Compound desulfurization management method and device based on big data, terminal and medium

Abstract

The invention discloses a composite desulfurization management method and device based on big data, a terminal and a medium. The composite desulfurization management method based on the big data comprises the following steps: collecting operation data, external environment data, desulfurizer components and desulfurizer dosage of a desulfurization reactor; the operation data of the desulfurization reactor, the external environment data, the desulfurizer components and the desulfurizer dosage are transmitted to a central data management system for data preprocessing; establishing a desulfurization prediction model according to the preprocessed data, and predicting desulfurization efficiency under different operation conditions; adjusting operation parameters of the desulfurization system according to the prediction result; the prediction model is constructed based on the big data technology, and the operation parameters of the desulfurization system are dynamically adjusted based on the prediction result, so that the desulfurization efficiency is remarkably improved, the energy consumption is reduced, and the adaptability of the system to environmental change is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of desulfurization management, and in particular to a composite desulfurization management method, device, terminal and medium based on big data. Background Art

[0002] In recent years, desulfurization technology has made significant progress in the field of industrial waste gas treatment, especially in reducing sulfur dioxide (SO2) emissions. Desulfurization technologies mainly include wet desulfurization, dry desulfurization and semi-dry desulfurization. Among them, wet desulfurization has become the most important application method due to its high treatment efficiency and wide application range. Wet desulfurization uses desulfurizers to react with SO2 in flue gas to generate by-products such as calcium sulfate or sulfur, thereby achieving desulfurization. With the continuous improvement of environmental protection requirements, desulfurization systems are also constantly developing. Modern desulfurization systems have moved towards intelligence and automation, including real-time monitoring, online analysis and process optimization. Functions such as have gradually become mainstream. Through integrated sensors and automatic control systems, modern desulfurization technology can make real-time adjustments to the desulfurization process to improve treatment efficiency and reduce operating costs.

[0003] However, existing desulfurization systems still face some key challenges in the process. Traditional desulfurization control methods usually rely on static operating parameters and empirical rules, which limits the system's adjustment and optimization capabilities when facing complex and dynamic operating conditions. They are often unable to integrate and analyze these multi-source data in real time, making it difficult to make effective predictions and adjustments in actual operations. In addition, the existing technologies for predicting desulfurization efficiency and adjusting system parameters are mostly based on a single static model, which lacks flexibility and adaptability to handle different operating conditions and environmental changes. Summary of the invention

[0004] In order to overcome the defects in the above-mentioned prior art, the present invention provides a composite desulfurization management method based on big data, including: collecting the operation data, external environmental data, desulfurizer composition and desulfurizer dosage of the desulfurization reactor; transmitting the operation data, external environmental data, desulfurizer composition and desulfurizer dosage of the desulfurization reactor to the central data management system for data preprocessing; establishing a desulfurization prediction model based on the preprocessed data to predict the desulfurization efficiency under different operating conditions; and adjusting the operating parameters of the desulfurization system according to the prediction results.

[0005] As a preferred scheme of the composite desulfurization management method based on big data described in the present invention, wherein: the prediction model includes an input layer, a feature extraction layer, a codec, a fusion layer and an output layer; the feature extraction layer includes an adaptive convolution unit and a conversion unit, the adaptive convolution unit adjusts the dimension and parameters of the convolution kernel by learning the characteristics of the data to adapt to different types of input data, and then performs nonlinear mapping and feature transformation on the input data through the conversion unit; the codec encodes the input data into a distribution in a latent space, and then reconstructs the input data from the latent space to learn the latent features; the features extracted by the feature extraction layer and the latent features extracted by the codec are fused through the fusion layer to form a comprehensive feature representation; the output layer predicts the desulfurization efficiency under different operating conditions through the LeakyReLu activation function.

[0006] As a preferred solution of the composite desulfurization management method based on big data described in the present invention, wherein: the LeakyReLu activation function includes: the mathematical expression of the LeakyReLu activation function is as follows:

[0007]

[0008] in, represents the negative gradient, and x represents the input vector.

