Machine and furnace coordinated control system and method, electronic equipment and storage medium

Abstract

The invention belongs to the technical field of machine furnace control, and discloses a machine furnace coordination control system and method, electronic equipment and a storage medium. The method comprises the steps of collecting machine-furnace characteristic parameters in real time; preprocessing the machine furnace characteristic parameters, and marking the machine furnace characteristic parameters as machine furnace processing parameters; obtaining a heat storage coefficient; predicting power data according to the turbine furnace processing parameters and the heat storage coefficient; calculating the energy conversion efficiency of the furnace according to the power data, and judging whether a low-efficiency instruction is generated or not; if the instruction with poor efficiency is generated, carrying out coordination control on machine furnace processing parameters; dynamic optimization of the energy conversion efficiency of the machine furnace is achieved, so that the overall energy utilization efficiency of the machine furnace system is effectively improved, the performance and the automation level of the machine furnace are improved, the machine furnace is in the optimal operation state, and the purposes of energy conservation and emission reduction are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of turbine and boiler control, and more specifically, to a turbine and boiler coordinated control system, method, electronic equipment and storage medium. Background Art

[0002] In modern industrial production and energy supply, efficient and stable production of electricity and heat is crucial. As the core equipment of power plants and cogeneration plants, the energy conversion efficiency and stability of the boiler (boiler-turbine) system directly affect the economy and reliability of the entire production system. Traditional boiler control systems usually adopt simple PID control strategies. Although they can meet basic operating requirements to a certain extent, they are unable to cope with complex and changing operating conditions and strict environmental protection requirements. With the advancement of technology, intelligent control technology and Internet of Things technology are gradually being applied to industrial production. Through real-time monitoring, data analysis and intelligent optimization control, the energy conversion efficiency and reliability of the boiler system can be significantly improved. Therefore, the development of a boiler-to-turbine coordinated control system based on intelligent perception and optimization control has become the key to improving the performance of the boiler system. The Chinese patent publication number CN115963725A discloses a control method for a boiler-turbines coordinated control system; the method comprises the following steps: (1) inputting set control parameters into a Bell-Astrom system fuzzy model to obtain model parameters; (2) optimizing the model parameters in step (1); (3) using a nonlinear robust model predictive controller and a drum boiler unit load controlled object to form a boiler-turbines coordinated control system; (4) controlling the boiler-turbines coordinated system through a state feedback controller and a predictive control algorithm of the controller; by using a nonlinear robust model predictive controller and a drum boiler unit load controlled object to form a coordinated control system, the dynamic performance of the multivariable system after decoupling can be effectively improved, while reducing the system adjustment time and overshoot, thereby improving the accuracy and timeliness of parameter adjustment during the operation of the boiler-turbines coordinated control system; The above technologies primarily focus on improving system dynamic performance and reducing overshoot during regulation time, but fail to address the control objective of improving boiler energy conversion efficiency. This efficiency varies with boiler operation, and failure to monitor and optimize it directly impacts power generation costs and economic benefits, making it difficult to meet actual production needs and ultimately achieving optimal boiler operation. In view of this, the present invention proposes a machine-boiler coordinated control system, method, electronic device and storage medium to solve the above problems. Summary of the Invention

[0003] In order to overcome the above-mentioned defects of the prior art and achieve the above-mentioned objectives, the present invention provides the following technical solutions: a method for coordinated control of a turbine and a boiler, comprising: Real-time collection of boiler characteristic parameters; Pre-process the boiler characteristic parameters and mark them as boiler processing parameters; Get the heat storage coefficient; Predict power data based on boiler processing parameters and heat storage coefficient; calculate the energy conversion efficiency of the boiler based on power data and determine whether to generate inefficient instructions; If poor efficiency instructions are generated, the machine and boiler processing parameters will be coordinated and controlled.

[0004] Furthermore, the turbine and boiler characteristic parameters include steam parameters, fuel parameters, air parameters, flue gas parameters and water side parameters; the turbine and boiler include boilers and steam turbines; The methods for preprocessing the characteristic parameters of the machine and boiler include: Calculate the mean and standard deviation of each parameter in the furnace characteristic parameters; Obtain the historical parameters corresponding to each parameter in the boiler characteristic parameters, and count the number of historical parameters of each parameter, where the historical parameters are the boiler characteristic parameters collected historically; add the corresponding historical parameters to each parameter in the real-time boiler characteristic parameters to obtain the total number of parameters of each parameter; add one to the number of historical parameters of each parameter to obtain the total number of parameters of each parameter; divide the total number of parameters of each parameter in the boiler characteristic parameters by the total number of corresponding parameters to obtain the average value of each parameter; Subtract the corresponding average value from the historical parameter corresponding to each parameter in the boiler characteristic parameters to obtain the historical parameter difference corresponding to each parameter; subtract the corresponding average value from each parameter in the real-time collected boiler characteristic parameters to obtain the real-time parameter difference of each parameter; add the squares of the historical parameter differences of each parameter in sequence, and then add the square of the real-time parameter difference to obtain the sum of the squares of each parameter; divide the sum of the squares of each parameter by the total number of corresponding parameters and then take the square root to obtain the standard deviation of each parameter; add and subtract three times the standard deviation from the average value of each parameter in the boiler characteristic parameters to obtain the corresponding parameter range ; , ; is the average value of the i-th parameter in the boiler characteristic parameters, is the standard deviation of the i-th parameter in the boiler characteristic parameters; Compare each parameter with the corresponding parameter range; if , If it is or, the corresponding parameter is marked as an abnormal parameter; if , the corresponding parameter will not be marked as an abnormal parameter; is the i-th parameter; The historical parameters corresponding to the abnormal parameters are fitted using a polynomial interpolation method to obtain a fitting curve. The values ​​of the abnormal parameters are re-obtained based on the fitting curve, and the corresponding abnormal parameters in the furnace characteristic parameters are replaced with the re-obtained values.

[0005] Furthermore, the steam parameters include steam pressure, steam temperature and steam flow; the steam pressure includes main steam pressure, drum pressure and regulating stage pressure; the fuel parameters include fuel flow, fuel calorific value and fuel temperature; the air parameters include air flow and air temperature; the flue gas parameters include flue gas flow, flue gas composition and flue gas temperature; the water side parameters include feed water flow, feed water temperature and feed water pressure; the heat storage coefficient includes the steam-water working medium heat storage coefficient and the pipe metal heat storage coefficient; The methods for obtaining the heat storage coefficient of steam-water working fluid include: Obtain the specific heat capacity of steam; perform weighted summation of the specific heat capacity of steam, steam temperature and main steam pressure to obtain the heat storage coefficient of the steam-water working medium; Methods for obtaining the heat storage coefficient of pipeline metal include: Collect d pipeline images, where d is the number of pipelines in the boiler. Identify each of the d pipeline images to obtain the corresponding pipeline material. Determine the specific heat capacity of the corresponding pipeline based on the pipeline material. Obtain the pipeline metal heat storage coefficient by performing a weighted summation of the pipeline specific heat capacity and the temperature and flow rate of the fluid inside the pipeline. Fluid temperatures include steam temperature, fuel temperature, air temperature, flue gas temperature, and feed water temperature. Fluid flow rates include steam flow, fuel flow, air flow, flue gas flow, and feed water flow.

[0006] Furthermore, the method of respectively identifying d pipeline images and obtaining corresponding pipeline materials includes: Use the trained material recognition model to identify the pipeline image and output the recognition result. The recognition result is the digital label corresponding to the pipeline material. The corresponding pipeline material is obtained according to the digital label corresponding to the pipeline material. The material recognition model training process includes: Pre-collection pipeline images, , annotate each pipeline image with the pipeline material; convert the pipeline materials into different digital labels; divide the annotated pipeline images into a training set and a test set; use the training set to train the material recognition model, and use the test set to test the material recognition model; preset an error threshold, and when the mean of the prediction errors of all pipeline images in the test set is less than the error threshold, output the material recognition model; the material recognition model is a convolutional neural network model.

[0007] Furthermore, the method for predicting power data includes: The boiler processing parameters and heat storage coefficient are used as analysis data, and the analysis data are respectively input into the trained power prediction model to predict the power data; the power prediction model includes an input prediction model and an output prediction model, and the output prediction model includes a first output model and a second output model; the power data includes boiler input power, boiler output power and turbine output power; among them, the input prediction model is used to predict boiler input power, the first output model is used to predict boiler output power, and the second output model is used to predict turbine output power.

