Fine sorting and regenerating system for construction waste brick-concrete materials

Abstract

The invention relates to the technical field of equipment control, and discloses a construction waste brick-concrete material fine sorting and regeneration system, which comprises a characteristic detection subsystem for carrying out characteristic detection on a construction waste brick-concrete material entering a sorting and regeneration system to obtain brick-concrete material characteristic data; the construction subsystem is used for constructing a multi-equipment control network operation strategy of the crusher, the vibrating screen, the winnowing machine and the magnetic separator according to the brick-concrete material characteristic data; the dynamic parameter adjustment subsystem is used for carrying out dynamic parameter adjustment on each device in the sorting and regeneration system based on the brick-concrete material characteristic data and the multi-device control network operation strategy to obtain a device operation parameter set; and the power distribution subsystem is used for inputting the equipment operation parameter set into an energy consumption optimization algorithm for power distribution to obtain an equipment power optimization control instruction, and the optimal balance between the sorting precision and the energy efficiency is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment control, and in particular, to a fine sorting and recycling system for construction waste brick and concrete materials. Background Art

[0002] In traditional construction waste treatment systems, each device such as crushers, vibrating screens, air separators, and magnetic separators usually adopts an independent control mode, lacking an effective coordination mechanism, resulting in low overall treatment efficiency and difficulty in precisely controlling the sorting process. In addition, the existing technology generally adopts a fixed parameter control strategy, which cannot flexibly cope with the fluctuations in the composition of construction waste brick and concrete materials. When the material characteristics change, the system adjusts slowly and the sorting accuracy significantly decreases.

[0003] The energy consumption problem of construction waste treatment systems is also very prominent. In traditional sorting systems, each device often operates at the maximum power or a fixed power, failing to make dynamic adjustments according to the actual material conditions, resulting in a large amount of energy waste. At the same time, the existing control systems have poor adaptability to material inhomogeneity, generally adopting open-loop control or simple feedback mechanisms, lacking effective material characteristic detection and interference compensation mechanisms, and unable to respond in real time to changes in density, hardness, and particle size distribution in brick and concrete materials, resulting in unstable sorting accuracy. Summary of the Invention

[0004] The present invention provides a fine sorting and recycling system for construction waste brick and concrete materials, and the present invention achieves the optimal balance between sorting accuracy and energy efficiency.

[0005] In a first aspect, the present invention provides a fine sorting and recycling system for construction waste brick and concrete materials, and the fine sorting and recycling system for construction waste brick and concrete materials includes: A characteristic detection subsystem for detecting the characteristics of construction waste brick and concrete materials entering the sorting and recycling system to obtain brick and concrete material characteristic data; A construction subsystem for constructing an operation strategy for a multi-device control network of crushers, vibrating screens, air separators, and magnetic separators according to the brick and concrete material characteristic data; A dynamic parameter adjustment subsystem for dynamically adjusting the parameters of each device in the sorting and recycling system based on the brick and concrete material characteristic data and the operation strategy of the multi-device control network to obtain a set of device operation parameters; A power distribution subsystem for inputting the set of device operation parameters into an energy consumption optimization algorithm for power distribution to obtain a device power optimization control instruction.

[0006] Optionally, in the first implementation manner of the first aspect of the present invention, the characteristic detection subsystem is specifically used for: Using an infrared spectrum sensor, a vision sensor, and a pressure sensor, multi-parameter acquisition is performed on the construction waste brick-concrete materials entering the sorting and regeneration system to obtain the original sensing data of the materials; Transmit and process the original sensing data of the materials to obtain the data received by the central control unit; Based on the data received by the central control unit, feature extraction is performed to obtain a multi-dimensional feature set of the materials. The multi-dimensional feature set of the materials includes the surface texture of the materials, color features, pressure distribution, and spectral absorption curves; Perform characteristic analysis on the multi-dimensional feature set of the materials to obtain the basic characteristic indexes of the materials, and perform time-series integration on the basic characteristic indexes of the materials to obtain the time-series data stream of the material characteristics; Based on the time-series data stream of the material characteristics, threshold comparison and data verification processing are performed to obtain the characteristic data of the brick-concrete materials.

[0007] Optionally, in the second implementation manner of the first aspect of the present invention, the construction subsystem is specifically used for: Perform process layout analysis on crushers, vibrating screens, air separators, and magnetic separators according to the characteristic data of the brick-concrete materials to obtain an equipment material flow diagram, and the equipment material flow diagram defines the material transfer paths and flow relationships between the equipment; Perform equipment control level division on the equipment material flow diagram to obtain a three-level control architecture, and the three-level control architecture includes a central controller, a process unit controller, and an equipment-level controller; Based on the three-level control architecture, a control network deployment is performed to obtain a basic architecture for the operation strategy of the multi-device control network. The basic architecture for the operation strategy of the multi-device control network uses industrial Ethernet and supports real-time data interaction between the equipment; Perform material balance modeling on the basic architecture for the operation strategy of the multi-device control network to obtain a material transfer relationship model between the equipment; Based on the material transfer relationship model, configure the operation parameters of each equipment to obtain an equipment operation parameter table, and the equipment operation parameter table includes the working range and initial parameter setting values of each equipment; Create an operation strategy for the multi-device control network according to the material transfer relationship model and the equipment operation parameter table, and the operation strategy for the multi-device control network defines the collaborative control rules of each equipment under different material conditions.

[0008] Optionally, in the third implementation manner of the first aspect of the present invention, the dynamic parameter adjustment subsystem is specifically used for: Construct a state observation model for each equipment according to the characteristic data of the brick-concrete materials and the operation strategy of the multi-device control network, and calculate the equipment state estimation value based on the state observation model; Perform recursive least squares calculation on the operation data of each device to obtain the device dynamic characteristic parameters; Execute adaptive control rule parsing based on the device state estimation value and the device dynamic characteristic parameters to obtain the device control input quantity; Perform device characteristic matching on the device control input quantity to obtain device-specific control parameters; Calculate the control strategy adjustment coefficient according to the change rate of the brick-concrete material characteristic data to obtain the dynamic control gain; Perform performance evaluation on the device-specific control parameters and the dynamic control gain to obtain the device operation parameter set.

[0009] Optionally, in the fourth implementation manner of the first aspect of the present invention, the power distribution subsystem further includes: A cooperative control module, configured to construct a global cooperative control protocol based on the device operation parameter set to obtain a device cooperative control equation; A balance constraint module, configured to establish a material flow balance constraint for the device cooperative control equation to obtain a device material balance equation and a system power constraint condition; A Lagrangian optimization module, configured to perform Lagrangian optimization according to the device material balance equation and the system power constraint condition to obtain a power constraint optimization objective function; A solution calculation module, configured to transform the power constraint optimization objective function into a quadratic programming problem for solution calculation to obtain an optimal control input set, where the optimal control input set includes the optimal control values of each device; A power optimization module, configured to perform power dynamic distribution calculation on each device based on the optimal control input set to obtain a device power distribution scheme, and perform power saturation characteristic curve processing on the device power distribution scheme to obtain a device power optimization control instruction.

[0010] Optionally, in the fifth implementation manner of the first aspect of the present invention, the power optimization module is specifically configured to: Perform device importance analysis on the control values of each device in the optimal control input set to obtain a device importance weight coefficient set; Perform preliminary power distribution calculation based on the device importance weight coefficient set to obtain a device initial power distribution numerical table; Perform power balance adjustment calculation according to the device initial power distribution numerical table and the material transfer path and flow relationship between devices to obtain a device power dynamic balance scheme; Verify the system total power constraint for the device power dynamic balance scheme to obtain a power reallocation instruction, and trigger power reallocation when the device power dynamic balance scheme does not meet the total power constraint condition; Construct a device power saturation characteristic curve according to the conversion efficiency characteristics of each device, obtain a set of power conversion functions, and perform conversion calculations on the device power dynamic balance scheme through the set of power conversion functions to obtain device power optimization control instructions.

[0011] Optionally, in the sixth implementation manner of the first aspect of the present invention, the fine sorting and recycling system for construction waste brick and concrete materials further includes: A material flow prediction subsystem, configured to distribute the device power optimization control instructions to each device controller for execution to obtain real-time device operation state data, where the real-time device operation state data includes device rotation speed, amplitude, power, and material throughput; construct a material processing prediction model based on the real-time device operation state data; input the brick and concrete material characteristic data as an external disturbance into the material processing prediction model for forward calculation to obtain a predicted state quantity; perform feedforward compensation calculation according to the difference between the predicted state quantity and the current actual system state to obtain a feedforward compensation quantity; perform a processing mode judgment based on the feedforward compensation quantity and the brick and concrete material characteristic data to obtain a control mode switching signal, where the control mode switching signal is used for intelligent switching between a batch processing mode and a continuous operation mode; perform smoothing processing on the control mode switching signal and execute corresponding control strategies to obtain material flow prediction data, where the material flow prediction data includes predicted values of material flow velocity, flow rate, accumulation state, and trend between devices in the sorting and recycling system; An association analysis subsystem, configured to perform association analysis on the material flow prediction data and real-time sorting indicators to generate an automatic optimization scheme for device parameters and an evaluation result of the device operation state.

[0012] Optionally, in the seventh implementation manner of the first aspect of the present invention, the association analysis subsystem is specifically configured to: Perform hierarchical storage on the material flow prediction data and real-time sorting indicators to obtain a data experience library, where the data experience library includes material characteristic data, device parameter data, and processing effect data; Calculate a comprehensive performance index based on the processing effect data in the data experience library to obtain a system performance evaluation value; Input the system performance evaluation value into a reinforcement learning algorithm for control strategy update calculation to obtain an optimized control strategy; Calculate the difference between the actual output and the model prediction output of each device to obtain a device residual vector, and perform wavelet decomposition on the device residual vector to obtain multi-band residual components; Calculate a device health index based on the multi-band residual components to obtain an evaluation result of the device health state, and trigger corresponding maintenance or protection processes when the evaluation result of the device health state is lower than a preset threshold; Periodically update the control model parameters according to the accumulated processing experience to obtain an automatic optimization scheme for equipment parameters. The automatic optimization scheme for equipment parameters includes updated values of a feedback gain matrix, a feedforward compensation matrix, and a cooperative control weight.