[0009] As a preferred solution of the composite desulfurization management method based on big data described in the present invention, it includes: equipment operation data including: temperature, pressure, flow; external environment data including: external temperature, humidity, air pressure, pollutant concentration.

[0010] As a preferred scheme of the composite desulfurization management method based on big data described in the present invention, it includes: storing the operation data of the desulfurization reactor, external environment data, desulfurizer composition and desulfurizer usage in the data lake; performing data preprocessing through the AWS Glue tool, including data extraction, cleaning and integration; and establishing a desulfurization prediction model based on the preprocessed data through the Amazon SageMaker platform.

[0011] As a preferred scheme of the composite desulfurization management method based on big data described in the present invention, it includes: using the AdaGrad optimizer to iteratively train the prediction model, setting the initial learning rate, and continuously adjusting the weight w and bias b of the prediction model until the target loss function value reaches the minimum, and the target loss function is the Log-Cosh loss function.

[0012] As a preferred scheme of the composite desulfurization management method based on big data described in the present invention, it includes: pre-compensating the feedforward control signal according to the prediction result; setting the target value of the reaction temperature and desulfurization efficiency of the desulfurization system, inputting the target value and actual value of the reaction temperature and desulfurization efficiency of the desulfurization system into the controller, and adjusting the reagent flow and heating power according to the error between the target value and the actual value.

[0013] The present invention also provides a composite desulfurization management device based on big data, including: the composite desulfurization management device based on big data is used to implement the composite desulfurization management method based on big data as described in any of the above items, a composite desulfurization management device based on big data includes: a data collection module, configured to collect the operation data, external environment data, desulfurizer composition and desulfurizer usage of the desulfurization reactor; a data processing module, configured to transmit the operation data, external environment data, desulfurizer composition and desulfurizer usage of the desulfurization reactor to the central data management system for data preprocessing; a desulfurization prediction module, configured to establish a desulfurization prediction model based on the preprocessed data to predict the desulfurization efficiency under different operating conditions; a desulfurization management module, configured to adjust the operating parameters of the desulfurization system according to the prediction results.

[0014] The present invention also provides a terminal device, comprising:

[0015] one or more processors;

[0016] A memory, coupled to the processor, for storing one or more programs;

[0017] When the one or more programs are executed by the one or more processors, the one or more processors implement the composite desulfurization management method based on big data as described in any one of the above items.

[0018] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the composite desulfurization management method based on big data as described in any one of the above items.

[0019] Beneficial effects of the present invention: The present invention constructs a prediction model based on big data technology, and dynamically adjusts the operating parameters of the desulfurization system based on the prediction results, thereby significantly improving the desulfurization efficiency, reducing energy consumption, and enhancing the system's adaptability to environmental changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing 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 labor. Among them:

[0021] Figure 1 This is a schematic flow chart of the composite desulfurization management method based on big data described in the first embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0023] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0024] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0025] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0026] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0027] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0028] Example 1

[0029] Reference Figure 1 , which is the first embodiment of the present invention, and provides a composite desulfurization management method based on big data, including:

[0030] S1: Collect the operation data of the desulfurization reactor, external environment data, desulfurization agent composition and desulfurization agent dosage.

[0031] (1) Collect equipment operation data

[0032] Install temperature sensors at key locations (such as reactor inlet, outlet, and desulfurizer injection point) to collect temperature data;

[0033] Pressure sensors are installed inside the reactor and at the inlet and outlet to monitor the pressure changes during the desulfurization reaction.

[0034] Install flow meters at the desulfurizer inlet and gas outlet to ensure accurate measurement of flow changes.

[0035] (2) Collect external environment data

[0036] Collect the temperature, humidity and air pressure near the desulfurization facility through meteorological sensors (such as temperature sensors, humidity sensors and air pressure sensors);

[0037] Deploy gas analyzers (such as SO2, NOx sensors) to monitor changes in the concentration of pollutants in the atmosphere.

