Real-time monitoring method for intelligent sorting system

Abstract

The invention relates to the technical field of renewable resource processing, and discloses a real-time monitoring method for an intelligent sorting system, which comprises the following steps of: acquiring a full-dimensional original data set by adopting a sensing module, and transmitting the full-dimensional original data set to a PLC (Programmable Logic Controller), a renewable resource recycling information platform and each cooperative system; a sorting decision control instruction is generated in combination with a preset renewable resource adaptation rule, and the sorting decision control instruction is issued to the execution module; performing renewable resource sorting operation execution according to the sorting decision control instruction and feeding back running state data; summarizing the data of each link to form a whole-process data set, carrying out abnormity judgment and early warning in combination with a preset core monitoring index, and carrying out abnormity grading processing execution; and summarizing the multi-dimensional operation data of the whole process of the preorder, and carrying out secondary processing and hierarchical storage to realize the full-life-cycle tracing of the renewable resources. According to the invention, through cooperation of the PLC and the multi-type sensing module, comprehensive acquisition of multi-dimensional information of renewable resources, cross-system cooperation and data sharing, abnormal grading processing and full-life-cycle tracing are realized.

Description

Technical Field

[0001] This invention relates to the field of renewable resource processing technology, and in particular to a real-time monitoring method for an intelligent sorting system. Background Technology

[0002] Recycling and utilizing renewable resources is a core element in practicing the concept of green development and promoting the circular economy. With the continuous improvement of industrial intelligence and environmental protection requirements, the industry has placed higher demands on the accuracy, efficiency, and informatization level of renewable resource sorting. Traditional renewable resource sorting mainly relies on manual operation, which is not only labor-intensive and involves a complex working environment, but is also easily affected by factors such as human experience and fatigue, resulting in unstable sorting quality, high risk of resource damage, and difficulty in achieving real-time monitoring and data recording of the entire sorting process.

[0003] While existing automated sorting systems have replaced manual labor to some extent, they still have many shortcomings: First, data collection dimensions are limited, focusing only on basic physical parameters such as resource size and weight, failing to capture comprehensive key information such as material type, surface defects, and recycling traceability. This results in insufficient basis for sorting decisions and difficulty in adapting to the diverse sorting needs of recyclable resources. Second, inter-system collaboration is poor, lacking standardized data interaction interfaces with platforms related to intelligent waste classification, environmental supervision, sanitation transportation, and processing scheduling, creating information silos and hindering cross-domain business collaboration and data sharing. Third, core algorithms lack adaptability, often employing fixed rules or simple control logic, lacking dynamic adaptation capabilities for recyclable resources with different characteristics, and lacking continuous optimization mechanisms, making it difficult to continuously improve sorting accuracy and efficiency. Fourth, remote control and full-chain traceability capabilities are weak, unable to achieve real-time monitoring and remote intervention in different locations, and the data from resource recycling to processing and utilization is fragmented, which is detrimental to quality control, responsibility traceability, and system optimization.

[0004] These problems severely restrict the overall efficiency and quality of recycling and utilization of renewable resources, and hinder the intelligent and information-based upgrading of diversified recyclable systems. Therefore, developing a real-time monitoring method for an intelligent sorting system for renewable resources with multi-dimensional data collection, cross-system collaborative linkage, dynamic algorithm optimization, and full-chain traceability has become an urgent need for the industry's development. Summary of the Invention

[0005] This invention provides a real-time monitoring method for an intelligent sorting system. By collaborating with a PLC and multiple types of sensing modules, and combining wireless communication and API interfaces, it enables comprehensive collection of multi-dimensional information on recyclable resources, cross-system collaboration and data sharing, anomaly classification and handling, and full lifecycle traceability.

[0006] This invention provides a real-time monitoring method for an intelligent sorting system, based on an intelligent sorting system composed of a PLC, a sensing module, an execution module, and a wireless communication module. The method includes: S1. The sensor module is used to collect physical parameters, omnidirectional images, quality parameters, material parameters and traceability data of the recycled resources as a full-dimensional raw data set, and the full-dimensional raw data set is transmitted to the PLC and transmitted to the recycled resource recycling information platform and various collaborative systems through the wireless transmission module. S2 and PLC preprocess the full-dimensional raw data set, load the fuzzy control algorithm and generate sorting decision control instructions in combination with the preset recyclable resource adaptation rules, send the sorting decision control instructions to the execution module, and at the same time synchronize the decision result data to the remote control terminal and each collaborative system; S3. The execution module performs the sorting operation of recycled resources according to the sorting decision control instruction, and feeds back the running status data to the PLC, remote control terminal, recycled resource recycling information platform and various collaborative systems. S4 and PLC aggregate data from each stage to form a full-process dataset, combine it with preset core monitoring indicators to determine and warn of anomalies, and link the execution modules to perform anomaly classification and processing according to preset anomaly level rules. S5. It summarizes multi-dimensional operational data from the entire process and performs secondary processing and hierarchical storage. It also enables bidirectional data exchange across systems through API interfaces to build a full lifecycle traceability system for renewable resources.

[0007] Furthermore, S1 specifically includes: S101. Connect and configure the PLC with the sensing module and the wireless communication module; the sensing module includes a laser displacement sensor, a vision sensor, a weight sensor, a material sensor, and a recycling traceability information acquisition module. S102, the laser displacement sensor collects the size and radial runout of the recycled resources as the physical parameters, the vision sensor collects the all-round image of the recycled resources and performs feature recognition, the weight sensor collects the actual mass data of the recycled resources, the material sensor identifies the material type of the recycled resources and outputs the material category identification signal, and the recycling traceability information collection module reads the traceability data of the recycled resources, finally forming a full-dimensional original data set. S103. Upload the full-dimensional raw data set to the PLC in real time through the preset wired industrial communication protocol, and push the data to the renewable resource recycling information platform in the form of encrypted data packets through the 4G / 5G wireless communication module. S104. Transmit the full-dimensional raw data set to various collaborative systems through the pre-configured API interface, including the intelligent waste sorting platform, the smart sanitation data collection system, the smart environmental protection big data integrated service system, and the environmental cloud platform.

