Artificial intelligence large model-based power generation enterprise comprehensive energy safety operation method and system

Abstract

The invention discloses a power generation enterprise comprehensive energy safety operation method and system based on an artificial intelligence large model, and relates to the technical field of safety operation situation management and control, and the method comprises the steps: collecting internal and external data of a power generation enterprise, and carrying out the data preprocessing; constructing a comprehensive energy risk assessment model according to the preprocessed data, and training the model; and performing real-time monitoring and security situation analysis by using the comprehensive energy risk assessment model. According to the invention, the energy management efficiency and the system response capability of a power generation enterprise are effectively improved, the adaptability of the enterprise to environment change and market dynamics is enhanced through intelligent risk assessment, the power generation safety and economic benefits are remarkably improved, and a comprehensive and efficient energy safety management solution is provided for the power generation enterprise.

Description

Technical Field

[0001] The present invention relates to the technical field of safe operation situation control and management, and in particular to a comprehensive energy safety operation method and system for power generation enterprises based on an artificial intelligence large model. Background Art

[0002] With the continuous growth of global energy demand and the dual pressure of environmental protection, power generation companies are facing unprecedented challenges. Especially driven by the wave of energy transformation and digitalization, traditional power generation operation methods can no longer meet the modern society's needs for energy efficiency, safety and environmental friendliness. In recent years, the rapid development of artificial intelligence technology has brought revolutionary changes to the field of energy management. Through technologies such as big data analysis and machine learning, it is possible to optimize the management of the power generation process, improve energy utilization efficiency, reduce operating costs, and enhance the safety and responsiveness of the system. For example, through real-time data monitoring and prediction algorithms, potential risk points of the system can be identified at the first time, and early warning and automatic adjustment can be achieved, thereby ensuring the stable operation of the power grid. However, the existing related technologies still have some significant limitations.

[0003] Existing technologies often focus on optimizing a single aspect, such as simply improving power generation efficiency or only focusing on environmental emissions, and lack a comprehensive risk assessment and management framework. This results in the inability of existing systems to make optimal decisions when dealing with complex energy management issues, such as optimization and risk control of multi-energy supply. In addition, existing energy management systems are usually not flexible enough to adapt to rapidly changing market demands and environmental conditions. Based on these shortcomings, the present invention proposes a comprehensive energy safety operation method and system for power generation enterprises based on an artificial intelligence large model. The system designs a set of diversified risk assessment models, which not only covers multiple dimensions such as power generation performance, energy diversity and conversion efficiency, weather impact, and market demand sensitivity, but also comprehensively evaluates and manages various risks by constructing corresponding collaborative functions. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is: how to solve the problem that the existing methods are usually not flexible enough and difficult to adapt to the rapidly changing market demands and environmental conditions.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a comprehensive energy safety operation method for power generation enterprises based on a large artificial intelligence model, comprising: collecting internal and external data of the power generation enterprise and performing data preprocessing; constructing a comprehensive energy risk assessment model based on the preprocessed data and training the model; and using the comprehensive energy risk assessment model for real-time monitoring and safety situation analysis.

[0007] As a preferred solution of the comprehensive energy safety operation method for power generation enterprises based on the artificial intelligence large model described in the present invention, the internal and external data of the power generation enterprise include power generation data, energy consumption data, weather data and market demand data; the preprocessing includes missing value and outlier processing.

[0008] As a preferred solution of the comprehensive energy safety operation method of power generation enterprises of the artificial intelligence large model of the present invention, the construction of the comprehensive energy risk assessment model includes establishing a power generation performance function, an energy diversity and conversion efficiency function, a weather impact function, a market demand sensitivity function and an energy synergy function according to the collected internal and external data of the power generation enterprise; the power generation performance function includes determining according to the power generation, expressed as:

[0009]

[0010] Among them, F is the power generation performance function, λ is the weight factor, i is the i-th moment, n is the total number of moments, P t is the power generation at the current moment, P t-i is the power generation before the i-th moment, is the average value of power generation during the calculation period; the energy diversity and conversion efficiency function includes determination based on energy usage and energy conversion efficiency, expressed as:

[0011]

[0012] Among them, S is the energy diversity and conversion efficiency function, j is the jth energy, m is the total number of energy types, E j is the usage of the jth energy, E is the total energy usage, η j is the conversion efficiency of the jth energy source, and δ is the parameter for adjusting the influence of the energy diversity index.

