Industrial big data monitoring and risk assessment system

Abstract

The invention relates to the technical field of industrial data assessment, in particular to an industrial big data monitoring and risk assessment system. Multi-dimensional industrial big data risk assessment is realized through production monitoring, operation monitoring, AGV equipment monitoring, associated equipment health monitoring and supply chain monitoring, and finally, an intelligent key switching rule between a current monitoring time period and a next monitoring time period is constructed based on assessment data and assessment results of each time through a dynamic key management scheme, so that the risk assessment of the AGV equipment is realized. The flexibility and safety of data management are improved, and meanwhile, potential safety hazards caused by secret key leakage are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial data assessment, and in particular to an industrial big data monitoring and risk assessment system. Background Art

[0002] With the rapid development of intelligent manufacturing and big data technologies, modern production systems increasingly rely on various real-time monitoring and data analysis methods to optimize production efficiency, ensure equipment health, and enhance supply chain flexibility and responsiveness. However, in complex production environments, how to comprehensively monitor data across multiple dimensions, including production status, warehouse center scheduling, equipment operation, personnel operations, and supply chain changes, conduct effective risk assessments, and implement real-time response measures, has become a key challenge in improving the efficiency and accuracy of industrial big data management.

[0003] Among them, for warehouse center scheduling, the AGV equipment currently performs operations according to preset scales by presetting the control system. Therefore, how to combine its operating status in the warehouse center with industrial big data for evaluation, consider the dynamic impact of the warehouse center AGV equipment on industrial big data, and improve the accuracy of industrial big data analysis is also a problem that needs to be solved; In addition, the current monitoring of equipment operation mainly relies on sensor data collection, and the sensor status is not analyzed and evaluated in advance. Therefore, if there is an abnormality in the sensor, it is difficult to achieve real-time monitoring and accurate early warning based directly on the monitoring data of the sensor. Summary of the Invention

[0004] In response to the above-mentioned shortcomings of the existing technology, the present invention provides an industrial big data monitoring and risk assessment system, which can effectively solve the problem in the existing technology that it is impossible to improve the accuracy of industrial big data analysis and assessment.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: The present invention provides an industrial big data monitoring and risk assessment system, which at least includes: Production monitoring unit, predicting production monitoring value SC; The active operation monitoring unit obtains the active operation monitoring value SK and also includes: AGV equipment monitoring unit is divided into: Driving risk monitoring: determine the driving path constructed by the AGV equipment, monitor the real-time coordinates of the AGV equipment, determine whether it deviates from the driving path and generate a deviation path, and calculate the driving deviation risk value SRA based on the deviation path, the driving path deviation interval distance SP, and the deviation driving time ST; Equipment collision monitoring, calculation of equipment collision value SPA; Task risk monitoring: Based on the task dependency network, the order and dependency between multiple tasks of the AGV equipment are analyzed, the total delay value DIA of the task is calculated, and the AGV equipment monitoring value SDA is obtained comprehensively; The associated device monitoring unit predicts the associated device monitoring value y of the associated device, where: Predetermine the sensors related to the associated equipment, analyze usage data to determine abnormal sensors, and re-determine the monitoring time period based on the detection loss time and disposal loss time of the abnormal sensors; Supply chain monitoring unit, predicting the supply chain monitoring value yg of the supply chain; The production monitoring unit, active operation monitoring unit, AGV equipment monitoring unit, associated equipment monitoring unit, and supply chain monitoring unit are all analyzed based on the monitoring time period; Realize risk assessment of industrial big data based on SC, SK, SDA, y, and yg.

[0006] Furthermore, the method for calculating the driving departure risk value SRA is: Obtain the driving path constructed by the AGV device based on the preset target coordinates and preset starting coordinates; Monitor whether the real-time coordinates of the AGV equipment are within the driving path. If not, record the deviation path formed after the AGV equipment deviates from the driving path, clearly record the distance of the deviation path as the deviation driving distance SS, determine the deviation path target coordinates of the deviation path, and determine whether it deviates from the preset target coordinates.