[0008] Furthermore, S2 specifically includes: S201, the PLC receives the full-dimensional raw data set and preprocesses it, specifically including: using the moving average method for noise filtering; identifying and removing abnormal data from the weight sensor and vision sensor outputs that exceed reasonable ranges based on the 3σ principle; converting physical parameters of different dimensions to the [0,1] interval through normalization; and simultaneously converting the traceability information and material type data according to the preset data format requirements of each collaborative system to generate data copies adapted to each collaborative system. S202. Load the fuzzy control algorithm program adapted to the recycling resource sorting scenario into the PLC, configure the input fuzzy subset, clarify the boundary range of each subset, define the linguistic values ​​of recycling resource category, size, weight, and material type, and match the corresponding membership function for each linguistic value. Establish a fuzzy inference rule library for recycling resources that combines the difficulty of recycling resource dismantling, processing and utilization adaptability, and environmental compliance requirements. S203. The preprocessed full-dimensional original dataset is used as the input variable of the fuzzy controller. Fuzzy decision calculation is performed to generate precise control quantities as sorting decision control instructions. S204. The PLC sends the sorting decision control instructions to the execution module in real time, pushes the decision results to the remote control terminal through the wireless communication module, and through the pre-configured API interface, extracts and adapts the data of the decision results according to the needs of each collaborative system, and then synchronizes them to each collaborative system to achieve cross-system business collaboration.

[0009] Furthermore, S203 specifically includes: Substitute the preprocessed full-dimensional original data set into the preset membership function to calculate the membership degree of each input variable corresponding to different linguistic values; based on the fuzzy inference rule base, the MAX-MIN synthetic inference method is used to perform a minimum operation on the membership degree of the premise of each rule to obtain the trigger strength of the rule, and then perform a maximum operation on the trigger strength of all rules to finally obtain the membership degree of each linguistic value of the output variable. By using the centroid defuzzification method, the centroid coordinates of the output fuzzy set are calculated and transformed into precise control quantities, including key control parameters such as the sorting channel number corresponding to the recycled resource, the robotic arm gripping angle, the gripping force threshold, the dismantling station number, and the processing flow indicator. While generating the control quantities, the recycling traceability information of the recycled resource is associated and bound with the control parameters to form a complete data chain of sorting control instructions and traceability information.

[0010] Furthermore, S3 specifically includes: S301. Connect and configure the PLC with the execution module, wherein the execution module includes a multi-axis manipulator, cylinders, servo motors, conveyor belts, and linkage control components for disassembly and processing units; S302. The execution module receives and parses the sorting decision control instructions issued by the PLC as local control instructions, and receives instructions sent by the remote control terminal as remote instructions. It determines the conflict between local control instructions and remote instructions according to a preset priority mechanism. Specifically, if it is an emergency intervention instruction, the execution of the local instruction is immediately suspended, and the remote instruction is responded to first. If it is a normal parameter adjustment instruction, it is determined whether it can be adjusted in real time based on the current sorting progress. If it does not affect the sorting action being executed, it takes effect directly. If it may cause the action to be abnormal, it waits for the current action to be completed before executing. S303, the multi-axis manipulator of the execution module starts a preset adaptive robust control algorithm to adaptively adjust the gripping strategy according to the parsed sorting decision control command; the cylinder drives the piston to extend and retract according to the set stroke to complete the sorting channel switching and recyclable resource positioning and clamping; the servo motor adjusts the speed according to the sorting decision control command to drive the conveyor belt to run at the appropriate speed; the disassembly unit and the processing unit trigger the disassembly / processing action start signal through the photoelectric sensor at the workstation according to the sorting decision control command, so as to realize seamless collaboration between sorting and subsequent processes; S304. The built-in sensors of the execution module collect and transmit the operating status data to the PLC in real time. The PLC sorts, classifies, and displays the received operating status data in real time. The operating status data is also transmitted to the remote control terminal, the renewable resource recycling information platform, and various collaborative systems via the wireless communication module.

[0011] Furthermore, S4 specifically includes: S401 and PLC aggregate data from each stage, including the data collected in S1, the sorting decision data in S2, and the operating status data in S3. At the same time, they receive feedback data from the renewable resource recycling information platform and various collaborative systems to form a full-process dataset. Based on the full-process dataset, core monitoring indicators are calculated according to preset formulas, including performance indicators, process progress indicators, traceability integrity indicators, and equipment and environmental protection indicators. S402 and PLC preset anomaly judgment thresholds, including performance thresholds, equipment operating parameter thresholds, environmental protection thresholds, and data integrity thresholds. They extract various data from the entire process dataset in real time and compare them one by one with the anomaly judgment thresholds. They also combine the judgment logic of instantaneous exceedance and continuous verification to make anomaly judgments. At the same time, the intelligent environmental protection big data integrated service system synchronously verifies environmental protection parameters, forming a dual anomaly detection mechanism of local detection + collaborative system cross-verification. S403. When the dual anomaly detection mechanism determines an anomaly, it triggers an audible and visual alarm and displays the anomaly type, occurrence time, associated equipment number, batch number of the recycled resources involved, current positioning deviation value, and specific values ​​of the environmental parameters exceeding the standard; it pushes the anomaly data to the remote control terminal and various collaborative systems for cross-system collaborative alarm, while the recycled resource recycling information platform records all anomaly information. S404. Determine the abnormal level of the abnormal data according to the preset abnormal level rules, and process it in stages according to the abnormal level; wherein, the abnormal level includes minor abnormality, serious abnormality, and emergency abnormality. When there is a minor abnormality, the PLC automatically starts an emergency adjustment command. When there is a serious abnormality, the PLC immediately sends a command to suspend the operation of the recyclable resource sorting line and lock the execution module. When there is an emergency abnormality, the PLC immediately triggers the system emergency shutdown, cuts off the power supply of the execution module, and starts the on-site safety warning device.

[0012] Furthermore, in step S401, the core monitoring indicators are calculated according to a preset formula based on the full-process dataset, specifically including: Performance metrics: Sorting accuracy = Qualified sorted quantity / Total sorted quantity × 100%, System response time = Time elapsed from data collection trigger to execution completion, Resource damage rate = Damaged resource quantity / Total sorted quantity × 100%, Production cycle time = Number of sorted resources per unit time; Process progress indicators include: recycled resource recovery volume, current batch sorting completion rate, dismantling efficiency, and processing utilization rate. Specifically, dismantling efficiency = (number of dismantled items / number of sorted items) × 100%, and processing utilization rate = (number of qualified processed items / number of dismantled items) × 100%. Traceability integrity index: Traceability information integrity rate = Number of resources with no missing information / Total number of resources × 100%; Equipment and environmental indicators: operating load of execution modules and compliance rate of environmental parameters, where the compliance rate of environmental parameters = number of environmentally compliant resources / total number of resources × 100%.

[0013] Furthermore, S5 specifically includes: S501. Summarize the full-dimensional operation data, including the full-process processing data of steps S1, S2, S3, and S4. All data are associated and bound by timestamp-resource unique identifier-stage number. The full-dimensional operation data is then processed and hierarchically stored and managed. S502. Through the preset API interface, realize the two-way data flow between various collaborative systems and PLC, and the information platform for recycling and utilization of renewable resources, clarify the core dimensions of the whole chain traceability data, so as to form a whole life cycle traceability system for renewable resources, including recycling, sorting, dismantling and processing, and the data of each dimension is bound to the unique identifier of the resource.

