An industrial automation processing production line information intelligent monitoring system

Abstract

The present application relates to the field of industrial production line information, and is used to solve the problem that the conventional system lacks targeted and differentiated collection mechanism, resulting in a large amount of redundant data, and affecting the system response speed and analysis depth, in particular to an industrial automation processing production line information intelligent monitoring system, the present application divides the production line into levels and regions, and configures differentiated information collection density for the production line, dynamically adjusts the collection strategy of high-risk areas and low-risk areas, realizes the precise control of data collection behavior, so that the production line can maintain wide area monitoring with lower resource consumption when running normally, and can immediately enhance perception when finding abnormal signs, realize the on-demand allocation of monitoring resources, at the same time, make use of the advantages of fast response of edge computing and deep insight of cloud computing, realize the diagnosis and disposal of potential faults of the production line, and improve the reliability and intelligent operation and maintenance level of the production process.

Description

Technical Field

[0001] This invention relates to the field of industrial production line informatization, specifically to an intelligent monitoring system for information on industrial automated processing production lines. Background Technology

[0002] Industrial automated processing production lines are the core of modern manufacturing. Stable and efficient operation is crucial for ensuring product quality and improving production efficiency. With the development of technologies such as the Internet of Things and big data, real-time monitoring of the production line's operating status has become a basic means of realizing intelligent manufacturing. Conventional monitoring systems typically collect data by deploying various sensors on the production line and transmit it to a monitoring center or cloud platform via network for analysis and display. For example, relevant content is disclosed in patent applications CN118916245B and CN109710678B.

[0003] However, current monitoring systems still have many limitations. First, at the data acquisition level, most systems adopt a fixed frequency and fixed data type acquisition strategy, lacking a differentiated acquisition mechanism for different areas and equipment on the production line, resulting in a large amount of redundant data. This not only occupies network bandwidth and storage resources, but also easily leads to insufficient deep data capture capabilities for potential fault areas.

[0004] Furthermore, at the data analysis and decision-making closed-loop level, there is a lack of efficient collaboration between on-site edge computing and the powerful computing power of the cloud. The results of preliminary analysis on the edge side cannot effectively guide the real-time optimization of the front-end acquisition strategy, and the in-depth analysis conclusions from the cloud are difficult to be fed back to the on-site execution layer in a timely and accurate manner, resulting in limited response speed of the entire system.

[0005] To address the aforementioned technical problems, this invention proposes a solution. Summary of the Invention

[0006] This invention proposes an intelligent monitoring system for industrial automated processing production lines. It divides the production line into hierarchical and regional sections, assigns differentiated information collection densities, and dynamically adjusts collection strategies for high-risk and low-risk areas. This allows for precise control of data collection, enabling wide-area monitoring with low resource consumption during normal production line operation. Upon detecting abnormal signs, it immediately enhances perception, allowing for on-demand allocation of monitoring resources. Furthermore, leveraging the rapid response of edge computing and the deep insight of cloud computing, it diagnoses and addresses potential production line faults, improving the reliability and intelligent operation and maintenance level of the production process.

[0007] The objective of this invention can be achieved through the following technical solution: an intelligent monitoring system for information of an industrial automated processing production line, comprising a real-time information acquisition module, wherein the real-time information acquisition module is capable of acquiring the operating information of different zones of the production line according to the set information acquisition instructions, and obtaining the corresponding production line operating parameter data package;

[0008] The acquisition and control module is capable of acquiring operating parameter data packets, performing local parsing and judgment based on the operating parameter data packets, and dividing the operating parameter data packets into high-risk abnormal data blocks and suspected abnormal data blocks based on the parsing and judgment results.

[0009] The transmission control module is capable of acquiring the running parameter data packet, performing a first priority division based on the division result of the running parameter data packet, and then performing a second priority division through the data source of the running parameter data packet.

[0010] The priority decision module obtains the first priority division result and the second priority division result, generates an information transmission sequence based on the priority division result, and sends the information transmission sequence back to the transmission control module.

[0011] The transmission control module simultaneously acquires the current industrial ring network parameters and uploads the operating parameter data packets to the cloud based on the industrial ring network parameters and the information transmission sequence.

