Power plant intelligent early warning method and system based on data fusion

Abstract

The invention provides a power plant intelligent early warning method based on data fusion. The power plant intelligent early warning method comprises the following steps: acquiring historical power generation amounts of a target power plant in a plurality of past fixed time periods; building a generating capacity model for the target power plant through the historical generating capacity, and extracting an overall factor about the generating capacity of the target power plant from the generating capacity model; acquiring a plurality of power generation units of the target power plant, wherein each power generation unit comprises power generation equipment and power generation energy; building a plurality of power generation sub-models according to the plurality of power generation units, and calculating a plurality of limiting factors corresponding to the plurality of power generation sub-models; calculating power generation factors of the plurality of power generation units according to the overall factor and the plurality of limiting factors; and inputting the plurality of power generation factors into a power generation amount model to estimate the current power generation amount of the target power plant so as to realize intelligent early warning of the target power plant. The accuracy of power plant safety early warning can be improved, the difficulty of power plant early warning is reduced, and therefore the power plant is safer in the power generation process.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent early warning of power plants, and in particular to an intelligent early warning method for power plants based on data fusion and an intelligent early warning system for power plants based on data fusion. Background Art

[0002] With the rapid development of digital operation in my country, smart power plants have gradually become a new goal of the power industry. As data fusion technology is fully integrated into all aspects of the power industry, there are more stringent requirements for the safety of power generation in power plants.

[0003] Aiming at the safe power generation and production construction of smart power plants, building a safe, intelligent and efficient smart power plant system and using data fusion technology to promote safe power generation in power plants have become new challenges for safe power generation in smart power plants at this stage. In existing technologies, the failure and aging of power generation equipment in power plants are usually the causes of power plant safety accidents. Secondly, there are also safety risks in the transportation and use of power generation fuel. Both of the above reasons will lead to high difficulty in early warning of power plants and low accuracy of early warning, which will cause safety hazards in the power plant during power generation. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a power plant intelligent early warning method and system based on data fusion, which can improve the accuracy of power plant safety early warning and reduce the difficulty of power plant early warning, thereby making the power plant safer during the power generation process.

[0005] The technical solution adopted by the present invention is as follows:

[0006] A method for intelligent early warning of power plants based on data fusion, comprising the following steps: obtaining historical power generation of a target power plant in multiple fixed time periods in the past, the target power plant comprising multiple power generation units, the power generation units comprising power generation equipment and power generation energy; building a power generation model for the target power plant through the historical power generation, and extracting an overall factor about the power generation of the target power plant from the power generation model; building multiple power generation sub-models based on multiple power generation units and calculating multiple limiting factors corresponding to the multiple power generation sub-models; calculating power generation factors of multiple power generation units based on the overall factor and multiple limiting factors; inputting the multiple power generation factors into the power generation model to estimate the current power generation of the target power plant and realize intelligent early warning of the target power plant.

[0007] A power plant intelligent early warning method based on data fusion also includes: if the difference between the estimated current power generation of the target power plant and the actual power generation of the target power plant is greater than 10% of the actual power generation of the target power plant, the target power plant sends a warning signal.

[0008] In one embodiment of the present invention, the extracting of the overall factor of the power generation of the target power plant from the power generation model specifically includes: creating multiple power generation sequences based on multiple power generation units, the power generation sequence including a power generation equipment sequence and a power generation energy sequence; summarizing the processed values ​​of the power generation sequence into a specific range by means of data preprocessing; estimating the power generation of a single power generation unit through the power generation model; training the power generation model based on the historical power generation to obtain an optimal power generation model; extracting the overall factor of the power generation of the target power plant based on the optimal power generation model.

[0009] In one embodiment of the present invention, the construction of multiple power generation sub-models based on the multiple power generation units and the calculation of multiple limiting factors corresponding to the multiple power generation sub-models specifically include: obtaining the power generation of a single power generation unit, and organizing the power generation of a single power generation unit into a data sequence with a depth of x according to a time series algorithm, and the collection gap of the data sequence is y; calculating the depth x of the data sequence and the collection gap y to build a high-dimensional multivariate regression model; and calculating the limiting factors according to the multivariate regression model.

