An adaptive control system for solid waste management

Abstract

The application discloses a kind of self-adaptive control systems for solid waste treatment, it is related to solid waste treatment technical field.The system includes: three-parameter detection module, for the density, average particle size and moisture content of material are obtained in real time;Fuzzy adaptive controller is used to calculate target air speed according to the density, average particle size and moisture content;Servo execution module is used to adjust the real-time air speed of sorting cavity according to the target air speed;Closed-loop correction module is used to fine-tune the output parameters of the fuzzy adaptive controller according to the sorting effect.The application effectively improves the automation and intelligent level of the sorting process, enhances the adaptability to material composition fluctuation, reduces manual intervention, ensures the stability and reliability of sorting effect, and promotes the development of construction waste air separation technology in the direction of high efficiency, intelligence and precision.

Description

Technical Field

[0001] This invention relates to the field of solid waste treatment technology, specifically to an adaptive control system for solid waste treatment. Background Technology

[0002] In the wind-based sorting stage of construction waste recycling, the efficient separation of lightweight and heavy materials relies on precise wind speed control. However, traditional wind-based sorting technologies use fixed wind speed parameters, making it difficult to adapt to the dynamic changes in the composition of construction waste. Differences in material density, particle size, and moisture content significantly affect aerodynamic characteristics, often leading to over-sorting or under-sorting during the process. Existing control methods rely on manual experience to adjust the fan frequency, resulting in significant control delays and an inability to establish a real-time mapping relationship between material characteristics and wind speed, leading to unstable sorting efficiency and high costs associated with manual intervention.

[0003] The core deficiency of existing technology lies in the lack of adaptive adjustment capability to changes in material properties, and the failure to achieve dynamic matching of "real-time material properties - optimal wind speed". There is an urgent need for an adaptive control system that can detect key material parameters in real time and automatically adjust the control strategy to solve the problem of sorting accuracy under the coupling of multiple factors. Summary of the Invention

[0004] The purpose of this invention is to provide an adaptive control system for solid waste management, in order to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an adaptive control system for solid waste treatment, comprising:

[0006] The three-parameter detection module is used to obtain the density, average particle size and moisture content of materials in real time.

[0007] A fuzzy adaptive controller is used to calculate the target wind speed based on the density, average particle size, and moisture content.

[0008] The servo execution module is used to adjust the real-time wind speed of the sorting cavity according to the target wind speed;

[0009] The closed-loop correction module is used to fine-tune the output parameters of the fuzzy adaptive controller based on the sorting effect.

[0010] Preferably, the three-parameter detection module includes:

[0011] The particle size detection unit uses a laser diameter gauge to scan the particle size distribution of materials in real time and calculates the average particle size using a weighted average algorithm.

[0012]

[0013] In the formula, di For each particle size, m i This represents the mass percentage of materials with the corresponding particle size.

[0014] The moisture content detection unit uses a capacitive humidity sensor to directly detect the moisture content H of the material;

[0015] The density detection unit calculates the average density of the material using the pressure difference method through an array of pressure sensors arranged upstream of the sorting chamber.

[0016]

[0017] In the formula, k is the calibration coefficient, ΔP is the differential pressure detection value, and v0 is the initial calibration wind speed of the system.

[0018] Preferably, the calibration coefficient k of the density detection unit is obtained in the following ways:

[0019] A standard material of known density is added, and the pressure difference ΔP is measured. Then, according to the formula... Calculate, where ρ is the density of the standard material.

[0020] Preferably, the three-parameter detection module further includes a data processing unit for performing a 5-second moving average filtering process on the density data detected by the pressure sensor, thereby controlling the density detection error to within 5%.

[0021] Preferably, the fuzzy adaptive controller includes:

[0022] The input variable module defines the fuzzy universe of discourse for the material density ρ as [0.2, 1.2] g / cm³. 3 Average particle size d avg The fuzzy universe of discourse is [5, 100] mm, and the fuzzy universe of discourse for moisture content H is [5%, 30%].