[0013] As a preferred solution of the comprehensive energy safety operation method of power generation enterprises of the artificial intelligence large model of the present invention, the weather impact function includes integrating multiple meteorological parameters to evaluate the impact of weather on power generation efficiency and safety, which is expressed as:

[0014]

[0015] Among them, W is the weather impact function, w t is the weight based on the current weather conditions, T is the current temperature, and T opt is the optimal operating temperature, T rangc is the normal range of temperature variation, ψ is the coefficient for adjusting relative humidity, RH is the relative humidity, φ is the coefficient for adjusting wind speed, WS is the wind speed, WS maxis the maximum wind speed considered; the market demand sensitivity function includes assessing the risk by combining the forecast error and actual volatility of market demand, expressed as:

[0016]

[0017] Among them, D is the market demand sensitivity function, σ is the sensitivity coefficient of the impact of demand fluctuations on the strategy, and Dm actual To meet the actual market demand, Dm forccast is to predict market demand, ξ is the weight factor, Dm i is the market demand at the ith moment, is the average value of the market demand during the calculation period; the energy synergy function is determined according to the synergy between different energy sources and is expressed as:

[0018]

[0019] Among them, C is the energy synergy function, k is the kth energy, l is the lth energy, E k is the kth energy consumption, E l is the consumption of the first type of energy, ρ k,l is the synergy coefficient between the kth and lth energy sources, μ is the parameter for adjusting the impact of a single energy source, Ω k is the operation and maintenance complexity index of the kth energy source.

[0020] As a preferred solution of the comprehensive energy safety operation method of power generation enterprises of the artificial intelligence large model of the present invention, the comprehensive energy risk assessment model includes determining the interaction terms between different functions; the interaction terms include the interaction terms between power generation performance and energy diversity and conversion efficiency, the interaction terms between weather impact and market demand sensitivity, and the interaction terms between energy synergy and energy diversity and conversion efficiency, expressed as:

[0021]

[0022] Among them, H XY is the interaction term, w X and w Y are the weights corresponding to X and Y respectively, X is the relevant sub-function, and Y is another relevant sub-function.

[0023] As a preferred solution of the comprehensive energy safety operation method of power generation enterprises of the artificial intelligence large model of the present invention, the comprehensive energy risk assessment model also includes the output and interaction terms of all sub-functions as input, including two hidden layers, and outputs the assessment value of the comprehensive energy risk, which is expressed as:

[0024] H1=ReLU(W1x+b1)

[0025] H2=ReLU(W2H1+b2)

[0026] R=Sigmoid(W3H2+b3)

[0027] Among them, H1 is the output of the first hidden layer, H2 is the output of the second hidden layer, ReLU is the activation function, W1 is the weight matrix of the first hidden layer, x is the input vector, b1 is the bias vector of the first hidden layer, W2 is the weight matrix of the second hidden layer, b2 is the bias vector of the second hidden layer, R is the assessment value of the comprehensive energy risk, Sigmoid is the activation function, W3 is the weight matrix of the output layer, and b3 is the bias of the output layer; the model is trained using the loss function.

[0028] As a preferred scheme of the comprehensive energy safety operation method of power generation enterprises of the artificial intelligence large model described in the present invention, the real-time monitoring and safety situation analysis includes setting a low threshold value of the comprehensive energy risk assessment value, a medium threshold value of the comprehensive energy risk assessment value and a high threshold value of the comprehensive energy risk assessment value; if R is less than the low threshold value of the comprehensive energy risk assessment value, it is a low risk, and normal operation continues, and routine monitoring is performed; if R is greater than or equal to the low threshold value of the comprehensive energy risk assessment value and less than the medium threshold value of the comprehensive energy risk assessment value, it is a medium risk, and monitoring is strengthened, potential risk factors are evaluated, and preventive measures are prepared to be taken; if R is greater than or equal to the medium threshold value of the comprehensive energy risk assessment value and less than the high threshold value of the comprehensive energy risk assessment value, it is a high risk, and preventive measures are implemented, operating parameters are adjusted, and inspection frequency is increased; if R is greater than or equal to the high threshold value of the comprehensive energy risk assessment value, it is a serious risk, and the emergency response procedure is initiated, including suspending operation, activating the backup system, and urgently troubleshooting and solving the problem.

[0029] Another object of the present invention is to provide a system of comprehensive energy safety operation methods for power generation enterprises with artificial intelligence large models, which can solve the comprehensive energy safety operation problems of power generation enterprises with artificial intelligence large models by constructing a comprehensive energy safety operation system.