[0008] Furthermore, the training process of the input prediction model includes: Collect e sets of analysis data corresponding to the boiler input power in advance, where e is an integer greater than 1, and convert the analysis data and the corresponding boiler input power into a corresponding set of feature vectors; Each set of feature vectors is used as input to an input prediction model. The input prediction model outputs a set of predicted boiler input powers corresponding to each set of analysis data, and uses the actual boiler input power corresponding to each set of analysis data as a prediction target. The actual boiler input power is the pre-collected boiler input power corresponding to the analysis data. The training objective is to minimize the sum of the prediction errors of all analysis data. The input prediction model is trained until the sum of the prediction errors reaches convergence. The input prediction model is a deep neural network model. The training process of the first output model and the second output model is consistent with the training process of the input prediction model, and both are deep neural network models.

[0009] Furthermore, the method for calculating the energy conversion efficiency of the furnace includes: The energy conversion efficiency of the boiler includes the energy conversion efficiency of the boiler and the energy conversion efficiency of the steam turbine; the energy conversion efficiency of the boiler The ratio of boiler output power to boiler input power; turbine energy conversion efficiency It is the ratio of turbine output power to boiler output power.

[0010] Furthermore, the method for determining whether an inefficient instruction is generated includes: Preset efficiency thresholds, including boiler efficiency thresholds and turbine efficiency threshold ; Set the boiler efficiency threshold and boiler energy conversion efficiency For comparison, the turbine efficiency threshold and steam turbine energy conversion efficiency Make a comparison; like , then generate inefficient instructions; like , If is and , then no inefficient instructions are generated.

[0011] Furthermore, the steps of coordinating and controlling the boiler processing parameters include: Step 1: Construct m traffic sets and obtain the corresponding set labels; Step 2: Encode the set labels, obtain chromosomes, and construct the initial population; Step 3: Determine the fitness function; Step 4: Natural selection of chromosomes in the population; Step 5: Perform crossover recombination on the chromosomes in the population; Step 6: Calculate the dynamic boundary, generate the reverse solution corresponding to each chromosome and add it to the population, and treat the reverse solution as a chromosome; Step 7: mutate the chromosomes in the population; Step 8: Screen the chromosomes in the population to obtain a new population; Step 9: Determine whether the new population satisfies the corresponding generation F or whether there is a chromosome with a fitness greater than S. If not, return to step 4. If satisfied, obtain the set label corresponding to the chromosome with the largest fitness in the new population, obtain the corresponding flow set according to the set label, and coordinate the fluid flow in the boiler processing parameters according to the flow set; where F is the preset population generation and S is the preset fitness threshold.

[0012] Furthermore, in step 1, a flow range is obtained, and the flow range includes a steam flow range, a fuel flow range, an air flow range, a flue gas flow range, and a water supply flow range; a value is randomly selected from each range in the flow range to construct a flow set, and a total of m flow sets are constructed, where m is an integer greater than 1, and the m flow sets are all different; different digital labels are set for the m flow sets, and are marked as set labels.

[0013] Furthermore, in step 2, the set label is encoded as X, where X is the chromosome, and the range of X is ; Randomly generate G chromosomes to form the initial population , .

[0014] Furthermore, in step 3, the fitness function is expressed as: ; Where, is the fitness corresponding to the I-th chromosome, is the regulatory effect corresponding to chromosome I, .

[0015] Furthermore, the method for obtaining the adjustment effect includes: The boiler energy conversion efficiency and the steam turbine energy conversion efficiency are added together to obtain the total efficiency; according to the set label corresponding to the i-th chromosome, the corresponding flow set is obtained, and the fluid flow in the boiler processing parameters in the analysis data is replaced with the flow set; the replaced analysis data are input into the power prediction model again to predict the power data and mark it as the new power data; the boiler energy conversion efficiency and the steam turbine energy conversion efficiency are recalculated according to the new power data; the recalculated boiler energy conversion efficiency and the steam turbine energy conversion efficiency are added together to obtain the new total efficiency; the new total efficiency is subtracted from the total efficiency to obtain the regulation effect.

[0016] Furthermore, in step 5, N chromosomes are randomly selected from the population for crossover recombination to obtain N new chromosomes; the crossover recombination adopts the PMX method; after the chromosome crossover recombination, the fitness of the N new chromosomes is calculated, and the fitness of the N new chromosomes and the fitness of the N chromosomes are sorted from large to small to generate a sorting table, and the N chromosomes in the sorting table are replaced in positive order with the N chromosomes that have undergone crossover recombination in the population.

[0017] Furthermore, in step 6, the dynamic boundary is , obtain the set label corresponding to the chromosome with the smallest fitness in the population and the set label corresponding to the chromosome with the largest fitness, and compare them. is a collection label with a smaller value, is a set label with a larger value; if the generated reverse solution is greater than or less than , it is marked as a transcendental solution, a random number function is used to randomly generate a value within the dynamic boundary, and the randomly generated value is assigned to the transcendental solution; Methods for generating inverse solutions include: ; Where, is the reverse solution of chromosome I, for The random number in is the set label of chromosome I; In step 7, the mutation includes common mutation and cloud adaptive mutation; when the number of generations corresponding to the population is less than When , or the fitness of the chromosome in the population is less than When the number of generations corresponding to the population is greater than or equal to And the fitness of the chromosome in the population is greater than or equal to When , common mutation is used; the common mutation method is: the mutation probability is preset to Y, and the G chromosomes in the population are mutated according to the mutation probability. The mutation method is to randomly select the positions of two genes in the chromosome and exchange the values ​​of the two genes; In step 8, all chromosomes in the population are sorted from large to small according to fitness, and the top G chromosomes are retained to form a new population.

[0018] Furthermore, the power loss value is calculated to calibrate the energy conversion efficiency of the steam turbine; Methods for calculating power loss values ​​include: Collect power impact data, including pipeline inner diameter, pipeline length, friction factor, temperature difference and pressure difference; The temperature difference is obtained by: collecting the turbine inlet temperature; subtracting the turbine inlet temperature from the steam temperature to obtain the temperature difference; The pressure difference is obtained by: collecting the turbine inlet pressure; subtracting the turbine inlet pressure from the main steam pressure to obtain the pressure difference; Calculate power loss value based on power impact data and steam flow rate; The expression for the power loss value is: ; Where, is the power loss value, is the friction factor, is the pipe length, is the steam flow rate, is the acceleration due to gravity, is the inner diameter of the pipe, is the temperature difference, is the pressure difference, 、 is the preset scale factor; is the boiler output power; The power loss value is subtracted from the boiler output power to obtain the turbine input power, and the turbine input power is divided by the turbine output power to obtain the calibrated turbine energy conversion efficiency.

[0019] A turbine and boiler coordinated control system, which implements the turbine and boiler coordinated control method, comprises: Parameter acquisition module, used to collect the characteristic parameters of the machine and furnace in real time; Parameter processing module, used to pre-process the boiler characteristic parameters and mark them as boiler processing parameters; Parameter acquisition module, used to obtain heat storage coefficient; The efficiency analysis module is used to predict power data based on the boiler processing parameters and heat storage coefficient; based on the power data, it calculates the energy conversion efficiency of the boiler and determines whether to generate a poor efficiency instruction; The coordination control module is used to coordinate and control the machine and boiler processing parameters if an instruction with poor efficiency is generated.

[0020] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, a method for coordinated control of a machine and a boiler is implemented.

[0021] A computer-readable storage medium stores a computer program, and when the computer program is executed, the machine-boiler coordinated control method is implemented.

[0022] The technical effects and advantages of the boiler-turbine coordinated control system, method, electronic device, and storage medium of the present invention are as follows: 1. By real-time acquisition and pre-processing of boiler and turbine characteristic parameters, combined with the heat storage characteristics of steam-water working fluids and pipeline metal, a machine learning model is established to predict the power input and output of boilers and turbines. Based on the calculated energy conversion efficiency, an improved genetic algorithm is used to automatically coordinate and control the fluid flow rate. This achieves dynamic optimization of the boiler and turbine energy conversion efficiency, thereby effectively improving the overall energy utilization efficiency of the boiler and turbine system, enhancing boiler performance and automation level, ensuring the boiler and turbine are in optimal operating state, and achieving energy conservation and emission reduction goals.

