Conveyor operation state monitoring system based on edge calculation

Abstract

The invention relates to the field of conveyor state monitoring, and discloses a conveyor running state monitoring system based on edge calculation, which is used for running state monitoring and fault early warning of an industrial conveyor system. The conveyor operation state monitoring system based on edge calculation comprises a sensing module, a prediction module, an identification module, a decision module and an optimization module. The sensing module constructs a virtual sensing field by deploying a multi-physical-quantity sensor, and continuous field description of the running state of the conveyor is established; the prediction module performs multi-state parallel deduction based on a quantum superposition principle to generate a prediction result; the identification module uses a biological field resonance principle to realize abnormity identification and fault positioning; the decision module generates a control strategy according to the abnormity severity and the resource state; and the optimization module forms a closed-loop system by adjusting resources. Accurate monitoring, early warning and intelligent decision making of the running state of the conveyor are achieved, and the reliability and efficiency of equipment monitoring are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of conveyor state monitoring, and in particular to a conveyor operation state monitoring system based on edge computing. BACKGROUND

[0002] As a key transportation equipment in mining, port, logistics and other industries, the operation state of the conveyor directly affects the reliability and efficiency of the entire production system. The traditional conveyor state monitoring method mainly relies on periodic manual inspection and simple threshold alarm mechanism. This method is not only inefficient, but also difficult to find potential faults in time, which can easily lead to sudden shutdown accidents and cause huge economic losses.

[0003] In recent years, the state monitoring technology based on sensor network has been widely applied, but there are still obvious limitations in practical application. Traditional prediction methods rely mainly on statistical analysis of historical data or pattern recognition based on machine learning. These methods require a large amount of training data and have high requirements for data quality, and often perform unstable in complex and variable industrial sites.

[0004] More prominent is that the existing monitoring system has the following deficiencies in several aspects: first, in the perception layer, the discrete sensor layout cannot form a continuous field description of the equipment operation state, resulting in monitoring blind area; second, in the prediction layer, the prediction model based on single state assumption is difficult to accurately describe the multi-possibility evolution process of equipment operation; third, in the abnormal identification layer, the traditional method is difficult to establish the correlation between micro abnormal features and macro performance degradation, resulting in fault early warning lag.

[0005] Therefore, we propose a conveyor operation state monitoring system based on edge computing to solve the above problems. SUMMARY

[0006] The present application provides a conveyor operation state monitoring system based on edge computing for the operation state monitoring and fault early warning of industrial conveyor systems.

[0007] The first aspect of the present application provides a conveyor running state monitoring system based on edge computing, which comprises: a perception module, which deploys multiple physical quantity sensors in an edge computing node network based on the structure and characteristics of the conveyor, forms a virtual sensing field, establishes a continuous field description of the conveyor through the sensor nodes, and provides a basis for subsequent state prediction; a prediction module, which performs deduction based on the quantum superposition principle through the continuous state description output by the virtual sensing field, filters and optimizes the running state through the probability amplitude evolution mechanism, generates a prediction result of the multi-state evolution path, and provides information for abnormal identification; an identification module, which analyzes the multi-state evolution path and real-time perception data, identifies the correlation relationship based on the biological field resonance principle, realizes the identification and positioning of potential faults by establishing a space-time propagation model of abnormal patterns; and a decision module, which generates a control strategy by combining the identified abnormal patterns and their severity with the state of the edge computing node, ensures the response of critical abnormalities through scheduling, and maintains the overall monitoring effectiveness of the system.

[0008] Optionally, in the first implementation manner of the first aspect of the present application, the method further comprises: deploying heterogeneous sensor nodes according to the conveyor characteristics and running conditions, forming a dynamic perception topology through the nodes; performing space-time registration and feature extraction on the multiple physical quantity data in the formed dynamic perception topology to generate a fusion feature vector; taking the generated fusion feature vector as input, generating state field distribution data based on a continuous field description model; the state field distribution data describes the conveyor state and changes; performing quality assessment on the generated state field distribution data to generate a perception quality assessment report; dynamically adjusting the dynamic perception topology according to the perception quality assessment report to generate an optimized sensing field configuration scheme.