[0023] The fuzzy rule base module employs Mamdani fuzzy inference and sets triangular membership functions to divide input variables into intervals. These membership functions include:

[0024] Density ρ: Low range (0.2~0.5g / cm³) 3 ), middle range (0.5~1.0g / cm) 3 High range (1.0~1.2g / cm) 3 );

[0025] Average particle size d avg Small interval (5-20mm), medium interval (20-50mm), large interval (50-100mm);

[0026] Moisture content H: Dry range (5%–15%), Medium range (15%–25%), Humid range (25%–30%);

[0027] The fuzzy rule base module contains 27 control rules in a 3×3×3 pattern, establishing a relationship between the input variable and the target wind speed v. set The mapping relationship.

[0028] Preferably, the fuzzy adaptive controller further includes a dynamic weight adjustment module, which is used to introduce a moisture content correction factor α = 1 + 0.01H to adjust the target wind speed v output by the fuzzy rule base. set Real-time compensation is performed to obtain the final target wind speed v. final =v set ·α, where H is the percentage value of the moisture content measurement.

[0029] Preferably, the servo execution module includes:

[0030] The servo fan uses a permanent magnet synchronous motor to drive a centrifugal fan and can perform wind speed regulation;

[0031] The guide plate is installed inside the sorting chamber.

[0032] Preferably, the closed-loop correction module includes:

[0033] The sorting effect detection unit is equipped with an infrared through-beam photoelectric sensor array located downstream of the sorting cavity. It calculates the entrainment rate of light materials by counting the number of times heavy particles penetrate the material.

[0034] The parameter fine-tuning unit adjusts the target wind speed v corresponding to the current operating condition when the entrainment rate E > 5%. set Based on this, the target wind speed is adjusted incrementally or incrementally in steps of 0.5 m / s, with a maximum of 3 adjustments before triggering a manual calibration prompt.

[0035] Preferably, the adjustment direction of the parameter fine-tuning unit is determined according to the material moisture content condition: when the condition is humid (i.e., moisture content H > 25%), the target wind speed is increased; when the condition is dry (i.e., moisture content H < 15%), the target wind speed is decreased.

[0036] Preferably, the fuzzy adaptive controller is implemented using an industrial computer or PLC program, and its working steps are as follows:

[0037] Within 50cm of the material entering the separator, the three-parameter detection module simultaneously collects the density ρ and average particle size d. avg Moisture content α;

[0038] The fuzzy adaptive controller matches a fuzzy rule base based on the membership degrees of the three parameters and obtains the initial target wind speed v by defuzzifying using the centroid method. set The final target wind speed v is then calculated using a moisture content correction factor α. final ;

[0039] The servo execution module adjusts the airflow speed in the sorting chamber to v within 1 second. final And the guide vanes ensure uniform wind speed;

[0040] The entrainment rate E is detected every 10 seconds. If E > 5% for two consecutive times, parameter fine-tuning is initiated; otherwise, the current control parameters are maintained.

[0041] Compared with the prior art, the beneficial effects of the present invention are:

[0042] The three-parameter detection module accurately acquires material characteristics, and the data processing unit ensures data reliability. The fuzzy adaptive controller builds a rule base based on multiple parameters and achieves precise control through dynamic weight adjustment. The servo execution module ensures stable wind speed adjustment, and the closed-loop correction module fine-tunes parameters in a timely manner based on the sorting effect.

[0043] It achieves full-process adaptive management from material characteristic detection to precise wind speed control and sorting effect optimization, solving the problems of low sorting efficiency and strong reliance on manual labor under traditional fixed wind speed control. It effectively improves the automation and intelligence level of the construction waste wind sorting process, enhances the system's adaptability to material composition fluctuations, and ensures stable and reliable sorting results. Attached Figure Description

[0044] Figure 1 A schematic diagram of the structure of an adaptive control system for solid waste treatment provided in an embodiment of the present invention;

[0045] Figure 2 This is a diagram illustrating the working steps of a fuzzy adaptive controller in an adaptive control system for solid waste management, provided as an embodiment of the present invention. Detailed Implementation

[0046] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0047] Please see Figure 1 This invention provides an adaptive control system for solid waste treatment, the system being applied in the solid waste wind separation stage, comprising:

[0048] The three-parameter detection module 11 is used to acquire the density, average particle size and moisture content of the material in real time.