[0023] 2. By collecting data such as pipeline parameters, temperature and pressure differences, the power loss value caused by the pipeline system can be accurately calculated, thus avoiding the direct use of boiler output power as turbine input power. The turbine input power can be obtained more accurately to correct the turbine energy conversion efficiency; thereby more effectively monitoring and optimizing the coordinated operation of the turbine and boiler, improving the coordinated control effect of the turbine and boiler, and further achieving the optimal operation state of the turbine and boiler. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a schematic diagram of a boiler-turbine coordinated control system according to embodiment 1 of the present invention; Figure 2 This is a schematic diagram of a boiler-turbine coordinated control system according to embodiment 2 of the present invention; Figure 3 This is a flow chart of a boiler-turbine coordinated control method according to embodiment 3 of the present invention; Figure 4 This is a schematic diagram of an electronic device according to embodiment 4 of the present invention; Figure 5 This is a schematic diagram of the storage medium of Example 5 of the present invention. DETAILED DESCRIPTION

[0025] 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.

[0026] Example 1 See also Figure 1 As shown, the boiler coordinated control system described in this embodiment includes a parameter acquisition module, a parameter processing module, a parameter acquisition module, an efficiency analysis module and a coordinated control module; each module is connected by wired and / or wireless means to achieve data transmission between modules; Parameter acquisition module, used to collect machine and furnace characteristic parameters in real time.

[0027] The characteristic parameters of the turbine and boiler include steam parameters, fuel parameters, air parameters, flue gas parameters and water side parameters; the turbine and boiler include boilers and turbines.

[0028] Steam parameters include steam pressure, steam temperature and steam flow rate; Steam pressure includes main steam pressure, drum pressure and regulating stage pressure; main steam pressure is the steam pressure generated by the boiler, which is obtained by the pressure sensor installed in the boiler outlet pipe; drum pressure is the pressure inside the boiler drum, which is obtained by the pressure sensor installed in the drum; regulating stage pressure is the pressure of the turbine regulating stage, which is obtained by the pressure sensor installed in the regulating stage inlet pipe; steam temperature is the temperature of the steam generated by the boiler, which is obtained by the temperature sensor installed in the boiler outlet pipe; steam flow is the flow of steam generated by the boiler, which is obtained by the flow meter installed in the boiler outlet pipe.

[0029] Fuel parameters include fuel flow, fuel calorific value and fuel temperature; fuel is the fuel input into the boiler; the fuel flow is obtained by a flow meter installed in the fuel supply pipeline; the fuel calorific value is the energy released when the fuel is completely burned, which is obtained in advance by technical personnel in this field using a calorific value meter; the fuel temperature is obtained by a temperature sensor installed in the fuel supply pipeline.

[0030] Air parameters include air flow and air temperature; air is the air input to the boiler; the air flow is obtained by a flow meter installed in the air preheater inlet pipe; the air temperature is obtained by a temperature sensor installed in the air preheater inlet pipe.

[0031] The flue gas parameters include flue gas flow, flue gas composition and flue gas temperature; the flue gas is the flue gas discharged from the boiler; the flue gas flow is obtained by a flow meter installed at the boiler flue outlet; the flue gas composition is obtained by a flue gas analyzer installed at the boiler flue outlet; and the flue gas temperature is obtained by a temperature sensor installed at the boiler flue outlet.

[0032] The water side parameters include water flow, water temperature and water pressure; the water flow is obtained by a flow meter installed in the water supply pipeline; the water temperature is obtained by a temperature sensor installed in the water supply pipeline; and the water pressure is obtained by a pressure sensor installed in the water supply pipeline.

[0033] It should be noted that the boiler and turbine characteristic parameters are used to reflect the input power of the boiler and steam turbine, and can evaluate the operating status of the boiler and steam turbine, analyze the energy conversion efficiency of the boiler and steam turbine, facilitate the subsequent coordinated control of the boiler and turbine, and facilitate the dynamic optimization of the control strategy to improve the energy conversion efficiency of the boiler and turbine. The parameter processing module is used to pre-process the machine and boiler characteristic parameters and mark them as machine and boiler processing parameters.

[0034] The methods for preprocessing the characteristic parameters of the machine and boiler include: Calculate the mean and standard deviation of each parameter in the furnace characteristic parameters; The expression for the mean value is: Where, is the average value of the i-th parameter in the boiler characteristic parameters, is the first parameter corresponding to the Historical parameters, is the i-th parameter, , , b is the number of historical parameters corresponding to each parameter, and the historical parameters are the boiler characteristic parameters collected historically; The expression for standard deviation is: Where, is the standard deviation of the i-th parameter in the boiler characteristic parameters.

[0035] Add and subtract three times the standard deviation from the average value of each parameter in the boiler characteristic parameters to obtain the corresponding parameter range ; , .

[0036] Compare each parameter with the corresponding parameter range; if , If it is or, the corresponding parameter is marked as an abnormal parameter; if , the corresponding parameter is not marked as an abnormal parameter.

[0037] The historical parameters corresponding to the abnormal parameters are fitted using polynomial interpolation method (such as Lagrange interpolation method, Newton interpolation method, etc.) to obtain a fitting curve. The values ​​of the abnormal parameters are re-obtained according to the fitting curve, and the corresponding abnormal parameters in the furnace characteristic parameters are replaced with the re-obtained values.

[0038] The parameter acquisition module is used to obtain the heat storage coefficient.

[0039] The heat storage coefficient includes the heat storage coefficient of steam-water working medium and the heat storage coefficient of pipe metal; The methods for obtaining the heat storage coefficient of steam-water working fluid include: Obtain the specific heat capacity of steam, which can be obtained from a saturated steam thermophysical property table (such as the ASME steam performance table, VDI thermodynamic table, etc.). Calculate the heat storage coefficient of the steam-water working medium based on the steam specific heat capacity, steam temperature, and main steam pressure. The expression for the heat storage coefficient of the steam-water working medium is: Where, is the heat storage coefficient of steam-water working fluid, is the steam temperature, is the main steam pressure, is the specific heat capacity of steam, 、 is the preset scale factor.

[0040] It should be noted that the specific value of the proportional coefficient in the formula can be set according to actual conditions. The proportional coefficient reflects the degree of influence of the steam temperature and the main steam pressure on the specific heat capacity of steam. Those skilled in the art can preset the corresponding proportional coefficient according to the actual degree of influence of the steam temperature and the main steam pressure on the specific heat capacity of steam, so as to accurately evaluate the specific heat capacity of steam under the influence of steam temperature and steam pressure; the heat storage coefficient of the steam-water working medium is the specific heat capacity of steam under the influence of steam temperature and main steam pressure, so the steam temperature and main steam pressure in the calculation process of the heat storage coefficient of the steam-water working medium are both dimensionless values.

[0041] Methods for obtaining the heat storage coefficient of pipeline metal include: Collect d pipeline images, where d is the number of pipelines in the boiler. The pipeline images are acquired by an image sensor installed in each pipeline. Each of the d pipeline images is identified to determine the corresponding pipeline material. The corresponding pipeline specific heat capacity is obtained from a metal thermal property table (such as MatWeb or NIST). The pipeline metal heat storage coefficient is calculated based on the pipeline specific heat capacity and the temperature and flow rate of the fluid inside the pipeline. The expression for the pipeline metal heat storage coefficient is: Where, is the metal heat storage coefficient of the jth pipe, is the fluid temperature corresponding to the jth pipe, is the fluid flow rate corresponding to the j-th pipe, , 、 is the preset weight coefficient; fluid temperature includes steam temperature, fuel temperature, air temperature, flue gas temperature and feed water temperature; fluid flow includes steam flow, fuel flow, air flow, flue gas flow and feed water flow; obtain the corresponding temperature and flow according to the specific fluid in the pipeline.

[0042] It should be noted that the specific value of the weight coefficient in the formula can be set according to actual conditions. The weight coefficient reflects the degree of influence of the fluid temperature and fluid flow in the pipeline on the specific heat capacity of the pipeline. Technical personnel in this field can preset the corresponding weight coefficient according to the actual degree of influence of the fluid temperature and fluid flow in the pipeline on the specific heat capacity of the pipeline, so as to accurately evaluate the specific heat capacity of the pipeline under the influence of the fluid temperature and fluid flow in the pipeline; the pipeline metal heat storage coefficient is the specific heat capacity of the pipeline under the influence of the fluid temperature and fluid flow in the pipeline, so the fluid temperature and fluid flow in the calculation process of the pipeline metal heat storage coefficient are both dimensionless values.

