Energy-saving optimization method for operating parameters of boiler cluster

Abstract

The invention discloses an energy-saving optimization method for operating parameters of a boiler cluster, which belongs to the technical field of energy conservation of special equipment, and comprises the following steps of: 1, calculating to obtain the actual condition of a demand side, and establishing a function relationship between the overall required heat supply amount and each influence factor through analog calculation; 2, respectively establishing an energy consumption model of a fan and a pump and an energy consumption model of boiler equipment by using the collected actual equipment operation data; thirdly, the energy consumption model of the whole heat supply system serves as a target function, safe operation of boiler equipment serves as a boundary condition, and optimization calculation is conducted; 4, verifying by using the obtained parameters, and substituting a verification result into an original energy consumption model for secondary learning to obtain an accurate model; according to the energy-saving optimization method for the operating parameters of the boiler cluster, the change of the energy demand quantity is accurately grasped, so that the energy consumption is clearly shown in the front; and global solution is carried out, so that the global optimality of the result and the quickness of calculation are ensured.

Description

Technical Field

[0001] The invention relates to a method for energy-saving optimization of boiler cluster operating parameters, belonging to the technical field of energy-saving of special equipment. Background Art

[0002] In winter, heating in the north is mostly done in the form of centralized heating, so centralized thermal power stations mostly operate in the form of multiple boilers in parallel, that is, boiler cluster mode. Since the operating conditions of boiler clusters are relatively complex, the boilers are not operated under the optimal conditions most of the time, resulting in energy waste. Therefore, in order to solve the above problems, it is urgent to propose an energy-saving optimization calculation for boiler cluster operating parameters. Summary of the invention

[0003] To solve the above problems, the present invention proposes a method for energy-saving optimization of boiler cluster operating parameters, which can accurately grasp the changes in energy demand and clearly display the energy consumption; and provide safety protection with safe operation as the boundary condition; and perform global solution to ensure the global optimality of the results and the speed of calculation; and after the operation starts, establish an operating parameter database, perform deep learning through the BP-neural network algorithm, and then fine-tune the operating parameters.

[0004] The method for energy-saving optimization of boiler cluster operating parameters of the present invention comprises the following steps:

[0005] The first step is to calculate the actual situation on the demand side and establish the functional relationship between the overall required heating amount and various influencing factors through simulation calculation;

[0006] The second step is to use the collected actual equipment operation data to establish the energy consumption model of the fan and pump and the energy consumption model of the boiler equipment respectively;

[0007] The third step is to use the energy consumption model of the overall heating system as the objective function and the safe operation of the boiler equipment as the boundary condition to perform optimization calculation;

[0008] The fourth step is to use the obtained parameters for verification and bring the verification results into the original energy consumption model for secondary learning to obtain an accurate model.

[0009] Furthermore, establishing the functional relationship between the overall required heating amount and various influencing factors in the first step specifically includes the following steps: starting with energy consumption simulation, simulating the process after the boiler supplies energy from the perspective of energy consumption, and accurately grasping the changes in energy consumption with external factors, including the functional relationship between the required heating amount of the heating boiler and the number of users, the degree of building insulation, dry-bulb temperature, wet-bulb temperature, humidity and light conditions; and the functional relationship between the steam supply of the steam boiler and the process production, insulation measures and process operating conditions.

[0010] Furthermore, the specific operation steps of the second step are as follows:

[0011] (1) Establish the energy consumption model of the fan and pump. The pump and fan are related to three key variables: rotation frequency, fluid flow rate and electrical power. Directly collect actual operation data and use the least squares method to fit equations (1) to (3):

[0012]

[0013] In the formula, P is the electric power, Q is the fluid flow rate, f is the rotation frequency, a1~a3 and n1~n3 are the coefficients to be fitted;