[0049] A fuzzy adaptive controller 12 is used to calculate the target wind speed based on the density, average particle size and moisture content;

[0050] Servo execution module 13 is used to adjust the real-time wind speed of the sorting cavity according to the target wind speed;

[0051] The closed-loop correction module 14 is used to fine-tune the output parameters of the fuzzy adaptive controller 12 according to the sorting effect.

[0052] In an optional embodiment, the three-parameter detection module 11 includes:

[0053] The particle size detection unit uses a high-precision laser diameter gauge to construct a three-dimensional scanning matrix. It employs multi-beam cross-scanning technology to perform real-time dynamic monitoring of the material. The system automatically collects particle size data from no fewer than 1000 detection points and calculates the average particle size using an adaptive weighted average algorithm.

[0054]

[0055] In the formula, d i The measured values ​​for various particle sizes cover multi-dimensional data such as the major diameter, minor diameter, and equivalent diameter of the material particles, in m. i The mass percentage of materials corresponding to the particle size is generated synchronously by the online weighing system and the particle size detection data.

[0056] The moisture content detection unit is equipped with an industrial-grade capacitive humidity sensor and employs a four-electrode method to eliminate edge effect interference, enabling rapid and accurate detection of the material's moisture content (H). The sensor features automatic temperature compensation, with a built-in Pt100 temperature sensor monitoring the ambient temperature in real time. A compensation algorithm corrects for the influence of temperature on the detection results, ensuring a detection accuracy of ±0.5%.

[0057] The density detection unit consists of six sets of high-precision pressure sensors arranged in an array upstream of the sorting chamber. A differential pressure detection model is constructed using Bernoulli's principle. The system updates the calibration coefficient k in real time through a dynamic calibration program, optimizes the calculation model using a Reynolds number correction algorithm, and finally calculates the average density of the material using the differential pressure method.

[0058]

[0059] In the formula, k is the calibration coefficient, ΔP is the differential pressure detection value, which is obtained through differential calculation of the pressure sensor array, and v0 is the initial calibration wind speed of the system, which is calibrated in multiple directions using a hot-wire anemometer to ensure the stability and reliability of the detection results.

[0060] In an optional embodiment, the density detection unit also has a fault self-checking function. It monitors the output signal of the pressure sensor array in real time through a built-in diagnostic program. When any sensor data deviation exceeds the threshold, the system automatically marks the faulty sensor and enables redundant sensors for data compensation to ensure the continuity and accuracy of density detection.

[0061] In an optional embodiment, the calibration coefficient k of the density detection unit is obtained in the following ways:

[0062] A standard material of known density is added, and the pressure difference ΔP is measured. Then, according to the formula... Calculate, where ρ is the density of the standard material.

[0063] Specifically, the calibration coefficient k of the density detection unit is obtained through the following standardization process:

[0064] Preparation phase: Select at least three sets of standard materials with known density ρ. The standard materials must have stable physicochemical properties, and their density values ​​must be calibrated and certified by a nationally recognized metrology institution.

[0065] Measurement operation: The standard materials are put into the detection device in sequence. After the material reaches a stable flow rate v0 in the pipeline, the corresponding differential pressure sensor measurement value ΔP is recorded. Each standard material is measured three times and the average value is taken to reduce random error.

[0066] Coefficient calculation: Calculation formula derived from Bernoulli's equation The calculation is performed, where v0 is a pre-set constant flow velocity parameter, and the weighted average of multiple calculation results is taken as the final calibration coefficient k.

[0067] Verification and correction: Use the newly obtained k value to test another set of verification materials with known density, compare the theoretical calculation value with the actual measurement value, and repeat the above process to recalibrate if the error exceeds ±2%.

[0068] In an optional embodiment, the three-parameter detection module 11 further includes a data processing unit for performing a 5-second moving average filtering process on the density data detected by the pressure sensor to control the density detection error within 5%.

[0069] Specifically, the data processing unit continuously collects and dynamically updates real-time detection data from the pressure sensor within a 5-second time window. By performing an arithmetic average of the data within the window, it effectively eliminates data fluctuations caused by environmental interference, sensor noise, and other factors. After this processing, the density detection error can be precisely controlled within 5%, significantly improving the stability and reliability of the detection data and ensuring that the density detection results can truly and accurately reflect the actual working conditions.

