Coupling anaerobic fermentation system for gradient utilization of pyrolysis waste heat and optimization control method

Abstract

The embodiment of the invention provides a coupled anaerobic fermentation system for gradient utilization of pyrolysis waste heat. The system comprises an organic solid waste pyrolysis unit, a drying furnace, a hot water tank, a cooling heat exchanger, a condensation heat exchanger, a flue gas heat exchanger, a warming heat exchanger, a heat preservation heat exchanger, a heater, a radiator and an LSTM neural network central control unit. The embodiment of the invention further provides an optimal control method of the coupled anaerobic fermentation system for gradient utilization of the pyrolysis waste heat. According to the technical scheme, the low-grade waste heat generated by the pyrolysis system is recycled in a gradient mode and used for heating and temperature maintaining of the anaerobic fermentation unit, the anaerobic fermentation temperature is controlled through LSTM neural network prediction, the excellent self-adaption and non-linear adjustment capacity of a neural network algorithm is fully played, and the energy consumption of the system is reduced. The interference of time sequence, uncertainty and volatility of a pyrolysis system and an anaerobic fermentation unit on the control process is overcome, and rapid, accurate and stable control over the anaerobic fermentation temperature is achieved.

Description

Technical Field

[0001] This invention belongs to the field of biomass energy utilization technology, and specifically relates to a coupled anaerobic fermentation system for the cascade utilization of pyrolysis waste heat. This invention also provides an optimized control method for the aforementioned coupled anaerobic fermentation system for the cascade utilization of pyrolysis waste heat. Background Technology

[0002] Anaerobic fermentation refers to the process of obtaining methane-rich biogas through the decomposition of organic matter by microorganisms under suitable conditions. It is one of the methods for large-scale utilization of biomass energy, and is particularly suitable for the efficient utilization of low-calorific-value biomass such as poultry and livestock manure and wet straw. Temperature is one of the key factors affecting biogas production during anaerobic fermentation. Depending on the temperature of the biogas digester, anaerobic fermentation is generally divided into ambient temperature fermentation (10~30℃), mesophilic fermentation (30~40℃), and thermophilic fermentation (50~60℃). Furthermore, temperature fluctuations also have a significant impact on anaerobic fermentation efficiency. Generally speaking, the daily temperature fluctuation for anaerobic fermentation should be controlled within ±2℃; when the temperature fluctuation reaches ±3℃, it will inhibit the anaerobic fermentation rate; when the temperature change reaches ±5℃, the gas production will decrease significantly.

[0003] In cold northern regions, temperatures are low and there are significant temperature differences between winter and summer, as well as between day and night. To maintain stable and efficient biogas production, appropriate heating and insulation measures are necessary, and the anaerobic fermentation temperature must be strictly controlled to prevent interference from external environmental factors. Therefore, the rational selection and design of anaerobic fermentation heating and insulation modes and control methods are urgent problems to be solved in the development of large and medium-sized biogas projects in cold northern regions, and are also key to the application and promotion of biogas projects in these areas.

[0004] To address the high energy consumption associated with heating for maintaining anaerobic fermentation temperatures in cold regions, some scholars have proposed utilizing renewable energy sources such as solar or geothermal energy. However, these renewable energy sources are significantly affected by geographical location, resulting in unstable heating and requiring auxiliary heating from other energy sources. This complicates the anaerobic fermentation temperature control system, hindering its widespread application. Furthermore, current anaerobic fermentation temperature control primarily employs the traditional PID algorithm. When applied to systems with instability and time-varying characteristics, this algorithm is prone to large overshoot and long settling times, failing to meet the high temperature control precision requirements of anaerobic fermentation. Given these existing technological limitations, there is an urgent need to develop an anaerobic fermentation process with significant energy savings, achieving efficient heating, insulation, and temperature control in cold environments. Summary of the Invention

[0005] To overcome the aforementioned shortcomings in the existing technology, this invention provides a coupled anaerobic fermentation system and optimized control method that utilizes pyrolysis waste heat in stages. This system recovers and utilizes the low-grade waste heat generated by pyrolysis in stages and uses it for anaerobic fermentation heating and temperature maintenance. Then, it uses an LSTM neural network to predict and control the anaerobic fermentation temperature, thereby achieving rapid, accurate and stable control of the anaerobic fermentation temperature.

