AGV single vehicle state monitoring method based on operation state analysis

Abstract

The invention relates to the technical field of AGV monitoring, in particular to an AGV single vehicle state monitoring method based on operation state analysis, and the method comprises the steps: calculating a multi-dimensional operation state index based on the multi-source sensor data of an AGV, and generating a comprehensive state score; dynamically adjusting operation parameters of the AGV monitoring system based on the comprehensive state score and the change trend thereof; and based on the link quality index calculated in real time and the comprehensive state score, cooperatively adjusting a data transmission strategy between the AGV and the cloud. When the communication quality is lower than a preset threshold value, optimizing a local state record according to the comprehensive state score; and carrying out grading diagnosis and verification on the detected abnormity in combination with the comprehensive state score.

Description

Technical Field

[0001] This invention relates to the field of AGV monitoring technology, and in particular to a method for monitoring the status of a single AGV based on operational status analysis. Background Technology

[0002] With the development of intelligent manufacturing and smart logistics, the application of Automated Guided Vehicles (AGVs) is becoming increasingly widespread. Efficient and reliable status monitoring and fault diagnosis of AGV clusters are crucial for ensuring their stable operation and improving overall system efficiency.

[0003] However, existing AGV monitoring systems still have the following shortcomings: wireless networks (such as Wi-Fi) in industrial environments are susceptible to interference, leading to packet loss or delays in monitoring data, and critical status information cannot be uploaded in a timely manner. When the AGV is in a network blind spot or communication is interrupted, its operating status cannot be recorded, resulting in discontinuity in status history and affecting subsequent performance analysis and fault tracing. Alarm mechanisms based on fixed thresholds are prone to misjudging instantaneous interference or normal fluctuations under specific operating conditions as faults, generating a large number of false alarms and increasing the maintenance burden.

[0004] Existing solutions often focus on single-point optimizations, such as simply improving network hardware or optimizing a single diagnostic algorithm, lacking a collaborative mechanism that can dynamically adjust the entire monitoring strategy based on the AGV's real-time health and performance. This leads to rigid system resource allocation; when the AGV's condition deteriorates and requires close monitoring, sufficient data may not be available due to network or policy limitations; conversely, when the AGV's condition is good, unnecessary communication and computational overhead may occur. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the prior art by analyzing the status of the AGV in real time and dynamically adjusting the communication, data recording and fault diagnosis links accordingly, so as to ensure the reliable acquisition of AGV operation data in complex environments and ensure the reliability and efficiency of monitoring.

[0006] The technical solution proposed in this invention is: an AGV single vehicle status monitoring method based on operation status analysis, the method comprising: calculating multi-dimensional operation status indicators based on multi-source sensor data of the AGV, and generating a comprehensive status score; Based on the comprehensive status score and its changing trend, the operating parameters of the AGV monitoring system are dynamically adjusted. Based on the real-time calculated link quality index and the comprehensive status score, the data transmission strategy between the AGV and the cloud is adjusted collaboratively. When the communication quality is lower than a predetermined threshold, the local status record is optimized based on the comprehensive status score. The detected anomalies are graded and verified by combining the comprehensive status score.

[0007] Preferably, the calculation of multi-dimensional operating status indicators based on multi-source sensor data of AGV and the generation of a comprehensive status score includes: Calculate the health status index, performance status index, and load status index; the health status index is derived based on at least one of mechanical vibration spectrum, electrical parameter deviation, and navigation sensor quality. By fusing the health status index, performance status index, and load status index through a pre-trained fuzzy logic or neural network model, a comprehensive status score between 0 and 1 is generated. Analyze the short-term trend of the comprehensive state score and predict the state evolution in future time periods.

[0008] Preferably, the dynamic adjustment of the operating parameters of the AGV monitoring system based on the comprehensive status score and its changing trend includes: Based on the comprehensive status score, the operating status of the AGV is divided into multiple levels; Based on the current status level, dynamically assign sending priorities and recording importance weights to different categories of monitoring data; When the overall status score is detected to be trending negatively and falling below the warning threshold, predictive monitoring enhancement operations are triggered, including immediately uploading a complete status snapshot and increasing the frequency of key data recording.

