Intelligent gasification feedstock blending system and method

Abstract

[0013] An embodiment of the present invention provides an intelligent gasification feedstock blending system and method, belonging to the coal chemical industry. The gasification feedstock blending subsystem includes a feedstock property rapid analysis module for obtaining feedstock property parameters based on the characteristic spectral line intensity of the feedstock fed to the furnace; a feedstock property prediction module for forming a prediction model and predicting the property parameters of the feedstock blend using the prediction model based on the feedstock property parameters and blending ratios; a feedstock blending plan optimization module for forming an optimization model and obtaining an optimized feedstock blending plan using the optimization model based on the property parameters of the feedstock blend; and a feedstock blending plan economic evaluation module for outputting a feedstock blending plan with the best technical and economical efficiency. The present invention establishes an intelligent gasification feedstock blending system that can be used throughout the entire lifecycle process, achieving intelligent and accurate control of gasification feedstock blending.

Description

Detailed Description of the Invention

[0001] [Technical field]

[0002] The present invention relates to the field of coal chemical industry, and more particularly to an intelligent gasification raw material blending system and an intelligent gasification raw material blending method. [Background technology]

[0003] The stable operation of gasifiers is one of the important economic goals pursued by coal chemical industry enterprises. Gasifiers have certain operating conditions and have strict restrictions on the characteristics of the raw materials fed to the furnace. In the actual production of coal chemical industry enterprises, the following problems may occur. First, the properties of coal near the project are not suitable for gasifiers and cannot be applied to the site. Second, the quality of coal fluctuates greatly, making it difficult for the gasifier to operate stably for a long time. Third, the supply of the currently used coal types is problematic, or the price fluctuates greatly, making the gasifier operate stably, resulting in corrosion, ash blocking, and even production stoppage. Coal blending technology can effectively solve the above problems, allowing the coal near the project to be applied to the site, thereby reducing costs. And the gasifier can operate stably for a long time, increasing profits. It can also increase the flexibility of coal use in the project and reduce risks. Traditional coal blending is mainly achieved by scientific research institutes' experimenters under a large number of complicated conditions, or by the accumulated operating experience of factory personnel over a long period of time, which results in low efficiency and low accuracy, and the optimal coal blending ratio of the gasifier cannot be effectively achieved. In addition, gasification technology has been developed, promoted and applied on a large scale in China. Coal is no longer the only gasification raw material, and mixing various carbon-containing compounds to become gasification raw materials has become an important development trend of coal gasification technology. Therefore, it is necessary to develop an intelligent gasification raw material blending system that can build a raw material blending plan and covers the entire life cycle process. Summary of the Invention

[0004] An objective of the embodiments of the present invention is to provide an intelligent system and method for gasification feedstock blending, which can solve the problems that traditional coal blending techniques have low efficiency, low accuracy, and cannot be used to develop a full life cycle process of feedstock blending proposals. [Means for solving the problem]

[0005] In order to achieve the above object, the first embodiment of the present invention provides an intelligent gasification feedstock blending system including a gasification feedstock blending subsystem. The gasification feedstock blending subsystem is a gasification feedstock blending subsystem including a feedstock property rapid analysis module that acquires the characteristic spectral line intensity of the feedstock to be supplied to the furnace and acquires the feedstock property parameters of the feedstock based on the characteristic spectral line intensity, a blending feedstock property prediction module that forms a prediction model and predicts the property parameters of the blended feedstock by the prediction model based on the feedstock property parameters and a preset blending ratio, a feedstock blending plan optimization module that forms an optimization model and acquires an optimized feedstock blending plan by the objective function of the optimization model based on the property parameters of the blended feedstock, and a feedstock blending plan economic evaluation module that performs technical and economic analysis on the optimized feedstock blending plan and outputs the feedstock blending plan with the best technical and economic efficiency.

[0006] Alternatively, the system also includes a raw material property standard subsystem having a raw material standard management module for supplying to the furnace, which forms and stores a correspondence between different types of gasification furnaces and raw materials corresponding to the gasification furnaces in order to determine the raw material to be supplied to the furnace after determining the type of the gasification furnace.

[0007] Alternatively, the property parameters of the blended raw material also include basic properties, ash melting properties, slurry forming properties, and gasification reaction properties.

[0008] Alternatively, the basic properties include a proximate analysis parameter, an elemental analysis parameter, a grindability parameter, and a calorific value parameter.

[0009] Alternatively, the system further includes an information management subsystem, which includes a raw material information management module, a gasifier information management module, an additive information management module, and a gasification slag information management module.

[0010] The raw material information management module stores the raw material property parameters obtained from the raw material property rapid analysis module.

[0011] The gasifier information management module forms and stores a correspondence relationship between different types of gasifiers and the operation parameters corresponding to the gasifiers.

[0012] The additive information management module forms and stores a correspondence between predictions of ash melting characteristics and slurry formation characteristics and additives corresponding to the predictions.

[0013] The gasification slag information management module forms and stores a one-to-one correspondence between the type of gasification furnace, the raw material, the gasification furnace operation parameters, and the properties of the slag.

[0014] Alternatively, the gasification feedstock blending subsystem further includes a gasification furnace early warning module that forms a functional relationship between the blended feedstock, gasification furnace operating parameters, and slag properties, predicts the corresponding slag properties based on the blended feedstock and gasification furnace operating parameters of the obtained feedstock blending plan with the best technical and economical efficiency, and determines whether the obtained slag properties are abnormal.

[0015] Alternatively, if it is determined that the obtained slag properties are abnormal, the gasifier early warning module compares the obtained slag properties with pre-stored slag properties, and obtains parameters related to the abnormality of the slag properties based on the correspondence between the pre-stored slag properties and the type of gasifier, the raw material, and the gasifier operation parameters.

[0016] In a second embodiment of the present invention, an intelligent gasification feedstock blending method is provided, which includes a gasification feedstock blending sub-step, which includes a step of acquiring a characteristic spectral line intensity of the feedstock to be supplied to a furnace, acquiring a feedstock property parameter of the feedstock based on the characteristic spectral line intensity, a step of forming a prediction model, and predicting the property parameter of the blended feedstock by the prediction model based on the feedstock property parameter and the feedstock blending ratio, a step of forming an optimization model, and acquiring an optimized feedstock blending plan by the optimization model based on the property parameter of the blended feedstock, and a step of performing a technical-economic analysis on the optimized feedstock blending plan, and outputting a feedstock blending plan with the best technical-economic efficiency.

[0017] Alternatively, the method further includes a feedstock property criterion sub-step, which includes the following steps: after determining the type of the gasifier, forming and storing a correspondence relationship between different types of gasifiers and feedstocks corresponding to the gasifiers in order to determine the feedstock to be supplied to the gasifier;

[0018] Alternatively, the property parameters of the blended raw material include basic properties, ash melting properties, slurry formation properties, and gasification reaction properties.

