52 results about "Dynamic priority scheduling" patented technology

The invention provides a vehicle fault root cause diagnosis method, equipment, equipment and a medium, and the method comprises the steps: obtaining a vehicle target fault phenomenon, determining a to-be-detected fault event set based on a preset fault logic relation, constructing an initial scoring matrix, enabling a row vector to correspond to a fault event, enabling a column vector to correspond to the state feature parameters of a plurality of evaluation dimensions, and carrying out the detection of the fault event set; executing the detection task of the highest comprehensive score fault event, obtaining feedback data, updating the initial score matrix parameters based on the feedback data to obtain an updated score matrix, and calculating the comprehensive score of each event based on the updated score matrix again. Iteratively executing the detection task corresponding to the updated highest score event to identify whether the detection event is a fault root cause or not until the fault root cause of the target fault phenomenon is determined; according to the method, through a dynamic priority scheduling mechanism, real-time feedback data is fused in multi-dimensional evaluation, a high-value diagnosis task is executed preferentially, the resource consumption of traditional traversal diagnosis is remarkably reduced, and the fault positioning efficiency is effectively improved.

The invention discloses a multi-dimensional demand-driven large-model multi-task dynamic priority scheduling and multi-model collaboration method. The method comprises the steps of multi-task input and environment state perception: receiving an input concurrent task set and real-time environment parameters; multi-dimensional demand feature extraction: semantically analyzing the task set, and extracting a security demand level, a timeliness threshold, a social association degree and a personal comfort influence value of each task; dynamic weight generation based on a style model: calling a pre-training style decision model to generate a dynamic weight distribution rule; task priority quantitative calculation: carrying out tensor product calculation on the demand features and the weight vectors to obtain a comprehensive priority score; and multi-model collaborative scheduling execution: according to priority ranking, distributing high-priority tasks to a real-time response type model, distributing low-priority tasks to a resource optimization type model, and monitoring in real time and dynamically adjusting a queue. The invention also discloses a scheduling cooperation system for realizing the method, and the system has a wide application scene.

The invention relates to the technical field of photovoltaic power generation cloud platforms, and discloses a multi-site energy storage cluster cloud scheduling platform based on photovoltaic power generation prediction, and the platform employs a real-time data collection and space-time synchronization module to carry out the timestamp alignment and space grid processing of multi-source heterogeneous data. In combination with a dynamic priority scheduling mechanism of a prediction task distribution module based on volatility and a power grid security situation, the effects of cooperative execution of prediction tasks and priority guarantee of key tasks are achieved; through containerized parallel reasoning and consistency Hash load balancing technology of a distributed prediction calculation module, time consistency of a multi-node prediction result is ensured, and a rolling optimization algorithm and a time sequence constraint embedding strategy of a unified scheduling decision module are adopted. Accurate calculation of power generation unbalanced power and time sequence consistency generation of an energy storage strategy are achieved, and through instruction verification and conflict detection and filtering frequency reduction processing of a smoothing module, the effects of prolonging the service life of equipment and guaranteeing stable operation of a power grid are achieved.

The invention relates to the technical field of artificial intelligence, provides an edge computing task unloading method based on DRL and dynamic scheduling collaboration, and solves the problem that a task unloading decision is not matched with execution efficiency in an MEC environment. Task unloading is modeled as a Markov decision process, a state space containing task attributes, a transmission rate and computing resources is defined, a discrete action space covers local or edge server execution, and a reward function is designed based on time delay and overtime penalty. And carrying out offline training by adopting an LSTM-D3QN algorithm integrated with a long short-term memory network, extracting time sequence features and optimizing a state-action value function. A time-aware dynamic priority scheduling mechanism is introduced, an emergency area, a balance area and a waiting area are divided according to task remaining deadline, and remaining time sorting, dynamic weight priority and FIFO variant strategies are adopted respectively. In the online decision-making stage, the real-time environment state is input into the model to generate an unloading action, and task execution is scheduled according to the dynamic priority.