[0009] Optionally, in the second implementation manner of the first aspect of the present application, the method further comprises: constructing a quantum state description based on the data provided by the virtual sensing field to generate an initial quantum state set; taking the generated initial quantum state set as input, generating a multi-state evolution path based on a time evolution process; performing quantum interference effect analysis on the generated multi-state evolution path to generate an interference-enhanced state path; the interference-enhanced state path strengthens the possible evolution trend; performing a selective state collapse operation based on the interference-enhanced state path to generate a most likely state sequence; performing uncertainty analysis on the generated most likely state sequence to generate a prediction report with confidence evaluation.

[0010] Optionally, in the third implementation form of the first aspect of the present application, the method further comprises: constructing a biological field resonance perception model based on the distribution data provided by the virtual sensing field and the multi-state evolution path provided by the quantum prediction module to generate biological field resonance mode features; inputting the generated biological field resonance mode features to analyze the propagation law and generate an abnormal propagation network; constructing a spatiotemporal fault evolution graph based on the generated abnormal propagation network in combination with the spatial layout and time series data of the conveyor; inputting the generated spatiotemporal fault evolution graph to perform comprehensive risk assessment and generate hierarchical early warning information; and adjusting the focus and frequency of the virtual sensing field according to the generated hierarchical early warning information to generate an optimized monitoring configuration scheme.

[0011] Optionally, in the fourth implementation form of the first aspect of the present application, the method further comprises: constructing a multi-dimensional factor decision matrix based on the abnormal mode recognition data in combination with the resource state monitoring data to generate a resource task matching evaluation report; inputting the generated resource task matching evaluation report to establish a dynamic mapping relationship and generate a priority control instruction set; performing hierarchical scheduling based on the generated priority control instruction set to generate a resource allocation execution scheme; generating a device control command set in combination with the conveyor operation state according to the resource allocation execution scheme; and monitoring the control command execution effect in combination with the system operation state to generate a scheduling efficiency evaluation report.

[0012] Optionally, in the fifth implementation form of the first aspect of the present application, the method further comprises an optimization module: optimizing the virtual sensing field by using the control execution effect feedback and abnormal distribution information, focusing the monitoring resources by dynamically adjusting the sensor nodes, and forming a closed-loop monitoring system. Optionally, in the sixth implementation form of the first aspect of the present application, based on the control command execution effect feedback and the information of the abnormal recognition module, the system response and the abnormal area distribution are analyzed to generate a topology optimization basis report; the generated topology optimization basis report is inputted to evaluate the sensor network nodes in combination with the conveyor structure and the operation criticality to generate a key node identification list; the sampling frequency, the sensing accuracy and the communication priority of the virtual sensing field are adjusted according to the generated key node identification list to generate a sensing parameter optimization scheme; the communication link topology is configured based on the sensing parameter optimization scheme, the data transmission path and the bandwidth allocation are optimized, and a communication link reconstruction scheme is generated; the communication link reconstruction effect is monitored, the system monitoring efficiency index is compared, a topology optimization verification report is generated, and the report is fed back to the topology optimization decision process.

[0013] Optionally, in the seventh implementation manner of the first aspect of the present application, further comprising: constructing a system comprehensive performance evaluation model based on the verification report and the evaluation report of the control decision module, and generating a multi-dimensional performance evaluation report; taking the generated multi-dimensional performance evaluation report as input, adjusting the fusion parameters of the virtual sensing field, the evolution of quantum prediction and the threshold of anomaly identification, and generating a system parameter adjustment scheme; and based on the generated system parameter adjustment scheme, coordinating the operation parameters of the perception, prediction, identification, decision and optimization modules, and generating a cross-module collaborative optimization strategy. Optionally, in the eighth implementation manner of the first aspect of the present application, according to the execution effect of the cross-module collaborative optimization strategy, a system optimization knowledge base is constructed in combination with successful case modes to generate an optimization mode set; the generated optimization mode is verified in real time, a system evolution performance report is generated through comparative analysis, and the report is fed back to the performance evaluation model.

[0014] The second aspect of the present application provides a conveyor running state monitoring device based on edge computing, comprising: a memory and at least one processor, the memory storing instructions; the at least one processor invokes the instructions in the memory to make the conveyor running state monitoring device based on edge computing execute the above-mentioned conveyor running state monitoring system based on edge computing.