[0010] In one embodiment of the present invention, the method of building multiple power generation sub-models based on the multiple power generation units to calculate the power generation factors of the multiple power generation units specifically includes: establishing a factor group corresponding to each power generation unit, the factor group including an overall factor group and a restriction factor group; combining the overall factor group and the restriction factor group; and calculating the power generation factors of the multiple power generation units based on the combined factor group.

[0011] A power plant intelligent early warning system based on data fusion, comprising: an acquisition module, the acquisition module is used to obtain the historical power generation of a target power plant in multiple fixed time periods in the past, the target power plant includes multiple power generation units, and the power generation units include power generation equipment and power generation energy; a model building module, the model building module is used to build a power generation model for the target power plant through the historical power generation, and extract the overall factor about the power generation of the target power plant from the power generation model; a first calculation module, the first calculation module is used to build multiple power generation sub-models according to multiple power generation units and calculate multiple limiting factors corresponding to the multiple power generation sub-models; a second calculation module, the second calculation module is used to calculate the power generation factors of multiple power generation units according to the overall factor and multiple limiting factors; an intelligent early warning module, the intelligent early warning module is used to input the multiple power generation factors into the power generation model to estimate the current power generation of the target power plant and realize the intelligent early warning of the target power plant.

[0012] An intelligent early warning system for power plants based on data fusion also includes: a judgment module, which is used to judge the size of the estimated current power generation of the target power plant and the actual power generation of the target power plant. If the difference between the estimated current power generation of the target power plant and the actual power generation of the target power plant is greater than 10% of the actual power generation of the target power plant, the target power plant will issue a warning signal.

[0013] In one embodiment of the present invention, the model building module is also used to: create multiple power generation sequences based on multiple power generation units, the power generation sequence includes a power generation equipment sequence and a power generation energy sequence; summarize the power generation sequence into a specific range through data preprocessing; estimate the power generation of a single power generation unit through the power generation model; train the power generation model according to the historical power generation to obtain the optimal power generation model; extract the overall factor of the power generation of the target power plant according to the optimal power generation model.

[0014] In one embodiment of the present invention, the first calculation module is also used to: obtain the power generation of a single power generation unit, and organize the power generation of a single power generation unit into a data sequence with a depth of x according to a time series algorithm, and the collection gap of the data sequence is y; calculate the depth x of the data sequence and the collection gap y to build a high-dimensional multivariate regression model; calculate the limiting factor according to the multivariate regression model.

[0015] In one embodiment of the present invention, the second calculation module is also used to: establish a corresponding factor group for each power generation unit, the factor group including an overall factor group and a restriction factor group; combine the overall factor group and the restriction factor group; and calculate the power generation factors of multiple power generation units based on the combined factor group.

[0016] Beneficial effects of the present invention:

[0017] The present invention obtains the historical power generation of the power plant, builds a power generation model based on the historical power generation, extracts the overall factor from the power generation model, then builds multiple power generation sub-models according to the multiple power generation units and calculates multiple limiting factors corresponding to the multiple power generation sub-models, finally calculates the power generation factor of the power unit according to the overall factor and the limiting factor, and inputs the power generation factor into the power generation model to estimate the power generation, thereby realizing intelligent early warning of the target power plant, thereby improving the accuracy of the power plant's safety early warning, reducing the difficulty of the power plant's early warning, and making the power plant safer during the power generation process. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1It is a flow chart of a power plant intelligent early warning method based on data fusion according to an embodiment of the present invention;

[0019] Figure 2 It is a block diagram of a power plant intelligent early warning system based on data fusion according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] 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.

[0021] Figure 1 The present invention is a flowchart of a power plant intelligent early warning method based on data fusion according to an embodiment of the present invention.

[0022] like Figure 1 As shown, the power plant intelligent early warning method based on data fusion according to an embodiment of the present invention comprises the following steps:

[0023] S1, obtaining the historical power generation of a target power plant in multiple fixed time periods in the past, where the target power plant includes multiple power generation units, each of which includes power generation equipment and power generation energy.