[0012] The cloud computing analysis module acquires the operating parameter data packet, performs in-depth cloud analysis on the operating parameter data packet, obtains the production line operating status analysis through the results of the in-depth cloud analysis, and simultaneously transmits the production line operating status analysis results back to the acquisition and control module.

[0013] The data acquisition and control module generates an optimized information acquisition instruction based on the production line's operating status and feeds it back to the real-time information acquisition module, which then collects production line operating information based on the optimized information acquisition instruction.

[0014] In a preferred embodiment of the present invention, the information acquisition instruction obtained by the information acquisition module includes an information acquisition area and an information acquisition density. The information acquisition area is used to divide the production line into layers and regions to obtain multiple sub-regions.

[0015] The information acquisition density obtained by the information acquisition module includes data acquisition frequency and data acquisition volume. Data acquisition frequency is the acquisition interval when information is acquired, while data acquisition volume is the number of types of information acquired.

[0016] The information acquisition module creates multiple sub-data packets according to different levels and different sub-regions, and then aggregates them into a running parameter data packet.

[0017] In a preferred embodiment of the present invention, the acquisition control module performs fault prediction on multiple sub-data packets to obtain fault prediction results at different levels and in different sub-regions. The fault prediction results include high-confidence fault results and low-confidence fault results.

[0018] The acquisition and control module marks the level and sub-region corresponding to the high-confidence fault results as high-risk areas, and records the corresponding sub-data packets as high-risk abnormal data blocks.

[0019] The acquisition and control module records the level and region corresponding to the low-confidence fault result as a low-risk region, and records the corresponding sub-data packet as a suspected abnormal data block;

[0020] The acquisition and control module records the operational information of other areas as normal data blocks.

[0021] In a preferred embodiment of the present invention, when the transmission control module performs a priority division, it assigns high-order abnormal data blocks as high transmission priority, suspected abnormal data blocks as normal transmission priority, and normal data blocks as low transmission priority.

[0022] When the transmission control module performs secondary priority division, it counts the level corresponding to each sub-data packet and verifies the compliance of the sub-data packets contained in each level. It obtains the proportion of high-risk abnormal data blocks and suspected abnormal data blocks in the sub-data packets corresponding to each level, and then performs weighted summation of the proportions to obtain the evaluation value of different levels.

[0023] The transmission control module sorts the network layer evaluation value, relay layer evaluation value, and processing layer evaluation value from high to low to obtain the secondary priority division result.

[0024] In a preferred embodiment of the present invention, the priority decision module generates a preliminary transmission sequence with three priorities based on the result of the first priority division, and then internally arranges each priority in the generated preliminary transmission sequence according to the second priority to obtain an information transmission sequence with nine priorities.

[0025] In a preferred embodiment of the present invention, the transmission control module acquires the network parameters of the industrial ring network through the network probe matrix and rates the current network status based on the network parameters. If the evaluation result is excellent, the information transmission sequence is transmitted in blocks together. If the evaluation result is abnormal, the sequence is transmitted step by step.

[0026] In a preferred embodiment of the present invention, after acquiring the operating parameter data packet, the cloud computing analysis module uses cloud computing power to combine and analyze the sub-data packets of the network layer, relay layer and processing layer in the operating parameter data packet. By using cloud computing power to perform more accurate fault analysis, the fault probability at the production line level and the fault probability of the production line area are obtained. The two sets of fault probabilities are then superimposed to obtain the final production line operating status analysis.

[0027] In a preferred embodiment of the present invention, the acquisition control module records the sub-regions as high-risk regions, low-risk regions, and normal regions, and performs different information acquisition densities and amounts for different regions through the real-time information acquisition module.

[0028] Compared with the prior art, the beneficial effects of the present invention are:

[0029] 1. This invention divides the production line into multiple logical layers and sub-regions, such as the network layer, relay layer, and processing layer, and configures them with differentiated information collection densities. This enables precise control of data collection behavior from the source. At the same time, the system can dynamically adjust the collection strategies for high-risk and low-risk areas based on the fault prediction confidence feedback from the edge side and the cloud. This allows the system to maintain wide-area monitoring with low resource consumption when the production line is running normally, and to immediately focus resources and enhance perception when abnormal signs are detected. This enables on-demand allocation of monitoring resources and greatly improves the targeting and efficiency of data collection.

