Production line data visualization method and device, equipment and storage medium

Abstract

The invention discloses a production line data visualization method and device, equipment and a storage medium. The method comprises the following steps: acquiring production line equipment data by using a sensor arranged on production line equipment, and transmitting the production line equipment data to an edge gateway; controlling the edge gateway to obtain production line state data based on processing of the production line equipment data, and transmitting the production line state data to a cloud platform; and driving the cloud platform to determine production line production data based on the production line state data, extracting production data features of the production line production data, matching a target visualization mode by using the production data features, and displaying the production line production data by using the target visualization mode. According to the scheme, an efficient data processing and transmission mechanism is constructed between the edge gateway and the cloud platform, real-time collection, analysis and visualization of the production line data are realized, the operation state and the abnormal condition of the production line are visually displayed, and the efficiency and the accuracy of production line monitoring are improved.

Description

Technical Field

[0001] This application relates to the field of industrial technology, and in particular to a method, apparatus, equipment and storage medium for visualizing production line data. Background Technology

[0002] With the rapid development of smart manufacturing and industrial IoT technologies, instant noodle manufacturers are increasingly demanding advanced data analysis and visualization for their production lines. Traditional production line management relies heavily on manual recording, statistics, and monitoring, which not only results in slow data response and difficulty in real-time analysis but also limits production efficiency and fails to support the high demands of enterprises in cost control and capacity optimization.

[0003] However, existing production lines generally suffer from problems such as data fragmentation, information silos, and frequent manual intervention in high-level data analysis and visualization. This not only results in slow response speed and low data utilization efficiency, but also makes it difficult to provide enterprises with real-time production optimization decision support, thus limiting the progress of digital and intelligent transformation. Summary of the Invention

[0004] This application provides a production line data visualization method, apparatus, equipment, and storage medium. It can dynamically perceive the production line's operating status based on production line equipment data and generate high-level production data features, thereby achieving intelligent analysis and visualization of the production line status. This application achieves real-time analysis and visualization of production line status and anomaly information by collecting production line equipment data and processing it at the edge and cloud levels. This method supports intelligent monitoring and visualization of production status, significantly improving the digitalization and intelligence level of production line management, and is particularly suitable for high-capacity, continuously operating food processing production environments.

[0005] Firstly, this application provides a production line data visualization method, including:

[0006] Data from the production line equipment is collected using sensors installed on the equipment and then transmitted to an edge gateway.

[0007] The edge gateway is controlled to obtain production line status data based on the production line equipment data processing, and the production line status data is transmitted to the cloud platform.

[0008] The cloud platform is driven to determine production data based on the production line status data, extract production data features from the production data, match the production data features with a target visualization method, and display the production data using the target visualization method.

[0009] Secondly, this application provides a production line data visualization device, comprising:

[0010] The acquisition module is used to collect data from the production line equipment using sensors installed on the production line equipment, and transmit the data from the production line equipment to the edge gateway;

[0011] An edge module is used to control the edge gateway to obtain production line status data based on the production line equipment data processing, and to transmit the production line status data to the cloud platform.

[0012] The visualization module is used to drive the cloud platform to determine the production data of the production line based on the production line status data, extract the production data features of the production data, match the production data features with the target visualization method, and display the production data of the production line using the target visualization method.

[0013] Thirdly, this application provides a production line data visualization device, comprising:

[0014] One or more processors;

[0015] A memory that stores one or more programs that, when executed by one or more processors, enable the one or more processors to implement the production line data visualization method as described in the first aspect.

[0016] Fourthly, this application provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the production line data visualization method as described in the first aspect.