[0013] In the technical solution provided by the present invention, through the multi-device cooperative control technology, the optimal balance between sorting accuracy and energy efficiency is achieved. The system dynamically adjusts control parameters based on the results of real-time material property detection, enabling devices such as crushers, vibrating screens, air separators, and magnetic separators to work efficiently in cooperation. Even in the case of sudden changes in material composition, a stable sorting effect can still be maintained. The time-varying parameter adaptive control algorithm adopted by the system can accurately control the operating parameters of each level of equipment, ensuring a significant improvement in the sorting purity of brick-concrete materials. At the same time, through the power constraint optimization mechanism, the system can significantly reduce the overall energy consumption on the premise of ensuring the safe operation of the equipment. The feedforward control mechanism based on the virtual reference model enables the system to respond to material changes in advance, reduce the adjustment time, and improve the processing efficiency. The system also has the functions of self-learning optimization and equipment status self-diagnosis. By continuously accumulating processing experience, the control strategy is optimized, and at the same time, the health status of the equipment is monitored to prevent failures, reduce maintenance costs, extend the service life of the equipment, and greatly improve the equipment utilization rate. Overall, the system solves the key problems in traditional construction waste treatment technologies and realizes the efficient, fine sorting and resource utilization of brick-concrete materials in construction waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0015] Figure 1 It is a schematic diagram of a fine sorting and regeneration system for brick-concrete materials in construction waste in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] An embodiment of the present invention provides a fine sorting and recycling system for construction waste brick-concrete materials. Terms such as "first", "second", "third", "fourth", etc. (if any) in the specification, claims and the above-mentioned drawings of the present invention are used to distinguish similar objects and do not necessarily need to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the term "comprising" or "having" and any variation thereof are intended to cover non-exclusive inclusion. For example, a process, system, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, systems, products or devices.

[0017] For ease of understanding, the specific process of the embodiment of the present invention will be described below. Please refer to Figure 1 , an embodiment of the fine sorting and recycling system for construction waste brick-concrete materials in the embodiment of the present invention includes: A characteristic detection subsystem 11 for detecting the characteristics of the construction waste brick-concrete materials entering the sorting and recycling system to obtain brick-concrete material characteristic data; In this embodiment, through various sensing devices such as infrared spectrum sensors, vision sensors, and pressure sensors, multi-parameter acquisition is carried out on the construction waste brick-concrete materials entering the sorting and recycling system to obtain the original sensing data of the materials. The infrared spectrum sensor obtains the chemical composition information and spectral absorption curve of the materials by detecting the absorption of infrared light with specific wavelengths by the materials, so as to identify different material components in the brick-concrete materials, such as distinguishing components like bricks, concrete, and mortar. The vision sensor uses machine vision technology to obtain the appearance characteristics such as the surface texture, color characteristics, and particle morphology of the materials by collecting and analyzing images of the material surface, helping to identify the physical state of the brick-concrete materials. The pressure sensor is used to detect the deformation characteristics and strength characteristics of the materials under the action of pressure. By obtaining the pressure distribution data, the mechanical properties of the materials are analyzed, such as the compressive strength and brittleness degree, etc. The original sensing data of the materials is transmitted and processed, and the data collected by various sensors is subjected to format conversion, data cleaning, and preprocessing to obtain the standardized data format transmitted to the central control unit. During the data transmission process, the processed data is transmitted to the central control unit safely and quickly through a data bus or wireless transmission method to ensure the real-time and integrity of the data. In the central control unit, these data are synchronously received through a multi-channel data interface and automatically allocated to different processing modules for feature extraction. The feature extraction process is based on specific algorithm models, such as image processing algorithms (such as edge detection, texture analysis), spectral analysis algorithms (such as spectral peak recognition, characteristic band analysis), and pressure data analysis algorithms (such as pressure-strain curve fitting, mechanical property analysis), etc. The original data is converted into higher-level feature information to obtain the multi-dimensional feature set of the materials. The characteristics of the multi-dimensional feature set of the materials are analyzed to obtain the basic characteristic indexes of the materials. The characteristic analysis process uses a variety of data analysis methods, such as the calculation of characteristic values based on statistical models, classification and clustering analysis based on machine learning models, and parameter derivation based on physical models, etc. These analysis methods extract representative indexes that are closely related to the material characteristics from the multi-dimensional feature set of the materials, such as the density, water absorption rate, hardness, strength, etc. of the materials. The data at different time points are integrated to form a continuous time-series data stream of material characteristics. Threshold comparison and data verification processing are carried out based on the time-series data stream of material characteristics. During the threshold comparison process, the real-time time-series data of material characteristics is compared and analyzed with the preset standard characteristic thresholds. For example, whether the brick content, concrete particle size distribution, metal impurity ratio, etc. in the brick-concrete materials are within a reasonable range. If it is detected that the data exceeds the threshold range, the system triggers an alarm or automatically adjusts the device operation parameters. The data verification processing is to ensure the accuracy and reliability of the data. The material characteristic data is verified through various means (such as data redundancy check, historical data comparison, outlier rejection). While ensuring the data quality, the stability and intelligent level of the entire sorting and recycling system are improved. The characteristic data of the brick-concrete materials is obtained.

[0018] A construction subsystem 12 is configured to build an operation strategy for a multi-device control network of a crusher, a vibrating screen, a pneumatic separator, and a magnetic separator according to the characteristic data of the brick-concrete mixture materials; In this embodiment, based on the characteristic data of the brick-concrete mixture materials, the process layout analysis of equipment such as crushers, vibrating screens, air separators, and magnetic separators is carried out to obtain the equipment material flow diagram. The equipment material flow diagram defines the material transfer paths and flow distribution between different equipment by analyzing the processing characteristics of each equipment, the material passing paths, and their flow relationships. The construction of the material flow diagram not only depends on the physical layout of the equipment but also involves the flow direction of the materials, the transfer methods, and the distribution of the materials after being processed by different equipment. For example, after the construction waste is coarsely crushed by the crusher, the particles are screened by the vibrating screen, the air separator separates the light materials from the heavy materials according to the density difference of the materials, and the magnetic separator removes the metal impurities therein. The role of the equipment material flow diagram is to clarify the connection relationships between various processing links and provide visual data support for the collaborative work of the equipment. The equipment control hierarchy is divided for the equipment material flow diagram to establish a three-level control architecture. The control hierarchy is divided into the central controller, the process unit controller, and the equipment-level controller. The central controller is responsible for the high-level decision-making and coordination work of the entire system and processes global tasks such as production scheduling and equipment status monitoring; the process unit controller is responsible for the management of a specific process unit, such as crushing, screening, air separation, etc., and optimizes the inside of the unit according to the instructions of the central controller; the equipment-level controller is directly connected to the specific equipment and controls parameters such as the on-off state, operating speed, and load of the equipment. Through the hierarchical control architecture, it is ensured that the task division between each level is clear, and the anti-interference ability and fault recovery ability of the system are improved. Based on the three-level control architecture, the basic infrastructure of the multi-device control network operation strategy is constructed. In order to ensure the real-time data interaction and information sharing between each device, the control network adopts the industrial Ethernet architecture, which provides a high-speed and stable data transmission channel to ensure that each device in the system can transmit data and control instructions in a timely manner during the working process. For example, the operating status of the crusher, the screening effect of the vibrating screen, the air volume adjustment of the air separator, etc. are fed back in real time through the industrial Ethernet, and the central controller adjusts the system according to the real-time data. The material balance modeling is carried out for the basic infrastructure of the multi-device control network operation strategy to establish the material transfer relationship model between the equipment. The material balance modeling is a key process. By analyzing the material flow situation between the equipment, the material transfer relationship between each equipment is established to provide accurate reference data for the operation of each equipment. In the modeling process, factors such as the material processing capacity of the equipment, the material characteristics (such as particle size, density, humidity, etc.), and the material transfer efficiency between the equipment are considered. Based on the material transfer relationship model, the operating parameters of each equipment are configured to obtain the equipment operating parameter table. The equipment operating parameter table lists the working ranges and initial parameter setting values of each equipment, such as the feed particle size range of the crusher, the screening particle size of the vibrating screen, the wind speed range of the air separator, and the magnetic field strength of the magnetic separator. The setting of these parameters is based on the material characteristics and the regulations in the material flow diagram to ensure that each equipment achieves the best processing effect within its working range.Based on the material transfer relationship model and the equipment operation parameter table, construct the operation strategy of the multi-equipment control network. The core of this strategy is to define the collaborative control rules for each device under different material conditions, so as to achieve the coordinated cooperation of the devices. Different material characteristics (such as particle size distribution, water content, composition ratio, etc.) will affect the operation status of each device. Therefore, flexible control rules need to be formulated to ensure that each device works efficiently and collaboratively under different working conditions. For example, when dealing with larger pieces of construction waste, the crushing force of the crusher and the screening speed of the vibrating screen need to be increased accordingly. When dealing with smaller particle waste, the air volume and magnetic field intensity of the air separator and magnetic separator need to be adjusted to ensure the stability and energy efficiency of the system operation.

