Temperature control system and method of intelligent efficient composite biological filter bed

Abstract

The invention provides a temperature control system and method based on an intelligent efficient composite biological filter bed. The system comprises a washing tank, a biological filter bed, a waste heat recovery device and a temperature control device. Waste gas is washed, heated and humidified through washing water in the washing tank, then the waste gas is degraded through microorganisms in the reactor, the waste heat recovery device recovers waste heat of equipment and supplies heat to the washing tank and the reactor, and the temperature in the reactor is predicted through a temperature prediction module in the temperature control device. And the PLC module is used for controlling operation of equipment in the system according to a prediction result of the temperature prediction module so as to regulate and control the temperature of the reactor. According to the system and the method provided by the invention, the problems of high energy consumption, overlarge size and easiness in blockage of a traditional heat exchanger are solved, the waste gas treatment efficiency is improved, and a stable and appropriate temperature is provided for the reactor in the biological filter bed through the intelligent temperature control device.

Description

Technical Field

[0001] The present invention relates to the technical field of waste gas treatment, and in particular to a temperature control system and method for an intelligent and efficient composite biological filter bed. Background Art

[0002] With the rapid development of industrialization, waste gas emissions have become one of the important sources of environmental pollution. Waste gas contains various harmful substances, such as volatile organic compounds (VOCs), sulfides, nitrogen oxides, etc. These substances not only cause serious pollution to the environment, but also have a negative impact on human health. Therefore, it is particularly important to develop efficient and economical waste gas treatment technology. As an environmentally friendly and efficient waste gas treatment method, biofilter bed technology has been widely studied and applied in recent years.

[0003] In practical applications, biofilter bed technology that uses microorganisms to treat organic waste gas will encounter significant challenges in low temperature environments in winter (i.e., when the temperature is below 15 degrees Celsius), because a sharp drop in microbial activity or even death may lead to loss of system function. Therefore, a technology has been derived to install a heating system for the biofilter bed, such as installing an electric heater, a hot water circulation system, or a steam heating system to maintain a suitable temperature inside the biofilter bed. The heating system can ensure that the microorganisms can still maintain a high activity in a low-temperature external environment. Although the low temperature problem of the microbial environment has been solved, there are still some technical defects in the field of temperature control. The temperature control inside the biofilter bed does not respond in time, resulting in the death of microorganisms in local areas due to excessively high or low temperatures. The factors affecting the temperature inside the biofilter bed are too complex, and the temperature control parameters are difficult to determine, making it too difficult to keep the temperature within a safe range.

[0004] In addition, when treating low-temperature organic waste gas, there is a technology that uses a heat exchanger for heat exchange. This technology involves electrically assisted heating and heat exchange through a fin heat exchanger. However, this method consumes a lot of energy. Furthermore, organic waste gas usually contains other inorganic acid and alkali components, which have a strong corrosive effect on the heat exchanger. Due to the complex components of organic waste gas and its easy polymerization, as well as the large amount of fluff and grease mixed in the baking process, the heat exchanger is very easy to get blocked, resulting in failure. Therefore, traditional heat exchange technology has the problems of high power consumption and easy blockage of the heat exchanger.

[0005] Therefore, there is an urgent need for a method that can solve the problems of high power consumption and easy clogging of heat exchangers in traditional heat exchange technology, and can also solve the problem that current technology is difficult to accurately control the internal temperature of the biofilter bed. Summary of the invention

[0006] The present invention describes a temperature control system and method for an intelligent and efficient composite biological filter bed, which can solve the above technical problems.

[0007] According to a first aspect, a temperature control system based on an intelligent and efficient composite biological filter bed is provided, the system comprising:

[0008] A washing tank, comprising an air inlet, an air outlet, washing water and a heating device, wherein the washing tank is used to wash, heat and increase the humidity of the exhaust gas, wherein the washing water is heated by the heating device, and the heated washing water is then heat-exchanged with the exhaust gas;

[0009] The biofilter bed comprises a reactor, microorganisms, and a microorganism environment support system. The biofilter bed degrades waste gas through microorganisms, wherein the microorganisms are located in the reactor, the microorganism environment support system is connected to the reactor and provides a growth environment for the microorganisms, the washing tank is connected to the reactor, and the waste gas is washed in the washing tank and then flows into the reactor; wherein a heating device and a cooling device are also provided in the reactor;

[0010] A waste heat recovery device, including a heat accumulator and a heat exchanger, wherein the heat accumulator recovers the waste heat in the whole system through a pipeline, and the heat exchanger is used to provide heat for the washing tank and the reactor;

[0011] The temperature control device includes a temperature sensor, a temperature prediction module, and a PLC module. The temperature sensor is arranged in a washing tank, a reactor, and a waste heat recovery device. The temperature prediction module is used to predict the temperature inside the reactor. The PLC module is used to control the operation of the equipment in the system according to the prediction results of the temperature prediction module to adjust the temperature inside the reactor.