[0030] To solve the above technical problems, the present invention provides the following technical solutions: an artificial intelligence large-scale model comprehensive energy safety operation system for power generation enterprises, comprising a data acquisition module, a model construction module and an evaluation module; the data acquisition module is used to collect internal and external data of the power generation enterprise and perform data preprocessing; the model construction module is used to construct a comprehensive energy risk assessment model based on the preprocessed data and train the model; the evaluation module is used to use the comprehensive energy risk assessment model for real-time monitoring and safety situation analysis.

[0031] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the comprehensive energy safety operation method for a power generation enterprise based on the artificial intelligence large model as described above are implemented.

[0032] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the comprehensive energy safety operation method for power generation enterprises based on the artificial intelligence large model as described above.

[0033] The beneficial effects of the present invention are as follows: the comprehensive energy safety operation method for power generation enterprises based on the artificial intelligence large model provided by the present invention effectively improves the energy management efficiency and system responsiveness of power generation enterprises by constructing a comprehensive energy risk assessment model. Through intelligent risk assessment, it enhances the adaptability of enterprises to environmental changes and market dynamics, significantly improves power generation safety and economic benefits, and provides power generation enterprises with a comprehensive and efficient energy safety management solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0035] Figure 1 A flow chart of the comprehensive energy safety operation method for power generation enterprises based on the artificial intelligence large model provided in the first embodiment of the present invention.

[0036] Figure 2 A structural diagram of the comprehensive energy safety operation system for power generation enterprises based on the artificial intelligence large model provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0038] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0039] Example 1, reference Figure 1, which is the first embodiment of the present invention, provides a comprehensive energy safety operation method for power generation enterprises based on an artificial intelligence large model, including: collecting internal and external data of the power generation enterprise and performing data preprocessing; constructing a comprehensive energy risk assessment model based on the preprocessed data and training the model; using the comprehensive energy risk assessment model to perform real-time monitoring and security situation analysis.

[0040] S1. Collect internal and external data of power generation enterprises and perform data preprocessing.

[0041] Internal and external data of power generation enterprises include power generation data, energy consumption data, weather data and market demand data.

[0042] Preprocessing includes missing value and outlier processing.

[0043] S2. Construct a comprehensive energy risk assessment model based on the preprocessed data and train the model.

[0044] Based on the collected internal and external data of power generation enterprises, power generation performance function, energy diversity and conversion efficiency function, weather impact function, market demand sensitivity function and energy synergy function are established.

[0045] The power generation performance function includes determining according to the power generation, which is expressed as:

[0046]

[0047] Where F is the power generation performance function, λ is the weight factor used to adjust the relative importance of the two calculation items, i is the i-th moment, n is the total number of moments, P t is the power generation at the current moment, P t-i is the power generation before the i-th moment, is the average value of power generation during the calculation period.

[0048] The energy diversity and conversion efficiency function is determined based on energy usage and energy conversion efficiency and is expressed as:

[0049]

[0050] Among them, S is the energy diversity and conversion efficiency function, j is the jth energy, m is the total number of energy types, E j is the usage of the jth energy, E is the total energy usage, η j is the conversion efficiency of the jth energy source, and δ is the parameter for adjusting the influence of the energy diversity index.

[0051] The weather impact function includes integrating multiple meteorological parameters to evaluate the impact of weather on power generation efficiency and safety, which is expressed as:

[0052]

[0053] Among them, W is the weather impact function, w t is the weight based on the current weather conditions, T is the current temperature, and T opt is the optimal operating temperature, T rangc is the normal range of temperature variation, ψ is the coefficient for adjusting relative humidity, RH is the relative humidity, φ is the coefficient for adjusting wind speed, WS is the wind speed, WS max is the maximum wind speed considered.

[0054] The market demand sensitivity function includes assessing risk by combining the forecast error and actual volatility of market demand, expressed as:

[0055]

[0056] Among them, D is the market demand sensitivity function, σ is the sensitivity coefficient of the impact of demand fluctuations on the strategy, and Dm actual To meet the actual market demand, Dm forccast To predict market demand, ξ is the weight factor, considering demand volatility, Dm i is the market demand at the ith moment, It is the average value of market demand during the calculation period.

[0057] The energy synergy function is determined based on the synergy between different energy sources and is expressed as:

[0058]

[0059] Among them, C is the energy synergy function, k is the kth energy, l is the lth energy, E k is the kth energy consumption, E l is the consumption of the first type of energy, ρ k,l is the synergy coefficient between the kth and lth energy sources, μ is the parameter for adjusting the impact of a single energy source, Ω k is the operation and maintenance complexity index of the kth energy source.

