Coal-fired generating set boiler combustion and coal mill parameter matching control optimization method

Abstract

The invention discloses a coal-fired generating set boiler combustion and coal mill parameter matching control optimization method, and relates to the technical field of coal mill operation optimization. Comprising the steps that boiler parameters, coal mill parameters and pulverized coal fineness of a coal mill in the boiler combustion process are monitored and obtained, the combustion efficiency related parameter relation is calculated and obtained, an initial data set is obtained, the initial data set is preprocessed, a processed data set is obtained, and a parameter space is determined according to the processed data set; hyper-parameter combinations are randomly extracted according to the parameter space, the hyper-parameter combinations are optimized through the Bayesian algorithm, the optimal hyper-parameter combination is determined, and the boiler parameters and the coal mill parameters are kept consistent with the optimal hyper-parameter combination. According to the method, the fineness of the pulverized coal of the coal mill can be optimized, the operation safety of the boiler is improved, and the economic loss is reduced.

Description

Technical Field

[0001] The invention relates to the technical field of coal mill operation optimization, and in particular to a method for optimizing the matching control of boiler combustion and coal mill parameters of a coal-fired power generation unit. Background Art

[0002] In the context of the increasingly complex energy structure and the increasing environmental protection requirements, the research on the matching of 660MW boiler combustion and medium-speed mill parameters is particularly important. The 660MW large-scale thermal power generating unit is an important part of the power system, and its combustion efficiency directly affects the economy and environmental impact of power production. In the operation of the 660MW boiler, the relationship between coal grinding parameters and combustion efficiency is crucial. As a key equipment for coal powder preparation, the working state of the coal mill directly affects the particle size distribution and uniformity of the coal powder, thereby affecting the sufficiency and efficiency of combustion.

[0003] Therefore, it is an urgent problem for those skilled in the art to propose a method for optimizing the control of boiler combustion and coal mill parameter matching in a coal-fired power generation unit to solve the problems existing in the prior art. Summary of the invention

[0004] In view of this, the present invention provides a method for optimizing the control of boiler combustion and coal mill parameter matching of a coal-fired power generation unit, which can optimize the coal powder fineness of the coal mill, improve the safety of boiler operation, and reduce economic losses.

[0005] In order to achieve the above object, the present invention adopts the following technical solution:

[0006] A method for optimizing the control of boiler combustion and coal mill parameter matching of a coal-fired power generation unit, comprising the following steps:

[0007] S1. Monitor and obtain boiler parameters and coal mill parameters during boiler combustion, as well as coal powder fineness of the coal mill, calculate and obtain the parameter relationship related to combustion efficiency, and obtain the initial data set;

[0008] S2, preprocessing the initial data set to obtain a processed data set;

[0009] S3, determining the parameter space according to the processed data set, and randomly extracting hyperparameter combinations according to the parameter space;

[0010] S4. Use the Bayesian algorithm to optimize the hyperparameter combination and determine the optimal hyperparameter combination;

[0011] S5. Keep the boiler parameters and coal mill parameters consistent with the optimal hyperparameter combination.

[0012] In the above method, optionally, determining the coal powder fineness related parameters in S1 includes: establishing a particle model using a Bayesian algorithm, defining each dimensional component of the particle group position vector as internal parameters of the parameter space, and optimizing the particle group position.

[0013] In the above method, optionally, the initial data set in S1 is a parameter set generated based on the optimized coal mill parameters.

[0014] In the above method, optionally, the parameter space in S3 is a Boostedtree method for determining the importance of the processed data set.

[0015] In the above method, optionally, in S4, the optimization of the hyperparameter combination includes constructing a multi-layer network based on the internal burner group of the boiler, including an input layer, a hidden layer and an output layer.

[0016] In the above method, the hidden layer neurons are optionally divided into N groups of burners and other systems, and the exclusive input layer neurons of the N burner groups are only connected to the hidden layer neurons belonging to the burner groups, and the burner groups are independent of each other. The input layer is connected to each hidden layer neuron in pairs, and all hidden layer neuron outputs are connected to output layer neurons in pairs. The output layer outputs NO X content.

[0017] It can be seen from the above technical solution that, compared with the prior art, the present invention provides a method for optimizing the control of boiler combustion and coal mill parameter matching of a coal-fired power generation unit, which has the following beneficial effects: a relationship model between coal mill operating parameters and coal powder fineness is obtained through data modeling, and the coal powder fineness of the coal mill is optimized in combination with a particle swarm algorithm, so that the coal mill has a suitable air-coal ratio, thereby improving the safety of boiler operation and reducing economic losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0019] Figure 1 The present invention discloses a flow chart of a method for optimizing the matching control of boiler combustion and coal mill parameters of a coal-fired power generation unit. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] In this application, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, the elements defined by the sentence "comprise one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0022] Reference Figure 1 As shown, the present invention discloses a method for optimizing the control of boiler combustion and coal mill parameter matching of a coal-fired power generation unit, comprising the following steps:

[0023] S1. Monitor and obtain boiler parameters and coal mill parameters during boiler combustion, as well as coal powder fineness of the coal mill, calculate and obtain the parameter relationship related to combustion efficiency, and obtain the initial data set;

[0024] S2, preprocessing the initial data set to obtain a processed data set;

[0025] S3, determining the parameter space according to the processed data set, and randomly extracting hyperparameter combinations according to the parameter space;

[0026] S4. Use the Bayesian algorithm to optimize the hyperparameter combination and determine the optimal hyperparameter combination;

[0027] S5. Keep the boiler parameters and coal mill parameters consistent with the optimal hyperparameter combination.