[0014] (2) Establish the energy consumption model of boiler equipment,

[0015] a. Establish an energy consumption model for a cooling tower. To build an energy consumption model for a cooling tower, it is necessary to solve the water temperature of the lower tower. The factors affecting the water temperature of the lower tower include the water temperature of the upper tower, the wet bulb temperature of the air, and the air flow rate in the cooling tower. Divide the heat exchange volume in the cooling tower into a number of small units and establish the heat transfer energy equation between air and water, as shown in formula (4):

[0016] LC p dt=Gdh=K'a(h'-h a )dV, (4)

[0017] Then, by integrating both sides of equation (4), we can obtain the heat transfer balance equation of the cooling tower as a whole, as shown in equations (5) and (6):

[0018]

[0019] The integral result of (5) is called the number of heat transfer units of the cooling tower. Substituting the calculated number of heat transfer units and the cooling tower model into the model, the water temperature of the lower tower can be obtained.

[0020] Where a is the heat transfer area per unit volume of the cooling tower heat transfer part, C p is the specific heat capacity of water at constant pressure, G is the air flow rate in the cooling tower, h1 is the air enthalpy at the inlet of the cooling tower, h2 is the air enthalpy at the outlet of the cooling tower, h' is the air enthalpy at the same temperature as the cooling water, and h a is the enthalpy of air exchanging heat with cooling water, K' is the comprehensive heat transfer coefficient, L is the cooling water flow rate, t1 is the cooling water lower tower temperature, t2 is the cooling water upper tower temperature, and V is the volume of the heat transfer part of the cooling tower;

[0021] b. Establish a boiler energy consumption model. Relying on thermal engineering theory, establish a complete mathematical energy consumption model, fit it with the actual operation data, obtain the correlation coefficient, and then obtain a mathematical model that can be used for actual calculations.

[0022] Furthermore, when establishing the boiler energy consumption model, it also includes simulating the boiler operation, applying a large amount of simulation data and actual operation data to perform machine training, and using the machine training model to replace the mathematical energy consumption model.

[0023] Furthermore, the machine training is performed using a BP-neural network algorithm.

[0024] Furthermore, the process of searching for boundary conditions in the third step is as follows: determine the highest allowable boundary conditions based on the rated data of the boiler design and external pipe network factors, wherein the safety boundary conditions of the boiler include: the highest and lowest usage requirements of boiler pressure, medium inlet and outlet temperatures, and fuel combustion rate factors under triple safety conditions; on this basis, simulate the boiler operation with reference to the boiler design materials, actual operating data, and the current status of the boiler to obtain theoretical values; and compare the simulation results with the actual data to finally obtain the safety boundary conditions for the boiler operation.

[0025] Furthermore, the specific steps of the third step are as follows: establish a boiler energy consumption objective function, take triple safety operation as boundary conditions, and use a genetic algorithm to optimize the optimal operating condition.

[0026] Furthermore, the specific steps of the fourth step are as follows: obtain the optimal operating conditions of various boiler clusters under different external conditions, and input them into the boiler cluster system for testing; substitute the test results into the boiler energy consumption model, and perform secondary correction on the coefficients in the model. This test is repeated many times until the error of the operating result is <5%.

[0027] Compared with the prior art, the method for energy-saving optimization of boiler cluster operating parameters of the present invention establishes a functional relationship between the overall heat demand and various factors such as the local environment, and accurately grasps the changes in energy demand; establishes energy consumption models of various equipment through mathematical modeling and machine learning methods, so that the energy consumption is clearly displayed in front of us; takes safe operation as the boundary condition, which not only guarantees the safety of personnel and equipment, but also guarantees the heat supply; uses genetic algorithms as heuristic algorithms for global solution, which can not only ensure the global optimality of the results, but also ensure the speed of calculation; after the operation starts, establishes an operating parameter database, and conducts deep learning through the BP-neural network algorithm, and then fine-tunes the operating parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a schematic diagram of the overall process of the present invention.