[0060] Determine the interaction terms between different functions; the interaction terms include the interaction terms between power generation performance and energy diversity and conversion efficiency, the interaction terms between weather impact and market demand sensitivity, and the interaction terms between energy synergy and energy diversity and conversion efficiency, expressed as:

[0061]

[0062] Among them, H XY is the interaction term, w X and w Y are the weights corresponding to X and Y respectively, X is the relevant sub-function, and Y is another relevant sub-function.

[0063] Specifically, the interaction term between power generation performance and energy diversity and conversion efficiency is expressed as:

[0064]

[0065] Among them, H FS is the interaction term between power generation performance, energy diversity and conversion efficiency, w F is the weight corresponding to the power generation performance, w S are the weights corresponding to energy diversity and conversion efficiency.

[0066] The interaction term between weather impact and market demand sensitivity is expressed as:

[0067]

[0068] Among them, H WD is the interaction term between weather impact and market demand sensitivity, w W is the weight corresponding to the weather impact, w D is the weight corresponding to the market demand sensitivity.

[0069] The interaction term between energy synergy and energy diversity and conversion efficiency is expressed as:

[0070]

[0071] Among them, H SC is the interaction term between energy synergy and energy diversity and conversion efficiency, w S is the weight corresponding to energy diversity and conversion efficiency, w C is the weight corresponding to energy synergy.

[0072] Calculating the interaction terms for harmonic mean prevents an abnormally high risk score from excessively affecting the overall risk assessment results, reduces extreme impacts, and thus avoids overreaction.

[0073] The weights are analyzed based on historical data.

[0074] The output and interaction terms of all sub-functions are used as input, including two hidden layers, outputting the assessment value of comprehensive energy risk, input layer, input dimension: 8 (corresponding to 8 input values: F, S, W, D, C, H FS , H WD , H SC ).

[0075] Hidden layer, the first hidden layer: 64 neurons, the activation function is ReLU (Rectified Linear Unit); the second hidden layer: 32 neurons, the activation function is ReLU.

[0076] Output layer, output: 1 neuron, activation function is Sigmoid (output probability value of risk assessment).

[0077] It is expressed as:

[0078] H1=ReLU(W1X+b1)

[0079] H2=ReLU(W2H1+b2)

[0080] R=Sigmoid(W3H2+b3)

[0081] Among them, H1 is the output of the first hidden layer, H2 is the output of the second hidden layer, ReLU is the activation function, W1 is the weight matrix of the first hidden layer (dimension is [64x8]), X is the input vector, b1 is the bias vector of the first hidden layer (dimension is [64x1]), W2 is the weight matrix of the second hidden layer (dimension is [32x64]), b2 is the bias vector of the second hidden layer (dimension is [32x1]), R is the assessment value of the comprehensive energy risk, Sigmoid is the activation function, W3 is the weight matrix of the output layer ([1x32]), and b3 is the bias (scalar) of the output layer.

[0082] The model is trained using a loss function.

[0083] S3. Use comprehensive energy risk assessment models to conduct real-time monitoring and security situation analysis.

[0084] Real-time monitoring and security situation analysis include setting a low threshold value for the assessment value of the comprehensive energy risk, a medium threshold value for the assessment value of the comprehensive energy risk, and a high threshold value for the assessment value of the comprehensive energy risk.

[0085] If R is less than the low threshold of the comprehensive energy risk assessment value, it is a low risk and normal operation should continue and routine monitoring should be carried out. If R is greater than or equal to the low threshold of the comprehensive energy risk assessment value and less than the medium threshold of the comprehensive energy risk assessment value, it is a medium risk and monitoring should be strengthened, potential risk factors should be assessed and preventive measures should be prepared. If R is greater than or equal to the medium threshold of the comprehensive energy risk assessment value and less than the high threshold of the comprehensive energy risk assessment value, it is a high risk and preventive measures should be implemented, operating parameters should be adjusted and inspection frequency should be increased to ensure that the risk does not increase further. If R is greater than or equal to the high threshold of the comprehensive energy risk assessment value, it is a serious risk and emergency response procedures should be initiated, including suspension of operation, activation of backup systems, and emergency investigation and resolution of problems.

[0086] Example 2, reference Figure 2 , which is the second embodiment of the present invention, is different from the previous embodiment in that it provides a comprehensive energy safety operation system for power generation enterprises based on an artificial intelligence large model, including: a data acquisition module, a model building module and an evaluation module;

[0087] The data acquisition module is used to collect internal and external data of power generation enterprises and perform data preprocessing.