[0043] The method of identifying d pipeline images and obtaining the corresponding pipeline materials includes: Use the trained material recognition model to identify the pipeline image and output the recognition result. The recognition result is the digital label corresponding to the pipeline material. According to the digital label corresponding to the pipeline material, the corresponding pipeline material is obtained. Pipeline materials such as carbon steel, alloy steel, stainless steel, etc.

[0044] The specific training process of the material recognition model includes: Pre-collection pipeline images, , annotate each pipeline image with the pipeline material; convert the pipeline materials into different digital labels, for example, convert carbon steel into 1, alloy steel into 2, and stainless steel into 3; divide the annotated pipeline images into training sets and test sets, with 70% of the pipeline images as the training set and 30% of the pipeline images as the test set; use the training set to train the material recognition model, and use the test set to test the material recognition model; preset an error threshold, and when the mean of the prediction errors of all pipeline images in the test set is less than the error threshold, output the material recognition model; the calculation formula for the mean prediction error is: ,in is the prediction error, is the number of the pipeline image, For the The predicted annotations corresponding to the group pipeline images, For the The actual annotations corresponding to the group of pipeline images are represented by U, where U is the number of pipeline images in the test set. The error threshold is pre-set according to the accuracy required by the material recognition model. The material recognition model is specifically a convolutional neural network model.

[0045] It should be understood that obtaining the heat storage coefficient of the steam-water working fluid and the heat storage coefficient of the pipeline metal can accurately predict the dynamic response characteristics of the boiler and provide a basis for power prediction and regulation strategy optimization.

[0046] The efficiency analysis module is used to predict power data based on the boiler processing parameters and heat storage coefficient; based on the power data, calculate the energy conversion efficiency of the boiler and determine whether to generate a poor efficiency instruction.

[0047] Methods for predicting power data include: The boiler processing parameters and heat storage coefficient are used as analysis data, and the analysis data are respectively input into the trained power prediction model to predict the power data; the power prediction model includes an input prediction model and an output prediction model, and the output prediction model includes a first output model and a second output model; the power data includes boiler input power, boiler output power and turbine output power; among them, the input prediction model is used to predict boiler input power, the first output model is used to predict boiler output power, and the second output model is used to predict turbine output power.

[0048] The training process of the input prediction model includes: Pre-collect e groups of analysis data corresponding to the boiler input power, where e is an integer greater than 1, and convert the analysis data and the corresponding boiler input power into a corresponding set of feature vectors; the boiler input power corresponding to the analysis data is obtained by a person skilled in the art by collecting e groups of analysis data during the historical operation of the boiler, and respectively analyzing and obtaining the corresponding boiler input power under the conditions of the e groups of analysis data, and then sequentially setting the corresponding boiler input power for the e groups of analysis data; Each set of feature vectors is used as the input of the input prediction model. The input prediction model takes a set of predicted boiler input power corresponding to each set of analysis data as the output, and takes the actual boiler input power corresponding to each set of analysis data as the prediction target. The actual boiler input power is the boiler input power corresponding to the analysis data collected in advance. The training goal is to minimize the sum of the prediction errors of all analysis data. The calculation formula of the prediction error is: ,in is the prediction error, is the group number of the eigenvector corresponding to the analysis data, For the The predicted boiler input power corresponding to the group analysis data, For the The actual boiler input power corresponding to the group analysis data is trained on the input prediction model until the sum of the prediction errors reaches convergence.

[0049] The above-mentioned input prediction model is specifically a deep neural network model; it includes an input layer, a hidden layer and an output layer; each hidden layer includes multiple neurons, each neuron is connected to the neurons in the next layer, and the connection contains weights, which determine the importance and influence of data transmission in the neural network; each neuron between the hidden layer and the output layer applies an activation function, which maps nonlinearity, allowing the network to learn more complex patterns and features.

[0050] The specific training process of the first output model and the second output model is consistent with the training process of the input prediction model, and they are also deep neural network models.

[0051] Methods for calculating the energy conversion efficiency of a furnace include: The energy conversion efficiency of boilers and steam turbines includes the energy conversion efficiency of boilers and steam turbines; The expression of boiler energy conversion efficiency is: ; Where, is the boiler energy conversion efficiency, is the boiler output power, Input power to the boiler.

[0052] The expression of steam turbine energy conversion efficiency is: ; Where, is the energy conversion efficiency of the steam turbine, is the turbine output power, is the boiler output power.

[0053] Methods for determining whether inefficient instructions are generated include: Preset efficiency thresholds, including boiler efficiency thresholds and turbine efficiency threshold ; Set the boiler efficiency threshold and boiler energy conversion efficiency For comparison, the turbine efficiency threshold and steam turbine energy conversion efficiency Make a comparison; like , then a poor efficiency instruction is generated, indicating that the energy conversion efficiency of the boiler or steam turbine is low, which will increase energy consumption and reduce the stability of boiler operation. Coordinated control is needed to improve the energy conversion efficiency of the boiler or steam turbine; like , If and , no poor efficiency instruction is generated, indicating that the energy conversion efficiencies of the boiler and turbine are both at normal levels and no coordinated control is required.

[0054] The coordination control module is used to coordinate and control the machine and boiler processing parameters if an instruction with poor efficiency is generated.

[0055] The steps for coordinated control of boiler processing parameters include: Step 1: Construct m traffic sets and obtain the corresponding set labels.

[0056] Step 2: Encode the collection labels, obtain chromosomes, and construct the initial population.

[0057] Step 3: Determine the fitness function.

[0058] Step 4: Natural selection occurs on the chromosomes in the population.

[0059] Step 5: Perform crossover recombination on the chromosomes in the population.

[0060] Step 6: Calculate the dynamic boundary, generate the reverse solution corresponding to each chromosome and add it to the population, and treat the reverse solution as a chromosome.

[0061] Step 7: Mutate the chromosomes in the population.

[0062] Step 8: Screen the chromosomes in the population to obtain a new population.

[0063] Step 9: Determine whether the new population satisfies the corresponding generation F or whether there is a chromosome with a fitness greater than S. If not, return to step 4. If satisfied, obtain the set label corresponding to the chromosome with the largest fitness in the new population, obtain the corresponding flow set according to the set label, and coordinate the fluid flow in the boiler processing parameters according to the flow set; wherein F is the preset population generation, and S is the preset fitness threshold; illustratively, if the preset population generation is 1, the chromosomes in the initial population are subjected to natural selection, crossover recombination, reverse solution calculation and mutation to obtain a new population. At this time, the generation corresponding to the new population is 1, so the loop ends.

[0064] In the above step 1, the flow range is obtained, and the flow range includes the steam flow range, the fuel flow range, the air flow range, the flue gas flow range and the feed water flow range; the flow range is obtained according to the equipment manual or technical parameter table provided by the boiler manufacturer; a value is randomly selected from each range in the flow range to construct a flow set, and a total of m flow sets are constructed, where m is an integer greater than 1, and the m flow sets are all different; different digital labels are set for the m flow sets and marked as set labels.

[0065] In step 2 above, the set label is encoded as X, where X is the chromosome and the range of X is ; Randomly generate G chromosomes to form the initial population , .

[0066] In step 3 above, the fitness function is expressed as: ; Where, is the fitness corresponding to the I-th chromosome, is the regulatory effect corresponding to chromosome I, .

[0067] Methods for obtaining adjustment effects include: Add the boiler energy conversion efficiency and the turbine energy conversion efficiency to obtain the total efficiency; According to the set label corresponding to the i-th chromosome, the corresponding flow set is obtained, and the fluid flow in the boiler processing parameters in the analysis data is replaced with the flow set; the replaced analysis data are input into the power prediction model again to predict the power data and mark it as the new power data; the boiler energy conversion efficiency and the turbine energy conversion efficiency are recalculated according to the new power data; the recalculated boiler energy conversion efficiency and the turbine energy conversion efficiency are added together to obtain the new total efficiency; the new total efficiency is subtracted from the total efficiency to obtain the regulation effect.

[0068] In step 4 above, natural selection is carried out by combining the elite method and the rotation method; the elite method produces For a population with a capacity of G, the fitness of the G chromosomes is arranged from large to small, and the one at the front is Each chromosome produces one offspring chromosome; the rotation method produces offspring chromosomes, that is, G chromosomes are generated according to the corresponding rotation probability offspring chromosomes; , in order to keep the offspring population capacity G unchanged and the population increases exponentially.

[0069] The expression of rotation probability is: ; Where, is the rotation probability corresponding to the I-th chromosome.