[0017] This application constructs a multi-stage collaborative mechanism covering production line data acquisition, edge processing, and cloud analysis, combined with status awareness and visualization matching strategies, to achieve automated and high-precision execution of production line data visualization. First, sensors installed on production line equipment collect data, which is then transmitted to an edge gateway for preliminary processing to generate production line status data. Based on the aggregation of multi-source status data, the cloud platform-driven analysis module generates production line production data and extracts its features. Subsequently, the scheduling visualization module matches the target visualization method based on the production data features and uses this method to display the production line production data, providing an intuitive presentation of production line operating status, key indicators, and anomaly information. This method, through the combination of edge computing and cloud analysis, ensures the efficiency, real-time performance, and stability of data processing and visualization, effectively improving the intelligence level of production line management and is suitable for high-capacity, continuously operating food processing environments. Attached Figure Description

[0018] Figure 1 This is a flowchart of a production line data visualization method provided in an embodiment of this application;

[0019] Figure 2This is a flowchart of an edge gateway determination method provided in an embodiment of this application;

[0020] Figure 3 This is a flowchart of an edge gateway score filtering method provided in an embodiment of this application;

[0021] Figure 4 This is a flowchart of a method for determining production data on a production line, provided in an embodiment of this application.

[0022] Figure 5 This is a flowchart of a production line production data visualization method provided in an embodiment of this application;

[0023] Figure 6 This is a flowchart of a sensor acquisition frequency adjustment method provided in an embodiment of this application;

[0024] Figure 7 This is a system architecture diagram of a production line data visualization method provided in an embodiment of this application;

[0025] Figure 8 This is a structural block diagram of a production line data visualization device provided in an embodiment of this application;

[0026] Figure 9 This is a schematic diagram of the structure of a production line data visualization device provided in an embodiment of this application. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this application clearer, specific embodiments of this application will be described in further detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely for explaining this application and not for limiting it. It should also be noted that, for ease of description, only the parts relevant to this application are shown in the drawings, not all of them. Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe operations (or steps) as being processed sequentially, many of these operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. A process can be terminated when its operation is completed, but it may also have additional steps not included in the drawings. A process can correspond to a method, function, procedure, subroutine, subroutine, etc.

[0028] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0029] With the rapid advancement of intelligent and digital transformation in the food processing industry, traditional instant noodle production lines generally rely on manual statistics and experience-based management, which struggles to meet enterprises' high demands for production efficiency, cost control, and equipment operation visualization. However, existing production lines commonly suffer from problems such as data fragmentation, information silos, and frequent manual intervention in advanced data analysis and visualization. This not only results in delayed responses but also hinders real-time monitoring of production status, rapid anomaly identification, and optimization decisions. Especially in complex scenarios involving multiple production lines and concurrent equipment operation, efficient and accurate production data management and visualization become even more difficult, limiting enterprises' progress in digital and intelligent management.

[0030] To address the aforementioned challenges, this application constructs a production line data visualization system based on edge computing and cloud analytics. This system enables the automatic collection, processing, and visualization of production line equipment data without manual intervention. By integrating an IoT sensing platform, the system can collect real-time data on the operating status of production line equipment, key process parameters, and environmental information. This data is then transmitted to an edge gateway for preliminary processing to generate production line status data. Based on this, a cloud platform analytics module drives advanced data processing to determine production line data and extract its features. Subsequently, a visualization scheduling module matches the target visualization method to the production data features and uses this method to display the production line data, providing an intuitive presentation of the production line's operating status, key indicators, and anomaly information.

[0031] The production line data visualization method proposed in this application not only improves the efficiency of production line status information collection and processing, but also significantly enhances production data analysis and visualization capabilities, making it particularly suitable for complex production environments with multiple devices and processes. Compared with traditional manual statistics and monitoring methods, it boasts higher real-time performance, intelligence, and scalability, enabling precise monitoring of equipment operating status and optimization of production efficiency while ensuring production continuity. This provides food processing enterprises, especially instant noodle manufacturers, with a high-level management platform oriented towards digitalization and intelligence.

[0032] The production line data visualization method provided in this embodiment can be executed by a production line data visualization device. This device can be implemented through software and / or hardware, and can consist of two or more physical entities, or a single physical entity. For example, the production line data visualization device can be a cloud server used to monitor the production line status.

