Intelligent algorithm-based kilowatt-hour fuel cost optimization method and system

Abstract

The invention discloses an intelligent algorithm-based kilowatt-hour fuel cost optimization method and system, and particularly relates to the field of intelligent algorithm kilowatt-hour fuel cost optimization, and the system comprises a data collection terminal, an intelligent algorithm module, an execution mechanism and a control center. The data acquisition terminal is responsible for acquiring key parameters in a power generation process in real time, and the data provides basic information for subsequent modeling and optimization calculation; the intelligent algorithm module is used for performing modeling and optimization calculation based on the data acquired by the data acquisition terminal, is a core module for realizing kilowatt-hour fuel cost optimization, and provides a basis for adjusting the running state of equipment for an execution mechanism through continuous iterative calculation; according to the method, the nonlinear relation is accurately captured, the combustion efficiency model containing the rotating speed, the load rate and the environment temperature is constructed, the influence of all parameters on the fuel cost is accurately described, and compared with a traditional univariate optimization method, the kilowatt-hour fuel cost reduction amplitude is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent algorithm-based fuel cost optimization per kilowatt-hour, and more specifically, to a method and system for optimizing fuel cost per kilowatt-hour based on an intelligent algorithm. Background Art

[0002] In the field of energy generation, the fuel cost per kilowatt-hour is a core indicator for measuring the economic efficiency of power generation. Traditional methods for optimizing the fuel cost per kilowatt-hour mainly rely on manual experience to set operating parameters, or use fixed models for offline optimization, which makes it difficult to respond to dynamic changes in fuel characteristics, equipment status, and environmental conditions in real time. Specifically, it is difficult to accurately capture the nonlinear coupling relationship between fuel flow and power generation, resulting in low fuel utilization; second, the impact of parameters such as ambient temperature and equipment speed on combustion efficiency is ignored, which easily leads to fuel waste when the load fluctuates; third, there is a lack of a closed-loop feedback mechanism. When the equipment ages or the fuel quality changes, the optimization effect decreases significantly, resulting in large fluctuations in the fuel cost per kilowatt-hour.

[0003] Therefore, based on the above problems, it is urgent to propose a method and system for optimizing the fuel cost per kilowatt-hour based on an intelligent algorithm, which can realize accurate control of the fuel cost per kilowatt-hour through an intelligent algorithm that perceives multi-dimensional parameters in real time and dynamically optimizes the operation strategy. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides a method and system for optimizing the fuel cost per kilowatt-hour based on an intelligent algorithm, and solves the problems raised in the above-mentioned background technology through the following scheme.

[0005] To achieve the above objectives, the present invention provides the following technical solution: comprising a data acquisition terminal, an intelligent algorithm module, an actuator, and a control center, wherein the data acquisition terminal, the intelligent algorithm module, and the actuator are all communicatively connected to the control center. The data acquisition terminal is used to collect key parameters of the power generation process in real time. The intelligent algorithm module performs modeling and optimization calculations based on the collected data. The actuator adjusts the equipment operating parameters according to the optimization results. Specifically, the solution includes the following steps:

[0006] S1, the high-precision sensor in the data acquisition terminal obtains parameters in real time;

[0007] S2. The intelligent algorithm module preliminarily constructs a mathematical model of the fuel cost per kilowatt-hour and introduces a correction factor for the equipment combustion efficiency;

[0008] S3, the intelligent algorithm module uses the improved particle swarm optimization algorithm to optimize parameters;

[0009] S4, the intelligent algorithm module executes the optimal parameters through the actuator mapping;

[0010] S5. The control center monitors the minimum electricity fuel cost data in real time and makes dynamic adjustments through closed-loop feedback.

[0011] Preferably, the parameters include measuring the instantaneous mass flow rate of the fuel through a Coriolis mass flowmeter, collecting the generated power P in real time through a power transmitter, measuring the ambient temperature T through a platinum resistance temperature sensor, obtaining the equipment spindle speed n through a photoelectric encoder, and obtaining the load rate by calculating the ratio of the generated power to the rated power.