[0015] The mechanism of the present application is as follows: a theoretical leap from traditional discrete monitoring to continuous intelligent perception is realized. The principle of quantum superposition is introduced into device state prediction, which breaks through the limitations of traditional single prediction model through multi-state parallel deduction; the cross-scale correlation model of micro anomalies and macro performance is established by using the biological field resonance theory, solving the problem of early fault identification; the continuous holographic perception of device running state is realized by using the virtual sensing field technology; and the self-evolution ability is formed through dynamic resource scheduling and topology optimization, which gets rid of the dependence on machine learning model.

[0016] Advantages: the continuous field description of the perception module provides input for the prediction module, the multi-state evolution path of the prediction module and the real-time perception data jointly drive the identification module analysis, the identification result supports the decision module to formulate strategies, and the optimization module completes the system reconstruction by comprehensively considering the execution effect and abnormal information. This collaborative architecture produces a significant composite effect: the strict data flow and control flow connection between modules eliminates information silos, realizes the transition from passive response to active optimization; the cooperation of virtual sensing field and dynamic topology optimization realizes the synergy of global monitoring and local key monitoring; the distributed architecture and adaptive mechanism ensure the reliability and flexibility of the system, so that the system has the ability of closed-loop autonomy, dynamic adaptation and continuous evolution, realizes the organic integration of the functions of each module, and provides a system-level solution for intelligent monitoring of industrial equipment. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 Figure 1 is a schematic diagram of an embodiment of the conveyor operation state monitoring system based on edge computing in the present application; Figure 2 Figure 2 is a schematic diagram of the conveyor operation state monitoring device based on edge computing in the present application. DETAILED DESCRIPTION

[0018] The embodiment of the present application provides a conveyor operation state monitoring system based on edge computing, which is used for operation state monitoring and fault early warning of an industrial conveyor system. The terms "first", "second", "third", "fourth" and the like (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the term "comprising" or "having" and any variation thereof is intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0019] For the sake of understanding, the specific flow of the embodiment of the present application is described below. Please refer to Figure 1 An embodiment of the conveyor operation state monitoring system based on edge computing in the present application includes: 101, a perception module, based on the physical structure and operation characteristics of the conveyor, deploying multiple physical quantity sensors in the edge computing node network to form a virtual sensing field with self-organizing capability; through the collaborative perception and data fusion of the sensor nodes, a continuous field description of the conveyor operation state is established to provide a complete perception basis for subsequent state prediction.

[0020] It can be understood that the execution subject of the present application can be a conveyor operation state monitoring device based on edge computing, and can also be a terminal or a server, which is not limited here. The embodiment of the present application takes the server as the execution subject for example.

[0021] It should be noted that according to the mechanical structure characteristics and operation conditions of the conveyor, heterogeneous sensor nodes are deployed at key monitoring positions, and through autonomous negotiation and link establishment between nodes, a dynamic perception topology is formed; the key monitoring positions include a driving device, a redirection roller, a bearing roller and a tension device; The vibration, temperature, acoustic and other multi-physical quantity data collected by each sensor node in the formed dynamic perception topology are subjected to space-time registration and feature extraction to generate a fusion feature vector; the fusion feature vector includes time domain features, frequency domain features and time-frequency domain features; The generated fusion feature vector is taken as input, a continuous field description model of the conveyor running state is constructed based on field theory principles, and state field distribution data is generated; the state field distribution data describes the running state of each position of the conveyor and the gradient change thereof in the form of a vector field; The generated state field distribution data is subjected to quality assessment, and a perception quality assessment report is generated based on information completeness and measurement accuracy indexes; the perception quality assessment report is used to guide the reliability weight distribution of subsequent state prediction; According to the perception quality assessment report, the dynamic perception topology is dynamically adjusted, and an optimized sensing field configuration scheme is generated through node wake-up and sleep mechanisms and adaptive adjustment of sampling frequency.

[0022] 102. A prediction module performs multi-state parallel deduction based on the continuous state description output by the virtual sensing field and the quantum superposition principle; and filters and optimizes a plurality of possible running states through a probability amplitude evolution mechanism to generate a prediction result containing a multi-state evolution path in a future period, thereby providing state evolution information for abnormal identification.

