Operation equipment state monitoring and management system based on Internet of Things technology

Abstract

The invention discloses an operation equipment state monitoring and management system based on the Internet of Things technology, and relates to the technical field of equipment monitoring and management.The system constructs a hierarchical data chain of equipment by using historical monitoring and management records, constructs an equipment maintenance experience library at the same time, and then performs corresponding monitoring on the equipment; according to the method, a hierarchical data link is established, equipment operation analysis is performed according to types of different data in the hierarchical data link, when equipment is abnormal, faulty parts and fault types are confirmed, an optimal maintenance scheme is selected from an equipment maintenance experience library according to a current production plan, and after the maintenance scheme is implemented, continuous monitoring is performed, and the maintenance effect of the equipment is tracked. And according to the maintenance effect, the hierarchical data chain and the equipment maintenance experience library are updated, so that the comprehensiveness of operation equipment monitoring and data processing is improved, the accuracy of equipment fault positioning is improved, the equipment maintenance effect is guaranteed, and the influence on production is reduced.

Description

Technical Field

[0001] This invention relates to the field of equipment monitoring and management technology, and more specifically to an operational equipment status monitoring and management system based on Internet of Things (IoT) technology. Background Art

[0002] With the rapid development of digitalization and intelligence, applying IoT technology to the monitoring and management of operating equipment status can solve the problems of low efficiency, large errors, and poor real-time performance in traditional management models such as manual inspection or single-point monitoring, thereby improving the safety of enterprise equipment.

[0003] Existing technology, such as the one disclosed in patent application CN116224882A, describes a system, method, device, and storage medium for monitoring the operating status of industrial equipment. The system includes an industrial gateway, a Kafka subsystem, a storage unit, and a big data analysis and modeling platform. The industrial gateway acquires raw operating data from the industrial equipment, cleans the data to obtain first operating data, and transmits this first operating data to a first message node of the Kafka subsystem. The first message node then transmits the first operating data to the storage unit. The big data analysis and modeling platform retrieves the first operating data from the first message node to perform data monitoring tasks. If the first operating data is abnormal, it marks the first operating data to obtain second operating data and transmits it to a second message node of the Kafka subsystem. The second message node then transmits the second operating data to the storage unit. This method enables real-time monitoring of the operating status of industrial equipment.

[0004] Existing technologies, such as the equipment monitoring and management method and system based on equipment data interaction disclosed in application CN117785854A, belong to the field of equipment monitoring and management technology. They include: a data acquisition module responsible for collecting monitoring data from the equipment; a data storage module comprising a database for storing the equipment monitoring data, which can also store, index, and back up the data; a data processing module responsible for processing, analyzing, and visualizing the equipment monitoring data collected by the data acquisition module; and a data display module for displaying the equipment monitoring data and analysis results. This invention can improve the comprehensiveness of data collection and the accuracy of data analysis, support real-time monitoring capabilities, and improve equipment management efficiency, thereby bringing significant benefits to the industrial field.

[0005] The above solution analyzes the status of the equipment by monitoring and processing the monitoring data, but it still has the following shortcomings: 1. The normal operation of the equipment depends on the cooperation of multiple parts. Therefore, when a single part fails, it may cause abnormalities in the operating data of other parts. However, the above solution lacks analysis of the correlation between different fault types of each part and the data directly monitored by the part and the indirect monitoring data related to the part. At the same time, it does not build a hierarchical data chain for each part based on the correlation. It is impossible to accurately locate the specific abnormal part and the fault type when monitoring the equipment, resulting in insufficient fault location accuracy and failing to provide a reliable reference for subsequent maintenance.

[0006] 2. The above solutions lack the ability to build an equipment maintenance experience database and do not select the best maintenance plan for the equipment based on the production plan after equipment malfunctions. This leads to premature production line shutdowns, resulting in order delivery delays. Consequently, the maintenance plan becomes disconnected from the production plan, increasing equipment maintenance costs and reducing equipment management effectiveness. Summary of the Invention

[0007] To address the aforementioned technical shortcomings, the present invention aims to provide an operational equipment status monitoring and management system based on Internet of Things (IoT) technology.