[0033] The production line data visualization device is equipped with at least one type of operating system, including but not limited to Android, Linux, and Windows. The device can install at least one application based on the operating system; this application can be a built-in application of the operating system or an application downloaded from a third-party device or server. In this embodiment, the production line data visualization device has at least one application capable of executing production line data visualization methods.

[0034] For ease of understanding, this embodiment uses the operation and maintenance server as the main body for executing the production line data visualization method as an example for description.

[0035] Figure 1 A flowchart of a production line data visualization method provided in an embodiment of this application is given. (Reference) Figure 1 The specific methods for visualizing production line data include:

[0036] S110. Collect production line equipment data using sensors installed on the production line equipment, and transmit the production line equipment data to the edge gateway.

[0037] In some embodiments, sensors installed on the production line equipment collect data from the production line equipment. The production line equipment refers to mechanical equipment or tooling used for production, processing, or assembly. The sensors refer to various detection modules installed on the production line equipment, used to collect physical quantities such as temperature, pressure, speed, current, voltage, vibration, or displacement in real time. The production line equipment data refers to digital information collected by the sensors that characterizes the equipment's operating status, processing parameters, and environmental conditions. Subsequently, the production line equipment data is transmitted to an edge gateway. The edge gateway refers to computing and communication equipment deployed on the production site for aggregating, preprocessing, and forwarding data.

[0038] In one embodiment, the method for collecting production line equipment data can be: sensors acquire equipment operating parameters through timed sampling or event triggering, and store the raw data in a local cache or send it to a gateway.

[0039] In one embodiment, the method of collecting production line equipment data can also be: collecting multi-dimensional data through a combination of multiple sensors, including temperature sensors, current sensors, acceleration sensors, etc., to comprehensively reflect the operating status of the equipment.

[0040] In one embodiment, data can be transmitted to the edge gateway by sending the collected production line equipment data to the edge gateway via a wired or wireless communication interface.

[0041] In one embodiment, the data can be transmitted to the edge gateway by preprocessing or compressing the production line equipment data during transmission to reduce network load and ensure real-time performance.

[0042] Optionally, Figure 2 A flowchart of an edge gateway determination method provided in an embodiment of this application is given. (Reference) Figure 2 The method for determining the edge gateway specifically includes:

[0043] S1101. Determine several candidate gateways from a preset gateway list, and obtain the network data, processing speed, and queue cache corresponding to each candidate gateway.

[0044] For example, several candidate gateways are determined from a preset gateway list. A gateway refers to an edge computing node used to aggregate, process, and forward data from production line equipment. Candidate gateways are a subset of gateways selected from the preset gateway list for performing data processing or task distribution. Subsequently, the network data, processing speed, and queue cache corresponding to each candidate gateway are obtained. Network data refers to indicators reflecting the communication performance between the gateway and the cloud platform or production line equipment, such as bandwidth, latency, and packet loss rate. Processing speed refers to the rate at which the gateway processes tasks or data streams. Queue cache refers to the buffer capacity used by the gateway to temporarily store tasks or data during task scheduling or data processing.

[0045] In one embodiment, the candidate gateway can be determined by selecting several gateways that meet the requirements from a preset list as candidates based on the gateway's geographical location, historical load, or network connection status.

[0046] In one embodiment, network data can be obtained by collecting metrics such as bandwidth, latency, and packet loss rate in real time through the gateway's own monitoring module or network detection tools.

[0047] In one embodiment, the processing speed can be obtained by calculating the amount of data or number of tasks processed per unit time based on the gateway's task execution records or processing performance test results.

[0048] In one embodiment, the queue cache can be obtained by reading the gateway's internal task queue status or buffer usage to assess its available cache capacity and task throughput.

[0049] S1102. Based on the network data, the processing speed, and the queue cache, obtain the network performance score, processing performance score, and queue cache score of the candidate gateway, respectively.