[0070] In an optional embodiment, the fuzzy adaptive controller 12 includes:

[0071] The input variable module defines the fuzzy universe of discourse for the material density ρ as [0.2, 1.2] g / cm³. 3 This domain covers a common density range from lightweight to relatively heavy materials; average particle size d avg The fuzzy domain of the controller is [5, 100] mm, which is suitable for particle size characteristics ranging from fine particles to larger lumps; the fuzzy domain of the moisture content H is [5%, 30%], covering the moisture state of materials from dry, moderate to wet. The setting of each domain is based on the common distribution of material characteristics in actual engineering, ensuring the universality and effectiveness of the controller input variables;

[0072] The fuzzy rule base module employs Mamdani fuzzy inference and sets triangular membership functions to divide input variables into intervals. These membership functions include:

[0073] Density ρ:

[0074] Low range (0.2~0.5g / cm) 3 It is suitable for materials with low density, such as foam and lightweight plastics.

[0075] The middle range (0.5~1.0g / cm) 3 It covers most conventional solid particulate materials;

[0076] High range (1.0~1.2g / cm) 3 This corresponds to heavier materials such as metal scraps and high-density ores.

[0077] Average particle size d avg :

[0078] Small intervals (5-20mm) are suitable for fine sand, small pellet feed, etc.

[0079] The medium range (20-50mm) is commonly found in crushed building aggregates and medium-sized parts;

[0080] Large range (50-100mm), suitable for large ore blocks and larger industrial raw materials;

[0081] Moisture content H:

[0082] Drying range (5%–15%) corresponds to materials in an air-dried state or those that have undergone drying treatment;

[0083] The medium range (15%–25%) represents conventional materials with a certain level of humidity under natural conditions;

[0084] Moisture range (25%–30%), suitable for materials that have just been washed or stored in high humidity environments;

[0085] The fuzzy rule base module, based on the intrinsic relationship between material properties and target wind speed, and summarized from historical experimental data and engineering experience, contains 27 control rules in a 3×3×3 structure. These rules establish the relationship between input variables (material density, average particle size, moisture content) and target wind speed v. set The precise mapping relationship ensures that the system can output a reasonable target wind speed under different material conditions, achieving efficient and stable operation.

[0086] In an optional embodiment, the fuzzy adaptive controller 12 further includes a dynamic weight adjustment module. This module introduces a moisture content correction factor α based on the significant influence of moisture content on target wind speed in actual engineering. The formula for α is α = 1 + 0.01H, where H represents the moisture content detection value (presented as a percentage) acquired in real-time by a high-precision sensor and processed by signal processing. This correction factor can adjust the target wind speed v output by the fuzzy rule base according to the dynamic changes in moisture content. set Perform real-time compensation;

[0087] The specific compensation mechanism is as follows: the correction factor α is compared with the initial target wind speed v. set Perform multiplication, i.e., v final =v set ·α, from which the final target wind speed v after considering the influence of water content is obtained. final This effectively improves the control accuracy and stability of the system under different humidity conditions.

[0088] In an optional embodiment, the servo execution module 13 includes:

[0089] The servo fan uses a permanent magnet synchronous motor to drive a centrifugal fan and can perform wind speed regulation;

[0090] The guide plate is installed inside the sorting chamber.

[0091] Specifically, the servo fan uses a high-performance permanent magnet synchronous motor as the drive core, combined with a high-efficiency centrifugal fan structure to build a closed-loop control system. Through advanced vector control algorithms, it can achieve precise control of the fan speed, with a speed control accuracy of ±0.5%. It can complete the wind speed adjustment in an extremely short response time of ≤1 second, ensuring the timeliness and stability of the wind speed output during the sorting process.

[0092] The baffle consists of multiple streamlined baffles, precisely positioned in key locations within the sorting chamber. Through a unique baffle surface design and array layout, combined with CFD (Computational Fluid Dynamics) simulation optimization, it effectively guides the airflow to distribute evenly, ensuring that the wind speed uniformity deviation of the chamber cross-section is controlled within ≤±0.3m / s, providing a stable airflow environment for precise material sorting.