[0014] The present invention also provides a real-time monitoring device for an intelligent sorting system, based on the real-time monitoring method for an intelligent sorting system described above, the device comprising: The acquisition unit is used to acquire physical parameters, omnidirectional images, quality parameters, material parameters and traceability data of the recycled resources using the sensing module as a full-dimensional raw data set, and to transmit the full-dimensional raw data set to the PLC, and to the recycled resource recycling information platform and various collaborative systems through the wireless transmission module; The generation unit is used by the PLC to preprocess the full-dimensional raw data set, load the fuzzy control algorithm and generate sorting decision control instructions in combination with the preset recyclable resource adaptation rules, send the sorting decision control instructions to the execution module, and synchronize the decision result data to the remote control terminal and various collaborative systems. An execution unit is used by the execution module to perform the sorting operation of recycled resources according to the sorting decision control instructions, and to feed back the running status data to the PLC, remote control terminal, recycled resource recycling information platform and various collaborative systems. The early warning unit is used by the PLC to aggregate data from each stage to form a full-process dataset, combine it with preset core monitoring indicators to make anomaly judgments and issue early warnings, and link the execution module to perform anomaly classification processing according to preset anomaly level rules. The traceability unit is used to summarize multi-dimensional operational data from the entire preceding process, perform secondary processing and hierarchical storage, and achieve cross-system bidirectional data exchange through API interfaces to build a traceability system for the entire life cycle of renewable resources.

[0015] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described method.

[0016] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the above-described method.

[0017] The beneficial effects of this invention are as follows: This invention, through the collaborative work of a programmable logic controller and multiple types of sensing modules, combined with wireless communication technology and a standardized API interface adaptation scheme, achieves comprehensive collection and synchronous processing of multi-dimensional information such as physical parameters, material types, and recycling traceability of recycled resources. It effectively compensates for the shortcomings of traditional sorting systems with their single data collection dimension, providing sufficient basis for accurate sorting decisions. The constructed full life cycle traceability system for recycled resources realizes data traceability throughout the entire process from recycling to processing and utilization, providing strong support for quality control and accountability. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of a method flow according to an embodiment of the present invention.

[0019] Figure 2 This is a schematic diagram of the device structure according to an embodiment of the present invention.

[0020] Figure 3 This is a schematic diagram of the internal structure of a computer device according to an embodiment of the present invention.

[0021] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0023] like Figure 1 As shown, the present invention also provides a real-time monitoring method for an intelligent sorting system, based on the intelligent sorting system composed of a PLC, a sensing module, an execution module, and a wireless communication module. The method includes: S1. The sensing module collects physical parameters, omnidirectional images, quality parameters, material parameters, and traceability data of the recycled resources as a full-dimensional raw data set, and transmits the full-dimensional raw data set to the PLC, and also transmits it to the recycled resource recycling information platform and various collaborative systems through the wireless transmission module. Specifically, this includes: S101. Connect and configure the PLC with the sensing module and the wireless communication module; the sensing module includes a laser displacement sensor, a vision sensor, a weight sensor, a material sensor, and a recycling traceability information acquisition module. Using a programmable logic controller (PLC) as the control core, the PLC is connected and configured with sensing modules and wireless communication modules. The PLC's diagnostic functions are used to verify the signal output stability and data acquisition response capabilities of each part of the sensing module, ensuring there are no hardware faults or connection anomalies. Simultaneously, 4G / 5G wireless communication modules are configured, and the network registration and signal strength verification process for the wireless modules is initiated. Signal quality testing tools are used to confirm that the packet loss rate and latency of the wireless link meet real-time transmission requirements, ensuring wireless communication stability. Furthermore, dedicated API interfaces are designed and configured for collaborative systems such as the intelligent waste sorting platform, smart sanitation data acquisition system, smart environmental protection big data integrated service system, and environmental cloud platform. The communication protocols used by the interfaces (such as RESTful and JSON-RPC) are clearly defined, interface permission authentication mechanisms are set up (such as token verification and IP whitelist binding), and a data field mapping table between each system is established to ensure that the collected data and the data format and field definitions of the collaborative systems are fully compatible, eliminating data interaction barriers.

[0024] After recycled resources are transported to the designated inspection station via the sorting line conveyor belt at a preset transmission speed, the photoelectric sensor placed at the station entrance detects the workpiece signal and immediately sends a data acquisition trigger command to the PLC. After receiving the command, the PLC synchronously sends start signals to the laser displacement sensor, vision sensor, weight sensor, material sensor, and recycling traceability information acquisition module through the wired industrial communication link. This enables the coordinated linkage of multiple sensing modules, ensuring that each module starts data acquisition at the same time node and guarantees the spatiotemporal consistency of the data.

[0025] S102, Data Acquisition: Laser displacement sensors collect key physical parameters of recycled resources at high frequency, focusing on acquiring data such as dimensional specifications (such as diameter, length, and thickness) and radial runout, and capturing subtle dimensional differences in parts. A visual sensor captures a 360-degree image of the recycled resources. After the image data is transmitted to the visual processing system, a deep learning algorithm based on a convolutional neural network (CNN) is launched. The algorithm sequentially performs convolution operations (extracting low-level texture features), pooling operations (reducing data dimensionality and retaining key features), and fully connected operations (integrating multi-layer feature information). The extracted features are mapped to probability values ​​corresponding to recycled resource categories, surface defects (such as damage and stains), and identification barcodes through the Softmax function, thereby achieving quantitative identification of feature information. The weight sensor collects actual quality data of regenerated resources through pressure sensing elements. During the collection process, a data stabilization filtering mechanism is activated to eliminate instantaneous fluctuation interference and output stable quality parameters. Material sensors identify the material type of recycled resources (such as metal, plastic, paper, glass, fabric, etc.) and output a material category identification signal; The recycling traceability information collection module automatically reads and records traceability data such as the recycling batch number, recycling time, source area, recycling point number, and transport vehicle information of the recycled resource by connecting with the data of the recycling registration system. Finally, it forms a full-dimensional raw data set of physical parameters, material type, and traceability information.

[0026] S103. Upload the full-dimensional raw data set to the PLC in real time through the preset wired industrial communication protocol, and push the data to the renewable resource recycling information platform in the form of encrypted data packets through the 4G / 5G wireless communication module. S104. Transmit the full-dimensional raw data set to various collaborative systems through the pre-configured API interface, including the intelligent waste sorting platform, the smart sanitation data collection system, the smart environmental protection big data integrated service system, and the environmental cloud platform.