The invention relates to a priority dynamic scheduling and load self-adaption method for an unmanned aerial vehicle in a complex task scene based on an AUTOSAR real-time operating system. According to the method, the task priority is dynamically adjusted through a multi-dimensional dynamic priority scheduling algorithm, multi-core load balancing is achieved in combination with a prediction-based task migration strategy and a hybrid load balancing algorithm, resource allocation is optimized by adopting resource pooling dynamic allocation and PID feedback control, and the problem that when the AUTOSAR is applied to flight control of the unmanned aerial vehicle, the load balancing efficiency is high is solved. The problems that a static priority mechanism cannot respond to an emergency scene, the task load balancing control capability is lacked, task execution is easy to interfere and resource allocation is low in efficiency are solved, the real-time responsiveness, the task completion rate and the resource utilization rate of an unmanned aerial vehicle flight control system are effectively improved, and the flight safety and the operation reliability of the unmanned aerial vehicle in a complex scene are guaranteed.

The invention discloses a value maximization calculation unloading method and system based on dynamic priority scheduling and reinforcement learning. According to the method, an optimization framework with maximization of the'long-term average task value 'of the system as a core target is constructed, and the task value is defined by introducing an exponential value function, so that the problem of'value neglect' existing in a traditional'average delay or energy consumption optimization 'strategy is solved. According to the value-oriented optimization mechanism, the multi-agent system can autonomously learn a strategy which preferentially ensures high-value task execution when resources are limited in the training process. In addition, the invention further provides a dynamic priority function which can accurately measure the actual emergency level of the task at different moments, so that the defect that a static priority model is difficult to deal with the real-time change of the emergency state is overcome. Particularly, the dynamic priority method is not only used for task selection in a waiting queue, but also innovatively introduced into a resource dynamic allocation mechanism of a running queue.

The invention belongs to the technical field of electrochemical water treatment, and provides an electrochemical water treatment equipment cluster monitoring method and system based on cloud collaboration, and the method comprises the steps of data collection and preprocessing, low-delay high-credibility data transmission, intelligent fault diagnosis, dynamic energy efficiency optimization and collaborative scheduling, and whole-process monitoring visualization. According to the method, through dynamic priority scheduling, multi-link backup and full-link encryption transmission mechanisms, low-delay and high-reliability transmission of key data is realized on the premise of ensuring data security. Especially in emergency scenes such as sudden water quality change, through 5G slicing and differential compression technologies, real-time performance and bandwidth cost are effectively balanced, millisecond response of a control instruction is ensured, through federal transfer learning and digital twinning scene adaptation, on the premise that privacy data of each water plant is not shared, diagnosis capability of small sample faults is improved, and fault diagnosis efficiency is improved. And rapid parameter optimization in an extreme water quality scene is realized.

This invention provides an e-book lending management system based on OPAC bidirectional linkage, belonging to the field of library information technology. It includes: a hardware acceleration layer that constructs a dynamic resource distribution matrix and calculates the matrix norm in real time using an FPGA coprocessor, combined with an ASIC anti-collision controller to implement request queue scanning every 100ms and a redundant copy generation algorithm; a system service layer that deploys a dynamic priority scheduling engine, achieving intelligent resource allocation based on cross-campus collaboration coefficients and edge-cloud collaboration strategies, while recording borrowing operations and performing automated copyright revenue sharing audits through blockchain notarization services; and a user interaction layer that provides a bidirectional association search interface and a priority borrowing channel based on credit scoring. The system improves resource scheduling efficiency in high-concurrency scenarios through hardware-accelerated matrix norm calculation, an elastic copy allocation mechanism, and an anti-collision algorithm embedded in ASICs. Combined with geolocation scoring and blockchain technology, it achieves cross-campus resource collaboration and accurate allocation of copyright revenue.

The invention provides an Internet of Vehicles redundant data supplementary transmission method and system based on dynamic priority scheduling, and relates to the technical field of new energy vehicle Internet of Vehicles. The method comprises the following steps: acquiring multi-mode vehicle state time sequence data; analyzing the multi-modal vehicle state time sequence data through an early warning prediction model, and predicting the early warning probability of the data; determining a multi-modal data supplementary transmission priority based on the timeliness, the data volume and the early warning probability of the multi-modal data; performing hierarchical compression processing on different types of data based on the multi-modal data supplementary transmission priority to obtain compressed data; and storing the compressed data into the emergency cache region and / or the main storage region according to a preset rule, and carrying out supplementary transmission according to the supplementary transmission priority after the network is recovered. The method and the device are used in the process of complementary transmission of redundant data of the Internet of Vehicles based on dynamic priority scheduling, and solve the technical problems of high redundancy overhead and low complementary transmission efficiency of vehicle-mounted complementary transmission data in the prior art.