[0050] For example, network performance score, processing performance score, and queue cache score of candidate gateways are obtained based on network data, processing speed, and queue cache, respectively. Here, candidate gateways refer to a subset of gateways selected from a preset gateway list for performing data processing or task distribution. Network performance score refers to a comprehensive performance score calculated based on indicators such as network bandwidth, latency, and packet loss rate of the gateway. Processing performance score refers to a processing capacity score calculated based on the rate at which the gateway processes tasks or data streams. Queue cache score refers to a queue processing capacity score calculated based on the available capacity of the gateway buffer and the task throughput.

[0051] In one embodiment, the network performance score can be obtained by assigning weights to network metrics such as bandwidth, latency, and packet loss rate, and calculating a comprehensive score to characterize the communication quality of the candidate gateway.

[0052] In one embodiment, the processing performance score can be obtained by normalizing the score based on the amount of data or tasks processed by the gateway per unit time to quantify its task processing capability.

[0053] In one embodiment, the queue cache score can be obtained by combining the remaining capacity of the gateway buffer and the task queue length to calculate a score of the queue processing capacity, which is used to evaluate the gateway's scheduling potential under high load conditions.

[0054] In one embodiment, a comprehensive performance evaluation of candidate gateways can be further performed based on network performance score, processing performance score, and queue cache score, providing a basis for task allocation or gateway selection.

[0055] S1103. Based on the network performance score, the processing performance score, and the queue cache score, select an edge gateway from the candidate gateways and transmit the production line equipment data to the edge gateway.

[0056] For example, edge gateways are selected from candidate gateways based on network performance score, processing performance score, and queue buffer score. Candidate gateways refer to a subset of gateways selected from a preset gateway list for performing data processing or task distribution. The network performance score is a communication quality score calculated based on bandwidth, latency, and packet loss rate. The processing performance score is a processing capacity score calculated based on task processing rate. The queue buffer score is a queue processing capacity score calculated based on buffer capacity and task queue length. The edge gateway is the gateway node ultimately selected to receive, process, and forward production line equipment data. Subsequently, the production line equipment data is transmitted to the edge gateway. This production line equipment data refers to equipment operating parameters, environmental information, and processing status data collected by sensors installed on the production line equipment.

[0057] In one embodiment, the method for selecting edge gateways from candidate gateways may be: to perform a weighted comprehensive score based on network performance score, processing performance score, and queue cache score, and select one or more gateways with the highest comprehensive score as edge gateways.

[0058] In one embodiment, the method for selecting edge gateways from candidate gateways can also be: setting a predefined threshold and selecting only gateways that simultaneously meet the requirements of network performance, processing capacity, and queue capacity as edge gateways.

[0059] In one embodiment, the production line equipment data can be transmitted to the edge gateway in real time or in batches via a wired or wireless communication interface.

[0060] In one embodiment, the way to transmit production line equipment data to the edge gateway can also be by compressing or encrypting the data during transmission to ensure network transmission efficiency and data security.

[0061] Optionally, Figure 3 A flowchart of an edge gateway score filtering method provided in an embodiment of this application is given. (Reference) Figure 3 The edge gateway score filtering method specifically includes:

[0062] S11031. Obtain the data type of the production line equipment data, and determine the network performance weight, processing performance weight, and queue cache weight corresponding to the network performance score, processing performance score, and queue cache score respectively based on the data type.

[0063] For example, the data type of the production line equipment data is obtained. This data refers to the equipment operating parameters, environmental information, and processing status data collected by sensors installed on the production line equipment. The data type refers to the attribute characterizing the category of the production line equipment data, such as temperature, pressure, current, vibration, image, or video. Subsequently, based on the data type, the network performance score, processing performance score, and queue cache score are determined, each with its corresponding network performance weight, processing performance weight, and queue cache weight. The network performance weight refers to the weighting coefficient of the network performance score when comprehensively evaluating candidate gateways; the processing performance weight refers to the weighting coefficient of the processing performance score; and the queue cache weight refers to the weighting coefficient of the queue cache score, reflecting the relative importance of different data types in gateway selection.

