Device system and method for autonomously regulating and controlling feeding parameters of entrained-flow bed coal gasifier

Abstract

The invention relates to a device system and method for autonomously regulating and controlling feeding parameters of an entrained-flow bed coal gasifier. The device system comprises a feeding unit, an ash analysis unit, a gasifier state analysis unit, a data storage platform and a feeding parameter autonomous calculation unit, the feeding unit comprises a feeding control unit and a feeding analysis unit; the data output ends of the feeding control unit, the feeding analysis unit, the ash analysis unit and the gasifier state analysis unit are connected with the data storage platform; the data output end of the data storage platform is connected with the feeding parameter autonomous calculation unit; and the signal output end of the feeding parameter autonomous calculation unit is connected with the feeding control unit. The method can effectively solve the problem that the judgment of an operator is not timely and inaccurate during the operation of the existing coal gasifier, and overcomes the limitation of only depending on theoretical calculation or empirical data, so that the coal gasification efficiency is effectively improved, and the coal conversion rate is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of gasifiers, and particularly relates to a device system and method for autonomously regulating the feed parameters of an entrained flow coal gasifier. Background Art

[0002] Coal gasification is the core technology for realizing the clean and efficient conversion of coal, and is mainly used for producing clean fuels and chemicals, including synthetic ammonia, methanol, natural gas, oil products, olefins, ethylene glycol, etc. Coal gasification technologies include fixed bed gasification, fluidized bed gasification, and entrained flow gasification, etc. Among them, entrained flow gasification technology has become the mainstream coal gasification technology in the market due to its advantages such as wide coal type applicability and large processing capacity. The feed of entrained flow gasification is water, oxygen, and coal, and in a high-temperature and high-pressure environment, synthesis gas is generated through complex reactions. The content of effective synthesis gas components, carbon conversion rate, cold gas efficiency, etc. are important indicators for evaluating the performance of coal gasification.

[0003] In industrial production, the efficient and stable operation of the gasifier can be achieved by regulating the oxygen-to-coal ratio, the mass ratio of steam to oxygen, and the water-to-coal ratio. However, in the production process, due to the complex diversity of coal quality, the production process often fluctuates. For example, fluctuations in factors such as the carbon-hydrogen ratio, ash content, and moisture content of coal will cause fluctuations in the temperature and pressure inside the furnace, thereby affecting the gasification efficiency. In addition, fluctuations in the differential pressure of the gasification burner will also lead to incomplete reactions. Therefore, it is necessary to adjust the gasification feed parameters in a timely manner. At present, the existing adjustment methods mainly rely on observing the temperature, pressure, and synthesis gas composition inside the gasifier to adjust the gasification parameters. This method has certain empiricism, and due to reasons such as the high temperature inside the gasifier, complex flow field, and lag in temperature display, the adjustment of process parameters is not timely enough, and it is greatly affected by human factors, thus affecting the gasification efficiency and increasing production energy consumption. In order to improve the energy conversion efficiency and promote the green upgrading of the industry, it is urgent to regulate the coal gasification parameters through the digital transformation of coal gasification and the analysis with the help of the Internet of Things, so as to maintain the stable and efficient operation of the coal gasifier.

[0004] For example, CN102399594A discloses a control method for the operating conditions of a "Texaco gasifier" in a Texaco water coal slurry pressurized gasification process with a "quenching process". By screening the data at corresponding time points under steady-state conditions, no less than 300 sets of historical data samples are collected, and based on this, a BP neural network model is used to predict the "effective gas production rate" in the gasification system.

[0005] CN115125037A discloses a method for online adjustment of gasifier operation parameters. Based on coal quality data and effective gas demand, combined with the theories of element conservation, energy conservation, and minimization of Gibbs free energy, the target coal quantity and target oxygen quantity are calculated. Meanwhile, based on the actual operation data and actual oxygen input of the gasifier, the actual coal input is calculated using the carbon element balance principle, and the coal flow rate is adjusted accordingly.