[0019] The dynamic parameter adjustment subsystem 13 is used to dynamically adjust the parameters of each device in the sorting and regeneration system based on the brick-concrete material characteristic data and the multi-equipment control network operation strategy, and obtain the equipment operation parameter set; In this embodiment, state observation models of each device are constructed based on the characteristics data of brick-concrete materials and the operation strategy of the multi-device control network. Using the material characteristics data, such as the particle size, density, water content, etc. of the material, and the operating conditions of the device, including load, speed, efficiency, etc., the actual operating state of each device under different working conditions is deduced. These models adopt the Kalman filter or state estimation method to obtain a more accurate device state estimation value. Through these models, various sensor data of the system are combined with the working characteristics of the device to dynamically predict the performance of each device. Based on the established state observation models, the recursive least squares method is used to calculate the operation data of each device, and the dynamic characteristic parameters of the device are obtained. The recursive least squares method is an adaptive filtering algorithm that updates the parameter estimation of the device in real time during the data flow process. By real-time analyzing the historical operation data of the device, the parameters of the device are dynamically adjusted and optimized, so that the device always maintains the best performance under changing working conditions. Through the recursive least squares method, continuously track the dynamic behavior of the device, and identify the dynamic characteristic parameters of the device, including key indicators such as its response speed, stability, energy consumption efficiency, etc. Based on the device state estimation value and the dynamic characteristic parameters, perform adaptive control rule parsing to calculate the device control input quantity. The adaptive control rule is a method that automatically adjusts the device control strategy according to the real-time state and characteristic data of the device, and can flexibly adjust various control parameters according to the actual operation situation of the device to ensure that the device always operates in the optimal state. This process comprehensively considers various parameters of the device, including the load, rotation speed, feed rate, etc. of the device, and adjusts the control input through an intelligent algorithm to enable the device to quickly adapt to different materials and working environments. In this process, the control algorithm obtains the control input quantity for the device operation by analyzing the real-time sensing data, state estimation value and dynamic characteristic parameters. Perform device characteristic matching on the device control input quantity to generate the dedicated control parameters of the device, including adjustment parameters related to the specific working characteristics of the device, such as the rotation speed of the crusher, the screening frequency of the vibrating screen, the wind force of the air separator, the magnetic field strength of the magnetic separator, etc. Through the device characteristic matching process, according to the physical characteristics and operation requirements of the device, the control input quantity is converted into specific device control parameters. In order to cope with the dynamic changes of the brick-concrete material characteristics during the whole processing process, calculate the control strategy adjustment coefficient according to the change rate of the material characteristics data to obtain the dynamic control gain. The control strategy adjustment coefficient is dynamically adjusted according to the real-time change situation of the material characteristics, reflecting the influence of the change of the material attributes on the system control strategy. When the characteristics of the material change significantly, such as the particle size distribution changes, or the humidity content is relatively high, calculate the new dynamic control gain and adjust the device control parameters accordingly to ensure that the processing effect and energy efficiency of the device always remain in the optimal state. Evaluate the performance of the dedicated control parameters and dynamic control gain of the device to obtain the device operation parameter set.Taking into comprehensive consideration multiple factors such as the operating efficiency, processing effect, energy consumption of each device, and the stability of the system, by comparing and evaluating the performance of each device under different control parameters, optimizing various control decisions, and ensuring the overall efficiency and reliability of the system. The finally generated set of device operating parameters includes the optimal operating range and adjustment parameters of each device under different working conditions.

[0020] The power distribution subsystem 14 is used to input the set of device operating parameters into the energy consumption optimization algorithm for power distribution to obtain the device power optimization control instruction.

[0021] In this embodiment, a design collaborative control module is designed, which constructs a global collaborative control protocol based on the set of device operation parameters. The core of this protocol lies in coordinating the operation states of various devices to ensure that each device can achieve the maximum efficiency in the overall system, and that each device can adjust its working parameters according to the needs of material flow, so that all links of the system operation cooperate with each other to achieve overall optimization. Through the device collaborative control equation, the control parameters of each device are unifiedly modeled with elements such as material flow rate and energy efficiency to ensure that the devices cooperate and coordinate under different working conditions, and maintain the stability and high efficiency of the system through a unified control logic. Through the balance constraint module, a material flow balance constraint is established for the device collaborative control equation to obtain the device material balance equation and the system power constraint conditions. The balance constraint of the material flow rate requires that in each link of the system, the input and output flow rates of the material need to meet certain balance conditions to ensure that there is no material retention or overload in the processing of each device. At the same time, considering the system power constraint conditions, the power consumption of each device must be within a certain range to avoid overload or energy waste. The balance constraint module adjusts the device collaborative control equation to achieve a globally optimized balance between the two elements of material flow rate and power consumption. The Lagrangian optimization module optimally solves the device material balance equation and the power constraint conditions by introducing the Lagrangian optimization method to obtain the power constraint optimization objective function. The Lagrangian optimization method can effectively handle constraint condition problems. By constructing Lagrange multipliers, the constraint conditions are introduced into the objective function and transformed into an unconstrained optimization problem for solution. The construction of the optimization objective function aims to minimize the system power consumption while maximizing the working efficiency and processing capacity of the devices, so that each device maintains an optimal power distribution under different working conditions. The solution calculation module transforms the obtained power constraint optimization objective function into a quadratic programming problem for solution calculation. The quadratic programming problem is a special type of optimization problem, usually convex, and is quickly solved by an efficient numerical algorithm. The solution calculation module uses modern optimization algorithms (such as the interior point method, simplex method, etc.) to solve this problem to obtain the optimal control input set for each device. The optimal control input set contains the optimal working parameters of each device under power constraints, including rotational speed, load, operation time, etc. The power optimization module calculates the dynamic power distribution for each device. This module makes real-time power adjustments for each device according to the optimal control input set to meet the requirements under different working conditions and ensure that the devices always maintain the best state during actual operation. The calculation of the dynamic power distribution not only considers the power consumption of each device, but also needs to combine various factors such as system load and material flow characteristics to ensure the maximization of the energy efficiency of the entire system. At the same time, the power optimization module processes the device power distribution scheme with a power saturation characteristic curve to ensure that the device does not exceed its maximum power range and avoid equipment failures or efficiency drops.The processing of the power saturation characteristic curve models the boundary conditions of the device power consumption, dynamically adjusts the power output of the device, enables it to work within a reasonable range, and avoids unnecessary power waste. Through the above steps, the device power optimization control instructions generated by the power optimization module are fed back to each device in real time, instructing them to adjust the operating parameters according to the current working state.

[0022] Perform device importance analysis on the control values of each device in the optimal control input set to evaluate the key role of each device in the entire system, thereby determining its contribution to the overall system performance. Obtain the device importance weight coefficient set by calculating the influence and effectiveness of each device, reflecting the priority of each device in power distribution. Based on the device importance weight coefficient set, perform preliminary power distribution calculations to obtain the device initial power distribution value table. The purpose of the preliminary distribution calculation is to reasonably allocate the power resources of each device on the premise of ensuring the stable and efficient operation of the system. By assigning weight values to the importance of each device, according to the key role of the device, give priority to ensuring the power requirements of high-priority devices, and at the same time reasonably allocate the required power resources to other devices. In the preliminary distribution calculation, the allocation of power resources not only considers the importance of the device, but also needs to combine the actual operating requirements and power consumption characteristics of the device to ensure that the device operates efficiently in the best working state. Based on the material transfer path and flow relationship between devices, perform power balance adjustment calculations to obtain the device power dynamic balance scheme. The flow of materials determines the processing load of each device and directly affects the power requirements of the device. Therefore, the power balance adjustment calculation must consider these factors. By optimizing and adjusting the power distribution between devices, the power of the entire system is balanced, ensuring that each device dynamically adjusts its power consumption according to the change of material flow, achieving the energy efficiency optimization of the entire system. Perform system total power constraint verification on the device power dynamic balance scheme to ensure that the entire system meets the total power constraint conditions during the process of material handling and power consumption, that is, the power consumption of the entire system cannot exceed the maximum power upper limit of the system. If the device power dynamic balance scheme fails to meet the total power constraint conditions, trigger the power redistribution mechanism. The process of power redistribution involves readjusting the power distribution of each device to ensure that the total power consumption does not exceed the standard. In this process, automatically adjust the power of the devices that do not meet the constraint conditions to ensure that the system maintains the operating efficiency and material handling capacity of each device while meeting the total power constraint. After the power redistribution is completed, construct the device power saturation characteristic curve according to the conversion efficiency characteristics of each device, reflecting the efficiency change of the device at different power levels, and helping the system evaluate the performance of the device under different power inputs. The device power saturation characteristic curve shows the efficiency change of the device under low-power and high-power conditions, helping the system identify the optimal power working range. These characteristic curves can also show the risk of efficiency decline or excessive energy consumption when the device exceeds its power saturation range. Based on these conversion efficiency characteristics, the power optimization module constructs the device power conversion function set. Through the device power conversion function set, perform conversion calculations on the device power dynamic balance scheme. According to the power saturation characteristics of each device, precisely adjust the power distribution of the device to ensure that each device operates at the best efficiency without exceeding its power saturation range.Adjust the power input of the device in real time through a set of power conversion functions to maximize the working efficiency and energy efficiency of the device while avoiding power waste. Obtain the power optimization control instruction of the device.