[0006] To address the aforementioned technical problems, embodiments of the present invention provide a coupled anaerobic fermentation system that utilizes waste heat from pyrolysis in stages, comprising an anaerobic fermentation unit, an organic solid waste pyrolysis unit, a drying furnace, a hot water tank, a cooling heat exchanger, a condensing heat exchanger, a flue gas heat exchanger, a heating heat exchanger, an insulation heat exchanger, and an LSTM neural network central control unit; wherein:

[0007] The pyrolysis raw material is fed into the drying furnace for drying. The dried pyrolysis raw material is then fed into the organic solid waste pyrolysis unit to undergo a pyrolysis reaction, producing high-temperature pyrolysis char, high-temperature pyrolysis gas, and hot flue gas. The high-temperature pyrolysis char is fed into the cooling heat exchanger to recover waste heat, and the cooled pyrolysis char is discharged from the cooling heat exchanger. The high-temperature pyrolysis gas is fed into the condensing heat exchanger to recover waste heat, and the cooled pyrolysis oil and gas are discharged from the condensing heat exchanger. The hot flue gas is first fed into the drying furnace as a heat source, and then fed from the drying furnace into the flue gas heat exchanger to recover waste heat. The cooled low-temperature flue gas is discharged from the flue gas heat exchanger.

[0008] The hot water in the hot water tank is input into the heat exchanger, where it serves as process water and participates in heat exchange. After heat exchange, the process water is output from the heat exchanger and enters the heating heat exchanger as a heat source. The heating heat exchanger outputs process water to the cooling heat exchanger, condensing heat exchanger, and flue gas heat exchanger as cooling water. The cooling water in the cooling heat exchanger, condensing heat exchanger, and flue gas heat exchanger absorbs heat, increases in temperature, and is then returned to the hot water tank, forming a circulating water circuit.

[0009] The fermentation broth of the anaerobic fermentation unit is fed into the heat exchanger, where it is heated by exchanging heat with the process water. The fermentation broth is then returned to the anaerobic fermentation unit to maintain the required fermentation temperature, thus forming a fermentation broth circulation. The fermentation raw materials are preheated in the heat exchanger to prevent a significant drop in the anaerobic fermentation temperature caused by directly entering cold materials. The heated fermentation raw materials are then sent to the anaerobic fermentation unit for anaerobic fermentation.

[0010] The LSTM neural network central control unit is connected to the organic solid waste pyrolysis unit, hot water tank and anaerobic fermentation unit to collect control data. Based on the LSTM neural network model, it generates temperature control parameters according to the difference between the set temperature and the measured temperature of anaerobic fermentation, and then sends the temperature control parameters to the heat exchanger. The temperature of anaerobic fermentation is controlled by adjusting the output process water volume.

[0011] Preferably, the condenser heat exchanger is a liquid-liquid shell-and-tube heat exchanger.

[0012] Preferably, the cooling heat exchanger is a water-cooled spiral heat exchanger.

[0013] Preferably, the flue gas heat exchanger is a gas-liquid shell-and-tube heat exchanger.

[0014] As a preferred embodiment of the above technical solution, the coupled anaerobic fermentation system further includes a heater and a radiator, wherein: the heater is used to heat the water in the hot water tank; the radiator is installed in the circulating water circuit connecting the heating heat exchanger, the cooling heat exchanger, the condensing heat exchanger and the flue gas heat exchanger, and cools the process water from the heating heat exchanger before inputting it into the cooling heat exchanger, the condensing heat exchanger and the flue gas heat exchanger as cooling water.

[0015] In a second aspect, the present invention also provides an optimized control method for a coupled anaerobic fermentation system that utilizes waste heat from pyrolysis in stages, comprising the following steps:

[0016] 1. Collect time-series data of the organic solid waste pyrolysis unit, hot water tank, and anaerobic fermentation unit;

[0017] 2. Perform data preprocessing on the system's historical operating data and collected time-series data;

[0018] 3. Create an LSTM neural network by dividing the preprocessed data into training and testing sets, and then using the training and testing sets to train the LSTM neural network model.