[0027] S2 and PLC preprocess the full-dimensional raw data set, load a fuzzy control algorithm, and generate sorting decision control instructions based on preset recyclable resource adaptation rules. These instructions are then sent to the execution module and simultaneously synchronized to the remote control terminal and various collaborative systems. Specifically, this includes: S201 and PLC receive the full-dimensional raw data set and use the moving average method to filter noise from the high-frequency data collected by the laser displacement sensor to eliminate random errors caused by environmental vibration and electromagnetic interference. Based on the 3σ principle (or a preset outlier judgment threshold), they identify and remove abnormal data from the weight sensor and vision sensor that exceed the reasonable range. Through normalization processing, they convert physical parameters such as size and weight of different dimensions to the [0,1] interval to unify the data format and range. At the same time, according to the preset data format requirements (such as field name, data type, and precision retention bits) of various collaborative systems such as the intelligent waste classification platform and the smart sanitation data collection system, they perform targeted format conversion on traceability information, material type and other data to generate data copies adapted to each system. The information platform for recycling and utilizing renewable resources simultaneously receives raw data and pre-processed data transmitted wirelessly. It classifies and stores the data according to a hierarchical structure of resource category, recycling batch, and collection time, and adds information management tags (such as pending decision, verified) to facilitate subsequent traceability and analysis.

[0028] S202. Load the fuzzy control algorithm program adapted to the recycling resource sorting scenario into the PLC. First, configure the input fuzzy subsets (set the number of subsets according to the recycling resource sorting accuracy requirements, such as material category subsets, size specification subsets, weight range subsets, etc.), and clarify the boundary range of each subset (e.g., the metal material subset corresponds to a specific signal range output by the material sensor, and the large size subset corresponds to a preset diameter / length threshold range); define the linguistic values ​​of input variables such as recycling resource category, size, weight, and material type (e.g., light, medium, heavy, small size, medium size, large size, qualified, light). (Minor defects, severe defects, etc.), and match a corresponding membership function (such as triangular membership function, trapezoidal membership function, select the appropriate type according to variable characteristics) for each linguistic value; establish a fuzzy reasoning rule base specifically for recycled resources, and formulate the rule content based on factors such as the difficulty of dismantling recycled resources, the adaptability of processing and utilization, and environmental compliance requirements (for example, if the resource is metal material + medium size + no defects, it is sorted to the A-type dismantling station; if the resource is plastic material + small size + minor defects, it is sorted to the B-type processing channel), to ensure that the rules cover the main types and scenarios of recycled resources and that there are no logical conflicts.

[0029] S203. Using the pre-processed parameters such as size, weight, material type, and defect level of the recycled resources as input variables for the fuzzy controller, and substituting them into a preset membership function, calculate the membership degree μ corresponding to different linguistic values ​​for each input variable (e.g., the membership degree of a certain plastic resource's weight parameter for a lightweight linguistic value is 0.8, and the membership degree for a medium-weight linguistic value is 0.2). Based on the fuzzy inference rule base, the MAX-MIN synthetic inference method is used to minimize the membership degree of the preconditions of each rule to obtain the trigger strength of that rule. Then, the trigger strengths of all rules are maximized to finally obtain the membership degree μ of each linguistic value of the output variable (sorting action) (e.g., the membership degree for sorting to the B-type processing channel is 0.7). The membership degree of sorting to the C-class processing channel is 0.3); through the centroid defuzzification method, the centroid coordinates of the output fuzzy set are calculated and transformed into precise control quantities y*, including the sorting channel number corresponding to the recycled resource, the robotic arm gripping angle (e.g., 30°, 45°), the gripping force threshold (set according to material type, e.g., 0.5-1N for plastic materials, 2-3N for metal materials), the dismantling station number, the processing flow identification, and other key control parameters; while generating the control quantities, the recycling traceability information (recycling batch, source area) of the recycled resource is associated and bound with the control parameters to form a complete data chain of sorting control instructions - traceability information, ensuring that every sorting decision can be traced back to the specific resource individual.

[0030] The S204 and PLC generate precise sorting control instructions and send them to the execution module in real time. At the same time, they transmit the decision results (including control parameters, related traceability information, and key data on the basis of the decision) to remote control terminals (such as monitoring center computers and mobile management APPs) through 4G / 5G wireless communication modules. This allows managers to remotely monitor the decision-making process in real time and intervene manually when necessary. Through pre-configured API interfaces, the decision results are extracted and formatted according to the needs of each collaborative system, and then synchronized to the smart environmental protection big data integrated service system (for real-time verification of environmental compliance) and the environmental cloud platform (for processing capacity matching and scheduling) to achieve cross-system business collaboration. In addition, the PLC transmits decision data (such as sorting category, current resource processing progress), core performance indicators (real-time sorting accuracy, current batch sorting efficiency), and the proportion of recyclable resource categories to the human-machine interface for display, so that on-site operators can view the decision results and system operation status and complete on-site feedback of the decision results.

[0031] S3. The execution module performs recycled resource sorting and process coordination according to the sorting decision control instructions, and feeds back the operating status data to the PLC, the recycled resource recycling information platform, and various collaborative systems; specifically including: S301. Connect and configure the PLC and the execution module. The execution module includes a multi-axis robot, cylinder, servo motor, conveyor belt, and linkage control components for the disassembly unit and processing unit. At the same time, detect the accuracy of the signal feedback from the built-in sensors (position sensor, force sensor, limit switch) of the execution module to ensure that there are no mechanical jamming, electrical faults, or other problems. Based on the sorting decision requirements and the characteristics of recycled resources, set the conveyor belt speed, the linkage trigger threshold of the disassembly station, and the capacity matching parameters of the processing unit.

[0032] S302. The execution module receives and parses the sorting decision control instructions issued by the PLC as local control instructions. The instructions include core information such as sorting channel number, robot gripping angle / force threshold, cylinder extension stroke, servo motor speed adjustment parameters, disassembly station number, and processing flow direction identifier. The execution module decodes and parses the received instructions, extracts key action parameters, and converts them into drive signals that can be recognized by each execution module. The execution module receives instructions sent by the remote control terminal as remote instructions (such as manually adjusting the gripping force, pausing sorting urgently, modifying the sorting channel allocation, etc.). It determines the conflict between local control instructions and remote instructions according to a preset priority mechanism. Specifically, if it is an emergency intervention instruction (such as emergency shutdown due to equipment failure), the execution of the local instruction is immediately suspended, and the remote instruction is responded to first. If it is a routine parameter adjustment instruction, it is determined whether it can be adjusted in real time based on the current sorting progress. If it does not affect the sorting action being executed, it takes effect directly. If it may cause abnormal action, it waits for the current action to be completed before execution.