[0006] Therefore, it is very important to achieve the autonomous control and online real-time adjustment of the gasifier. However, most of the above methods focus on theoretical model calculations and analysis and speculation based on historical data. Although they can provide guidance to a certain extent, in actual applications, due to certain deviations between theory and practice and situations such as sudden changes in coal types, they often cannot effectively adapt to complex production environments. Therefore, providing a device system and method for autonomously controlling the feed parameters of an entrained flow gasifier is a technical problem that needs to be solved in the current field. Summary of the Invention

[0007] Aiming at the deficiencies of the existing technology, the purpose of the present invention is to provide a device system and method for autonomously controlling the feed parameters of an entrained flow gasifier. Compared with the existing technology, the present invention can effectively solve the problems of untimely and inaccurate judgment by operators during the operation of existing gasifiers, and at the same time overcome the limitations of relying only on theoretical calculations or empirical data, thereby effectively improving the gasification efficiency and enhancing the coal conversion rate.

[0008] To achieve the purpose of this invention, the following technical solutions are adopted:

[0009] In the first aspect, the present invention provides a device system for autonomously controlling the feed parameters of an entrained flow gasifier. The device system includes a feeding unit, a slag analysis unit, a gasifier state analysis unit, a data storage platform, and a feed parameter autonomous calculation unit;

[0010] The feeding unit includes a feeding control unit and a feeding analysis unit;

[0011] The data output ends of the feeding control unit, the feeding analysis unit, the slag analysis unit, and the gasifier state analysis unit are connected to the data storage platform;

[0012] The data output end of the data storage platform is connected to the feed parameter autonomous calculation unit;

[0013] The signal output end of the feed parameter autonomous calculation unit is connected to the feeding control unit.

[0014] In the device system provided by the present invention, the feed analysis unit acquires the physical parameters of the feed, the feed control unit acquires the feed control parameters, the ash analysis unit acquires the ash characteristics parameters, and the gasifier state analysis unit acquires the gasifier characteristics parameters. The acquired parameters are transmitted to the data storage platform through the data output terminal and stored in the data storage platform; the data storage platform can also transmit the stored data to the feed parameter self-calculation unit through the data output terminal, and the data is processed and calculated in the feed parameter self-calculation unit to obtain the optimal feed control parameters; the feed parameter self-calculation unit transmits the optimal feed control parameters to the feed control unit in the form of a control signal, thereby realizing the autonomous regulation of the feed.

[0015] In the present invention, the entrained flow gasifier includes a water coal slurry gasifier and a pulverized coal gasifier. The pulverized coal gasifier uses dry pulverized coal as the raw material, and the pulverized coal is transported into the gasifier through pneumatic conveying; the water coal slurry gasifier uses water coal slurry as the raw material, and a high-pressure pump is used to transport the water coal slurry to the gasifier.

[0016] Preferably, the feed analysis unit includes a raw coal analysis unit, a raw water analysis unit, and a raw oxygen analysis unit.

[0017] Preferably, the raw coal analysis unit includes a raw coal quality measuring device, an elemental analyzer, an industrial analyzer, a sulfur content measuring instrument, and a calorific value measuring instrument.

[0018] Preferably, the raw water analysis unit includes a temperature sensor, a flow meter, and a pressure sensor.

[0019] Preferably, the raw oxygen analysis unit includes a temperature sensor, a pressure sensor, a flow meter, and an oxygen component analyzer.

[0020] Preferably, the ash analysis unit includes an ash content analyzer, a moisture analyzer, an elemental analyzer, and a mass meter.

[0021] Preferably, the gasifier state analysis unit includes a syngas component analyzer, a gasifier temperature sensor, and a gasifier pressure sensor.

[0022] Preferably, the feed control unit includes a raw coal feed sensor, a raw water feed valve, and a raw oxygen feed valve.

[0023] In a second aspect, the present invention provides a method for autonomously regulating the feed parameters of an entrained flow gasifier. The method uses the device system for autonomously regulating the feed parameters of an entrained flow gasifier provided in the first aspect of the present invention. The method includes the following steps:

[0024] (1)Collect the feed physical parameters of the feed analysis unit, the feed control parameters of the feed control unit, the ash residue characteristic parameters of the ash residue analysis unit, and the gasifier characteristic parameters of the gasifier state analysis unit, and transmit them to the data storage platform for storage to form historical production data;

[0025] (2)Process the historical production data stored in the data storage platform in step (1), establish a multivariate optimization model for the feed control parameters, and form a program for the feed parameter independent calculation unit;

[0026] (3)During actual operation, transmit the feed physical parameters, ash residue characteristic parameters, and gasifier characteristic parameters to the feed parameter independent calculation unit in real time through the data storage platform, and use the multivariate optimization model obtained in step (2) for calculation to obtain the optimal feed control parameters;

[0027] (4)Transmit the optimal feed control parameters obtained in step (3) to the feed control unit, and the feed control unit adjusts according to the feed control parameters, so as to realize the independent control of the feed.