[0012] Preferably, the mathematical model of the fuel cost per kilowatt-hour is specifically expressed as: Where C represents the fuel cost per kWh, t represents time, τ represents the integral variable, and q m represents the instantaneous mass flow rate of fuel, and P represents the power generation power. The equipment combustion efficiency correction coefficient η is obtained by fitting the experimental data of the speed n, load rate λ and ambient temperature T, and is specifically expressed as: η=1.2-0.01×|nn n |-0.8×(1-λ) 2 -0.05×(T-T0), n n Indicates the rated speed, and T0 indicates the standard ambient temperature.

[0013] Preferably, the method of parameter optimization is: using an improved particle swarm optimization algorithm, with the goal of minimizing C, to search for the optimal parameter combination (n * ,λ * ,T * ), specifically as follows:

[0014] SS1, set the number of particles N = 50, the maximum number of iterations M = 100, the particle position dimension D = 3, corresponding to (n * ,λ * ,T * ), the initial position of the particle is randomly generated within the safe operating range of the equipment: n∈[0.8n n ,1.2n n ],λ∈[0.6,1.0],T∈[15℃,35℃],initial velocity V i Set to 10% of the position range, indicating that V i At speed n dimension is [-0.04n n , 0.04n n ], the load rate λ dimension is [-0.04, 0.04], and the ambient temperature T dimension is [-4°C, 4°C];

[0015] SS2, taking the fuel cost C as the fitness function and introducing the combustion efficiency correction, the effective fuel flow actually involved in power generation is The fitness function is constructed as follows:

[0016] SS3. In each iteration, the particle velocity is updated according to the following formula: V id (t+1)=ωV id (t)+c1r 1d (t)(p id (t)-x id (t))+c2r 2d (t)(p gd (t)-x id (t)), the particle position is updated according to the following formula: id (t+1)=x id (t)+V id (t+1); where V id (t) represents the velocity of particle i in dimension d at the tth iteration, where d corresponds to the three dimensions of speed n, load rate λ, and ambient temperature T. V id (t+1) represents the velocity of particle i in dimension d at the (t+1)th iteration, ω represents the inertia weight, c1 and c2 represent the learning factors, r 1d 、r 2d represents a random number between [0, 1], p id (t) represents the individual optimal position of particle i in dimension d at the tth iteration, p gd (t) represents the global optimal position; x id (t) represents the position of particle i in dimension d at the tth iteration, x id (t+1) represents the position of particle i in dimension d at the (t+1)th iteration;

[0017] SS4. During the iteration process, the particle position must meet the physical constraints of the device: speed constraint: n>0.7n n And n <= 1.3n n ; Load rate constraint: λ>=0.5; Ambient temperature constraint: T∈[10℃,40℃].

[0018] Preferably, the mapping execution method is: the optimal parameter (n * ,λ * ,T * ) is imported into the equipment combustion efficiency correction coefficient and fitness function to obtain the minimum fuel cost C min And map the optimal parameters to the equipment execution instructions: adjust the spindle speed to n through the speed control system * ; Adjust the power generation to P through the load distribution system * =λ * ×P n ; Adjust the ambient temperature to T through the air conditioning system* .

[0019] Preferably, the closed-loop feedback includes: uploading the collected parameters in real time with a period of 100mm, performing optimization iteration every 10 minutes, and triggering an emergency re-optimization mechanism to recalculate the optimal parameters when it is detected that the fuel calorific value fluctuates by more than 5%.

[0020] Preferably, a per-kilowatt-hour fuel cost optimization system based on an intelligent algorithm includes a data acquisition terminal, an intelligent algorithm module, an actuator, and a control center, wherein the data acquisition terminal, the intelligent algorithm module, and the actuator are all connected to the control center for communication. The data acquisition terminal is used to collect key parameters in the power generation process in real time. The intelligent algorithm module performs modeling and optimization calculations based on the collected data. The actuator adjusts the equipment operating parameters according to the optimization results. Specifically, it includes:

[0021] Data acquisition module: High-precision sensors in the data acquisition terminal acquire parameters in real time;

[0022] Data analysis module: The intelligent algorithm module preliminarily constructs a mathematical model of the fuel cost per kilowatt-hour and introduces a correction factor for the equipment combustion efficiency;

[0023] Parameter optimization module: The intelligent algorithm module uses the improved particle swarm optimization algorithm to optimize parameters;

[0024] Optimal parameter execution module: The intelligent algorithm module executes the optimal parameters through the execution mechanism mapping;

[0025] Closed-loop feedback module: The control center monitors the minimum electricity fuel cost data in real time and makes dynamic adjustments through closed-loop feedback.