[0038] (3) Detection of desulfurizer composition

[0039] The composition of the desulfurizer is detected in real time by a chemical analyzer or an online monitoring instrument.

[0040] (4) Record the amount of desulfurizer used

[0041] Install weighing sensors or flow meters in the desulfurizer storage and delivery system to accurately record the amount of desulfurizer used.

[0042] S2: The operation data of the desulfurization reactor, the external environment data, the desulfurization agent composition and the desulfurization agent dosage are transmitted to the central data management system for data preprocessing.

[0043] The operating data of the desulfurization reactor, external environmental data, desulfurizer composition and desulfurizer usage are stored in the data lake, namely Amazon S3. Amazon S3 can store a large amount of raw data and processed data, including structured, semi-structured and unstructured data. In addition, the data stored in the data lake can be queried through Amazon Athena.

[0044] Furthermore, create data connections in AWS Glue, configure access permissions and authentication methods to extract data from data sources, and preprocess data through AWS Glue tools, including using AWS Glue's ETL jobs to extract, clean, and integrate data, and convert data into a format suitable for analysis and model training.

[0045] Preferably, this embodiment can efficiently process data extraction, conversion, and loading through the AWS Glue tool, providing reliable data support for subsequent data analysis and model training.

[0046] S3: A desulfurization prediction model is established based on the pretreated data to predict the desulfurization efficiency under different operating conditions.

[0047] Based on the preprocessed data, a desulfurization prediction model is established through the Amazon SageMaker platform. The prediction model includes an input layer, a feature extraction layer, a codec, a fusion layer, and an output layer.

[0048] The feature extraction layer includes an adaptive convolution unit and a conversion unit. The adaptive convolution unit adjusts the dimensions and parameters of the convolution kernel by learning the characteristics of the data to adapt to different types of input data, and then performs nonlinear mapping and feature transformation on the input data through the conversion unit (deep transformation network, DTN);

[0049] The encoder-decoder is used to generate a latent representation of the data and enhance the feature expression. Specifically, the input data is first encoded into a distribution in the latent space, and then the input data is reconstructed from the latent space to learn the latent features.

[0050] The features extracted by the feature extraction layer and the potential features extracted by the codec are fused through the fusion layer, that is, the features from different sources are spliced ​​by channel to form a comprehensive feature representation;

[0051] The output layer predicts the desulfurization efficiency under different operating conditions through the LeakyReLu activation function.

[0052] The mathematical expression of the LeakyReLu activation function is as follows:

[0053]

[0054] in, represents the negative gradient, and x represents the input vector.

[0055] Furthermore, the prediction model is iteratively trained using the AdaGrad optimizer, with the initial learning rate set to 0.001 and the number of training epochs set to 100. The weights w and bias b of the prediction model are continuously adjusted until the target loss function value is minimized. The target loss function is the Log-Cosh loss function.

[0056] Log-Cosh loss function for:

[0057]

[0058] In the formula, represents the predicted value, y represents the true value, and cosh() is the hyperbolic cosine function.

[0059] In a desulfurization system used by a power company, the desulfurization efficiency under different operating conditions and desulfurizer compositions was tested through a predictive model.

[0060] Operating conditions:

[0061] Temperature: 80℃, 85℃, 88℃, 90℃;

[0062] Pressure: 100kPa, 101kPa, 102kPa;

[0063] Flow rate: 100m 3 、150m 3 、180m 3 、200m 3 ;

[0064] External temperature: 13℃, 14℃, 15℃, 16℃;

[0065] Humidity: 55%, 60%, 65%, 70%;

[0066] Air pressure: 100kPa, 101kPa, 102kPa;

[0067] Pollutant concentration: 48mg / m 3 , 49mg / m 3 , 50mg / m 3 , 52mg / m 3 ;

[0068] Desulfurizer dosage: 50kg / h, 55kg / h, 60kg / h, 65kg / h;

[0069] Desulfurizer ingredients:

[0070] Desulfurization agent concentration: 0.1M;

[0071] Desulfurization powder: 0.1mm;

[0072] The temperature, pressure, flow, external temperature, humidity, air pressure, pollutant concentration, desulfurizer composition and desulfurizer dosage are predicted. Some of the prediction results are shown in the following table.