[0009] Preferably, the link quality index based on real-time calculation and the comprehensive status score are used to coordinately adjust the data transmission strategy between the AGV and the cloud, including: Based on the comprehensive status score, the reporting frequency of status data is dynamically adjusted. The lower the status score, the greater the increase coefficient of the reporting frequency of key health and safety data. Based on the comprehensive status score and the link quality index, the local data caching time and cache replacement strategy are dynamically adjusted. When the overall status score is below the first threshold and the link quality index indicates network instability, communication resources are allocated preferentially to security alarm data and health degradation data.

[0010] Preferably, optimizing the local status record based on the comprehensive status score when the communication quality is lower than a predetermined threshold includes: When the status score is low, allocate protected storage space for status record data to prevent it from being overwritten by regular data.

[0011] Preferably, the step of combining comprehensive status scoring to classify and verify detected anomalies includes: When constructing the fault feature vector, the comprehensive state score, state indices of each dimension and their changing trends are incorporated as contextual features. The sensitivity threshold for fault diagnosis is dynamically adjusted based on the comprehensive status score. The lower the status score, the lower the diagnosis threshold is to improve sensitivity. Based on the comprehensive status score, failure probability, and failure impact, a comprehensive risk score is calculated, and the priority and urgency of maintenance are determined accordingly.

[0012] Preferred options also include: By utilizing a reinforcement learning framework, and with the goal of improving the overall effectiveness of the monitoring system, the parameters of each adjustment strategy in the state-driven control step are optimized.

[0013] An electronic device for implementing the aforementioned AGV single-vehicle status monitoring method based on operational status analysis, comprising: The operation status analysis engine, deployed at the edge of the AGV and / or in the cloud, is used to calculate multi-dimensional operation status indicators and comprehensive status scores; An adaptive controller, connected to the operating status analysis engine, is used to generate parameter adjustment instructions for each module of the monitoring system based on the comprehensive status score. An edge agent module, deployed on the AGV body, includes a communication management unit, a status recording unit, and a rapid diagnostic unit configured to receive instructions from the adaptive controller; The cloud-based analytics platform includes a deep diagnostic engine configured to receive instructions from the adaptive controller, a model management unit, and a data fusion center that interacts with the runtime analysis engine.

[0014] Preferably, the adaptive regulator includes: The strategy decision-making unit is pre-set with a state-policy table that maps state scores to different operation modes; The parameter calculation unit is used to calculate the dynamic value of at least one of the following in real time: communication frequency, recording detail, and diagnostic threshold, based on the status score and a preset algorithm. The predictive execution unit is used to proactively trigger data backup and early warning reporting operations when the state trend deteriorates.

[0015] A computer-readable storage medium storing a computer program that is executed by a processor to implement the aforementioned AGV single-vehicle status monitoring method based on operational status analysis.

[0016] The beneficial effects of this invention are: 1. This invention adjusts the monitoring intensity in real time based on the AGV's own status, strengthening monitoring when the status is poor and conserving resources when the status is good, thus achieving global optimization of monitoring efficiency. Through status-aware communication and storage, the delivery rate and integrity of critical status data are significantly improved in unstable network environments.

[0017] 2. This invention incorporates a comprehensive state score when constructing the fault feature vector, enabling the system to more intelligently distinguish between true and false faults and reduce false alarm and missed alarm rates. Through reinforcement learning, the corresponding weights are adjusted, allowing the system to continuously adapt to new operating environments. Attached Figure Description

[0018] Figure 1 This is a flowchart of an AGV single-vehicle status monitoring method based on operational status analysis according to the present invention. Detailed Implementation

[0019] The following description is intended to disclose the present invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious modifications will occur to those skilled in the art. The basic principles of the invention defined in the following description can be applied to other embodiments, modifications, improvements, equivalents, and other technical solutions that do not depart from the spirit and scope of the invention.

[0020] It is understood that the term "a" should be understood as "at least one" or "one or more," that is, in one embodiment, the number of an element can be one, while in another embodiment, the number of the element can be multiple, and the term "a" should not be understood as a limitation on the number.