[0012] In some embodiments, the temperature prediction module includes:

[0013] A data acquisition module is used to acquire temperature data of the washing tank, the reactor and the external environment, and to record the time series of the temperature data, and is also used to acquire the operating parameters of the reactor such as the air intake flow rate, aeration volume, and nutrient addition amount; wherein the temperature data is acquired through a temperature sensor, and the operating parameters are acquired from a microbial environment support system;

[0014] Model training module, used to train the temperature data of the washing tank, reactor and external environment, as well as the operating parameters of the reactor's air intake flow, aeration volume, and nutrient addition amount;

[0015] The model prediction module is used to predict the reactor temperature in the next time period based on the temperature data of the washing tank and the external environment, as well as the operating parameters of the reactor's air intake flow, aeration volume, and nutrient addition volume.

[0016] In some embodiments, the prediction model in the temperature prediction module is an SVM-LSTM model, which includes two input layers, an SVM module, an LSTM module, a feature fusion layer, two fully connected layers and an output layer, wherein:

[0017] One input layer is connected to the SVM module and is used to input the temperature data of the washing tank, the reactor and the external environment to the SVM module, and the other input layer is connected to the LSTM module and is used to input the temperature data of the washing tank, the reactor and the external environment, as well as the operating parameters of the air intake flow rate, aeration volume and nutrient addition amount of the reactor to the LSTM module;

[0018] The feature fusion layer is used to fuse the output results of the SVM module and the LSTM module to form a unified feature vector;

[0019] The two fully connected layers further extract the features of the fused feature vector to obtain higher-level features;

[0020] The output layer is used to output the prediction results of the SVM-LSTM model.

[0021] In some embodiments, the process of the PLC module in the temperature control device controlling the operation of the reactor and the waste heat recovery device according to the prediction result of the temperature prediction module specifically includes:

[0022] When the temperature prediction result of the reactor exceeds the set maximum temperature threshold, the heating device of the reactor and / or the washing tank is turned off through the PLC module, and the pipeline valve connecting the heat exchanger in the waste heat recovery device and the reactor is turned off, and the cooling device of the reactor is turned on to prevent the temperature of the next time period from exceeding the set maximum temperature threshold;

[0023] When the predicted temperature result of the reactor is lower than the set minimum temperature threshold, the heating device of the reactor and / or the washing tank is turned on through the PLC module, the pipe valve connecting the heat exchanger in the waste heat recovery device and the reactor is opened, and the cooling device of the reactor is closed to prevent the temperature in the next time period from being lower than the set minimum temperature threshold.

[0024] According to the second aspect, a temperature control method based on an intelligent and efficient composite biological filter bed is implemented based on the temperature control system of the intelligent and efficient composite biological filter bed described in the first aspect, and the method specifically includes:

[0025] The exhaust gas is washed, heated and humidified by the washing water in the washing tank; wherein the washing water is heated by a heating device, and the heated washing water is then heat-exchanged with the exhaust gas;

[0026] The washed waste gas is passed through a reactor of a biological filter bed, and the waste gas is degraded by microorganisms in the reactor; wherein a heating device and a cooling device are also provided in the reactor;

[0027] The waste heat in the whole system is recovered by the heat accumulator in the waste heat recovery device. When the washing tank and the reactor need to be heated, the waste heat recovery device provides heat to the washing tank and the reactor through the heat exchanger.

[0028] The temperature in the reactor is predicted by the temperature prediction module in the temperature control device, and the PLC module is used to control the operation of the equipment in the system according to the prediction result of the temperature prediction module to adjust the temperature of the reactor.

[0029] In some embodiments, the method of predicting the temperature in the reactor by the temperature prediction module in the temperature control device specifically includes:

[0030] Obtain the temperature data of the washing tank, reactor and external environment, record the time series of the temperature data, and obtain the operating parameters of the reactor's air intake flow, aeration volume, and nutrient addition amount;

[0031] The model was trained using the temperature data of the washing tank, reactor and external environment, as well as the operating parameters of the reactor's air flow rate, aeration volume, and nutrient addition;

[0032] The temperature data of the washing tank and the external environment, as well as the operating parameters of the reactor such as air inlet flow, aeration volume, and nutrient addition amount are input into the trained model to predict the reactor temperature in the next time period.