[0007] If so, determine the deviation interval distance SP between the deviated path target coordinate and the preset target coordinate, and calculate the deviation travel time ST generated by the deviated path target coordinate reaching the preset target coordinate; The operation risk value of each AGV device in the monitoring time period is obtained by weighted summation based on the deviation driving distance SS, deviation interval distance SP and deviation driving time ST. The operation values ​​of all AGV devices in the monitoring time period are counted and recorded as the driving deviation risk value SRA.

[0008] Furthermore, the method for calculating the device collision value SPA is: During the monitoring period, the number of collisions that occur during the AGV's travel, the area of ​​the AGV affected by each collision, the time required to repair the affected area, and the downtime of the AGV are determined. The equipment collision value (SPA) is calculated by taking the weighted sum of the number of collisions, the area of ​​the collision, the time required to repair the affected area, and the downtime of the AGV.

[0009] Furthermore, the total delay value DIA is determined as follows: Define all tasks ; According to the order relationship between tasks, a task dependency network is constructed. Indicates a task Depends on the task .

[0010] If the task Delayed and the delay time is , for the task Delay time , then there is, in, Indicates a task Task The dependency strength of the task Task The impact of Indicates a task The time sensitivity coefficient, Indicates a task The resource availability coefficient; Calculate the actual delay time of each task due to the delay of the predecessor task .

[0011] The impact of task delay depends on the delay of the previous task. Calculate the total delay value DIA of all tasks: .

[0012] Furthermore, the method for determining the associated device monitoring value y is: Forecasting based on the linear regression model, we have: Among them, y represents the predicted monitoring value of the associated equipment, represents the intercept term, Represent the corresponding weight coefficients, Represent the input characteristics of the device, represents the error term.

[0013] Furthermore, the specific method for resetting the monitoring time period is as follows: Obtain usage data of sensors related to associated devices, evaluate the usage risk value of the sensor, and if the usage risk value exceeds a threshold, determine the sensor as an abnormal sensor and perform status detection to generate a judgment result, which may include repair or replacement; Obtaining a detection loss time based on the detection time of each abnormal sensor; The repair and replacement of abnormal sensors correspond to different disposal times. The disposal loss time is obtained by summing up the disposal time corresponding to each abnormal sensor. The disposal control time is obtained based on the sum of the detection loss time and the disposal loss time. The start time of the monitoring time period is limited based on the disposal control time.

[0014] Furthermore, the total estimated risk value is calculated based on the weighted sum of the production volume monitoring value SC, the active operation monitoring value SK, the AGV equipment monitoring value SDA, the associated equipment monitoring value y, and the supply chain monitoring value yg, thereby realizing an overall risk assessment of industrial big data.

[0015] Furthermore, it also includes: The information data management unit is used to encrypt and store the evaluation results of industrial big data and the evaluation data collected during the evaluation process, including: Set a set time interval for industry big data risk assessment; The monitoring time period for the next risk assessment is determined based on the monitoring time period of the current risk assessment. Between the current monitoring time period and the next monitoring time period, the key of the information data management unit changes dynamically.

[0016] The dynamic changes of the key of the information data management unit are as follows: Obtain the number of risk assessment items, and divide the time between the current monitoring period and the next monitoring period into multiple intermediate time points using the number of items. Set the key corresponding to each intermediate time point as the assessment result output by the risk assessment; The output time of the assessment result of each risk assessment project is obtained, and the risk assessment projects are respectively corresponding to an intermediate time point in chronological order from early to late, and the key of the information data management unit is dynamically switched at different intermediate time points.

[0017] The preset number of keys is determined by the number of numeric characters corresponding to the evaluation results at the initial intermediate time point, where: If the number of numeric characters corresponding to the subsequent intermediate time points exceeds the preset number of keys, the numeric characters corresponding to the intermediate time points will be collected in order; If the number of numeric characters corresponding to the subsequent intermediate time point is less than the preset number of the key, the number of missing characters is determined, the corresponding supplementary rule is determined based on the number of missing characters, and the corresponding supplementary key is determined based on the supplementary rule.

[0018] The supplementary rules are as follows: Determine the number of days between the start time and the end time of this monitoring period, and record it as the day key character; Determine the start time and end time of the monitoring period, record one character of the day key as a side character and assign it to the rightmost side of the start time or end time, and assign the other character to the month of the start time or end time so that the month forms a three-digit number; According to the start time or end time, a supplementary rule is constructed based on the number of characters corresponding to the year, month, day and side characters in sequence.