[0070] In the above step 5, N chromosomes are randomly selected from the population for crossover recombination to obtain N new chromosomes; the crossover recombination adopts the PMX method, which is a prior art method and will not be described in detail here; after the chromosome crossover recombination, the fitness of the N new chromosomes is calculated, and the fitness of the N new chromosomes and the fitness of the N chromosomes are sorted from large to small to generate a sorting table, and the N chromosomes in the sorting table are replaced in positive order with the N chromosomes in the population for crossover recombination; this embodiment is preferred If the calculated U is not an integer, round N up to ensure that the calculated N is an integer.

[0071] In step 6 above, the dynamic boundary is , obtain the set label corresponding to the chromosome with the smallest fitness in the population and the set label corresponding to the chromosome with the largest fitness, and compare them. is a collection label with a smaller value, is the collection label with the larger value.

[0072] Methods for generating inverse solutions include: ; Where, is the reverse solution of chromosome I, for The random number in is the set label of chromosome I.

[0073] If the generated inverse solution is greater than or less than , it is marked as a transcendental solution, a random number function is used to randomly generate a value within the dynamic boundary, and the randomly generated value is assigned to the transcendental solution.

[0074] In the above step 7, mutation includes common mutation and cloud adaptive mutation; when the number of generations corresponding to the population is less than When , or the fitness of the chromosome in the population is less than When the number of generations corresponding to the population is greater than or equal to And the fitness of the chromosome in the population is greater than or equal to When , common mutation is used; Cloud adaptive mutation is an existing technology and will not be described in detail here. The method of ordinary mutation is: the mutation probability is preset to Y, and G chromosomes in the population are mutated according to the mutation probability. The mutation method is to randomly select the positions of two genes in the chromosome and exchange the values ​​of the two genes. In this embodiment, Y is preferably 0.02. The mutation probability is preset by those skilled in the art based on algorithm efficiency and algorithm accuracy. It should be understood that the purpose of combining ordinary mutation with cloud adaptive mutation is that cloud adaptive mutation can adaptively adjust the mutation probability according to the dynamic situation of the evolutionary process, can dynamically perceive and adapt to the characteristics of the problem, adopt different mutation intensities at different stages, and use it in the early stage of the algorithm to expand the exploration solution space. In contrast, the mutation probability in ordinary mutation is fixed, and use it in the later stage of the algorithm to accelerate convergence, improve computational efficiency, increase the probability of the algorithm finding the global optimal solution, and improve the quality of the final solution.

[0075] In the above step 8, all chromosomes in the population are sorted from large to small according to fitness, and the top G chromosomes are retained to form a new population.

[0076] It should be noted that the fitness threshold S is preset by those skilled in the art based on the accuracy of the algorithm, and the population generation F is obtained by those skilled in the art using a genetic algorithm multiple times under multiple sets of different test data conditions to obtain the corresponding set labels. In each process of using the genetic algorithm, when the fitness corresponding to the chromosome in the new population is greater than or equal to the fitness threshold S, the loop ends and the generation corresponding to the new population is obtained; the largest generation among the multiple generations is taken as the population generation F.

[0077] This embodiment establishes a machine learning model to predict the power input and output of the boiler and steam turbine by real-time acquisition and pre-processing of boiler characteristic parameters, combined with the heat storage characteristics of steam-water working fluid and pipeline metal; and automatically coordinates and controls the fluid flow rate based on the calculated energy conversion efficiency using an improved genetic algorithm; thus achieving dynamic optimization of the boiler energy conversion efficiency, thereby effectively improving the overall energy utilization efficiency of the boiler system, enhancing the boiler performance and automation level, ensuring that the boiler is in the optimal operating state, and achieving the goals of energy conservation and emission reduction.

[0078] Example 2 See also Figure 2As shown, this embodiment further improves the design on the basis of Example 1. In Example 1, when calculating the turbine energy conversion efficiency, the boiler output power is used as the turbine input power. However, in actual conditions, due to the influence of pipeline friction and the influence of changes in steam temperature and steam pressure, the turbine input power may be lower than the boiler output power. If the boiler output power is directly used as the turbine input power, the calculated turbine energy conversion efficiency will be too low, thereby affecting the coordinated control effect of the turbine and boiler. Therefore, this embodiment provides a turbine-boiler coordinated control system, which also includes an efficiency calibration module.

[0079] The efficiency calibration module is used to calculate the power loss value and calibrate the energy conversion efficiency of the steam turbine.

[0080] Methods for calculating power loss values ​​include: Collect power impact data, including pipeline inner diameter, pipeline length, friction factor, temperature difference, and pressure difference. Pipeline inner diameter and length are measured by technicians before the boiler is operational, and neither of these values ​​changes. The friction factor is determined based on the pipeline material using pipeline system simulation and analysis software tools (such as PIPE-FLO). The temperature difference is obtained by collecting the turbine inlet temperature, which is obtained by a temperature sensor installed in the turbine inlet pipe; subtracting the turbine inlet temperature from the steam temperature to obtain the temperature difference; The pressure difference is obtained by collecting the turbine inlet pressure, which is obtained by a pressure sensor installed in the turbine inlet pipe; subtracting the turbine inlet pressure from the main steam pressure to obtain the pressure difference; Calculate power loss value based on power impact data and steam flow rate; The expression for the power loss value is: ; Where, is the power loss value, is the friction factor, is the pipe length, is the steam flow rate, is the acceleration due to gravity, is the inner diameter of the pipe, is the temperature difference, is the pressure difference, 、 is the preset scale factor.

[0081] It should be noted that the specific value of the proportional factor in the formula can be set according to actual conditions. The proportional factor reflects the degree of influence of the power impact data and steam flow on the boiler output power. Those skilled in the art can preset the corresponding proportional factor based on the actual degree of influence of the power impact data and steam flow on the boiler output power, so as to accurately evaluate the loss value of the boiler output power under the influence of the power impact data and steam flow; the power impact data and steam flow in the power loss value calculation process are both dimensionless values.

[0082] It should be understood that both power impact data and steam flow rate will affect the boiler output power. Among them, the greater the friction factor and length of the pipeline, as well as the steam flow rate, the greater the friction loss will be, and the greater the loss of boiler output power will be, and vice versa; the larger the inner diameter of the pipeline, the smaller the friction loss will be, and the smaller the loss of boiler output power will be, and vice versa; the greater the temperature difference and pressure difference, the faster the steam flow rate will be, and thus the greater the loss of boiler output power, and vice versa.

[0083] Subtract the power loss value from the boiler output power to obtain the turbine input power, and divide the turbine input power by the turbine output power to obtain the calibrated turbine energy conversion efficiency; This embodiment collects data such as pipeline parameters, temperature and pressure differences, and accurately calculates the power loss value caused by the pipeline system, thereby avoiding directly using the boiler output power as the turbine input power. The turbine input power can be obtained more accurately to correct the turbine energy conversion efficiency; thereby more effectively monitoring and optimizing the coordinated operation of the turbine and boiler, improving the coordinated control effect of the turbine and boiler, and further achieving the optimal operation state of the turbine and boiler.

[0084] Example 3 See also Figure 3 As shown, for the parts not described in detail in this embodiment, please refer to the description of embodiment 1 and embodiment 2. A method for coordinated control of a turbine and a boiler is provided, the method comprising: Real-time collection of boiler characteristic parameters; Pre-process the boiler characteristic parameters and mark them as boiler processing parameters; Get the heat storage coefficient; Predict power data based on boiler processing parameters and heat storage coefficient; calculate the energy conversion efficiency of the boiler based on power data and determine whether to generate inefficient instructions; If poor efficiency instructions are generated, the machine and boiler processing parameters will be coordinated and controlled.