[0023] It should be noted that based on the state field distribution data provided by the virtual sensing field, a quantum state description of the conveyor running state is constructed, and an initial quantum state set is generated; the initial quantum state set includes a plurality of possible state basis vectors and corresponding probability amplitudes; The generated initial quantum state set is taken as input, and a time evolution process of the state is simulated based on the Schrödinger equation to generate a multi-state evolution path; the multi-state evolution path describes the probability amplitude change trajectory of each quantum state in the prediction period; The generated multi-state evolution path is subjected to quantum interference effect analysis to identify constructive and destructive interference phenomena, and an interference-enhanced state path is generated; the interference-enhanced state path strengthens the possible evolution trend through probability amplitude superposition; Based on the interference-enhanced state path, a selective state collapse operation is implemented at the end of the prediction time domain to generate a most probable state sequence; the most probable state sequence includes a dominant evolution path from the current to the prediction endpoint and its occurrence probability; The generated most probable state sequence is subjected to uncertainty analysis, a confidence index of the prediction result is calculated based on the probability amplitude distribution, and a prediction report with confidence evaluation is generated.

[0024] 103、identification module, through the multi-state evolution path and real-time perception data, the correlation analysis is carried out across the scale, and the correlation between the micro abnormal characteristics and the macro performance degradation is identified based on the biological field resonance principle; through the establishment of the abnormal mode space propagation model, the early identification and accurate positioning of potential faults are realized.

[0025] It should be noted that based on the real-time state field distribution data provided by the virtual sensing field and the multi-state evolution path provided by the quantum prediction module, a biological field resonance perception model is constructed, and a biological field resonance mode feature is generated; the biological field resonance mode feature can reflect the coupling relationship between micro abnormal vibration and macro performance degradation at the same time; The generated biological field resonance mode feature is taken as input, the propagation law of abnormal characteristics between different physical scales is analyzed, and an abnormal propagation network is generated; the abnormal propagation network describes the path and intensity of the abnormality from the local component to the system as a whole; Based on the generated abnormal propagation network, the spatial layout and time series data of the conveyor are combined to construct a space-time fault evolution graph; the graph contains three-dimensional description of fault origin location, propagation path and evolution speed; Taking the generated space-time fault evolution graph as input, the comprehensive risk assessment is carried out based on the abnormal propagation intensity and evolution speed, and the graded early warning information is generated; the graded early warning information includes probability estimation and impact range prediction of fault occurrence; According to the generated graded early warning information, the monitoring focus and sampling frequency of the virtual sensing field are dynamically adjusted, and the optimized monitoring configuration scheme is generated; the optimized configuration scheme can implement key monitoring for high-risk areas, and improve the fault identification accuracy.

[0026] 104、decision module, through the identified abnormal mode and its severity, combined with the real-time resource state of the edge computing node, a hierarchical and priority control strategy is generated; through dynamic resource scheduling, the rapid response of key abnormalities is ensured, and the overall monitoring efficiency of the system is maintained.

[0027] It should be noted that based on the abnormal mode identification data provided by the abnormal identification module, combined with the resource state monitoring data of the edge computing node, a decision matrix containing abnormal severity, resource availability, response timeliness and other multi-dimensional factors is constructed, and a resource task matching evaluation report is generated; Taking the generated resource task matching evaluation report as input, the dynamic mapping relationship between abnormal types and computing resources is established, and a priority control instruction set is generated; the control instruction set clearly defines the response priority and resource allocation scheme of different levels of abnormalities; Based on the generated priority control instruction set, the computing resources, storage resources and communication resources of the edge computing node are scheduled in layers, and a resource allocation execution scheme is generated; the execution scheme ensures that the key abnormal processing enjoys the highest priority of resource guarantee; According to the resource allocation execution scheme, combined with the actual running state of the conveyor, a specific device control command set is generated; the control command set includes operation parameter adjustment, early warning signal issuance and device shutdown protection instruction; The effect of the control command is monitored in real time, and a scheduling efficiency evaluation report is generated in combination with the overall running state of the system; the report is used as feedback information for the optimization of the decision factor weight setting in step one.