[0033] In some embodiments, the prediction model in the temperature prediction module is an SVM-LSTM model, which includes two input layers, an SVM module, an LSTM module, a feature fusion layer, two fully connected layers and an output layer, wherein:

[0034] One input layer is connected to the SVM module and is used to input the temperature data of the washing tank, the reactor and the external environment to the SVM module, and the other input layer is connected to the LSTM module and is used to input the temperature data of the washing tank, the reactor and the external environment, as well as the operating parameters of the air intake flow rate, aeration volume and nutrient addition amount of the reactor to the LSTM module;

[0035] The feature fusion layer is used to fuse the output results of the SVM module and the LSTM module to form a unified feature vector;

[0036] The two fully connected layers further extract the features of the fused feature vector to obtain higher-level features;

[0037] The output layer is used to output the prediction results of the SVM-LSTM model.

[0038] In some embodiments, the method in which the PLC module in the temperature control device controls the operation of the reactor and the waste heat recovery device according to the prediction result of the temperature prediction module specifically includes:

[0039] When the temperature prediction result of the reactor exceeds the set maximum temperature threshold, the heating device of the reactor and / or the washing tank is turned off through the PLC module, and the pipeline valve connecting the heat exchanger in the waste heat recovery device and the reactor is turned off, and the cooling device of the reactor is turned on to prevent the temperature of the next time period from exceeding the set maximum temperature threshold;

[0040] When the predicted temperature result of the reactor is lower than the set minimum temperature threshold, the heating device of the reactor and / or the washing tank is turned on through the PLC module, the pipe valve connecting the heat exchanger in the waste heat recovery device and the reactor is opened, and the cooling device of the reactor is closed to prevent the temperature in the next time period from being lower than the set minimum temperature threshold.

[0041] The present invention provides a temperature control system and method based on an intelligent and efficient composite biofilter bed. The system includes a washing tank, a biofilter bed, a waste heat recovery device, and a temperature control device. The washing water in the washing tank is used to wash, heat, and increase the humidity of the waste gas. The waste gas is then degraded by microorganisms in the reactor. The waste heat recovery device recovers the waste heat of the equipment and provides heat for the washing tank and the reactor. The temperature in the reactor is predicted by the temperature prediction module in the temperature control device, and the operation of the equipment in the system is controlled by a PLC module according to the prediction result of the temperature prediction module to adjust the temperature of the reactor. The system and method provided by the present invention solve the problems of high energy consumption, large volume, and easy clogging of traditional heat exchangers, and improve the waste gas treatment efficiency, and provide a stable and suitable temperature for the biofilter bed reactor through an intelligent temperature control device. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0043] Figure 1 A schematic diagram showing a temperature control system based on an intelligent and efficient composite biofilter bed provided in an embodiment of this specification is shown;

[0044] Figure 2 A schematic diagram of a temperature prediction module framework provided in an embodiment of this specification is shown;

[0045] Figure 3 A schematic flow chart of a temperature control method based on an intelligent and efficient composite biological filter bed provided in an embodiment of this specification is shown; DETAILED DESCRIPTION

[0046] The solution provided in this specification is described below in conjunction with the accompanying drawings.

[0047] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0048] In the description of the embodiments of the present application, words such as "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a concrete way.

[0049] In the description of the embodiments of the present application, the term "and / or" is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, B exists alone, and A and B exist at the same time. In addition, unless otherwise specified, the term "plurality" means two or more.

[0050] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprises", "has" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0051] Figure 1 A schematic diagram of a temperature control system based on an intelligent and efficient composite biofilter provided in an embodiment of this specification is shown, Figure 1 As shown, the system includes: a washing tank, a biofilter bed, a temperature control device, and a waste heat recovery device. The exhaust gas first passes through the washing tank, where it is washed, heated, and humidified, and then enters the reactor in the biofilter bed to be degraded by microorganisms. The waste heat recovery device can recover the excess heat generated by the washing tank and the biofilter bed, and can also provide heat to the washing tank and the reactor. The temperature control device is used to predict the temperature of the reactor, and to control the washing tank, the reactor, and the waste heat recovery device according to the temperature prediction results to prevent the temperature of the reactor from being too high or too low, resulting in the death of microorganisms. Among them:

[0052] The washing tank includes an air inlet, an air outlet, washing water and a heating device. The washing tank is used to wash, heat and increase the humidity of the exhaust gas. Specifically, the washing water is heated by the heating device, and the heated washing water is then heat-exchanged with the exhaust gas. In addition, the exhaust gas contacts the washing water to increase the humidity of the exhaust gas.