[0028] In the method provided by the present invention, a multivariate optimization model for the feed control parameters is established by combining the calculation data of the theoretical model and the historical production data, and the optimal feed control parameters can be calculated according to the real-time data, with good accuracy.

[0029] Preferably, the process of establishing the multivariate optimization model in step (2) includes:

[0030] S1. Establish a first data set, which includes the actual values of the feed physical parameters, feed control parameters, ash residue characteristic parameters, and gasifier characteristic parameters;

[0031] S2. Use the feed physical parameters in the first data set as input data, construct a theoretical model, and calculate the theoretical feed control parameters, ash residue characteristic parameters, and gasifier characteristic parameters;

[0032] S3. Use the actual values of the feed physical parameters, feed control parameters, ash residue characteristic parameters, and gasifier characteristic parameters in the first data set and the theoretical values of the feed control parameters, ash residue characteristic parameters, and gasifier characteristic parameters obtained in step S2 to construct a second data set, and extract the ash residue characteristic parameters, gasifier characteristic parameters that meet the optimization requirements in the second data set and their corresponding feed control parameters to form a third data set;

[0033] S4. Use the actual values of the feed physical parameters in the first data set and the feed control parameters in the third data set to establish a multivariate optimization model for the feed control parameters.

[0034] In the present invention, the optimization requirements generally refer to the working conditions with high effective gas content and low carbon content in ash. The specific values need to be determined according to the actual working conditions. Taking the water-coal slurry gasifier as an example, for example, the carbon content of gasification fine ash is controlled to be 20-30%, the carbon content of coarse slag is 3-5%, the gasification temperature is 1200-1300°C, and the effective gas content is 81-82%. The ash characteristic parameters, gasifier characteristic parameters and corresponding feeding control parameters that meet the above requirements are extracted; taking the pulverized coal gasifier as an example, for example, the carbon content of gasification fine ash is controlled to be 15-25%, the carbon content of coarse slag is 2-5%, the gasification temperature is 1400-1600°C, and the effective gas content is 89-92%. The ash characteristic parameters, gasifier characteristic parameters and corresponding feeding control parameters that meet the above requirements are extracted.

[0035] Preferably, the method for establishing the first data set in step S1 specifically comprises the following steps:

[0036] S101, preprocessing the historical production data, wherein the preprocessing includes processing missing values and duplicate values, and then performing normalization or standardization to obtain preprocessed data;

[0037] S102, performing outlier detection on the preprocessed data obtained in step S101 and removing outliers to obtain a first data set.

[0038] Preferably, step S2 specifically includes the following steps:

[0039] S201, construct theoretical models based on the physical and chemical reactions in the coal gasification process;

[0040] S202, calculating theoretical feed control parameters, ash characteristic parameters and gasifier characteristic parameters according to the feed physical parameters in the first data set and the theoretical model described in step S201.

[0041] Preferably, the theoretical model includes a thermodynamic equilibrium model and / or a rate model.

[0042] Preferably, the thermodynamic equilibrium model includes an equilibrium constant method and / or a Gibbs free energy minimization method.

[0043] Preferably, the rate model comprises a three-dimensional model and / or a reduced-order model.

[0044] Preferably, the method for establishing the multivariate optimization model in step S4 comprises the following steps:

[0045] S401. According to the actual production requirements, with the effective gas production rate and the carbon content in ash residue as the main targets and the gasifier temperature as the secondary target, the set constraints include: the volume percentage of effective gas in water-coal slurry gasification ≥ 80% or the mass percentage of effective gas in pulverized coal gasification ≥ 88%, the carbon content in fine ash ≤ 35%, the carbon content in coarse slag ≤ 5%, and the gasifier temperature ≤ 1700°C; using the feed physical parameters in the first dataset as input data and the feed control parameters in the third dataset as output data, a multi-objective optimization model is established.

[0046] S402. Combine the feed physical parameters in the first dataset and the feed control parameters in the third dataset, and divide them into a training set and a test set.

[0047] Based on the multi-objective optimization algorithm of machine learning, use the training set to train the multi-objective optimization model, and use the test set for verification. Adjust and optimize the multi-objective optimization model according to the verification results to obtain the multi-objective optimization model of the feed control parameters.

[0048] Preferably, the multi-objective optimization algorithm based on machine learning includes any one or a combination of at least two of the principal component analysis method, the deep learning method, the random forest method, or the ensemble learning method.