[0019] Alternatively, the basic properties include a proximate analysis parameter, an elemental analysis parameter, a grindability parameter, and a calorific value parameter.

[0020] Alternatively, the method further includes an information management substep, which includes the following steps: storing the feedstock property parameters obtained from the feedstock property rapid analysis module, forming and storing a correspondence relationship between different types of gasifiers and operation parameters corresponding to the gasifiers, forming and storing a correspondence relationship between predictions of ash melting characteristics and slurry formation characteristics and additives corresponding to the predictions, and forming and storing a one-to-one correspondence relationship between the type of gasifier, the feedstock, the gasifier operation parameters, and the properties of slag.

[0021] Alternatively, the gasification feedstock blending sub-step includes the following steps: forming a functional relationship between the blended feedstock, the gasification furnace operation parameters, and the properties of slag, and predicting the properties of the corresponding slag based on the blended feedstock and the gasification furnace operation parameters of the obtained feedstock blending plan with the best technical and economical efficiency, and judging whether the obtained slag properties are abnormal.

[0022] Alternatively, the gasification raw material blending sub-step includes the following steps: if it is determined that the obtained slag properties are abnormal, comparing the obtained slag properties with pre-stored slag properties, and obtaining parameters related to the abnormality of the slag properties based on the correspondence between the pre-stored slag properties and the type of gasifier, the raw material, and the gasifier operation parameters; Effect of the Invention

[0023] In the above technical solution of the present invention, the raw materials are quickly analyzed to obtain raw material property parameters, a prediction model is formed based on the obtained raw material property parameters to predict the blended raw material property parameters, a raw material blending plan is optimized based on the target function formed based on the blended raw material property parameters, and a technical and economic analysis is performed on the optimized raw material blending plan to obtain the best raw material blending plan, thereby building an intelligent gasification raw material blending system with a full life cycle process, effectively improving the efficiency and accuracy of blending coal, achieving intelligent and accurate control of gasification raw material blending, and effectively reducing the adverse impacts on enterprises caused by raw material property problems.

[0024] Specifically, the present invention also provides the following technical solutions:

[0025] Technical proposal 1 A gasification feedstock blending system including a gasification feedstock blending subsystem, comprising: a feedstock property rapid analysis module that acquires characteristic spectral line intensities of feedstock to be supplied to a furnace and acquires feedstock property parameters of the feedstock based on the characteristic spectral line intensities; a blended feedstock property prediction module that forms a prediction model and predicts the property parameters of the blended feedstock by the prediction model based on the feedstock property parameters and the blending ratio of the feedstock; a feedstock blending plan optimization module that forms an optimization model and acquires an optimized feedstock blending plan by a target function of the optimization model based on the property parameters of the blended feedstock; and a feedstock blending plan economic evaluation module that performs technical and economic analysis on the optimized feedstock blending plan and outputs the feedstock blending plan with the best technical and economic efficiency.

[0026] Technical proposal 2 In the gasification raw material blending system described in Technical Proposal 1, the system also includes a raw material property standard subsystem having a raw material standard management module supplied to the furnace, which forms and stores a correspondence between different types of gasification furnaces and the raw materials corresponding to the gasification furnaces in order to determine the raw material to be supplied to the furnace after determining the type of the gasification furnace.

[0027] Technical proposal 3 In the gasification raw material blending system described in Technical Scheme 1 or 2, the property parameters of the blended raw material include basic properties, ash melting properties, slurry formation properties, and gasification reaction properties. Preferably, the basic properties include industrial analysis parameters, elemental analysis parameters, grindability parameters, and calorific value parameters. More preferably, the property parameters of the blended raw material predicted by the prediction model are industrial analysis parameters, elemental analysis parameters, calorific value parameters, and optional ash melting property parameters.

[0028] Technical proposal 4 In the gasification raw material blending system according to any one of technical proposals 1 to 3, the system is characterized in that it further includes an information management subsystem, and the information management subsystem includes a raw material information management module, a gasification furnace information management module, an additive information management module, and a gasification slag information management module. The raw material information management module stores raw material property parameters obtained from the raw material property rapid analysis module. The gasification furnace information management module forms and stores a correspondence relationship between different types of gasification furnaces and operation parameters corresponding to the gasification furnaces. The additive information management module forms and stores a correspondence relationship between predictions of ash melting characteristics and slurry formation characteristics and additives corresponding to the predictions. The gasification slag information management module forms and stores a one-to-one correspondence relationship between the type of gasification furnace, raw materials, gasification furnace operation parameters, and slag properties.

[0029] Technical proposal 5 In the gasification raw material blending system described in any of technical proposals 1 to 4, the gasification raw material blending subsystem is characterized in that it further includes a gasification furnace early warning module that forms a functional relationship between the blended raw materials, gasification furnace operation parameters, and slag properties, and predicts the corresponding slag properties based on the blended raw materials and gasification furnace operation parameters of the obtained raw material blending plan with the best technical and economical efficiency, and determines whether the obtained slag properties are abnormal.

[0030] Technical plan 6 In the gasification raw material blending system described in any of technical proposals 1 to 5, when it is determined that the properties of the obtained slag are abnormal, the gasification furnace early warning module compares the obtained slag properties with pre-stored slag properties, and obtains parameters related to the abnormality of the slag properties based on the correspondence between the pre-stored slag properties and the type of gasification furnace, the raw material, and the gasification furnace operating parameters.

[0031] Technical proposal 7 In the gasification raw material blending system according to any one of technical proposals 1 to 6, the blended raw material property prediction module forms a prediction model, and the blended raw material property prediction module calculates the raw material property parameters, the raw material blending ratio, and the internal moisture content M ad , grindability index HGI, and specific surface area S BET and predicting blended feedstock property parameters with the predictive model based on the optional additive information, and the predicted blended feedstock property parameters include slurry formation characteristics of the blended feedstock, gasification reaction characteristics of the blended feedstock, and optional ash melting characteristics.

[0032] Technical proposal 8 A gasification feedstock blending method characterized by including a gasification feedstock blending sub-step, the gasification feedstock blending sub-step including a step of acquiring characteristic spectral line intensities of feedstock to be supplied to a furnace and acquiring feedstock property parameters of the feedstock based on the characteristic spectral line intensities; a step of forming a prediction model and predicting property parameters of the blended feedstock by the prediction model based on the feedstock property parameters and the feedstock blending ratio; a step of forming an optimization model and acquiring an optimized feedstock blending plan by the optimization model based on the property parameters of the blended feedstock; and a step of performing a technical-economic analysis on the optimized feedstock blending plan and outputting the feedstock blending plan with the best technical-economic efficiency.

[0033] Technical proposal 9 In the gasification raw material blending method described in Technical Proposal 8, the method further includes a raw material property criterion sub-step, which is characterized in that after determining the type of gasification furnace, the raw material property criterion sub-step includes a step of forming and storing a correspondence between different types of gasification furnaces and raw materials corresponding to the gasification furnaces in order to determine the raw material to be supplied to the furnace.