[0024] In one embodiment of the present invention, the historical power generation of the selected target power plant in the past period of time can be obtained through the networked power system, and the power generation of the target power plant can be obtained multiple times through multiple fixed time nodes. For example, when the frequency of obtaining the historical power generation of the target power plant is once a day, if the power generation X of the target power plant in the past 3 days in a certain period of time is to be obtained, the power generation X of the target power plant can be expressed as:

[0025]

[0026] Among them, p is the power generation of the target power plant in one day, i is the number of days, and n is an integer.

[0027] S2, building a power generation model for the target power plant through historical power generation, and extracting the overall factor of the power generation of the target power plant from the power generation model.

[0028] Specifically, first, multiple power generation sequences can be created based on multiple power generation units, and this sequence can include a power generation equipment sequence and a power generation energy sequence. It can be understood that since power generation equipment is large-scale equipment with many spare parts, different spare parts can be sequenced to form a power generation equipment sequence. Similarly, power generation energy can also be composed of multiple fuels and chemicals, which can also be sequenced to form a power generation energy sequence.

[0029] Secondly, the power generation sequence can be processed by data preprocessing so that the processed values ​​are summarized in a specific range. For example, the Z-score algorithm in the data preprocessing method can be used to summarize the values ​​in a specific range, that is, the power generation X of the target power plant minus the mean of the power generation of the target power plant every day is divided by the standard deviation of the power generation sequence, so that the processed value is summarized in a specific range, where the calculation formula of the processed value can be expressed as:

[0030]

[0031] Among them, X q is the processing value, q is the time interval for obtaining power generation, is the mean value of the power generation series, and std(X) is the standard deviation of the power generation series.

[0032] Furthermore, the power generation model can be used to estimate the power generation of a single power generation unit. Specifically, the time recurrent neural network algorithm can be used to estimate the power generation of a single power generation unit in a single day, that is, two filters are added to the time recurrent neural network algorithm, and the two filters are set in parallel, and the two filters can be the power generation estimation of a power generation unit and the power generation estimation of the power generation unit in a fixed time period.

[0033] Furthermore, the power generation sequence after data preprocessing can be used as a training set, and the power generation in different time periods can be classified as training labels to train the power generation model. When the loss function in the power generation model is the minimum, the optimal power generation model can be obtained.

[0034] Finally, the overall factor of the target power plant's power generation can be extracted through the optimal power generation model, that is, the two filters added to the time recurrent neural network algorithm can be convolved through the convolution layer to output the overall factor of the target power plant's power generation.

[0035] S3, constructing a plurality of power generation sub-models according to the plurality of power generation units and calculating a plurality of limiting factors corresponding to the plurality of power generation sub-models.

[0036] Specifically, first, the power generation of a single power generation unit can be obtained, and the processing value X of each power generation unit can be obtained. q For example, the power generation of a single power generation unit can be organized into a data sequence M with a depth of x through a time series algorithm, and the collection interval of the data sequence M is y, where the calculation formula of the data sequence M can be expressed as:

[0037] M(p)=[ X q , X q-y , ...,X q+d-x*d ] T

[0038] Among them, M is the data sequence, y is the collection interval, and p is the power generation of a single power generation unit at the current time.

[0039] Furthermore, x and y can be calculated by the sliding window algorithm, and a high-dimensional multivariate regression model can be built, where the expression of the multivariate regression model can be:

[0040] F=a0+bM(p)

[0041] Among them, b is a data sequence composed of a0.

[0042] Furthermore, the processed values ​​of the power generation unit obtained through the multivariate regression model may constitute cache data, and the cache data is the limiting factor of the power generation unit.

[0043] S4, calculating power generation factors of multiple power generation units according to the overall factor and multiple limiting factors.

[0044] Specifically, a factor group corresponding to each power generation unit can be established, wherein the factor group can include an overall factor group t1 and a limiting factor group t2. Since the power generation factor of the power generation unit can be formed by combining the overall factor group t1 and the limiting factor group t2, the overall factor group t1 and the limiting factor group t2 can be partially connected, that is, the local t1' of the overall factor group t1 and the local t2' of the limiting factor group t2 can be connected and combined to obtain the power generation factor of the power generation unit, that is, [t1+t2', t2+t1'].

[0045] S5, multiple power generation factors are input into the power generation model to estimate the current power generation of the target power plant and realize intelligent early warning of the target power plant.