[0028] 105、Optimization module, using control execution effect feedback and abnormal distribution information, topological structure optimization of virtual sensing field; through dynamic adjustment of the sensing weight and communication link of the sensor node, realize intelligent focusing of monitoring resources to key area, form a closed-loop monitoring system with self-optimization ability.

[0029] It should be noted that, based on the control decision module control command execution effect feedback and abnormal recognition module abnormal distribution information, comprehensive analysis of system response efficiency and abnormal area distribution characteristics, generate topological optimization basis report; The generated topological optimization basis report is used as input, combined with the structural importance and operation criticality of each part of the conveyor, the importance of each node in the sensing network is evaluated, and a key node identification list is generated; According to the generated key node identification list, dynamically adjust the sampling frequency, sensing accuracy and communication priority of each node in the virtual sensing field, generate the sensing parameter optimization scheme; Based on the sensing parameter optimization scheme, reconfigure the communication link topology between sensor nodes, optimize the data transmission path and bandwidth allocation, and generate the communication link reconstruction scheme; Real-time monitoring of the implemented communication link reconstruction effect, by comparing the system monitoring efficiency indicators before and after optimization, generate topological optimization verification report, and feed back the report to the topological optimization decision process of step one.

[0030] 106、Also includes: based on the optimization verification report of the topological optimization module and the scheduling efficiency evaluation report of the control decision module, build a system comprehensive performance evaluation model, generate a multi-dimensional performance evaluation report containing response time, identification accuracy, resource utilization rate; The generated multi-dimensional performance evaluation report is used as input, and the fusion parameters of the virtual sensing field, the evolution step of the quantum prediction and the sensitivity threshold of the abnormal identification are dynamically adjusted according to the performance index deviation, and a system parameter adjustment scheme is generated; Based on the generated system parameter adjustment scheme, coordinate the running parameters of the five core modules of virtual sensing field construction, quantum state prediction, abnormal identification, decision generation and topological optimization, generate cross-module collaborative optimization strategy; According to the cross-module collaborative optimization strategy execution effect, combined with the successful case mode in the historical operation data, a system optimization knowledge base is constructed, and a set of migratable optimization mode is generated; The generated migratable optimization mode is verified in real time, the system performance improvement effect is compared and analyzed, a system evolution efficiency report is generated, and the report is fed back to the efficiency evaluation model of step one for continuous optimization.

[0031] In the embodiment of the application, the principles of quantum superposition, biological field resonance theory and field theory are applied, the virtual sensing field is constructed, and the dynamic topology optimization is combined, the single-point monitoring is realized to full-field perception, the quantum heuristic multi-state parallel deduction mechanism is used to improve the comprehensiveness and accuracy of state prediction, the biological field resonance-based cross-scale anomaly identification system is used to effectively analyze the correlation between microscopic characteristics and macroscopic performance, and early fault detection and accurate positioning are realized.

[0032] In terms of monitoring efficiency, early warning and accurate identification are realized, and false positives and false negatives are greatly reduced.In terms of resource utilization, intelligent scheduling and dynamic optimization mechanisms are used to realize efficient utilization of multi-dimensional resources such as computing, communication and energy consumption, and the system has self-adaptability and fault tolerance capability, can automatically adjust operation parameters according to working condition changes, and ensures stable and reliable operation in different environments.

[0033] Figure 2 It is a structure schematic view of a conveyor running state monitoring equipment based on edge computing provided by the embodiment of the application, and the conveyor running state monitoring equipment 200 based on edge computing can have great difference due to different configurations or performances, and the equipment 200 includes a transmitter 201, a receiver 202 and a processor 203. Figure 2 The processor 203 can also be a controller,

[0034] In one example, the transmitter 201 conditions (e.g., analogizes, filters, amplifies, and upconverts, etc.) the output samples and generates the uplink signal, which is transmitted via an antenna to the access network equipment. On the downlink, the antenna receives the downlink signal transmitted by the access network equipment. The receiver 202 conditions (e.g., filters, amplifies, downconverts, and digitizes, etc.) the signal received from the antenna and provides input samples. In the modem processor 205, the encoder 206 receives traffic data and signaling messages to be sent on the uplink and processes (e.g., formats, encodes, and interleaves, etc.) the traffic data and signaling messages. The modulator 207 further processes (e.g., symbol maps and modulates) the encoded traffic data and signaling messages and provides output samples. The demodulator 209 processes (e.g., demodulates) the input samples and provides symbol estimates. The decoder 208 processes (e.g., deinterleaves and decodes) the symbol estimates and provides decoded data and signaling messages sent to the device 200. The encoder 206, the modulator 207, the demodulator 209, and the decoder 208 can be implemented by a synthesized modem processor 205. These units process in accordance with the radio access technology employed by the wireless access network (e.g., the access technology of LTE and other evolved systems). It is noted that when the device 200 does not include the modem processor 205, the above functions of the modem processor 205 can also be completed by the processor 203.

