Intelligent temperature control system and method for thermal depolymerization reaction
By deploying multiple types of sensors with three-dimensional grid nodes on the inner wall of the pyrolysis polymerization reactor, and combining them with the quantum annealing fruit fly optimization algorithm, precise and intelligent control of the pyrolysis polymerization reaction temperature was achieved. This solved the problems of insufficient accuracy and intelligence in traditional temperature control systems, improved reaction stability and product quality, and reduced energy consumption.
Patent Information
- Application Number
- CN202510836636.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-21
- Publication Date
- 2025-10-31
AI Technical Summary
Existing temperature control systems for pyrolysis polymerization reactions suffer from low temperature control accuracy and a lack of intelligent control. They are ill-suited to the nonlinear, time-varying, and large hysteresis characteristics of the reaction process, resulting in poor reaction stability and product quality, as well as high operating costs.
By deploying multiple types of temperature sensors using a three-dimensional mesh node, and combining the quantum annealing fruit fly optimization algorithm and dynamic weight fitness function, the reactor temperature can be dynamically adjusted by collecting temperature data in real time, extracting time and spatial domain feature parameters, and generating precise control commands.
It significantly improves the intelligence and adaptability of temperature control, enhances reaction stability and product quality consistency, reduces energy consumption, and minimizes the need for manual intervention.
Smart Images
Figure CN120872071A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of pyrolysis polymerization control technology, and in particular to an intelligent temperature control system and method for pyrolysis polymerization. Background Technology
[0002] Pyrolysis polymerization is the process of decomposing high-molecular-weight polymers into low-molecular-weight substances through heating, and it has wide applications in chemical engineering, energy, and other fields. During pyrolysis polymerization, temperature is a key factor affecting the reaction rate, product quality, and yield. Currently, existing temperature control systems for pyrolysis polymerization typically employ traditional PID control methods. These systems collect the reaction temperature using temperature sensors, compare it with the set temperature, and adjust the output power of the heating or cooling devices based on the deviation. However, this traditional control method has several shortcomings. Firstly, the pyrolysis polymerization process is characterized by nonlinearity, time-varying nature, and large time lag. Traditional PID control struggles to adjust control parameters accurately in real time, resulting in low temperature control precision and significant temperature fluctuations, which negatively impact reaction stability and product quality. Secondly, existing systems often lack comprehensive consideration of various complex factors during the reaction process, such as changes in reactant composition and fluctuations in reaction pressure. This prevents intelligent temperature control, requiring frequent manual intervention, increasing operating costs and the risk of human error.
[0003] Therefore, there is an urgent need for a system and method that can adapt to the characteristics of thermal depolymerization reactions and achieve high-precision, intelligent temperature control. Summary of the Invention
[0004] The purpose of this invention is to provide an intelligent temperature control system and method for pyrolysis polymerization reactions, so as to solve the problems of low accuracy and lack of intelligent control in traditional PID control mentioned in the background art.
[0005] To achieve the above objectives, this application provides the following solution: In a first aspect, this application provides an intelligent temperature control system for a pyrolysis polymerization reaction, comprising: The temperature acquisition module is configured to be deployed on three-dimensional mesh nodes on the inner wall of the reactor. One temperature sensor is used to collect the temperature sequence of discrete spatial points inside the reactor in real time. The data processing module is configured to extract feature parameters from the collected temperature data and generate a parameter set containing time-domain and spatial-domain features. The control decision module is configured to use the quantum annealing fruit fly optimization algorithm as input to generate control commands by optimizing the control parameter vector. The execution module is configured to output heating power and cooling flow rate according to control commands, thereby achieving dynamic adjustment of the reactor temperature.
[0006] Optionally, the temperature sensors of the temperature acquisition module are arranged in a hexahedral grid on the inner wall of the reactor, and the spacing between adjacent sensors is... ,in Let be the side length of the reactor's inner cavity.
[0007] Optionally, the temperature sensor includes at least one of a thermocouple, an infrared temperature sensor, or a fiber Bragg grating sensor.
