parameters includes the following steps: A set of historical operation data is collected within the range of 50% to 100% of the rated load of the unit, and another set of historical operation data is collected within the range of 50% to 100% of the rated value of the monitored target parameter, and the two sets of historical operation data are merged to obtain a historical data set; Eliminate abnormal data of each operating parameter in the historical data set to obtain an initial data set; Perform vector deduplication operation on the initial data set to obtain a new data set; Based on the new data set, the correlation between each operating parameter and the monitored target parameter is analyzed using the PCA principal component analysis method, and the operating parameters with a correlation higher than a set threshold are determined as characteristic parameters that affect the monitored target parameter.

3. The method for monitoring operating parameters of a generator set based on information fusion according to claim 2 is characterized in that: The step of performing vector deduplication operation on the initial data set includes: The average relative deviation between the corresponding elements in the two data vectors is calculated by formula (1): ； （1） In the formula, represents the absolute value, Indicates that the i-th operating parameter in the initial data set is The value of the moment, Indicates that the i-th operating parameter in the initial data set is The value of the moment, , n represents the total number of operating parameters in the initial data set; If the average relative deviation value of more than one-third of the elements in the two calculated data vectors is less than 2%, the two calculated data vectors are determined to be in the same state, and one of the two calculated data vectors is removed.

4. The method for monitoring operating parameters of a generator set based on information fusion according to any one of claims 1 to 3, characterized in that: When the monitored target parameter is the main steam pressure, the characteristic parameters affecting the monitored main steam pressure include unit load, feed water pressure, feed water flow, reheat steam pressure, main steam flow and extraction pressures of each stage.

5. A generator set operating parameter monitoring system based on information fusion, characterized in that: The system comprises: The data acquisition module is used to collect historical data of various operating parameters of the generator set and perform preprocessing to determine the characteristic parameters that affect the monitored target parameters; A regression calculation module is used to obtain the operating data information of the target parameter and the characteristic parameter within the sliding time series of the set sliding window, and substitute it into the regression formula of the linear function to perform regression calculation to obtain the corresponding regression coefficient; Constructing a coefficient deviation monitoring indicator module, used to construct a coefficient deviation monitoring indicator of the target parameter in the current sliding window according to the regression coefficient; The threshold calculation module is used to calculate the threshold of the next sliding window based on the coefficient deviation monitoring index of the current sliding window using the AR autoregressive prediction method; The abnormality monitoring module is used to determine that the monitored target parameter is abnormal and issue a warning signal when it is detected that the coefficient deviation monitoring index of the next sliding window exceeds the threshold value; Among them, the regression formula of the linear function is: ； （2） In the formula, They represent the operating data information of the target parameter and characteristic parameter of the kth sliding window respectively; k represents the number of the sliding window, k= and They represent the regression coefficient and constant term of the k-th sliding window operation data information respectively; The step of constructing a coefficient deviation monitoring index of the target parameter in the current sliding window according to the regression coefficient includes: The number of the current sliding window is set to r, and the operating data information of the target parameters and characteristic parameters of the first q sliding windows including the current sliding window r is intercepted, and regression calculations are performed respectively using formula (2) to obtain the regression coefficients of the first q sliding windows, that is, , ; According to the regression coefficients of the first q sliding windows, the coefficient deviation monitoring index of the current sliding window r is calculated : ；（3） The step of calculating the threshold of the next sliding window by using the AR autoregressive prediction method based on the coefficient deviation monitoring index of the current sliding window includes: Intercept the front of the current sliding window r The target parameters and characteristic parameters of the sliding window are used to calculate the operation data information of the previous The coefficient deviation monitoring index of a sliding window is ; According to the previous The coefficient deviation monitoring indicator of the sliding window is used to calculate the deviation coefficient of the next sliding window using the AR autoregression prediction method. : ； （4） In the formula, , , …, , Respectively represent the time series coefficients of the corresponding items, and satisfy , j = ; Combine the coefficient deviation monitoring index of the current sliding window and the deviation coefficient of the next sliding window to calculate the threshold of the next sliding window : ； In the formula, represents the scaling factor, The value of is determined by the speed at which the current operating conditions of the generator set change.

6. A generator set operating parameter monitoring device based on information fusion, characterized in that: including processor and storage medium; The storage medium is used to store instructions; The processor is used to operate according to the instructions to execute the steps of the generator set operating parameter monitoring method based on information fusion according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the generator set operating parameter monitoring method based on information fusion as described in any one of claims 1 to 4 are implemented.

Images