[0029] Figure 2 It is a schematic diagram of input and output of the cooling tower model of the present invention. DETAILED DESCRIPTION

[0030] Embodiment 1:

[0031] like Figure 1 The method for energy-saving optimization of boiler cluster operating parameters shown includes the following steps:

[0032] The first step is to calculate the actual situation on the demand side, and establish the functional relationship between the overall required heat supply and various influencing factors through simulation calculation; specifically, the calculation of required heat is an important basis for ensuring operational safety. Whether the boiler is supplying heat or steam, it is necessary to accurately grasp the required heat. There are many documents available for search, and it is easy to form results, but there are few energy consumption simulations in various industries; therefore, the present invention starts with energy consumption simulation, simulates the process after the boiler is powered from the perspective of energy consumption, and accurately grasps the situation where energy consumption changes with external factors, including the functional relationship between the required heat supply of the heating boiler and the number of users, the degree of house insulation, the dry-bulb temperature, the humidity and the light conditions; and the functional relationship between the steam supply of the steam boiler and the process production, insulation measures and process operating conditions;

[0033] The second step is to use the collected actual equipment operation data to establish the energy consumption model of the fan and pump and the energy consumption model of the boiler equipment respectively; specifically,

[0034] (1) Establish energy consumption models for fans and pumps. Pumps and fans are fluid delivery equipment, and their energy consumption is relatively large. Therefore, efficient and energy-saving operation of pumps and fans is very important. Pumps and fans deliver water and air respectively. There is no essential difference in mathematical energy consumption models. The only difference is the density of the delivered fluid. Pumps and fans have three key variables: rotation frequency, fluid flow rate, and electrical power. The mathematical model modeled by transmission efficiency is relatively complex, and the model data is not easy to obtain. The data error is also relatively large. The actual operation data can be directly collected and fitted with the least squares method (1) to (3):

[0035]

[0036] In the formula, P is the electric power, Q is the fluid flow rate, f is the rotation frequency, a1~a3 and n1~n3 are the coefficients to be fitted;

[0037] (2) Establish the energy consumption model of boiler equipment,

[0038] a. Establish the energy consumption model of cooling tower. Cooling tower is the heat dissipation equipment in the boiler system. The waste heat of the working fluid needs to be discharged to the atmosphere through this equipment. Therefore, the performance of cooling tower is directly related to the efficiency of working fluid circulation. There are two common types of cooling towers: open cooling tower and closed cooling tower. Most special equipment boiler clusters currently use open cooling towers. The cooling tower model mainly needs to solve the physical quantity of the lower tower water temperature. The main influencing factors are: upper tower water temperature, air wet bulb temperature, and air flow in the cooling tower (including the fan induced air volume and natural air volume).

[0039] The heat exchange volume in the cooling tower is divided into a number of small units, and the heat transfer energy equation between air and water is established, as shown in formula (4):

[0040] LC p dt=Gdh=K'a(h'-h a )dV, (4)

[0041] Then, by integrating both sides of equation (4), we can obtain the heat transfer balance equation of the cooling tower as a whole, as shown in equations (5) and (6):

[0042]

[0043] The integral result of (5) is called the number of transfer units (NTU) of the cooling tower. The NTU value is determined by the inherent physical properties of the cooling tower and can be calculated based on the product model and related ratings provided by the cooling tower supplier or based on actual operating data. Figure 2 As shown, the water temperature of the lower tower can be obtained by substituting the calculated NTU value and the cooling tower model into the model;

[0044] Where a is the heat transfer area per unit volume of the cooling tower heat transfer part, C p is the specific heat capacity of water at constant pressure, G is the air flow rate in the cooling tower, h1 is the air enthalpy at the inlet of the cooling tower, h2 is the air enthalpy at the outlet of the cooling tower, h' is the air enthalpy at the same temperature as the cooling water, and h a is the enthalpy of air exchanging heat with cooling water, K' is the comprehensive heat transfer coefficient, L is the cooling water flow rate, t1 is the cooling water lower tower temperature, t2 is the cooling water upper tower temperature, and V is the volume of the heat transfer part of the cooling tower;