[0008] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: The present invention provides an operational equipment status monitoring and management system based on Internet of Things technology, including: a knowledge construction unit, an operation supervision unit, and an equipment feedback unit.

[0009] The knowledge building unit is used to build a hierarchical data chain for equipment by utilizing historical monitoring and management records, and at the same time build an equipment maintenance experience base.

[0010] The operation monitoring unit is used to input the data collected by the sensor devices in the equipment into the hierarchical data chain of the equipment, and to analyze the operation of the equipment. If the equipment is abnormal, it will extract the production plan from the production center and analyze the maintenance plan of the equipment based on the equipment maintenance experience library.

[0011] The equipment feedback unit is used to acquire equipment operating data after maintenance, analyze the maintenance effect, and update the hierarchical data chain and equipment maintenance experience base.

[0012] The beneficial effects of this invention are as follows: 1. This invention provides an operational equipment status monitoring and management system based on Internet of Things (IoT) technology. By utilizing historical monitoring and management records, a hierarchical data chain for the equipment is constructed, along with an equipment maintenance experience database. The equipment is then monitored accordingly, and the operation of the equipment is analyzed based on different data types in the hierarchical data chain. When the equipment malfunctions, the faulty parts and fault type are identified. Based on the current production plan, the optimal maintenance plan is selected from the equipment maintenance experience database. After the maintenance plan is implemented, continuous monitoring is conducted to track the maintenance effect. Based on the maintenance effect, the hierarchical data chain and equipment maintenance experience database are updated, thereby improving the comprehensiveness of operational equipment monitoring and data processing, increasing the accuracy of equipment fault location, ensuring the effectiveness of equipment maintenance, and reducing the impact on production.

[0013] 2. This invention constructs a hierarchical data chain for equipment, reflecting the data transmission path of parts, realizing the analysis and application of the mapping relationship between part faults and multi-dimensional data, ensuring the comprehensiveness of fault feature extraction, increasing fault location accuracy, and providing a reliable reference for equipment maintenance.

[0014] 3. Based on the construction of an equipment maintenance experience database and the equipment production plan, this invention selects the best maintenance plan for the equipment, reduces the occurrence of premature production line downtime, ensures smooth order delivery, avoids the disconnect between maintenance plan and production plan, reduces equipment maintenance costs, and ensures the effectiveness of equipment management. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a schematic diagram of the system structure connection of the present invention. Detailed Implementation

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 creative efforts are within the scope of protection of the present invention.

[0018] Please see Figure 1As shown, the operational equipment status monitoring and management system based on Internet of Things (IoT) technology includes: a knowledge building unit, an operation supervision unit, an equipment feedback unit, and a database.

[0019] The knowledge building unit is used to build a hierarchical data chain for equipment by utilizing historical monitoring and management records, and at the same time build an equipment maintenance experience base.

[0020] In one specific embodiment, the knowledge building unit includes a data chain building module and an experience base building module.

[0021] The data chain construction module is used to obtain historical monitoring and management records from the database, obtain basic operating data and maintenance records of the equipment from the historical monitoring and management records, obtain the data corresponding to each part in the equipment from the basic operating information of the equipment, and obtain the set of direct abnormal monitoring data types, abnormal value sets, abnormal indirect monitoring data types, and abnormal value sets corresponding to each maintenance of each part from the maintenance records of the equipment, and construct the hierarchical data chain of the equipment.

[0022] Preferably, the specific process of the hierarchical data chain is as follows: S101, obtain the abnormal values ​​of each direct monitoring data type corresponding to the abnormality of each maintenance of each part from the abnormal direct monitoring data type set and value set corresponding to each maintenance of each part, and at the same time obtain the fault type corresponding to each maintenance of each part from the equipment maintenance record, and count the abnormal values ​​of each direct monitoring data type corresponding to the abnormality of each maintenance of each fault type of each part.

[0023] It should be noted that the data type of direct monitoring refers to the data type obtained by directly monitoring the part. For example, if the part is a motor, the motor temperature is the data type obtained by monitoring the motor using a temperature sensor. Therefore, when the part is a motor, the motor temperature is the data type of direct monitoring. This example is only for illustrative purposes and is not the only limitation.