[0023] Distribute the device power optimization control instructions to each device controller for execution. After receiving the control instructions, the device adjusts its own operating parameters according to the instructions, and monitors and feedbacks the operating status of the device in real time. The real-time device operating status data includes key parameters such as the rotation speed, amplitude, power consumption, and material throughput of the device. The material flow prediction subsystem uses these real-time data to construct a material processing prediction model, which describes the flow characteristics and change trends of materials in each device. By recording and analyzing the working status of the device, the model infers the rules of material flow. Input the brick-concrete material characteristic data as an external disturbance into the material processing prediction model for forward calculation to obtain the predicted state quantity. The brick-concrete material characteristic data directly determines the flow mode, speed, and change trend of materials in each device. By inputting these characteristic data into the prediction model, the interference effect of different material characteristics on the processing process is accurately simulated, improving the accuracy of prediction. According to the predicted state quantity, calculate the difference between the current state and the predicted state, and perform feedforward compensation calculation. The purpose of feedforward compensation is to correct between the prediction and the actual state, reducing errors caused by external factors (such as changes in material characteristics), thereby ensuring the accuracy and stability of device operation. Execute the processing mode judgment according to the obtained compensation quantity and brick-concrete material characteristic data. According to the current operating state of the system, intelligently judge whether it is necessary to switch the control mode, switch from the batch processing mode to the continuous operation mode, or vice versa. The batch processing mode and the continuous operation mode have different advantages and disadvantages in different working environments. The batch processing mode is suitable for processing materials with large flow variations, while the continuous operation mode is suitable for situations where the material flow is relatively stable. By intelligently switching between these two modes, the system obtains the optimal processing efficiency under different operating conditions and reduces unnecessary energy waste or equipment burden. When the system decides to perform a mode switch, generate a control mode switch signal and perform smoothing processing to avoid sudden changes or impacts during the switch. The smoothing processing adjusts the change rate of the signal to make the mode switch process smoother, avoiding problems such as device instability or reduced production efficiency caused by sudden switches. Input the smoothed control mode switch signal into the control center of the system to execute the corresponding control strategy. During the execution of the control strategy, the material flow prediction subsystem outputs material flow prediction data based on the aforementioned control signal. The material flow prediction data contains important information such as the predicted values of the material flow rate, flow volume, accumulation state, and trend between each device in the sorting and regeneration system. By real-time tracking and analyzing the material flow prediction data, unstable factors in the material flow process are promptly detected, and corresponding adjustment measures are taken to avoid device failures caused by poor material flow or overloading. In addition to the material flow prediction subsystem, the system also includes a correlation analysis subsystem, whose function is to perform correlation analysis on the material flow prediction data and real-time sorting indicators.By analyzing the relationship between material flow and sorting effect, potential optimization space is discovered, and an optimization plan for equipment parameters is automatically generated. Correlation analysis can reveal the internal connection between material flow characteristics and sorting effect, thus providing a scientific basis for equipment optimization. At the same time, the correlation analysis subsystem generates the evaluation results of equipment operation status. Through the evaluation of the real-time operation status of the equipment, the working efficiency and operation stability of the equipment are comprehensively evaluated. Through continuous evaluation and feedback, the operation strategies of each equipment are adjusted in real time to ensure that each equipment can work in the best state, thereby improving the production efficiency and material handling capacity of the entire system.

[0024] Hierarchically store the material flow prediction data and real-time sorting indicators to construct a data experience library. In the data experience library, the material characteristic data includes information such as the particle size distribution, density, and humidity of the material, the equipment parameter data covers the operating status, power consumption, operating mode, etc. of the equipment, while the processing effect data reflects the sorting accuracy, output rate, and energy efficiency level of the system under different material conditions. Based on the processing effect data in the data experience library, calculate the comprehensive performance indicators to obtain the performance evaluation value of the system. The method for calculating the comprehensive performance indicators adopts the weighted evaluation or multi-index comprehensive analysis method, and converts multiple performance indicators of the system (such as sorting efficiency, resource utilization rate, energy consumption level, operating stability, etc.) into a single evaluation value through an evaluation model. To achieve the continuous optimization of the system control strategy, input the system performance evaluation value into the reinforcement learning algorithm for control strategy update calculation to obtain the optimized control strategy. The reinforcement learning algorithm simulates the system operation effect under different control strategies and continuously adjusts the control parameters according to the actual feedback to obtain the optimal control scheme. The reward mechanism in reinforcement learning can guide the system to gradually approach the optimal control path. Through multiple iterations and learning, the generated optimized control strategy can effectively improve the response speed, stability, and resource utilization efficiency of the system. While calculating the optimized control strategy, the correlation analysis subsystem calculates the difference between the actual output and the model prediction output of each device to obtain the residual vector of the device. The device residual vector reflects the deviation between the actual operating state and the ideal state of the device. Perform wavelet decomposition on the device residual vector, and decompose the residual signal into residual components of multiple frequency bands through the multi-band analysis method. The wavelet decomposition method can effectively extract different frequency components in the signal, thereby separating information such as high-frequency noise, low-frequency drift, and intermediate-frequency mechanical vibration characteristics during the device operation process. Based on the multi-band residual components, calculate the device health index to obtain the evaluation result of the device health status. The device health index constructs a device health evaluation model by analyzing the residual characteristics of the device at different frequencies and combining historical data experience to evaluate the current operating state of the device. When the evaluation result of the device health status is lower than the safety threshold preset by the system, the system automatically triggers the corresponding maintenance or protection process, and prevents the device from occurring more serious failures through measures such as early warning, load reduction, and shutdown to ensure the safety and continuous operation of the system. At the same time, the correlation analysis subsystem periodically updates the control model parameters according to the accumulated processing experience to generate an automatic optimization scheme for device parameters. The automatic optimization scheme for device parameters mainly includes the updated values of the feedback gain matrix, feedforward compensation matrix, and cooperative control weight. The adjustment of these parameters enables the control model to better adapt to the actual operating conditions. For example, the update of the feedback gain matrix helps to improve the response ability of the system to input disturbances, the feedforward compensation matrix can improve the dynamic performance of the system, and the update of the cooperative control weight can optimize the cooperation efficiency between multiple devices, thereby achieving the improvement of the overall performance of the system.

[0025] Optionally, the feature detection subsystem 11 is specifically configured to: Use an infrared spectrum sensor, a vision sensor, and a pressure sensor to collect multi-parameters of the brick-concrete building waste materials entering the sorting and regeneration system, and obtain the original sensing data of the materials; Transmit and process the original sensing data of the materials to obtain the data received by the central control unit; Extract features based on the data received by the central control unit to obtain a multi-dimensional feature set of the materials. The multi-dimensional feature set of the materials includes the surface texture, color features, pressure distribution, and spectral absorption curve of the materials; Analyze the characteristics of the multi-dimensional feature set of the materials to obtain the basic characteristic indexes of the materials, and perform time-series integration on the basic characteristic indexes of the materials to obtain the time-series data stream of the material characteristics; Perform threshold comparison and data verification processing based on the time-series data stream of the material characteristics to obtain the characteristic data of the brick-concrete materials.

[0026] In this embodiment, an infrared spectrum sensor, a vision sensor, and a pressure sensor are used to obtain the original sensing data of the materials. The infrared spectrum sensor obtains the chemical composition information and spectral absorption curve of the materials by detecting the absorption of specific wavelength infrared light by the materials. For example, the absorption peak differences of bricks, concrete, and mortar in specific bands help to distinguish these materials. The vision sensor uses machine vision technology to collect images of the material surface through a high-resolution camera, and extracts the surface texture and color features of the materials through image processing algorithms, such as the red color of different bricks, the grayish-white color of concrete, and the rough surface characteristics of mortar. The pressure sensor is used to detect the mechanical response of the materials under the action of external forces. By applying a known pressure, the deformation amount and force distribution of the materials are recorded to obtain the pressure distribution data. The original sensing data is transmitted to the central control unit for processing through a data transmission system. During the transmission process, a high-speed data bus (such as industrial Ethernet) or wireless transmission technology (such as Wi-Fi or LoRa) is used, and data cleaning and format conversion are performed during the data transmission process to ensure that the data received by the central control unit is standardized. When the data enters the central control unit, the system automatically calls the feature extraction algorithm to convert these original data into a more abstract multi-dimensional feature set of the materials. During the feature extraction process, the image data undergoes edge detection, texture analysis, and color histogram calculation to obtain the surface texture and color features of the materials; the spectral data extracts the characteristic peak and absorption band information in the spectral absorption curve through Fourier transform or wavelet transform; the pressure data is obtained through pressure-strain curve fitting (such as a linear fitting model , where represents pressure, represents deformation, (where the elastic coefficient is used) to calculate the mechanical property parameters and pressure distribution characteristics of the material. Conduct characteristic analysis on the multi-dimensional characteristic set of the material to extract the basic characteristic indexes of the material. For example, the hardness of the material ( is calculated from the pressure sensing data, and its calculation formula is:

[0027] where, is the applied pressure, is the contact area. By analyzing the pressure distribution diagram, the force conditions in different regions are calculated to obtain the overall hardness distribution. The color characteristic of the material is calculated through the color channel mean value in image analysis:

[0028] where, represents the th color channel (such as the red channel in RGB), represents the color value of the th pixel in the image in the th channel, is the total number of pixels in the image. For the spectral absorption curve, the chemical composition of the material is characterized by calculating the absorption coefficient of the characteristic band and the calculation formula of the absorption coefficient is:

[0029] where, is the incident light intensity, is the transmitted light intensity, is the thickness of the material. This formula is derived from the Lambert-Beer law and can accurately describe the spectral absorption characteristics. Conduct temporal integration on the basic characteristic indexes to generate the temporal data stream of material characteristics. Through time series analysis methods, the characteristic data collected at different time points are smoothed and trend analyzed. For example, using the moving average or exponential smoothing method, the temporal data of the material characteristics are smoothed into a continuously changing curve, which helps to eliminate the random fluctuations in the data and highlight the overall trend of the material characteristic changes. For some complex temporal characteristics, such as the changes in the hardness of the material during different batch processes, an autoregressive moving average model is used for prediction, and the model expression is:

[0030] where, represents the characteristic value at the current moment, is the constant term, is the autoregressive coefficient, is the moving average coefficient, It is white noise. The time series prediction method can help the system identify emerging characteristic changes in advance. Based on the time series data stream of material characteristics, threshold comparison and data verification processing are performed to obtain the characteristic data of brick-concrete materials. During the threshold comparison process, the material characteristic values calculated in real time are compared with the preset standard thresholds. For example, the hardness should be within a certain range, the color characteristic should conform to the color distribution of brick-concrete materials, and the spectral absorption coefficient should reach a specific absorption rate in a specific wavelength band, etc. When the data exceeds the threshold range, the system will issue a warning signal or automatically adjust the processing parameters of the equipment. During the data verification process, historical data and model prediction data are used for cross-verification. By calculating the error between the predicted value and the actual measured value, the reliability of the data is judged. If the error is too large, it indicates that the sensor data is abnormal or the material characteristics have changed significantly.

