Intelligent control self-adaptive carbonization method and system

Abstract

The embodiment of the invention provides an intelligent-control self-adaptive carbonization method and system. The intelligent-control self-adaptive carbonization method comprises the steps that the water content of a material, the proportion of functional groups of a carbonization product and oxygen concentration data are collected in real time through a multi-parameter sensing network; analyzing the material moisture content, the carbonization product functional group proportion and the oxygen concentration data based on a long short-term memory neural network model, and establishing a mapping relation; dynamically adjusting the dip angle of the drying pipe and the flue gas flow rate according to the mapping relation; the modular units are spliced and / or replaced through standardized interfaces, and the distributed control system automatically identifies newly-built modules to complete system expansion. According to the embodiment of the invention, the problem of one-sidedness of single-point sensing data is solved, and the comprehensiveness and real-time performance of a process regulation and control basis are ensured; meanwhile, a multi-dimensional data basis is provided for intelligent analysis, control deviation caused by distortion of a single parameter is avoided, and the production line transformation period and shutdown loss are greatly shortened.

Description

Technical Field

[0001] This application belongs to the technical field of carbonization production equipment, specifically involving a multi-dimensional dynamic collaborative skill evaluation method and system. Background Technology

[0002] Carbonization technology is widely used in biomass treatment, solid waste resource utilization, and chemical raw material preparation. Existing carbonization equipment generally suffers from two major technical bottlenecks: Firstly, the control strategy relies on human experience. When material properties such as moisture content fluctuate, it is impossible to dynamically adjust process parameters through real-time data feedback, resulting in unstable quality of carbonized products, such as poor carbonization uniformity and large fluctuations in specific surface area. Secondly, the equipment adopts a fixed integrated structure, and there is a lack of standardized interfaces between the functional units, making it difficult to adapt to different scales of production capacity or process route adjustments. Moreover, maintenance requires complete shutdown and disassembly, resulting in high maintenance costs and long capacity expansion cycles.

[0003] Currently, although a few devices in existing technologies have attempted to introduce sensors for parameter monitoring, they only remain at the level of displaying a single parameter and have not formed a closed-loop control system that integrates multiple parameters. In terms of device structure, modular design is mostly limited to simple component replacement and lacks a systematic distributed control architecture, making it impossible to achieve true "plug and play" expansion.

[0004] Therefore, there is an urgent need for an intelligent carbonization control solution that can solve the above-mentioned technical problems. Summary of the Invention

[0005] This application proposes an intelligent control-based adaptive carbonization method and system to address the shortcomings of the prior art.

[0006] According to a first aspect of the embodiments of this application, an intelligent control adaptive carbonization method is provided, comprising: Data on material moisture content, percentage of functional groups in carbonization products, and oxygen concentration are collected in real time using a multi-parameter sensor network. The data on the moisture content of the material, the proportion of functional groups in the carbonization products, and the oxygen concentration were analyzed based on a long short-term memory neural network model, and a mapping relationship was established. The drying tube tilt angle and flue gas velocity are dynamically adjusted according to the mapping relationship. Modular units are assembled and / or replaced through standardized interfaces, and the newly created modules are automatically identified by the distributed control system to complete system expansion.

[0007] In some embodiments, the real-time acquisition of material moisture content, the proportion of functional groups in carbonization products, and oxygen concentration data via a multi-parameter sensor network includes: Real-time monitoring of material particle moisture content using a microwave resonant sensor; The proportions of C=O and CH bonds in the carbonization products were detected online using a near-infrared spectroscopy analyzer. The oxygen concentration and flue gas velocity are monitored by linking a laser oxygen sensor with a high-temperature flue gas flow meter.

[0008] In some embodiments, dynamically adjusting the drying tube tilt angle and flue gas velocity according to the mapping relationship includes: When the particle size of the crushed material exceeds the particle size threshold, the saw blade roller is triggered to perform frequency conversion speed regulation and the screen aperture is adjusted to ensure that the particle size meets the preset requirements.

[0009] In some embodiments, the particle size threshold is 5 mm, the frequency conversion speed regulation range is 50-200 Hz, and the screen aperture adjustment range is 1-3 mm.