[0073] Table 1: Desulfurization efficiency prediction results.

[0074]

[0075] It can be seen from Table 1 that the prediction model of this application has a high prediction accuracy and is 3 / h, external temperature 13°C, humidity 70%, air pressure 100kPa, pollutant concentration 49mg / m 3 Under the conditions of 0.1 mm desulfurization powder and 65 kg / h desulfurizer dosage, the predicted desulfurization efficiency is the highest (92.1%). Therefore, these conditions and desulfurizer components can be considered for use in actual operations.

[0076] S4: Adjust the operating parameters of the desulfurization system according to the prediction results.

[0077] (1) Pre-compensating the feedforward control signal according to the prediction results;

[0078] Based on the predicted results and the expected target value, the error is calculated, and based on the calculated error, the feedforward control signal is adjusted to offset the expected error. For example, if the prediction shows that the desulfurization system output will deviate from the target, the feedforward control signal is increased or decreased accordingly.

[0079] (2) setting target values ​​of the reaction temperature and desulfurization efficiency of the desulfurization system, inputting the target values ​​and actual values ​​of the reaction temperature and desulfurization efficiency of the desulfurization system into the controller, and adjusting the reagent flow rate and heating power according to the error between the target value and the actual value;

[0080] Design the sliding surface of the controller to ensure that it can effectively handle the dynamic changes in desulfurization efficiency and ensure that the system can still operate stably when there are disturbances or parameter changes. The specific steps are as follows:

[0081] Step 1: Define system state variables

[0082] Desulfurization efficiency (η): The main control target of the system, which can be measured in real time by sensors.

[0083] Control input (u): reagent flow rate and heating power.

[0084] Step 2: Select the error variable related to desulfurization efficiency and design the sliding surface σ(t) as:

[0085] σ(t)=e(t)+λ∫e(t)dt

[0086] Among them, e(t) is the error of desulfurization efficiency, that is, the difference between the set value and the actual value, and λ is a positive constant that determines the integral effect of the error.

[0087] Preferably, the sliding surface designed in this way ensures that the error of the system slides on the sliding surface, thereby making the system stable on the sliding surface.

[0088] Step 3: Design the control law:

[0089] u(t)=-K·sign(σ(t))

[0090] Where K is the control gain and sign(·) is the sign function, indicating the direction of the sliding surface.

[0091] Set the target values ​​of the reaction temperature and desulfurization efficiency of the desulfurization system, input the target values ​​and actual values ​​of the reaction temperature and desulfurization efficiency of the desulfurization system into the controller, and adjust the reagent flow rate and heating power according to the error between the target value and the actual value;

[0092] For example, if the goal is to improve desulfurization efficiency and the actual efficiency is lower than the set value, the controller will increase the efficiency by increasing the reagent flow rate.

[0093] If the goal is to maintain a stable reaction temperature and the actual temperature is below the set point, the controller increases the heating power; if the temperature is too high, it reduces the heating power.

[0094] Example 2

[0095] The present invention provides a composite desulfurization management device based on big data, which is used to implement the steps of the composite desulfurization management method based on big data in any of the above embodiments. The composite desulfurization management device based on big data includes:

[0096] A data collection module is configured to collect operation data of the desulfurization reactor, external environment data, desulfurization agent composition and desulfurization agent usage;

[0097] A data processing module is configured to transmit the operation data of the desulfurization reactor, the external environment data, the desulfurization agent composition and the desulfurization agent dosage to the central data management system for data preprocessing;

[0098] A desulfurization prediction module is configured to establish a desulfurization prediction model based on the preprocessed data to predict the desulfurization efficiency under different operating conditions;

[0099] The desulfurization management module is configured to adjust the operating parameters of the desulfurization system according to the prediction results.