[0019] Compared with the prior art, the technical solution provided by the present invention has the following beneficial effects: By dividing AGV equipment into driving risk monitoring, equipment collision monitoring, and task risk monitoring, we can realize the identification and analysis of the intelligent control of AGV equipment in the warehouse center, and clarify the impact of AGV equipment on the overall industry big data during operation. The task risk monitoring analyzes the sequence and dependency between multiple tasks of AGV equipment through the introduction of task dependency network, which further clarifies the progressive impact of AGV equipment tasks on the entire industry.

[0020] By pre-clarifying the sensor operating status of production-related equipment, defining the existing abnormal sensors and thereby determining their detection loss time and disposal loss time, the sensors can be rearranged, thereby regenerating the limited control of the monitoring time period when conducting industrial big data assessment, ensuring that the accurate assessment of industrial big data risks can be reflected during the monitoring time period.

[0021] Through the dynamic key management solution, based on the evaluation data and results of each time, intelligent key switching rules are constructed between the current monitoring period and the next monitoring period, which improves the flexibility and security of data management and reduces the security risks caused by key leakage. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0023] Figure 1 It is the overall module block diagram of the present invention. DETAILED DESCRIPTION

[0024] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0025] The present invention will be further described below with reference to the embodiments.

[0026] Example 1 (see Figure 1 ): An industrial big data monitoring and risk assessment system, comprising at least: The production monitoring unit is used to set a monitoring time period to monitor the production status of the production line, including: The historical production volume is used to construct time series data. Based on the time series data, the ARIMA model is trained to predict the corresponding future production volume in the future monitoring period. The expression of the ARIMA model is: in, represents the production volume at time point t, represents a constant term, are the corresponding autoregressive coefficients, Respectively represent the lag value (corresponding to historical production), represents the error term, Represent the corresponding moving average coefficients, respectively, to measure the relationship between the current value and the error of the past q moments, They represent the error terms corresponding to the time.

[0027] Thus, the future moment to be predicted is determined The corresponding future production volume at (the time corresponding to the monitoring period) is: in, Indicates the predicted time future production, They represent the future production at the corresponding future moments.

[0028] Then, get the preset future time The calibrated production volume is divided into multiple production volume intervals. Different production volumes correspond to different production volume intervals, and different production volume intervals correspond to different risk values ​​(usually, the larger the production volume, the smaller the production volume risk value, which is not specifically limited in this embodiment). Therefore, according to the future production volume The production volume monitoring value SC is determined by comparing with the calibrated production volume (it should be noted that the above method of predicting the future production volume in advance improves the efficiency of data analysis).

[0029] Active operation monitoring unit, including: During the monitoring period, the risk operation time of each operator in the operation center is obtained separately (accidental touching of equipment / operating equipment, resulting in abnormal operation of the equipment, the time from accidental touching of equipment / operating equipment to the end of abnormal operation of the equipment; entering the unsafe operation area, the time from entering the unsafe operation area to leaving the unsafe operation area, etc.), and the sum of the risk operation time of multiple operators is counted and recorded as the total risk operation time.

[0030] During the monitoring period, the number of risky operations (number of false touches, number of abnormal equipment operations, etc.) of each operator in each operation center is obtained respectively. The sum of the number of risky operations of multiple operators is counted and recorded as the total number of risky operations. The total risky operation time and the number of risky operations are assigned corresponding weight coefficients respectively, and the weighted sum is used to obtain the active operation monitoring value SK.