[0049] In the present invention, the feed physical parameters include the physical parameters of coal, oxygen, water, water-coal slurry, etc.

[0050] In the present invention, the physical parameters of coal include temperature, total water, industrial analysis parameters, elemental analysis parameters, sulfur, calorific value, etc.

[0051] In the present invention, the physical parameters of oxygen include temperature, pressure, purity, etc.

[0052] In the present invention, the physical parameters of water include temperature, pressure.

[0053] In the present invention, the physical parameters of water-coal slurry include concentration, temperature, pressure, etc.

[0054] In the present invention, the feed control parameters include the mass of coal, the flow rate of water, the flow rate of oxygen, the flow rate of water-coal slurry, etc.

[0055] In the present invention, the ash residue characteristic parameters include the mass of gasification coarse slag, the ash content in gasification coarse slag, the moisture content in gasification coarse slag, the carbon element content in gasification coarse slag, the mass of gasification fine ash, the ash content in gasification fine ash, the moisture content in gasification fine ash, the carbon element content in gasification fine ash, etc.

[0056] In the present invention, the gasifier characteristic parameters include the temperature, pressure, and syngas composition in the reaction zone of the gasifier.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] (1) The device system and method provided by the present invention can monitor data such as the physical parameters of the feed material. By combining theoretical calculations and actual data, it can adjust the feed control parameters in real time, enabling the gasification reaction to be in a better working condition, thereby effectively improving the coal gasification efficiency, enhancing the coal conversion rate, reducing the energy loss during the gasification process, and improving the energy utilization efficiency.

[0059] (2) The device system and method provided by the present invention can solve the problems such as untimely reaction and large operation errors when production enterprises use manual experience to regulate the feed parameters of the entrained flow gasifier, and solve the problem of insufficient accuracy in the regulation method relying on theoretical calculations, historical data or calculation models with low accuracy, realizing timely and accurate regulation of the feed parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 is a schematic structural diagram of the device system provided in Embodiment 1 of the present invention;

[0061] Figure 2 is a flowchart of the methods provided in Embodiment 2 and Embodiment 3 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0062] The technical solutions of the present invention will be further described below through specific embodiments. Those skilled in the art should understand that the embodiments are only for helping to understand the present invention and should not be regarded as specific limitations on the present invention.

[0063] Embodiment 1

[0064] This embodiment provides a device system for autonomously regulating the feed parameters of an entrained flow gasifier, as Figure 1 shown. The device system includes a feed unit, a slag analysis unit, a gasifier state analysis unit, a data storage platform, and a feed parameter autonomous calculation unit;

[0065] The feed unit includes a feed control unit and a feed analysis unit;

[0066] The data output ends of the feed control unit, the feed analysis unit, the slag analysis unit, and the gasifier state analysis unit are connected to the data storage platform;

[0067] The data output end of the data storage platform is connected to the feed parameter autonomous calculation unit;

[0068] The signal output end of the feed parameter autonomous calculation unit is connected to the feed control unit;

[0069] The feed analysis unit includes a raw coal analysis unit, a raw water analysis unit and a raw oxygen analysis unit; the raw coal analysis unit includes a raw coal mass measuring instrument, an elemental analyzer, an industrial analyzer, a sulfur content measuring instrument and a calorific value measuring instrument; the raw water analysis unit includes a temperature sensor, a flow meter and a pressure sensor; the raw oxygen analysis unit includes a temperature sensor, a pressure sensor, a flow meter and an oxygen component analyzer; the ash analysis unit includes an ash analyzer, a moisture analyzer, an elemental analyzer and a mass meter; the gasifier state analysis unit includes a synthesis gas component analyzer, a gasifier temperature sensor and a gasifier pressure sensor; the feed control unit includes a raw coal feed sensor, a raw water feed valve and a raw oxygen feed valve.