[0053] It is worth noting that during the process of washing the waste gas, washing water can remove the fluff and grease in the waste gas, solving the problem of pipe blockage. In addition, during the washing process, heat exchange occurs between the washing water and the waste gas, increasing the temperature of the waste gas and the humidity of the waste gas. However, the degradation of the waste gas by microorganisms in the biological filter bed requires high humidity conditions, so washing the waste gas through the washing tank provides temperature and humidity conditions for microbial degradation, thereby improving the efficiency of waste gas degradation. In addition, because the water environment in the washing tank can store more heat than the air environment of the traditional heat exchanger (the specific heat capacity of water is greater than the specific heat capacity of air), the problem of excessive volume of the traditional heat exchanger can be avoided by exchanging heat with the waste gas through washing water. The water environment in the washing tank can use the waste heat collected by the waste heat recovery device, thereby saving energy.

[0054] The biofilter bed includes a reactor, microorganisms, and a microbial environment support system. The biofilter bed degrades waste gas through microorganisms. Specifically, the microorganisms are located in the reactor, and the microbial environment support system is connected to the reactor and provides a growth environment for the microorganisms. The washing tank is connected to the reactor, and the waste gas is washed in the washing tank and then flows into the reactor. Among them, a heating device and a cooling device are also provided in the reactor to ensure that the microorganisms are in a suitable temperature environment.

[0055] The waste heat recovery device includes a heat accumulator and a heat exchanger. Specifically, the heat accumulator recovers the excess heat in the entire system through pipelines, and the heat exchanger is used to provide heat for the washing tank and the reactor;

[0056] It is worth noting that the heat accumulator can utilize the waste heat generated by any equipment included in the heating device and cooling device in the entire system device, such as the waste heat generated by the air compressor, air conditioner, steam condensate, etc.

[0057] The temperature control device includes a temperature sensor, a temperature prediction module, and a PLC module. The temperature sensors are arranged in the washing tank, the reactor, and the waste heat recovery device. The temperature prediction module is used to predict the temperature inside the reactor, and the PLC module is used to control the operation of the equipment in the system according to the prediction results of the temperature prediction module to adjust the temperature inside the reactor.

[0058] In one embodiment, reference Figure 2 The temperature prediction module includes a data acquisition module 201, a model training module 202 and a model prediction module 203.

[0059] The data acquisition module 201 is used to acquire the temperature data of the washing tank, the reactor and the external environment, and record the time series of the temperature data, and is also used to acquire the operating parameters of the reactor's air intake flow, aeration volume, and nutrient addition volume. The temperature data is acquired through a temperature sensor, and the operating parameters are acquired from the microbial environment support system.

[0060] It is worth noting that the reactor needs oxygen, nitrogen, phosphorus and other nutrients to supply microorganisms to grow and decompose waste gas, which can be achieved through the microbial environmental support system, which can record detailed operating parameters during the supply process. Figure 1 The temperature sensor of the external environment is not shown in the figure, but it is easy to understand that the external environment refers to the external environment of the reactor. A temperature sensor can be placed outside the reactor to collect temperature data of the external environment.

[0061] The model training module 202 is used to train the temperature data of the washing tank, the reactor and the external environment, as well as the operating parameters of the reactor's air intake flow rate, aeration volume, and nutrient addition volume.

[0062] Before training the data, it is necessary to preprocess it. First, clean the data, remove missing values ​​and outliers in the data, and process the outliers, such as using interpolation or median filling. Secondly, normalize the data and normalize all features to between 0 and 1 to improve the training efficiency and stability of the model. Furthermore, extract time series features such as lag terms, rolling mean, rolling standard deviation, etc. to capture time dependencies. The preprocessed training data is divided into a training set, a validation set, and a test set. Use the training set to train the model. Specifically, the temperature data of the washing tank, reactor, and external environment in the previous time period, as well as the operating parameters of the reactor's air intake flow, aeration volume, and nutrient addition are used as input, and the reactor temperature in the next time period is used as output. Use the validation set to verify the model training effect, use the test set to test the model training effect, and adjust the model parameters until a model with significant prediction effect is obtained.

[0063] The temperatures of the washing tank, reactor and external environment are the main factors affecting the internal temperature of the reactor in the next time period. The operating parameters of the reactor's air intake flow, aeration volume, and nutrient addition amount will affect the thermal balance and biochemical reaction process of the reactor's internal environment through different mechanisms, and affect the temperature inside the reactor to a certain extent.

[0064] The model prediction module 203 is used to predict the reactor temperature in the next time period based on the temperature data of the washing tank and the external environment, as well as the operating parameters of the reactor such as the air intake flow rate, aeration volume, and nutrient addition volume.