[0008] Optionally, the spatial domain features extracted by the data processing module include the temperature change rate:
[0009] in, For the first A temperature sensor in Temperature collected at all times The sampling time interval; The spatial domain features extracted by the data processing module include the temperature gradient magnitude: .
[0010] Optionally, in the control decision module, the quantum annealing fruit fly optimization algorithm uses feature parameters. and To obtain input, control commands are generated through the following steps: Multiple fruit fly individuals are randomly generated within a preset control parameter space, and each fruit fly individual corresponds to a control parameter vector. With characteristic parameters and As input, the control parameter vectors of each fruit fly individual are evaluated through a fitness function, and the current optimal vector is selected. The control parameter vector of individual fruit flies is adjusted using the quantum state update formula, while the annealing temperature is updated simultaneously. Substitute the updated control parameter vector back into the fitness function to calculate and determine whether the iteration termination condition is met. If it is met, stop the optimization and output the optimal control parameter vector; otherwise, continue the iteration. The optimal control parameter vector is substituted into the control law calculation to generate control commands for heating power and cooling flow rate, which are then sent to the execution module.
[0011] Optionally, the fitness function is:
[0012] in, For temperature tracking error, Constrained by the rate of temperature change, To equalize the temperature gradient; The dynamic weighting coefficients satisfy the following conditions: .
[0013] Optionally, for each individual fruit fly The quantum state update formula is: in, For individual fruit flies Updated control parameter vector, This is the control parameter vector corresponding to the fruit fly individual with the best fitness in the current iteration. For individual fruit flies The current control parameter vector, This represents the current iteration number; For quantum perturbation coefficients, It follows a standard normal distribution.
[0014] Optionally, the termination condition of the optimization algorithm is that the fitness change is less than a threshold after K consecutive iterations. ,Right now: .
[0015] Optionally, the execution module includes a heating submodule and a cooling submodule, wherein: The heating submodule includes at least one of an electric heating wire, a microwave heating device, or a resistance heating element. The cooling submodule includes at least one of a circulating cooling water system, a refrigerant spray device, or an air cooler.
[0016] Secondly, this application provides a smart temperature control method for a pyrolysis polymerization reaction, comprising the following steps: The temperature sequence of discrete spatial points inside the reactor is collected in real time by deploying multiple temperature sensors on three-dimensional grid nodes on the inner wall of the reactor. Spatiotemporal feature parameters are extracted from the temperature sequence to generate a parameter set containing the temperature change rate and temperature gradient magnitude. Based on the quantum annealing fruit fly optimization algorithm, the parameter set is used as input to generate control commands by optimizing the control parameter vector. The control command outputs heating power and cooling flow rate to achieve dynamic adjustment of the reactor temperature.
[0017] Through the above technical solutions, the beneficial effects of this invention are as follows: This application combines the quantum annealing fruit fly optimization algorithm with a dynamic weighted fitness function, overcoming the limitations of traditional PID control in nonlinear, time-varying, and large-lag scenarios of pyrolysis polymerization reactions. The system deploys multiple types of sensors through three-dimensional mesh nodes to achieve high-density spatiotemporal sampling of the temperature field. It utilizes the weighted Delaunay triangulation method to accurately extract the temperature change rate and gradient features, and leverages the quantum annealing mechanism to enhance the algorithm's global optimization capability. The control strategy can be dynamically adjusted according to the reaction stage, achieving precise temperature tracking, rate-of-change constraint, and spatial uniformity control without manual intervention. This solution not only significantly improves the intelligence and adaptability of pyrolysis polymerization temperature control but also enhances reaction stability, improves product quality consistency, and reduces energy consumption through multi-dimensional collaborative optimization, providing an efficient and reliable solution for intelligent temperature control in pyrolysis polymerization processes. Attached Figure Description
[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention, and the embodiments in the accompanying drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0019] Figure 1 This is a schematic diagram of the structure of an intelligent temperature control system for a pyrolysis polymerization reaction provided in an embodiment of this application; Figure 2 A flowchart of an intelligent temperature control method for a pyrolysis polymerization reaction provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a computer device provided in one embodiment of this application; The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0020] It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of the application. Rather, these embodiments are provided to make the disclosure more thorough and complete, and to fully convey the scope of the disclosure to those skilled in the art.