[0070] Example 2

[0071] This embodiment provides a method for autonomously controlling the feeding parameters of an entrained flow coal gasifier. The method is based on the actual application of a water-coal slurry gasifier. The method uses the device system for autonomously controlling the feeding parameters of an entrained flow coal gasifier provided in Example 1, such as Figure 2 As shown, the method comprises the following steps:

[0072] (1) collecting and transmitting to the data storage platform for storage, the physical parameters of the feed analysis unit, the feed control parameters of the feed control unit, the ash characteristic parameters of the ash analysis unit, and the gasifier characteristic parameters of the gasifier state analysis unit to form historical production data;

[0073] (2) Processing the historical production data stored in the data storage platform of step (1), establishing a multivariate optimization model of feed control parameters, and forming a program of an autonomous calculation unit for feed parameters;

[0074] S1, establishing a first data set, wherein the first data set includes actual values of parameters such as total moisture content, ash content, volatile matter, fixed carbon, carbon, hydrogen, oxygen, nitrogen and sulfur content of coal, oxygen purity, temperature of raw materials (coal, oxygen, water, coal water slurry), coal water slurry pressure, oxygen pressure, mass flow rate of coal water slurry, coal water slurry concentration, volume flow rate of oxygen, moisture and carbon content of gasified fine ash and gasified coarse slag, temperature and pressure of gasifier, etc.;

[0075] S101, preprocessing the historical production data, wherein the preprocessing includes processing missing values and duplicate values, and then performing normalization processing to obtain preprocessed data;

[0076] S102, performing outlier detection on the preprocessed data obtained in step S101 and removing outliers that differ greatly from the average value to obtain a first data set;

[0077] S2. Using the feed physical parameters in the first dataset as input data, construct a theoretical model to calculate the theoretical feed control parameters, ash residue characteristic parameters, and gasifier characteristic parameters;

[0078] S201. Based on the physical and chemical reactions in the coal gasification process, construct a thermodynamic equilibrium model by the Gibbs free energy minimization method;

[0079] S202. According to the feed physical parameters in the first dataset and the thermodynamic equilibrium model described in step S201, calculate the theoretical feed control parameters, ash residue characteristic parameters, and gasifier characteristic parameters;

[0080] S3. Using the actual values of the feed physical parameters, feed control parameters, ash residue characteristic parameters, and gasifier characteristic parameters in the first dataset and the theoretical values of the feed control parameters, ash residue characteristic parameters, and gasifier characteristic parameters obtained in step S2, construct a second dataset, and extract the ash residue characteristic parameters, gasifier characteristic parameters that meet the optimization requirements and their corresponding feed control parameters in the second dataset to form a third dataset;

[0081] The optimization requirements include: the carbon element content of the fine gasification ash is 20 - 30%, the carbon element content of the coarse slag is 3 - 5%, the gasification temperature is 1200 - 1300 °C, and the effective gas content is 81 - 82%;

[0082] S4. Using the actual values of the feed physical parameters in the first dataset and the feed control parameters in the third dataset, establish a multi - optimization model for the feed control parameters;

[0083] S401. According to the actual production requirements, taking the effective gas production rate and the ash residue carbon content as the main objectives and the gasifier temperature as the secondary objective, set the constraint conditions as: the carbon content of the fine gasification ash ≤ 35%, the carbon content of the coarse slag ≤ 5%, the effective gas content ≥ 80.5%, and the gasifier temperature ≤ 1300 °C; using the feed physical parameters in the first dataset as input data and the feed control parameters in the third dataset as output data, establish a multi - optimization model;

[0084] S402. Combine the feed physical parameters in the first dataset and the feed control parameters in the third dataset, and divide them into a training set and a test set;

[0085] Based on the multi - objective optimization algorithm of machine learning, use the training set to train the multi - optimization model, and use the test set for verification. Adjust and optimize the multi - optimization model according to the verification results to obtain the multi - optimization model of the feed control parameters;

[0086] (3) During actual operation, the physical parameters of the feedstock, the ash residue characteristic parameters, and the gasifier characteristic parameters are sent to the feed parameter self-calculation unit in real time through the data storage platform, and the obtained multivariate optimization model in step (2) is used for calculation to obtain the optimal feed control parameters;

[0087] (4) The obtained optimal feed control parameters in step (3) are sent to the feed control unit, and the feed control unit adjusts according to the feed control parameters, thereby realizing the autonomous regulation of the feed.