[0065] Specifically, the prediction model can select a model suitable for processing time series data, such as ARIMA (autoregressive integrated moving average model), LSTM (long short-term memory network), GRU (gated recurrent unit), Prophet, XGBoost, etc. Using the temperature data of the washing tank and the external environment, as well as the operating parameters of the reactor's air intake flow rate, aeration volume, and nutrient addition as input, the prediction model is used to predict the internal temperature of the reactor at the next time point.

[0066] In one embodiment, in order to better adapt to the temperature control of the intelligent and efficient composite biological filter bed of this scheme, the present invention provides a new temperature prediction model, namely, the SVM-LSTM model. The SVM-LSTM model includes two input layers, an SVM module, an LSTM module, a feature fusion layer, two fully connected layers and an output layer.

[0067] Specifically, one of the input layers is connected to the SVM module for inputting the temperature data of the washing tank, reactor and external environment into the SVM module, and the other input layer is connected to the LSTM module for inputting the temperature data of the washing tank, reactor and external environment into the LSTM module, as well as the operating parameters of the reactor's air intake flow, aeration volume, and nutrient addition amount.

[0068] In the actual production process, the temperature of the washing tank, reactor and external environment in the previous time period directly affects the temperature of the reactor in the next time period, and there is a strong correlation between them, so the SVM module can be used to capture the linear relationship in the input features. The operating parameters of the reactor's air flow, aeration volume, and nutrient addition are weakly correlated with the reactor's temperature, and are nonlinear. A more complex LSTM module can be used to capture the nonlinear relationship of its input features. The LSTM module is better at processing time series data and can also be used to capture the time characteristics between the temperature data of the washing tank, reactor and external environment. Therefore, the input of the LSTM module can be all features, that is, the washing tank, reactor, and environmental temperature data in the previous time period, as well as the operating parameters of the air flow, aeration volume, and nutrient addition.

[0069] The feature fusion layer is used to fuse the output results of the SVM module and the LSTM module to form a unified feature vector.

[0070] Exemplarily, the prediction result of the SVM module is a scalar, such as 0.8, which represents the predicted temperature value of the reactor. The output of the LSTM module is a multidimensional vector, which represents the features extracted by the LSTM model after processing the time series data. Assume that the output of the LSTM module is a 64-dimensional vector, such as [0.01, 0.02, ... 0.64]. The scalar output of the SVM module and the vector output of the LSTM module are concatenated together to form a new feature vector. The concatenated feature vector will be a 65-dimensional vector, such as [0.8, 0.01, 0.02, ... 0.64]. The concatenated feature vector will be used as a new input and passed to the subsequent fully connected layer for further processing.

[0071] The two fully connected layers further extract the features of the fused feature vector to obtain higher-level features.

[0072] For example, the first fully connected layer converts the 65-dimensional feature vector into a 128-dimensional feature vector through a linear transformation. Nonlinearity is introduced through the ReLU activation function to extract higher-level features. The second fully connected layer converts the 128-dimensional feature vector into a 64-dimensional feature vector through a linear transformation. The ReLU activation function is used to further extract higher-level features.

[0073] The output layer is used to output the prediction results of the SVM-LSTM model.

[0074] Exemplarily, the output layer converts the 64-dimensional feature vector into a scalar through a linear transformation, which represents the final prediction result.

[0075] In one embodiment, the process of the PLC module in the temperature control device controlling the operation of the reactor and the waste heat recovery device according to the prediction result of the temperature prediction module specifically includes:

[0076] When the predicted temperature result of the reactor exceeds the set maximum temperature threshold, the heating device of the reactor and / or the washing tank is shut down through the PLC module, and the pipe valve connecting the heat exchanger in the waste heat recovery device to the reactor is closed, and the cooling device of the reactor is turned on to prevent the temperature in the next time period from exceeding the set maximum temperature threshold.

[0077] When the predicted temperature result of the reactor is lower than the set minimum temperature threshold, the heating device of the reactor and / or the washing tank is turned on through the PLC module, the pipe valve connecting the heat exchanger in the waste heat recovery device and the reactor is opened, and the cooling device of the reactor is closed to prevent the temperature in the next time period from being lower than the set minimum temperature threshold.