[0033] S303, Execution of actions in each part of the execution module: The multi-axis robot arm initiates an adaptive robust control algorithm based on the analyzed control commands. Based on the established dynamic model (including joint inertia matrix, Coriolis force and centripetal force matrix, and gravity matrix), and combined with the material type and weight parameters of the recycled resources, it adaptively adjusts the gripping strategy. For example, for easily damaged materials such as plastics and fabrics, the gripping force threshold is set in a low range, and a flexible gripping method is adopted to avoid surface scratches or structural damage. The joint motion trajectory is adjusted according to the gripping angle in the command, and the actual position is fed back in real time through position sensors. The actual position is compared with the expected trajectory to dynamically compensate for positioning deviations.

[0034] After receiving the command, the cylinder drives the piston to extend and retract according to the set stroke to complete auxiliary actions such as switching the sorting channel and positioning and clamping the recycled resources.

[0035] The servo motor adjusts its speed according to the command, drives the conveyor belt to run at the appropriate speed, and coordinates with the grasping and transferring rhythm of the robotic arm to ensure the smooth transmission of recyclable resources in the sorting channel. At the same time, the speed sensor monitors the motor's operating status in real time to avoid transmission abnormalities caused by overspeed or speed fluctuations.

[0036] After receiving the coordination instruction, the disassembly unit and the processing unit trigger the disassembly / processing action start signal through the photoelectric sensor at the workstation, realizing seamless coordination between sorting and subsequent processes; during the execution of the action, the progress information is fed back to the PLC in real time, forming a closed loop of the process.

[0037] S304. The built-in sensors of the execution module (position sensor, force sensor, speed sensor, limit switch) collect real-time operating status data. Specifically, the position sensor records the actual position coordinates and positioning accuracy error of the robot and cylinder; the force sensor monitors the real-time value of the robot's gripping force and determines whether it exceeds the threshold; the speed sensor feeds back the actual speed of the servo motor; the limit switch confirms the position of the cylinder and conveyor belt; at the same time, the status sensors of the disassembly unit and processing unit collect data such as equipment operating load, process completion status, and fault warning signals. All operating status data are summarized by the execution module and transmitted to the PLC.

[0038] The PLC organizes, categorizes, and displays the received operating status data in real time, including displaying information such as the operating parameters of the execution module, process progress, and equipment load in the form of numbers, curves, and charts, so that on-site operators can monitor in real time. The system transmits operational status data to the remote control terminal and the renewable resource recycling information platform via a wireless communication module, ensuring that remote management personnel can monitor the system's operational status in real time. The status data is then filtered and formatted according to the needs of each collaborative system via an API interface, and synchronized to each collaborative system to achieve cross-system status linkage, providing data support for subsequent scheduling and optimization.

[0039] S4. Issue early warnings for the operational status data based on preset core monitoring indicators, and handle or link the execution module to suspend operations according to preset anomaly levels, recording anomaly tracing information; specifically including: S401 and PLC aggregate data from each stage, including physical parameters, material types, and traceability information of recycled resources collected by S1; sorting decision data (such as sorting categories and control parameters) from S2; and operating status data of execution modules (such as robot positioning accuracy, motor speed, and process progress) and collaborative status data of dismantling / processing units from S3. At the same time, they receive feedback data (such as environmental compliance verification results and capacity matching status) from the recycled resource recycling information platform, the smart environmental protection big data integrated service system, and the environmental cloud platform, forming a full-process dataset.

[0040] Based on the full-process dataset, core monitoring indicators are calculated according to preset formulas, including performance indicators, process progress indicators, traceability integrity indicators, and equipment and environmental protection indicators, specifically including: ①Performance indicators: Sorting accuracy rate = number of qualified sorted items / total number of sorted items × 100%; System response time = time from triggering data collection to completing the action; Resource damage rate = number of damaged resources / total number of sorted items × 100%; Production cycle time = number of sorted resources per unit time. ② Process progress indicators: Recyclable resource recovery volume, current batch sorting completion rate, dismantling efficiency = dismantled quantity / sorted quantity × 100%, processing utilization rate = processed qualified quantity / dismantled quantity × 100%; ③ Traceability integrity index: Traceability information integrity rate = Number of resources with no missing information / Total number of resources × 100%; ④ Equipment and Environmental Indicators: The environmental parameter compliance rate is calculated as follows: Execution module operating load = (Number of environmentally compliant resources / Total number of resources) × 100%. The number of environmentally compliant resources is derived from multi-dimensional detection, cross-system verification, and comprehensive judgment statistics throughout the entire process of recycling resource sorting and processing. Specifically, the material sensors and component detection sensors in the sensing module first collect core environmental attribute data such as material composition, harmful element content, and pollution residue of recycled resources in real time. Then, the pollutant emission sensors deployed in the dismantling and processing unit capture data on pollutant emissions such as waste gas, wastewater, and dust during the processing. Subsequently, the system connects to the intelligent environmental protection big data integrated service system to synchronize the latest environmental compliance standards and complete the cross-verification of the above data. Finally, the PLC and the recycled resource recycling information platform summarize all detection data and verification results, compare them with preset environmental thresholds, and determine whether a single recycled resource is fully compliant in both its own environmental attributes and environmental emissions during the processing. Then, all compliant resources are counted and statistically analyzed to generate the final number of environmentally compliant resources.

[0041] S402, PLC preset anomaly judgment thresholds, including performance thresholds, equipment operating parameter thresholds, environmental protection thresholds, and data integrity thresholds, specifically including: ① Performance thresholds (such as sorting accuracy rate below 98%, system response time exceeding 500ms, resource damage rate above 0.5%); ② Equipment operating parameter thresholds (such as robot positioning deviation exceeding ±0.05mm, servo motor speed fluctuation range exceeding ±5%, cylinder extension / retraction response delay exceeding 20ms); ③ Environmental protection thresholds (such as pollutant emission concentration exceeding national standards during resource processing, and material harmful component exceeding the standard threshold); ④ Data integrity thresholds (such as the number of missing traceability information fields exceeding 2).

[0042] The PLC extracts various data points from the entire process dataset in real time and compares them one by one with preset thresholds. It uses a judgment logic of instantaneous exceedance + continuous verification to determine anomalies. For example, for instantaneous fluctuation data (such as motor speed), it is only judged as an anomaly if it exceeds the threshold for three consecutive scanning cycles to avoid false alarms. For key indicators (such as sorting accuracy and environmental parameters), anomalies are determined in real time. At the same time, the intelligent environmental protection big data integrated service system verifies environmental parameters synchronously, forming a dual anomaly detection mechanism of PLC local detection + collaborative system cross-verification.