[0064] In one embodiment, network performance weights can be determined by assigning different network performance weights based on the sensitivity of data types to communication bandwidth, latency, or packet loss, in order to ensure the transmission priority of critical data types.

[0065] In one embodiment, the processing performance weight can be determined by allocating processing performance weights according to the differences in gateway processing rate requirements based on data types, so that gateways with stronger processing capabilities are preferentially selected for data types with high computational demands.

[0066] In one embodiment, the queue cache weight can be determined by allocating queue cache weights based on the differences in buffer capacity requirements of data types, so that high-frequency or large-volume data types receive higher priority in queue management.

[0067] In one embodiment, based on determined weights, candidate gateways can be weighted and comprehensively scored to provide a reference for the final selection of the edge gateway.

[0068] S11032. Calculate the gateway score of the candidate gateway based on the network performance score, the processing performance score, and the queue cache score, as well as their corresponding network performance weights, processing performance weights, and queue cache weights, and determine the candidate gateway with the highest gateway score as the edge gateway.

[0069] For example, the gateway score of a candidate gateway is calculated based on the network performance score, processing performance score, and queue cache score, along with their corresponding network performance weights, processing performance weights, and queue cache weights. Here, a candidate gateway refers to a subset of gateways selected from a pre-defined gateway list for performing data processing or task distribution. The network performance score reflects the gateway's communication quality, the processing performance score reflects its task processing capability, and the queue cache score reflects its buffer processing capability. The network performance weight, processing performance weight, and queue cache weight are weights assigned to each score based on data type. The gateway score is the weighted calculation result based on each score and weight, used to comprehensively evaluate the overall performance of the candidate gateways. Subsequently, the candidate gateway with the highest gateway score is determined as the edge gateway, where the edge gateway is the gateway node ultimately selected for receiving, processing, and forwarding data from production line equipment.

[0070] In one embodiment, the gateway score of a candidate gateway can be calculated by multiplying the network performance score, processing performance score, and queue cache score by their respective weights and then summing them to obtain the comprehensive gateway score for each candidate gateway.

[0071] In one embodiment, the edge gateway can be determined by comparing the gateway scores of all candidate gateways and selecting the gateway with the highest score as the edge gateway to ensure optimal overall performance of data transmission and processing.

[0072] In one embodiment, a candidate list can be established for multiple candidate gateways with similar gateway scores to switch over when the main edge gateway malfunctions or is overloaded, ensuring the stability and reliability of the system.

[0073] S120. Control the edge gateway to obtain production line status data based on the production line equipment data processing, and transmit the production line status data to the cloud platform.

[0074] In some embodiments, the control edge gateway obtains production line status data based on production line equipment data processing. Here, the edge gateway refers to computing and communication equipment deployed on the production site for data aggregation, preprocessing, and forwarding; the production line equipment data refers to equipment operating parameters and environmental information collected by sensors installed on the production line equipment; and the production line status data refers to comprehensive information that, after data processing, analysis, and fusion, can characterize the operating status, production efficiency, abnormal indicators, and processing quality of the production line equipment. Subsequently, the production line status data is transmitted to a cloud platform, where the cloud platform refers to a computing environment deployed in a remote or local data center for centralized storage, analysis, visualization, and scheduling management of the production line data.

[0075] In one embodiment, the way to obtain production line status data based on production line equipment data processing can be: through data cleaning, anomaly detection, normalization processing and feature extraction, the raw equipment data is converted into standardized indicators that can be used for status assessment and decision-making.

[0076] In one embodiment, the method of obtaining production line status data based on production line equipment data processing can also be: combining edge computing capabilities to perform real-time analysis and aggregation of data to generate various operating indicators, alarm statuses, and production efficiency statistics.

[0077] In one embodiment, the production line status data can be transmitted to the cloud platform by sending the data processed by the edge gateway to the cloud platform in batch or real-time stream via a wired or wireless network interface.