[0035] The processor 203 controls and manages the actions of the device 200, and is configured to execute the processes described above as performed by the device 200 in the embodiments of the present disclosure. For example, the processor 203 is further configured to execute the steps of the transmitting device or the receiving device in the above-described system embodiments, and / or other steps of the technical solutions described in the embodiments of the present disclosure.

[0036] Further, the device 200 can further include a memory 204, which is configured to store program codes and data for the device 200.

[0037] It can be understood that, Figure 2 Only a simplified design of the device 200 is shown. In actual applications, the device 200 can include any number of transmitters, receivers, processors, modem processors, memories, etc., and all devices that can implement the embodiments of the present disclosure are within the protection scope of the embodiments of the present disclosure.

[0038] The present disclosure further provides a conveyor running state monitoring device based on edge computing, which comprises a memory and a processor, the memory stores computer readable instructions, and the computer readable instructions are executed by the processor to make the processor execute the steps of the conveyor running state monitoring system based on edge computing in the above-mentioned embodiments.

[0039] The application also provides a computer readable storage medium, which can be a non-volatile computer readable storage medium or a volatile computer readable storage medium, and the computer readable storage medium stores instructions, and the instructions make a computer execute the steps of the conveyor running state monitoring system based on edge computing when the instructions run on the computer.

[0040] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing system embodiments, which will not be described here.

[0041] The integrated unit, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the application or the whole or part of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions for making a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the system described in each embodiment of the application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0042] The above-described and above-mentioned embodiments are only used to illustrate the technical solutions of the application, rather than limit them; although the application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the application.

Claims

1. An edge-computing-based conveyor operation state monitoring system, characterized by, The edge computing-based conveyor operation state monitoring system comprises: A perception module, based on the structure and characteristics of the conveyor, deploys multiple physical quantity sensors in the edge computing node network to form a virtual sensing field, establishes a continuous field description of the conveyor through the sensor nodes, and provides a basis for subsequent state prediction; A prediction module, through the continuous state description output by the virtual sensing field, performs deduction based on the quantum superposition principle, filters and optimizes the operation state through the probability amplitude evolution mechanism, generates a prediction result of the multi-state evolution path, and provides information for anomaly identification; An identification module, through analysis of the multi-state evolution path and real-time perception data, identifies the correlation relationship based on the biological field resonance principle, establishes a time-space propagation model of abnormal patterns, and realizes identification and positioning of potential faults; A decision module, through the identified abnormal patterns and their severity, combines the state of the edge computing node, generates a control strategy, ensures the response of critical abnormalities through scheduling, and maintains the overall monitoring effectiveness of the system.

2. The edge-computing-based conveyor operating status monitoring system according to claim 1, characterized in that, It comprises: According to the characteristics and operation conditions of the conveyor, deploy heterogeneous sensor nodes to form a dynamic perception topology through the nodes; The multi-physical quantity data in the formed dynamic perception topology is subjected to space-time registration and feature extraction to generate a fusion feature vector; The generated fusion feature vector is taken as input to generate state field distribution data based on a continuous field description model; the state field distribution data describes the state and change of the conveyor; The generated state field distribution data is subjected to quality assessment to generate a perception quality assessment report; According to the perception quality assessment report, dynamically adjust the dynamic perception topology to generate an optimized sensing field configuration scheme.