[0043] S403. When the dual anomaly detection mechanism determines an anomaly, it triggers an audible and visual alarm and displays the anomaly type, occurrence time, associated equipment number, batch number of the recycled resources involved, current positioning deviation value, and specific values ​​of the environmental parameters exceeding the standard, so as to facilitate on-site personnel to quickly locate the problem.

[0044] Abnormal data is pushed to remote control terminals to ensure timely response from remote management personnel, and to various collaborative systems, including the Smart Environmental Protection Big Data Integrated Service System (triggering environmental compliance warnings and marking batches of resources exceeding standards), the Environmental Cloud Platform (recording equipment anomaly logs and linking them to production capacity scheduling plans), and the Smart Sanitation Data Acquisition System (suspending subsequent transfer and scheduling of the batch of resources), to achieve cross-system collaborative alarms and avoid risks in process connection; at the same time, the renewable resource recycling information platform automatically records all abnormal information, including system operation data before and after the anomaly occurred, and the triggered rule thresholds, forming an unalterable abnormal alarm log.

[0045] S404. Determine the anomaly level of the abnormal data according to the preset anomaly level rules, wherein the anomaly level rules divide the anomalies into three levels based on the scope of impact and severity: ① Minor anomalies (such as excessive positioning deviation of a single robot arm, missing traceability information, or slight fluctuations in instantaneous production cycle) do not affect the overall process and product quality; the PLC automatically initiates emergency adjustment commands, such as controlling the robot arm to reposition, supplementing traceability information collection, and dynamically adjusting the conveyor belt speed, without the need for manual intervention; after adjustment, real-time monitoring is conducted to check whether the indicators return to normal. If they return to normal after 3 consecutive scanning cycles, the alarm is lifted; otherwise, it is upgraded to a serious anomaly.

[0046] ② Serious anomalies (such as sensor signal interruption, execution module jamming, damage to 3 consecutive resources, or slight exceedance of environmental parameters) may lead to a decrease in sorting accuracy or process interruption; the PLC immediately sends an instruction to suspend the operation of the recycled resource sorting line, lock the execution module (such as stopping the robot arm and stopping the conveyor belt), and simultaneously link the dismantling unit and processing unit to suspend operations to prevent unqualified resources from flowing into subsequent processes; the anomaly handling process is automatically written into the recycled resource recycling information platform, and a traceability record is formed by associating it with the corresponding resource batch.

[0047] ③ Emergency anomalies (such as equipment malfunction and fire risk, serious exceedance of environmental parameters, or large accumulation of resources clogging the sorting line) directly threaten production safety and environmental compliance. The PLC immediately triggers an emergency system shutdown, cuts off the power supply to the execution module, and activates on-site safety warning devices (such as emergency lights and high-decibel alarms); sends emergency rescue notices to relevant personnel, and simultaneously reports to the environmental supervision platform (if environmental standards are involved); a special report is generated for the entire emergency anomaly handling process and archived on the renewable resource recycling information platform.

[0048] S5. Acquire and aggregate full-process operational data, enabling end-to-end data traceability through the renewable resource recycling information platform. Specifically, this includes: S501. Summarize all operational data, including the processing data for steps S1, S2, S3, and S4, specifically: ①S1's original data collection on recycled resources (physical parameters, material type, recycling traceability information) and sensor operating parameters (sampling frequency, signal stability); ②S2 data preprocessing results, fuzzy decision operation data (membership degree calculation value, inference rule matching record), sorting control instructions and traceability association data; ③ S3 execution module running status data (positioning accuracy, gripping force, rotation speed, process progress), disassembly / processing unit collaborative data; ④S4's core monitoring metrics data (sorting accuracy, resource damage rate, etc.), anomaly detection records, alarm information, and hierarchical processing data.

[0049] All data is linked and bound by timestamp, unique resource identifier, and process number to ensure that data can be accurately located to specific resources and specific process steps.

[0050] The aggregated data undergoes secondary processing, including using data deduplication algorithms to remove duplicate records, using interpolation to supplement a small amount of missing non-critical data, and using an outlier re-judgment mechanism (combined with historical normal data ranges) to verify and correct outlier data that was not completely removed in S4. In accordance with preset industry data standards and system unified data specifications, data format standardization (such as unified units, unified field names, and unified precision retention digits) and coding standardization (such as resource category coding, outlier type coding, and workstation number coding) are completed to form a structured data set and eliminate data heterogeneity.

[0051] The information platform for recycling and utilizing renewable resources adopts a hot data-cold data hierarchical storage architecture. It stores recent real-time operational data and frequently queried data in a high-speed cache to ensure query and analysis efficiency, while storing historical data and archived data in a distributed database to ensure long-term secure data storage.

[0052] S502. Through the preset API interface, bidirectional data flow is realized between various collaborative systems and PLCs and the renewable resource recycling information platform, specifically as follows: ① The intelligent waste sorting platform will feed back updated resource category standards (such as adding new subcategories of recyclable resources and revising material judgment standards) and resource distribution data of recycling areas to the system; ②The Smart Environmental Protection Big Data Integrated Service System will synchronize the latest environmental compliance requirements (such as adjustments to pollutant emission limits and updates to the list of hazardous materials) and environmental verification results analysis data to the platform; ③ The environmental cloud platform pushes dynamic data on processing capacity (such as equipment load warnings and remaining capacity) and suggestions for optimizing processing technology; ④ The smart sanitation data collection system provides feedback on recycling and transportation efficiency data and resource arrival timeliness data.

[0053] The core dimensions of the full-chain traceability data are clearly defined, forming a traceability chain for the entire resource lifecycle, including recycling, sorting, dismantling, and processing. Data in each dimension is bound to a unique resource identifier (such as a QR code or RFID tag number), ensuring forward traceability (from recycling to processing) and reverse tracing (from processing results back to the recycling source). The renewable resource recycling information platform provides flexible traceability query functions, establishes a hierarchical access control mechanism, and employs data encryption storage and access auditing mechanisms to prevent data leakage and tampering, ensuring the authenticity and security of traceability data.

[0054] like Figure 2 As shown, the present invention also provides a real-time monitoring device for an intelligent sorting system. Based on the real-time monitoring method for an intelligent sorting system described above, the device includes: The acquisition unit is used to acquire physical parameters, omnidirectional images, quality parameters, material parameters and traceability data of the recycled resources using the sensing module as a full-dimensional raw data set, and to transmit the full-dimensional raw data set to the PLC, and to the recycled resource recycling information platform and various collaborative systems through the wireless transmission module; The generation unit is used by the PLC to preprocess the full-dimensional raw data set, load the fuzzy control algorithm and generate sorting decision control instructions in combination with the preset recyclable resource adaptation rules, send the sorting decision control instructions to the execution module, and synchronize the decision result data to the remote control terminal and various collaborative systems. An execution unit is used by the execution module to perform the sorting operation of recycled resources according to the sorting decision control instructions, and to feed back the running status data to the PLC, remote control terminal, recycled resource recycling information platform and various collaborative systems. The early warning unit is used by the PLC to aggregate data from each stage to form a full-process dataset, combine it with preset core monitoring indicators to make anomaly judgments and issue early warnings, and link the execution module to perform anomaly classification processing according to preset anomaly level rules. The traceability unit is used to summarize multi-dimensional operational data from the entire preceding process, perform secondary processing and hierarchical storage, and achieve cross-system bidirectional data exchange through API interfaces to build a traceability system for the entire life cycle of renewable resources.