[0078] In one embodiment, the production line status data can also be transmitted to the cloud platform by encrypting or compressing the status data during the data transmission process to ensure data security and network transmission efficiency.

[0079] S130. Drive the cloud platform to determine the production line production data based on the production line status data, extract the production data features of the production line production data, use the production data features to match the target visualization method, and display the production line production data using the target visualization method.

[0080] In some embodiments, the cloud platform determines production line production data based on production line status data. Here, the cloud platform refers to a computing environment used for centralized storage, analysis, and visualization of production line information; the production line status data refers to equipment operating parameters, abnormal indicators, and processing quality information processed by an edge gateway; and the production line production data refers to comprehensive information that, after further analysis, calculation, and integration, can characterize production progress, output, efficiency, quality status, and resource utilization. Subsequently, production data features are extracted from the production line production data. These production data features refer to statistical information or sets of indicators that can reflect production patterns, equipment load, bottlenecks, and key performance indicators.

[0081] In one embodiment, production data characteristics are used to match target visualization methods, where target visualization methods refer to charts, graphs, or interactive interfaces suitable for displaying specific types of data, such as line charts, bar charts, heat maps, or dashboards. The most suitable display format can be selected by matching production data characteristics.

[0082] In one embodiment, the method of displaying production line production data using target visualization can be as follows: the extracted production data features are mapped to corresponding graphic elements, interactive charts are generated through visualization tools or interface components, and then presented on the cloud platform interface.

[0083] In one embodiment, the method of displaying production line production data using target visualization can also be: combining a real-time refresh mechanism to periodically update and display dynamically changing production data to reflect the real-time status and trend changes of the production line operation.

[0084] In one embodiment, the way to display production line data using a target visualization approach can also be to filter and customize the display of different categories of production data according to user roles or permissions, thereby meeting the differentiated needs of managers, operators, or maintenance personnel.

[0085] Optionally, Figure 4 A flowchart of a method for determining production line production data according to an embodiment of this application is provided. (Reference) Figure 4 The specific methods for determining the production data of this production line include:

[0086] S1301. Determine abnormal status data based on the production line status data and the preset standard status data.

[0087] For example, abnormal status data is determined based on production line status data and preset standard status data. The production line status data refers to the equipment operation and processing status information obtained by the edge gateway after processing the production line equipment data. The standard status data refers to the preset reference data that characterizes various parameters of the production line under normal production conditions. Abnormal status data refers to status information that deviates from the range of standard status data, and is used to identify production situations that may have equipment failures, process abnormalities, or environmental abnormalities.

[0088] In one embodiment, the abnormal state data can be determined by comparing the production line state data with the standard state data item by item, marking parameters that exceed a preset threshold as abnormal states, and generating an abnormal state data set.

[0089] In one embodiment, a statistical model or machine learning model can also be established based on historical production data to automatically identify abnormal state data through deviation analysis with standard state data, thereby improving the accuracy and real-time performance of anomaly detection.

[0090] In one embodiment, the identified abnormal state data can be used for subsequent production line data feature extraction, visualization, and intelligent scheduling applications to assist in production management and equipment maintenance.

[0091] S1302. Match the corresponding abnormality type according to the abnormality data, and determine the corresponding parameter processing model based on the abnormality type.

[0092] For example, the system matches the corresponding anomaly type based on the abnormal state data. Abnormal state data refers to production line status information that deviates from the standard state data range, and anomaly type refers to different anomaly categories classified according to the characteristics of the abnormal state data, such as equipment failure, process anomaly, or environmental anomaly, used to characterize the nature and source of the abnormal state. Subsequently, the system determines the corresponding parameter processing model based on the anomaly type. The parameter processing model refers to a computational model or algorithm used to analyze, correct, or optimize production line parameters, guiding the handling of abnormal states and adjustments to the production process.