The invention relates to a continuous intelligent refueling control method for a fracturing unit, and the method achieves the integration of the monitoring of the fuel oil liquid level of a diesel-driven fracturing unit and the control of a continuous refueling device through the construction of a data center, and achieves the prediction of the oil consumption of each device of the fracturing unit through the introduction of an LSTM oil consumption prediction model and a dynamic priority scheduling algorithm. Dynamic priority refueling scheduling ensures timely fuel oil supply of the whole unit, and fully ensures continuity in the construction process of the fracturing unit. The system effectively solves the problems that a current continuous refueling automatic control system only supplies fuel oil simply according to high and low liquid level domain values, cannot cope with the working condition that multiple large-scale fracturing devices need to be refueled at the same time, and needs manual control; according to the invention, the labor intensity of operators can be greatly reduced, and the continuity of the construction operation of the diesel-driven fracturing unit is improved.

The invention provides an intelligent door lock cleaning service system and method based on multi-mode perception and dynamic scheduling, and belongs to the technical field of intelligent identity recognition. According to the system, a multi-mode interaction and infrared sensing unit is integrated through an intelligent door lock, and a cleaning instruction of a user is received and verified. And the housekeeper service system generates cleaning tasks by adopting a dynamic priority scheduling algorithm fused with user behavior prediction, and performs optimal allocation in combination with the real-time state of the intelligent door lock. A temporary authorization mechanism based on a one-time dynamic password or a two-dimensional code is provided for cleaning personnel, the mechanism is bound with the door lock state, and the safety is high. And the system monitors the task execution track and state in real time, and feeds back the progress to the user side through the encryption link. According to the invention, the problems that the traditional cleaning service is low in efficiency, opaque and disjointed with an access control system are solved, the intelligent and credible closed-loop management of the whole process from demand triggering to completion is realized, and the user experience and the service management efficiency are improved.

The invention provides an automatic processing method for experimental process state data based on artificial intelligence, and relates to the technical field of artificial intelligence, and the method comprises the steps: carrying out the feature extraction and fusion of multi-source heterogeneous data obtained in an experimental process, so as to output a real-time state data set reflecting an experimental process; according to the real-time state data set and the experimental process characteristics, performing dynamic priority scheduling and resource allocation on a plurality of concurrent decision calculation tasks to obtain an allocation result; and according to the distribution result, executing the scheduled task so as to output a series of decision-making instructions adaptive to the current experiment process. According to the invention, experimental stage identification and decision support based on an artificial intelligence rich knowledge base and interdisciplinary knowledge can be provided, the automation level of experimental intervention and the experimental safety are improved, the personnel participation risk is reduced, and the experimental record precision and the experimental result analysis depth are improved; and the experiment efficiency, the experiment safety and the discovery probability of a new experiment path and a new experiment result are remarkably improved.

The application discloses a kind of high-performance CPU-GPU collaborative processing architecture of audio integrated signal processor, belong to audio integrated signal processing technical field, this architecture is based on dynamic priority scheduling model, through hierarchical resource management and protocol level optimization, the efficient cooperation of CPU and GPU is realized, hardware layer uses multi-GPU cluster and distributed storage node, support high concurrency task processing;Transport layer fuses RapidIO and Ethernet protocol, respectively adapts short frame control signal and long packet data stream;Application layer calculates task resource demand by dynamic priority weight, and combines normalization allocation algorithm to guarantee the low latency of key task.The architecture in the scene of audio signal processing, task scheduling efficiency is improved by 40%, short frame transmission delay is as low as 0.5, long data stream throughput reaches 100Gbps, can satisfy the real-time and calculation accuracy demand under complex acoustic environment.

The invention belongs to the technical field of data communication, and provides a real-time network communication system and method, a storage medium and equipment. The real-time network communication system comprises a data grouping module, a dynamic priority scheduling module, a composite network diagnosis module and a data security transmission module, the data grouping module is used for grouping the acquired communication data; the dynamic priority scheduling module is used for performing dynamic priority scheduling on the communication data through a dual-priority queue scheduler and an event driving mechanism based on a data grouping result; the composite network diagnosis module is used for carrying out composite network diagnosis by deploying an embedded broadcast probe and calculating the bus health degree to carry out health degree evaluation; and the data security transmission module is used for performing encryption processing on the data of different groups based on the data grouping result and verifying data access and network connection. According to the real-time network communication system, the communication performance, the real-time performance, the reliability and the safety are improved.