[0026] Technical effects and advantages of the present invention:

[0027] 1. This invention accurately captures nonlinear relationships and constructs a combustion efficiency model that includes speed, load rate, and ambient temperature, precisely characterizing the impact of each parameter on fuel cost. Compared with traditional single-variable optimization methods, the fuel cost per kilowatt-hour is reduced significantly;

[0028] 2. This invention uses a multi-parameter collaborative optimization and an improved particle swarm algorithm to introduce dynamic inertia weights and constraint processing mechanisms. When the equipment load fluctuates, the speed is improved compared to traditional algorithms, shortening the optimization response time.

[0029] 3. The present invention establishes a complete closed-loop feedback mechanism to ensure the system's adaptability to disturbances such as changes in fuel quality and equipment aging, thereby reducing the fluctuation range of fuel costs per kilowatt-hour, which is significantly better than the traditional method with large fluctuation range of fuel costs per kilowatt-hour. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 This is a schematic diagram of the device connection of the present invention;

[0031] Figure 2 Schematic diagram of the method structure of the present invention;

[0032] Figure 3 Schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION

[0033] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0034] As attached Figure 1 The method for optimizing fuel cost per kilowatt-hour based on an intelligent algorithm is shown, and includes a data acquisition terminal, an intelligent algorithm module, an actuator, and a control center. The data acquisition terminal, the intelligent algorithm module, and the actuator are all connected to the control center for communication. The data acquisition terminal is used to collect key parameters of the power generation process in real time. The intelligent algorithm module performs modeling and optimization calculations based on the collected data, and the actuator adjusts the equipment operating parameters according to the optimization results.

[0035] Data acquisition terminal: responsible for real-time collection of key parameters in the power generation process. These data provide basic information for subsequent modeling and optimization calculations.

[0036] Intelligent algorithm module: This module performs modeling and optimization calculations based on data acquired from the data acquisition terminal. It is the core module for optimizing fuel costs per kilowatt-hour. Through continuous iterative calculations, it provides the actuator with a basis for adjusting the operating status of the equipment.

[0037] Actuator: Based on the optimal parameter combination calculated by the intelligent algorithm module, it converts it into specific equipment execution instructions, which directly act on the power generation equipment to adjust the equipment's operating status to achieve the goal of reducing fuel costs per kilowatt-hour;

[0038] Control Center: The hub of the entire system, the control center is responsible for coordinating the work between the data acquisition terminal, the intelligent algorithm module and the actuator, receiving the real-time data uploaded by the data acquisition terminal and transmitting it to the intelligent algorithm module; obtaining the optimal parameter combination calculated by the intelligent algorithm module, and then sending these parameters to the actuator, instructing the actuator to adjust the equipment, and finally establishing a closed-loop mechanism for dynamic adjustment.

[0039] As attached Figure 2The method for optimizing the fuel cost per kilowatt-hour based on an intelligent algorithm includes the following steps:

[0040] S1, the high-precision sensor in the data acquisition terminal obtains parameters in real time;

[0041] In this embodiment, it should be specifically noted that: the parameters include the instantaneous mass flow rate of the fuel q measured by the Coriolis mass flow meter m , collect the generated power P in real time through the power transmitter, measure the ambient temperature T through the platinum resistance temperature sensor, obtain the equipment spindle speed n through the photoelectric encoder, and obtain the load rate λ by calculating the ratio of the generated power to the rated power.

[0042] S2. The intelligent algorithm module preliminarily constructs a mathematical model of the fuel cost per kilowatt-hour and introduces a correction factor for the equipment combustion efficiency;