[0010] In some embodiments, the modular unit includes: The sawtooth roller is equipped with a quick-release blade assembly for the crushing unit, which supports dual-mode switching for dry and wet materials and is suitable for materials with a moisture content of 10-50%. The segmented drying tubes, each 2m long, support free splicing layouts in either straight or spiral configurations. Plug-in and replaceable plate or finned heat exchangers to adapt to different heat source quality requirements.

[0011] In some embodiments, the analysis of the material moisture content, the proportion of functional groups in the carbonization products, and the oxygen concentration data based on the long short-term memory neural network model includes: Based on the real-time collected data on the material moisture content, functional group ratio, and oxygen concentration, the calorific value stability of the carbonization product is predicted. Based on the prediction results, the carbonization temperature curve and material residence time are optimized in reverse.

[0012] In some implementations, the step of splicing and / or replacing modular units through standardized interfaces, and having the distributed control system automatically identify the newly created modules to complete system expansion, includes: When production capacity is expanded, increase the number of segmented drying tubes; otherwise, maintain the current operating status. When the process is adjusted, the type of heat exchange module is replaced, and plug-and-play control is achieved by an independent programmable control substation connected to the industrial Ethernet; otherwise, the current operating state is maintained.

[0013] In some embodiments, the method further includes: When the oxygen concentration data exceeds the safety threshold, the inert gas protection mechanism is automatically triggered, and the control log is recorded in real time and a carbonization efficiency optimization report is generated; otherwise, the current operating state is maintained.

[0014] In some embodiments, the step of dynamically adjusting the drying tube inclination angle and flue gas velocity according to the mapping relationship further includes: The tilt angle adjustment range is calculated based on the rate of change of the moisture content of the material. The tilt angle of each section of the drying tube is independently controlled by a hydraulic actuator.

[0015] According to a second aspect of this application, an intelligently controlled adaptive carbonization system is provided, comprising: The data acquisition module is used to collect data on material moisture content, the proportion of functional groups in carbonization products, and oxygen concentration in real time through a multi-parameter sensor network. The data processing module is used to analyze the moisture content of the material, the proportion of functional groups of the carbonization products, and the oxygen concentration data based on a long short-term memory neural network model, and to establish a mapping relationship. The dynamic adjustment module is used to dynamically adjust the drying tube tilt angle and flue gas velocity according to the mapping relationship; System expansion modules are used to connect and / or replace modular units through standardized interfaces, and the distributed control system automatically identifies the newly created modules to complete system expansion.

[0016] The beneficial effects of the intelligent control adaptive carbonization method and system of the embodiments of this application include at least the following: This application's embodiments address the limitation of single-point sensor data by collaboratively monitoring three core parameters: moisture content, functional group ratio, and oxygen concentration, ensuring the comprehensiveness and real-time nature of process control. Simultaneously, it provides a multi-dimensional data foundation for intelligent analysis, avoiding control deviations caused by distortion from a single parameter. Utilizing the time-series modeling capabilities of long short-term memory neural networks for time-varying process data (such as moisture content fluctuations and functional group evolution trends), it accurately captures the nonlinear coupling relationship between carbonization temperature, residence time, and product performance. This overcomes the limitations of traditional static models, significantly improving the dynamic adaptability and predictive reliability of process optimization. By adjusting the tilt angle in conjunction with the flue gas velocity, the conveying rate and heat exchange efficiency of materials within the drying tube are precisely controlled, effectively solving the problem of unstable product calorific value. Real-time closed-loop optimization of process parameters is achieved, reducing manual intervention costs and minimizing energy waste caused by response lag. The plug-and-play design of modular units supports rapid reconfiguration and capacity expansion of crushing, drying, and heat exchange processes, addressing the pain point of fixed equipment being difficult to adapt to multiple process variations. The automatic identification mechanism of the distributed control system ensures seamless connection of control logic during expansion, significantly shortening the production line modification cycle and reducing downtime losses. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the intelligent control adaptive carbonization method according to an embodiment of this application. Figure 2 This is a flowchart illustrating a specific embodiment of the intelligent control adaptive carbonization method according to this application. Figure 3 This is a schematic diagram of the structure of the intelligent control adaptive carbonization system according to an embodiment of this application; Figure 4 This is a schematic diagram of a specific embodiment of the intelligent control adaptive carbonization system according to this application. Detailed Implementation

[0018] To enable those skilled in the art to better understand the technical solution of this application, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0019] The embodiments of this application will be described in further detail below with reference to the accompanying drawings and examples. The detailed description of the following embodiments and the accompanying drawings are used to illustrate the principles of this application by way of example, but should not be used to limit the scope of this application, that is, this application is not limited to the described embodiments.