[0046] In one embodiment of the present invention, the intelligent early warning method for power plants based on data fusion also includes: if the difference between the estimated current power generation of the target power plant and the actual power generation of the target power plant is greater than 10% of the actual power generation of the target power plant, the target power plant sends a warning signal.

[0047] According to the intelligent early warning method for power plants based on data fusion according to an embodiment of the present invention, a power generation model is built through historical power generation, and the overall factor is extracted from the power generation model. Then, multiple power generation sub-models are built according to multiple power generation units and multiple limiting factors corresponding to the multiple power generation sub-models are calculated. Finally, the power generation factor of the power generation unit is calculated according to the overall factor and the limiting factor, and the power generation factor is input into the power generation model to estimate the power generation, thereby realizing intelligent early warning of the target power plant. As a result, the accuracy of the power plant safety early warning can be improved, the difficulty of the power plant early warning can be reduced, and the power plant can be safer during the power generation process.

[0048] In order to implement the power plant intelligent early warning method based on data fusion of the above embodiment, the present invention also proposes a power plant intelligent early warning system based on data fusion.

[0049] like Figure 2 As shown, the intelligent early warning system for power plants based on data fusion of an embodiment of the present invention includes: an acquisition module 100, a model building module 200, a first calculation module 300, a second calculation module 400 and an intelligent early warning module 500, wherein the acquisition module 100 is used to obtain the historical power generation of the target power plant in multiple fixed time periods in the past, and the target power plant includes multiple power generation units, and the power generation units include power generation equipment and power generation energy; the model building module 200 is used to build a power generation model for the target power plant through the historical power generation, and extract the overall factor about the power generation of the target power plant from the power generation model; the first calculation module 300 builds multiple power generation sub-models according to the multiple power generation units and calculates multiple limiting factors corresponding to the multiple power generation sub-models; the second calculation module 400 is used to calculate the power generation factors of the multiple power generation units according to the overall factor and the multiple limiting factors; the intelligent early warning module 500 is used to input the multiple power generation factors into the power generation model to estimate the current power generation of the target power plant and realize the intelligent early warning of the target power plant.

[0050] In one embodiment of the present invention, the acquisition module 100 can acquire the historical power generation of the selected target power plant in the past period of time through the networked power system, and can acquire the power generation of the target power plant multiple times through multiple fixed time nodes. For example, when the frequency of acquiring the historical power generation of the target power plant is once a day, if the power generation X of the target power plant in the past three days in a certain period of time is to be acquired, the power generation X of the target power plant can be expressed as:

[0051]

[0052] Among them, p is the power generation of the target power plant in one day, i is the number of days, and n is an integer.

[0053] In one embodiment of the present invention, the model building module 200 can create multiple power generation sequences based on multiple power generation units, and the sequences may include power generation equipment sequences and power generation energy sequences. It is understandable that since power generation equipment is large-scale equipment with many spare parts, different spare parts can be sequenced to form a power generation equipment sequence. Similarly, power generation energy can also be composed of multiple fuels and chemicals, which can also be sequenced to form a power generation energy sequence.

[0054] Secondly, the model building module 200 can summarize the processed values ​​of the power generation sequence into a specific range by means of data preprocessing. For example, the values ​​can be summarized into a specific range by means of the Z-score algorithm in the data preprocessing method, that is, the power generation X of the target power plant minus the mean of the power generation of the target power plant every day is divided by the standard deviation of the power generation sequence, so that the processed value is summarized into a specific range, wherein the calculation formula of the processed value can be expressed as:

[0055]

[0056] Among them, X q is the processing value, q is the time interval for obtaining power generation, is the mean value of the power generation series, and std(X) is the standard deviation of the power generation series.

[0057] Furthermore, the model building module 200 can estimate the power generation of a single power generation unit through the power generation model. Specifically, the time recurrent neural network algorithm can be used to estimate the power generation of a single power generation unit in a single day, that is, two filters can be added to the time recurrent neural network algorithm, and the two filters are set in parallel, and the two filters can be the power generation estimation value of a power generation unit and the power generation estimation value of the power generation unit in a fixed time period.