The invention discloses a multi-dimensional data quality control method for offshore wind power environment data, and relates to the technical field of data analysis, and the method comprises the steps: obtaining the historical multi-dimensional data of a wind power plant in a target sea area, extracting the spatial-temporal characteristics of the multi-dimensional data, and constructing a multi-dimensional data knowledge base; based on the multi-dimensional data knowledge base, taking a target sea area fan as a node, taking the multi-dimensional environment parameters as edge weights, establishing a multi-dimensional environment-fan association map, and identifying abnormal data of a target sea area wind power plant; according to the identified abnormal data of the wind power plant in the target sea area, dividing the abnormal data into two types of environmental interference and equipment fault, and generating a multi-dimensional data quality portrait and a health degree evaluation report; and on the basis of the multi-dimensional data quality portrait and the health degree evaluation report, monitoring abnormal data of the target sea area wind power plant in real time to perform dynamic priority scheduling, and automatically generating a targeted sea area wind power plant multi-dimensional data governance optimization instruction. According to the invention, high-reliability and self-adaptive data basic guarantee is provided.

The present application relates to the production line material scheduling technical field, especially to a kind of double-source material dynamic priority scheduling method based on production line station state driving, comprising the following steps: S1, real-time acquisition production line each station's working state signal, double-source material's inventory state and availability signal, conveying equipment's task state signal;S2, based on station's working state signal quantitative evaluation station state, in combination with double-source material's inventory state and availability, conveying equipment's task state, dynamically calculate each station from double-source material supply source obtains the distribution priority of material;S3, according to distribution priority generation global optimal task execution sequence, issues scheduling instruction to corresponding execution unit;S4, receives the task execution feedback signal of execution unit, updates system state and triggers new round of scheduling decision.The present application can solve the staticity, local optimization and response lag problem of existing scheduling method.

The present application relates to the technical field of data collection and real-time calculation, and in particular to a method for on-demand accurate real-time data collection and calculation. The method comprises the following steps: through multi-dimensional on-demand collection request analysis and dynamic priority scheduling, the present application performs adaptive data collection and incremental transmission optimization on enterprise data, realizes real-time data processing and end-to-end consistency guarantee, and performs multi-dimensional data readiness confirmation and intelligent calculation triggering, so as to reduce data collection cost, improve data scheduling flexibility and calculation efficiency.

The application discloses a dynamic-priority-based relay protection automatic test sequence optimization method and system, and belongs to the technical field of power relay protection. n S1, test task modeling and parameterization; the test case to be executed is modeled into a task set, n the total number of tasks, and multi-dimensional feature parameters are defined for each task; S2, real-time monitoring of system resource state; in the test execution process, the resource state vector of the test platform is continuously acquired; S3, dynamic priority calculation and task selection; according to the current resource state and task parameters, the dynamic priority scores of the executable candidate set and each ready task are calculated, and the task with the highest score is selected for execution; S4, task execution and state updating; S5, loop iteration, steps S2 to S4 are repeated until all tasks are executed. By introducing the dynamic priority scheduling mechanism, the contradiction between the static preset of the test sequence and the dynamic change of the test resources is solved.

The application relates to the technical field of industrial Internet of Things, and particularly discloses an embedded Internet of Things data gateway based on resource sensing and a data processing method, which introduces a protocol feature code single matching mechanism to replace multi-round state analysis, combines with a chain JSON encapsulation rule to avoid heap operation without dynamic memory application, and uses a dynamic priority scheduler to monitor the uplink buffer usage rate and the system real-time load in real time, dynamically adjusts the event execution sequence, actively triggers a simplified analysis mode and implements flow control under high load, so that the memory stability and instruction response certainty are significantly improved while the protocol compatibility is ensured, and the dual hard requirements of reliability and real-time performance of the industrial Internet of Things are met.