[0078] It is worth noting that the maximum and minimum temperature thresholds can be set according to the growth temperature adapted by different microbial flora, and are not limited to a specific temperature range. PLC (Programmable Logic Controller) is a computer system designed for industrial environments, used to automatically control various mechanical equipment and processes. It is understandable that in this solution, PLC can connect all temperature sensors to obtain temperature data. It can adjust the parameters of the heating device and the cooling device, control the pipeline valve used for heat transfer in the waste heat recovery device, control the transmission pipeline valve between the washing tank and the reactor, connect and control the microbial environment support system in real time, and record its control data. It can collect various data of the internal environment of the reactor, such as: temperature, humidity, TDS (total dissolved solids), pH, DO (dissolved oxygen), TN (total nitrogen), TP (total phosphorus), COD (chemical oxygen demand), etc. It is easy to understand that this solution is not limited to controlling the reactor's heating device and cooling device, and the pipeline valves of the waste heat recovery device to regulate the temperature inside the reactor, but can also be regulated by operating other equipment, such as controlling the transmission pipeline valve between the washing tank and the reactor, and controlling the microbial environment support system.

[0079] Figure 3 A schematic flow chart of a temperature control method based on an intelligent and efficient composite biofilter provided in an embodiment of this specification is shown, as Figure 3 As shown, the method includes:

[0080] Step S301, washing, heating and increasing the humidity of the exhaust gas by washing water in the washing tank. Specifically, the washing water is heated by a heating device, and the heated washing water is then heat-exchanged with the exhaust gas.

[0081] It is worth mentioning that during the process of washing the exhaust gas, the washing water can remove the lint and grease in the exhaust gas, and during the washing process, heat exchange occurs between the washing water and the exhaust gas, which increases the temperature of the exhaust gas and at the same time increases the humidity of the exhaust gas.

[0082] Step S302, the washed waste gas is passed into the reactor of the biological filter bed, and the waste gas is degraded by the microorganisms in the reactor. Specifically, a heating device and a cooling device are also provided in the reactor.

[0083] Step S303, the waste heat in the whole system is recovered by the heat accumulator in the waste heat recovery device. When the washing tank and the reactor need to be heated, the waste heat recovery device provides heat to the washing tank and the reactor through the heat exchanger.

[0084] It is worth mentioning that the heat accumulator can utilize the waste heat generated by any equipment included in the heating device and cooling device in the entire system device, such as the waste heat generated by the air compressor, air conditioner, steam condensate, etc.

[0085] Step S304, predicting the temperature in the reactor by the temperature prediction module in the temperature control device, and using the PLC module to control the operation of the equipment in the system according to the prediction result of the temperature prediction module to adjust the temperature of the reactor.

[0086] In one embodiment, the method for predicting the temperature in the reactor by the temperature prediction module in the temperature control device specifically includes:

[0087] Step S3041, obtaining the temperature data of the washing tank, the reactor and the external environment, and recording the time series of the temperature data, and obtaining the operating parameters of the reactor's air intake flow, aeration volume, and nutrient addition volume.

[0088] The temperature data of the washing tank, the reactor and the external environment are obtained through the data acquisition module, and the time series of the temperature data is recorded, and the operating parameters of the reactor's air intake flow, aeration volume, and nutrient addition amount are obtained. The temperature data is obtained through a temperature sensor, and the operating parameters are obtained from the microbial environment support system.

[0089] Step S3042, using the temperature data of the washing tank, the reactor and the external environment, as well as the operating parameters of the reactor's air intake flow rate, aeration volume, and nutrient addition amount to train the model.

[0090] The model training module is used to train the temperature data of the washing tank, reactor and external environment, as well as the operating parameters of the reactor's air intake flow, aeration volume, and nutrient addition amount.

[0091] Step S3043, input the temperature data of the washing tank and the external environment, as well as the operating parameters of the reactor's air intake flow, aeration volume, and nutrient addition volume into the trained model to predict the reactor temperature in the next time period.

[0092] The model prediction module predicts the reactor temperature in the next time period based on the temperature data of the washing tank and the external environment, as well as the operating parameters of the reactor's air intake flow, aeration volume, and nutrient addition amount.

[0093] Specifically, the prediction model can select a model suitable for processing time series data, such as ARI MA (autoregressive integrated moving average model), LSTM (long short-term memory network), GRU (gated recurrent unit), Prophet, XGBoost, etc. Using the temperature data of the washing tank and the external environment, as well as the operating parameters of the reactor's air intake flow, aeration volume, and nutrient addition as input, the prediction model is used to predict the internal temperature of the reactor at the next time point.

[0094] In one embodiment, in order to better adapt to the temperature control of the intelligent and efficient composite biological filter bed of this scheme, the present invention provides a new temperature prediction model, namely, the SVM-LSTM model. The SVM-LSTM model includes two input layers, an SVM module, an LSTM module, a feature fusion layer, two fully connected layers and an output layer.