[0034] Technical proposal 10 In the method for blending raw materials for gasification described in Technical Scheme 8 or 9, the property parameters of the blended raw materials include basic properties, ash melting properties, slurry formation properties, and gasification reaction properties. Preferably, the basic properties include industrial analysis parameters, elemental analysis parameters, grindability parameters, and calorific value parameters. More preferably, the property parameters of the blended raw materials predicted by the prediction model are industrial analysis parameters, elemental analysis parameters, calorific value parameters, and optional ash melting property parameters.

[0035] Technical proposal 11 In the gasification raw material blending method described in any of Technical Proposals 8 to 10, it is characterized in that it further includes an information management sub-step, and the information management sub-step includes the following steps: a step of storing raw material property parameters obtained from the raw material property rapid analysis module, a step of forming and storing a correspondence relationship between different types of gasification furnaces and operating parameters corresponding to these gasification furnaces, a step of forming and storing a correspondence relationship between predictions of ash melting characteristics and slurry formation characteristics and additives corresponding to these predictions, and a step of forming and storing a one-to-one correspondence relationship between the type of gasification furnace, the raw material, the gasification furnace operating parameters, and the properties of the slag.

[0036] Technical proposal 12 In the gasification raw material blending method described in any one of technical proposals 8 to 11, the gasification raw material blending sub-step is characterized in that it further includes a step of forming a functional relationship between the blended raw materials, gasification furnace operation parameters, and slag properties, and predicting the corresponding slag properties based on the blended raw materials and gasification furnace operation parameters of the obtained raw material blending plan with the best technical and economical efficiency, and determining whether the obtained slag properties are abnormal.

[0037] Technical proposal 13 In the gasification raw material blending method described in any of Technical Proposals 8 to 12, when it is determined that the properties of the obtained slag are abnormal, the method further includes a step of comparing the properties of the obtained slag with pre-stored slag properties, and obtaining parameters related to the abnormality of the slag properties based on the correspondence between the pre-stored slag properties and the type of gasifier, the raw material, and the gasifier operation parameters.

[0038] Technical proposal 14 In the gasification raw material blending method according to any one of technical proposals 8 to 13, a prediction model is formed, and the raw material property parameters, the raw material blending ratio, and the internal moisture content M ad , grindability index HGI, and specific surface area S BET and predicting property parameters of the blended raw materials by the predictive model based on optional additive information, wherein the predicted property parameters of the blended raw materials include a slurry formation characteristic of the blended raw materials, a gasification reaction characteristic of the blended raw materials, and optional ash melting characteristic.

[0039] Other features and advantages of the embodiments of the present invention are described in detail in the Detailed Description section below. [Brief description of the drawings]

[0040] The drawings are used to provide a further understanding of the embodiments of the present invention, constitute a part of the specification, and, together with the following detailed description, are used to explain the embodiments of the present invention, but are not intended to limit the embodiments of the present invention. [Figure 1] FIG. 1 is a schematic diagram showing the structure of an intelligent gasification raw material blending system provided in one embodiment of the present invention. [Diagram 2] 1 is a flowchart showing the operation of an intelligent gasification feedstock blending system provided according to one embodiment of the present invention. [Diagram 3] 1 is a flowchart showing the process flow of an intelligent gasification raw material blending method provided according to one embodiment of the present invention.

[0041] Hereinafter, specific embodiments of the present invention will be described in detail with reference to the drawings. It should be understood that the specific embodiments described herein are only used to explain and explain the present invention, and are not intended to limit the present invention.

[0042] In embodiments of the invention, the terms "comprise", "include", and any other variations are intended to include a non-exclusive inclusion, such that a process, method, product, or facility that includes a set of elements not only includes the elements, but also includes other elements not expressly listed or that are inherent to the process, method, product, or facility. In the absence of further limitations, an element qualified by the term "comprises a" does not exclude the process, method, product, or facility that includes the element from including other identical elements.

[0043] As shown in Figures 1 and 2, the first embodiment of the present invention provides an intelligent gasification feedstock blending system including a gasification feedstock blending subsystem. The gasification feedstock blending subsystem is a gasification feedstock blending subsystem including a feedstock property rapid analysis module that acquires the characteristic spectral line intensity of the feedstock to be supplied to the furnace and acquires the feedstock property parameters of the feedstock based on the characteristic spectral line intensity, a blended feedstock property prediction module that forms a prediction model and predicts the property parameters of the blended feedstock by the prediction model based on the feedstock property parameters and a preset blending ratio, a feedstock blending plan optimization module that forms an optimization model and acquires an optimized feedstock blending plan by the objective function of the optimization model based on the property parameters of the blended feedstock, and a feedstock blending plan economic evaluation module that performs technical and economic analysis on the optimized feedstock blending plan and outputs the feedstock blending plan with the best technical and economic efficiency.

[0044] In this way, in the above technical solution of this embodiment, the raw materials are quickly analyzed to obtain the raw material property parameters, the blended raw material property parameters are predicted by the prediction model formed according to the obtained raw material property parameters and the preset blending ratio, the raw material blending plan is optimized by the optimization model formed according to the blended raw material property parameters, and a technical-economic analysis is performed on the optimized raw material blending plan to obtain the best raw material blending plan, thereby building an intelligent gasification raw material blending system with a whole life cycle process, effectively improving the efficiency and accuracy of blended coal, and achieving intelligent and accurate control of gasification raw material blending by using computer technology to form a quality prediction model of blended coal, and effectively reducing the adverse impact of raw material property problems on the enterprise.

[0045] Specifically, the stable operation of the gasifier is closely related to the properties of the raw materials fed to the furnace. In order to maintain the stable operation of the gasifier, it is necessary to impose strict restrictions on the raw materials fed to the furnace. Different individual raw materials have different properties. To meet the gasification requirements, the raw materials fed to the furnace are usually mixed with multiple individual raw materials, so the raw material blending plan of the raw materials fed to the furnace is particularly important. In this embodiment, the individual raw materials may be carbon-containing materials such as coal, semi-coke, petroleum coke, biomass, sludge, oil sludge and waste carbon. Due to the disadvantages of slow analysis speed and complicated process, offline analysis, which is currently commonly used for coal component analysis, cannot provide operators with real online reference data and is difficult to adapt to the requirements of industrial production. In this embodiment, laser-induced breakdown spectroscopy (LIBS) is used to obtain the characteristic spectral line intensity of the measurement sample. In laser-induced breakdown spectroscopy, when a strong pulsed laser is focused and irradiated onto a sample, the sample instantly gasifies into a high-temperature, high-density plasma, and the excited plasma emits different lines to the outside. The wavelength and intensity of the spectral lines emitted by the plasma represent the composition elements and their concentrations of the measured object. LIBS has the advantages of fast detection speed, high sensitivity, low cost, and the ability to simultaneously measure multiple elements. The rapid analysis module of raw material properties obtains the characteristic spectral line intensity of the measured raw material from the LIBS detector, and uses the current special algorithm, such as the spectrum normalization algorithm and the self-absorption calibration algorithm, to calculate and analyze the characteristic spectral line intensity to obtain the raw material property parameters of the measured raw material, and detects each individual raw material to obtain the property parameters of each raw material. Among them, the raw material property parameters include the content of carbon, hydrogen, sulfur, and ash-forming elements, ash content, volatile content, and calorific value.