[0031] Optionally, the construction subsystem 12 is specifically configured to: Conduct process layout analysis on crushers, vibrating screens, air separators, and magnetic separators according to the brick-concrete material characteristic data to obtain an equipment material flow diagram, which defines the material transfer paths and flow relationships between equipment; Perform equipment control level division on the equipment material flow diagram to obtain a three-level control architecture, which includes a central controller, a process unit controller, and an equipment-level controller; Based on the three-level control architecture, deploy a control network to obtain a multi-equipment control network operation strategy infrastructure, which uses industrial Ethernet and supports real-time data interaction between equipment; Conduct material balance modeling on the multi-equipment control network operation strategy infrastructure to obtain a material transfer relationship model between equipment; Based on the material transfer relationship model, configure the operation parameters of each equipment to obtain an equipment operation parameter table, which contains the working range and initial parameter setting values of each equipment; Create a multi-equipment control network operation strategy according to the material transfer relationship model and the equipment operation parameter table, which defines the collaborative control rules of each equipment under different material conditions.

[0032] In this embodiment, process analysis is performed on crushers, vibrating screens, air separators, and magnetic separators according to the brick-concrete material characteristic data to construct an equipment material flow diagram. The equipment material flow diagram describes the flow trajectories of different materials during the processing process and the interlocking relationships between equipment by defining the material transfer paths and flow relationships between equipment. When constructing the material flow diagram, the inlet and outlet connection relationships of each equipment in the system are presented in a graphical form, and the flow direction calculation is performed in combination with the mathematical model of the material flow rate. For example, in the crusher, the feed flow rate of the material is expressed as , and the discharge flow rate is , the material balance inside the equipment is expressed as:

[0033] Among them, represents the waste or loss generated during the crushing process. For the vibrating screen, the flow relationship during the screening process is expressed as:

[0034] Among them, is the flow rate of fine particles passing through the sieve mesh, is the flow rate of large particles being intercepted. The air separator and magnetic separator are also described by similar flow balance equations. The air separator separates materials by wind force, generating a light material flow rate and a heavy material flow rate . The magnetic separator uses magnetic force to separate metal impurities from non-metallic materials , satisfying the following relationship:

[0035] In the formula, Both represent the material flow rate between equipment rooms. Through these flow relationships, a material flow diagram of the equipment is established to optimize the flow path of materials throughout the processing chain. The equipment material flow diagram is divided into equipment control levels to construct a three-level control architecture, including a central controller, a process unit controller, and an equipment-level controller. The central controller is responsible for the global scheduling and decision-making of the entire system, such as the global regulation of material flow rate, the allocation of production tasks, and the real-time monitoring of equipment status. The process unit controller is responsible for the operation coordination within each functional unit, such as the coordinated operation of the equipment in the crushing process unit, the screening process unit, the air separation process unit, and the magnetic separation process unit. The equipment-level controller is directly connected to specific equipment to execute specific control commands, such as adjusting the rotation speed of the crusher, setting the screen hole size of the vibrating screen, adjusting the wind speed of the air separator, and controlling the magnetic field strength of the magnetic separator. Based on the three-level control architecture, the deployment of the control network is carried out to form the infrastructure of the multi-equipment control network operation strategy. This network architecture uses industrial Ethernet as the communication carrier to support real-time data interaction between equipment. Industrial Ethernet has the characteristics of high speed, low latency, and high reliability, and can ensure that the status data, control instructions, and alarm information of each equipment in the system are transmitted within milliseconds, ensuring the system response speed and control accuracy. The controller of each equipment is connected to the central controller through Ethernet, and the process unit controller coordinates the operation of the equipment within the same unit. The central controller dynamically adjusts the control strategy of each equipment by monitoring the operation status of all equipment to achieve intelligent and refined management of the entire system. In order to enable the control network to better reflect the actual situation of material flow, a material balance model is established for the infrastructure of the multi-equipment control network operation strategy to obtain the material transfer relationship model between equipment. The material balance model is based on the principle of material flow conservation, that is, the material flow rate entering each equipment should be equal to the sum of its output flow rate and losses. The material balance model is represented in matrix form. Let be the input flow rate vector, be the output flow rate vector, be the material loss vector, then there is:

[0036] Through this model, the optimal operating state of each equipment under different material input conditions is calculated. For example, when the input flow rate increases, the processing speed of the crusher and the screening frequency of the vibrating screen are automatically calculated to be adjusted to maintain the balance state of material flow. Based on the material transfer relationship model, the operating parameters of each equipment are configured to generate an equipment operating parameter table. The equipment operating parameter table includes the working range and initial parameter setting values of each equipment, such as the rotation speed of the crusher, the amplitude of the vibrating screen, the wind speed of the air separator, and the magnetic field strength The settings of these parameters should consider the physical characteristics of the equipment itself and be dynamically adjusted in combination with the material characteristic data. For example, when the system detects an increase in the hardness of the input material, the rotation speed of the crusher is automatically increased to ensure the crushing effect of the material. When the particle size of the material is small, the amplitude of the vibrating screen needs to be reduced to avoid a decrease in efficiency caused by over-screening. According to the material transfer relationship model and the equipment operation parameter table, a multi-equipment control network operation strategy is created to define the collaborative control rules of each equipment under different material conditions. For example, when the material humidity is high, the wind speed of the air separator is automatically reduced to prevent wet materials from adhering and affecting the separation effect. At the same time, the magnetic field strength of the magnetic separator is appropriately adjusted to maintain the accuracy of metal sorting. This control strategy not only includes the setting of equipment parameters but also dynamically evaluates the flow state of the material in the system. By adjusting the operation modes of each equipment, the overall efficiency of the system is optimized.

[0037] Optionally, the dynamic parameter adjustment subsystem 13 is specifically used for: Constructing a state observation model for each equipment based on the brick-mixed material characteristic data and the multi-equipment control network operation strategy, and calculating the equipment state estimation value based on the state observation model; Performing recursive least squares calculation on the operation data of each equipment to obtain the equipment dynamic characteristic parameters; Performing adaptive control rule analysis based on the equipment state estimation value and the equipment dynamic characteristic parameters to obtain the equipment control input quantity; Performing equipment characteristic matching on the equipment control input quantity to obtain equipment-specific control parameters; Calculating the control strategy adjustment coefficient according to the change rate of the brick-mixed material characteristic data to obtain the dynamic control gain; Performing performance evaluation on the equipment-specific control parameters and the dynamic control gain to obtain the equipment operation parameter set.

[0038] In this embodiment, according to the operating principles and characteristics of the crusher, vibrating screen, air separator, and magnetic separator in the system, corresponding state space models are established. The state space model can describe the dynamic behavior of the equipment, including the relationship between inputs, outputs, and system states. For a typical equipment state model, a discrete state space expression is used:

[0039]

[0040] where, is the state vector of the equipment at time (such as equipment rotation speed, vibration frequency, material throughput), is the control input vector (such as the crusher speed setting value, the air separation machine wind force size), is the output vector of the equipment (actual operating data, such as actual speed, actual power consumption), are the state, control and observation matrices of the system respectively, and represent the system noise and measurement noise respectively. This model can accurately describe the input and output of the equipment in a mathematical form, and quickly obtain the state estimation value of the equipment through matrix calculation. Calculate the equipment state estimation value based on the state observation model. The calculation of the state estimation value adopts the Kalman filter or extended Kalman filter method, and predicts the current true state of the equipment by combining the actual output data of the equipment and the state space model. For example, when the speed of the crusher is set to (rpm), and the actually detected speed is (rpm), predict the response delay and dynamic changes of the equipment under different material characteristics conditions through the state estimation model. After the calculation of the state estimation value is completed, perform the recursive least squares method calculation on the operation data of each equipment to obtain the dynamic characteristic parameters of the equipment. The core idea of the recursive least squares method is to dynamically adjust the system parameters each time new data is input, so that the sum of the squares of the errors between the model output and the actual observed value is minimized. The specific calculation process is:

[0041]

[0042]

[0043] Among them, is the dynamic characteristic parameter vector of the equipment (such as response time constant, gain coefficient), is the gain matrix, is the input data vector, is the covariance matrix, is the forgetting factor, which is used to balance the weights of historical data and new data. Through this step, when the material characteristics change or the equipment working conditions change, quickly adjust the dynamic characteristic parameters of the equipment, so that the control model of the equipment always remains accurate. Based on the equipment state estimation value and dynamic characteristic parameters, perform adaptive control rule parsing to calculate the equipment control input quantity. The core of the adaptive control rule is to dynamically adjust the control input when the equipment response is lagging and non-linearly changing, and keep the output of the equipment stable. For example, for a PID (Proportional-Integral-Derivative) controller, its control input quantity is expressed as:

[0044] Among them, is the equipment control input quantity (such as the crusher speed setting value), is the deviation (the difference between the set value and the actual value), , , are the proportional, integral, and derivative gain coefficients respectively. In adaptive control, these gain coefficients are dynamically adjusted according to the dynamic characteristic parameters of the device. For example, when the device load increases, the proportional gain is increased to enhance the response speed, or when the device runs unstably, the integral gain is increased to reduce the steady-state error. After the system calculates the device control input quantities, these input quantities are matched with the device characteristics to obtain the dedicated control parameters of the device. The process of device characteristic matching needs to combine the physical characteristics of the device, such as the maximum rotational speed limit of the crusher, the frequency adjustment range of the vibrating screen, the wind output limit of the air classifier, etc., and map the control input quantities to the allowable operation interval of the device. For example, for the crusher, its rotational speed should be between 500 and 3000 rpm. When the control input quantity exceeds this range, it is automatically limited to a reasonable interval:

[0045] Thus, it can be avoided that the device has operation failures or reduced efficiency due to too high or too low control inputs. The control strategy adjustment coefficient is calculated according to the change rate of the brick-concrete material characteristic data to obtain the dynamic control gain. When the material characteristics change rapidly, such as an increase in humidity or a decrease in hardness, the control gain is automatically adjusted so that the device can quickly respond to the material changes. The dynamic control gain is calculated by the following formula:

[0046] where, is the dynamic control gain, is the initial gain, is the adjustment coefficient, represents the change rate of the material characteristic data (such as the change speed of temperature, humidity, and particle size). The dedicated control parameters of the device and the dynamic control gain are evaluated for performance to obtain the device operation parameter set. The performance evaluation calculates the response speed, stability, and control accuracy of the device by comparing the error between the actual output and the model predicted output of the device. For example, by calculating the root mean square error of the tracking error :

[0047] where, is the actual output value, is the predicted output value, is the number of sampling points. When the RMSE is less than the set threshold, it indicates that the device control effect is good, and the current control parameters are saved into the device operation parameter set. Otherwise, the system will readjust the control rules and iteratively optimize the device parameters until a satisfactory control effect is achieved.