[0093] In an optional embodiment, the closed-loop correction module 14 includes:

[0094] The sorting effect detection unit precisely deploys an infrared through-beam photoelectric sensor array 1m downstream of the sorting chamber. This array consists of multiple sets of through-beam photoelectric sensors arranged in a matrix, enabling real-time monitoring of the movement trajectory of particles in the material flow. By counting the number of times heavy particles penetrate the infrared light curtain and combining this with the total number of light materials, the system calculates the result according to the formula... Accurately calculate the entrainment rate of lightweight materials to provide quantitative evaluation data for the system's sorting effect;

[0095] The parameter fine-tuning unit sets the entrainment rate threshold to 5% as the automatic adjustment trigger condition. When the entrainment rate E > 5%, the target wind speed v corresponding to the current operating condition is used. set Based on this, the wind speed adaptive adjustment mechanism is activated, and the target wind speed is adjusted incrementally or incrementally in steps of 0.5 m / s. After a maximum of 3 adjustments, a manual calibration prompt is triggered.

[0096] If the entrainment rate still does not drop below the threshold after three automatic adjustments, a manual calibration prompt will be triggered immediately. At the same time, the current equipment operating parameters will be locked to prevent over-adjustment, and a detailed calibration suggestion report containing current operating data and historical adjustment records will be pushed to the operator.

[0097] In an optional embodiment, the adjustment direction of the parameter fine-tuning unit is determined according to the material moisture content condition: when the condition is humid (i.e., moisture content H > 25%), the target wind speed is increased; when the condition is dry (i.e., moisture content H < 15%), the target wind speed is decreased.

[0098] Specifically, the adjustment direction of the parameter fine-tuning unit includes:

[0099] In humid conditions (moisture content H>25%): activate the positive compensation mechanism, and simultaneously start the auxiliary drying components with the target wind speed increasing in a gradient of 0.3 to 0.5 m / s per hour to ensure that the material is dehydrated quickly in a high humidity environment;

[0100] Drying condition (moisture content H<15%): Trigger reverse adjustment program, reduce target wind speed by 0.2-0.4 m / s per batch, and automatically shut down heating device to prevent material from losing quality due to over-drying;

[0101] Critical operating condition (moisture content 15% ≤ H ≤ 25%): Maintain the current wind speed parameters, start the real-time monitoring module, collect moisture content data at a frequency of 3 times per minute, and automatically switch to the corresponding operating condition adjustment mode when the detection value exceeds the threshold range for 3 consecutive times.

[0102] In this embodiment, the material characteristics are accurately obtained by the three-parameter detection module 11, and the data processing unit ensures the reliability of the data; the fuzzy adaptive controller 12 builds a rule base based on multiple parameters and achieves precise control through dynamic weight adjustment; the servo execution module 13 ensures stable wind speed adjustment, and the closed-loop correction module 14 fine-tunes the parameters in a timely manner according to the sorting effect.

[0103] It achieves full-process adaptive management from material characteristic detection to precise wind speed control and sorting effect optimization, solving the problems of low sorting efficiency and strong reliance on manual labor under traditional fixed wind speed control. It effectively improves the automation and intelligence level of the construction waste wind sorting process, enhances the system's adaptability to material composition fluctuations, and ensures stable and reliable sorting results.

[0104] Based on the above embodiments, such as Figure 2 As shown, the present invention also provides the working steps of a fuzzy adaptive controller 12 in an adaptive control system for solid waste treatment. The working steps of the fuzzy adaptive controller 12 are implemented by an industrial computer or PLC program, and the working steps include:

[0105] Step S1: 50cm before the material enters the separator, the three-parameter detection module 11 simultaneously collects the density ρ and average particle size d. avg Moisture content α;

[0106] Specifically, step S1 is the multi-parameter real-time acquisition stage. Within a preset trigger zone 50cm before the material enters the sorter, the three-parameter detection module 11 initiates a synchronous acquisition program. The density detection unit uses the gamma-ray transmission method, achieving ±0.05g / cm³. 3 High-precision measurement; average particle size detection is completed by laser diffraction particle size analyzer, with a detection range covering 0.1mm to 100mm; moisture content detection adopts capacitive sensor, combined with temperature compensation algorithm, to control the measurement error within ±1.5%;

[0107] In step S2, the fuzzy adaptive controller 12 matches the fuzzy rule base according to the membership degrees of the three parameters, and obtains the initial target wind speed v by defuzzifying using the centroid method. set The final target wind speed v is then calculated using a moisture content correction factor α. final ;