[0058] Furthermore, the model building module 200 can use the power generation sequence after data preprocessing as a training set, and classify the power generation in different time periods as training labels to train the power generation model. When the loss function in the power generation model is the minimum, the optimal power generation model can be obtained.

[0059] Finally, the model building module 200 can extract the overall factor of the power generation of the target power plant through the optimal power generation model, that is, the two filters added to the time recurrent neural network algorithm are convolved through the convolution layer to output the overall factor of the power generation of the target power plant.

[0060] In one embodiment of the present invention, first, the power generation of a single power generation unit can be obtained by the first calculation module 300, and the processing value X of each power generation unit is qFor example, the power generation of a single power generation unit can be organized into a data sequence M with a depth of x through a time series algorithm, and the collection interval of the data sequence M is y, where the calculation formula of the data sequence M can be expressed as:

[0061] M(p)=[X q , X q-y , ..., X q+d-x*d ] T

[0062] Among them, M is the data sequence, y is the collection interval, and p is the power generation of a single power generation unit at the current time.

[0063] Furthermore, the first calculation module 300 can calculate x and y by a sliding window algorithm and build a high-dimensional multivariate regression model, wherein the expression of the multivariate regression model can be:

[0064] F=a0+bM(p)

[0065] Among them, b is a data sequence composed of a0.

[0066] Furthermore, the first calculation module 300 may form cache data using the processed values ​​of the power generation unit obtained through the multivariate regression model, and the cache data is the limiting factor of the power generation unit.

[0067] In one embodiment of the present invention, the second calculation module 400 may establish a factor group corresponding to each power generation unit, wherein the factor group may include an overall factor group t1 and a limiting factor group t2. Since the power generation factor of the power generation unit can be formed by combining the overall factor group t1 and the limiting factor group t2, the overall factor group t1 and the limiting factor group t2 may be partially connected, that is, the local t1' of the overall factor group t1 and the local t2' of the limiting factor group t2 may be connected and combined to obtain the power generation factor of the power generation unit, that is, [t1+t2', t2+t1'].

[0068] In one embodiment of the present invention, the intelligent early warning system for power plants based on data fusion also includes: a judgment module 600, which is used to judge the size of the estimated current power generation of the target power plant and the actual power generation of the target power plant. If the difference between the estimated current power generation of the target power plant and the actual power generation of the target power plant is greater than 10% of the actual power generation of the target power plant, the target power plant sends a warning signal.

[0069] To summarize, the historical power generation of the target power plant is acquired through the acquisition module, and the power generation model is built through the model building module. Then, the first calculation module calculates multiple limiting factors corresponding to multiple power generation sub-models, and the second calculation module calculates the power generation factor of the power generation unit according to the overall factor and the limiting factor. Finally, the power generation factor is input into the power generation model through the intelligent early warning module to estimate the power generation, thereby realizing the intelligent early warning of the target power plant. As a result, the accuracy of the power plant's safety early warning can be improved, the difficulty of the power plant's early warning can be reduced, and the power plant can be safer during the power generation process.

[0070] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. "Multiple" means two or more, unless otherwise clearly and specifically defined.

[0071] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0072] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0073] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0074] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0075] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0076] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0077] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0078] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0079] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A power plant intelligent early warning method based on data fusion, characterized in that: The following steps are involved: Acquire historical power generation of a target power plant in multiple fixed time periods in the past, wherein the target power plant includes multiple power generation units, and the power generation units include power generation equipment and power generation energy; Building a power generation model for the target power plant through the historical power generation, and extracting an overall factor about the power generation of the target power plant from the power generation model; Building a plurality of power generation sub-models according to the plurality of power generation units and calculating a plurality of limiting factors corresponding to the plurality of power generation sub-models; Calculate the power generation factors of the plurality of power generation units according to the overall factor and the plurality of limiting factors; The plurality of power generation factors are input into the power generation model to estimate the current power generation of the target power plant and realize intelligent early warning of the target power plant.

2. The power plant intelligent early warning method based on data fusion according to claim 1 is characterized in that: Also includes: If the difference between the estimated current power generation of the target power plant and the actual power generation of the target power plant is greater than 10% of the actual power generation of the target power plant, the target power plant sends out an early warning signal.