[0085] Furthermore, the turbine and boiler characteristic parameters include steam parameters, fuel parameters, air parameters, flue gas parameters and water side parameters; the turbine and boiler include boilers and steam turbines; The methods for preprocessing the characteristic parameters of the machine and boiler include: Calculate the mean and standard deviation of each parameter in the furnace characteristic parameters; Obtain the historical parameters corresponding to each parameter in the boiler characteristic parameters, and count the number of historical parameters of each parameter, where the historical parameters are the boiler characteristic parameters collected historically; add the corresponding historical parameters to each parameter in the real-time boiler characteristic parameters to obtain the total number of parameters of each parameter; add one to the number of historical parameters of each parameter to obtain the total number of parameters of each parameter; divide the total number of parameters of each parameter in the boiler characteristic parameters by the total number of corresponding parameters to obtain the average value of each parameter; Subtract the corresponding average value from the historical parameter corresponding to each parameter in the boiler characteristic parameters to obtain the historical parameter difference corresponding to each parameter; subtract the corresponding average value from each parameter in the real-time collected boiler characteristic parameters to obtain the real-time parameter difference of each parameter; add the squares of the historical parameter differences of each parameter in sequence, and then add the square of the real-time parameter difference to obtain the sum of the squares of each parameter; divide the sum of the squares of each parameter by the total number of corresponding parameters and then take the square root to obtain the standard deviation of each parameter; add and subtract three times the standard deviation from the average value of each parameter in the boiler characteristic parameters to obtain the corresponding parameter range ; , ; Compare each parameter with the corresponding parameter range; if , If it is or, the corresponding parameter is marked as an abnormal parameter; if , the corresponding parameter will not be marked as an abnormal parameter; The historical parameters corresponding to the abnormal parameters are fitted using a polynomial interpolation method to obtain a fitting curve. The values ​​of the abnormal parameters are re-obtained based on the fitting curve, and the corresponding abnormal parameters in the furnace characteristic parameters are replaced with the re-obtained values.

[0086] Furthermore, the steam parameters include steam pressure, steam temperature and steam flow; the steam pressure includes main steam pressure, drum pressure and regulating stage pressure; the fuel parameters include fuel flow, fuel calorific value and fuel temperature; the air parameters include air flow and air temperature; the flue gas parameters include flue gas flow, flue gas composition and flue gas temperature; the water side parameters include feed water flow, feed water temperature and feed water pressure; the heat storage coefficient includes the steam-water working medium heat storage coefficient and the pipe metal heat storage coefficient; The methods for obtaining the heat storage coefficient of steam-water working fluid include: Obtain the specific heat capacity of steam; perform weighted summation of the specific heat capacity of steam, steam temperature and main steam pressure to obtain the heat storage coefficient of the steam-water working medium; Methods for obtaining the heat storage coefficient of pipeline metal include: Collect d pipeline images, where d is the number of pipelines in the boiler. Identify each of the d pipeline images to obtain the corresponding pipeline material. Determine the specific heat capacity of the corresponding pipeline based on the pipeline material. Obtain the pipeline metal heat storage coefficient by performing a weighted summation of the pipeline specific heat capacity and the temperature and flow rate of the fluid inside the pipeline. Fluid temperatures include steam temperature, fuel temperature, air temperature, flue gas temperature, and feed water temperature. Fluid flow rates include steam flow, fuel flow, air flow, flue gas flow, and feed water flow.

[0087] Furthermore, the method of respectively identifying d pipeline images and obtaining corresponding pipeline materials includes: Use the trained material recognition model to identify the pipeline image and output the recognition result. The recognition result is the digital label corresponding to the pipeline material. The corresponding pipeline material is obtained according to the digital label corresponding to the pipeline material. The material recognition model training process includes: Pre-collection pipeline images, , annotate each pipeline image with the pipeline material; convert the pipeline materials into different digital labels; divide the annotated pipeline images into a training set and a test set; use the training set to train the material recognition model, and use the test set to test the material recognition model; preset an error threshold, and when the mean of the prediction errors of all pipeline images in the test set is less than the error threshold, output the material recognition model; the material recognition model is a convolutional neural network model.

[0088] Furthermore, the method for predicting power data includes: The boiler processing parameters and heat storage coefficient are used as analysis data, and the analysis data are respectively input into the trained power prediction model to predict the power data; the power prediction model includes an input prediction model and an output prediction model, and the output prediction model includes a first output model and a second output model; the power data includes boiler input power, boiler output power and turbine output power; among them, the input prediction model is used to predict boiler input power, the first output model is used to predict boiler output power, and the second output model is used to predict turbine output power.

[0089] Furthermore, the training process of the input prediction model includes: Collect e sets of analysis data corresponding to the boiler input power in advance, where e is an integer greater than 1, and convert the analysis data and the corresponding boiler input power into a corresponding set of feature vectors; Each set of feature vectors is used as input to an input prediction model. The input prediction model outputs a set of predicted boiler input powers corresponding to each set of analysis data, and uses the actual boiler input power corresponding to each set of analysis data as a prediction target. The actual boiler input power is the pre-collected boiler input power corresponding to the analysis data. The training objective is to minimize the sum of the prediction errors of all analysis data. The input prediction model is trained until the sum of the prediction errors reaches convergence. The input prediction model is a deep neural network model. The training process of the first output model and the second output model is consistent with the training process of the input prediction model, and both are deep neural network models.

[0090] Furthermore, the method for calculating the energy conversion efficiency of the furnace includes: The energy conversion efficiency of the boiler includes the energy conversion efficiency of the boiler and the energy conversion efficiency of the steam turbine; the energy conversion efficiency of the boiler The ratio of boiler output power to boiler input power; turbine energy conversion efficiency It is the ratio of turbine output power to boiler output power.

[0091] Furthermore, the method for determining whether an inefficient instruction is generated includes: Preset efficiency thresholds, including boiler efficiency thresholds and turbine efficiency threshold ; Set the boiler efficiency threshold and boiler energy conversion efficiency For comparison, the turbine efficiency threshold and steam turbine energy conversion efficiency Make a comparison; like , then generate inefficient instructions; like , If is and , then no inefficient instructions are generated.

[0092] Furthermore, the steps of coordinating and controlling the boiler processing parameters include: Step 1: Construct m traffic sets and obtain the corresponding set labels; Step 2: Encode the set labels, obtain chromosomes, and construct the initial population; Step 3: Determine the fitness function; Step 4: Natural selection of chromosomes in the population; Step 5: Perform crossover recombination on the chromosomes in the population; Step 6: Calculate the dynamic boundary, generate the reverse solution corresponding to each chromosome and add it to the population, and treat the reverse solution as a chromosome; Step 7: mutate the chromosomes in the population; Step 8: Screen the chromosomes in the population to obtain a new population; Step 9: Determine whether the new population satisfies the corresponding generation F or whether there is a chromosome with a fitness greater than S. If not, return to step 4. If satisfied, obtain the set label corresponding to the chromosome with the largest fitness in the new population, obtain the corresponding flow set according to the set label, and coordinate the fluid flow in the boiler processing parameters according to the flow set; where F is the preset population generation and S is the preset fitness threshold.

[0093] Furthermore, in step 1, a flow range is obtained, and the flow range includes a steam flow range, a fuel flow range, an air flow range, a flue gas flow range, and a water supply flow range; a value is randomly selected from each range in the flow range to construct a flow set, and a total of m flow sets are constructed, where m is an integer greater than 1, and the m flow sets are all different; different digital labels are set for the m flow sets, and are marked as set labels.

[0094] Furthermore, in step 2, the set label is encoded as X, where X is the chromosome, and the range of X is ; Randomly generate G chromosomes to form the initial population , .

[0095] Furthermore, in step 3, the fitness function is expressed as: ; Where, is the fitness corresponding to the I-th chromosome, is the regulatory effect corresponding to chromosome I, .

[0096] Furthermore, the method for obtaining the adjustment effect includes: The boiler energy conversion efficiency and the steam turbine energy conversion efficiency are added together to obtain the total efficiency; according to the set label corresponding to the i-th chromosome, the corresponding flow set is obtained, and the fluid flow in the boiler processing parameters in the analysis data is replaced with the flow set; the replaced analysis data are input into the power prediction model again to predict the power data and mark it as the new power data; the boiler energy conversion efficiency and the steam turbine energy conversion efficiency are recalculated according to the new power data; the recalculated boiler energy conversion efficiency and the steam turbine energy conversion efficiency are added together to obtain the new total efficiency; the new total efficiency is subtracted from the total efficiency to obtain the regulation effect.

[0097] Furthermore, in step 5, N chromosomes are randomly selected from the population for crossover recombination to obtain N new chromosomes; the crossover recombination adopts the PMX method; after the chromosome crossover recombination, the fitness of the N new chromosomes is calculated, and the fitness of the N new chromosomes and the fitness of the N chromosomes are sorted from large to small to generate a sorting table, and the N chromosomes in the sorting table are replaced in positive order with the N chromosomes that have undergone crossover recombination in the population.