[0019] 4. Define the objective optimization function and use an LSTM neural network model to predict the future multi-step output of the anaerobic fermentation temperature under the current input control;

[0020] 5. Using an optimization algorithm, calculate the control input vector that minimizes the objective function, and use it as the current optimal control input vector;

[0021] 6. Use the first component of the optimal control input vector to adjust the temperature control parameters, and output the temperature control parameters to regulate the anaerobic fermentation temperature;

[0022] 7. Repeat steps 1 to 6 to perform the next round of optimization control.

[0023] As a preferred embodiment of step 1, the time-series data is temperature data collected at preset time intervals and preset durations. The temperature data includes flue gas temperature and flow rate, pyrolysis char temperature, pyrolysis gas temperature, hot water tank temperature, anaerobic fermentation temperature, and ambient temperature. The preset time interval is 10s to 2h, and the preset duration is not less than one month.

[0024] As a preferred embodiment of step 2, the data preprocessing includes data cleaning, data updating, and data normalization / standardization; more preferably, the data cleaning involves removing invalid data; the data updating involves extracting historical running data with a duration longer than a preset duration, removing the earliest data from the period equal to the preset duration, and adding newly collected time-series data of the preset duration to form the updated data; the data normalization / standardization involves normalizing / standardizing the updated data.

[0025] As a preferred embodiment of step 3, the ratio of data divided into training set and test set is 7:3 to 8:2.

[0026] The technical solution described in this invention employs an anaerobic fermentation unit design coupled with a pyrolysis unit. This system utilizes a flue gas heat exchanger, a condenser heat exchanger, and a cooling heat exchanger to recover heat from the flue gas, pyrolysis gas, and pyrolysis char contained in the organic solid waste pyrolysis process. Energy is stored in a hot water tank, and energy is utilized in a cascade manner through an insulation heat exchanger and a heating heat exchanger to maintain a stable anaerobic fermentation temperature. Heaters and radiators overcome system fluctuations, achieving optimal energy matching and utilization. Simultaneously, an LSTM neural network model is used to automatically control the anaerobic fermentation process, enabling precise regulation of the anaerobic fermentation temperature. Its beneficial effects are as follows:

[0027] 1. The flue gas, high-temperature pyrolysis gas, and pyrolysis char of the pyrolysis system have abundant low-grade waste heat. By recovering and utilizing the energy, the waste heat of pyrolysis can be recovered for heating of the anaerobic fermentation unit, which can avoid burning biogas or other methods to provide heat to maintain the anaerobic fermentation temperature, and has significant energy-saving benefits.

[0028] 2. Taking full account of the differences in temperature and energy quality among the flue gas, pyrolysis gas, and pyrolysis char generated from the pyrolysis of organic solid waste (for example, the flue gas temperature in a pyrolysis system is generally between 300 and 500°C, the pyrolysis char temperature is between 400 and 600°C, and the high-temperature pyrolysis gas temperature is between 300 and 400°C), the waste heat energy can be utilized in stages and in zones to overcome system fluctuations and achieve optimal matching and utilization of waste heat.

[0029] 3. Based on the strong time-series characteristics of organic solid waste pyrolysis and anaerobic fermentation units, an LSTM neural network was created to perform nonlinear fitting and dynamic identification of anaerobic fermentation. LSTM neural networks are currently the most widely used neural network algorithms, possessing powerful nonlinear fitting capabilities and adaptive energy adjustment, making them particularly suitable for time-series data analysis and processing. Based on the trained LSTM neural network model, an optimal control method for the system within the predicted time frame was obtained, and only the first step of optimal control was implemented. This overcomes the problem that the time-varying nature of the system leads to a decrease in the prediction accuracy of the neural network, significantly improving the accuracy, precision, and stability of the system control. Attached Figure Description

[0030] The following figures are provided to further illustrate the invention and form part of the specification. They are used together with the detailed embodiments to explain the invention, but do not constitute a limitation thereof. They include:

[0031] Figure 1 This is a system connection diagram of the coupled anaerobic fermentation system utilizing waste heat from pyrolysis in a cascade manner, as provided in Embodiment 1 of the present invention.