[0021] The foregoing and other technical contents, features and effects of the present invention are described in conjunction with the appendix below. Figure 1-3 The detailed description of the embodiments will make this clear. All structural details mentioned in the following embodiments are based on the accompanying drawings.
[0022] Exemplary embodiments of the present invention will now be described with reference to the accompanying drawings.
[0023] In one exemplary embodiment, such as Figure 1 As shown, an intelligent temperature control system for a pyrolysis polymerization reaction is provided, including a temperature acquisition module 101, a data processing module 102, a control decision module 103, and an execution module 104. These modules work together to achieve precise and intelligent control of the pyrolysis polymerization reaction temperature.
[0024] Temperature acquisition module 101 is configured to be deployed on three-dimensional mesh nodes on the inner wall of the reactor. One temperature sensor is used to collect data on discrete spatial points within the reactor in real time. The temperature sequence is shown. The temperature sensors are arranged in a hexahedral grid on the inner wall of the reactor, with adjacent sensors spaced apart... ,in This is the side length of the reactor's inner cavity. The temperature sensor includes at least one of a thermocouple, an infrared temperature sensor, or a fiber Bragg grating sensor.
[0025] For example, in a cylindrical pyrolysis reactor with a diameter of 2 meters and a height of 3 meters, the temperature acquisition module constructs a three-dimensional grid structure on the inner wall and deploys 36 high-precision temperature sensors, including 24 K-type thermocouple sensors and 12 infrared temperature sensors. The sensors are distributed in a hexahedral grid, with 6 layers arranged axially at 0.5-meter intervals, 2 concentric circles arranged radially at 0.3-meter intervals, and 3 points evenly distributed circumferentially at 120° intervals. During operation, all sensors synchronously acquire temperature data from each discrete spatial point at a sampling interval of 1 second, forming a temperature matrix containing time series and spatial coordinates, which is transmitted to the data processing module via wired / wireless dual channels. Among them, the K-type thermocouple sensors are suitable for measuring the temperature in the central area or near the heating source where the temperature fluctuates greatly and is relatively high, while the infrared sensors can monitor the temperature of the reaction liquid surface non-contactly. The two work together to achieve multi-dimensional coverage of the temperature field inside the reactor. This module, through a high-density grid layout and a combination of multiple types of sensors, can capture the axial, radial, and circumferential temperature change trends within the reactor in real time, ensuring the spatiotemporal integrity of temperature acquisition and avoiding control lag caused by sampling blind spots, thus providing a comprehensive and accurate data foundation for subsequent extraction of temperature characteristic parameters.
[0026] The data processing module 102 is configured to extract feature parameters from the collected temperature data and generate a parameter set containing time domain features and spatial domain features.
[0027] Specifically, the time-domain features extracted by the data processing module 102 include the temperature change rate, which is obtained by calculating the time derivative of the single-sensor data, as shown in the following formula:
[0028] in, For the first A temperature sensor in Temperature collected at all times The sampling time interval; The spatial domain features extracted by the data processing module include the temperature gradient magnitude. The temperature gradient magnitude is obtained by spatial interpolation of multi-sensor data to obtain a continuous temperature field, and then the temperature gradient at each point is calculated by the finite difference method.
[0029] Specifically, this embodiment employs weighted Delaunay triangulation for spatial interpolation. Weighted Delaunay triangulation is a spatial interpolation method that integrates geometric optimization and data weighting. Its core principle is to assign weight coefficients to different types of sensor data based on Delaunay triangulation, and then reconstruct a continuous temperature field from discrete temperature sampling points using an inverse distance weighting formula. This method ensures the topological rationality of spatial interpolation through geometric triangulation and compensates for the accuracy differences between different sensors using weight coefficients. It can reconstruct discrete temperature data into a continuous field reflecting the true temperature distribution, thereby accurately calculating spatial characteristic parameters such as temperature gradients. The specific steps are as follows: First, the data from the 36 sensors acquired by the temperature acquisition module are arranged according to spatial coordinates. and timestamp Perform spatiotemporal alignment to construct a discrete point set. For each sampling time Generate independent spatial point sets .