[0030] 2. In this invention, through the collaborative work of the transmission control module and the priority decision module, the anomaly level of the data block itself and the production line logical level where the data source is located are considered simultaneously to generate a fine transmission sequence with multiple priorities. At the same time, combined with the real-time network status evaluation results, the transmission strategy is intelligently selected to ensure that the most valuable abnormal data and the most critical information are always transmitted first. This effectively avoids network congestion delays in fault reporting and diagnosis, and provides strong communication support for the safe and stable operation of the production line.

[0031] 3. This invention constructs a dual analysis between edge computing and cloud computing. It utilizes the powerful computing power of the cloud to perform deep fusion and correlation analysis on the data across the entire domain, obtains an accurate fault probability distribution, and dynamically adjusts the monitoring intensity of each area accordingly. This allows the system to simultaneously take into account the rapid response of edge computing and the deep insight advantages of cloud computing, enabling the diagnosis and handling of potential faults in the production line, and improving the reliability and intelligent operation and maintenance level of the production process. Attached Figure Description

[0032] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to the accompanying drawings.

[0033] Figure 1This is a system block diagram of the present invention;

[0034] Figure 2 This is a system flowchart of the present invention. Detailed Implementation

[0035] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0036] Example 1: Please refer to Figure 1 - Figure 2 As shown, an intelligent monitoring system for industrial automated processing production lines includes an information acquisition module, an acquisition control module, a transmission control module, a priority decision-making module, and a cloud computing analysis module.

[0037] The information acquisition module is used to collect the production line's operating information according to the information acquisition instructions, and package the collected operating information to obtain the operating parameter data package. Specifically, the information acquisition instructions obtained by the information acquisition module include the information acquisition area and the information acquisition density. The information acquisition area is used to divide the production line into three levels: network layer, relay layer and processing layer. Each level is then divided according to the production line area to obtain multiple sub-areas.

[0038] The information acquisition density acquired by the information acquisition module includes data acquisition frequency and data acquisition volume. The data acquisition frequency is the acquisition interval when the information acquisition module collects information from different levels and sub-areas in the production line, while the data acquisition volume is the number of information types collected, which are collected sequentially from high to low priority according to the information types.

[0039] The information acquisition module creates multiple sub-data packets based on different levels and sub-regions, and aggregates them into a running parameter data packet, which is then sent to the acquisition control module. By dividing the data according to levels and regions, and combining it with configurable acquisition density, the system can achieve refined management of data acquisition from the source, avoiding the waste of resources and processing burden caused by indiscriminate data acquisition, and ensuring the density and quality of data acquisition in key areas and under abnormal conditions, thus laying a solid data foundation for subsequent accurate analysis and fault prediction.

[0040] The acquisition and control module parses the data packets of operating parameters collected by the information acquisition module, and further divides them into multiple sub-data packets of different levels and different sub-regions. It then uses local computing power and machine learning algorithms to perform fault prediction on multiple sub-data packets, and obtains fault prediction results of different levels and different sub-regions. The fault prediction results include high-confidence fault results and low-confidence fault results.

[0041] When the acquisition and control module obtains a high-confidence fault result, it marks the level and sub-region corresponding to the high-confidence fault result and records it as a high-risk region. The high-risk region is fed back to the real-time information acquisition module. The real-time information acquisition module increases the information acquisition density and information acquisition volume of the high-risk region and records the sub-data packets corresponding to the high-risk region as high-risk abnormal data blocks.

[0042] When the acquisition and control module obtains a low-confidence fault result, it records the area corresponding to the low-confidence fault result as a low-risk area. The acquisition and control module feeds back the low-risk area to the real-time information acquisition module. The real-time information acquisition module increases the information acquisition density and information acquisition amount of the low-risk area, and records the sub-data packets corresponding to the low-risk area as suspected abnormal data blocks.

[0043] The data acquisition and control module records operational information that does not belong to high-risk or low-risk areas as normal data blocks.

[0044] Example 2: Please refer to Figure 1 - Figure 2 As shown, after acquiring the operating parameter data packet, the transmission control module prioritizes high-order abnormal data blocks, normal data blocks, and normal data blocks.