[0031] The AGV equipment monitoring unit monitors the operating status of each AGV equipment in the storage center during the monitoring period (current storage centers are usually intelligent storage centers, which use intelligent AGV equipment to take over the supply chain's raw material storage / delivery / processing center distribution, etc. The integrated control of the AGV equipment reflects whether the control configuration of the storage center is complete and the process connection between the storage center and the processing center, etc.), including: Driving risk monitoring: obtain the driving path constructed by the AGV device based on the preset target coordinates and preset starting coordinates (including the driving path constructed based on the preset starting coordinates and preset target coordinates when the AGV device encounters an obstacle during driving), monitor whether the real-time coordinates of the AGV device are on the driving path, if not, record the deviation path formed after the AGV device deviates from the driving path, and clearly record the distance of the deviation path as the deviation driving distance SS. At the same time, determine the deviation path target coordinates of the deviation path, and determine whether it deviates from the preset target coordinates. If so, determine the deviation interval distance SP between the deviation path target coordinates and the preset target coordinates, and calculate the deviation driving time ST generated by the deviation path target coordinates reaching the preset target coordinates. Based on the deviation driving distance SS, the deviation interval distance SP and the deviation driving time ST, corresponding weight coefficients are assigned respectively. The operation risk value of each AGV device in the monitoring time period is obtained by weighted summation, and the operation values ​​of all AGV devices in the monitoring time period are counted and recorded as the driving deviation risk value SRA.

[0032] Equipment collision monitoring, including: During the monitoring period, the number of collisions that occur during the AGV's travel, the area of ​​the AGV affected by each collision, the time required to repair the affected area, and the downtime of the AGV are determined. Corresponding weights are assigned based on the number of collisions, the area of ​​the collision, the time required to repair the affected area, and the downtime of the AGV. The weighted sum is used to calculate the equipment collision value (SPA).

[0033] Task risk monitoring, calculate the total delay value DIA of the AGV equipment task (the processing product step corresponds to the material transportation task or scheduling task): By introducing a task dependency network to analyze the sequence and dependencies between multiple tasks (AGV equipment tasks), we can find: Define all tasks Determine the task time RT (preset task completion time) for each task; According to the order relationship between tasks, a task dependency network is constructed. Indicates a task Depends on the task , that is, in the task Once completed, you can proceed with the task .

[0034] If the task Delayed and the delay time is (Depending on the task The difference between the completion time of the task and the task time RT, if the task The completion time is less than or equal to the task time RT, then Equal to 0, otherwise is the difference, and is a positive number), for the task Delay time , then there is, in, Indicates a task Task The dependency strength of the task Task The impact of Indicates a task The time sensitivity coefficient reflects the impact of task delay on The degree of impact, Indicates a task The resource availability coefficient describes the effect of resource adequacy on delay propagation; This can be used to calculate the actual delay time of each task due to the delay of the predecessor task. .

[0035] In a task dependency network, the impact of all task delays depends on the delay of the previous task, and the total delay value DIA of all tasks is calculated as follows: N represents the number of tasks, and the driving risk value SRA, collision value SPA, and total delay value DIA are assigned corresponding weight coefficients respectively, and the AGV equipment monitoring value SDA is obtained by weighted summation.

[0036] The associated equipment monitoring unit is used to monitor the health status of associated equipment (including pretreatment equipment corresponding to the raw material pretreatment center, processing equipment corresponding to the product production center, and testing equipment corresponding to the product testing center) at the monitoring time point, including: The health status of production-related equipment is predicted based on the linear regression model: Where y represents the predicted associated device monitoring value of the associated device, represents the intercept term, Represent the corresponding weight coefficients, Respectively represent the input characteristics of the equipment, including the equipment's usage time, average temperature, number of failures, vibration duration, etc. during the monitoring period (monitoring data is obtained through sensors installed on the equipment). represents the error term.