[0043] In this embodiment, it should be specifically explained that the mathematical model of the fuel cost per kilowatt-hour is specifically expressed as: Where C represents the fuel cost per kWh, t represents time, τ represents the integral variable, and q m represents the instantaneous mass flow rate of fuel, and P represents the power generation power. The equipment combustion efficiency correction coefficient η is obtained by fitting the experimental data of the speed n, load rate λ and ambient temperature T, and is specifically expressed as: η=1.2-0.01×|nn n |-0.8×(1-λ) 2 -0.05×(T-T0), n n represents the rated speed, T0 represents the standard ambient temperature; it should be understood that the fuel cost per kilowatt-hour, C, represents the mass of fuel consumed per unit of power generation and is a key indicator for measuring the economic efficiency of power generation; the integral variable, τ, represents time and is used to perform cumulative calculations of fuel flow and power generation in the time dimension; the integral upper limit, t, represents the end point of the time period for calculating the cumulative fuel consumption mass and cumulative power generation, and the starting point is 0; the equipment combustion efficiency correction coefficient, η, is used to measure the difference between the equipment's combustion efficiency under different operating conditions and the ideal state, and its value range will change according to the changes in n, λ, and T; the rated speed, n n , is the standard operating speed designed for the equipment and is used as a reference value to calculate the impact of the speed on the combustion efficiency. The equipment combustion efficiency correction coefficient η is first pre-processed to eliminate the influence of the dimension before calculation. The combustion efficiency correction coefficient η is introduced because the combustion efficiency of the equipment is not fixed in the actual power generation process, but is affected by multiple factors such as the speed n, load rate λ, and ambient temperature T.

[0044] S3, the intelligent algorithm module uses the improved particle swarm optimization algorithm to optimize parameters;

[0045] In this embodiment, it should be specifically explained that the method of parameter optimization is: the intelligent algorithm module uses an improved particle swarm optimization algorithm to minimize C and search for the optimal parameter combination (n * ,λ * ,T * ), specifically as follows:

[0046] SS1, set the number of particles N = 50, the maximum number of iterations M = 100, the particle position dimension D = 3, corresponding to (n * ,λ * ,T * ), the initial position of the particle is randomly generated within the safe operating range of the equipment: n∈[0.8n n ,1.2n n ],λ∈[0.6,1.0],T∈[15℃,35℃],initial velocity V i Set to 10% of the position range, indicating that V i At speed n dimension is [-0.04n n , 0.04n n ], the load factor λ dimension is [-0.04, 0.04], and the ambient temperature T dimension is [-4°C, 4°C]. It is important to understand that the number of particles determines the number of initial exploration points in the algorithm's search space. Setting it to 50 means the algorithm will begin searching from 50 different initial operating parameter combinations. A larger number of particles allows the algorithm to more broadly cover the solution space in the early stages of the search, increasing the chances of finding the global optimal solution. A smaller number of particles may not fully explore the solution space and may easily become trapped in a local optimal solution. After repeated experiments and empirical analysis, 50 particles have been found to strike a good balance between computational efficiency and search effectiveness. The maximum number of iterations limits the algorithm's runtime. In each iteration, particles adjust their positions based on their own speed and position update formula, and the fitness function value is recalculated. Setting the number of iterations to 100 ensures that the algorithm has sufficient time to converge to a relatively optimal solution. The particle position dimension corresponds to the number of variables to be optimized. In the optimization of fuel cost per kWh, the primary variables to be optimized are the equipment spindle speed n, load factor λ, and ambient temperature T, so the dimension D = 3. The position of each particle in this three-dimensional space represents a set of equipment operating parameter combinations (n, λ, T). The algorithm continuously adjusts the position of the particles in this three-dimensional space to find the optimal parameter combination that minimizes the fuel cost C per kilowatt-hour. The initial position of the particle is randomly generated within the safe operating range of the equipment, where the speed [0.8n n ,1.2n n], load rate [0.6, 1.0], ambient temperature [15℃, 35℃]. This random initialization method can make the particles evenly distributed in the search space, avoid all particles starting the search from the same initial point, and thus increase the possibility of the algorithm finding the global optimal solution. These ranges are determined according to the safe operation limits and common working conditions of the equipment to ensure that the parameter combination searched by the algorithm is feasible in practice; the initial velocity provides an initial setting of the direction of movement and the magnitude of the speed for the particles at the beginning of the search. The positive or negative velocity indicates the direction of movement of the particle in the corresponding dimension, and the magnitude of the velocity determines the amplitude of the position change of the particle in each iteration. It is set to 10% of the position range so that the particles can have a certain range of exploration when they start searching, but they will not jump out of the area where the optimal solution may exist due to excessive speed;