[0021] refer to Figure 1 The technical solution provided by this invention is: a method for monitoring the status of a single AGV based on operational status analysis, the method comprising: Step 1: Calculate multi-dimensional operational status indicators based on multi-source sensor data of the AGV and generate a comprehensive status score; specifically including the following steps: Step 1.1: Calculate the health status index, performance status index, and load status index; The health status index is derived based on at least one of mechanical vibration spectrum, electrical parameter deviation, and navigation sensor quality. Specifically, it involves acquiring vibration spectrum, battery charge, battery discharge current and voltage, lidar signal-to-noise ratio, and circuit leakage current by collecting multi-source sensor data from the AGV body. Obtain the characteristic frequencies of the fault, such as the amplitude corresponding to the fault frequencies of the bearing outer ring, inner ring, and ball bearings. The mechanical health status index ;in, Indicates the first The amplitude of the fault frequency; The electrical deviation mainly refers to the battery's health. The ratio of the dynamic voltage drop of the battery under the current pulse to its initial value is calculated based on the emitted pulse voltage; this is the internal resistance increase ratio. .

[0022] Then, the battery health status index ;in, The actual maximum capacity of the current battery can be estimated online by combining the ampere-hour integration method with battery discharge curve fitting. Indicates the rated capacity of the battery; The sensor quality refers to the health status of the LiDAR. Specifically, first, point cloud data of the LiDAR is obtained; then, the number of valid points and the number of noise points are extracted from the point cloud data, and the ratio of valid points to noise points is calculated. Then, the health status of the lidar ;in, Indicates the signal-to-noise ratio of the lidar; Obtain Health Status Index ,in, , , Indicates the fusion weight coefficient; The calculation process for the performance status index is as follows: Obtain task instructions, task start and end times, task route length, target point coordinates, task status feedback (success, failure, timeout), and AGV real-time speed and positioning data from the AGV's task management system. Computational task performance Navigation performance and efficiency performance ; Then, performance status index ; in, , , This represents the task performance fusion weighting coefficient. This indicates the number of tasks that were successfully completed. This indicates the total number of tasks received, and the coordinate offset distance. , Indicates the length of the task route. This represents the average actual speed of the AGV. Indicates the average speed threshold; and This indicates the X-axis and Y-axis offsets when the AGV reaches the target point; The calculation process for the load state index is as follows: The load weight is obtained from the AGV's own pressure sensor or weighing sensor, the ambient temperature and humidity information is obtained through the temperature and humidity sensor, and the ambient particulate matter content is obtained through the particulate matter sensor. Calculate load factor Time load factor ;in, The actual load weight is indicated by measurement using a pressure sensor. Indicates the rated load capacity of the AGV; Indicates continuous running time. Indicates the threshold for a single continuous run; The load state index is Among them, the environmental index ;in, Indicates ambient temperature. Indicates the ideal working environment temperature. This indicates the concentration of particulate matter in the environment (PM10, PM2.5, etc.). Indicates the threshold for particulate matter content; Step 1.2: Using a pre-trained fuzzy logic or neural network model, fuse the health status index, performance status index, and load status index to generate a comprehensive status score between 0 and 1. Specifically, the health status index, performance status index, and load status index are normalized and then input into the pre-trained fuzzy logic or neural network model to output the comprehensive status score. .

[0023] Step 1.3: Analyze the short-term trend of the comprehensive state score and predict the state evolution in the future. Specifically, calculate the comprehensive state score. , ;Will The input is fed into a pre-trained Long Short-Term Memory (LSTM) network, which outputs a comprehensive state score for the next possible time. and its uncertainty That is, the confidence level of the state score. Among them, Indicates time interval, Indicates the task start time. Indicates the task completion time.

[0024] Step 2: Based on the comprehensive status score and its changing trend, dynamically adjust the operating parameters of the AGV monitoring system, specifically including the following steps: Step 2.1: Based on the comprehensive status score, the operating status of the AGV is divided into multiple levels, specifically as follows: if The AGV's operating status is excellent. if The AGV is operating in a good condition. if The AGV is operating in a normal state. if The AGV's operating status is at the "concern level"; if The AGV's operating status is abnormal.