[0046] The blended raw material property prediction module forms a prediction model using the property parameters and blending ratio of each raw material as input and the property parameters of the blended raw material as output. Among them, the property parameters of the blended raw material include basic properties, ash melting properties, slurry formation properties, and gasification reaction properties. The basic properties include industrial analysis parameters, elemental analysis parameters, grindability parameters, and calorific value parameters. In this embodiment, the blended raw material property prediction module predicts the basic properties, ash melting properties, slurry formation properties, and gasification reaction properties of the blended raw material, respectively, by forming a basic property prediction model, an ash melting property prediction model, a slurry formation property prediction model, and a gasification reaction property prediction model. The basic property prediction model is formed based on a linear weighted sum algorithm, and the ash melting property prediction model, the slurry formation property prediction model, and the gasification reaction property prediction model are formed based on a BP neural network. The prediction model is not limited to the above algorithm and may be formed based on other algorithms, such as a convolutional neural network.

[0047] The raw material blending plan optimization module forms an objective function based on the requirements of the raw material blending plan. The number of objective functions may be one or more. The number of feasible raw material blending plans obtained may be more than one. For example, the objective function may be formed based on requirements such as the lowest price of the blended raw material, the highest calorific value, or the most environmentally friendly. The constraint conditions that the gasification blended raw material must satisfy are determined. The constraint conditions are limiting conditions when calculating the limit value of the objective function. The constraint conditions in this embodiment are the requirements of the gasification furnace for the blended raw material to be supplied to the furnace, that is, the requirements of the gasification furnace for the property parameters of the blended raw material to be supplied to the furnace and the variation range of the related property parameters. The blended raw material property prediction module obtains the functional relationship between the property parameters of each raw material and the blending ratio of the raw material, and obtains the upper and lower limits of the conversion range of the raw material property parameters by the gasification furnace to obtain the constraint conditions of the objective function. Based on the formed objective function, the constraint conditions are taken into consideration to form an optimization model.

[0048] On the other hand, the raw material blending plan economics evaluation module can perform technical and economic analysis on all feasible raw material blending plans obtained by optimization by calling up the process simulation software, and based on the preset targets, can select the plan with appropriate product structure and good economics as the optimal raw material blending plan, achieving real-time online adjustment of the blended raw material ratio. On the other hand, by adjusting the operating parameters of the gasifier, the effect of optimizing the product structure and economics can be achieved, and the stability of operation can be guaranteed. Among them, the feasible raw material blending plans can be selected based on the preset targets, and the product structure and economics can be optimized as the optimal raw material blending plan. combination The techno-economic analysis of the process proposal can be analyzed based on the actual demand based on the technical conditions of gasification, including feed rate, oxygen flow rate, amount of additive, gasification temperature, gasification pressure and carbon conversion rate, and the composition components of the synthesis gas and the feedstock cost are used as the criteria.

[0049] In this embodiment, the system also includes a feedstock property standard subsystem. The feedstock property standard subsystem includes a feedstock standard management module for feeding to the furnace, which is used to form and store a correspondence relationship between different types of gasifiers and feedstocks corresponding to the gasifiers, and determines the feedstock to be fed to the furnace after determining the type of the gasifier. Different types of gasifiers have different requirements for the feedstock to be fed to the furnace, for example, the gasifiers have different requirements for the composition, blending ratio and calorific value of the feedstock to be fed to the furnace. In order to stably operate the gasifier, the feedstock to be fed to the furnace must satisfy the gasifier's requirements for the feedstock. The feedstock standard management module for feeding to the furnace forms and stores a correspondence relationship between different types of gasifiers and the requirements for the feedstock to be fed to the furnace corresponding to the furnace in advance. When predicting a feedstock blending plan for the feedstock to be fed to the furnace, quickly calling up the requirements for the feedstock corresponding to the selected gasifier is helpful in executing subsequent steps. Meanwhile, switching between different types of gasifiers can be easily performed, effectively improving the working efficiency.

[0050] The system of this embodiment further includes an information management subsystem. The information management subsystem includes a raw material information management module, a gasifier information management module, an additive information management module, and a gasification slag information management module. The raw material information management module stores raw material property parameters obtained from the raw material property rapid analysis module. The gasifier information management module forms and stores a correspondence relationship between different types of gasifiers and operation parameters corresponding to the gasifiers. The additive information management module forms and stores a correspondence relationship between predictions of ash melting characteristics and slurry formation characteristics and additives corresponding to the predictions. The gasification slag information management module forms and stores a one-to-one correspondence relationship between the type of gasifier, raw material, gasifier operation parameters, and slag properties.

[0051] Specifically, for ease of inquiry and use, each time the feedstock property rapid analysis module predicts and obtains feedstock property parameters, the obtained feedstock property parameters are stored in the feedstock information management module. Since different types of gasifiers have different operating parameters, in order to maintain stable operation of the gasifier, it is necessary to strictly adjust the gasifier based on the operating parameters of different types of gasifier. By forming and storing in advance the correspondence between various gasifiers and the operating parameters corresponding to these furnaces in the gasifier information management module, the corresponding gasifier operating parameters can be used after an optimal feedstock blend proposal is obtained by the feedstock blend proposal economics evaluation module. This allows the operating parameters of the gasifier to be adjusted to ensure stable operation of the gasifier.

[0052] In the process of predicting ash fusion characteristics using the ash fusion characteristic prediction model, and in the process of predicting slurry formation characteristics using the slurry formation characteristic prediction model, it is necessary to add appropriate additives to the supplied raw materials, and by forming and storing in advance in the additive information management module the correspondence between the predictions of ash fusion characteristics and slurry formation characteristics and the corresponding additives, the additives can be added accurately and quickly when predicting ash fusion and slurry formation characteristics.

[0053] In the coal gasification business, coal gasification slag accounts for a significant proportion of solid waste. Coal gasification slag includes coarse slag and fine slag. The composition of the slag is related to the content and composition of coal ash in the gasification feedstock, the gasification process, etc., and is mainly composed of SiO 2 , Al 2 O 3 , CaO, residual carbon, etc. The composition of the gasification slag can be used to determine whether the raw materials and operating parameters supplied to the gasification furnace meet the requirements. By forming and storing in advance in the gasification slag information management module the properties of slag obtained from different raw materials under different gasification furnace operating parameters, a one-to-one correspondence can be obtained between the type of gasification furnace, the raw materials, the gasification furnace operating parameters, and the properties of the slag. As a result, by using the previously stored properties of the slag, it can be determined whether the obtained gasification slag is abnormal, and the cause of the abnormality can be diagnosed based on the correspondence.