[0032] Figure 2 This is a system connection diagram of the coupled anaerobic fermentation system utilizing pyrolysis waste heat in a cascade manner, as provided in Embodiment 2 of the present invention.

[0033] Figure 3 The flowchart illustrates the steps of the optimized control method for a coupled anaerobic fermentation system utilizing waste heat from pyrolysis, as provided in Embodiment 3 of the present invention.

[0034] [Explanation of Key Component Symbols]

[0035] 1-Anaerobic fermentation unit; 2-Organic solid waste pyrolysis unit; 21-Drying furnace; 3-Hot water tank; 31-Heater; 32-Radiator; 4-Cooling heat exchanger; 5-Condensing heat exchanger; 6-Flue gas heat exchanger; 7-Heating heat exchanger; 8-Insulation heat exchanger; 9-LSTM neural network central control unit. Detailed Implementation

[0036] To make the technical problems, technical solutions, and advantages of the present invention clearer, a detailed description will be provided below in conjunction with the accompanying drawings and specific embodiments. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0037] To address the limitations of existing renewable energy heating technologies for anaerobic fermentation, which are complex to control and difficult to promote, and the shortcomings of traditional anaerobic fermentation temperature control algorithms in unstable time-varying systems (such as large overshoot and long settling time), making it difficult to meet the temperature control accuracy requirements of anaerobic fermentation, this invention develops a coupled anaerobic fermentation process that utilizes pyrolysis waste heat in stages. This process recovers low-grade waste heat generated by pyrolysis in stages to heat and maintain the temperature of anaerobic fermentation. The anaerobic fermentation temperature is then controlled by predictive LSTM neural network models, achieving rapid, accurate, and stable temperature control.

[0038] Example 1

[0039] To achieve the above technical effects, such as Figure 1 As shown, this embodiment provides a coupled anaerobic fermentation system that utilizes waste heat from pyrolysis in stages, including an anaerobic fermentation unit 1, an organic solid waste pyrolysis unit 2, a drying furnace 21, a hot water tank 3, a cooling heat exchanger 4, a condensing heat exchanger 5, a flue gas heat exchanger 6, a heating heat exchanger 7, a heat preservation heat exchanger 8, and an LSTM neural network central control unit 9; wherein:

[0040] The pyrolysis raw materials are fed into the drying furnace 21 for drying. The dried pyrolysis raw materials are then fed into the organic solid waste pyrolysis unit 2 to undergo a pyrolysis reaction, producing high-temperature pyrolysis char, high-temperature pyrolysis gas, and hot flue gas. The high-temperature pyrolysis char is fed into the cooling heat exchanger 4 to recover waste heat, and the cooled pyrolysis char is discharged from the cooling heat exchanger 4. The high-temperature pyrolysis gas is fed into the condensing heat exchanger 5 to recover waste heat, and the cooled pyrolysis oil and gas are discharged from the condensing heat exchanger 5. The hot flue gas is first fed into the drying furnace 21 as a heat source, and then fed from the drying furnace 21 into the flue gas heat exchanger 6 to recover waste heat. The cooled low-temperature flue gas is discharged from the flue gas heat exchanger 6. The hot water in the hot water tank 3 is fed into the insulation heat exchanger 8, where it serves as process water and participates in heat exchange. The heat-exchanged process water is output from the insulation heat exchanger 8 and enters the heating heat exchanger 7 as a heat source. The heating heat exchanger 7 outputs process water to the cooling heat exchanger 4, the condensing heat exchanger 5, and the flue gas heat exchanger 6 as cooling water. Cooling water in cooling heat exchanger 4, condensing heat exchanger 5, and flue gas heat exchanger 6 absorbs heat and is heated before being returned to hot water tank 3, forming a circulating water path. The fermentation liquid of anaerobic fermentation unit 1 is input into heat-insulating heat exchanger 8, where it exchanges heat with process water and is heated before being returned to anaerobic fermentation unit 1 to maintain the required fermentation temperature, forming a fermentation liquid circulation. The fermentation raw materials are preheated in heating heat exchanger 7 to prevent a significant drop in anaerobic fermentation temperature caused by direct entry of cold materials. The heated fermentation raw materials are then sent to anaerobic fermentation unit 1 for anaerobic fermentation. The LSTM neural network central control unit 9 connects to organic solid waste pyrolysis unit 2, hot water tank 3, and anaerobic fermentation unit 1 to collect control data. Based on the LSTM neural network model, it generates temperature control parameters according to the difference between the set temperature and the measured temperature of anaerobic fermentation, and then sends the temperature control parameters to heat-insulating heat exchanger 8. The output process water flow is adjusted to control the anaerobic fermentation temperature.