[0020] This application provides an intelligently controlled adaptive carbonization method, which is executed by an intelligently controlled adaptive carbonization system. (See attached document.) Figure 1-2 As shown, the method includes the following steps 110-140.

[0021] Step 110: Collect data on material moisture content, percentage of functional groups in carbonized products, and oxygen concentration in real time through a multi-parameter sensor network.

[0022] In some implementations, the real-time acquisition of material moisture content, the proportion of functional groups in carbonized products, and oxygen concentration data via a multi-parameter sensor network includes: real-time monitoring of material particle moisture content using a microwave resonant sensor (e.g., with an accuracy of ±0.5%); online detection of the proportion of C=O and CH bonds in carbonized products using a near-infrared spectroscopy analyzer, and dynamic feedback to the control system; and monitoring of oxygen concentration and flue gas velocity using a laser oxygen sensor (e.g., with an accuracy of ±0.02%) linked to a high-temperature flue gas flow meter, thereby preventing dust explosions.

[0023] Step 120: Analyze the moisture content of the material, the proportion of functional groups in the carbonization product, and the oxygen concentration data based on the Long Short-Term Memory Neural Network (LSTM) model, and establish a mapping relationship.

[0024] This mapping relationship can be optimized using artificial intelligence (AI) to build a mapping model of carbonization temperature, residence time, and product performance.

[0025] In some implementations, the analysis of the material moisture content, the proportion of functional groups in the carbonized product, and the oxygen concentration data based on the long short-term memory neural network model includes: predicting the calorific value stability of the carbonized product based on the real-time collected data of the material moisture content, the proportion of functional groups, and the oxygen concentration; and optimizing the carbonization temperature curve and the material residence time based on the prediction results.

[0026] Step 130: Dynamically adjust the drying tube tilt angle and flue gas velocity according to the mapping relationship.

[0027] In some embodiments, the dynamic adjustment of the drying tube inclination angle and flue gas velocity according to the mapping relationship includes: when the particle size of the crushed material exceeds the particle size threshold, triggering the saw blade roller to perform frequency conversion speed regulation and adjusting the screen aperture to ensure that the particle size meets the preset requirements.

[0028] In some embodiments, the dynamic adjustment of the drying tube inclination angle and flue gas velocity based on the mapping relationship further includes: calculating the inclination angle adjustment range based on the rate of change of the material moisture content; and realizing independent control of the segmented inclination angle of the drying tube through a hydraulic actuator.

[0029] In one exemplary embodiment, the particle size threshold is 5 mm, the frequency conversion speed regulation range is 50-200 Hz, and the screen aperture adjustment range is 1-3 mm.

[0030] For example, the drying tube tilt angle, automatically adjusted according to the above embodiment, is adjustable from 0-15°, and the flue gas velocity is 0.5-2.5 m / s. Carbonization uniformity can be improved by more than 30%. When the particle size of the crushed material is detected to be >5 mm, the serrated roller frequency conversion speed regulation (50-200 Hz) is triggered, and the screen aperture (1-3 mm) is adjusted synchronously to ensure that the particle size of the crushed material meets the requirements.

[0031] This step in the embodiments of this application significantly improves the uniformity of carbonization.

[0032] Step 140: Modular units are spliced ​​and / or replaced through standardized interfaces, and the newly created modules are automatically identified by the distributed control system to complete the system expansion.

[0033] In some implementations, the modular units are spliced ​​and / or replaced through standardized interfaces, and the newly added modules are automatically identified by the distributed control system to complete system expansion. This includes: increasing the number of segmented drying tubes when production capacity is expanded, otherwise maintaining the current operating state; replacing the type of heat exchange module when the process is adjusted, and implementing plug-and-play control by an independent programmable control substation connected to an industrial Ethernet network, otherwise maintaining the current operating state.