[0024] Based on their different mechanisms of occurrence, fault types can be divided into mechanical faults and electrical faults, etc.

[0025] S102. Obtain the safe value range of each directly monitored data type in each part from the monitoring center. Input the abnormal value and safe value range of each directly monitored data type corresponding to each maintenance abnormality in each part and each fault type into the correlation calculation model to calculate the correlation between each fault type of each part and each directly monitored data type.

[0026] The process for calculating the correlation between each fault type of each part and each directly monitored data type is as follows: count the number of times each directly monitored data type is abnormal in each fault type of each part, and take the difference between the abnormal value and the safe value range of each directly monitored data type corresponding to each maintenance abnormality in each fault type of each part as the abnormal value difference of each directly monitored data type corresponding to each maintenance abnormality in each fault type of each part, and obtain the average abnormal value difference of each directly monitored data type in each fault type of each part by averaging.

[0027] It should be noted that when the abnormal value is greater than the maximum value of the safe value range, the abnormal value difference is the difference between the abnormal value and the maximum value of the safe value range. When the abnormal value is less than the minimum value of the safe value range, the abnormal value difference is the difference between the minimum value of the safe value range and the abnormal value. When the abnormal value is within the safe value range, the abnormal value difference is 0.

[0028] The number of anomalies and the average difference in anomaly values ​​for each directly monitored data type in each part and each fault type are denoted as C1. xgr and C2 xgr Where x represents the part number, g represents the fault type number, and r represents the direct monitoring data type number, x, g, and r are all positive integers. The expression for the correlation calculation model is: In the formula, α xgr C1 represents the correlation between the g-th fault type of the x-th part and the r-th directly monitored data type. xg R represents the number of times the x-th part has the g-th fault type, and R represents the number of directly monitored data types.

[0029] C1 was obtained from historical monitoring and management records. xg .

[0030] S103. Obtain the values ​​of each indirect monitoring data type corresponding to each maintenance of each part from the set of indirect monitoring data types and the set of values ​​corresponding to each maintenance of each part, and calculate the correlation between each fault type of each part and each indirect monitoring data type.

[0031] It should be noted that indirect monitoring data types are data types that do not directly monitor the parts. For example, if the part is a motor, when the motor fails, the gears in the gearbox will wear and break due to uneven force, resulting in increased vibration and noise. The vibration and noise values ​​monitored by the vibration and noise sensors in the gearbox are the indirect monitoring data types of the motor. This example is only for illustration and is not the only limitation.

[0032] It should be noted that, according to α xgrThe calculation method for determining the correlation between each fault type of each part and each type of indirect monitoring data is not elaborated here.

[0033] S104. Sort the correlation between each fault type of each part and each directly monitored data type in descending order. The sorting result is used as the connection order of the monitored data types in the main-line data chain of each fault type of each part. Similarly, sort the correlation between each fault type of each part and each indirectly monitored data type in descending order. The sorting result is used as the connection order of the monitored data types in the auxiliary-line data chain of each fault type of each part of the equipment. The hierarchical data chain of the equipment is composed of the main-line data chain and the auxiliary-line data chain of each fault type of each part.

[0034] The experience base construction module is used to obtain equipment maintenance records from historical monitoring and management records, obtain the maintenance plan corresponding to each maintenance of each part and the attenuation coefficient after maintenance from the equipment maintenance records, analyze the maintenance plan corresponding to each part in the equipment, and construct the equipment maintenance experience base.

[0035] Preferably, the construction process of the equipment maintenance experience base is as follows: S201, based on the fault type corresponding to each maintenance of each part, the attenuation coefficients of each maintenance scheme corresponding to each fault type of each part are statistically analyzed, and the experience coefficients of each maintenance scheme corresponding to each fault type of each part are output.

[0036] In the above, the maximum and minimum attenuation coefficients of each maintenance scheme for each fault type of each part are denoted as W. xgpmax and W xgpmin Where p represents the number of each maintenance scheme, and p is a positive integer; the expression for the empirical coefficient analysis model is:

[0037] In the formula, δ xgp This represents the empirical coefficient for the p-th maintenance plan corresponding to the g-th fault type of the x-th part. This represents the average value of the attenuation coefficients for each maintenance scheme corresponding to the g-th fault type of the x-th part, where P represents the number of maintenance schemes.