3. The power plant intelligent early warning method based on data fusion according to claim 2 is characterized in that: The extracting of the overall factor about the power generation of the target power plant from the power generation model specifically includes: Creating a plurality of power generation sequences according to the plurality of power generation units, wherein the power generation sequence includes a power generation equipment sequence and a power generation energy sequence; The power generation sequence is processed by data preprocessing so that the processed values ​​are summarized into a specific range; estimating the power generation of a single power generation unit by using the power generation model; Training the power generation model according to the historical power generation to obtain an optimal power generation model; An overall factor of the power generation of the target power plant is extracted according to the optimal power generation model.

4. The power plant intelligent early warning method based on data fusion according to claim 3 is characterized in that: The said building of multiple power generation sub-models according to the multiple power generation units and calculating the multiple limiting factors corresponding to the multiple power generation sub-models specifically includes: Acquire the power generation of a single power generation unit, and organize the power generation of a single power generation unit into a data sequence with a depth of x according to a time series algorithm, and the collection interval of the data sequence is y; Calculate the depth x of the data sequence and the acquisition gap y to build a high-dimensional multivariate regression model; The limiting factor is calculated according to the multivariate regression model.

5. The power plant intelligent early warning method based on data fusion according to claim 4 is characterized in that: The method of building multiple power generation sub-models based on the multiple power generation units to calculate the power generation factors of the multiple power generation units specifically includes: For each power generation unit, a factor group corresponding to the power generation unit is established, wherein the factor group includes an overall factor group and a limiting factor group; combining the overall factor group and the limiting factor group; The power generation factors of the plurality of power generation units are calculated based on the combined factor group.

6. A power plant intelligent early warning system based on data fusion, characterized in that: include: An acquisition module, the acquisition module is used to acquire the historical power generation of a target power plant in multiple fixed time periods in the past, the target power plant includes multiple power generation units, and the power generation units include power generation equipment and power generation energy; A model building module, the model building module is used to build a power generation model for the target power plant through the historical power generation, and extract an overall factor about the power generation of the target power plant from the power generation model; A first calculation module, the first calculation module is used to build a plurality of power generation sub-models according to the plurality of power generation units and calculate a plurality of limiting factors corresponding to the plurality of power generation sub-models; A second calculation module, the second calculation module is used to calculate the power generation factors of the plurality of power generation units according to the overall factor and the plurality of limiting factors; An intelligent early warning module is used to input the plurality of power generation factors into the power generation model to estimate the current power generation of the target power plant and realize intelligent early warning of the target power plant.

7. The power plant intelligent early warning system based on data fusion according to claim 6 is characterized in that: Also includes: A judgment module, the judgment module is used to judge the size of the estimated current power generation of the target power plant and the actual power generation of the target power plant. If the difference between the estimated current power generation of the target power plant and the actual power generation of the target power plant is greater than 10% of the actual power generation of the target power plant, the target power plant sends out a warning signal.

8. The power plant intelligent early warning system based on data fusion according to claim 7 is characterized in that: The model building module is also used to: Creating a plurality of power generation sequences according to a plurality of the power generation units, wherein the power generation sequence includes a power generation equipment sequence and a power generation energy sequence; The power generation sequence is processed by data preprocessing so that the processed values ​​are summarized into a specific range; estimating the power generation of a single power generation unit by using the power generation model; Training the power generation model according to the historical power generation to obtain an optimal power generation model; An overall factor of the power generation of the target power plant is extracted according to the optimal power generation model.

9. The power plant intelligent early warning system based on data fusion according to claim 8 is characterized in that: The first calculation module is also used for: Acquire the power generation of a single power generation unit, and organize the power generation of a single power generation unit into a data sequence with a depth of x according to a time series algorithm, and the collection interval of the data sequence is y; Calculate the depth x of the data sequence and the acquisition gap y to build a high-dimensional multivariate regression model; The limiting factor is calculated according to the multivariate regression model.

10. The power plant intelligent early warning system based on data fusion according to claim 9 is characterized in that: The second calculation module is also used for: For each power generation unit, a factor group corresponding to the power generation unit is established, wherein the factor group includes an overall factor group and a limiting factor group; combining the overall factor group and the limiting factor group; The power generation factors of the plurality of power generation units are calculated based on the combined factor group.

Images