[0108] Specifically, step S2 is the fuzzy logic decision-making stage: the fuzzy adaptive controller 12 is based on the collected density ρ and average particle size d avg The measured values ​​of three parameters—moisture content α, water content α, and humidity—are mapped to three-level fuzzy subsets ("low / medium / high") using membership functions. The system's built-in fuzzy rule base contains 27 experimentally optimized control rules. Logical matching is performed using the Mamdani inference algorithm, and the defuzzification process employs the centroid method to calculate the initial target wind speed v. set A moisture content correction factor α is introduced for secondary adjustment. This factor is dynamically valued based on a three-dimensional mapping table constructed according to the material's moisture characteristics, and finally the target wind speed v that meets the sorting requirements is determined. final ;

[0109] In step S3, the servo execution module 13 adjusts the airflow speed of the sorting cavity to v within 1 second. final And the guide vanes ensure uniform wind speed;

[0110] Specifically, step S3 is the dynamic response control stage: after receiving the control command, the servo execution module 13 completes the adjustment of the airflow in the sorting cavity within 1 second through the closed-loop PID adjustment system. Combined with the adjustable guide vane mechanism, which includes 12 sets of independently adjustable baffle blades, and an optimized layout scheme through CFD simulation, it ensures that the airflow uniformity within the cavity reaches over 95%.

[0111] Step S4: Detect the entrainment rate E every 10 seconds. If E > 5% for two consecutive times, start parameter fine-tuning; otherwise, maintain the current control parameters.

[0112] Specifically, step S4 is the intelligent feedback optimization stage: the system detects the entrainment rate E in 10-second cycles, using machine vision counting to achieve a detection accuracy of ±0.3%. When E>5% is detected twice consecutively, a parameter fine-tuning mechanism is triggered: first, a more sensitive submicron particle detection channel is activated, and correlation analysis is performed using a historical parameter database. Then, the weight coefficients of the fuzzy rule base are optimized using a genetic algorithm, ultimately achieving adaptive adjustment of the control parameters. If the detection results meet the standards, the current control parameters are maintained and continue to operate.

[0113] In this embodiment, the material characteristics are accurately obtained by the three-parameter detection module 11, and the data processing unit ensures the reliability of the data; the fuzzy adaptive controller 12 builds a rule base based on multiple parameters and achieves precise control through dynamic weight adjustment; the servo execution module 13 ensures stable wind speed adjustment, and the closed-loop correction module 14 fine-tunes the parameters in a timely manner according to the sorting effect.

[0114] It achieves full-process adaptive management from material characteristic detection to precise wind speed control and sorting effect optimization, solving the problems of low sorting efficiency and strong reliance on manual labor under traditional fixed wind speed control. It effectively improves the automation and intelligence level of the construction waste wind sorting process, enhances the system's adaptability to material composition fluctuations, and ensures stable and reliable sorting results.

[0115] In the several embodiments provided in this application, it should be understood that the disclosed modules and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or units may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or equipment, and may be electrical, mechanical, or other forms.

[0116] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0117] In addition, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0118] Furthermore, it should be noted that the combination of the various technical features in this case is not limited to the combination methods described in the claims of this case or the combination methods described in the specific embodiments. All technical features described in this case can be freely combined or combined in any way, unless they contradict each other.

[0119] It should be noted that the above examples are merely specific embodiments of the present invention, and the present invention is obviously not limited to the above embodiments, with many similar variations. All modifications that can be directly derived or conceived by those skilled in the art from the content disclosed in this invention should fall within the protection scope of this invention.