[0045] b. Establish a boiler energy consumption model. The boiler energy consumption model is the calculation core and includes two paths:

[0046] Path 1: Relying on thermal engineering theory, establish a complete mathematical energy consumption model, fit it with the actual operation data, obtain the correlation coefficient, and then obtain a mathematical model that can be used for actual operation;

[0047] Path 2: Simulate the operation of the boiler, use a large amount of simulation data and actual operation data for machine training, and use the machine training model to replace the mathematical energy consumption model; wherein the machine training is performed using the BP-neural network algorithm;

[0048] The third step is to use the energy consumption model of the overall heating system as the objective function and the safe operation of the boiler equipment as the boundary condition to perform optimization calculations; specifically, establish the boiler energy consumption objective function, use triple safe operation as the boundary condition, and use the genetic algorithm to optimize the optimal operating conditions; the genetic algorithm is used for optimization, which has advantages in fast and global optimization; other heuristic algorithms can be used as alternatives, and the final algorithm is selected by comparison with the operating result data; the boundary condition exploration process is as follows: it is determined according to the rated data of the boiler design and factors such as the external pipe network, so only the highest allowable boundary condition is specified, and its lower limit is not specified; such as the boiler medium outlet temperature The temperature of the outlet is only specified, but the minimum temperature is not required. In actual use, the user sets the outlet temperature of the medium at a lower value in order to save energy, which causes serious corrosion of the boiler in a short period of time, affecting the service life of the boiler. This step is mainly to determine the safety boundary conditions of the boiler: the highest and lowest use requirements of factors such as boiler pressure, medium inlet and outlet temperatures, and fuel combustion rate under triple safety conditions. For this purpose, it is necessary to refer to the boiler design materials, actual operation data and the current status of the boiler, simulate the boiler operation, and obtain the theoretical value. The simulation results are compared with the actual data to finally obtain the safety boundary conditions of the boiler operation.

[0049] The fourth step is to use the obtained parameters for verification, and bring the verification results into the original energy consumption model for secondary learning to obtain an accurate model; specifically, obtain the optimal operating conditions of various boiler clusters under different external conditions, and input them into the boiler cluster system for testing; substitute the test results into the boiler energy consumption model, and make secondary corrections to the coefficients in the model. This test is repeated many times until the error of the operating results is <5%.

[0050] The above embodiments are only preferred implementations of the present invention, so all equivalent changes or modifications made according to the structures, features and principles described in the scope of the patent application of the present invention are included in the scope of the patent application of the present invention.

Claims

1. A method for energy-saving optimization of boiler cluster operating parameters, characterized in that: The following steps are involved: The first step is to calculate the actual situation on the demand side and establish the functional relationship between the overall required heating amount and various influencing factors through simulation calculation; The second step is to use the collected actual equipment operation data to establish the energy consumption model of the fan and pump and the energy consumption model of the boiler equipment respectively; The third step is to use the energy consumption model of the overall heating system as the objective function and the safe operation of the boiler equipment as the boundary condition to perform optimization calculation; The fourth step is to use the obtained parameters for verification and bring the verification results into the original energy consumption model for secondary learning to obtain an accurate model.

2. The method for energy-saving optimization of boiler cluster operating parameters according to claim 1, characterized in that: The first step of establishing the functional relationship between the overall required heating amount and various influencing factors specifically includes the following steps: starting with energy consumption simulation, simulating the process after the boiler supplies energy from the perspective of energy consumption, and accurately grasping the changes in energy consumption with external factors, including the functional relationship between the required heating amount of the heating boiler and the number of users, the degree of building insulation, dry-bulb temperature, wet-bulb temperature, humidity and light conditions; and the functional relationship between the steam supply of the steam boiler and the process production, insulation measures and process operating conditions.