[0100] Example 3

[0101] This embodiment provides a terminal device, including:

[0102] one or more processors;

[0103] A memory, coupled to the processor, for storing one or more programs;

[0104] When the one or more programs are executed by the one or more processors, the one or more processors implement the composite desulfurization management method based on big data as described above.

[0105] The processor is used to control the overall operation of the terminal device to complete all or part of the steps of the above-mentioned composite desulfurization management method based on big data. The memory is used to store various types of data to support the operation of the terminal device, which data may include, for example, instructions for any application or method used to operate on the terminal device, and application-related data. The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk.

[0106] The terminal device can be implemented by one or more application-specific integrated circuits (Application Specific Integrated Circuit, ASC), digital signal processors (Digital Signal Processor, DSP), digital signal processing devices (Digital Signal Processing Device, DSPD), programmable logic devices (Programmable Logic Device, PLD), field programmable gate arrays (Field Programmable Gate Array, FPGA), controllers, microcontrollers, microprocessors or other electronic components, and is used to execute the composite desulfurization management method based on big data as described in any of the above embodiments, and achieve the same technical effect as the above method.

[0107] Example 4

[0108] This embodiment provides a computer-readable storage medium, and when the program instructions are executed by a processor, the steps of the composite desulfurization management method based on big data as described in any of the above embodiments are implemented. For example, the computer-readable storage medium can be the above-mentioned memory including the program instructions, and the above-mentioned program instructions can be executed by the processor of the terminal device to complete the composite desulfurization management method based on big data as described in any of the above embodiments, and achieve the same technical effect as the above method.

[0109] It should be appreciated that embodiments of the present invention may be implemented or enforced by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable memory. The method may be implemented in a computer program using standard programming techniques - including a non-transitory computer-readable storage medium configured with a computer program, wherein the storage medium so configured causes the computer to operate in a specific and predefined manner - according to the methods and drawings described in the specific embodiments. Each program may be implemented in a high-level procedural or object-oriented programming language to communicate with a computer system. However, if desired, the program may be implemented in an assembly or machine language. In any case, the language may be a compiled or interpreted language. In addition, the program may be run on a programmed ASIC for this purpose.

[0110] Furthermore, the operations of the processes described herein may be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and / or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) that is executed collectively on one or more processors, by hardware, or a combination thereof. The computer program includes a plurality of instructions that may be executed by one or more processors.

[0111] Further, the method can be implemented in any type of computing platform that is operably connected to a suitable computer, including but not limited to a personal computer, a minicomputer, a mainframe, a workstation, a network or distributed computing environment, a separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, etc. Aspects of the present invention can be implemented in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, an optical read and / or write storage medium, a RAM, a ROM, etc., so that it can be read by a programmable computer, and when the storage medium or device is read by the computer, it can be used to configure and operate the computer to perform the process described herein. In addition, the machine-readable code, or part thereof, can be transmitted via a wired or wireless network. When such media includes instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor, the invention described herein includes these and other different types of non-transitory computer-readable storage media. When programmed according to the methods and techniques described in the present invention, the present invention also includes the computer itself. The computer program can be applied to input data to perform the functions described herein, thereby converting the input data to generate output data stored in a non-volatile memory. The output information can also be applied to one or more output devices such as a display. In a preferred embodiment of the present invention, the converted data represents a physical and tangible object, including a specific visual depiction of the physical and tangible object produced on a display.

[0112] As used in this application, the terms "component", "module", "system", etc. are intended to refer to a computer-related entity, which can be hardware, firmware, a combination of hardware and software, software, or software in operation. For example, a component can be, but is not limited to: a process running on a processor, a processor, an object, an executable file, a thread in execution, a program, and / or a computer. As an example, an application running on a computing device and the computing device can both be components. One or more components can exist in a process and / or thread in execution, and a component can be located in a computer and / or distributed between two or more computers. In addition, these components can be executed from various computer-readable media having various data structures thereon. These components can communicate in a local and / or remote process manner, such as according to a signal having one or more data packets (e.g., data from a component that interacts with another component in a local system, a distributed system, and / or interacts with other systems in a signal manner through a network such as the Internet).