[0095] Specifically, one of the input layers is connected to the SVM module for inputting the temperature data of the washing tank, reactor and external environment into the SVM module, and the other input layer is connected to the LSTM module for inputting the temperature data of the washing tank, reactor and external environment into the LSTM module, as well as the operating parameters of the reactor's air intake flow, aeration volume, and nutrient addition amount.

[0096] The feature fusion layer is used to fuse the output results of the SVM module and the LSTM module to form a unified feature vector.

[0097] The two fully connected layers further extract the features of the fused feature vector to obtain higher-level features.

[0098] The output layer is used to output the prediction results of the SVM-LSTM model.

[0099] In one embodiment, the process of the PLC module in the temperature control device controlling the operation of the reactor and the waste heat recovery device according to the prediction result of the temperature prediction module specifically includes:

[0100] When the predicted temperature result of the reactor exceeds the set maximum temperature threshold, the heating device of the reactor and / or the washing tank is shut down through the PLC module, and the pipe valve connecting the heat exchanger in the waste heat recovery device to the reactor is closed, and the cooling device of the reactor is turned on to prevent the temperature in the next time period from exceeding the set maximum temperature threshold.

[0101] When the predicted temperature result of the reactor is lower than the set minimum temperature threshold, the heating device of the reactor and / or the washing tank is turned on through the PLC module, the pipe valve connecting the heat exchanger in the waste heat recovery device and the reactor is opened, and the cooling device of the reactor is closed to prevent the temperature in the next time period from being lower than the set minimum temperature threshold.

[0102] According to another embodiment of the present invention, a computing device is provided, including a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, the Figure 3 The method described.

[0103] According to another embodiment, there is also provided a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to execute a combination of Figure 3 The method described.

[0104] Those skilled in the art should be aware that in one or more of the above examples, the functions described in the present invention can be implemented by hardware, software, firmware or any combination thereof. When implemented by software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium.

[0105] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solution of the present invention should be included in the scope of protection of the present invention.

Claims

1. A temperature control system based on an intelligent and efficient composite biofilter bed, characterized in that: include: Washing tank, biological filter bed, temperature control device, waste heat recovery device; among them, A washing tank, comprising an air inlet, an air outlet, washing water and a heating device, wherein the washing tank is used to wash, heat and increase the humidity of the exhaust gas, wherein the washing water is heated by the heating device, and the heated washing water is then heat-exchanged with the exhaust gas; The biofilter bed comprises a reactor, microorganisms, and a microorganism environment support system. The biofilter bed degrades waste gas through microorganisms, wherein the microorganisms are located in the reactor, the microorganism environment support system is connected to the reactor and provides a growth environment for the microorganisms, the washing tank is connected to the reactor, and the waste gas is washed in the washing tank and then flows into the reactor; wherein a heating device and a cooling device are also provided in the reactor; A waste heat recovery device, including a heat accumulator and a heat exchanger, wherein the heat accumulator recovers the waste heat in the whole system through a pipeline, and the heat exchanger is used to provide heat for the washing tank and the reactor; The temperature control device includes a temperature sensor, a temperature prediction module, and a PLC module. The temperature sensor is arranged in a washing tank, a reactor, and a waste heat recovery device. The temperature prediction module is used to predict the temperature inside the reactor. The PLC module is used to control the operation of the equipment in the system according to the prediction results of the temperature prediction module to adjust the temperature inside the reactor.

2. The system according to claim 1, characterized in that The temperature prediction module includes: A data acquisition module is used to acquire temperature data of the washing tank, the reactor and the external environment, and to record the time series of the temperature data, and is also used to acquire the operating parameters of the reactor such as the air intake flow rate, aeration volume, and nutrient addition amount; wherein the temperature data is acquired through a temperature sensor, and the operating parameters are acquired from a microbial environment support system; Model training module, used to train the temperature data of the washing tank, reactor and external environment, as well as the operating parameters of the reactor's air intake flow, aeration volume, and nutrient addition amount; The model prediction module is used to predict the reactor temperature in the next time period based on the temperature data of the washing tank and the external environment, as well as the operating parameters of the reactor's air intake flow, aeration volume, and nutrient addition volume.

3. The system according to claim 2, characterized in that The prediction model in the temperature prediction module is an SVM-LSTM model, which includes two input layers, an SVM module, an LSTM module, a feature fusion layer, two fully connected layers and an output layer, wherein: One input layer is connected to the SVM module and is used to input the temperature data of the washing tank, the reactor and the external environment to the SVM module, and the other input layer is connected to the LSTM module and is used to input the temperature data of the washing tank, the reactor and the external environment, as well as the operating parameters of the air intake flow rate, aeration volume and nutrient addition amount of the reactor to the LSTM module; The feature fusion layer is used to fuse the output results of the SVM module and the LSTM module to form a unified feature vector; The two fully connected layers further extract the features of the fused feature vector to obtain higher-level features; The output layer is used to output the prediction results of the SVM-LSTM model.