[0041] As a preferred embodiment, the condenser heat exchanger 5 can be a liquid-liquid shell-and-tube heat exchanger; the cooling heat exchanger 4 can be a water-cooled spiral heat exchanger; and the flue gas heat exchanger 6 can be a gas-liquid shell-and-tube heat exchanger.

[0042] Example 2

[0043] like Figure 2 As shown, the coupled anaerobic fermentation system utilizing waste heat from pyrolysis provided in this embodiment, compared to Embodiment 1, adds a heater 31 and a radiator 32. Wherein:

[0044] Heater 31 is used to heat the water in hot water tank 3;

[0045] The radiator 32 is installed in the circulating water circuit connecting the heating heat exchanger 7, the cooling heat exchanger 4, the condensing heat exchanger 5, and the flue gas heat exchanger 6. After the process water from the heating heat exchanger 7 is cooled down, it is fed into the cooling heat exchanger 4, the condensing heat exchanger 5, and the flue gas heat exchanger 6 as cooling water.

[0046] Example 3

[0047] This embodiment provides an optimized control method for a coupled anaerobic fermentation system that utilizes waste heat from pyrolysis in stages, such as... Figure 3 As shown, it includes the following steps:

[0048] S1. Collect time-series data from the organic solid waste pyrolysis unit, hot water tank, and anaerobic fermentation unit;

[0049] S2. Perform data preprocessing on the system's historical operating data and the collected time-series data;

[0050] S3. Create an LSTM neural network by dividing the preprocessed data into a training set and a test set, and using the training set and test set to train and obtain the LSTM neural network model;

[0051] S4. Define the objective optimization function and use an LSTM neural network model to predict the future multi-step output of the anaerobic fermentation temperature under the current input control;

[0052] S5. Using an optimization algorithm, calculate the control input vector that minimizes the objective optimization function, and use it as the current optimal control input vector;

[0053] S6. Use the first component of the optimal control input vector to adjust the temperature control parameters, and output the temperature control parameters to regulate the anaerobic fermentation temperature;

[0054] S7. Repeat steps S1 to S6 to perform the next round of optimization control.

[0055] As a better implementation method:

[0056] In S1, the time-series data consists of temperature data collected at preset time intervals and preset durations. The temperature data includes the temperature of pyrolysis char, pyrolysis gas, flue gas, medium-temperature water tank, high-temperature water tank, and anaerobic fermentation. The preset time interval can be set from 10s to 2h, for example, 10s, 30s, 1min, 5min, 10min, 30min, 45min, 1h, 1.2h, 1.5h, and 2h. The preset duration is set to be no less than one month, for example, one month, three months, six months, ten months, twelve months, etc.

[0057] In S2, data preprocessing includes data cleaning, data updating, and data normalization / standardization. As a more specific implementation, the specific steps are as follows:

[0058] Data cleaning, also known as data cleaning, is the removal of invalid data.

[0059] Data update involves retrieving historical running data with a duration longer than the preset duration, removing the earliest data from the period with the preset duration, and adding newly collected time-series data of the preset duration to form the updated data.

[0060] Data normalization / standardization refers to the normalization / standardization process performed on updated data.

[0061] In S3, the ratio of training set to test set data is 7:3 to 8:2, for example, it can be divided into 7:3, 7.2:2.8, 7.5:2.5, 7.7:2.3 or 8:2.