[0047] SS2, taking the fuel cost C as the fitness function and introducing the combustion efficiency correction, the effective fuel flow actually involved in power generation is The fitness function is constructed as follows: It is important to understand that the fitness function takes into account the fuel flow rate q m , power generation power P and combustion efficiency correction coefficient η are the three key parameters. m represents the fuel consumption rate, P in the denominator reflects the output power of power generation, and η reflects the impact of combustion efficiency on fuel utilization. Through this combination, the fitness function can fully reflect the fuel cost per kilowatt-hour under different equipment operating parameter combinations. In the iterative process of the particle swarm algorithm, each particle represents a set of operating parameters, and the corresponding (n * ,λ * ,T * ), and then obtain the fitness function value. The smaller the value, the lower the fuel cost per kilowatt-hour under the operating parameter combination represented by the particle, which means that this parameter combination is more optimal. The algorithm continuously adjusts the position of the particle, that is, changes the operating parameters, so that the fitness function value is continuously reduced, and finally finds the optimal operating parameter combination that minimizes the fuel cost per kilowatt-hour, thereby optimizing the fuel cost per kilowatt-hour.

[0048] SS3. In each iteration, the particle velocity is updated according to the following formula: V id (t+1)=ωV id (t)+c1r 1d (t)(p id (t)-x id (t))+c2r 2d (t)(p gd (t)-x id (t)), the particle position is updated according to the following formula: id (t+1)=xid (t)+V id (t+1); where V id (t) represents the velocity of particle i in dimension d at the tth iteration, where d corresponds to the three dimensions of speed n, load rate λ, and ambient temperature T. V id (t+1) represents the velocity of particle i in dimension d at the (t+1)th iteration, ω represents the inertia weight, c1 and c2 represent the learning factors, r 1d 、r 2d represents a random number between [0, 1], p id (t) represents the individual optimal position of particle i in dimension d at the tth iteration, p gd (t) represents the global optimal position; x id (t) represents the position of particle i in dimension d at the tth iteration, x id (t+1) represents the position of particle i in dimension d at the (t+1)th iteration. It is important to understand that ω is used to balance the algorithm's global search and local development capabilities. When ω is large, the particle is more affected by its velocity at the previous moment and tends to search new areas in a larger range, which is beneficial to global search. When ω is small, the particle focuses more on fine-grained search in local areas. c1 controls the step size of the particle moving towards its historical optimal position, and r 1d is a random number between [0, 1], which introduces randomness to the particle's movement direction. This part makes the particle tend to move closer to the optimal position it has reached before, reflecting the particle's self-learning ability and helping the particle to further explore better solutions in its familiar area. c2 determines the step size of the particle moving towards the global optimal position, r 2d Randomness is also introduced. This part allows particles to refer to the optimal position found by other particles in the group, so that particles have social learning capabilities, prompting the entire particle group to move towards the direction of the global optimal solution, and accelerating the convergence of the algorithm; the speed update formula calculates the speed change of the particle in each dimension, and the position update formula adjusts the position of the particle in the search space according to this speed change. By continuously iteratively updating the speed and position, the particles continue to move in the search space, gradually approaching the optimal solution that minimizes the fitness function value. After each iteration, the particle will recalculate the fitness function value based on the new position and update the individual optimal position p id (t) and the global optimal position p gd (t), provides a more accurate reference for the next iteration; using the initialized V i Calculate the updated values of particle velocity and position at each iteration, so that the particles move continuously in the search space and gradually approach the optimal solution.