[0038] S202. Based on the experience coefficients of each maintenance scheme corresponding to each fault type of each part, select each experience maintenance scheme corresponding to each fault type of each part, use each experience maintenance scheme corresponding to each fault type of each part as the equipment maintenance experience library, and sort each experience maintenance scheme corresponding to each fault type of each part in descending order according to the experience coefficient. The sorting result is the order of each experience maintenance scheme in the equipment maintenance experience library.

[0039] It should be noted that the experience coefficients of each maintenance scheme corresponding to each fault type of each part are compared with the preset experience coefficient thresholds. Maintenance schemes with experience coefficients greater than the experience coefficient thresholds are selected as experience maintenance schemes, thereby filtering out the experience maintenance schemes corresponding to each fault type of each part.

[0040] The preset experience coefficient threshold is a benchmark value for judging whether the maintenance plan is effective. The specific value is set by the staff based on their work experience and monitoring needs, and no specific numerical limit is set here.

[0041] The operation monitoring unit is used to input the data collected by the sensor devices in the equipment into the hierarchical data chain of the equipment, and to analyze the operation of the equipment. If the equipment is abnormal, it will extract the production plan from the production center and analyze the maintenance plan of the equipment based on the equipment maintenance experience library.

[0042] In one specific embodiment, the operation monitoring unit includes an operation monitoring module and an equipment maintenance module.

[0043] The operation monitoring module is used to input the data collected by the sensor devices in the equipment into the hierarchical data chain of the equipment, analyze the operation of the equipment, and execute the equipment maintenance module when the equipment is malfunctioning.

[0044] It should be noted that the sensors in the equipment are installed on various parts, including temperature sensors, vibration sensors, and noise sensors.

[0045] Preferably, the process of analyzing the operation of the equipment is as follows: extracting the monitoring values ​​of each directly monitored data type of each component in the hierarchical data chain, comparing them with the safe value range of each directly monitored data type, and determining the operating status of the equipment, wherein the operating status includes normal and abnormal.

[0046] It should be noted that if at least one directly monitored data type value of a certain component is within the safe value range, it indicates that the equipment is in an abnormal operating state.

[0047] Extract the monitoring values ​​of each direct and indirect monitoring data type of each part in the equipment. At the same time, extract the correlation between each fault type of each part and each direct and indirect monitoring data type to identify the faulty part and the fault type.

[0048] In the above process, the monitoring values ​​of each direct and indirect monitoring data type for each part are compared with the safe data range to obtain the abnormal value difference of each direct and indirect monitoring data type for each part. This difference is then normalized, and the processed data is denoted as C1′. xr and C1′ xuWhere u represents the number of each indirect monitoring data type, u is a positive integer, calculated according to the formula: Obtain the occurrence evaluation coefficient γ of the g-th failure type of the x-th part. xg , where α xgu This represents the correlation between the g-th fault type of the x-th part and the u-th indirect monitoring data type, where U represents the number of indirect monitoring data types.

[0049] The occurrence evaluation coefficient is compared with the preset occurrence evaluation coefficient threshold. If the occurrence evaluation coefficient of a certain fault type of a certain part is greater than the occurrence evaluation coefficient threshold, it indicates that the part and the fault type are faulty parts and fault types.

[0050] The equipment maintenance module is used to obtain various pre-selected maintenance schemes for the equipment based on the equipment maintenance experience library, obtain the current remaining production volume, production rate and remaining time from the production plan, and select the best maintenance scheme from the various pre-selected maintenance schemes for the equipment.

[0051] Preferably, the process of selecting the best maintenance scheme is as follows: taking each experience maintenance scheme corresponding to the fault type of the part of the equipment failure in the equipment maintenance experience database as each pre-selected maintenance scheme, obtaining the equipment status in each pre-selected maintenance scheme, and taking each pre-selected maintenance scheme with the same equipment status as a scheme group, thereby obtaining each scheme group.

[0052] It should be noted that equipment status includes immediate shutdown, low operation, and standby.