[0062] As an example of the above-mentioned optimized control method, the preset time interval for collecting time-series data is 30 seconds, and the preset duration is 2 months. When updating the data, 9 months of historical operating data are retrieved, the earliest 2 months of data in the historical data are removed, and the newly collected 2 months of data are added to complete the data update. The ratio of training set to test set is 7:3. Under this optimized control method, the anaerobic fermentation temperature fluctuation during system operation does not exceed ±0.4℃, and the adjustment time does not exceed 8 minutes.

[0063] As another example of the above-mentioned optimized control method, the preset time interval for collecting time-series data is 10 seconds, and the preset duration is 3 months. When updating the data, 12 months of historical operating data are retrieved, the earliest 3 months of data in the historical data are removed, and the newly collected 3 months of data are added to complete the data update. The ratio of training set to test set is 8:2. Under this optimized control method, the anaerobic fermentation temperature fluctuation during system operation does not exceed ±0.2℃, and the adjustment time does not exceed 6 minutes.

[0064] The technical solution of the above embodiment recovers the low-grade waste heat generated by the pyrolysis system in stages and uses it for heating and temperature maintenance of the anaerobic fermentation unit. The anaerobic fermentation temperature is controlled by predicting with an LSTM neural network, giving full play to the excellent adaptive and nonlinear adjustment capabilities of the neural network algorithm. This overcomes the interference of the timing, uncertainty and fluctuation of the pyrolysis system and the anaerobic fermentation unit on the control process, and achieves rapid, accurate and stable control of the anaerobic fermentation temperature.

[0065] In the description of this invention, unless otherwise expressly specified and limited, the terms "connection," "linked," and "connected" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Furthermore, the term "optimal" is used for descriptive purposes only and should not be construed as indicating or implying relative importance. Those skilled in the art will understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0066] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Units described as separate components may or may not be physically separate; components shown as units may or may not be physical units, i.e., they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0067] For the preferred embodiments of the present invention described above, common knowledge such as specific structures and characteristics in the technical solutions are not described in detail; each embodiment is described in a progressive manner, and the technical features involved in each embodiment can be combined with each other without conflicting with each other. The same or similar parts between the embodiments can be referred to each other.

[0068] It should be noted that, for those skilled in the art, the above embodiments can be improved and modified in various ways without departing from the principles of the present invention, and such improvements and modifications should also be considered to fall within the protection scope of the present invention.

Claims

1. A coupled anaerobic fermentation system utilizing pyrolysis waste heat in steps, comprising an anaerobic fermentation unit (1) for carrying out anaerobic fermentation, characterized in that, Also comprising: The organic solid waste pyrolysis unit (2), the drying furnace (21), the hot water tank (3), the cooling heat exchanger (4), the condensing heat exchanger (5), the flue gas heat exchanger (6), the temperature increasing heat exchanger (7), the heat preservation heat exchanger (8) and the LSTM neural network central control unit (9); wherein: The pyrolysis raw material is sent into the drying furnace (21) for drying, and the dried pyrolysis raw material is sent into the organic solid waste pyrolysis unit (2) to generate high-temperature pyrolysis carbon, high-temperature pyrolysis gas and hot flue gas through pyrolysis reaction, wherein the high-temperature pyrolysis carbon is sent into the cooling heat exchanger (4) to recover waste heat, and the cooled pyrolysis carbon is discharged from the cooling heat exchanger (4); the high-temperature pyrolysis gas is sent into the condensing heat exchanger (5) to recover waste heat, and the cooled pyrolysis oil gas is discharged from the condensing heat exchanger (5); the hot flue gas is first sent into the drying furnace (21) as a heat source, and then from the drying furnace (21) into the flue gas heat exchanger (6) to recover waste heat, and the cooled low-temperature flue gas is discharged from the flue gas heat exchanger (6); The hot water in the hot water tank (3) is input into the heat preservation heat exchanger (8), and the hot water participates in heat exchange in the heat preservation heat exchanger (8) as process water; the heat exchanged process water is output from the heat preservation heat exchanger (8) into the temperature increasing heat exchanger (7) as a heat source; the temperature increasing heat exchanger (7) outputs process water to the cooling heat exchanger (4), the condensing heat exchanger (5) and the flue gas heat exchanger (6) as cooling water; the cooling water in the cooling heat exchanger (4), the condensing heat exchanger (5) and the flue gas heat exchanger (6) is heated and then input back into the hot water tank (3), forming a circulating water path; The fermentation liquid of the anaerobic fermentation unit (1) is input into the heat preservation heat exchanger (8), and the fermentation liquid heated by heat exchange with process water is input back into the anaerobic fermentation unit (1), forming a fermentation liquid circulation; the fermentation raw material is preheated in the temperature increasing heat exchanger (7), and the heated fermentation raw material is sent into the anaerobic fermentation unit (1) for anaerobic fermentation; The LSTM neural network central control unit (9) is connected to the organic solid waste pyrolysis unit (2), the hot water tank (3) and the anaerobic fermentation unit (1) to collect control data, generates temperature control parameters based on the LSTM neural network model, and then sends the temperature control parameters to the heat preservation heat exchanger (8) to regulate and control the output of process water.