The invention discloses a dynamic priority scheduling method and system based on multi-heat-source cooperative heat supply in a greenhouse, and the method comprises the following steps: S1, collecting three-dimensional environment parameters in the greenhouse in real time through a multi-mode sensor array, the three-dimensional environment parameters comprising temperature field distribution, humidity gradient change and photosynthetically active radiation intensity; s2, carrying out real-time preprocessing on operation parameters of each heat source by adopting an edge computing node, wherein the operation parameters comprise instantaneous power fluctuation characteristics, a unit time energy consumption curve, a fault prediction state and dynamic residual life; and S3, establishing a crop growth demand-environmental parameter mapping model, and dynamically generating a target heat supply demand map according to a three-dimensional thermodynamic simulation result of temperature field distribution in combination with crop variety specific parameters. According to the method and the system, efficient collaborative scheduling of multiple heat sources in the greenhouse can be realized, the energy utilization efficiency is improved, and the crop growth environment is accurately regulated and controlled.

The application relates to the technical field of electric vehicle charging and discloses a flexible direct-current charging pile power distribution method and system based on dynamic priority scheduling, which comprises the following steps: real-time monitoring of power unit states and delay compensation, and the direct available and quasi-available units are included in the schedulable upper limit statistics; when a target terminal request is received, the schedulable upper limit quantity is taken as a target to distribute power units, so as to provide the maximum initial charging power; during the charging process, the real-time demand power of the vehicle is filtered to calculate the minimum demand quantity, and the dynamic redundancy is set based on the demand change rate; when the online unit exceeds the demand, the shutdown priority score is calculated by combining the efficiency loss, the operation time and the temperature and other multi-dimensional parameters, the redundant units are orderly controlled to sleep; the adjustment is circularly executed, and the resources are safely released after the charging is completed. The application can improve the initial charging response speed, effectively avoid light-load low-efficiency operation, maximize the system energy efficiency and balance the equipment life.

The invention relates to the technical field of memory chip read-write control, and discloses a memory chip read-write control method and system. The method comprises the following steps: firstly, receiving a plurality of read-write requests, generating structured request data according to preset dimension classification such as request types and data block sizes, constructing a multi-dimensional time sequence constraint model containing a time axis and the like, and determining an initial time sequence constraint condition; and then executing data flow simulation to generate a preliminary scheduling scheme, and after path conflict detection, performing optimization by using a dynamic priority scheduling algorithm to generate a conflict-free optimal scheduling scheme. And then synchronously correcting model parameters with real-time load data, and generating an instruction set to trigger a scheduling process. According to the technology, multi-factor optimization scheduling is comprehensively considered, the read-write performance of the storage chip is improved, energy consumption is reduced, system stability and adaptability are enhanced, and the method is suitable for various scenes needing efficient read-write control of the storage chip.

This invention discloses a model training and resource scheduling method and system based on LlamaFactory, relating to the field of resource scheduling and distributed model training optimization technology. Specifically, this invention combines the LlamaFactory model training process with a dynamic priority scheduling mechanism to construct an intelligent training and resource allocation system for multi-task, multi-GPU clusters. This achieves adaptive adjustment of task sorting and resource allocation. By combining a comprehensive dynamic priority score function with a cat swarm optimization algorithm, it realizes efficient scheduling solutions under multi-objective constraints, obtaining high-quality scheduling solutions within a limited time, improving the overall energy efficiency and task throughput of the cluster. Furthermore, by combining the LlamaFactory training loop structure with a safe preemption point design, it achieves refined interruption control during the training process, improving the success rate of task migration and recovery.

The invention relates to the technical field of emergency management informatization and intelligent collaborative scheduling control, in particular to a dynamic priority scheduling method for multi-disaster emergency collaboration, which comprises the following steps: acquiring multi-modal sensing data uploaded by a preset fixed sensing node to generate a modal imperfection degree representing a data missing state; inputting the multi-modal sensing data into a preset physical evolution prediction model, and calculating a data uncertainty penalty term of the task node; calculating a current global situation awareness entropy based on the evolution emergency degree and the data uncertainty penalty term; judging whether the global situation sensing entropy is greater than a preset sensing entropy safety threshold value or not to generate an absolute optimal scheduling instruction; the robustness sub-optimal scheduling instruction or the absolute optimal scheduling instruction is taken as a target scheduling instruction to be issued to a preset maneuvering execution node, and the global situation awareness entropy in the global task distribution network is updated; according to the method, the recognition capability of the system on the fragmentation degree of the sensing network in an extreme disaster scene is remarkably improved.