[0037] It should be noted that when obtaining monitoring data output by sensors, the status of the sensors themselves should be taken into consideration. In order to avoid collecting monitoring data output by abnormal sensors, the status of the deployed sensors should be analyzed in advance before obtaining monitoring data in the monitoring time period. The presence of abnormal sensors should be identified and handled, thereby improving the accuracy of subsequent evaluation of the monitoring values ​​of related equipment. The usage data of each sensor is obtained, including usage time, usage failure rate, repair time, maintenance time, and failure rate. The usage risk value of the sensor is defined based on the weighted sum of usage time, usage failure rate, repair time, maintenance time, and failure rate. If the usage risk value exceeds the threshold, the sensor is identified as an abnormal sensor and a detection signal of the abnormal sensor is generated. The detection personnel operate the detection equipment to perform status detection on the abnormal sensor, generate a judgment result, and determine whether to repair or replace it. Therefore: Determine the number of abnormal sensors and derive the detection loss time based on the detection time of each abnormal sensor (because each sensor needs to monitor the equipment and output monitoring data). Based on the judgment result of each abnormal sensor, determine whether the abnormal sensor needs to be repaired or replaced. It should be noted that: The repair and replacement of abnormal sensors correspond to different disposal times. Therefore, the disposal loss time is obtained by summing up the disposal time corresponding to each abnormal sensor, and the disposal control time is obtained based on the sum of the detection loss time and the disposal loss time. Therefore, if it is necessary to set a monitoring time period for industrial big data evaluation, it is necessary to determine it after the disposal control time, that is, to further limit the starting time of the monitoring time period to avoid arbitrarily setting the monitoring time period, resulting in abnormal, invalid and erroneous monitoring data collected during the monitoring time period, thereby affecting the accurate assessment of the health risk monitoring value of the equipment, and at the same time improving the monitoring and evaluation efficiency of industrial big data.

[0038] It should be noted that the supply chain monitoring unit predicts the risk data of the supply chain based on the above-mentioned linear regression model based on the determined monitoring time period, that is, the input characteristics affecting the supply chain include the average delivery cycle of the supplier during the monitoring time period, the number of supplier goods transportation interruption delays, the total delay time, etc., and the predicted supply chain monitoring value yg can be obtained.

[0039] Determine the production volume monitoring value SC, active operation monitoring value SK, AGV equipment monitoring value SDA, associated equipment monitoring value y, and supply chain monitoring value yg corresponding to the output monitoring unit, active operation monitoring unit, AGV equipment monitoring unit, associated equipment monitoring unit, and supply chain monitoring unit respectively, and calculate the total estimated risk value of the industrial big data by taking their weighted sum. Generally speaking, the larger the total estimated risk value, the greater the industrial risk, thereby achieving an overall risk assessment of the industrial big data.

[0040] Finally, this embodiment also includes an information data management unit for storing the above-mentioned evaluation results of industrial big data (total estimated risk value) and the evaluation data collected during the evaluation process (production volume data involved in the production monitoring unit, sensor data corresponding to the associated equipment monitoring unit, etc.), and encrypting the data with a key after storage to ensure the privacy of the evaluation data and avoid the loss or leakage of the evaluation data, so as to facilitate subsequent analysis and use.

[0041] In this embodiment, risk assessment of industrial big data is performed at predetermined intervals (set on a quarterly or annual basis). By performing risk assessments at predetermined intervals, risk security supervision of industrial big data is achieved. Therefore: Based on the monitoring period of the current risk assessment (e.g., July 10-20), the monitoring period for the next risk assessment is determined in combination with the established interval. Usually, each risk assessment requires the same number of days. Therefore, to ensure the privacy and security of the assessment data, the information data management unit dynamically changes the key used between the current monitoring period and the next risk assessment monitoring period, as follows: Obtain the number of categories and items for this risk assessment (production monitoring units, associated equipment monitoring units, etc.). Use the number of categories and items to equally divide the time between the current monitoring period and the next monitoring period into multiple intermediate time points (a specific day). In this embodiment, the key corresponding to each intermediate time point is set to the assessment result output by the risk assessment (production equipment monitoring value y, production volume monitoring value SC, AGV equipment monitoring value SDA or supply chain monitoring value yg); In this risk assessment, the time to obtain the output of the assessment results for each risk assessment item (the time to obtain the production equipment monitoring value y, the production volume monitoring value SC, the AGV equipment monitoring value SDA, or the supply chain monitoring value yg); According to the chronological order from early to late, the risk assessment items are respectively corresponding to an intermediate time point, thereby adaptively switching the key of the information data management unit at different intermediate time points.

[0042] Meanwhile, in this embodiment, the preset number of keys is determined by the number of digital characters corresponding to the evaluation results at the initial intermediate time point, where: If the number of numeric characters corresponding to subsequent intermediate time points exceeds the preset number of the key, the numeric characters corresponding to the intermediate time points are collected in sequence (e.g., starting from the left or right end of the numeric characters, characters are selected in sequence, and so on. When the preset number is reached, no more numeric characters are determined, and the collected and determined numeric characters are used to generate the key); If the number of numeric characters corresponding to the subsequent intermediate time point is less than the preset number of the key, the number of missing characters is determined, the corresponding supplementary rule is determined based on the number of missing characters, and the corresponding supplementary key is determined based on the supplementary rule.