[0045] The transmission control module statistically analyzes the data sources of sub-data packets in the running parameter data packet to obtain the layer corresponding to each sub-data packet, and verifies the compliance of the sub-data packets contained in each layer. That is, it selects all sub-data packets in the network layer, calculates the proportion of high-risk abnormal data blocks and suspected abnormal data blocks in the sub-data packets corresponding to the network layer, and then calculates the weighted sum of the proportions of the three types of compliant data blocks through weight allocation to obtain the network layer evaluation value.

[0046] The transmission control module then selects the relay layer in the same way, calculates the proportion of high-risk abnormal data blocks and suspected abnormal data blocks in the sub-data packets corresponding to the relay layer, and then performs a weighted sum based on the proportions to obtain the relay layer evaluation value.

[0047] Similarly, the transmission control module calculates the proportion of high-risk abnormal data blocks and suspected abnormal data blocks in the sub-data packets corresponding to the processing layer, and then obtains the processing layer evaluation value by weighted summation.

[0048] The transmission control module sorts the network layer evaluation value, relay layer evaluation value, and processing layer evaluation value from high to low, and uses the sorting result as the result of secondary priority division.

[0049] The priority decision module obtains the results of the first and second priority divisions from the transmission control module. Based on the first priority division result, it generates a preliminary transmission sequence with three priorities. Then, based on the second priority, it internally arranges each priority in the preliminary transmission sequence to obtain an information transmission sequence with nine priorities. The information transmission sequence is then fed back to the transmission control module. For example, if the preliminary transmission sequence generated by the first priority division is: high-risk abnormal data block, suspected abnormal data block, and normal data block, and the second priority ranking result is processing layer → network layer → relay layer, then the final generated information transmission sequence is: processing layer high-risk abnormal data block, network layer high-risk abnormal data block, relay layer high-risk abnormal data block, processing layer suspected abnormal data block, network layer suspected abnormal data block, relay layer suspected abnormal data block, processing layer normal data block, network layer normal data block, and relay layer normal data block.

[0050] The transmission control module acquires network parameters of the industrial ring network through a network probe matrix and rates the current network status based on these parameters. If the evaluation result is excellent, the information transmission sequence is transmitted in blocks together. If the evaluation result is abnormal, the sequence is transmitted step by step. Through dual priority decision-making, the data anomaly level is deeply integrated with the production line logic level, realizing multi-dimensional and refined data transmission sequence. Under any network bandwidth conditions, the most urgent and critical data is prioritized to be uploaded to the analysis center in a timely manner, optimizing network resource utilization efficiency and significantly shortening the end-to-end latency from the occurrence of an anomaly to cloud analysis, thus gaining valuable time for rapid response.

[0051] After acquiring the operating parameter data packet, the cloud computing analysis module uses cloud computing power to combine and analyze the sub-data packets of the network layer, relay layer, and processing layer in the operating parameter data packet. By using cloud computing power to perform more accurate fault analysis, it obtains the fault probability at the production line level and the fault probability of the production line area. Then, it superimposes the two sets of fault probabilities to obtain the final production line operating status analysis.

[0052] Specifically, after the cloud computing analysis module obtains the failure probability at the production line level and the failure probability at the production line area, it selects a sub-region and evaluates the failure probability of the sub-region based on the production line level and production line area to which the sub-region belongs, thereby obtaining a higher confidence level for failure prediction. After making high-confidence failure predictions for all sub-regions, the cloud computing analysis module feeds back the prediction results to the acquisition and control module.

[0053] The data acquisition and control module records sub-regions as either high-risk or normal based on the prediction results. The real-time information acquisition module then applies different data acquisition densities and volumes to these two regions. This allows the real-time information acquisition module to dynamically adjust its data acquisition based on the different states of different areas of the production line. During normal operation, simpler, lower-frequency acquisition is performed, reducing data volume while ensuring basic monitoring. Conversely, when an anomaly occurs, the acquisition frequency and data volume are increased, significantly improving the ability to monitor and respond to faults in the abnormal area, ensuring timely fault response.