3. The method for energy-saving optimization of boiler cluster operating parameters according to claim 1, characterized in that: The specific steps of the second step are as follows: (1) Establish the energy consumption model of the fan and pump. The pump and fan are related to three key variables: rotation frequency, fluid flow rate and electrical power. Directly collect actual operation data and use the least squares method to fit equations (1) to (3): In the formula, P is the electric power, Q is the fluid flow rate, f is the rotation frequency, a1~a3 and n1~n3 are the coefficients to be fitted; (2) Establish the energy consumption model of boiler equipment, a. Establish an energy consumption model for a cooling tower. To build an energy consumption model for a cooling tower, it is necessary to solve the water temperature of the lower tower. The factors affecting the water temperature of the lower tower include the water temperature of the upper tower, the wet bulb temperature of the air, and the air flow rate in the cooling tower. Divide the heat exchange volume in the cooling tower into a number of small units and establish the heat transfer energy equation between air and water, as shown in formula (4): LC p dt=Gdh=K'a(h'-h a )dV, (4) Then, by integrating both sides of equation (4), we can obtain the heat transfer balance equation of the cooling tower as a whole, as shown in equations (5) and (6): The integral result of (5) is called the number of heat transfer units of the cooling tower. Substituting the calculated number of heat transfer units and the cooling tower model into the model, the water temperature of the lower tower can be obtained. Where a is the heat transfer area per unit volume of the cooling tower heat transfer part, C p is the specific heat capacity of water at constant pressure, G is the air flow rate in the cooling tower, h1 is the air enthalpy at the inlet of the cooling tower, h2 is the air enthalpy at the outlet of the cooling tower, h' is the air enthalpy at the same temperature as the cooling water, and h a is the enthalpy of air exchanging heat with cooling water, K' is the comprehensive heat transfer coefficient, L is the cooling water flow rate, t1 is the cooling water lower tower temperature, t2 is the cooling water upper tower temperature, and V is the volume of the heat transfer part of the cooling tower; b. Establish a boiler energy consumption model. Relying on thermal engineering theory, establish a complete mathematical energy consumption model, fit it with the actual operation data, obtain the correlation coefficient, and then obtain a mathematical model that can be used for actual calculations.

4. The method for energy-saving optimization of boiler cluster operating parameters according to claim 3 is characterized in that: The establishment of the boiler energy consumption model also includes simulating the operation of the boiler, using a large amount of simulation data and actual operation data for machine training, and using the machine training model to replace the mathematical energy consumption model.

5. The method for energy-saving optimization of boiler cluster operating parameters according to claim 4, characterized in that: The machine training is performed using a BP-neural network algorithm.

6. The method for energy-saving optimization of boiler cluster operating parameters according to claim 1, characterized in that: The process of searching for boundary conditions in the third step is as follows: determine the highest allowable boundary conditions based on the rated data of the boiler design and external pipe network factors, where the safety boundary conditions of the boiler include: the highest and lowest usage requirements of boiler pressure, medium inlet and outlet temperatures and fuel combustion rate factors under triple safety conditions; on this basis, simulate the boiler operation with reference to the boiler design materials, actual operating data and the current status of the boiler to obtain the theoretical value; and compare the simulation results with the actual data to finally obtain the safety boundary conditions for the boiler operation.

7. The method for energy-saving optimization of boiler cluster operating parameters according to claim 1, characterized in that: The specific steps of the third step are as follows: establish a boiler energy consumption objective function, take triple safety operation as boundary conditions, and use a genetic algorithm to find the optimal operating condition.

8. The method for energy-saving optimization of boiler cluster operating parameters according to claim 1, characterized in that: The specific steps of the fourth step are as follows: obtain the optimal operating conditions of various boiler clusters under different external conditions, and input them into the boiler cluster system for testing; substitute the test results into the boiler energy consumption model, and perform secondary correction on the coefficients in the model. This test is repeated many times until the error of the operating result is <5%.

Images