[0025] Step 2.2: Based on the current status level, dynamically assign sending priorities and recording importance weights to different categories of monitoring data; Assign basic priorities to different types of monitoring data to form a basic priority sequence. The different types of monitoring data include task instructions, running status, health status, and running log data.

[0026] In this embodiment , Indicates the priority of task instruction data, Indicates the priority of runtime status data. Indicates the priority of health status data. This indicates the priority of the runtime log data. .

[0027] If the AGV's operating status is excellent, good, or average, the data will be fed back in the order of basic priority. If the AGV's operating status is at the "Concern" level, the priority of the health status feedback data is adjusted to... And record the importance level weights. .

[0028] Step 2.3: When the overall status score is detected to be on a negative trend and below the warning threshold, a predictive monitoring enhancement operation is triggered. The operation includes immediately uploading a complete status snapshot and increasing the frequency of key data recording.

[0029] The overall status score showing a negative trend and falling below the warning threshold refers to... and ; If the above conditions are met, predictive monitoring enhancement operations will be triggered, including: Back up the current task instructions, running status, health status, and running log data to local storage and then upload them to the cloud; Increase the frequency of collecting health status and operation log data.

[0030] Step 3: Based on the real-time calculated link quality index and the comprehensive status score, collaboratively adjust the data transmission strategy between the AGV and the cloud, specifically including: Step 3.1: Based on the comprehensive status score, dynamically adjust the reporting frequency of status data, wherein the lower the status score, the greater the increase coefficient of the reporting frequency of key health and safety data.

[0031] Specifically: when At the same time, increase the reporting frequency of health status and operation log data, and the new reporting frequency is consistent with the collection frequency of these two types of data.

[0032] The reporting frequency for health status data has been adjusted back to the original reporting frequency. The reporting frequency of runtime log data has been adjusted to ,in, The importance weights represent the health status and operational log data.

[0033] exist In this case, the importance weight of health status data is greater than that of operation log data.

[0034] Step 3.2: Based on the comprehensive status score and the link quality index, dynamically adjust the local data caching time and cache replacement strategy; specifically: Calculate the time from heartbeat packet transmission to interpretation and feedback. ; Calculate multiple consecutive times Standard deviation ; The packet loss rate is obtained by calculating the ratio of the number of heartbeat packets sent to the number of feedback packets received within multiple time windows. ; This indicates the number of heartbeat packets sent. This indicates the number of heartbeat packets received as feedback. Obtain link quality index ; if If so, the link quality is considered excellent; if If so, the link quality is considered good; if If so, the link quality is judged to be poor. , , Indicates the link quality fusion weight; , This indicates the threshold for link quality classification.

[0035] when and When this is the case, local storage space should be allocated first for storing health status and operation log data.

[0036] Step 3.3: When the overall status score is lower than the first threshold and the link quality index indicates network instability, communication resources are prioritized for security alarm data and health degradation data, i.e. When necessary, alarm information is generated, and communication bandwidth is prioritized for health status and alarm information to ensure monitoring of AGB health status.

[0037] Step 4: When the communication quality is lower than a predetermined threshold, optimize the local status record based on the comprehensive status score, specifically including the following steps: When the status score is low, allocate protected storage space for the status record data to prevent it from being overwritten by regular data; that is, when... At that time, allocate ROM storage space for health status data to prevent it from being overwritten by other data.

[0038] Step 5: Based on the comprehensive status score, classify and verify the detected anomalies, which includes the following steps: Step 5.1: When constructing the fault feature vector, the comprehensive state score, state indices of each dimension, and their changing trends are incorporated as contextual features. Specifically: the fault feature vector is... ; The fault feature vector is normalized and then input into a pre-trained fault prediction model (built based on a convolutional neural network), which outputs a predicted fault probability value. ; if If so, it is determined that the AGV will malfunction at a future time. Indicates the fault threshold; Step 5.2: Dynamically adjust the sensitivity threshold for fault diagnosis based on the comprehensive status score. The lower the status score, the lower the diagnostic threshold is to improve sensitivity. Specifically: when When, adjust the fault threshold to To reduce the sensitivity of fault diagnosis; when When, adjust the fault threshold to This is to improve the sensitivity of fault diagnosis.