4. The system according to claim 1, characterized in that The process in which the PLC module in the temperature control device controls the operation of the reactor and the waste heat recovery device according to the prediction result of the temperature prediction module specifically includes: When the temperature prediction result of the reactor exceeds the set maximum temperature threshold, the heating device of the reactor and / or the washing tank is turned off through the PLC module, and the pipeline valve connecting the heat exchanger in the waste heat recovery device and the reactor is turned off, and the cooling device of the reactor is turned on to prevent the temperature of the next time period from exceeding the set maximum temperature threshold; When the predicted temperature result of the reactor is lower than the set minimum temperature threshold, the heating device of the reactor and / or the washing tank is turned on through the PLC module, the pipe valve connecting the heat exchanger in the waste heat recovery device and the reactor is opened, and the cooling device of the reactor is closed to prevent the temperature in the next time period from being lower than the set minimum temperature threshold.

5. A temperature control method based on an intelligent and efficient composite biofilter bed, implemented based on the temperature control system of the intelligent and efficient composite biofilter bed according to any one of claims 1 to 4, characterized in that: The method specifically comprises: The exhaust gas is washed, heated and humidified by the washing water in the washing tank; wherein the washing water is heated by a heating device, and the heated washing water is then heat-exchanged with the exhaust gas; The washed waste gas is passed into the reactor of the biofilter bed, and the waste gas is degraded by the microorganisms in the reactor; wherein a heating device and a cooling device are also provided in the reactor; The waste heat in the whole system is recovered by the heat accumulator in the waste heat recovery device. When the washing tank and the reactor need to be heated, the waste heat recovery device provides heat to the washing tank and the reactor through the heat exchanger. The temperature in the reactor is predicted by the temperature prediction module in the temperature control device, and the PLC module is used to control the operation of the equipment in the entire system according to the prediction results of the temperature prediction module to regulate the temperature of the reactor.

6. The method according to claim 5, characterized in that The method for predicting the temperature in a reactor by a temperature prediction module in a temperature control device specifically comprises: Obtain the temperature data of the washing tank, reactor and external environment, record the time series of the temperature data, and obtain the operating parameters of the reactor's air intake flow, aeration volume, and nutrient addition amount; The model was trained using the temperature data of the washing tank, reactor and external environment, as well as the operating parameters of the reactor's air flow rate, aeration volume, and nutrient addition; The temperature data of the washing tank and the external environment, as well as the operating parameters of the reactor such as air inlet flow, aeration volume, and nutrient addition amount are input into the trained model to predict the reactor temperature in the next time period.

7. The method according to claim 6, characterized in that The prediction model in the temperature prediction module is an SVM-LSTM model, which includes two input layers, an SVM module, an LSTM module, a feature fusion layer, two fully connected layers and an output layer, wherein: One input layer is connected to the SVM module and is used to input the temperature data of the washing tank, the reactor and the external environment to the SVM module, and the other input layer is connected to the LSTM module and is used to input the temperature data of the washing tank, the reactor and the external environment, as well as the operating parameters of the air intake flow rate, aeration volume and nutrient addition amount of the reactor to the LSTM module; The feature fusion layer is used to fuse the output results of the SVM module and the LSTM module to form a unified feature vector; The two fully connected layers further extract the features of the fused feature vector to obtain higher-level features; The output layer is used to output the prediction results of the SVM-LSTM model.

8. The method according to claim 5, characterized in that The method in which the PLC module in the temperature control device controls the operation of the reactor and the waste heat recovery device according to the prediction result of the temperature prediction module specifically includes: When the temperature prediction result of the reactor exceeds the set maximum temperature threshold, the heating device of the reactor and / or the washing tank is turned off through the PLC module, and the pipeline valve connecting the heat exchanger in the waste heat recovery device and the reactor is turned off, and the cooling device of the reactor is turned on to prevent the temperature of the next time period from exceeding the set maximum temperature threshold; When the predicted temperature result of the reactor is lower than the set minimum temperature threshold, the heating device of the reactor and / or the washing tank is turned on through the PLC module, the pipe valve connecting the heat exchanger in the waste heat recovery device and the reactor is opened, and the cooling device of the reactor is closed to prevent the temperature in the next time period from being lower than the set minimum temperature threshold.

Images