[0088] The model building module is used to build a comprehensive energy risk assessment model based on the preprocessed data and train the model.

[0089] The assessment module is used to perform real-time monitoring and security situation analysis using a comprehensive energy risk assessment model.

[0090] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0091] 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 conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "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 conjunction with such instruction execution systems, devices or apparatuses.

[0092] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a 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, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0093] 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.

[0094] Embodiment 3 is the third embodiment of the present invention. It is different from the first two embodiments in that it is used to verify the technical effects adopted in the present invention so as to verify the real effects of the method.

[0095] Power generation enterprise data:

[0096] Power generation data: including power generation records in different time periods.

[0097] Energy consumption data: including the usage of various energy types and their conversion efficiency.

[0098] Weather data: including temperature, humidity, wind speed and other meteorological parameters.

[0099] Market demand data: including market demand forecasts and actual values.

[0100] Simulation time range: daily data within one year.

[0101] Traditional method 1: Single-dimensional optimization: only optimize power generation efficiency without considering other factors.

[0102] Traditional approach 2: Rule-based energy management: Energy management is performed according to predetermined rules without real-time risk assessment and adjustment.

[0103] This embodiment uses the traditional method and the method of the present invention to perform detection simultaneously, and the detection comparison results are shown in the following Table 1:

[0104] Table 1 Comparison table between traditional method and method of the present invention

[0105]

[0106] System response time: The system response time of the method of the present invention during simulation is significantly lower than that of the traditional method. This shows that the method of the present invention can respond to environmental changes and market dynamics more quickly, improving the flexibility and adaptability of the system.

[0107] Early warning accuracy: Through the application of the comprehensive energy risk assessment model, the method of the present invention significantly improves the early warning accuracy, reduces false alarms and missed alarms, and improves the safety and reliability of the system.

[0108] System stability: The system stability of the method of the present invention is excellent, and the number of annual abnormalities is significantly reduced. This shows that the system is more stable during operation, reducing the impact of downtime and maintenance due to failures.

[0109] Environmental friendliness: The method of the present invention effectively reduces emissions and significantly improves environmental friendliness by optimizing energy management. This is of great significance for power generation companies in dealing with environmental protection pressure.

[0110] Safety: The method of the present invention greatly reduces the accident rate, significantly improves the operational safety of power generation enterprises, and reduces safety risks.

[0111] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. The comprehensive energy safety operation method of power generation enterprises based on artificial intelligence large model is characterized by: include, Collect internal and external data of power generation enterprises and perform data preprocessing; Construct a comprehensive energy risk assessment model based on the preprocessed data and train the model; Use comprehensive energy risk assessment models for real-time monitoring and security situation analysis.

2. The method for comprehensive energy safety operation of power generation enterprises based on artificial intelligence large model as claimed in claim 1, characterized in that: The internal and external data of the power generation enterprise include power generation data, energy consumption data, weather data and market demand data; The preprocessing includes missing value and outlier processing.

3. The comprehensive energy safety operation method for power generation enterprises based on the artificial intelligence large model as claimed in claim 2 is characterized by: The construction of the comprehensive energy risk assessment model includes establishing a power generation performance function, an energy diversity and conversion efficiency function, a weather impact function, a market demand sensitivity function and an energy synergy function based on the collected internal and external data of the power generation enterprise; The power generation performance function includes determining according to the power generation amount and is expressed as: Among them, F is the power generation performance function, λ is the weight factor, i is the i-th moment, n is the total number of moments, P t is the power generation at the current moment, P t-i is the power generation before the i-th moment, is the average value of power generation during the calculation period; The energy diversity and conversion efficiency function includes determining according to energy usage and energy conversion efficiency, and is expressed as: Among them, S is the energy diversity and conversion efficiency function, j is the jth energy, m is the total number of energy types, E j is the usage of the jth energy, E is the total energy usage, η j is the conversion efficiency of the jth energy source, and δ is the parameter for adjusting the influence of the energy diversity index.