[0039] Step 5.3: Based on the comprehensive status score, failure probability, and failure impact, calculate the comprehensive risk score, and determine the priority and urgency of maintenance accordingly, specifically as follows: The failure probability is the same as the failure likelihood, and the failure impact is... ; A comprehensive risk score is calculated based on the overall condition score, failure probability, and failure impact. ;in, These represent risk weights; This represents the normalized overall state score; if If so, the AGV needs to be repaired immediately; If so, the AGV will perform maintenance after completing the current task; if The AGV will then undergo maintenance after completing all its tasks for the day. , This indicates the priority segmentation threshold.

[0040] In some preferred embodiments, reinforcement learning algorithms are used to update risk weight coefficients in real time according to different application scenarios. For example, for application scenarios with high real-time requirements, optimization is performed. This ensures sensitivity to the impact of failures; for example, in application scenarios with high stability requirements (or scenarios where AGV equipment is severely aged), optimization is necessary. This is to ensure sensitivity to the operating status.

[0041] The present invention also provides an electronic device for implementing the aforementioned AGV single-vehicle status monitoring method based on operational status analysis, comprising: The operation status analysis engine, deployed at the edge of the AGV and / or in the cloud, is used to calculate multi-dimensional operation status indicators and comprehensive status scores; An adaptive controller, connected to the operating status analysis engine, is used to generate parameter adjustment instructions for each module of the monitoring system based on the comprehensive status score. An edge agent module, deployed on the AGV body, includes a communication management unit, a status recording unit, and a rapid diagnostic unit configured to receive instructions from the adaptive controller; The cloud-based analytics platform includes a deep diagnostic engine configured to receive instructions from the adaptive controller, a model management unit, and a data fusion center that interacts with the runtime analysis engine.

[0042] The adaptive regulator includes: The strategy decision-making unit is pre-set with a state-policy table that maps state scores to different operation modes; The parameter calculation unit is used to calculate the dynamic value of at least one of the following in real time: communication frequency, recording detail, and diagnostic threshold, based on the status score and a preset algorithm. The predictive execution unit is used to proactively trigger data backup and early warning reporting operations when the state trend deteriorates.

[0043] The present invention also provides a computer-readable storage medium storing a computer program, which is executed by a processor to implement the aforementioned AGV single-vehicle status monitoring method based on operational status analysis.

[0044] The processes described above with reference to the flowcharts in the embodiments disclosed in this invention can be implemented as computer software programs. The embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), it performs the functions defined in the methods of this application. It should be noted that the computer-readable medium described above in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wire segments, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless segments, wire segments, optical fibers, RF, etc., or any suitable combination thereof.

[0045] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0046] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are merely examples and do not limit the present invention. The purpose of the present invention has been fully and effectively achieved. The functions and structural principles of the present invention have been shown and explained in the embodiments. Without departing from the principles described, the implementation of the present invention may have any changes or modifications.

Claims

1. A method for monitoring the status of a single AGV based on operational status analysis, characterized in that, The method includes: Calculate multi-dimensional operational status indicators based on multi-source sensor data of AGVs and generate a comprehensive status score; Based on the comprehensive status score and its changing trend, the operating parameters of the AGV monitoring system are dynamically adjusted. Based on the real-time calculated link quality index and the comprehensive status score, the data transmission strategy between the AGV and the cloud is adjusted collaboratively. When the communication quality is lower than a predetermined threshold, the local status record is optimized based on the comprehensive status score. The detected anomalies are graded and verified by combining the comprehensive status score.