[0054] In order to ensure the stable operation of the gasifier, the gasification raw material blending subsystem of this embodiment further includes a gasifier early warning module, which forms a functional relationship between blended raw materials, gasifier operation parameters, and slag properties, and predicts the corresponding slag properties based on the obtained blended raw materials and gasifier operation parameters of the raw material blending plan with the best technical and economical efficiency, and judges whether the obtained slag properties are abnormal. The gasifier early warning module forms a slag property prediction model based on, but is not limited to, the BP neural network. A raw material blending plan from the raw material blending plan optimization module is obtained. Based on the blended raw materials of the raw material blending plan and the corresponding gasifier operation parameters, the corresponding slag properties are obtained by predicting using the slag property prediction model. By using the correspondence relationship of the gasification slag information management module, the slag properties are matched and compared, and based on the comparison result, it is judged whether the slag properties are abnormal. If it is judged that the obtained slag properties are abnormal, an alarm is issued. The gasifier early warning module compares the obtained slag properties with the previously stored slag properties obtained by matching, and obtains the parameters related to the abnormality of the slag properties based on the correspondence between the previously stored slag properties, the type of gasifier, the raw materials, and the gasifier operation parameters. This is used to diagnose the gasification process and find problems. If the obtained slag properties are abnormal, the mixing ratio of each raw material is adjusted according to the second best plan obtained from the raw material mixing plan optimization module, and the ratio is updated in the raw material mixing property prediction module, and the process of predicting the raw material mixing property parameters is repeated until the optimized raw material mixing plan is obtained, technical and economic evaluation is performed, the optimal slag properties raw material mixing plan is output, and the slag properties are predicted and diagnosed, and the mixing plan with the best slag properties is obtained.

[0055] Hereinafter, this embodiment will be described using specific data.

[0056] Sample preparation Coal samples with particle size smaller than 0.2 mm were prepared according to the “Method of preparing coal samples” in GB-T474-2008, and slag samples were prepared according to the “Slag composition analysis” in GB-T1574-2007.

[0057] Basic properties In the present invention, the industrial analysis of the sample may be performed using a TGA701 industrial analyzer, the elemental analysis of the sample may be performed using a VARIO Macro elemental analyzer, the calorific value may be measured using an IKA C6000 oxygen combustion calorimeter, or the chemical composition of the slag of the sample may be measured using an X-ray fluorescence spectrometer. Industrial analysis of coal is also called technical analysis or practical analysis, and includes the measurement of moisture, ash, volatile matter and the calculation of fixed carbon in coal. Elemental analysis of coal is to determine the content of five elements, namely carbon, hydrogen, oxygen, nitrogen, and sulfur in coal. In the present invention, laser-induced breakdown spectroscopy may be used to measure raw material property parameters, including the content of carbon, hydrogen, sulfur, and elements that form ash, ash, volatile matter, and calorific value.

[0058] Ash melting properties Based on GB / T 219-2008 "Method of measurement of coal slag melting property", the melting characteristic temperatures (deformation temperature DT, softening temperature ST, hemisphere temperature HT, flow temperature FT) of the slag samples were measured using a CAF-5 slag melting point tester from Carbolite, UK. First, the slag samples were made into triangular pyramids with a certain shape and dimensions, placed in a high-temperature furnace in a weakly reducing environment, and heated at a certain temperature rate. The changes in the slag pyramids during the temperature increase were recorded with a camera, and the ash melting characteristic temperatures were obtained by software analysis or visual observation.

[0059] The measurement of the viscosity-temperature characteristics of slag refers to the power industry standard DL / T 600-2007 "Test method for viscosity of coal slag at high temperature". The viscosity-temperature characteristics of the slag samples were measured using a RV DV-III type high-temperature rotational viscometer manufactured by Theta Corporation, USA. The process was as follows: (1) Coal slag was prepared; (2) The measurement temperature was determined by the flow temperature or complete liquidus temperature of the coal slag; (3) The coal slag was premelted in a high-temperature furnace, and clinker for measurement was formed after cooling and cooling; (4) The clinker was placed in a measurement crucible, and a vacuum was created using a vacuum protection tube, after which a specified gas was passed through; (5) The temperature was raised to the measurement temperature, and the measurement was started after the temperature was stabilized. The cooling rate was 1°C / min; (6) The measurement was stopped when the viscosity exceeded 300 Pa.s, and the relationship between the viscosity and temperature of the slag samples was obtained.

[0060] Slurry Formation Characteristics The apparent viscosity of the water-coal slurry was measured using the NXS-4C water-coal slurry viscometer developed by China National Water-Coal Slurry Engineering Technology Research Center and Chengdu Measuring Instrument Factory. The actual concentration of the coal-water slurry was measured according to GB / T 18856.2-2008 "Part 2 of the test method for coal-water mixtures: Determination of mass percent solids". The fluidity of the coal-water slurry was measured by visual inspection and divided into four levels: A: continuous flow, B: semi-continuous flow, C: intermittent flow, and D: no flow. The actual concentration of the coal-water slurry was measured according to GB / T 18856.2-2008 "Part 5 of the test method for coal-water mixtures: Determination of stability".

[0061] Gasification reaction characteristics The gasification reaction characteristics of the samples were measured using a STA 449-F5 thermal analyzer manufactured by NETZSCH, Germany. The measurement conditions were a temperature rise rate of 15°C / min, a temperature rise range of 25 to 1400°C, and high-purity N 2 (99.999%) as protective gas, with a flow rate of 20 mL / min, and the furnace environment was CO 2 (99.999%) and N 2The gas mixture was 0.01% (99.999%) and the flow rate was 50 mL / min. The gasification reaction characteristic curve was obtained by the measurement, and the reactivity index was obtained.

[0062] It was determined that the gasifier was a GE water-coal-slurry gasifier, and the requirements of the GE coal-water slurry gasifier for the raw materials fed to the furnace, which were used by the raw material standard control module, were as follows: calorific value >25.12 MJ / kg, inherent moisture ≦8%, coal-slurry concentration ≧60%, apparent viscosity ≦1500 MPa.s, ash content ≦13%, and slag melting point ≦1300°C. Based on the requirements of the GE coal-water slurry gasifier for the raw materials fed to the furnace and the on-site conditions, it was determined that the raw materials fed to the furnace were obtained by mixing coal and semi-coke. The raw material property rapid analysis module was used to perform raw material property analysis on the two individual raw materials, and the property parameters of each raw material were obtained. The raw material property parameters included the contents of carbon, hydrogen, sulfur, and slag-forming elements, ash content, volatile matter, and calorific value. The ash melting characteristics, slurry formation characteristics, and gasification reaction characteristics of the raw materials were obtained through on-site experiments. The basic properties and ash melting characteristics of coal and semi-coke are shown in Table 1. The slurry formation characteristics of coal and semi-coke powder are shown in Table 2. The gasification reaction characteristics of coal and semi-coke powder are shown in Table 3.