[0030] Then, for each A Delaunay tetrahedral mesh is generated based on the sensor's spatial coordinates, ensuring that the circumsphere of each tetrahedron contains no other sampling points, thereby optimizing the spatial subdivision quality. This mesh structure provides the geometric basis for subsequent interpolation, guaranteeing the convex hull of the interpolation region and maximizing the minimum interior angle of the triangular facets.
[0031] For any point to be interpolated Its temperature value Calculated using the following formula:
[0032] in, For sensors At any moment The measured value; interpolation point To the sensor The Euclidean distance; As the weighting index, in this embodiment, we take... .
[0033] To compensate for the accuracy differences among different sensors, sensor type weights are introduced. Where: the weight of the thermocouple sensor Weight of infrared sensors .
[0034] For the interpolated continuous temperature field The temperature gradient at each point is calculated using the second-order central difference method:
[0035] Finally, for each point Calculate the magnitude of the temperature gradient: .
[0036] Using the interpolation method described above, the system reconstructs discrete temperature sampling points into a continuous temperature field, enabling it to clearly capture the temperature gradient distribution within the reactor. This provides a high-precision spatial temperature distribution model for subsequent control decision modules, significantly improving the system's ability to perceive dynamic changes in the temperature field.
[0037] In the control decision module 103, the Quantum Annealed Fruit Fly Optimization Algorithm (QAFOA) is an optimization algorithm that combines the concepts of quantum annealing and fruit fly optimization, incorporating a dynamic weight fitness function. Based on the traditional fruit fly optimization algorithm, it utilizes the characteristics of quantum annealing to enhance the algorithm's ability to escape local optima, thereby better finding the global optimum. This algorithm uses characteristic parameters... and To obtain input, control commands are generated through the following steps: Multiple fruit fly individuals are randomly generated within a preset control parameter space, with each fruit fly individual corresponding to a control parameter vector. ,in, For PID control parameters, The quantum annealing coefficient; With characteristic parameters and As input, the control parameter vectors of each fruit fly individual are evaluated through a fitness function, and the current optimal vector is selected. The control parameter vector of individual fruit flies is adjusted using the quantum state update formula, while the annealing temperature is updated simultaneously. Substitute the updated control parameter vector back into the fitness function to calculate and determine whether the iteration termination condition is met. If it is met, stop the optimization and output the optimal control parameter vector; otherwise, continue the iteration. The optimal control parameter vector is substituted into the control law calculation to generate control commands for heating power and cooling flow rate, which are then sent to the execution module 104.
[0038] In one specific embodiment, in Within the sample, 50 individual fruit flies were randomly generated using the Latin hypercube sampling method, with each individual fruit fly corresponding to a set of control parameter vectors. Latin hypercube sampling is a stratified sampling technique that ensures each variable interval has a representative sample when generating random samples, thus providing a more uniform coverage of the parameter space compared to simple random sampling. For example, in In the parameter space, Latin hypercube sampling ensures that the control parameters of the generated fruit fly individuals are distributed across a range of values, rather than being simply randomly concentrated in certain regions. This allows the algorithm to explore the parameter space more comprehensively and find the optimal control parameters.
[0039] With characteristic parameters and As input, the fitness function is used to evaluate the quality of each parameter vector:
[0040] in: Temperature tracking error: ; Temperature change rate constraint: ; Temperature gradient equalization: ; These are dynamic weighting coefficients, and they satisfy... .
[0041] Thermal depolymerization reactions typically consist of three main stages: initiation, stabilization, and termination, each with different temperature control requirements. To enable the algorithm to better adapt to these variations, the weighting coefficients are adjusted. The allocation will be dynamically adjusted, as shown in the table below:
[0042] During the start-up phase, the core objective is to quickly raise the reactor temperature to the set temperature. (Higher...) The weighting of temperature tracking prioritizes the algorithm, allowing for a certain degree of non-uniformity in temperature change rate and gradient to accelerate the heating rate. During the stabilization phase, maintaining temperature stability and ensuring uniform temperature distribution within the reactor are crucial for efficient thermal depolymerization. Therefore, the weighting of temperature tracking is appropriately reduced, while the weighting of temperature gradient uniformity is increased, and the temperature change rate is moderately constrained. In the final phase, the main task is to smoothly reduce the temperature to a safe range, avoiding temperature overshoot that could impact the equipment and subsequent operations. At this stage, the weighting of temperature tracking is increased, while the temperature change rate and gradient are reasonably controlled.