[0053] Predict the maintenance time and production rate in each plan group, and calculate the impact level of each plan group on the production plan based on the production plan. Select the plan group with the smallest impact level as the pre-selected plan group, and select the first-ranked pre-selected maintenance plan from the pre-selected plan group as the best maintenance plan.

[0054] In the above, the maintenance duration, production rate during maintenance, and production rate after maintenance are obtained from each pre-selected maintenance scheme in each scheme group. Then, the average of the maintenance duration, production rate during maintenance, and production rate after maintenance is calculated. The calculation results are the maintenance duration, production rate during maintenance, and production rate after maintenance in each scheme group.

[0055] Subtract the maintenance time in each plan group from the remaining time to obtain the normal production time of each plan group. Add the product of the production rate during maintenance and the maintenance time in each plan group to the product of the normal production time and the production rate after maintenance to obtain the expected production volume of each plan group. Subtract the current remaining production volume from the expected production volume of each plan group to obtain the production volume difference of each plan group. Then compare it with the production volume difference interval corresponding to each preset impact level. If the production volume difference of a plan group is within the production volume difference interval corresponding to a certain impact level, then the impact level is the impact level of that plan group on the production plan. This is how to obtain the impact level of each plan group on the production plan.

[0056] The preset production volume difference ranges corresponding to each impact level are set by staff based on their work experience and management needs. No specific numerical limits are imposed here. The higher the impact level, the greater the negative impact on the production plan.

[0057] The equipment feedback unit is used to acquire equipment operating data after maintenance, analyze the maintenance effect, and update the hierarchical data chain and equipment maintenance experience base.

[0058] In one specific embodiment, the device feedback unit includes a continuous monitoring module and a knowledge update module.

[0059] The continuous monitoring module is used to collect the direct monitoring data and indirect monitoring data of the faulty parts at preset time intervals after equipment maintenance, and to calculate the attenuation coefficient of the part monitoring data. The attenuation coefficient of the part monitoring data is then used to analyze the maintenance effect of the equipment.

[0060] Preferably, the calculation process of the attenuation coefficient of the part monitoring data is as follows: extract the safe value range of each direct monitoring data type and each indirect monitoring data type, and input the post-monitoring value and safe value range of each direct monitoring data type and each indirect monitoring data type corresponding to each time point into the attenuation coefficient calculation model, and output the attenuation coefficient of the part monitoring data.

[0061] The preset time interval is set and adjusted by staff, and no specific numerical limit is imposed here.

[0062] It should be noted that by comparing the post-dimensional monitoring values ​​and safe value ranges of each directly monitored data type and each indirectly monitored data type at each time point, the post-dimensional anomaly value difference of each directly monitored data type and each indirectly monitored data type at each time point is obtained, and is denoted as C1″. tr and C1″ tu Where t represents the time point number, and t is a positive integer; the expression for the attenuation coefficient calculation model is: In the formula, W1″ represents the attenuation coefficient of the part monitoring data, and C1″ represents the attenuation coefficient of the part monitoring data. (t+1)r and C1″ (t+1)u Let represent the difference in anomaly values ​​between the r-th directly monitored data type and the u-th indirectly monitored data type at the (t+1)-th time point, respectively. Let T represent the number of time points, ΔT represent the interval between time points, and κ1 and κ2 represent the preset threshold values ​​for the rate of change of anomaly values ​​of the directly monitored data type and the indirect monitored data type, respectively.

[0063] Where, when t=1, W1″=0. The abnormal value difference change rate of the direct monitoring data type and the abnormal value difference change rate of the indirect monitoring data type corresponding to the good maintenance effect of each faulty part are obtained from the historical monitoring and management records, and then the mean is calculated. The results are used as κ1 and κ2.

[0064] The attenuation coefficient of the component monitoring data is compared with the preset attenuation coefficient threshold. When the attenuation coefficient of the component monitoring data is less than the preset attenuation coefficient threshold, it indicates that the maintenance effect of the equipment is good, and vice versa.

[0065] Among them, the attenuation coefficient corresponding to the good maintenance effect of each faulty part is obtained from the historical monitoring and management records, and then the average value is calculated, and the result is used as the attenuation coefficient threshold.