[0098] Furthermore, in step 6, the dynamic boundary is , obtain the set label corresponding to the chromosome with the smallest fitness in the population and the set label corresponding to the chromosome with the largest fitness, and compare them. is a collection label with a smaller value, is a set label with a larger value; if the generated reverse solution is greater than or less than , it is marked as a transcendental solution, a random number function is used to randomly generate a value within the dynamic boundary, and the randomly generated value is assigned to the transcendental solution; Methods for generating inverse solutions include: ; Where, is the reverse solution of chromosome I, for The random number in is the set label of chromosome I; In step 7, the mutation includes common mutation and cloud adaptive mutation; when the number of generations corresponding to the population is less than When , or the fitness of the chromosome in the population is less than When the number of generations corresponding to the population is greater than or equal to And the fitness of the chromosome in the population is greater than or equal to When , common mutation is used; the common mutation method is: the mutation probability is preset to Y, and the G chromosomes in the population are mutated according to the mutation probability. The mutation method is to randomly select the positions of two genes in the chromosome and exchange the values ​​of the two genes; In step 8, all chromosomes in the population are sorted from large to small according to fitness, and the top G chromosomes are retained to form a new population.

[0099] Furthermore, the power loss value is calculated to calibrate the energy conversion efficiency of the steam turbine; Methods for calculating power loss values ​​include: Collect power impact data, including pipeline inner diameter, pipeline length, friction factor, temperature difference and pressure difference; The temperature difference is obtained by: collecting the turbine inlet temperature; subtracting the turbine inlet temperature from the steam temperature to obtain the temperature difference; The pressure difference is obtained by: collecting the turbine inlet pressure; subtracting the turbine inlet pressure from the main steam pressure to obtain the pressure difference; Calculate power loss value based on power impact data and steam flow rate; The expression for the power loss value is: ; Where, is the power loss value, is the friction factor, is the pipe length, is the steam flow rate, is the acceleration due to gravity, is the inner diameter of the pipe, is the temperature difference, is the pressure difference, 、 is the preset scale factor; The power loss value is subtracted from the boiler output power to obtain the turbine input power, and the turbine input power is divided by the turbine output power to obtain the calibrated turbine energy conversion efficiency.

[0100] Example 4 See also Figure 4 As shown, the present application also provides an electronic device 500. The electronic device 500 may include one or more processors and one or more memories. The memories may store computer-readable code, which, when executed by the one or more processors, may execute the above-described method for coordinated control of a turbine and a boiler.

[0101] The method or system according to the embodiment of the present application can also be used by Figure 4 The electronic device architecture shown in FIG. Figure 4 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, ROM 503, RAM 504, a communication port 505 connected to a network, an input / output 506, a hard disk 507, etc. The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, may store a method for coordinated control of a machine and a boiler provided in this application. Furthermore, the electronic device 500 may also include a user interface 508. Of course, Figure 4 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 4 One or more components of an electronic device are shown.

[0102] Example 5 See also Figure 5As shown, one embodiment of the present application discloses a computer-readable storage medium 600. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are executed by a processor, a method for coordinated control of a turbine and a boiler according to an embodiment of the present application described with reference to the above figures can be executed. The storage medium 600 includes, but is not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory. Non-volatile memory may include, for example, read-only memory (ROM), a hard disk, flash memory, etc.

[0103] Furthermore, according to embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the present application provides a non-transitory machine-readable storage medium storing machine-readable instructions capable of being executed by a processor to perform the instructions corresponding to the steps of the method provided herein, such as a method for coordinated control of a turbine and a boiler. When executed by a central processing unit (CPU), this computer program performs the functions defined in the method of the present application.

[0104] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

[0105] 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 coordinated control of a turbine and a boiler, characterized in that: include: Real-time collection of boiler characteristic parameters; Pre-process the boiler characteristic parameters and mark them as boiler processing parameters; Get the heat storage coefficient; Predict power data based on boiler processing parameters and heat storage coefficient; calculate the energy conversion efficiency of the boiler based on power data and determine whether to generate inefficient instructions; If poor efficiency instructions are generated, the machine and boiler processing parameters will be coordinated and controlled.

2. A coordinated control method for turbines and boilers according to claim 1, characterized in that: The turbine and boiler characteristic parameters include steam parameters, fuel parameters, air parameters, flue gas parameters and water side parameters; the turbine and boiler include boilers and steam turbines; The methods for preprocessing the characteristic parameters of the machine and boiler include: Calculate the mean and standard deviation of each parameter in the furnace characteristic parameters; Obtain the historical parameters corresponding to each parameter in the boiler characteristic parameters, and count the number of historical parameters of each parameter, where the historical parameters are the boiler characteristic parameters collected historically; add the corresponding historical parameters to each parameter in the real-time boiler characteristic parameters to obtain the total number of parameters of each parameter; add one to the number of historical parameters of each parameter to obtain the total number of parameters of each parameter; divide the total number of parameters of each parameter in the boiler characteristic parameters by the total number of corresponding parameters to obtain the average value of each parameter; Subtract the corresponding average value from the historical parameter corresponding to each parameter in the boiler characteristic parameters to obtain the historical parameter difference corresponding to each parameter; subtract the corresponding average value from each parameter in the real-time collected boiler characteristic parameters to obtain the real-time parameter difference of each parameter; add the squares of the historical parameter differences of each parameter in sequence, and then add the squares of the real-time parameter differences to obtain the sum of the squares of each parameter; divide the sum of the squares of each parameter by the total number of corresponding parameters and then take the square root to obtain the standard deviation of each parameter; Add and subtract three times the standard deviation from the average value of each parameter in the boiler characteristic parameters to obtain the corresponding parameter range ; , ; is the average value of the i-th parameter in the boiler characteristic parameters, is the standard deviation of the i-th parameter in the boiler characteristic parameters; Compare each parameter with the corresponding parameter range; if , If it is or, the corresponding parameter is marked as an abnormal parameter; if , the corresponding parameter will not be marked as an abnormal parameter; is the i-th parameter; The historical parameters corresponding to the abnormal parameters are fitted using a polynomial interpolation method to obtain a fitting curve. The values ​​of the abnormal parameters are re-obtained based on the fitting curve, and the corresponding abnormal parameters in the furnace characteristic parameters are replaced with the re-obtained values.

3. The method for coordinated control of turbine and boiler according to claim 2, characterized in that: The steam parameters include steam pressure, steam temperature and steam flow; the steam pressure includes main steam pressure, drum pressure and regulating stage pressure; the fuel parameters include fuel flow, fuel calorific value and fuel temperature; the air parameters include air flow and air temperature; the flue gas parameters include flue gas flow, flue gas composition and flue gas temperature; the water side parameters include feed water flow, feed water temperature and feed water pressure; The heat storage coefficient includes the heat storage coefficient of the steam-water working medium and the heat storage coefficient of the pipe metal; The methods for obtaining the heat storage coefficient of steam-water working fluid include: Obtain the specific heat capacity of steam; perform weighted summation of the specific heat capacity of steam, steam temperature and main steam pressure to obtain the heat storage coefficient of the steam-water working medium; Methods for obtaining the heat storage coefficient of pipeline metal include: Collect d pipeline images, where d is the number of pipelines in the boiler. Identify each of the d pipeline images to obtain the corresponding pipeline material. Determine the specific heat capacity of the corresponding pipeline based on the pipeline material. Obtain the pipeline metal heat storage coefficient by performing a weighted summation of the pipeline specific heat capacity and the temperature and flow rate of the fluid inside the pipeline. Fluid temperatures include steam temperature, fuel temperature, air temperature, flue gas temperature, and feed water temperature. Fluid flow rates include steam flow, fuel flow, air flow, flue gas flow, and feed water flow.

4. A coordinated control method for turbines and boilers according to claim 3, characterized in that: The method of identifying d pipeline images and obtaining the corresponding pipeline materials includes: Use the trained material recognition model to identify the pipeline image and output the recognition result. The recognition result is the digital label corresponding to the pipeline material. The corresponding pipeline material is obtained according to the digital label corresponding to the pipeline material. The material recognition model training process includes: Pre-collection pipeline images, , annotate each pipeline image with the pipeline material; convert the pipeline materials into different digital labels; divide the annotated pipeline images into a training set and a test set; use the training set to train the material recognition model, and use the test set to test the material recognition model; preset an error threshold, and when the mean of the prediction errors of all pipeline images in the test set is less than the error threshold, output the material recognition model; the material recognition model is a convolutional neural network model.