[0049] SS4. During the iteration process, the particle position must meet the physical constraints of the device: speed constraint: n>0.7n nAnd n <= 1.3n n ; Load rate constraint: λ>=0.5; Ambient temperature constraint: T∈[10℃,40℃]; It should be understood that the speed constraint is set based on the mechanical characteristics of the power generation equipment and the requirements for safe operation. When the speed is lower than 0.7n n When the speed is higher than 1.3n, the equipment may not be able to maintain a stable combustion and power generation state, resulting in incomplete combustion, reduced power generation efficiency, and even equipment failure. n Excessively high rotational speeds can subject the equipment to excessive mechanical stress, accelerating wear, shortening its service life, and potentially posing safety risks. During the particle swarm algorithm iteration process, if the rotational speed position n of a particle exceeds this range, it must be adjusted to a boundary value to ensure that the parameter combination the algorithm searches for is within the equipment's tolerable speed range. When the load factor is less than 0.5, the combustion process of the power generation equipment becomes unstable, resulting in incomplete fuel combustion, which not only increases fuel consumption but also potentially causes environmental pollution. To avoid this, the algorithm stipulates that the particle load factor position must be greater than or equal to 0.5. If the particle load factor λ is less than 0.5 during the iteration, it is adjusted to 0.5 to ensure that the equipment operates under a relatively stable load condition, improving power generation efficiency and fuel utilization. When the ambient temperature is below 10°C, the viscosity of the equipment's lubricating oil increases, increasing frictional resistance between components, affecting normal operation, and potentially leading to poor fuel atomization and reduced combustion efficiency. When the ambient temperature is above 40°C, heat dissipation becomes difficult, potentially causing overheating of components, impacting performance and lifespan. Therefore, the algorithm places constraints on the ambient temperature positions of particles. If they exceed the range, they are adjusted to the boundary value to ensure that the equipment operates at an appropriate ambient temperature and maintains good power generation performance. These constraint handling mechanisms ensure that the equipment operating parameter combinations found by the particle swarm algorithm are practical and feasible, preventing the algorithm from generating invalid solutions that cannot be applied to actual equipment. By continuously adjusting the particle positions to meet the constraints, the algorithm can search for the optimal fuel cost per kilowatt-hour parameter combination while ensuring safe and stable equipment operation, achieving a balance between the economic and safety aspects of the power generation process.

[0050] S4, the intelligent algorithm module executes the optimal parameters through the actuator mapping;

[0051] In this embodiment, it should be specifically explained that: the mapping execution method is: the optimal parameter (n * ,λ * ,T * ) is imported into the equipment combustion efficiency correction coefficient and fitness function to obtain the minimum fuel cost C min The optimal parameters are mapped to the equipment execution instructions: the actuator adjusts the spindle speed to n through the speed control system *; Adjust the power generation to P through the load distribution system * =λ * ×P n ; Adjust the ambient temperature to T through the air conditioning system * ; It should be understood that: according to the optimal load rate λ * , the load distribution system adjusts the power generation. Since the load rate is obtained by calculating the ratio of the power generation to the rated power, the actual power generation P that needs to be adjusted is * =λ * ×P n ; The key link of converting the theoretical optimal parameters obtained by the intelligent algorithm module into executable operations for actual power generation equipment, ensuring that the power generation equipment can be accurately adjusted according to the optimization results to achieve a reduction in fuel costs per kilowatt-hour.

[0052] S5. The control center monitors the minimum electricity fuel cost data in real time and makes dynamic adjustments through closed-loop feedback.

[0053] In this embodiment, it should be specifically explained that the dynamic adjustment method is as follows: the data acquisition terminal uploads parameters to the control center in real time with a period of 100 mm, and the intelligent algorithm module performs an optimization iteration every 10 minutes. When it is detected that the fuel calorific value fluctuates by more than 5%, the emergency re-optimization mechanism is triggered to recalculate the optimal parameters; at the same time, the control center establishes a minimum fuel cost threshold C per kWh. def , when the lowest electricity fuel cost C min Still greater than the minimum fuel cost threshold C defWhen a fault occurs, an early warning signal is issued to relevant technical personnel. It is important to understand that this data is uploaded to the control center in real time via the communication network, providing the latest information for subsequent analysis and decision-making. This high-frequency data collection allows for timely capture of subtle changes in parameters during the power generation process, ensuring the system's accurate perception of operating status. During each iteration, the algorithm uses the latest data received from the control center to recalculate the fitness function, update the particle swarm's velocity and position, and search for a new optimal parameter combination within the constraints of equipment safe operation. Through regular iterations, the system continuously adjusts equipment operating parameters based on dynamic changes in the power generation process, consistently optimizing towards reducing fuel costs per kilowatt-hour. Significant fluctuations in fuel calorific value can directly affect fuel energy release and combustion efficiency, thereby altering fuel costs per kilowatt-hour. Once an emergency reoptimization is triggered, the intelligent algorithm module immediately recalculates and quickly finds a new optimal parameter combination based on the new situation. This timely adjusts equipment operating status to address unexpected changes, ensuring stable operation of the power generation system and controlling fuel costs per kilowatt-hour. Closed-loop feedback and dynamic correction mechanisms enable the entire optimization system to form a self-regulating and self-optimizing closed loop. Through real-time data collection, regular optimization iterations, and an emergency optimization mechanism, the system can promptly respond to various changes in the power generation process. This dynamic correction ensures that the equipment always operates in a near-optimal state, minimizing fuel costs per kilowatt-hour and improving the economy and stability of power generation. It also helps extend the service life of the equipment and reduce equipment failures and maintenance costs.