[0088] Example 3

[0089] This example provides a method for autonomously regulating the feed parameters of an entrained flow gasifier. The method is based on the actual application of a pulverized coal gasifier. The method uses the device system for autonomously regulating the feed parameters of an entrained flow gasifier provided in Example 1, as Figure 2 shown. The method includes the following steps:

[0090] (1) The physical parameters of the feedstock of the feedstock analysis unit, the feed control parameters of the feed control unit, the ash residue characteristic parameters of the ash residue analysis unit, and the gasifier characteristic parameters of the gasifier state analysis unit are collected and sent to the data storage platform for storage, constituting historical production data;

[0091] (2) The historical production data stored in the data storage platform in step (1) is processed to establish a multivariate optimization model of the feed control parameters, forming a program for the feed parameter self-calculation unit;

[0092] S1. Establish a first data set. The first data set includes the actual values of parameters such as the total moisture, ash content, volatile matter, fixed carbon, carbon element, hydrogen element, oxygen element, nitrogen element, and sulfur element content, calorific value, oxygen purity, temperature of raw materials (coal, water, oxygen), water and oxygen pressures, mass flow rate of coal, mass flow rate of water, volume flow rate of oxygen, moisture and ash content of gasification fine ash and gasification coarse slag, gasifier temperature and pressure, etc.;

[0093] S101. Preprocess the historical production data. The preprocessing includes dealing with missing values and duplicate values, and then performing standardization processing to obtain preprocessed data;

[0094] S102. Detect outliers in the preprocessed data obtained in step S101 and remove the maximum and minimum values to obtain the first data set;

[0095] S2. Using the physical parameters of the feedstock in the first data set as input data, construct a theoretical model to calculate the theoretical feed control parameters, ash residue characteristic parameters, and gasifier characteristic parameters;

[0096] S201, Based on the physical and chemical reactions during the coal gasification process, construct a rate model by the equilibrium constant method;

[0097] S202, According to the feed physical parameters in the first dataset and the rate model described in step S201, calculate the theoretical feed control parameters, ash residue characteristic parameters, and gasifier characteristic parameters;

[0098] S3, Construct a second dataset with the actual values of the feed physical parameters, feed control parameters, ash residue characteristic parameters, and gasifier characteristic parameters in the first dataset and the theoretical values of the feed control parameters, ash residue characteristic parameters, and gasifier characteristic parameters obtained in step S2. Extract the ash residue characteristic parameters, gasifier characteristic parameters that meet the optimization requirements and their corresponding feed control parameters in the second dataset to form a third dataset;

[0099] The optimization requirements include: the carbon element content of the fine gasification ash is 15 - 25%, the carbon element content of the coarse slag is 2 - 5%, the gasification temperature is 1400 - 1600 °C, and the effective gas content is 89 - 92%;

[0100] S4, Use the actual values of the feed physical parameters in the first dataset and the feed control parameters in the third dataset to establish a multi - objective optimization model for the feed control parameters;

[0101] S401, According to the actual production requirements, with the effective gas production rate and the ash residue carbon content as the main objectives and the gasifier temperature as the secondary objective, set the constraint conditions as: the carbon content of the fine gasification ash ≤ 25%, the carbon content of the coarse slag ≤ 5%, the effective gas content ≥ 89%, and the gasifier temperature ≤ 1700 °C; Use the feed physical parameters in the first dataset as the input data and the feed control parameters in the third dataset as the output data to establish a multi - objective optimization model;

[0102] S402, Combine the feed physical parameters in the first dataset and the feed control parameters in the third dataset and divide them into a training set and a test set;

[0103] Based on the multi - objective optimization algorithm of machine learning, use the training set to train the multi - objective optimization model and use the test set for verification. Adjust and optimize the multi - objective optimization model according to the verification results to obtain the multi - objective optimization model of the feed control parameters;

[0104] (3) During actual operation, send the feed physical parameters, ash residue characteristic parameters, and gasifier characteristic parameters to the feed parameter independent calculation unit in real - time through the data storage platform, and use the multi - objective optimization model obtained in step (2) for calculation to obtain the optimal feed control parameters;

[0105] (4) Transmit the optimal feed control parameters obtained in step (3) to the feed control unit, and the feed control unit adjusts according to the feed control parameters, so as to achieve autonomous regulation of the feed.

[0106] Application Example 1

[0107] This application example provides a water coal slurry entrained flow gasification process, and the process adopts the method for autonomously regulating the feed parameters of the entrained flow coal gasifier provided in Example 2.