[0063] [Table 1]

[0064] [Table 2]

[0065] [Table 3]

[0066] The blended raw material property prediction module formed a basic property prediction model based on the linear weighted sum algorithm, and formed an ash melting property prediction model, a slurry formation property prediction model, and a gasification reaction property prediction model based on the BP neural network. By using the raw material property parameters stored in the raw material information management module, a data group was generated to train the BP neural network.

[0067] Taking the formation of an ash fusion property prediction model based on the BP neural network as an example, the formation of the prediction model is explained as follows: 80 raw material samples were collected (see Table A below), the basic properties and ash fusion properties of the coal samples were measured, and the obtained experimental data was used to form the prediction model. 40 pieces of data were used to form the model, and the remaining 40 were used to verify the prediction effect of the model. The BP neural network had a three-layer network structure. The input layer was the individual raw material property parameters and blending ratio, and the output layer was the blended raw material property parameters. The weight values ​​and thresholds of the BP neural network were optimized using the error backpropagation algorithm. The neurons in the hidden layer mainly used S-type transfer functions (e.g., tansig in Matlab), and the neurons in the output layer mainly used linear transfer functions (e.g., purelin in Matlab). The results showed that the model predicted values ​​and actual values ​​were in good agreement.

[0068] [Table 4]

[0069] JPEG0007668270000005.jpg164169

[0070] The raw material property parameters were input, and the raw material blend property parameters were predicted using a basic property prediction model, an ash melting property prediction model, a slurry formation property prediction model, and a gasification reaction property prediction model, respectively.

[0071] In this embodiment, the objective is to minimize the price of the raw materials blend, and an objective function is formed by the raw materials blend proposal economics evaluation module.

[0072]

number

[0073] The prices of coal and semi-coke are 500 yuan / ton and 200 yuan / ton, respectively. The constraints for determining the objective function are as follows: The mixing ratio of semi-coke powder is

[0074]

number

[0075] The calorific value of the raw materials is

[0076]

number

[0077] There are restrictions on heat generation

[0078]

number

[0079] The ash melting properties of the blended raw materials are

[0080]

number

[0081] The constraints on ash melting properties

[0082]

number

[0083] The slag content of the mixed raw materials

[0084]

number

[0085] Slag content restrictions

[0086]

number

[0087] The moisture content of the raw materials

[0088]

number

[0089] Water restrictions

[0090]

number

[0091] The slurry forming properties of the blended raw materials

[0092]

number

[0093] The gasification reactivity of the blended raw materials is

[0094]

number

[0095] M ad is the specific moisture content, HGI is the grindability index, O ad is the oxygen content, C d is the carbon content, A d is the slag content, CaO, Fe 2 O 3 , MgO and Na 2O indicates the content of each listed oxide, V daf indicates the content of volatile matter, and S BET indicates the specific surface area, and M ad The measurement method of inherent moisture content can refer to GB2565-2014, the measurement method of HGI grindability index can refer to GB / T 212-2008, S BET However, the measurement method of the specific surface area can refer to GB / T 19587-2017, and the rest can be obtained from the raw material property parameters.

[0096] The optimal blended coal ratio was obtained by an optimization model formed based on a genetic algorithm with the objective function and constraints as inputs and the blending ratio as output. The blended coal ratio was 97% and 3% semi-coke powder, and the price was 491 yuan / ton. A genetic algorithm usually converts a constrained problem into an unconstrained problem by a penalty function method. In this embodiment, the raw material property parameters are taken as individuals of a group, and the group is divided into several subgroups. Based on the fitness value of the individuals, the optimal solution is obtained through cyclic operations of selection, crossover, and mutation. The genetic algorithm is a conventional technology, and the specific process is omitted.

[0097] The raw material blend proposal economic evaluation module called up the process simulation software, and a gasification simulation and technical-economic evaluation of the obtained raw material blend proposal were performed. The results of the gasification simulation are shown in Table 4, and the technical-economic evaluation is shown in Table 5.

[0098] [Table 5]

[0099] [Table 6]

[0100] It was determined whether the current raw material blending plan met the economic evaluation requirements. If it met, the current raw material blending plan was used as the optimal raw material blending plan. In the opposite case, the economic evaluation of the alternative feasible raw material blending plan was performed until the optimal raw material blending plan was obtained. The alternative feasible raw material blending plan was the second best raw material blending plan output by the objective function. The gasifier early warning module performed a prediction on the obtained slag properties. By using the correspondence relationship in the gasification slag information management module, matching and comparison were performed on the obtained slag properties. The gasifier early warning module issued an alarm that the residual carbon amount of the coarse slag and fine slag reached the upper limit. The operator compared the raw material blending plans by using the raw material property parameters in the raw material information management module and the slag property correspondence relationship previously stored in the gasification slag information management module, and made a judgment on the blended raw materials as a result. For example, in this embodiment, if it was found by comparison that the gasification reactivity of the coal in the blended raw material used was relatively low, it was diagnosed that the possible reason was that the carbon content in the gasification residue was relatively high. As a result, the blending ratio of each raw material was updated by the feedstock property prediction module to reduce the ratio of coal in the blended raw material. The above process was repeated until the problem of the relatively high carbon content in the gasification residue was finally solved and an optimal feedstock blending plan was obtained.

[0101] As shown in Fig. 3, the second aspect of the present invention provides an intelligent gasification feedstock blending method including a gasification feedstock blending substep. The gasification feedstock blending substep includes: a step of acquiring characteristic spectral line intensity of the feedstock to be supplied to the furnace, and acquiring feedstock property parameters of the feedstock based on the characteristic spectral line intensity; a step of forming a prediction model, and predicting the property parameters of the blended feedstock by the prediction model based on the feedstock property parameters and the feedstock blending ratio; a step of forming an optimization model, and acquiring an optimized feedstock blending plan by the optimization model based on the property parameters of the blended feedstock; and a step of performing a technical-economic analysis on the optimized feedstock blending plan, and outputting the feedstock blending plan with the best technical-economic efficiency.

[0102] Alternatively, the method further includes a feedstock property criterion sub-step, which includes the following steps: forming and storing a correspondence relationship between different types of gasifiers and feedstocks corresponding to the gasifiers in order to determine the feedstock to be supplied to the gasifier after determining the type of the gasifier;

[0103] Alternatively, the property parameters of the blended raw material include basic properties, ash melting properties, slurry formation properties, and gasification reaction properties.