[0054] Based on the above scheme and Figure 3 The present invention also discloses a per-kilowatt-hour fuel cost optimization system based on an intelligent algorithm, comprising a data acquisition terminal, an intelligent algorithm module, an actuator, and a control center. The data acquisition terminal, the intelligent algorithm module, and the actuator are all in communication with the control center. The data acquisition terminal is used to collect key parameters of the power generation process in real time. The intelligent algorithm module performs modeling and optimization calculations based on the collected data. The actuator adjusts the equipment operating parameters according to the optimization results. Specifically, the system includes:

[0055] Data acquisition module: High-precision sensors in the data acquisition terminal acquire parameters in real time;

[0056] Data analysis module: The intelligent algorithm module preliminarily constructs a mathematical model of the fuel cost per kilowatt-hour and introduces a correction factor for the equipment combustion efficiency;

[0057] Parameter optimization module: The intelligent algorithm module uses the improved particle swarm optimization algorithm to optimize parameters;

[0058] Optimal parameter execution module: The intelligent algorithm module executes the optimal parameters through the execution mechanism mapping;

[0059] Closed-loop feedback module: The control center monitors the minimum electricity fuel cost data in real time and makes dynamic adjustments through closed-loop feedback.

[0060] Secondly: The drawings of the embodiments disclosed in the present invention only involve structures related to the embodiments disclosed in the present invention. Other structures may refer to conventional designs. The same embodiment and different embodiments of the present invention may be combined with each other without conflict.

[0061] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for optimizing fuel cost per kilowatt-hour based on an intelligent algorithm, characterized in that: The system includes a data acquisition terminal, an intelligent algorithm module, an actuator, and a control center. The data acquisition terminal, the intelligent algorithm module, and the actuator are all connected to the control center. The data acquisition terminal is used to collect key parameters of the power generation process in real time. The intelligent algorithm module performs modeling and optimization calculations based on the collected data. The actuator adjusts the equipment operating parameters according to the optimization results. The specific steps include: S1, the high-precision sensor in the data acquisition terminal obtains parameters in real time; S2. The intelligent algorithm module preliminarily constructs a mathematical model of the fuel cost per kilowatt-hour and introduces a correction factor for the equipment combustion efficiency; S3, the intelligent algorithm module uses the improved particle swarm optimization algorithm to optimize parameters; S4, the intelligent algorithm module executes the optimal parameters through the actuator mapping; S5. The control center monitors the minimum electricity fuel cost data in real time and makes dynamic adjustments through closed-loop feedback.

2. The method for optimizing fuel cost per kilowatt-hour based on an intelligent algorithm according to claim 1, characterized in that: The parameters include the instantaneous mass flow rate of the fuel q measured by a Coriolis mass flow meter m , collect the generated power P in real time through the power transmitter, measure the ambient temperature T through the platinum resistance temperature sensor, obtain the equipment spindle speed n through the photoelectric encoder, and obtain the load rate λ by calculating the ratio of the generated power to the rated power.

3. The method for optimizing fuel cost per kilowatt-hour based on an intelligent algorithm according to claim 1, characterized in that: The mathematical model of the kilowatt-hour fuel cost is specifically expressed as follows: Where C represents the fuel cost per kWh, t represents time, τ represents the integral variable, and q m represents the instantaneous mass flow rate of fuel, and P represents the power generation power. The equipment combustion efficiency correction coefficient η is obtained by fitting the experimental data of the speed n, load rate λ and ambient temperature T, and is specifically expressed as: η=1.2-0.01×|nn n |-0.8×(1-λ) 2 -0.05×(T-T0), n n Indicates rated speed, T0 indicates standard ambient temperature.