[0043] Taking the final stage as an example, within the reaction period of 120–150 minutes, the system needs to steadily reduce the temperature from 550℃ to 200℃ while avoiding overshoot. Its fitness function is: Simultaneously set the initial temperature. Cooling coefficient Its temperature update formula is: This provides a basis for dynamically adjusting the acceptance probability of quantum perturbations.
[0044] For each individual fruit fly Its quantum state update formula is: in, For individual fruit flies Updated control parameter vector, This is the control parameter vector corresponding to the fruit fly individual with the best fitness in the current iteration. For individual fruit flies The current control parameter vector, This represents the current iteration number.
[0045] For quantum perturbation coefficients, The distribution is a standard normal distribution. By introducing a standard normal distributed random vector to simulate the quantum tunneling effect, the algorithm is helped to escape local optima. In this embodiment, Take 0.2.
[0046] Through 50 iterations of optimization, the algorithm continuously optimizes the control parameter vector, and the parameter data is recorded every 10 iterations as follows:
[0047] In each iteration, the algorithm calculates and executes control commands based on the current parameter vector, collects actual temperature data, inputs it into the fitness function for evaluation, and selects the optimal individual. This serves as the benchmark for this iteration. Annealing temperature. This mechanism controls the probability of the algorithm accepting suboptimal solutions. In the early iterations (T=100), even if the fitness of a new solution is slightly lower than the current best, the algorithm still accepts it with a high probability, encouraging exploration of new parameter spaces. As the temperature decreases, such as in the later iterations (T=8.21), the algorithm gradually becomes more conservative, only accepting solutions that significantly improve fitness. This mechanism effectively balances global search and local exploitation, avoiding the "premature convergence" problem common in traditional optimization algorithms.
[0048] After 50 iterations, the quantum step size coefficient The value gradually decreases from 1.5 to 0.26 to ensure that the algorithm performs a fine search in the later stages of convergence; Increasing the value from 0.08 to 0.18 rapidly shrinks the search range, focusing on the region near the optimal solution. The algorithm converges to the optimal parameter vector. Substitute it into the PID control law:
[0049] Generate control commands: Heating power:
[0050] Cooling flow rate:
[0051] Specifically, the execution module 104 includes a heating submodule and a cooling submodule. The heating submodule includes at least one of an electric heating wire, a microwave heating device, or a resistance heating element. The cooling submodule includes at least one of a circulating cooling water system, a refrigerant spray device, or an air cooler.
[0052] The execution module adjusts the intelligent temperature control system for the pyrolysis polymerization reaction in real time according to the generated control commands, transmitting the control commands for heating power and cooling flow rate to the corresponding heating and cooling equipment. During actual operation, the system's temperature feedback is continuously monitored, and the data is recorded as follows:
[0053] During the cooling process, the system dynamically adjusts heating and cooling resources based on real-time temperature errors: when the temperature is higher than the target value, the cooling system is activated and the flow rate is adjusted according to the error derivative; when the temperature approaches the target value, the cooling flow rate is gradually reduced to avoid overshoot. For example, at 130 minutes, with a temperature error of +1.8℃, the system activates the cooling system, outputting a cooling flow rate of 2.3 m³ / h, allowing the temperature to steadily approach the target value.
[0054] After 50 iterations, the algorithm exhibits good convergence characteristics. For example, the fitness function monotonically decreases from the initial 18.7 to 3.6, and the convergence curve conforms to the exponential decay model. The PID parameters change by less than 5% after 30 iterations, and the quantum coefficient tends to stabilize after 40 iterations.