3. The edge computing based conveyor operational status monitoring system of claim 1, wherein, It comprises: Based on the data provided by the virtual sensing field, construct a quantum state description to generate an initial quantum state set; The generated initial quantum state set is taken as input to generate a multi-state evolution path based on a time evolution process; The generated multi-state evolution path is subjected to quantum interference effect analysis to generate an interference-enhanced state path; the interference-enhanced state path strengthens the possible evolution trend; Based on the interference-enhanced state path, perform a selective state collapse operation to generate a most likely state sequence; The generated most likely state sequence is subjected to uncertainty analysis to generate a prediction report with confidence evaluation.

4. The edge computing-based conveyor operational status monitoring system according to claim 3, wherein, It comprises: Based on the distribution data provided by the virtual sensing field and the multi-state evolution path provided by the quantum prediction module, construct a biological field resonance perception model to generate biological field resonance pattern features; The generated biological field resonance pattern features are taken as input to analyze the propagation law and generate an abnormal propagation network; Based on the generated abnormal propagation network, combined with the spatial layout and time series data of the conveyor, construct a time-space fault evolution map; The generated time-space fault evolution map is taken as input to perform comprehensive risk assessment and generate graded early warning information; According to the generated graded early warning information, adjust the focus and frequency of the virtual sensing field to generate an optimized monitoring configuration scheme.

5. The edge computing based conveyor operational status monitoring system of claim 4, wherein, It comprises: Based on the abnormal pattern identification data, combined with the resource state monitoring data, construct a multi-dimensional factor decision matrix to generate a resource task matching evaluation report; The generated resource task matching evaluation report is taken as input to establish a dynamic mapping relationship and generate a priority control instruction set; Based on the generated priority control instruction set, hierarchical scheduling is performed to generate a resource allocation execution scheme; According to the resource allocation execution scheme, device control command sets are generated in combination with the conveyor running state; The control command execution effect is monitored, and a scheduling efficiency evaluation report is generated in combination with the system running state.

6. The edge computing-based conveyor operational status monitoring system according to claim 1, wherein, It also includes an optimization module: using control execution effect feedback and abnormal distribution information, the virtual sensing field is optimized, the monitoring resource is focused by dynamically adjusting the sensor node, and a closed-loop monitoring system is formed.

7. The edge computing-based conveyor operational status monitoring system according to claim 6, wherein, Based on the control command execution effect feedback and the information of the abnormal recognition module, the system response and the abnormal area distribution are analyzed, and a topological optimization basis report is generated; The generated topological optimization basis report is taken as input, the sensing network node is evaluated in combination with the conveyor structure and the running criticality, and a key node identification list is generated; According to the generated key node identification list, the sampling frequency, the sensing accuracy and the communication priority of the virtual sensing field are adjusted, and a sensing parameter optimization scheme is generated; Based on the sensing parameter optimization scheme, the communication link topology is configured, the data transmission path and the bandwidth allocation are optimized, and a communication link reconstruction scheme is generated; The communication link reconstruction effect is monitored, the topological optimization verification report is generated by comparing the system monitoring efficiency index, and the report is fed back to the topological optimization decision process.

8. The edge computing-based conveyor operational status monitoring system according to claim 1, wherein, It also includes: Based on the verification report and the evaluation report of the control decision module, a system comprehensive efficiency evaluation model is constructed, and a multi-dimensional efficiency evaluation report is generated; The generated multi-dimensional efficiency evaluation report is taken as input to adjust the fusion parameters of the virtual sensing field, the evolution of the quantum prediction and the threshold of the abnormal recognition, and a system parameter adjustment scheme is generated; Based on the generated system parameter adjustment scheme, the running parameters of the sensing, prediction, identification, decision and optimization modules are coordinated, and a cross-module collaborative optimization strategy is generated.

9. The edge computing-based conveyor operational status monitoring system of claim 8, wherein, According to the cross-module collaborative optimization strategy execution effect, a system optimization knowledge base is constructed in combination with successful case modes, and an optimization mode set is generated; The generated optimization mode is verified in real time, a system evolution efficiency report is generated through comparative analysis, and the report is fed back to the efficiency evaluation model.

10. An edge-computing-based conveyor operation state monitoring apparatus characterized by comprising: The conveyor running state monitoring device based on edge computing includes a memory and at least one processor, and the memory stores instructions; The at least one processor invokes the instructions in the memory to enable the conveyor running state monitoring device based on edge computing to perform the conveyor running state monitoring system based on edge computing as claimed in any one of claims 1-9.

Images