[0108] Coal A: The total moisture content is 18.2%, the dry basis ash content is 6.37%, the dry basis volatile matter content is 33.28%, the fixed carbon is 60.35%, the dry basis carbon content is 75.92%, the hydrogen content is 4.38%, the oxygen content is 12.01%, the nitrogen content is 0.99%, and the sulfur content is 0.33%;

[0109] Coal B: The total moisture content is 11.28%, the dry basis ash content is 12.45%, the dry basis volatile matter content is 36.37%, the fixed carbon is 53.18%, the dry basis carbon content is 69.35%, the hydrogen content is 4.12%, the oxygen content is 12.84%, the nitrogen content is 0.71%, and the sulfur content is 0.53%;

[0110] When the feed raw material is adjusted from Coal A to Coal B, by adopting the method of Example 2 for regulation, adjusting the feed control parameters, and further adjusting the coal-water ratio and the oxygen-coal ratio, compared with the manual experience regulation, the content of effective gas can be increased by more than 0.9%.

[0111] Application Example 2

[0112] This application example provides a pulverized coal entrained flow gasification process, and the process adopts the method for autonomously regulating the feed parameters of the entrained flow coal gasifier provided in Example 3.

[0113] Coal A: The total moisture content is 17.6%, the dry basis ash content is 8.92%, the dry basis volatile matter content is 34.57%, the fixed carbon is 56.51%, the dry basis carbon content is 72.39%, the hydrogen content is 4.53%, the oxygen content is 12.78%, the nitrogen content is 0.96%, and the sulfur content is 0.43%;

[0114] Coal B: The total moisture content is 9.56%, the dry basis ash content is 7.35%, the dry basis volatile matter content is 35.99%, the fixed carbon is 56.66%, the dry basis carbon content is 76.55%, the hydrogen content is 4.26%, the oxygen content is 10.23%, the nitrogen content is 0.76%, and the sulfur content is 0.67%;

[0115] When the feedstock is adjusted from coal A to coal B, by adopting the method of Example 3 for regulation and control, the feed control parameters are adjusted, and then the feed rates of raw coal, oxygen and water are adjusted. Compared with the regulation and control based on manual experience, the content of effective gas can be increased by more than 1.2%.

[0116] Application Example 3

[0117] This application example provides a water coal slurry entrained flow gasification process, and the process adopts the method for independently regulating and controlling the feed parameters of the entrained flow gasifier provided in Example 2.

[0118] When the water coal slurry concentration is adjusted from 60% to 65%, by adopting the method of Example 2 for regulation and control, the feed control parameters are adjusted, so as to adjust the oxygen-to-coal ratio from 510 Nm 3 / m 3 to 495 Nm 3 / m 3 . Compared with the regulation and control based on manual experience, the content of effective gas can be increased by more than 3.5%.

[0119] In summary, the present invention can effectively solve the problems of untimely and inaccurate judgment by operators during the operation of the existing gasifier, and at the same time overcome the limitations of relying only on theoretical calculations or empirical data, thereby effectively improving the gasification efficiency and enhancing the coal conversion rate.

[0120] The applicant declares that the above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Those skilled in the art should understand that any changes or substitutions that can be easily thought of by any person skilled in the art within the technical scope disclosed by the present invention fall within the protection scope and the disclosure scope of the present invention.

Claims

1. An apparatus system for autonomously regulating the feed parameters of a entrained flow gasifier, characterized in that, The device system includes a feeding unit, a slag analysis unit, a gasifier state analysis unit, a data storage platform, and a feeding parameter self-calculation unit; The feeding unit includes a feeding control unit and a feeding analysis unit; The data output ends of the feeding control unit, the feeding analysis unit, the slag analysis unit, and the gasifier state analysis unit are connected to the data storage platform; The data output end of the data storage platform is connected to the feeding parameter self-calculation unit; The signal output end of the feeding parameter self-calculation unit is connected to the feeding control unit.

2. The device system according to claim 1, characterized in that, The feeding analysis unit includes a raw coal analysis unit, a raw water analysis unit, and a raw oxygen analysis unit; Preferably, the raw coal analysis unit includes a raw coal quality measurer, an elemental analyzer, an industrial analyzer, a sulfur content measurer, and a calorific value measurer; Preferably, the raw water analysis unit includes a temperature sensor, a flowmeter, and a pressure sensor; Preferably, the raw oxygen analysis unit includes a temperature sensor, a pressure sensor, a flowmeter, and an oxygen component analyzer.

3. The device system according to claim 1 or 2, characterized in that, The slag analysis unit includes an ash content analyzer, a moisture analyzer, an elemental analyzer, and a mass meter; Preferably, the gasifier state analysis unit includes a syngas component analyzer, a gasifier temperature sensor, and a gasifier pressure sensor.

4. The device system according to any one of claims 1-3, characterized in that, The feeding control unit includes a raw coal feeding sensor, a raw water feeding valve, and a raw oxygen feeding valve.