[0093] In one embodiment, the method for matching anomaly types may be: comparing the numerical characteristics, trends, or patterns of the anomaly state data with predefined anomaly type templates or rules to determine the most matching anomaly type.

[0094] In one embodiment, the parameter processing model can be determined by selecting a corresponding mathematical model, control algorithm, or machine learning model based on the processing strategy associated with the anomaly type, in order to predict the development of the anomaly, adjust production parameters, or optimize equipment operation.

[0095] In one embodiment, multiple parameter processing models can be selected for joint analysis of complex abnormal states to achieve refined processing and optimized decision-making for complex abnormal situations.

[0096] S1303. Input the production line status data into the parameter processing model to obtain production line production data.

[0097] For example, production line status data is input into a parameter processing model to obtain production line production data. Here, production line status data refers to the equipment operation and processing status information obtained after the edge gateway processes the production line equipment data. The parameter processing model refers to the calculation model or algorithm used to analyze, optimize or predict production line production parameters. Production line production data refers to the comprehensive data that can characterize the production process, equipment performance and product quality obtained by model processing of production line status data, and is used for subsequent production data feature extraction and visualization.

[0098] In one embodiment, the way to input production line status data into the parameter processing model can be: inputting various status parameters into the model's input interface in a preset format, and the model processing the data according to the built-in algorithm or training results to output the corresponding production line production data.

[0099] In one embodiment, production line production data can be obtained by: calculating equipment operation indicators, process parameter adjustment suggestions, capacity forecasts, or quality assessment results through a parameter processing model, and then organizing these results into a unified production line production data set.

[0100] In one embodiment, the resulting production line data can be used for subsequent production process monitoring, anomaly analysis, and intelligent scheduling, thereby improving production efficiency and product quality control capabilities.

[0101] Optionally, Figure 5 A flowchart of a production line production data visualization method provided in an embodiment of this application is given. (Reference) Figure 5 The specific methods for visualizing production data on this production line include:

[0102] S1304. Obtain the adjacent production data of the production line from the previous collection cycle.

[0103] For example, production data adjacent to the previous collection period of production line data is obtained. Production line data refers to comprehensive data that can characterize the production process, equipment performance and product quality after the production line status data is analyzed and processed by the parameter processing model. Adjacent production data refers to production line data obtained in the previous period that is immediately adjacent to the current collection period, which is used for data comparison, trend analysis or dynamic change assessment.

[0104] In one embodiment, the method for obtaining adjacent production data may be: locating the production data of the previous collection period from historical production data records stored in the edge gateway or cloud platform based on the timestamp or collection period index, and extracting it as adjacent production data.

[0105] In one embodiment, the acquired adjacent production data can be used to compare and analyze with the current cycle production line data to identify production trends, detect potential anomalies, or guide production process optimization. Alternatively, adjacent production data from multiple preceding cycles can be analyzed together to form a longer-cycle production dynamic sequence, thereby improving the accuracy of anomaly detection and predictive analysis.

[0106] S1305. Calculate the fluctuation range of the production line data and the adjacent production data, and determine the production line data with fluctuation range greater than the preset fluctuation range threshold as fluctuation state data.

[0107] For example, the fluctuation range of production line data and adjacent production data is calculated. Production line data refers to the comprehensive production information obtained after processing production line status data through a parameter processing model. Adjacent production data refers to the production line production data from the previous cycle, which is immediately adjacent to the current collection cycle. Fluctuation range refers to the degree of change in numerical values, indicators, or performance parameters between production line data and adjacent production data, used to characterize the dynamic fluctuations in the production process. Subsequently, production line data with fluctuation ranges exceeding a preset fluctuation range threshold are identified as fluctuating state data. Fluctuating state data refers to production line data that deviates from the normal fluctuation range and may reflect production instability, equipment malfunctions, or process fluctuations.

[0108] In one embodiment, the fluctuation range can be calculated by calculating the difference or relative rate of change between the current cycle and the previous cycle for each production line parameter, and then combining them to form a fluctuation range index.