[0034] In some embodiments, the modular unit includes: a crushing unit equipped with a quick-release blade assembly on a serrated cutter roller, which supports dual-mode switching for dry / wet materials and is adaptable to materials with a moisture content of 10-50%; a segmented drying tube, each segment being 2m long, supporting free splicing layouts in either an inline or spiral configuration; and pluggable and replaceable plate or finned heat exchangers to adapt to different heat source quality requirements.

[0035] In some implementations, the method further includes: when the oxygen concentration data exceeds a safety threshold, automatically triggering an inert gas protection mechanism and recording the control log and generating a carbonization efficiency optimization report in real time; otherwise, maintaining the current operating state.

[0036] For example, in a specific embodiment of biomass carbonization production, when biomass material with a moisture content of 30% enters the system, a microwave resonant sensor monitors the moisture content in real time, a near-infrared spectrometer detects the proportion of C=O and CH bonds in the carbonization products, and a laser oxygen sensor and a high-temperature flue gas flow meter monitor the oxygen concentration and flue gas velocity in real time. The control system, based on a long short-term memory neural network model, calculates the appropriate drying tube inclination angle as 8° and the flue gas velocity as 1.5 m / s, and automatically adjusts the drying tube and flue gas velocity to maintain uniformity of the biomass material during carbonization. During the crushing process, if the particle size after crushing is detected to be >5 mm, the saw blade frequency conversion speed is triggered to 120 Hz, and the mesh size is adjusted to 2 mm to ensure that the particle size of the crushed material meets the requirements of subsequent processes. When it is necessary to expand production capacity, the number of segmented drying tubes is increased, and the drying and carbonization units are expanded using a linear splicing method. The distributed control system automatically identifies the newly connected modules through an industrial Ethernet network, achieving rapid capacity expansion.

[0037] To illustrate further, in a specific embodiment of the solid waste treatment carbonization process, when treating solid waste with a moisture content of 15%, a multi-parameter sensor network collects data in real time. The control system adjusts the drying tube inclination angle to 5° and the flue gas velocity to 1.0 m / s based on the model. The crushing unit adopts a dry material mode, and the quick-release blade assembly is suitable for crushing materials with low moisture content. During the crushing process, the particle size is monitored in real time to ensure that the particle size is within a suitable range. When it is necessary to change the heat source, the plate heat exchanger of the heat exchange module is replaced with a finned heat exchanger, and the replacement is quickly completed through a standardized interface. The distributed control system reconfigures the parameters to adapt to the new heat source grade requirements.

[0038] This application's embodiments address the limitation of single-point sensor data by collaboratively monitoring three core parameters: moisture content, functional group ratio, and oxygen concentration, ensuring the comprehensiveness and real-time nature of process control. Simultaneously, it provides a multi-dimensional data foundation for intelligent analysis, avoiding control deviations caused by distortion from a single parameter. Utilizing the time-series modeling capabilities of long short-term memory neural networks for time-varying process data (such as moisture content fluctuations and functional group evolution trends), it accurately captures the nonlinear coupling relationship between carbonization temperature, residence time, and product performance. This overcomes the limitations of traditional static models, significantly improving the dynamic adaptability and predictive reliability of process optimization. By adjusting the tilt angle in conjunction with the flue gas velocity, the conveying rate and heat exchange efficiency of materials within the drying tube are precisely controlled, effectively solving the problem of unstable product calorific value. Real-time closed-loop optimization of process parameters is achieved, reducing manual intervention costs and minimizing energy waste caused by response lag. The plug-and-play design of modular units supports rapid reconfiguration and capacity expansion of crushing, drying, and heat exchange processes, addressing the pain point of fixed equipment being difficult to adapt to multiple process variations. The automatic identification mechanism of the distributed control system ensures seamless connection of control logic during expansion, significantly shortening the production line modification cycle and reducing downtime losses.

[0039] Reference Figure 3 As shown in the figure, this application discloses an intelligent control adaptive carbonization system, including: a data acquisition module 310, a data processing module 320, a dynamic adjustment module 330, and a system expansion module 340.