[0066] The knowledge update module is used to extract the monitoring values ​​of each direct monitoring data type and each indirect monitoring data type corresponding to the faulty part, as well as the attenuation coefficient of the part monitoring data, update the connection order of each direct monitoring data type and each indirect monitoring data type in the hierarchical data chain, and update the order of the experience maintenance schemes corresponding to the faulty parts in the equipment maintenance experience base.

[0067] It should be noted that the connection order of each direct monitoring data type and each indirect monitoring data type in the hierarchical data chain and the order of the experience maintenance schemes corresponding to the fault types of the faulty parts in the equipment maintenance experience library are updated in accordance with steps S101-S104 and S201-S202.

[0068] The database is used to store historical monitoring and management records.

[0069] The above description is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined in this specification, they should all fall within the protection scope of the present invention.

Claims

1. An operational equipment status monitoring and management system based on Internet of Things (IoT) technology, characterized in that, include: Knowledge building unit, operation monitoring unit, and equipment feedback unit; The knowledge building unit is used to build a hierarchical data chain for equipment by utilizing historical monitoring and management records, and at the same time build an equipment maintenance experience base. The operation monitoring unit is used to input the data collected by the sensor devices in the equipment into the hierarchical data chain of the equipment, and to analyze the operation of the equipment. If the equipment is abnormal, it will extract the production plan from the production center and analyze the maintenance plan of the equipment based on the equipment maintenance experience library. The equipment feedback unit is used to acquire equipment operating data after maintenance, analyze the maintenance effect, and update the hierarchical data chain and equipment maintenance experience base.

2. The operational equipment status monitoring and management system based on Internet of Things technology according to claim 1, characterized in that, The knowledge construction unit includes a data chain construction module and an experience base construction module; The data chain construction module is used to obtain historical monitoring and management records from the database, obtain basic operating data and maintenance records of the equipment from the historical monitoring and management records, obtain the data corresponding to each part in the equipment from the basic operating information of the equipment, and obtain the set of direct abnormal monitoring data types, abnormal value sets, abnormal indirect monitoring data types, and abnormal value sets corresponding to each maintenance of each part from the maintenance records of the equipment, and construct the hierarchical data chain of the equipment. The experience base construction module is used to obtain equipment maintenance records from historical monitoring and management records, obtain the maintenance plan corresponding to each maintenance of each part and the attenuation coefficient after maintenance from the equipment maintenance records, analyze the maintenance plan corresponding to each part in the equipment, and construct the equipment maintenance experience base.

3. The operational equipment status monitoring and management system based on Internet of Things technology according to claim 2, characterized in that, The specific process of the hierarchical data chain is as follows: S101. Obtain the abnormal values ​​of each direct monitoring data type corresponding to each maintenance of each part from the abnormal direct monitoring data type set and value set corresponding to each maintenance of each part. At the same time, obtain the fault type corresponding to each maintenance of each part from the equipment maintenance record, and count the abnormal values ​​of each direct monitoring data type corresponding to each maintenance of each fault type of each part. S102. Obtain the safe value range of each directly monitored data type in each part from the monitoring center, and input the abnormal value and safe value range of each directly monitored data type corresponding to each maintenance abnormality in each part and each fault type into the correlation calculation model to calculate the correlation between each fault type of each part and each directly monitored data type. S103. Obtain the values ​​of each indirect monitoring data type corresponding to each maintenance of each part from the set of abnormal indirect monitoring data types and the set of values ​​corresponding to each maintenance of each part, and calculate the correlation between each fault type of each part and each indirect monitoring data type. S104. Sort the correlation between each fault type of each part and each directly monitored data type in descending order. The sorting result is used as the connection order of the monitored data types in the main-line data chain of each fault type of each part. Similarly, sort the correlation between each fault type of each part and each indirectly monitored data type in descending order. The sorting result is used as the connection order of the monitored data types in the auxiliary-line data chain of each fault type of each part of the equipment. The hierarchical data chain of the equipment is composed of the main-line data chain and the auxiliary-line data chain of each fault type of each part.