5. A method for autonomously regulating the feed parameters of an entrained flow gasifier, characterized in that, The method uses the device system for autonomously regulating the feeding parameters of an entrained flow gasifier as described in any one of claims 1-4. The method includes the following steps: (1) Collect the feeding physical parameters of the feeding analysis unit, the feeding control parameters of the feeding control unit, the slag characteristic parameters of the slag analysis unit, and the gasifier characteristic parameters of the gasifier state analysis unit and transmit them to the data storage platform for storage to form historical production data; (2) Process the historical production data stored in the data storage platform in step (1), establish a multivariate optimization model of the feeding control parameters, and form the program of the feeding parameter self-calculation unit; (3) During actual operation, transmit the feeding physical parameters, slag characteristic parameters, and gasifier characteristic parameters to the feeding parameter self-calculation unit through the data storage platform in real time, and calculate using the multivariate optimization model obtained in step (2) to obtain the optimal feeding control parameters; (4) Transmit the optimal feeding control parameters obtained in step (3) to the feeding control unit, and the feeding control unit adjusts according to the feeding control parameters, thereby realizing the autonomous regulation of the feeding.

6. The method according to claim 5, wherein The process of establishing the multivariate optimization model in step (2) includes: S1. Establish a first data set, which includes the actual values of the feeding physical parameters, feeding control parameters, slag characteristic parameters, and gasifier characteristic parameters; S2. Use the feeding physical parameters in the first data set as input data, construct a theoretical model, and calculate the theoretical feeding control parameters, slag characteristic parameters, and gasifier characteristic parameters; S3. Construct a second data set with the actual values of the feed physical parameters, feed control parameters, ash residue characteristic parameters, and gasifier characteristic parameters in the first data set and the theoretical values of the feed control parameters, ash residue characteristic parameters, and gasifier characteristic parameters obtained in step S2. Extract the ash residue characteristic parameters, gasifier characteristic parameters that meet the optimization requirements in the second data set and their corresponding feed control parameters to form a third data set. S4. Use the actual values of the feed physical parameters in the first data set and the feed control parameters in the third data set to establish a multi-objective optimization model for the feed control parameters.

7. The method according to claim 6, wherein The method for establishing the first data set described in step S1 specifically includes the following steps: S101. Preprocess the historical production data. The preprocessing includes handling missing values and duplicate values, and then performing normalization or standardization processing to obtain preprocessed data. S102. Perform outlier detection on the preprocessed data obtained in step S101 and remove the outliers to obtain the first data set.

8. The method according to claim 6 or 7, characterized in that, Step S2 specifically includes the following steps: S201. Based on the physical and chemical reactions in the coal gasification process, construct a theoretical model. S202. According to the feed physical parameters in the first data set and the theoretical model described in step S201, calculate the theoretical feed control parameters, ash residue characteristic parameters, and gasifier characteristic parameters. Preferably, the theoretical model includes a thermodynamic equilibrium model and / or a rate model. Preferably, the thermodynamic equilibrium model includes the equilibrium constant method and / or the Gibbs free energy minimization method. Preferably, the rate model includes a three-dimensional model and / or a reduced-order model.

9. The method according to any one of claims 6-8, characterized in that, The method for establishing the multi-objective optimization model described in step S4 includes the following steps: S401. According to the actual production requirements, with the effective gas production rate and the ash residue carbon content as the main objectives and the gasifier temperature as the secondary objective, set the constraint conditions including: the volume percentage of effective gas in water slurry gasification ≥ 80% or the mass percentage of effective gas in pulverized coal gasification ≥ 88%, the fine ash carbon content ≤ 35%, the coarse slag carbon content ≤ 5%, and the gasifier temperature ≤ 1700°C. Use the feed physical parameters in the first data set as the input data and the feed control parameters in the third data set as the output data to establish a multi-objective optimization model. S402. Combine the feed physical parameters in the first data set and the feed control parameters in the third data set, and divide them into a training set and a test set. Based on the multi-objective optimization algorithm of machine learning, use the training set to train the multi-objective optimization model, and use the test set for verification. Adjust and optimize the multi-objective optimization model according to the verification results to obtain the multi-objective optimization model of the feed control parameters.

10. The method according to claim 9, characterized in that, The multi-objective optimization algorithm based on machine learning includes any one or at least two combinations of the principal component analysis method, the deep learning method, the random forest method, or the ensemble learning method.

Images