[0048] Optionally, the power distribution subsystem 14 further includes: A collaborative control module, configured to construct a global collaborative control protocol based on the device operation parameter set to obtain a device collaborative control equation; An equilibrium constraint module, configured to establish a material flow equilibrium constraint for the device collaborative control equation to obtain a device material balance equation and a system power constraint condition; A Lagrangian optimization module, configured to perform Lagrangian optimization according to the device material balance equation and the system power constraint condition to obtain a power constraint optimization objective function; A solution calculation module, configured to convert the power constraint optimization objective function into a quadratic programming problem for solution calculation to obtain an optimal control input set, where the optimal control input set includes the optimal control values of each device; A power optimization module, configured to perform power dynamic distribution calculation on each device based on the optimal control input set to obtain a device power distribution scheme, and perform power saturation characteristic curve processing on the device power distribution scheme to obtain a device power optimization control instruction.

[0049] In this embodiment, a global collaborative control protocol is constructed based on the device operation parameter set, thereby obtaining a device collaborative control equation. The device operation parameter set includes the working state data of each device such as crushers, vibrating screens, air separators, and magnetic separators, including parameters such as device rotation speed, amplitude, wind speed, and magnetic field strength. These parameters not only determine the working efficiency of the devices in the system but also directly affect the material flow state and separation effect. When constructing the global collaborative control protocol, the processing capabilities and material flow rates of each device are comprehensively considered to ensure the coordinated operation of the devices. For example, let be the control input of the th device, be the material flow rate of the device, and the collaborative control equation of the system is expressed as:

[0050] Among them, is the flow characteristic function of the device , are the dynamic characteristic parameters of the equipment, such as the response time, gain coefficient, etc. Through this relationship, the control inputs of each equipment are associated with the material flow rate. After obtaining the equipment collaborative control equation, the material flow rate balance constraint is established for this equation through the balance constraint module to form the equipment material balance equation and the system power constraint condition. The core of the material flow rate balance is to ensure the dynamic balance among the input, output, and processing amounts of materials in the system, that is, the total amount of materials entering each equipment should be equal to the sum of the output amount and the loss amount after the equipment processes. For example, for a typical sorting process, including a crusher, a vibrating screen, an air separator, and a magnetic separator, assuming the input and output flow rates of each equipment are , then the material balance equation is expressed as:

[0051] where, respectively represent the material loss amounts of each equipment during the processing. Through these material balance equations, the material flow relationship between the equipment is dynamically calculated to ensure the smooth flow transfer between the equipment under different working conditions. At the same time, the power constraint condition is established to ensure that the power consumption of each equipment is within the allowable range. Assume represents the power consumption of equipment , is the maximum power limit of the system, then the power constraint condition is expressed as:

[0052] where, is the total number of equipment in the system, represents the relationship between the equipment power consumption, the control input , and the equipment efficiency . Through these power constraint conditions, while ensuring the efficient operation of the equipment, excessive energy consumption is avoided, thereby improving the overall energy efficiency of the system. After establishing the material balance equation and the power constraint condition, the Lagrangian optimization module performs Lagrangian optimization according to these equations to obtain the power constraint optimization objective function. The Lagrangian optimization method combines the material flow rate and the balance constraint condition into a single objective function by introducing Lagrangian multipliers to achieve constraint optimization. The objective function is expressed as:

[0053] where, is the control input vector of all equipment, is the Lagrangian multiplier of the power constraint, is the Lagrangian multiplier of the material flow rate balance constraint, is the quantity of material flow constraints. By taking the partial derivative of the objective function and setting it equal to zero, the optimal control conditions of the equipment are obtained, thereby achieving the optimal power distribution of the system under the satisfaction of the constraint conditions. Through the solution calculation module, the power constraint optimization objective function obtained by the Lagrangian optimization module is transformed into a quadratic programming problem for solution. Quadratic programming is a method for minimizing a quadratic objective function under linear constraints and is suitable for dealing with the balance problem in power distribution. In this process, the objective function is discretized into a quadratic form:

[0054] subject to

[0055] where, is the quadratic term coefficient matrix (reflecting the incremental characteristics of power consumption), is the linear term coefficient vector (related to the power efficiency of the equipment), and are the constraint matrix and the constraint vector respectively. By solving this quadratic programming problem, an optimal control input set is obtained, which contains the optimal control values of each device, enabling the device to achieve the optimal operating state under the established power constraints. The power optimization module performs power dynamic distribution calculations on each device based on the optimal control values to generate a device power distribution plan. During the calculation process, the power output of each device is dynamically adjusted according to the real-time state and material characteristic data of the device. For example, when the material flow increases, more power is preferentially allocated to the crusher and the vibrating screen to ensure that the material processing speed matches the rhythm of the overall process. After obtaining the preliminary power distribution plan, the power saturation characteristic curve processing is performed on the plan to avoid excessive power consumption of the device under high load. The power saturation characteristic curve processing of the device is achieved by constructing the power conversion function of the device. For example, assuming that the relationship between the power of device and the control input is a non-linear saturation characteristic, which is expressed as:

[0056] where, is the maximum power output of the device, is the saturation characteristic function, is the adjustment coefficient. Through this non-linear function, the system smoothly limits the power output when the input exceeds a certain range, avoiding the device operating in a dangerous range. The power optimization module outputs device power optimization control instructions, and these instructions will be sent to the controllers of each device in real time to guide the device to automatically adjust the operating state under different material conditions, achieving the overall optimal power control of the system. For example, when the system detects that the metal separation efficiency of the magnetic separator decreases, the magnetic field intensity is automatically increased, and when the air separator processes more light materials, the wind speed is adjusted to improve the separation accuracy.

[0057] Optionally, the power optimization module is specifically configured to: Perform device importance analysis on the control values of each device in the optimal control input set to obtain a set of device importance weight coefficients; Perform preliminary power distribution calculation based on the set of device importance weight coefficients to obtain a device initial power distribution numerical table; Perform power balance adjustment calculation according to the device initial power distribution numerical table and the material transfer path and flow relationship between devices to obtain a device power dynamic balance scheme; Verify the total system power constraint for the device power dynamic balance scheme to obtain a power redistribution instruction, and trigger power redistribution when the device power dynamic balance scheme does not meet the total power constraint condition; Construct a device power saturation characteristic curve according to the conversion efficiency characteristics of each device to obtain a set of power conversion functions, and perform conversion calculation on the device power dynamic balance scheme through the set of power conversion functions to obtain a device power optimization control instruction.

[0058] In this embodiment, device importance analysis is performed on the control values of each device in the optimal control input set to determine the weight of the device in the entire system. Evaluate the contribution of each device to the overall operation efficiency and sorting effect of the system, and determine the importance weight coefficient of the device by analyzing the processing capacity of the device, the impact of the device on the bottleneck process, and the criticality of the device under specific material characteristic conditions. Let be the importance weight coefficient of the th device, then through the processing capacity of the device, the influence degree on the bottleneck process, and the criticality coefficient perform weighted calculation:

[0059] Among them, , , are weighted coefficients respectively, satisfying to ensure the normalization of the weight coefficient . This process can quantify the importance of each device, enabling the system to prioritize the power requirements of critical devices in subsequent power distribution. Perform preliminary power distribution calculation based on the set of device importance weight coefficients to obtain a device initial power distribution numerical table. The preliminary distribution process distributes the total system power according to the importance weight of the device, and the distribution formula is:

[0060] Among them, is the initial power value allocated to the th device, is the total available power of the system. Through the weight allocation method, it is ensured that high-priority devices can still maintain normal operation when resources are scarce, thus maintaining the overall stability and efficiency of the system. According to the initial power allocation value table of the devices and the material transfer paths and flow relationships among the devices, power balance adjustment calculations are carried out to obtain a dynamic power balance scheme for the devices. The core of power balance adjustment lies in ensuring that the material flow among the devices does not encounter bottlenecks due to uneven power distribution. For example, among the crusher, vibrating screen, air separator, and magnetic separator, assuming the material flow rates between the devices are , then the material flow relationship is expressed as:

[0061] To achieve the balance of material flow, the actual processing capacity of each device is calculated and the matching degree with the material flow is determined. By adjusting the device power such that:

[0062] where is the processing efficiency coefficient of the device. The system total power constraint verification is carried out on the dynamic power balance scheme of the devices to ensure that the power distribution of the devices does not exceed the maximum power output capacity of the system. If the sum of the power distributions in the dynamic balance scheme exceeds the system total power , that is:

[0063] then the system automatically triggers the power reallocation process. During the power reallocation process, the power requirements of high-importance weight devices are prioritized. For low-priority devices, the power consumption is reduced by lowering the operating frequency or entering the standby state. The specific implementation method is to reduce the control input of the device to reduce its power output ( is the device efficiency coefficient). At the same time, according to the conversion efficiency characteristics of each device, a device power saturation characteristic curve is constructed to obtain a set of power conversion functions. The power saturation characteristic curve is used to describe the efficiency change of the device under different power inputs. Usually, the device has lower efficiency in the low-power or high-power intervals and higher efficiency in the intermediate region. For example, for the air separator, the relationship between its power output and the control input is expressed by the saturation function as:

[0064] where is the maximum power of the device, is the saturation characteristic function, is the adjustment coefficient. When the control input is too high or too low, the actual power output of the device will tend to saturate, thus avoiding device overload or efficiency decline. After constructing the device power saturation characteristic curve, the power conversion function set is used to perform conversion calculations on the device power dynamic balance scheme to obtain the device power optimization control instruction. The conversion calculation maps the initially allocated power to the range actually acceptable by the device, for example, by restricting the input quantity to make the device operate in the high-efficiency range:

[0065] When finally outputting the device power optimization control instruction, the system not only adjusts the operating state of the device according to the current material processing requirements, but also dynamically monitors the health state and efficiency change of the device, and re-optimizes the power distribution scheme when necessary.