[0043] In the above, the supplementary rules are determined as follows: Determine the number of days between the start time and the end time of this monitoring period, which is recorded as the day key character (the number of digits of the day key character is usually two digits, such as 08 or 12, etc.); Determine the start and end time of the monitoring period (e.g., 2023.02.26), record one character of the day key as a side character and assign it to the rightmost side of the start or end time (the side corresponding to the specific day), and assign the other character to the month of the start or end time, so that the month forms a three-digit number (as described above, if the day key character is 12, 02 can form a three-digit number as 021, 022, 102, 202, etc. without restriction), thereby changing the start or end time, for example (2023.021.26.2); Therefore, the start time or end time of this time is the number of characters corresponding to 2023, 021, 26, and 8 according to the year, month, day and side characters in order.

[0044] Constructing supplementary rules: The year of the start time or end time is determined as the supplementary key corresponding to Supplementary Rule 1; The month of the start time or end time is determined as the supplementary key corresponding to Supplementary Rule 2; The day of the start time or end time is determined as the supplementary key corresponding to Supplementary Rule 3; The side characters of the start time or end time are determined as the supplementary key corresponding to Supplementary Rule 4; This forms key security management for the information data management unit and improves data security.

[0045] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the protection scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An industrial big data monitoring and risk assessment system, comprising: Production monitoring unit, predicting production monitoring value SC; The active operation monitoring unit obtains the active operation monitoring value SK, and is characterized by further comprising: AGV equipment monitoring unit is divided into: Driving risk monitoring: determine the driving path constructed by the AGV equipment, monitor the real-time coordinates of the AGV equipment, determine whether it deviates from the driving path and generate a deviation path, and calculate the driving deviation risk value SRA based on the deviation path, the driving path deviation interval distance SP, and the deviation driving time ST; Equipment collision monitoring, calculation of equipment collision value SPA; Task risk monitoring: Based on the task dependency network, the order and dependency between multiple tasks of the AGV equipment are analyzed, the total delay value DIA of the task is calculated, and the AGV equipment monitoring value SDA is obtained comprehensively; The associated device monitoring unit predicts the associated device monitoring value y of the associated device, where: Predetermine the sensors related to the associated equipment, analyze usage data to determine abnormal sensors, and re-determine the monitoring time period based on the detection loss time and disposal loss time of the abnormal sensors; Supply chain monitoring unit, predicting the supply chain monitoring value yg of the supply chain; The production monitoring unit, active operation monitoring unit, AGV equipment monitoring unit, associated equipment monitoring unit, and supply chain monitoring unit are all analyzed based on the monitoring time period; Realize risk assessment of industrial big data based on SC, SK, SDA, y, and yg.

2. The industrial big data monitoring and risk assessment system according to claim 1 is characterized in that: The method for calculating the driving departure risk value SRA is: Obtain the driving path constructed by the AGV device based on the preset target coordinates and preset starting coordinates; Monitor whether the real-time coordinates of the AGV device are within the driving path. If not, record the deviation path formed after the AGV device deviates from the driving path, clearly record the deviation distance as the deviation driving distance SS, determine the deviation path target coordinates of the deviation path, and determine whether it deviates from the preset target coordinates: If so, determine the deviation interval distance SP between the deviated path target coordinate and the preset target coordinate, and calculate the deviation travel time ST generated by the deviated path target coordinate reaching the preset target coordinate; The operation risk value of each AGV device in the monitoring time period is obtained by weighted summation based on the deviation driving distance SS, deviation interval distance SP and deviation driving time ST. The operation values ​​of all AGV devices in the monitoring time period are counted and recorded as the driving deviation risk value SRA.

3. The industrial big data monitoring and risk assessment system according to claim 1 is characterized in that: The method for calculating the device collision value SPA is: During the monitoring period, the number of collisions that occur during the AGV's travel, the area of ​​the AGV affected by each collision, the time required to repair the affected area, and the downtime of the AGV are determined. The equipment collision value (SPA) is calculated by taking the weighted sum of the number of collisions, the area of ​​the collision, the time required to repair the affected area, and the downtime of the AGV.