[0120] The above are merely preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An adaptive control system for solid waste treatment, characterized in that, include: The three-parameter detection module is used to obtain the density, average particle size and moisture content of materials in real time. A fuzzy adaptive controller is used to calculate the target wind speed based on the density, average particle size, and moisture content. The servo execution module is used to adjust the real-time wind speed of the sorting cavity according to the target wind speed; A closed-loop correction module is used to fine-tune the output parameters of the fuzzy adaptive controller based on the sorting effect; The closed-loop correction module includes: The sorting effect detection unit is equipped with an infrared through-beam photoelectric sensor array located downstream of the sorting cavity. It calculates the entrainment rate of light materials by counting the number of times heavy particles penetrate the material. ; Parameter fine-tuning unit, when the entrainment rate At that time, the target wind speed corresponding to the current operating conditions. Based on this, the target wind speed is adjusted incrementally or incrementally in steps of 0.5 m / s, with a maximum of 3 adjustments before triggering a manual calibration prompt. The fuzzy adaptive controller includes: Input variable module, define material density The fuzzy universe of discourse is [0.2, 1.2] g / cm³. 3 Average particle size The fuzzy universe of discourse is [5, 100] mm, and the moisture content is... The fuzzy domain is [5%, 30%]; The fuzzy rule base module employs Mamdani fuzzy inference and sets triangular membership functions to divide input variables into intervals. These membership functions include: density The low range is 0.2~0.5 g / cm³. 3 The middle range is 0.5~1.0 g / cm³. 3 The high concentration range is 1.0~1.2 g / cm³. 3 ; Average particle size Small interval: 5~20mm; Medium interval: 20~50mm; Large interval: 50~100mm. Moisture content The dry range is 5%~15%, the medium range is 15%~25%, and the humid range is 25%~30%. The fuzzy rule base module contains 27 control rules in a 3×3×3 structure, establishing the relationship between input variables and target wind speed. The mapping relationship.

2. The adaptive control system for solid waste treatment according to claim 1, characterized in that, The three-parameter detection module includes: The particle size detection unit uses a laser diameter gauge to scan the particle size distribution of materials in real time and calculates the average particle size using a weighted average algorithm. ; In the formula, These are the measured values ​​for each particle size. This represents the mass percentage of materials with the corresponding particle size. The moisture content detection unit uses a capacitive humidity sensor to directly detect the moisture content of the material. ; The density detection unit calculates the average density of the material using the pressure difference method through an array of pressure sensors arranged upstream of the sorting chamber. ; In the formula, For calibration coefficients, This is the differential pressure measurement value. The initial calibrated wind speed for the system.

3. The adaptive control system for solid waste treatment according to claim 2, characterized in that, The calibration coefficient of the density detection unit The methods of obtaining it include: A standard material of known density is added, and the pressure difference is measured. According to the formula Calculation, where This refers to the density of the standard material.

4. The adaptive control system for solid waste treatment according to claim 2, characterized in that, The three-parameter detection module also includes a data processing unit, which performs a 5-second moving average filtering on the density data detected by the pressure sensor to control the density detection error within 5%.

5. The adaptive control system for solid waste treatment according to claim 1, characterized in that, The fuzzy adaptive controller also includes a dynamic weight adjustment module, which is used to introduce a moisture content correction factor. The target wind speed output by the fuzzy rule base Real-time compensation is performed to obtain the final target wind speed. ,in This represents the percentage value of the moisture content test result.

6. The adaptive control system for solid waste treatment according to claim 1, characterized in that, The servo execution module includes: The servo fan uses a permanent magnet synchronous motor to drive a centrifugal fan and can perform wind speed regulation; The guide plate is installed inside the sorting chamber.

7. The adaptive control system for solid waste treatment according to claim 2, characterized in that, The adjustment direction of the parameter fine-tuning unit is determined according to the material moisture content condition: when in a humid condition, i.e., when the moisture content is high... The target wind speed increases progressively, and the operating conditions are dry, i.e., the moisture content is... The target wind speed decreases over time.

8. The adaptive control system for solid waste treatment according to any one of claims 1 to 7, characterized in that, The fuzzy adaptive controller is implemented using an industrial computer or PLC program, and its working steps are as follows: The density is simultaneously collected by the three-parameter detection module 50cm before the material enters the sorting machine. Average particle size Moisture content ; The fuzzy adaptive controller matches a fuzzy rule base based on the membership degrees of the three parameters and obtains the initial target wind speed by defuzzifying using the centroid method. Then, after moisture content correction factor The final target wind speed was calculated. ; The servo execution module adjusts the air speed in the sorting cavity to [a certain value] within 1 second. And the guide vanes ensure uniform wind speed; Detect the entrainment rate every 10 seconds. If twice in a row If the parameters are fine-tuned, then start fine-tuning; otherwise, maintain the current control parameters.

Images