4. The method for optimizing fuel cost per kilowatt-hour based on an intelligent algorithm according to claim 1, characterized in that: The method of parameter optimization is to use the improved particle swarm optimization algorithm, with the goal of minimizing C, to search for the optimal parameter combination (n * ,λ * ,T * ), specifically as follows: SS1, set the number of particles N = 50, the maximum number of iterations M = 100, the particle position dimension D = 3, corresponding to (n * ,λ * ,T * ), the initial position of the particle is randomly generated within the safe operating range of the equipment: n∈[0.8n n ,1.2n n ],λ∈[0.6,1.0],T∈[15℃,35℃],initial velocity V i Set to 10% of the position range, indicating that V i At speed n dimension is [-0.04n n , 0.04n n ], the load rate λ dimension is [-0.04, 0.04], and the ambient temperature T dimension is [-4°C, 4°C]; SS2, taking the fuel cost C as the fitness function and introducing the combustion efficiency correction, the effective fuel flow actually involved in power generation is The fitness function is constructed as follows: SS3. In each iteration, the particle velocity is updated according to the following formula: V id (t+1)=ωV id (t)+c1r 1d (t)(p id (t)-x id (t))+c2r 2d (t)(p gd (t)-x id (t)), the particle position is updated according to the following formula: id (t+1)=x id (t)+V id (t+1); Among them, V id (t) represents the velocity of particle i in dimension d at the tth iteration, where d corresponds to the three dimensions of speed n, load rate λ, and ambient temperature T. V id (t+1) represents the velocity of particle i in dimension d at the (t+1)th iteration, ω represents the inertia weight, c1 and c2 represent the learning factors, r 1d 、r 2d represents a random number between [0, 1], p id (t) represents the individual optimal position of particle i in dimension d at the tth iteration, p gd (t) represents the global optimal position; x id (t) represents the position of particle i in dimension d at the tth iteration, x id (t+1) represents the position of particle i in dimension d at the (t+1)th iteration; SS4. During the iteration process, the particle position must meet the physical constraints of the device: speed constraint: n>0.7n n And n <= 1.3n n ; Load rate constraint: λ>=0.5; Ambient temperature constraint: T∈[10℃,40℃].

5. The method for optimizing fuel cost per kilowatt-hour based on an intelligent algorithm according to claim 1, characterized in that: The mapping execution method is: the optimal parameter (n * ,λ * ,T * ) is imported into the equipment combustion efficiency correction coefficient and fitness function to obtain the minimum fuel cost C min And map the optimal parameters to the equipment execution instructions: adjust the spindle speed to n through the speed control system * ; Adjust the power generation to P through the load distribution system * =λ * ×P n ; Adjust the ambient temperature to T through the air conditioning system * .

6. The method for optimizing fuel cost per kilowatt-hour based on an intelligent algorithm according to claim 1, characterized in that: The dynamic adjustment method is as follows: the data acquisition terminal uploads parameters to the control center in real time with a period of 100 minutes, and the intelligent algorithm module performs optimization iteration every 10 minutes. When it detects that the fuel calorific value fluctuates by more than 5%, it triggers the emergency re-optimization mechanism and recalculates the optimal parameters. At the same time, the control center establishes the minimum fuel cost threshold C per kilowatt-hour. def , when the lowest electricity fuel cost C min Still greater than the minimum fuel cost threshold C def When an emergency occurs, an early warning signal is issued to relevant technical personnel.

7. A system for optimizing the fuel cost per kilowatt-hour based on an intelligent algorithm, for implementing the method for optimizing the fuel cost per kilowatt-hour based on an intelligent algorithm as described in any one of claims 1 to 6, characterized in that: It includes a data acquisition terminal, an intelligent algorithm module, an actuator, and a control center. The data acquisition terminal, the intelligent algorithm module, and the actuator are all connected to the control center. The data acquisition terminal is used to collect key parameters in the power generation process in real time. The intelligent algorithm module performs modeling and optimization calculations based on the collected data. The actuator adjusts the equipment operating parameters according to the optimization results. Specifically, it includes: Data acquisition module: High-precision sensors in the data acquisition terminal acquire parameters in real time; Data analysis module: The intelligent algorithm module preliminarily constructs a mathematical model of the fuel cost per kilowatt-hour and introduces a correction factor for the equipment combustion efficiency; Parameter optimization module: The intelligent algorithm module uses the improved particle swarm optimization algorithm to optimize parameters; Optimal parameter execution module: The intelligent algorithm module executes the optimal parameters through the execution mechanism mapping; Closed-loop feedback module: The control center monitors the minimum electricity fuel cost data in real time and makes dynamic adjustments through closed-loop feedback.

Images