[0054] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. An intelligent monitoring system for information in an industrial automated processing production line, characterized in that, It includes a real-time information acquisition module, which can collect the operating information of different zones of the production line according to the set information acquisition instructions, and obtain the corresponding production line operating parameter data package; The acquisition and control module is capable of acquiring operating parameter data packets, performing local parsing and judgment based on the operating parameter data packets, and dividing the operating parameter data packets into high-risk abnormal data blocks and suspected abnormal data blocks based on the parsing and judgment results. The transmission control module is capable of acquiring the running parameter data packet, performing a first priority division based on the division result of the running parameter data packet, and then performing a second priority division through the data source of the running parameter data packet. The priority decision module obtains the first priority division result and the second priority division result, generates an information transmission sequence based on the priority division result, and sends the information transmission sequence back to the transmission control module. The transmission control module simultaneously acquires the current industrial ring network parameters and uploads the operating parameter data packets to the cloud based on the industrial ring network parameters and the information transmission sequence. The cloud computing analysis module acquires the operating parameter data packet, performs in-depth cloud analysis on the operating parameter data packet, obtains the production line operating status analysis through the results of the in-depth cloud analysis, and sends the production line operating status analysis results back to the acquisition and control module. The data acquisition and control module generates an optimized information acquisition instruction based on the production line operating status and feeds it back to the real-time information acquisition module. The real-time information acquisition module then collects production line operating information based on the optimized information acquisition instruction. The information acquisition module obtains information acquisition instructions including information acquisition area and information acquisition density. The information acquisition area is used to divide the production line into layers and regions, resulting in multiple sub-regions. The information acquisition density obtained by the information acquisition module includes data acquisition frequency and data acquisition volume. Data acquisition frequency is the acquisition interval when information is acquired, while data acquisition volume is the number of types of information acquired. The information acquisition module creates multiple sub-data packets according to different levels and different sub-regions, and then aggregates them into a running parameter data packet.

2. The intelligent monitoring system for information on an industrial automated processing production line according to claim 1, characterized in that, The acquisition and control module performs fault prediction on multiple sub-data packets to obtain fault prediction results at different levels and in different sub-regions. The fault prediction results include high-confidence fault results and low-confidence fault results. The acquisition and control module marks the level and sub-region corresponding to the high-confidence fault results as high-risk areas, and records the corresponding sub-data packets as high-risk abnormal data blocks. The acquisition and control module records the level and region corresponding to the low-confidence fault result as a low-risk region, and records the corresponding sub-data packet as a suspected abnormal data block; The acquisition and control module records the operational information of other areas as normal data blocks.

3. The intelligent monitoring system for information on an industrial automated processing production line according to claim 2, characterized in that, When the transmission control module performs a priority division, it assigns high-order abnormal data blocks as high transmission priority, suspected abnormal data blocks as normal transmission priority, and normal data blocks as low transmission priority. When the transmission control module performs secondary priority division, it counts the level corresponding to each sub-data packet and verifies the compliance of the sub-data packets contained in each level. It obtains the proportion of high-risk abnormal data blocks and suspected abnormal data blocks in the sub-data packets corresponding to each level, and then performs weighted summation of the proportions to obtain the evaluation value of different levels. The transmission control module sorts the network layer evaluation value, relay layer evaluation value, and processing layer evaluation value from high to low to obtain the secondary priority division result.

4. The intelligent monitoring system for information on an industrial automated processing production line according to claim 3, characterized in that, The priority decision module generates a preliminary transmission sequence with three priorities based on the first priority division result. Then, based on the second priority, each priority in the generated preliminary transmission sequence is internally arranged to obtain an information transmission sequence with nine priorities.

5. The intelligent monitoring system for information on an industrial automated processing production line according to claim 3, characterized in that, The transmission control module acquires the network parameters of the industrial ring network through the network probe matrix and rates the current network status based on the network parameters. If the evaluation result is excellent, the information transmission sequence is transmitted in blocks together. If the evaluation result is abnormal, the sequence is transmitted step by step.

6. The intelligent monitoring system for information on an industrial automated processing production line according to claim 1, characterized in that, After acquiring the operating parameter data packet, the cloud computing analysis module uses cloud computing power to combine and analyze the sub-data packets of the network layer, relay layer, and processing layer in the operating parameter data packet. By using cloud computing power to perform more accurate fault analysis, it obtains the fault probability at the production line level and the fault probability of the production line area. Then, it superimposes the two sets of fault probabilities to obtain the final production line operating status analysis.

7. The intelligent monitoring system for information on an industrial automated processing production line according to claim 1, characterized in that, The acquisition control module records the sub-regions as high-risk areas, low-risk areas, and normal areas, and performs different information acquisition densities and amounts for different areas through the real-time information acquisition module.

Images