[0028] Furthermore, the boiler parameters and coal-fired machine parameters in S1 include coal quality parameters, coal powder concentration, flow rate, primary air, secondary air, burnout air, oxygen content, load, carbon monoxide content, furnace negative pressure, pressure of each wind box and opening of each regulating mechanism of the air-powder process.

[0029] Furthermore, the specific contents of determining the parameters related to the coal powder fineness in S1 include: using the Bayesian algorithm to establish a particle model, and then defining the various dimensional components of the particle group position vector as internal parameters of the parameter space, and optimizing the particle group position.

[0030] Specifically, the optimization process includes: using the particle swarm algorithm, setting the search target and number of iterations of the particle swarm, the search target is set to minimize the difference between the particle model prediction result and the coal powder fineness set by the combustion demand, and the number of iterations is set between 20 and 100 times; according to the actual design and operation requirements of the coal mill, the optimization range of each operating parameter is set, and the position vector is initialized, and then according to the search target set in the previous step, the particle model built by the particle swarm algorithm combined with the Bayesian algorithm is iteratively calculated, and the particle model predicts its corresponding coal powder fineness according to the position vector of the particle swarm algorithm, and then the search target is calculated to search for the optimal position of the particle swarm in the coal mill operating parameter vector space. When the particle swarm algorithm completes the number of iterations or finds the optimal setting, the calculation is stopped to obtain the corresponding optimal position vector, that is, the optimal coal mill operating parameter combination and the corresponding coal powder fineness are obtained.

[0031] Furthermore, the initial data set in S1 is a parameter set generated based on the optimized coal mill parameters.

[0032] Furthermore, the parameter space in S3 uses the Boosted tree method to determine the importance of the processed data set.

[0033] Specifically, the parameters whose importance threshold is greater than 0.1 obtained by the Boostedtree method are extracted, and the extracted parameter set is obtained as the hyperparameter set.

[0034] Furthermore, the data preprocessing in S2 includes standardizing the process parameters of the data set of the boiler production process using a conversion function, and the expression is as follows:

[0035]

[0036] in, is the kth parameter of the initial data set, k=1,…,K, and n is the parameter dimension.

[0037] Furthermore, in S4, the optimization of the hyperparameter combination includes constructing a multi-layer network based on the internal burner group of the boiler, including an input layer, a hidden layer, and an output layer.

[0038] Furthermore, the hidden layer neurons are divided into N groups of burners and other systems. The exclusive input layer neurons of the N burner groups are only connected to the hidden layer neurons belonging to the burner groups. The burner groups are independent of each other. The input layer is connected to each hidden layer neuron in pairs. All hidden layer neuron outputs are connected to output layer neurons in pairs. The output layer outputs NO X content.

[0039] Furthermore, the optimal hyperparameter combination includes, based on the output NO X The content and hyperparameter combination are used to divide the boiler into different operating conditions. The data corresponding to different operating conditions are input into the LS-SVM measurement model for test optimization. Different combustion efficiencies are obtained based on different operating conditions, and the parameters with the highest combustion efficiency are used as boiler parameters.

[0040] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0041] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for optimizing the control of boiler combustion and coal mill parameter matching of a coal-fired power generation unit, comprising the following steps: S1. Monitor and obtain boiler parameters and coal mill parameters during boiler combustion, as well as coal powder fineness of the coal mill, calculate and obtain the parameter relationship related to combustion efficiency, and obtain the initial data set; S2, preprocessing the initial data set to obtain a processed data set; S3, determining the parameter space according to the processed data set, and randomly extracting hyperparameter combinations according to the parameter space; S4. Use the Bayesian algorithm to optimize the hyperparameter combination and determine the optimal hyperparameter combination; S5. Keep the boiler parameters and coal mill parameters consistent with the optimal hyperparameter combination.

2. A method for optimizing the matching control of boiler combustion and coal mill parameters of a coal-fired power generation unit according to claim 1, characterized in that: Determining the parameters related to the fineness of the coal powder in S1 includes: using the Bayesian algorithm to establish a particle model, and then defining the various dimensional components of the particle group position vector as internal parameters of the parameter space, and optimizing the particle group position.

3. The method for optimizing the matching control of boiler combustion and coal mill parameters of a coal-fired power generation unit according to claim 1, characterized in that: The initial data set in S1 is a parameter set generated based on the optimized coal mill parameters.

4. The method for optimizing the matching control of boiler combustion and coal mill parameters of a coal-fired power generation unit according to claim 1, characterized in that: The parameter space in S3 uses the Boosted tree method to determine the importance of the processed data set.

5. The method for optimizing the matching control of boiler combustion and coal mill parameters of a coal-fired power generation unit according to claim 1, characterized in that: In S4, the optimization of the hyperparameter combination includes constructing a multi-layer network based on the internal burner group of the boiler, including an input layer, a hidden layer, and an output layer.

6. A method for optimizing the matching control of boiler combustion and coal mill parameters of a coal-fired power generation unit according to claim 5, characterized in that: Hidden layer neurons are divided into N groups of burners and other systems. The exclusive input layer neurons of N burner groups are only connected to the hidden layer neurons belonging to the burner group. The burner groups are independent of each other. The input layer is connected to each hidden layer neuron in pairs. All hidden layer neuron outputs are connected to output layer neurons in pairs. The output layer outputs NO X content.

Images