5. The method for coordinated control of turbine and boiler according to claim 4, characterized in that: The method for predicting power data includes: The boiler processing parameters and heat storage coefficient are used as analysis data, and the analysis data are respectively input into the trained power prediction model to predict the power data; the power prediction model includes an input prediction model and an output prediction model, and the output prediction model includes a first output model and a second output model; the power data includes boiler input power, boiler output power and turbine output power; among them, the input prediction model is used to predict boiler input power, the first output model is used to predict boiler output power, and the second output model is used to predict turbine output power.

6. A coordinated control method for turbines and boilers according to claim 5, characterized in that: The training process of the input prediction model includes: Collect e sets of analysis data corresponding to boiler input powers in advance, where e is an integer greater than 1, and convert the analysis data and the corresponding boiler input powers into a corresponding set of feature vectors; Each set of feature vectors is used as input to an input prediction model. The input prediction model outputs a set of predicted boiler input powers corresponding to each set of analysis data, and uses the actual boiler input power corresponding to each set of analysis data as a prediction target. The actual boiler input power is the pre-collected boiler input power corresponding to the analysis data. The training objective is to minimize the sum of the prediction errors of all analysis data. The input prediction model is trained until the sum of the prediction errors reaches convergence. The input prediction model is a deep neural network model. The training process of the first output model and the second output model is consistent with the training process of the input prediction model, and both are deep neural network models.

7. A coordinated control method for turbines and boilers according to claim 6, characterized in that: The method for calculating the energy conversion efficiency of a furnace comprises: The energy conversion efficiency of the boiler includes the energy conversion efficiency of the boiler and the energy conversion efficiency of the steam turbine; the energy conversion efficiency of the boiler The ratio of boiler output power to boiler input power; turbine energy conversion efficiency It is the ratio of turbine output power to boiler output power.

8. The method for coordinated control of turbine and boiler according to claim 7, characterized in that: The method for determining whether an inefficient instruction is generated includes: Preset efficiency thresholds, including boiler efficiency thresholds and turbine efficiency threshold ; Set the boiler efficiency threshold and boiler energy conversion efficiency For comparison, the turbine efficiency threshold and steam turbine energy conversion efficiency Make a comparison; like , then generate inefficient instructions; like , If is and , then no inefficient instructions are generated.

9. The method for coordinated control of turbine and boiler according to claim 8, characterized in that: The steps for coordinated control of boiler processing parameters include: Step 1: Construct m traffic sets and obtain the corresponding set labels; Step 2: Encode the set labels, obtain chromosomes, and construct the initial population; Step 3: Determine the fitness function; Step 4: Natural selection of chromosomes in the population; Step 5: Perform crossover recombination on the chromosomes in the population; Step 6: Calculate the dynamic boundary, generate the reverse solution corresponding to each chromosome and add it to the population, and treat the reverse solution as a chromosome; Step 7: mutate the chromosomes in the population; Step 8: Screen the chromosomes in the population to obtain a new population; Step 9: Determine whether the new population satisfies the corresponding generation F or whether there is a chromosome with a fitness greater than S. If not, return to step 4. If satisfied, obtain the set label corresponding to the chromosome with the largest fitness in the new population, obtain the corresponding flow set according to the set label, and coordinate the fluid flow in the boiler processing parameters according to the flow set; where F is the preset population generation and S is the preset fitness threshold.

10. The method for coordinated control of turbine and boiler according to claim 9, characterized in that: In the step 1, a flow range is obtained, and the flow range includes a steam flow range, a fuel flow range, an air flow range, a flue gas flow range, and a water supply flow range; a value is randomly selected from each range within the flow range to construct a flow set, and a total of m flow sets are constructed, where m is an integer greater than 1, and the m flow sets are all different; different digital labels are set for the m flow sets, and are marked as set labels.

11. The method for coordinated control of turbine and boiler according to claim 10, characterized in that: In step 2, the set label is encoded as X, where X is the chromosome and the range of X is ; Randomly generate G chromosomes to form the initial population , .

12. A coordinated control method for turbines and boilers according to claim 11, characterized in that: In step 3, the fitness function is expressed as: ; Where, is the fitness corresponding to the I-th chromosome, is the regulatory effect corresponding to chromosome I, .

13. A coordinated control method for turbines and boilers according to claim 12, characterized in that: Methods for obtaining adjustment effects include: The boiler energy conversion efficiency and the steam turbine energy conversion efficiency are added together to obtain the total efficiency; according to the set label corresponding to the i-th chromosome, the corresponding flow set is obtained, and the fluid flow in the boiler processing parameters in the analysis data is replaced with the flow set; the replaced analysis data are input into the power prediction model again to predict the power data and mark it as the new power data; the boiler energy conversion efficiency and the steam turbine energy conversion efficiency are recalculated according to the new power data; the recalculated boiler energy conversion efficiency and the steam turbine energy conversion efficiency are added together to obtain the new total efficiency; the new total efficiency is subtracted from the total efficiency to obtain the regulation effect.

14. A coordinated control method for turbines and boilers according to claim 13, characterized in that: In step 5, N chromosomes are randomly selected from the population for crossover recombination to obtain N new chromosomes; the crossover recombination adopts the PMX method; after the chromosome crossover recombination, the fitness of the N new chromosomes is calculated, the fitness of the N new chromosomes and the fitness of the N chromosomes are sorted from large to small and a sorting table is generated, and the N chromosomes in the sorting table are replaced in positive order with the N chromosomes that have undergone crossover recombination in the population.

15. The method for coordinated control of turbine and boiler according to claim 14, characterized in that: In step 6, the dynamic boundary is , obtain the set label corresponding to the chromosome with the smallest fitness in the population and the set label corresponding to the chromosome with the largest fitness, and compare them. is a collection label with a smaller value, is a set label with a larger value; if the generated reverse solution is greater than or less than , it is marked as a transcendental solution, a random number function is used to randomly generate a value within the dynamic boundary, and the randomly generated value is assigned to the transcendental solution; Methods for generating inverse solutions include: ； Where, is the reverse solution of chromosome I, for The random number in is the set label of chromosome I; In step 7, the mutation includes common mutation and cloud adaptive mutation; when the number of generations corresponding to the population is less than When , or the fitness of the chromosome in the population is less than When the number of generations corresponding to the population is greater than or equal to And the fitness of the chromosome in the population is greater than or equal to When , common mutation is used; the common mutation method is: the mutation probability is preset to Y, and the G chromosomes in the population are mutated according to the mutation probability. The mutation method is to randomly select the positions of two genes in the chromosome and exchange the values ​​of the two genes; In step 8, all chromosomes in the population are sorted from large to small according to fitness, and the top G chromosomes are retained to form a new population.

16. The method for coordinated control of turbine and boiler according to claim 15, characterized in that: Calculate power loss value and calibrate steam turbine energy conversion efficiency; Methods for calculating power loss values ​​include: Collect power impact data, including pipeline inner diameter, pipeline length, friction factor, temperature difference and pressure difference; The temperature difference is obtained by: collecting the turbine inlet temperature; subtracting the turbine inlet temperature from the steam temperature to obtain the temperature difference; The pressure difference is obtained by: collecting the turbine inlet pressure; subtracting the turbine inlet pressure from the main steam pressure to obtain the pressure difference; Calculate power loss value based on power impact data and steam flow rate; The expression for the power loss value is: ; Where, is the power loss value, is the friction factor, is the pipe length, is the steam flow rate, is the acceleration due to gravity, is the inner diameter of the pipe, is the temperature difference, is the pressure difference, 、 is the preset scale factor; is the boiler output power; The power loss value is subtracted from the boiler output power to obtain the turbine input power, and the turbine input power is divided by the turbine output power to obtain the calibrated turbine energy conversion efficiency.

17. A turbine and boiler coordinated control system, implementing a turbine and boiler coordinated control method according to any one of claims 1 to 16, characterized in that: include: Parameter acquisition module, used to collect machine and furnace characteristic parameters in real time; Parameter processing module, used to pre-process the boiler characteristic parameters and mark them as boiler processing parameters; Parameter acquisition module, used to obtain heat storage coefficient; The efficiency analysis module is used to predict power data based on the boiler processing parameters and heat storage coefficient; based on the power data, it calculates the energy conversion efficiency of the boiler and determines whether to generate a poor efficiency instruction; The coordination control module is used to coordinate and control the machine and boiler processing parameters if an instruction with poor efficiency is generated.

18. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the machine-boiler coordinated control method according to any one of claims 1 to 16 is implemented.

19. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed, the machine-boiler coordinated control method according to any one of claims 1 to 16 is implemented.

Images