[0055] Each of the above units is used to perform the corresponding steps in the real-time monitoring method of the intelligent sorting system. The specific implementation method is as described in the above method embodiment, and will not be repeated here.

[0056] like Figure 3 As shown, the present invention also provides a computer device, which may be a server, and its internal structure may be as follows: Figure 3 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores all data required for the real-time monitoring method of the intelligent sorting system. The network interface is used for communication with external terminals via a network connection. The computer program is executed by the processor to implement the real-time monitoring method of the intelligent sorting system.

[0057] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer equipment on which the present application is applied.

[0058] An embodiment of this application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements any of the above-described intelligent sorting system real-time monitoring methods.

[0059] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by hardware related to computer program instructions. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the above method embodiments. Any references to memory, storage, databases, or other media provided in this application and used in the embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM), such as dynamic RAM (used as main storage) or static RAM (commonly used as cache memory). By way of illustration and not limitation, RAM has various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), and Rambus DRAM (RDRAM).

[0060] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, apparatus, article, or method. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0061] The above description is merely a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A real-time monitoring method for an intelligent sorting system, characterized in that, The intelligent sorting system based on a PLC, a sensing module, an execution module, and a wireless communication module includes the following method: S1. The sensor module is used to collect physical parameters, omnidirectional images, quality parameters, material parameters and traceability data of the recycled resources as a full-dimensional raw data set, and the full-dimensional raw data set is transmitted to the PLC and transmitted to the recycled resource recycling information platform and various collaborative systems through the wireless transmission module. S2 and PLC preprocess the full-dimensional raw data set, load the fuzzy control algorithm and generate sorting decision control instructions in combination with the preset recyclable resource adaptation rules, send the sorting decision control instructions to the execution module, and at the same time synchronize the decision result data to the remote control terminal and each collaborative system; S3. The execution module performs the sorting operation of recycled resources according to the sorting decision control instruction, and feeds back the running status data to the PLC, remote control terminal, recycled resource recycling information platform and various collaborative systems. S4 and PLC aggregate data from each stage to form a full-process dataset, combine it with preset core monitoring indicators to determine and warn of anomalies, and link the execution modules to perform anomaly classification and processing according to preset anomaly level rules. S5. It summarizes multi-dimensional operational data from the entire process and performs secondary processing and hierarchical storage. It also enables bidirectional data exchange across systems through API interfaces to build a full lifecycle traceability system for renewable resources.

2. The real-time monitoring method for the intelligent sorting system according to claim 1, characterized in that, S1 specifically includes: S101. Connect and configure the PLC with the sensing module and the wireless communication module; the sensing module includes a laser displacement sensor, a vision sensor, a weight sensor, a material sensor, and a recycling traceability information acquisition module. S102, the laser displacement sensor collects the size and radial runout of the recycled resources as the physical parameters, the vision sensor collects the all-round image of the recycled resources and performs feature recognition, the weight sensor collects the actual mass data of the recycled resources, the material sensor identifies the material type of the recycled resources and outputs the material category identification signal, and the recycling traceability information collection module reads the traceability data of the recycled resources, finally forming a full-dimensional original data set. S103. Upload the full-dimensional raw data set to the PLC in real time through the preset wired industrial communication protocol, and push the data to the renewable resource recycling information platform in the form of encrypted data packets through the 4G / 5G wireless communication module. S104. Transmit the full-dimensional raw data set to various collaborative systems through the pre-configured API interface, including the intelligent waste sorting platform, the smart sanitation data collection system, the smart environmental protection big data integrated service system, and the environmental cloud platform.

3. The real-time monitoring method for the intelligent sorting system according to claim 2, characterized in that, S2 specifically includes: S201, the PLC receives the full-dimensional raw data set and preprocesses it, specifically including: using the moving average method for noise filtering; identifying and removing abnormal data from the weight sensor and vision sensor outputs that exceed reasonable ranges based on the 3σ principle; converting physical parameters of different dimensions to the [0,1] interval through normalization; and simultaneously converting the traceability information and material type data according to the preset data format requirements of each collaborative system to generate data copies adapted to each collaborative system. S202. Load the fuzzy control algorithm program adapted to the recycling resource sorting scenario into the PLC, configure the input fuzzy subset, clarify the boundary range of each subset, define the linguistic values ​​of recycling resource category, size, weight, and material type, and match the corresponding membership function for each linguistic value. Establish a fuzzy inference rule library for recycling resources that combines the difficulty of recycling resource dismantling, processing and utilization adaptability, and environmental compliance requirements. S203. The preprocessed full-dimensional original dataset is used as the input variable of the fuzzy controller. Fuzzy decision calculation is performed to generate precise control quantities as sorting decision control instructions. S204. The PLC sends the sorting decision control instructions to the execution module in real time, pushes the decision results to the remote control terminal through the wireless communication module, and through the pre-configured API interface, extracts and adapts the data of the decision results according to the needs of each collaborative system, and then synchronizes them to each collaborative system to achieve cross-system business collaboration.

4. The real-time monitoring method for the intelligent sorting system according to claim 3, characterized in that, S203 specifically includes: Substitute the preprocessed full-dimensional original data set into the preset membership function to calculate the membership degree of each input variable corresponding to different linguistic values; based on the fuzzy inference rule base, the MAX-MIN synthetic inference method is used to perform a minimum operation on the membership degree of the premise of each rule to obtain the trigger strength of the rule, and then perform a maximum operation on the trigger strength of all rules to finally obtain the membership degree of each linguistic value of the output variable. By using the centroid defuzzification method, the centroid coordinates of the output fuzzy set are calculated and transformed into precise control quantities, including key control parameters such as the sorting channel number corresponding to the recycled resource, the robotic arm gripping angle, the gripping force threshold, the dismantling station number, and the processing flow indicator. While generating the control quantities, the recycling traceability information of the recycled resource is associated and bound with the control parameters to form a complete data chain of sorting control instructions and traceability information.