4. The operational equipment status monitoring and management system based on Internet of Things technology according to claim 2, characterized in that, The process of building the equipment maintenance experience base is as follows: S201. Based on the fault type corresponding to each maintenance of each part, calculate the attenuation coefficient of each maintenance scheme corresponding to each fault type of each part, input it into the empirical coefficient analysis model, and output the empirical coefficient of each maintenance scheme corresponding to each fault type of each part. S202. Based on the experience coefficients of each maintenance scheme corresponding to each fault type of each part, select each experience maintenance scheme corresponding to each fault type of each part, use each experience maintenance scheme corresponding to each fault type of each part as the equipment maintenance experience library, and sort each experience maintenance scheme corresponding to each fault type of each part in descending order according to the experience coefficient. The sorting result is the order of each experience maintenance scheme in the equipment maintenance experience library.

5. The operational equipment status monitoring and management system based on Internet of Things technology according to claim 1, characterized in that, The operation monitoring unit includes an operation monitoring module and an equipment maintenance module; The operation monitoring module is used to input the data collected by the sensor devices in the equipment into the hierarchical data chain of the equipment, analyze the operation of the equipment, and execute the equipment maintenance module when the equipment is malfunctioning. The equipment maintenance module is used to obtain various pre-selected maintenance schemes for the equipment based on the equipment maintenance experience library, obtain the current remaining production volume, production rate and remaining time from the production plan, and select the best maintenance scheme from the various pre-selected maintenance schemes for the equipment.

6. The operational equipment status monitoring and management system based on Internet of Things technology according to claim 5, characterized in that, The specific process of analyzing the operation of the equipment is as follows: Extract the monitoring values ​​of each directly monitored data type of each part in the hierarchical data chain, and compare them with the safe value range of each directly monitored data type to determine the operating status of the equipment, which includes normal and abnormal operating status. Extract the monitoring values ​​of each direct and indirect monitoring data type of each part in the equipment. At the same time, extract the correlation between each fault type of each part and each direct and indirect monitoring data type to identify the faulty part and the fault type.

7. The operational equipment status monitoring and management system based on Internet of Things technology according to claim 6, characterized in that, The process for selecting the optimal maintenance scheme is as follows: Each experience maintenance plan corresponding to the fault type of the equipment fault in the equipment maintenance experience database is taken as a pre-selected maintenance plan. The equipment status in each pre-selected maintenance plan is obtained. Each pre-selected maintenance plan with the same equipment status is taken as a plan group, thus obtaining each plan group. Predict the maintenance time and production rate in each plan group, and calculate the impact level of each plan group on the production plan based on the production plan. Select the plan group with the smallest impact level as the pre-selected plan group, and select the first-ranked pre-selected maintenance plan from the pre-selected plan group as the best maintenance plan.

8. The operational equipment status monitoring and management system based on Internet of Things technology according to claim 1, characterized in that, The device feedback unit includes a continuous monitoring module and a knowledge update module; The continuous monitoring module is used to collect the direct monitoring data and indirect monitoring data of the faulty parts at preset time intervals after equipment maintenance, and to calculate the attenuation coefficient of the part monitoring data. The attenuation coefficient of the part monitoring data is then used to analyze the maintenance effect of the equipment. The knowledge update module is used to extract the monitoring values ​​of each direct monitoring data type and each indirect monitoring data type corresponding to the faulty part, as well as the attenuation coefficient of the part monitoring data, update the connection order of each direct monitoring data type and each indirect monitoring data type in the hierarchical data chain, and update the order of the experience maintenance schemes corresponding to the faulty parts in the equipment maintenance experience base.

9. The operational equipment status monitoring and management system based on Internet of Things technology according to claim 8, characterized in that, The calculation process for the attenuation coefficient of the component monitoring data is as follows: Extract the safe value ranges for each direct monitoring data type and each indirect monitoring data type, and input the post-monitoring values ​​and safe value ranges for each direct monitoring data type and each indirect monitoring data type at each time point into the attenuation coefficient calculation model, and output the attenuation coefficient of the part monitoring data.

10. The operational equipment status monitoring and management system based on Internet of Things technology according to claim 1, characterized in that, It also includes a database for storing historical monitoring and management records.

Images