[0040] The data acquisition module 310 is used to collect data on material moisture content, the proportion of functional groups in carbonization products, and oxygen concentration in real time through a multi-parameter sensor network.

[0041] The data processing module 320 is used to analyze the moisture content of the material, the proportion of functional groups of the carbonization products, and the oxygen concentration data based on a long short-term memory neural network model, and to establish a mapping relationship.

[0042] The dynamic adjustment module 330 is used to dynamically adjust the tilt angle of the drying tube and the flue gas velocity according to the mapping relationship.

[0043] The system expansion module 340 is used to connect and / or replace modular units through standardized interfaces, and the newly created module is automatically identified by the distributed control system to complete the system expansion.

[0044] See attached document Figure 4As shown, in one exemplary embodiment, this application further includes a crushing unit, wherein the serrated blade roller of the crushing unit adopts a quick-release blade assembly, supporting dual-mode switching for dry / wet materials, and preferably, can adapt to a moisture content of 10-50%; a drying and carbonization unit, whose segmented drying tubes (each segment 2m long) can be freely spliced, supporting inline or spiral layouts; a heat exchange unit, whose plate or finned heat exchangers are pluggable and replaceable to adapt to different heat source quality requirements. A distributed control system, whose modules are equipped with independent programmable logic controller (PLC) substations, achieves "plug-and-play" expansion through industrial Ethernet, reducing capacity expansion time by 70%.

[0045] This application's embodiments, through the combination of multi-parameter sensor networks and AI optimization algorithms, achieve precise control of production process parameters, reducing the fluctuation rate of production process parameters to +2% and achieving a specific surface area stability of 98% for carbonized products, significantly improving product quality stability and realizing a high level of intelligence. Through a modular and scalable architecture, standardized interface design, and a distributed control system, equipment investment costs are reduced by 25%, maintenance efficiency is increased by 50%, and capacity expansion time is reduced by 70%, enabling rapid adaptation to different scales and process adjustments, significantly enhancing flexibility and scalability. Furthermore, by linking a laser oxygen sensor with a high-temperature flue gas flow meter, real-time monitoring of oxygen concentration effectively prevents safety accidents such as dust explosions, significantly improving safety.

[0046] This application also discloses an electronic device that integrates the intelligent control adaptive carbonization system described above, used to implement the intelligent control adaptive carbonization method described above. Its core hardware architecture adopts a modular power unit design, supporting the rapid splicing or replacement of functional modules (such as drying tubes, heat exchangers, and carbonization reaction chambers) through standardized interfaces (such as PressFit Pin or industrial Ethernet interfaces). This design utilizes a distributed control system to achieve automatic identification and parameter configuration of newly added modules, ensuring that the system can flexibly adjust its physical scale and topology according to different biomass raw materials or production capacity requirements, while maintaining unified control logic. At the intelligent control level, the device embeds a multi-parameter sensor network (real-time monitoring of material moisture content, functional group ratio of carbonization products, and oxygen concentration) and a long short-term memory neural network analysis model. The long short-term memory neural network analysis model accurately predicts the optimal combination of flue gas flow rate and drying tube tilt angle for the carbonization process by establishing a multi-parameter dynamic mapping relationship, and drives the actuator to achieve closed-loop regulation. For example, when abnormal fluctuations in the functional group ratio are detected, the system can instantly optimize the flue gas flow rate to stabilize the pyrolysis temperature, thereby improving product consistency.

[0047] This electronic device is typically used in industrial-grade carbonization scenarios, such as biomass energy production or waste resource recovery. Its adaptability is significantly reflected in two aspects: First, it ensures the current balance of multiple parallel SiC power modules under dynamic loads through current sharing optimization technology (such as mutual inductance elimination circuits or differential mode inductor design), guaranteeing the stability of high-power output; second, it combines high-efficiency power devices to reduce system losses and support high-frequency switching operation to adapt to real-time process adjustment requirements, ultimately achieving the goals of high energy efficiency and low emissions in the carbonization process.

[0048] It is understood that the above embodiments are merely exemplary implementations used to illustrate the principles of this application, and this application is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and substance of this application, and these modifications and improvements are also considered to be within the scope of protection of this application.