[0104] Alternatively, the basic properties include a proximate analysis parameter, an elemental analysis parameter, a grindability parameter, and a calorific value parameter.

[0105] Alternatively, the method further includes an information management substep, which includes the following steps: storing the feedstock property parameters obtained from the feedstock property rapid analysis module, forming and storing a correspondence relationship between different types of gasifiers and operation parameters corresponding to the gasifiers, forming and storing a correspondence relationship between predictions of ash melting properties and slurry formation properties and additives corresponding to the predictions, and forming and storing a one-to-one correspondence relationship between the type of gasifier, the feedstock, the gasifier operation parameters, and the properties of slag.

[0106] Alternatively, the gasification feedstock blending sub-step further includes the following steps: forming a functional relationship between the blended feedstock, the gasification furnace operation parameters, and the properties of slag, and predicting the properties of the corresponding slag based on the blended feedstock and the gasification furnace operation parameters of the obtained feedstock blending plan with the best technical and economical efficiency, and predicting whether the obtained slag properties are abnormal.

[0107] Alternatively, the gasification raw material blending sub-step further includes the following steps: When it is determined that the obtained slag properties are abnormal, a step of comparing the obtained slag properties with pre-stored slag properties, and obtaining parameters related to the abnormality of the slag properties based on the correspondence between the pre-stored slag properties, the type of gasifier, the raw materials, and the gasifier operation parameters.

[0108] In the above technical solution of the present invention, the raw materials are quickly analyzed to obtain raw material property parameters, a prediction model is formed based on the obtained raw material property parameters to predict the blended raw material property parameters, a raw material blending plan is optimized based on the target function formed based on the blended raw material property parameters, and a technical and economic analysis is performed on the optimized raw material blending plan to obtain the best raw material blending plan, thereby building an intelligent gasification raw material blending system with a full life cycle process, effectively improving the efficiency and accuracy of blending coal, achieving intelligent and accurate control of gasification raw material blending, and effectively reducing the adverse impacts on enterprises caused by raw material property problems.

[0109] The present application will be described based on flowcharts and / or block diagrams of the method, device (system) and computer program product of the present application according to the embodiments of the present application. It should be understood that the instructions of a computer program can realize each flow and / or block in the flowcharts and / or block diagrams, and can realize combinations of each flow and / or block in the flowcharts and / or block diagrams. These computer program instructions can be provided to a processor of a general purpose computer, a special purpose computer, an embedded processor or other programmable data processing device to manufacture a machine and manufacture an apparatus in which the instructions executed by the processor of the computer or other programmable data processing device realize the functions specified by one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0110] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture that includes a command device that implements the functions specified by one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0111] These computer program instructions may also be loaded into a computer or other programmable data processing facility to execute a series of operational steps to generate a computer-implemented process, the instructions executed by the computer or other programmable data processing facility providing steps to implement the functions specified by one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0112] Although the embodiments of the present invention have been described in detail above with reference to the drawings, the embodiments of the present invention are not limited to the specific description of the above embodiments. Many simple modifications may be made to the technical solutions of the embodiments of the present invention within the technical concept of the embodiments of the present invention. All such simple modifications fall within the scope of protection of the present invention.

[0113] It should be further noted that each specific technical feature described in the above description of the invention may be combined in any appropriate manner unless there is a contradiction, and in order to avoid unnecessary repetition, the description of various possible combinations will be omitted in the embodiments of the present invention.

[0114] Those skilled in the art can understand that all or part of the steps of the method for implementing the above embodiments can be achieved by instructing related hardware by a program. The program is stored in a storage medium and includes some instructions to make a monolithic machine, chip or processor execute all or part of the steps of the method of each embodiment of the present invention. The storage medium includes U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk and other media that can store program code.

Claims

1. A gasification feedstock blending system including a gasification feedstock blending subsystem, The gasification raw material blending subsystem includes a raw material property rapid analysis module, a blended raw material property prediction module, a raw material blending plan optimization module, and a raw material blending plan economic evaluation module; The material property rapid analysis module obtains the characteristic spectral line intensity of the material fed into the furnace, and obtains the material property parameters of the material according to the characteristic spectral line intensity, the material property parameters of the material including carbon, hydrogen, sulfur, the content of elements forming ash, ash content, volatile content and calorific value; The blended raw material property prediction module forms a prediction model, and predicts the property parameters of the blended raw materials by the prediction model based on the raw material property parameters and the blending ratio of the raw materials; the prediction model predicts the basic properties, ash melting properties, slurry formation properties, and gasification reactivity properties of the blended raw materials by forming a basic property prediction model, an ash melting property prediction model, a slurry formation property prediction model, and a gasification reactivity property prediction model, respectively; the basic property prediction model is formed based on a linear weighted sum algorithm, and the ash melting property prediction model, the slurry formation property prediction model, and the gasification reactivity property prediction model are formed based on an algorithm including a BP neural network or a convolutional neural network; The raw material blending plan optimization module forms an optimization model, obtains an optimized raw material blending plan through the optimization model based on the property parameters of the blended raw materials, performs optimization using one or more objective functions according to the requirements for the raw material blending plan and the constraints of the objective function, and outputs an optimized raw material blending plan; The raw material blending plan economic evaluation module performs technical and economic analysis on the optimized raw material blending plan, and outputs the raw material blending plan with the best technical and economic efficiency. The raw material blending plan economic evaluation module calls the process simulation software to perform a gasification simulation of the obtained raw material blending plan, and performs technical and economic evaluation by determining whether the current raw material blending plan meets the economic evaluation requirements. If the answer is "yes," the current raw material blending plan is used as the optimal raw material blending plan; otherwise, evaluation is performed on alternative candidate feasible raw material blending plans until an optimal raw material blending plan is obtained, and the alternative candidate feasible raw material blending plan is a suboptimal scheme output by the objective function. The characteristic parameters of the blended raw materials include basic properties, ash melting characteristics, slurry formation characteristics, and gasification reaction characteristics; The basic properties include proximate analysis parameters, elemental analysis parameters, grindability parameters, and calorific value parameters; The proximate analytical parameters include moisture, ash, volatile matter and fixed carbon; The elemental analysis parameters include carbon, hydrogen, oxygen, nitrogen and sulfur. A gasification feedstock blending system.

2. The system further includes a raw material property reference subsystem having a reference management module for raw material supplied to the gasifier, which forms and stores a correspondence relationship between different types of gasifiers and raw materials corresponding to the gasifiers in order to determine the raw material to be supplied to the gasifier after determining the type of the gasifier. The gasification feedstock blending system according to claim 1 .

3. The property parameters of the blended raw materials predicted by the prediction model are an industrial analysis parameter, an elemental analysis parameter, a calorific value parameter, and an ash melting characteristic parameter. The gasification feedstock blending system according to claim 1 .