[0066] Optionally, the fine sorting and recycling system for construction waste brick and concrete materials further includes: A material flow prediction subsystem, which is used to distribute the device power optimization control instruction to each device controller for execution to obtain real-time device operating state data. The real-time device operating state data includes device rotation speed, amplitude, power, and material throughput; constructs a material processing prediction model based on the real-time device operating state data; inputs the brick and concrete material characteristic data as an external disturbance into the material processing prediction model for forward calculation to obtain the predicted state quantity; performs feedforward compensation calculation according to the difference between the predicted state quantity and the current actual system state to obtain the feedforward compensation quantity; performs processing mode judgment based on the feedforward compensation quantity and the brick and concrete material characteristic data to obtain a control mode switching signal, and the control mode switching signal is used for intelligent switching between the batch processing mode and the continuous operation mode; smooths the control mode switching signal and executes the corresponding control strategy to obtain the material flow prediction data, and the material flow prediction data includes the predicted values of the material flow rate, flow, accumulation state, and trend between each device in the sorting and recycling system; A correlation analysis subsystem, which is used to perform correlation analysis on the material flow prediction data and the real-time sorting index to generate an automatic optimization scheme for device parameters and an evaluation result of the device operating state.

[0067] In this embodiment, the device power optimization control instruction is distributed to each device controller for execution to obtain real-time device operating state data, including the key parameters of the device, such as the device rotation speed , amplitude , device power , and material throughput , where represents the These data are transmitted in real time to the central control unit via industrial Ethernet or fieldbus (such as Modbus, Profibus), enabling seamless connection between the equipment and the control system. Based on the real-time equipment operation status data, a material handling prediction model is constructed, which is used to simulate the material handling effect of the equipment under different working conditions. The material handling prediction model adopts the method of dynamic system modeling, such as the state space model, to predict the material flow by describing the relationship between the equipment input, output and internal state. The expression of the state space model is as follows:

[0068]

[0069] where, is the state vector of the equipment at time , for example, including equipment rotation speed, amplitude, material throughput, etc.; is the control input vector, including power optimization control instructions (such as wind speed adjustment, magnetic field strength setting, etc.); is the equipment output vector, representing the actual equipment operation status data; , , are the state, control and observation matrices respectively, used to describe the dynamic characteristics of the system; and are the system noise and measurement noise respectively, usually assumed to be Gaussian white noise to simulate the uncontrollable disturbances in the system. After the material handling prediction model is established, the brick-mixed material characteristic data is input into the model as an external disturbance for forward calculation to obtain the predicted state variables. The brick-mixed material characteristic data includes the particle size distribution , density , etc. During the forward calculation process, according to the current equipment state and material characteristics, the predicted equipment output is obtained through model calculation, such as the predicted material flow and equipment power . According to the difference between the predicted state variables and the current actual system state, feedforward compensation calculation is performed to obtain the feedforward compensation amount. The purpose of feedforward compensation calculation is to compensate for possible deviations by adjusting the control input before the prediction error occurs. For example, for the material throughput of the equipment, the feedforward compensation amount is expressed as:

[0070] where, is the actually measured material throughput, is the feedforward gain coefficient, by adjusting The size controls the response speed and stability of the control system. When the difference between the predicted state quantity and the actual state is large, the feedforward compensation quantity will automatically increase, enabling the system to quickly adjust the control parameters of the equipment. For example, increase the rotational speed of the crusher or increase the wind force of the air separator , to eliminate the imbalance phenomenon in material flow. After obtaining the feedforward compensation quantity, based on this compensation quantity and the characteristics data of the brick-concrete mixture, the processing mode is judged to obtain the control mode switching signal. The core of the processing mode judgment is that the system intelligently selects a suitable processing mode according to the current material characteristics (such as particle size and humidity) and the equipment operation status (such as load rate and processing speed), including batch processing mode and continuous operation mode. When the material characteristics fluctuate greatly or the equipment load is too high, the batch processing mode prevents equipment overload through intermittent operation; while when the material flow is stable, the continuous operation mode can maximize the processing capacity and energy efficiency of the equipment. The control mode switching signal is calculated through logical expressions:

[0071] wherein, represents the control mode switching signal, 1 represents switching to the batch processing mode, 0 represents maintaining the continuous operation mode, and are the switching thresholds of flow difference and humidity respectively. To avoid system instability caused by frequent mode switching, the control mode switching signal is smoothed and the corresponding control strategy is executed. The smoothing process uses a first-order lag filter or a moving average method, so that the mode switching signal changes gradually when approaching the threshold, avoiding equipment overload or tripping due to sudden control instructions. By executing the control strategy after smoothing, material flow prediction data is generated. These prediction data include the material flow velocity , flow rate , stacking state and trend prediction values (such as the flow rate change rate ) among the equipment in the sorting and regeneration system. After completing the material flow prediction, the correlation analysis subsystem uses these prediction data to perform correlation analysis with the real-time sorting indicators, generating an automatic optimization plan for equipment parameters and an evaluation result of the equipment operation status. The correlation analysis method uses a data-driven model (such as principal component analysis) or a rule-based expert system. By analyzing the relationship between material flow and key indicators such as sorting efficiency and energy consumption, the operation parameters of the equipment are automatically optimized, such as the updated values of the feedback gain matrix, feedforward compensation matrix, and equipment collaborative control weight. This automatic optimization plan can improve the working efficiency of the equipment and can also predict possible equipment failures in the equipment operation status evaluation. Calculate the current health status of the equipment through the equipment health index and take maintenance measures in advance. For example, when the actual wind speed of the air separator When the wind speed is lower than the predicted value by more than a certain threshold, the equipment load is automatically reduced or a maintenance alarm is triggered, thereby extending the service life of the equipment and ensuring the continuous and efficient operation of the system.

[0072] Optionally, the association analysis subsystem is specifically configured to: Hierarchically store the material flow prediction data and real-time sorting indexes to obtain a data experience library, which includes material characteristic data, equipment parameter data, and processing effect data; Calculate the comprehensive performance index based on the processing effect data in the data experience library to obtain the system performance evaluation value; Input the system performance evaluation value into the reinforcement learning algorithm for control strategy update calculation to obtain the optimized control strategy; Calculate the difference between the actual output and the model prediction output of each device to obtain the device residual vector, and perform wavelet decomposition on the device residual vector to obtain multi-band residual components; Calculate the equipment health index based on the multi-band residual components to obtain the equipment health status evaluation result, and trigger the corresponding maintenance or protection process when the equipment health status evaluation result is lower than the preset threshold; Periodically update the control model parameters according to the cumulative processing experience to obtain an automatic equipment parameter optimization plan, which includes the updated values of the feedback gain matrix, the feedforward compensation matrix, and the cooperative control weight.

[0073] In this embodiment, the material flow prediction data and real-time sorting indexes are hierarchically stored to establish a data experience library, which includes material characteristic data, and also includes equipment parameter data and processing effect data. The material characteristic data includes the particle size distribution of the material , density , humidity and other information; the equipment parameter data covers the operating status of the equipment, such as the equipment rotation speed , amplitude , power and the material throughput ; the processing effect data records the key performance indicators such as sorting efficiency , yield and energy consumption and other key performance indicators. Calculate the comprehensive performance index based on the processing effect data in the data experience library to obtain the system performance evaluation value. The system performance evaluation value is obtained by weighted comprehensive analysis of multiple processing effect data, and its calculation formula is expressed as: ; Wherein, represents the system performance evaluation value, is the sorting efficiency, is the yield, is the energy consumption, are the weighting coefficients, satisfying . The setting of the weighting coefficients is adjusted according to the system objectives. For example, when pursuing high output, the weight of is appropriately increased, while when energy conservation is prioritized, the proportion of is increased. By calculating the comprehensive performance index, the effectiveness of the current operation strategy is evaluated. The system performance evaluation value is input into the reinforcement learning algorithm to perform the control strategy update calculation and obtain the optimized control strategy. The reinforcement learning algorithm constructs an intelligent agent to execute the control strategy in the sorting system, observes the system state, and continuously adjusts the control strategy according to the actual feedback to maximize the system performance evaluation value . In the specific implementation, the deep Q-learning algorithm is adopted. Its core is to use the state-action value function to calculate the expected return of executing the action in the state . The update rule is:

[0074] where, is the learning rate, is the immediate reward, is the discount factor, is the new state reached after executing the action , and is the optimal action in the new state. Through repeated training, the system gradually optimizes the control strategy to make the operating states of each device close to the optimal, thereby improving the overall performance of the system. At the same time, the difference between the actual output and the model prediction output of each device is calculated to obtain the device residual vector. The device residual vector is used to measure the deviation between the actual operating state of the device and the prediction model. Its calculation formula is:

[0075] where, is the actual output of the device at time , such as the actually measured material flow or device power, and is the output value predicted by the model. By calculating the device residuals, the abnormal changes during the device operation are monitored in real time. For example, when the residuals are too large, it indicates that the device has wear, blockage, or sensor failure. The device residual vector is subjected to wavelet decomposition to obtain multi-band residual components. Wavelet decomposition is a time-frequency analysis method. By decomposing the signal into different frequency components, the low-frequency changes (such as the long-term performance degradation caused by device aging) and high-frequency changes (such as mechanical vibration or sudden failures) during the device operation are analyzed separately. The wavelet decomposition process is expressed as:

[0076] Among them, is the layer detail component (high-frequency component), is the layer approximation component (low-frequency component). Through multi-layer decomposition, the complex device operation signal is decomposed into multi-band signals that are easy to analyze. Based on the multi-band residual components, the device health index is calculated to obtain the device health status assessment result. The device health index realizes the quantitative assessment of the current state of the device by analyzing the energy distribution of the multi-band residual components, combining historical operation data and device design parameters. For example, the health index is calculated through multi-band energy as follows:

[0077] Among them, is the energy of the layer detail component, which is calculated by the sum of the squares of the wavelet coefficients. When the device health status assessment result is lower than the preset threshold, the system automatically triggers corresponding maintenance or protection processes, such as reducing the device load, adjusting the operation mode or issuing a maintenance alarm, to prevent greater losses caused by the device continuing to operate in an unhealthy state. According to the accumulated processing experience, the control model parameters are periodically updated to obtain an automatic optimization scheme for device parameters. This scheme includes updated values of the feedback gain matrix , the feedforward compensation matrix and the cooperative control weight . For example, the update of the feedback gain matrix is achieved by minimizing the sum of the squares of the residual as follows:

[0078] Among them, is the learning rate, represents the sensitivity of the device output to the control input. Through this adaptive adjustment, the control parameters are automatically optimized when the device characteristics change, realizing long-term stable and efficient operation.