4. The comprehensive energy safety operation method for power generation enterprises based on the artificial intelligence large model as claimed in claim 3 is characterized by: The weather impact function includes integrating multiple meteorological parameters to evaluate the impact of weather on power generation efficiency and safety, which is expressed as: Among them, W is the weather impact function, w t is the weight based on the current weather conditions, T is the current temperature, and T opt is the optimal operating temperature, T range is the normal range of temperature variation, ψ is the coefficient for adjusting relative humidity, RH is the relative humidity, φ is the coefficient for adjusting wind speed, WS is the wind speed, WS max is the maximum wind speed considered; The market demand sensitivity function includes assessing risk by combining the forecast error and actual volatility of market demand, expressed as: Among them, D is the market demand sensitivity function, σ is the sensitivity coefficient of the impact of demand fluctuations on the strategy, and Dm actual To meet the actual market demand, Dm forccast is to predict market demand, ξ is the weight factor, Dm i is the market demand at the ith moment, is the average value of market demand during the calculation period; The energy synergy function includes determining according to the synergy between different energy sources and is expressed as: Among them, C is the energy synergy function, k is the kth energy, l is the lth energy, E k is the kth energy consumption, E l is the consumption of the first type of energy, ρ k,l is the synergy coefficient between the kth and lth energy sources, μ is the parameter for adjusting the impact of a single energy source, and Ω k is the operation and maintenance complexity index of the kth energy source.

5. The method for comprehensive energy safety operation of power generation enterprises based on the artificial intelligence large model as claimed in claim 4 is characterized by: The comprehensive energy risk assessment model includes determining interaction terms between different functions; The interaction terms include the interaction terms between power generation performance and energy diversity and conversion efficiency, the interaction terms between weather impact and market demand sensitivity, and the interaction terms between energy synergy and energy diversity and conversion efficiency, which are expressed as: Among them, H XY is the interaction term, w X and w Y are the weights corresponding to X and Y respectively, X is the relevant sub-function, and Y is another relevant sub-function.

6. The method for comprehensive energy safety operation of power generation enterprises based on artificial intelligence large model as claimed in claim 5, characterized in that: The comprehensive energy risk assessment model also includes two hidden layers, which take the outputs and interaction terms of all sub-functions as inputs and output the assessment value of the comprehensive energy risk, expressed as: H1=ReLU(W1X+b1) H2=ReLU(W2H1+b2) R=Sigmoid(W3H2+b3) Among them, H1 is the output of the first hidden layer, H2 is the output of the second hidden layer, ReLU is the activation function, W1 is the weight matrix of the first hidden layer, X is the input vector, b1 is the bias vector of the first hidden layer, W2 is the weight matrix of the second hidden layer, b2 is the bias vector of the second hidden layer, R is the assessment value of the comprehensive energy risk, Sigmoid is the activation function, W3 is the weight matrix of the output layer, and b3 is the bias of the output layer; The model is trained using a loss function.

7. The method for comprehensive energy safety operation of power generation enterprises based on artificial intelligence large model as claimed in claim 6 is characterized by: The real-time monitoring and security situation analysis includes setting a low threshold value of the comprehensive energy risk assessment value, a medium threshold value of the comprehensive energy risk assessment value, and a high threshold value of the comprehensive energy risk assessment value; If R is less than the low threshold of the comprehensive energy risk assessment value, it is a low risk and normal operation should continue and routine monitoring should be carried out. If R is greater than or equal to the low threshold of the comprehensive energy risk assessment value and less than the medium threshold of the comprehensive energy risk assessment value, it is a medium risk and monitoring should be strengthened, potential risk factors should be assessed and preventive measures should be prepared. If R is greater than or equal to the medium threshold of the comprehensive energy risk assessment value and less than the high threshold of the comprehensive energy risk assessment value, it is a high risk and preventive measures should be implemented, operating parameters should be adjusted and inspection frequency should be increased. If R is greater than or equal to the high threshold of the comprehensive energy risk assessment value, it is a serious risk and emergency response procedures should be initiated, including suspension of operation, activation of backup systems, and emergency investigation and resolution of problems.

8. A system for a comprehensive energy safety operation method for a power generation enterprise using the artificial intelligence large model as described in any one of claims 1 to 7, characterized in that: Including data collection module, model building module and evaluation module; The data acquisition module is used to collect internal and external data of the power generation enterprise and perform data preprocessing; The model building module is used to build a comprehensive energy risk assessment model based on the preprocessed data and train the model; The assessment module is used to perform real-time monitoring and security situation analysis using a comprehensive energy risk assessment model.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the comprehensive energy safety operation method for power generation enterprises based on the artificial intelligence large model described in any one of claims 1 to 7 are implemented.

10. 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 comprehensive energy safety operation method for power generation enterprises based on the artificial intelligence large model described in any one of claims 1 to 7 are implemented.

Images