[0055] To more intuitively demonstrate the advantages of the quantum annealing fruit fly optimization algorithm based on dynamic weight fitness function, it is compared with the traditional PID control method on several key indicators. The results are shown in the table below:
[0056] Compared with traditional PID control methods, the quantum annealing fruit fly optimization algorithm based on dynamic weight fitness function has achieved significant improvements in several key indicators. Temperature control accuracy has been improved by 61.9%, temperature uniformity by 58.6%, and energy efficiency by 20.1%. These improvements not only help to improve the product quality and production efficiency of the pyrolysis polymerization reaction, but also reduce production costs and energy consumption, demonstrating significant engineering application value and economic benefits.
[0057] In the above, the termination condition of the optimization algorithm is that the fitness change after K consecutive iterations is less than a threshold. ,Right now: This termination condition prevents the algorithm from continuing to iterate due to minor fluctuations when it is close to the optimal solution. It ensures that the system outputs control parameters in a timely manner after reaching the preset accuracy requirements, avoids control lag caused by continuous iteration, and ensures that the reactor temperature decreases steadily within a safe range.
[0058] Based on the same inventive concept, this application also provides an intelligent temperature control method for the pyropolymerization reaction to implement the intelligent temperature control system for the pyropolymerization reaction described above. The solution provided by this method is similar to the implementation scheme described in the above system. Therefore, the specific limitations in one or more embodiments of the intelligent temperature control method for the pyropolymerization reaction provided below can be found in the limitations of the intelligent temperature control system for the pyropolymerization reaction described above, and will not be repeated here.
[0059] In one exemplary embodiment, such as Figure 2 As shown, a smart temperature control method for a pyrolysis polymerization reaction is provided, comprising the following steps: Step S201: The temperature sequence of discrete spatial points inside the reactor is collected in real time by multiple temperature sensors deployed on the three-dimensional grid nodes on the inner wall of the reactor. Step S202: Extract spatiotemporal feature parameters from the temperature sequence to generate a parameter set containing the temperature change rate and temperature gradient magnitude. Step S203: Based on the quantum annealing fruit fly optimization algorithm, the control command is generated by optimizing the control parameter vector, with the parameter set as input. Step S204: Output heating power and cooling flow rate according to control commands to achieve dynamic adjustment of reactor temperature.
[0060] This intelligent temperature control method for pyrolysis polymerization employs a three-dimensional grid node deployment of multiple types of temperature sensors to construct a real-time temperature field acquisition network with full coverage. This overcomes the limitations of traditional single-point temperature measurement, enabling dynamic spatiotemporal capture of temperature within the reactor and laying a data foundation for precise control. Secondly, by extracting spatiotemporal feature parameters, it simultaneously mines the temperature change rate and spatiotemporal gradient distribution characteristics, giving the system a deep perception capability for dynamic temperature changes and spatial non-uniformity, effectively addressing the nonlinearity and complexity of pyrolysis polymerization. Thirdly, it introduces a quantum annealing fruit fly optimization algorithm, fusing multi-objective optimization with a dynamic weight fitness function. Combined with quantum tunneling and annealing mechanisms, this endows the system with the ability to escape local optima and adaptive parameter optimization characteristics, overcoming the shortcomings of fixed parameters in traditional PID control. Finally, based on the optimized parameters, precise control commands are generated to drive the heating and cooling modules to dynamically adjust in tandem, achieving adaptive temperature control throughout the entire process from heating to stabilization to cooling. This eliminates the need for manual intervention to handle time-varying characteristics during the reaction process, significantly improving temperature control accuracy and system robustness.
[0061] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 3 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores intelligent temperature control data for the pyrolysis reaction. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements an intelligent temperature control system and method for the pyrolysis reaction.
[0062] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0063] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.
[0064] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.
[0065] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.
[0066] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.
[0067] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).
[0068] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.
[0069] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0070] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.