5. The real-time monitoring method for the intelligent sorting system according to claim 4, characterized in that, S3 specifically includes: S301. Connect and configure the PLC with the execution module, wherein the execution module includes a multi-axis manipulator, cylinders, servo motors, conveyor belts, and linkage control components for disassembly and processing units; S302. The execution module receives and parses the sorting decision control instructions issued by the PLC as local control instructions, and receives instructions sent by the remote control terminal as remote instructions. It determines the conflict between local control instructions and remote instructions according to a preset priority mechanism. Specifically, if it is an emergency intervention instruction, the execution of the local instruction is immediately suspended, and the remote instruction is responded to first. If it is a normal parameter adjustment instruction, it is determined whether it can be adjusted in real time based on the current sorting progress. If it does not affect the sorting action being executed, it takes effect directly. If it may cause the action to be abnormal, it waits for the current action to be completed before executing. S303, the multi-axis manipulator of the execution module starts a preset adaptive robust control algorithm to adaptively adjust the gripping strategy according to the parsed sorting decision control command; the cylinder drives the piston to extend and retract according to the set stroke to complete the sorting channel switching and recyclable resource positioning and clamping; the servo motor adjusts the speed according to the sorting decision control command to drive the conveyor belt to run at the appropriate speed; the disassembly unit and the processing unit trigger the disassembly / processing action start signal through the photoelectric sensor at the workstation according to the sorting decision control command, so as to realize seamless collaboration between sorting and subsequent processes; S304. The built-in sensors of the execution module collect and transmit the operating status data to the PLC in real time. The PLC sorts, classifies, and displays the received operating status data in real time. The operating status data is also transmitted to the remote control terminal, the renewable resource recycling information platform, and various collaborative systems via the wireless communication module.

6. The real-time monitoring method for the intelligent sorting system according to claim 5, characterized in that, S4 specifically includes: S401 and PLC aggregate data from each stage, including the data collected in S1, the sorting decision data in S2, and the operating status data in S3. At the same time, they receive feedback data from the renewable resource recycling information platform and various collaborative systems to form a full-process dataset. Based on the full-process dataset, core monitoring indicators are calculated according to preset formulas, including performance indicators, process progress indicators, traceability integrity indicators, and equipment and environmental protection indicators. S402 and PLC preset anomaly judgment thresholds, including performance thresholds, equipment operating parameter thresholds, environmental protection thresholds, and data integrity thresholds. They extract various data from the entire process dataset in real time and compare them one by one with the anomaly judgment thresholds. They also combine the judgment logic of instantaneous exceedance and continuous verification to make anomaly judgments. At the same time, the intelligent environmental protection big data integrated service system synchronously verifies environmental protection parameters, forming a dual anomaly detection mechanism of local detection + collaborative system cross-verification. S403. When the dual anomaly detection mechanism determines an anomaly, it triggers an audible and visual alarm and displays the anomaly type, occurrence time, associated equipment number, batch number of the recycled resources involved, current positioning deviation value, and specific values ​​of the environmental parameters exceeding the standard; it pushes the anomaly data to the remote control terminal and various collaborative systems for cross-system collaborative alarm, while the recycled resource recycling information platform records all anomaly information. S404. Determine the abnormal level of the abnormal data according to the preset abnormal level rules, and process it in stages according to the abnormal level; wherein, the abnormal level includes minor abnormality, serious abnormality, and emergency abnormality. When there is a minor abnormality, the PLC automatically starts an emergency adjustment command. When there is a serious abnormality, the PLC immediately sends a command to suspend the operation of the recyclable resource sorting line and lock the execution module. When there is an emergency abnormality, the PLC immediately triggers the system emergency shutdown, cuts off the power supply of the execution module, and starts the on-site safety warning device.

7. The real-time monitoring method for the intelligent sorting system according to claim 6, characterized in that, In step S401, the core monitoring indicators are calculated according to the full-process dataset using a preset formula, specifically including: Performance metrics: Sorting accuracy = Qualified sorted quantity / Total sorted quantity × 100%, System response time = Time elapsed from data collection trigger to execution completion, Resource damage rate = Damaged resource quantity / Total sorted quantity × 100%, Production cycle time = Number of sorted resources per unit time; Process progress indicators include: recycled resource recovery volume, current batch sorting completion rate, dismantling efficiency, and processing utilization rate. Specifically, dismantling efficiency = (number of dismantled items / number of sorted items) × 100%, and processing utilization rate = (number of qualified processed items / number of dismantled items) × 100%. Traceability integrity index: Traceability information integrity rate = Number of resources with no missing information / Total number of resources × 100%; Equipment and environmental indicators: operating load of execution modules and compliance rate of environmental parameters, where the compliance rate of environmental parameters = number of environmentally compliant resources / total number of resources × 100%.

8. The real-time monitoring method for the intelligent sorting system according to claim 7, characterized in that, S5 specifically includes: S501. Summarize the full-dimensional operation data, including the full-process processing data of steps S1, S2, S3, and S4. All data are associated and bound by timestamp-resource unique identifier-stage number. The full-dimensional operation data is then processed and hierarchically stored and managed. S502. Through the preset API interface, realize the two-way data flow between various collaborative systems and PLC, and the information platform for recycling and utilization of renewable resources, clarify the core dimensions of the whole chain traceability data, so as to form a whole life cycle traceability system for renewable resources, including recycling, sorting, dismantling and processing, and the data of each dimension is bound to the unique identifier of the resource.

9. A real-time monitoring device for an intelligent sorting system, based on the real-time monitoring method for an intelligent sorting system according to any one of claims 1-8, characterized in that, The device includes: The acquisition unit is used to acquire physical parameters, omnidirectional images, quality parameters, material parameters and traceability data of the recycled resources using the sensing module as a full-dimensional raw data set, and to transmit the full-dimensional raw data set to the PLC, and to the recycled resource recycling information platform and various collaborative systems through the wireless transmission module; The generation unit is used by the PLC to preprocess the full-dimensional raw data set, load the fuzzy control algorithm and generate sorting decision control instructions in combination with the preset recyclable resource adaptation rules, send the sorting decision control instructions to the execution module, and synchronize the decision result data to the remote control terminal and various collaborative systems. An execution unit is used by the execution module to perform the sorting operation of recycled resources according to the sorting decision control instructions, and to feed back the running status data to the PLC, remote control terminal, recycled resource recycling information platform and various collaborative systems. The early warning unit is used by the PLC to aggregate data from each stage to form a full-process dataset, combine it with preset core monitoring indicators to make anomaly judgments and issue early warnings, and link the execution module to perform anomaly classification processing according to preset anomaly level rules. The traceability unit is used to summarize multi-dimensional operational data from the entire preceding process, perform secondary processing and hierarchical storage, and achieve cross-system bidirectional data exchange through API interfaces to build a traceability system for the entire life cycle of renewable resources.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 8.

Images