2. The AGV single-vehicle status monitoring method based on operational status analysis according to claim 1, characterized in that, The AGV-based multi-source sensor data is used to calculate multi-dimensional operational status indicators and generate a comprehensive status score, including: Calculate the health status index, performance status index, and load status index; the health status index is derived based on at least one of mechanical vibration spectrum, electrical parameter deviation, and navigation sensor quality. By fusing the health status index, performance status index, and load status index through a pre-trained fuzzy logic or neural network model, a comprehensive status score between 0 and 1 is generated. Analyze the short-term trend of the comprehensive state score and predict the state evolution in future time periods.

3. The AGV single-vehicle status monitoring method based on operational status analysis according to claim 2, characterized in that, The dynamic adjustment of the AGV monitoring system's operating parameters based on the comprehensive status score and its changing trend includes: Based on the comprehensive status score, the operating status of the AGV is divided into multiple levels; Based on the current status level, dynamically assign sending priorities and recording importance weights to different categories of monitoring data; When the overall status score is detected to be trending negatively and falling below the warning threshold, predictive monitoring enhancement operations are triggered, including immediately uploading a complete status snapshot and increasing the frequency of key data recording.

4. The AGV single-vehicle status monitoring method based on operational status analysis according to claim 3, characterized in that, The link quality index based on real-time calculation and the comprehensive status score are used to coordinately adjust the data transmission strategy between the AGV and the cloud, including: Based on the comprehensive status score, the reporting frequency of status data is dynamically adjusted. The lower the status score, the greater the increase coefficient of the reporting frequency of key health and safety data. Based on the comprehensive status score and the link quality index, the local data caching time and cache replacement strategy are dynamically adjusted. When the overall status score is below the first threshold and the link quality index indicates network instability, communication resources are allocated preferentially to security alarm data and health degradation data.

5. The AGV single-vehicle status monitoring method based on operational status analysis according to claim 4, characterized in that, When the communication quality is lower than a predetermined threshold, optimizing the local status record based on the comprehensive status score includes: When the status score is low, allocate protected storage space for status record data to prevent it from being overwritten by regular data.

6. The AGV single-vehicle status monitoring method based on operational status analysis according to claim 5, characterized in that, The step of combining comprehensive status scoring to classify, diagnose, and verify detected anomalies includes: When constructing the fault feature vector, the comprehensive state score, state indices of each dimension and their changing trends are incorporated as contextual features. The sensitivity threshold for fault diagnosis is dynamically adjusted based on the comprehensive status score. The lower the status score, the lower the diagnosis threshold is to improve sensitivity. Based on the comprehensive status score, failure probability, and failure impact, a comprehensive risk score is calculated, and the priority and urgency of maintenance are determined accordingly.

7. The AGV single-vehicle status monitoring method based on operational status analysis according to claim 6, characterized in that, Also includes: By utilizing a reinforcement learning framework, and with the goal of improving the overall effectiveness of the monitoring system, the parameters of each adjustment strategy in the state-driven control step are optimized.

8. An electronic device for implementing the AGV single-vehicle status monitoring method based on operational status analysis as described in any one of claims 1-7, characterized in that, include: The operation status analysis engine, deployed at the edge of the AGV and / or in the cloud, is used to calculate multi-dimensional operation status indicators and comprehensive status scores; An adaptive controller, connected to the operating status analysis engine, is used to generate parameter adjustment instructions for each module of the monitoring system based on the comprehensive status score. An edge agent module, deployed on the AGV body, includes a communication management unit, a status recording unit, and a rapid diagnostic unit configured to receive instructions from the adaptive controller; The cloud-based analytics platform includes a deep diagnostic engine configured to receive instructions from the adaptive controller, a model management unit, and a data fusion center that interacts with the runtime analysis engine.

9. The AGV single-vehicle status monitoring method based on operational status analysis according to claim 8, characterized in that, The adaptive regulator includes: The strategy decision-making unit is pre-set with a state-policy table that maps state scores to different operation modes; The parameter calculation unit is used to calculate the dynamic value of at least one of the following in real time: communication frequency, recording detail, and diagnostic threshold, based on the status score and a preset algorithm. The predictive execution unit is used to proactively trigger data backup and early warning reporting operations when the state trend deteriorates.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which is executed by a processor to implement the AGV single-vehicle status monitoring method based on operational status analysis as described in any one of claims 1-7.

Images