4. The industrial big data monitoring and risk assessment system according to claim 1, characterized in that: The total delay value DIA is determined as follows: Define all tasks ; According to the order relationship between tasks, a task dependency network is constructed. Indicates a task Depends on the task ; If the task Delayed and the delay time is , for the task Delay time , then there is, in, Indicates a task Task The dependency strength of the task Task The impact of Indicates a task The time sensitivity coefficient, Indicates a task The resource availability coefficient; Calculate the actual delay time of each task due to the delay of the predecessor task ; The impact of task delay depends on the delay of the previous task. Calculate the total delay value DIA of all tasks: 。 5. The industrial big data monitoring and risk assessment system according to claim 1, characterized in that: The method for determining the associated device monitoring value y is: Forecasting based on the linear regression model, we have: Among them, y represents the predicted monitoring value of the associated equipment, represents the intercept term, Represent the corresponding weight coefficients, Represent the input characteristics of the device, represents the error term.

6. The industrial big data monitoring and risk assessment system according to claim 1, characterized in that: The specific method for resetting the monitoring time period is as follows: Obtain usage data of sensors related to associated devices, evaluate the usage risk value of the sensor, and if the usage risk value exceeds a threshold, determine the sensor as an abnormal sensor and perform status detection to generate a judgment result, which may include repair or replacement; Obtaining a detection loss time based on the detection time of each abnormal sensor; The repair and replacement of abnormal sensors correspond to different disposal times. The disposal loss time is obtained by summing up the disposal time corresponding to each abnormal sensor. The disposal control time is obtained based on the sum of the detection loss time and the disposal loss time. The start time of the monitoring time period is limited based on the disposal control time.

7. The industrial big data monitoring and risk assessment system according to claim 1, characterized in that: The total estimated risk value is calculated based on the weighted sum of production volume monitoring value SC, active operation monitoring value SK, AGV equipment monitoring value SDA, associated equipment monitoring value y, and supply chain monitoring value yg to achieve an overall risk assessment of industrial big data.

8. The industrial big data monitoring and risk assessment system according to claim 1, characterized in that: Also includes: The information data management unit is used to encrypt and store the evaluation results of industrial big data and the evaluation data collected during the evaluation process, including: Set a set time interval for industry big data risk assessment; The monitoring time period for the next risk assessment is determined based on the monitoring time period of the current risk assessment. Between the current monitoring time period and the next monitoring time period, the key of the information data management unit changes dynamically.

9. The industrial big data monitoring and risk assessment system according to claim 8, characterized in that: The key dynamic changes of the information data management unit are as follows: Obtain the number of risk assessment items, and divide the time between the current monitoring period and the next monitoring period into multiple intermediate time points using the number of items. Set the key corresponding to each intermediate time point as the assessment result output by the risk assessment; The output time of the assessment result of each risk assessment project is obtained, and the risk assessment projects are respectively corresponding to an intermediate time point in chronological order from early to late, and the key of the information data management unit is dynamically switched at different intermediate time points.

10. The industrial big data monitoring and risk assessment system according to claim 9, characterized in that: The preset number of keys is determined by the number of numeric characters corresponding to the evaluation results at the initial intermediate time point, wherein: If the number of numeric characters corresponding to the subsequent intermediate time points exceeds the preset number of keys, the numeric characters corresponding to the intermediate time points will be collected in order; If the number of numeric characters corresponding to the subsequent intermediate time point is less than the preset number of the key, the number of missing characters is determined, the corresponding supplementary rule is determined based on the number of missing characters, and the corresponding supplementary key is determined based on the supplementary rule; The supplementary rules are as follows: Determine the number of days between the start time and the end time of this monitoring period, and record it as the day key character; Determine the start time and end time of the monitoring period, record one character of the day key as a side character and assign it to the rightmost side of the start time or end time, and assign the other character to the month of the start time or end time so that the month forms a three-digit number; According to the start time or end time, a supplementary rule is constructed based on the number of characters corresponding to the year, month, day and side characters in sequence.

Images