Claims
1. An intelligent temperature control system for a thermal depolymerization reaction, characterized in that, include: The temperature acquisition module is configured to be deployed on three-dimensional mesh nodes on the inner wall of the reactor. One temperature sensor is used to collect the temperature sequence of discrete spatial points inside the reactor in real time. The data processing module is configured to extract feature parameters from the collected temperature data and generate a parameter set containing time-domain and spatial-domain features. The control decision module is configured to use the quantum annealing fruit fly optimization algorithm as input to generate control commands by optimizing the control parameter vector. The execution module is configured to output heating power and cooling flow rate according to control commands, thereby achieving dynamic adjustment of the reactor temperature.
2. The intelligent temperature control system for the pyrolysis polymerization reaction according to claim 1, characterized in that, The temperature sensors of the temperature acquisition module are arranged in a hexahedral grid on the inner wall of the reactor, with the spacing between adjacent sensors being... ,in Let be the side length of the reactor's inner cavity.
3. The intelligent temperature control system for the pyrolysis polymerization reaction according to claim 2, characterized in that, The temperature sensor includes at least one of a thermocouple, an infrared temperature sensor, or a fiber Bragg grating sensor.
4. The intelligent temperature control system for the pyrolysis polymerization reaction according to claim 1, characterized in that, The spatial domain features extracted by the data processing module include the temperature change rate: in, For the first A temperature sensor in Temperature collected at all times The sampling time interval; The spatial domain features extracted by the data processing module include the temperature gradient magnitude: 。 5. The intelligent temperature control system for the pyrolysis polymerization reaction according to claim 4, characterized in that, In the control decision module, the quantum annealing fruit fly optimization algorithm uses feature parameters and To obtain input, control commands are generated through the following steps: Multiple fruit fly individuals are randomly generated within a preset control parameter space, and each fruit fly individual corresponds to a control parameter vector. With characteristic parameters and As input, the control parameter vectors of each fruit fly individual are evaluated through a fitness function, and the current optimal vector is selected. The control parameter vector of individual fruit flies is adjusted using the quantum state update formula, while the annealing temperature is updated simultaneously. Substitute the updated control parameter vector back into the fitness function to calculate and determine whether the iteration termination condition is met. If it is met, stop the optimization and output the optimal control parameter vector; otherwise, continue the iteration. The optimal control parameter vector is substituted into the control law calculation to generate control commands for heating power and cooling flow rate, which are then sent to the execution module.
6. The intelligent temperature control system for the pyrolysis polymerization reaction according to claim 5, characterized in that, The fitness function is: in, For temperature tracking error, Constrained by the rate of temperature change, To equalize the temperature gradient; These are dynamic weighting coefficients, and they satisfy... .
7. The intelligent temperature control system for the pyrolysis polymerization reaction according to claim 6, characterized in that, For each individual fruit fly The quantum state update formula is: in, For individual fruit flies Updated control parameter vector, This is the control parameter vector corresponding to the fruit fly individual with the best fitness in the current iteration. For individual fruit flies The current control parameter vector, This represents the current iteration number; For quantum perturbation coefficients, It follows a standard normal distribution.
8. The intelligent temperature control system for the pyrolysis polymerization reaction according to claim 7, characterized in that, The termination condition of the optimization algorithm is that the fitness change after K consecutive iterations is less than a threshold. ,Right now: 。 9. The intelligent temperature control system for the pyrolysis polymerization reaction according to claim 1, characterized in that, The execution module includes a heating submodule and a cooling submodule, wherein: The heating submodule includes at least one of an electric heating wire, a microwave heating device, or a resistance heating element. The cooling submodule includes at least one of a circulating cooling water system, a refrigerant spray device, or an air cooler.
10. A smart temperature control method for a pyrolysis polymerization reaction, characterized in that, Includes the following steps: The temperature sequence of discrete spatial points inside the reactor is collected in real time by deploying multiple temperature sensors on three-dimensional grid nodes on the inner wall of the reactor. Spatiotemporal feature parameters are extracted from the temperature sequence to generate a parameter set containing the temperature change rate and temperature gradient magnitude. Based on the quantum annealing fruit fly optimization algorithm, the parameter set is used as input to generate control commands by optimizing the control parameter vector. The control command outputs heating power and cooling flow rate to achieve dynamic adjustment of the reactor temperature.