[0113] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A composite desulfurization management method based on big data, characterized in that: include: Collect the operation data of the desulfurization reactor, external environment data, desulfurization agent composition and desulfurization agent dosage; Transmit the desulfurization reactor operation data, external environment data, desulfurization agent composition and desulfurization agent dosage to the central data management system for data preprocessing; Establish a desulfurization prediction model based on the pre-treated data to predict the desulfurization efficiency under different operating conditions; Adjust the operating parameters of the desulfurization system according to the prediction results.

2. The composite desulfurization management method based on big data according to claim 1, characterized in that: The prediction model includes an input layer, a feature extraction layer, a codec, a fusion layer and an output layer; The feature extraction layer includes an adaptive convolution unit and a conversion unit. The adaptive convolution unit adjusts the dimension and parameters of the convolution kernel by learning the characteristics of the data to adapt to different types of input data, and then performs nonlinear mapping and feature transformation on the input data through the conversion unit. The codec encodes the input data into a distribution in a latent space, and then reconstructs the input data from the latent space to learn latent features; The features extracted by the feature extraction layer and the potential features extracted by the codec are fused through the fusion layer to form a comprehensive feature representation; The output layer predicts the desulfurization efficiency under different operating conditions through the LeakyReLu activation function.

3. The composite desulfurization management method based on big data according to claim 2, characterized in that: The LeakyReLu activation function includes: The mathematical expression of the LeakyReLu activation function is as follows: in, represents the negative gradient, and x represents the input vector.

4. The composite desulfurization management method based on big data according to claim 3 is characterized in that: include: Equipment operation data include: temperature, pressure, flow; External environmental data include: external temperature, humidity, air pressure, and pollutant concentration.

5. The composite desulfurization management method based on big data according to claim 4, characterized in that: include: Store the desulfurization reactor operation data, external environment data, desulfurization agent composition and desulfurization agent usage in the data lake; Use AWS Glue to preprocess data, including data extraction, cleaning, and integration; A desulfurization prediction model is established based on the preprocessed data through the Amazon SageMaker platform.

6. The composite desulfurization management method based on big data according to claim 5, characterized in that: include: The prediction model is iteratively trained using the AdaGrad optimizer. The initial learning rate is set and the weights w and bias b of the prediction model are continuously adjusted until the target loss function value is minimized. The target loss function is the Log-Cosh loss function.

7. The composite desulfurization management method based on big data according to claim 6, characterized in that: include: Pre-compensating the feedforward control signal according to the prediction result; Set the target values ​​of the reaction temperature and desulfurization efficiency of the desulfurization system, input the target value and actual value of the reaction temperature and desulfurization efficiency of the desulfurization system into the controller, and adjust the reagent flow and heating power according to the error between the target value and the actual value.

8. A composite desulfurization management device based on big data, used to implement the composite desulfurization management method based on big data according to any one of claims 1 to 7, the composite desulfurization management device based on big data comprising: A data collection module is configured to collect operation data of the desulfurization reactor, external environment data, desulfurization agent composition and desulfurization agent usage; A data processing module is configured to transmit the operation data of the desulfurization reactor, the external environment data, the desulfurization agent composition and the desulfurization agent dosage to the central data management system for data preprocessing; A desulfurization prediction module is configured to establish a desulfurization prediction model based on the preprocessed data to predict the desulfurization efficiency under different operating conditions; The desulfurization management module is configured to adjust the operating parameters of the desulfurization system according to the prediction results.

9. A terminal device, characterized in that: include: one or more processors; A memory, coupled to the processor, for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the big data-based composite desulfurization management method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement the composite desulfurization management method based on big data as described in any one of claims 1 to 7.

Images