2. The coupled anaerobic fermentation system of claim 1, wherein, The condensing heat exchanger (5) is a liquid-liquid shell-and-tube heat exchanger.

3. The anaerobic fermentation system of claim 1, wherein, The cooling heat exchanger (4) is a water-cooled spiral heat exchanger.

4. The coupled anaerobic fermentation system of claim 1, wherein, The flue gas heat exchanger (6) is a gas-liquid shell-and-tube heat exchanger.

5. The coupled anaerobic fermentation system of any one of claims 1-4, wherein, It also includes a heater (31) and a radiator (32); the heater (31) is used to heat the water in the hot water tank (3); the radiator (32) is arranged in the circulating water path of the temperature increasing heat exchanger (7) connected to the cooling heat exchanger (4), the condensing heat exchanger (5) and the flue gas heat exchanger (6), and is used to cool the process water from the temperature increasing heat exchanger (7).

6. A method for optimizing control of a coupled anaerobic fermentation system using pyrolysis waste heat of a step according to any one of claims 1 to 5, characterized in that, It comprises the following steps: Step 1: Collecting time series data of the organic solid waste pyrolysis unit, the hot water tank and the anaerobic fermentation unit; Step 2: Data preprocessing of historical operation data and collected time series data of the system; Step 3: create an LSTM neural network, divide the pre-processed data into a training set and a test set, and train the LSTM neural network model using the training set and the test set; Step 4: define a target optimization function, and use the LSTM neural network model to predict the future multi-step output of the anaerobic fermentation temperature under the current input control; Step 5: use an optimization algorithm to calculate the control input vector that minimizes the target optimization function, as the current optimal control input vector; Step 6: use the first component of the optimal control input vector to adjust the temperature control parameter, and output the temperature control parameter to regulate the anaerobic fermentation temperature; Step 7: repeat steps 1 to 6 to perform the next round of optimal control.

7. The optimal control method of claim 6, wherein, In step 1, the time series data is temperature data collected at a preset time interval and a preset length, including flue gas temperature and flow, pyrolysis carbon temperature, pyrolysis gas temperature, hot water tank temperature, anaerobic fermentation temperature, and environmental temperature; the preset time interval is 10s-2h, and the preset length is not less than 1 month.

8. The optimal control method of claim 6, wherein, In step 2, the data preprocessing includes data cleaning, data updating, and data normalization / standardization.

9. The optimal control method of claim 8, wherein, The data preprocessing includes the following steps: The data cleaning, i.e. removing invalid data; The data updating, i.e. taking out historical operation data with a length greater than the preset length, removing the earliest data in the preset length, adding newly collected time series data of the preset length, and constructing updated data; The data normalization / standardization, i.e. normalizing / standardizing the updated data.

10. An optimization control method according to any one of claims 6 to 9, characterized in that, In step 3, the data ratio of the training set and the test set is 7:3-8:2.

Images