Claims

1. An intelligently controlled adaptive carbonization method, characterized in that, include: Data on material moisture content, percentage of functional groups in carbonization products, and oxygen concentration are collected in real time using a multi-parameter sensor network. The data on the moisture content of the material, the proportion of functional groups in the carbonization products, and the oxygen concentration were analyzed based on a long short-term memory neural network model, and a mapping relationship was established. The drying tube inclination angle and flue gas velocity are dynamically adjusted according to the mapping relationship. Modular units are assembled and / or replaced through standardized interfaces, and the newly created modules are automatically identified by the distributed control system to complete system expansion.

2. The method according to claim 1, characterized in that, The real-time acquisition of material moisture content, carbonization product functional group ratio, and oxygen concentration data through a multi-parameter sensor network includes: Real-time monitoring of material particle moisture content using a microwave resonant sensor; The proportions of C=O and CH bonds in the carbonization products were detected online using a near-infrared spectroscopy analyzer. The oxygen concentration and flue gas velocity are monitored by linking a laser oxygen sensor with a high-temperature flue gas flow meter.

3. The method according to claim 1, characterized in that, The dynamic adjustment of the drying tube tilt angle and flue gas velocity according to the mapping relationship includes: When the particle size of the crushed material exceeds the particle size threshold, the saw blade roller is triggered to perform frequency conversion speed regulation and the screen aperture is adjusted to ensure that the particle size meets the preset requirements.

4. The method according to claim 3, characterized in that, The particle size threshold is 5mm, the frequency conversion speed regulation range is 50-200Hz, and the screen aperture adjustment range is 1-3mm.

5. The method according to claim 1, characterized in that, The modular unit includes: The sawtooth roller is equipped with a quick-release blade assembly for the crushing unit, which supports dual-mode switching for dry and wet materials and is suitable for materials with a moisture content of 10-50%. The segmented drying tubes, each 2m long, support free splicing layouts in either straight or spiral configurations. Plug-in and replaceable plate or finned heat exchangers to adapt to different heat source quality requirements.

6. The method according to claim 1, characterized in that, The analysis of the material moisture content, the proportion of functional groups in the carbonization products, and the oxygen concentration data based on the long short-term memory neural network model includes: Based on the real-time collected data on the material moisture content, functional group ratio, and oxygen concentration, the calorific value stability of the carbonization product is predicted. Based on the prediction results, the carbonization temperature curve and material residence time are optimized in reverse.

7. The method according to claim 1, characterized in that, The process of splicing and / or replacing modular units through standardized interfaces, with the distributed control system automatically identifying the newly created modules to complete system expansion, includes: When production capacity is expanded, increase the number of segmented drying tubes; otherwise, maintain the current operating status. When the process is adjusted, the type of heat exchange module is replaced, and plug-and-play control is achieved by an independent programmable control substation connected to the industrial Ethernet; otherwise, the current operating state is maintained.

8. The method according to claim 1, characterized in that, The method further includes: When the oxygen concentration data exceeds the safety threshold, the inert gas protection mechanism is automatically triggered, and the control log is recorded in real time and a carbonization efficiency optimization report is generated; otherwise, the current operating state is maintained.

9. The method according to claim 1, characterized in that, The dynamic adjustment of the drying tube tilt angle and flue gas velocity based on the mapping relationship also includes: The tilt angle adjustment range is calculated based on the rate of change of the moisture content of the material. The tilt angle of each section of the drying tube is independently controlled by a hydraulic actuator.

10. An intelligently controlled adaptive carbonization system, characterized in that, include: The data acquisition module is used to collect data on material moisture content, the proportion of functional groups in carbonization products, and oxygen concentration in real time through a multi-parameter sensor network. The data processing module is used to analyze the moisture content of the material, the proportion of functional groups of the carbonization products, and the oxygen concentration data based on a long short-term memory neural network model, and to establish a mapping relationship. The dynamic adjustment module is used to dynamically adjust the drying tube tilt angle and flue gas velocity according to the mapping relationship; System expansion modules are used to connect and / or replace modular units through standardized interfaces, and the distributed control system automatically identifies the newly created modules to complete system expansion.

Images