[0079] In summary, through the multi-device collaborative control technology, the present invention achieves the optimal balance between sorting accuracy and energy efficiency. The system dynamically adjusts control parameters based on the real-time detection results of material characteristics, enabling devices such as crushers, vibrating screens, air separators, and magnetic separators to work efficiently in coordination. Even in the case of sudden changes in material composition, a stable sorting effect can still be maintained. The time-varying parameter adaptive control algorithm adopted by the system can accurately control the operating parameters of each level of equipment, ensuring a significant improvement in the sorting purity of brick-concrete materials. At the same time, through the power constraint optimization mechanism, the system can significantly reduce the overall energy consumption on the premise of ensuring the safe operation of the equipment. The feedforward control mechanism based on the virtual reference model enables the system to respond to material changes in advance, reduce adjustment time, and improve processing efficiency. The system also has self-learning optimization and equipment status self-diagnosis functions, optimizing control strategies by continuously accumulating processing experience, while monitoring the health status of the equipment, preventing failures, reducing maintenance costs, extending the service life of the equipment, and significantly improving the equipment utilization rate. Overall, the system solves the key problems in traditional construction waste treatment technologies and realizes the efficient, fine sorting and resource utilization of brick-concrete materials in construction waste.

[0080] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, systems, and units can refer to the corresponding processes in the foregoing system embodiments and will not be elaborated herein.

[0081] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the system described in each embodiment of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0082] The above is the case. The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or perform equivalent replacements for some of the technical features. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of each embodiment of the present invention.

Claims

1. A fine sorting and recycling system for construction waste brick and concrete materials, characterized in that, The system includes: A characteristic detection subsystem, which is used to detect the characteristics of the construction waste brick-concrete materials entering the sorting and regeneration system to obtain brick-concrete material characteristic data; A construction subsystem, which is used to construct an operation strategy for the multi-device control network of crushers, vibrating screens, air separators, and magnetic separators according to the brick-concrete material characteristic data; A dynamic parameter adjustment subsystem, which is used to dynamically adjust the parameters of each device in the sorting and regeneration system based on the brick-concrete material characteristic data and the multi-device control network operation strategy to obtain a set of device operation parameters; A power distribution subsystem, which is used to input the set of device operation parameters into an energy consumption optimization algorithm for power distribution to obtain a device power optimization control instruction.

2. The fine sorting and recycling system for construction waste brick and concrete materials according to claim 1, wherein The characteristic detection subsystem is specifically used for: Using an infrared spectrum sensor, a vision sensor, and a pressure sensor to collect multi-parameters of the construction waste brick-concrete materials entering the sorting and regeneration system to obtain original material sensing data; Transmitting and processing the original material sensing data to obtain data received by the central control unit; Performing feature extraction based on the data received by the central control unit to obtain a multi-dimensional material feature set, where the multi-dimensional material feature set includes material surface texture, color characteristics, pressure distribution, and spectral absorption curve; Performing characteristic analysis on the multi-dimensional material feature set to obtain basic material characteristic indicators, and performing time-series integration on the basic material characteristic indicators to obtain a material characteristic time-series data stream; Performing threshold comparison and data verification processing based on the material characteristic time-series data stream to obtain brick-concrete material characteristic data.

3. The fine sorting and recycling system for construction waste brick and concrete materials according to claim 1, wherein, The construction subsystem is specifically used for: Performing process layout analysis on crushers, vibrating screens, air separators, and magnetic separators according to the brick-concrete material characteristic data to obtain an equipment material flow diagram, which defines the material transfer path and flow relationship between each device; Dividing the equipment control hierarchy of the equipment material flow diagram to obtain a three-level control architecture, where the three-level control architecture includes a central controller, a process unit controller, and a device-level controller; Deploying a control network based on the three-level control architecture to obtain a basic architecture for the multi-device control network operation strategy, where the basic architecture for the multi-device control network operation strategy uses industrial Ethernet and supports real-time data interaction between devices; Performing material balance modeling on the basic architecture for the multi-device control network operation strategy to obtain a material transfer relationship model between devices; Configuring the operation parameters of each device based on the material transfer relationship model to obtain a device operation parameter table, where the device operation parameter table contains the working range and initial parameter setting values of each device; Creating a multi-device control network operation strategy according to the material transfer relationship model and the device operation parameter table, where the multi-device control network operation strategy defines the collaborative control rules of each device under different material conditions.

4. The fine sorting and recycling system for construction waste brick and concrete materials according to claim 1, characterized in that, The dynamic parameter adjustment subsystem is specifically used for: Constructing a state observation model for each device according to the brick-concrete material characteristic data and the multi-device control network operation strategy, and calculating the device state estimation value based on the state observation model; Performing recursive least squares calculation on the operation data of each device to obtain device dynamic characteristic parameters; Perform adaptive control rule parsing based on the device state estimation value and the device dynamic characteristic parameters to obtain the device control input quantity; Perform device characteristic matching on the device control input quantity to obtain device-specific control parameters; Calculate the control strategy adjustment coefficient according to the change rate of the brick-concrete material characteristic data to obtain the dynamic control gain; Perform performance evaluation on the device-specific control parameters and the dynamic control gain to obtain the device operation parameter set.

5. The fine sorting and recycling system for construction waste brick and concrete materials according to claim 1, characterized in that, The power distribution subsystem further includes: A cooperative control module for constructing a global cooperative control protocol based on the device operation parameter set to obtain a device cooperative control equation; A balance constraint module for establishing a material flow balance constraint on the device cooperative control equation to obtain a device material balance equation and a system power constraint condition; A Lagrangian optimization module for performing Lagrangian optimization according to the device material balance equation and the system power constraint condition to obtain a power constraint optimization objective function; A solution calculation module for converting the power constraint optimization objective function into a quadratic programming problem for solution calculation to obtain an optimal control input set, where the optimal control input set includes the optimal control values of each device; A power optimization module for performing power dynamic distribution calculation on each device based on the optimal control input set to obtain a device power distribution plan, and performing power saturation characteristic curve processing on the device power distribution plan to obtain a device power optimization control instruction.

6. The fine sorting and recycling system for construction waste brick and concrete materials according to claim 5, characterized in that The power optimization module is specifically used for: Perform device importance analysis on the control values of each device in the optimal control input set to obtain a device importance weight coefficient set; Perform preliminary power distribution calculation based on the device importance weight coefficient set to obtain a device initial power distribution numerical table; Perform power balance adjustment calculation according to the device initial power distribution numerical table and the material transfer path and flow relationship between devices to obtain a device power dynamic balance plan; Perform system total power constraint verification on the device power dynamic balance plan to obtain a power reallocation instruction, and trigger power reallocation when the device power dynamic balance plan does not meet the total power constraint condition; Construct a device power saturation characteristic curve according to the conversion efficiency characteristics of each device to obtain a power conversion function set, and perform conversion calculation on the device power dynamic balance plan through the power conversion function set to obtain a device power optimization control instruction.

7. The fine sorting and recycling system for construction waste brick and concrete materials according to claim 1, characterized in that, The construction waste brick-concrete material fine sorting and recycling system further includes: The material flow prediction subsystem is used to distribute the equipment power optimization control instructions to each equipment controller for execution to obtain real-time equipment operation status data, where the real-time equipment operation status data includes equipment speed, amplitude, power, and material throughput; construct a material processing prediction model based on the real-time equipment operation status data; input the brick-concrete material characteristic data as an external disturbance into the material processing prediction model for forward calculation to obtain a predicted state quantity; perform feedforward compensation calculation according to the difference between the predicted state quantity and the current actual system state to obtain a feedforward compensation quantity; perform a processing mode judgment based on the feedforward compensation quantity and the brick-concrete material characteristic data to obtain a control mode switching signal, where the control mode switching signal is used for intelligent switching between the batch processing mode and the continuous operation mode; smooth the control mode switching signal and execute corresponding control strategies to obtain material flow prediction data, where the material flow prediction data includes the predicted values of the material flow rate, flow, accumulation state, and trend between each equipment in the sorting and regeneration system; The correlation analysis subsystem is used to perform a correlation analysis on the material flow prediction data and real-time sorting indicators to generate an automatic equipment parameter optimization plan and an equipment operation status evaluation result.

8. The fine sorting and recycling system for construction waste brick and concrete materials according to claim 7, characterized in that, Specifically, the correlation analysis subsystem is used for: Hierarchically store the material flow prediction data and real-time sorting indicators to obtain a data experience library, where the data experience library includes material characteristic data, equipment parameter data, and processing effect data; Calculate a comprehensive performance index based on the processing effect data in the data experience library to obtain a system performance evaluation value; Input the system performance evaluation value into a reinforcement learning algorithm for control strategy update calculation to obtain an optimized control strategy; Calculate the difference between the actual output and the model prediction output of each equipment to obtain an equipment residual vector, and perform wavelet decomposition on the equipment residual vector to obtain multi-band residual components; Calculate an equipment health index based on the multi-band residual components to obtain an equipment health status evaluation result, and trigger corresponding maintenance or protection processes when the equipment health status evaluation result is lower than a preset threshold; Periodically update the control model parameters according to the cumulative processing experience to obtain an automatic equipment parameter optimization plan, where the automatic equipment parameter optimization plan includes the updated values of the feedback gain matrix, feedforward compensation matrix, and cooperative control weight.

Images