4. The system includes an information management subsystem, the information management subsystem including a raw material information management module, a gasifier information management module, an additive information management module, and a gasification slag information management module; The raw material information management module stores the raw material property parameters obtained from the raw material property rapid analysis module; The gasification furnace information management module forms and stores a correspondence relationship between different types of gasification furnaces and operation parameters corresponding to the gasification furnaces; The additive information management module forms and stores a correspondence between predictions of ash melting characteristics and slurry formation characteristics and additives corresponding to the predictions; The gasification raw material blending system described in claim 3, characterized in that the gasification slag information management module forms and stores a one-to-one correspondence between the type of gasification furnace, raw materials, gasification furnace operating parameters, and slag properties.

5. The gasification feedstock blending subsystem further includes a gasification furnace early warning module for forming a functional relationship between blended feedstock, gasification furnace operation parameters, and slag properties, and predicting corresponding slag properties based on the blended feedstock and gasification furnace operation parameters of the obtained feedstock blending plan with optimal technical economy, and determining whether the obtained slag properties are abnormal. The gasification feedstock blending system according to claim 4.

6. When it is determined that the obtained slag properties are abnormal, the gasifier early warning module compares the obtained slag properties with pre-stored slag properties, and obtains parameters related to the abnormality of the slag properties based on the correspondence between the pre-stored slag properties, the type of the gasifier, the raw materials, and the gasifier operation parameters. The gasification feedstock blending system according to claim 5.

7. The blended raw material property prediction module forms a prediction model, and the blended raw material property prediction module predicts the blended raw material property parameters by the prediction model based on the raw material property parameters, the raw material blending ratio, the internal moisture content Mad, the grindability index GI, the specific surface area SBET, and additive information, and the predicted blended raw material property parameters include the slurry formation characteristics of the blended raw material, the gasification reaction characteristics of the blended raw material, and the ash melting characteristics. The gasification feedstock blending system according to claim 1 .

8. A gasification feedstock blending method including a gasification feedstock blending sub-step, the gasification feedstock blending sub-step comprising: a rapid analysis step of obtaining a characteristic spectral line intensity of the raw material fed to the furnace and obtaining a raw material property parameter of the raw material based on the characteristic spectral line intensity; A blended raw material property prediction step of forming a prediction model and predicting the property parameters of the blended raw materials using the prediction model based on the raw material property parameters and the raw material blending ratio; A raw material blending plan optimization step of forming an optimization model and obtaining an optimized raw material blending plan based on the property parameters of the raw material blend; A raw material blending plan economic evaluation step of performing a technical and economic analysis of the optimized raw material blending plan and outputting the raw material blending plan with the best technical and economic efficiency; In the step of rapidly analyzing the raw material properties, the raw material characteristic parameters of the raw material include carbon, hydrogen, sulfur, the content of elements forming ash, ash content, volatile matter and calorific value; In the blended raw material property prediction step, the prediction model predicts the basic properties, ash melting properties, slurry formation properties, and gasification reactivity properties of the blended raw materials by forming a basic property prediction model, an ash melting property prediction model, a slurry formation property prediction model, and a gasification reactivity property prediction model, respectively, and the basic property prediction model is formed based on a linear weighted sum algorithm, and the ash melting property prediction model, the slurry formation property prediction model, and the ash melting property prediction model are formed based on an algorithm including a BP neural network or a convolutional neural network; In the raw material blending plan optimization step, optimization is performed using one or more objective functions according to the requirements for the raw material blending plan and constraints of the objective functions, and an optimized raw material blending plan is output; In the raw material blending plan economic evaluation step, a process simulation software is called to perform a gasification simulation of the obtained raw material blending plan, and a technical and economic evaluation is performed by determining whether the current raw material blending plan meets the economic evaluation requirements, and if the answer is "yes," the current raw material blending plan is used as the optimal raw material blending plan; if not, an evaluation is performed on alternative candidate feasible raw material blending plans until an optimal raw material blending plan is obtained, and the alternative candidate feasible raw material blending plan is a suboptimal scheme output by an objective function; The property parameters of the blended raw materials include basic properties, ash melting properties, slurry formation properties, and gasification reaction properties; The basic properties include proximate analysis parameters, elemental analysis parameters, grindability parameters, and calorific value parameters; The proximate analytical parameters include moisture, ash, volatile matter and fixed carbon; The elemental analysis parameters include carbon, hydrogen, oxygen, nitrogen and sulfur. A method for blending raw materials for gasification.

9. The method further comprises a feedstock property criteria sub-step, the feedstock property criteria sub-step comprising: The method includes a step of forming and storing a correspondence relationship between different types of gasification furnaces and raw materials corresponding to the gasification furnaces in order to determine the raw materials to be supplied to the furnace after the type of the gasification furnace is determined. The method for blending raw materials for gasification according to claim 8.

10. The property parameters of the blended raw materials predicted by the prediction model are proximate analysis parameters, elemental analysis parameters, calorific value parameters, and ash melting characteristic parameters. The method for blending raw materials for gasification according to claim 8.

11. The method includes an information management sub-step, the information management sub-step comprising the steps of: storing the raw material property parameters obtained from the raw material property rapid analysis module; forming and storing a correspondence between different types of gasifiers and operation parameters corresponding to the gasifiers; forming and storing a correspondence between predictions of ash melting characteristics and slurry formation characteristics and additives corresponding to the predictions; The method for blending gasification raw materials according to claim 10, further comprising a step of forming and storing a one-to-one correspondence between the type of gasification furnace, the raw materials, the gasification furnace operation parameters, and the properties of the slag.

12. The gasification feedstock blending sub-step further comprises the steps of: forming a functional relationship between the raw material blend, the gasification furnace operation parameters, and the properties of the slag, and predicting the properties of the corresponding slag based on the raw material blend and the gasification furnace operation parameters of the obtained raw material blend plan with optimal technical economy, and judging whether the obtained properties of the slag are abnormal. The method for blending raw materials for gasification according to claim 11.

13. The gasification feedstock blending sub-step further includes the steps of: and when it is determined that the properties of the obtained slag are abnormal, comparing the properties of the obtained slag with pre-stored properties of the slag, and obtaining parameters related to the abnormality of the properties of the slag based on the correspondence between the pre-stored properties of the slag, the type of the gasifier, the raw materials, and the gasifier operation parameters. The method for blending gasification feedstocks according to claim 12.

14. The method further comprises forming a prediction model, predicting the property parameters of the blended raw materials by the prediction model based on the raw material property parameters, the raw material blending ratio, the internal moisture content Mad, the grindability index HGI, the specific surface area SBET, and additive information, and the predicted property parameters of the blended raw materials include a slurry formation characteristic of the blended raw materials, a gasification reaction characteristic of the blended raw materials, and an ash melting characteristic. The method for blending raw materials for gasification according to claim 8.

Images