The invention discloses a data acquisition method based on an end-cloud integrated architecture, which is suitable for an automatic driving data acquisition scene, is executed by a vehicle end system, and specifically comprises the following steps: receiving an acquisition configuration issued by a cloud end system; deploying a collection task according to the configuration, and continuously storing the original data through the annular cache; monitoring a plurality of acquisition triggers, and performing disk falling processing on the annular cache data when the acquisition triggers are triggered; carrying out preprocessing on the disk falling data; adding the tasks into an uploading queue according to the priorities of the acquisition triggers, and performing dynamic priority scheduling; and segmenting the data packet and uploading the data packet to a cloud system. Through cooperation of the annular cache and the trigger disk, cache data is immediately stored when an event is triggered, key event data loss caused by data coverage is avoided, and data integrity is ensured; through the dynamic priority scheduling based on the type of the collection trigger, the emergency degree of the task is distinguished, so that the priority uploading of the high-priority task is ensured, and the real-time performance of the system is improved.

The invention provides a dual-mode communication load monitoring system and method based on adaptive switching of HPLC and HRF, and the system comprises a dual-mode communication module which is used for the parallel transmission and dynamic switching of two communication modes of HPLC and HRF; the load monitoring unit is used for collecting load data of the power equipment in real time; the self-adaptive switching control unit is used for evaluating the communication quality and a preset dynamic weight and generating a switching instruction; the dynamic priority scheduling unit is used for adjusting task estimation running time in real time and optimizing communication resource distribution by adopting an improved HRF dynamic priority scheduling algorithm based on load data in an HRF communication mode; and the load prediction correction unit dynamically corrects a load prediction value through an exponential weighted moving average and resource demand modeling method in combination with historical load data and a real-time monitoring result, and feeds back the load prediction value to the adaptive switching control unit. And the continuity of load data transmission is ensured.

This application provides a method and system for redundant data retransmission in vehicle-to-everything (V2X) networks based on dynamic priority scheduling, relating to the field of V2X technology for new energy vehicles. The method includes: acquiring multimodal vehicle state time-series data; analyzing the multimodal vehicle state time-series data using an early warning prediction model to predict the early warning probability of the data; determining the retransmission priority of multimodal data based on the timeliness, data volume, and early warning probability of the multimodal data; performing layered compression processing on different types of data based on the retransmission priority to obtain compressed data; storing the compressed data in an emergency buffer and / or main storage area according to preset rules, and retransmitting it according to the retransmission priority after network recovery. This application solves the technical problems of high data redundancy overhead and low retransmission efficiency in existing technologies for redundant data retransmission in V2X networks based on dynamic priority scheduling.

This invention provides a method and system for scheduling equipment systems based on unmanned coal mining, relating to the field of equipment scheduling technology. By integrating safety level classification, multi-source data-driven conflict identification, and dynamic priority scheduling mechanisms, this invention achieves an organic unity of safety, intelligence, and efficiency. On one hand, it establishes an evaluation matrix based on historical risk cases, classifies equipment into safety levels according to the severity of failure consequences, and presets conflict coefficients. When a conflict occurs, it dynamically increases the conflict coefficient of high-risk equipment based on real-time scenarios, significantly improving the inherent safety level of the system. On the other hand, it relies on an industrial cloud platform to clean and analyze the location, status, and environmental data collected by sensors, accurately identifying logical conflicts where multiple devices compete for exclusive resources. It then uses a rolling, updated priority sequence to guide path planning, task timing, and energy allocation, achieving distributed collaborative control of "cloud decision-making—side execution."

The invention relates to the technical field of intelligent manufacturing, and particularly discloses a manufacturing industry-oriented digital cooperative supervision method and platform, and the method comprises the steps: S1, dividing a production line into a plurality of supervision sections, configuring an edge calculation module and a plurality of Internet of Things monitoring sensors for each section, and collecting the state parameters of a production environment and equipment in real time; according to the method, edge calculation and cloud intelligent analysis are combined, multi-level and self-adaptive identification and evaluation of production anomalies are realized, and data transmission quantity and cloud load are remarkably reduced by performing preliminary identification and quantification of anomalies on the edge side and introducing a section function weight and dynamic priority scheduling mechanism into the cloud; and the real-time performance and the accuracy of key abnormity response are improved, so that effective intelligent monitoring and collaborative management are carried out on the manufacturing production line.