[0109] In one embodiment, the method for determining fluctuation state data may be: comparing the calculated fluctuation amplitude with a preset fluctuation amplitude threshold, and marking production line production data that exceeds the threshold as fluctuation state data for subsequent anomaly analysis or production optimization.

[0110] In one embodiment, fluctuation data can be analyzed in conjunction with abnormal data to assist in production line monitoring, trend prediction, and intelligent scheduling, thereby improving production stability and efficiency.

[0111] S1306. The production data of the production line is displayed using a target visualization method, and the fluctuation status data is highlighted in the display interface.

[0112] For example, production line data is displayed using a target visualization approach. This production line data refers to the comprehensive production information obtained after processing production line status data through a parameter processing model. The target visualization approach refers to charts, dashboards, or dynamic interfaces used to intuitively present the production line process, equipment operating status, and product quality indicators, helping operators quickly understand the production status. Simultaneously, fluctuation data is highlighted in the display interface. This fluctuation data refers to the portion of the production line data where the fluctuation exceeds a preset threshold, alerting operators to abnormal fluctuations or potential risks during the production process.

[0113] In one embodiment, production line production data can be displayed by presenting various production parameters, indicator trends, equipment status, and production performance through a graphical interface, and using color, highlighting, or animation to identify fluctuating data in the charts.

[0114] In one embodiment, highlighting fluctuation status data can be achieved by applying different color codes, flashing cues, or graphic markers to the fluctuation status data, making it easily identifiable within the overall production data display and aiding in rapid decision-making and intervention.

[0115] In one embodiment, interactive viewing, filtering, or grouping functions can be provided based on different types of fluctuation status data, so that operators can analyze the source and potential impact of abnormal fluctuations in a targeted manner.

[0116] Optionally, Figure 6 A flowchart of a sensor acquisition frequency adjustment method provided in an embodiment of this application is given. (Reference) Figure 6 The specific methods for adjusting the sensor's acquisition frequency include:

[0117] S131. Obtain historical production data and periodic production data within a preset time window.

[0118] For example, historical production data and periodic production data within a preset time window are acquired. Historical production data refers to the set of production line production data recorded in previous collection cycles, which is used to reflect long-term production trends and equipment operation status. Periodic production data refers to the production line production data obtained in each collection cycle within the preset time window, which is used to analyze recent production fluctuations and trends.

[0119] In one embodiment, historical production data can be obtained by extracting production line data for the required period from historical records stored on the edge gateway or cloud platform, based on timestamps or collection period indexes.

[0120] In one embodiment, the method for obtaining periodic production data can be: continuously collecting production line data within a preset time window according to a fixed collection cycle, and forming a periodic data set for subsequent correlation calculation and anomaly analysis.

[0121] In one embodiment, the acquired historical and periodic production data can be used for applications such as production trend analysis, anomaly detection, fluctuation identification, and optimized scheduling to improve production line efficiency and quality control capabilities.

[0122] S132. Calculate the periodic anomaly index based on the historical average of the historical production data and the periodic average of the periodic production data.

[0123] For example, a periodic anomaly index is calculated based on the historical average of historical production data and the periodic average of periodic production data. Historical production data refers to the set of production line production data recorded in each previous collection period, and the historical average refers to the statistical average of various production parameters in the historical production data, used to characterize long-term production levels and equipment status. Periodic production data refers to the set of production line production data obtained in each collection period within a preset time window, and the periodic average refers to the statistical average of various production parameters in the periodic production data, used to characterize recent production status. The periodic anomaly index refers to an index that reflects the degree of production anomaly or deviation trend obtained by comparing the historical average with the periodic average, used to help identify potential anomalies.

[0124] In one embodiment, the method for calculating the cycle anomaly index can be: calculating the difference or ratio between the cycle average and the historical average for each production parameter, and combining them to form the cycle anomaly index, which is used to quantify the degree of production deviation.

[0125] In one embodiment, the cycle anomaly index can be used to determine whether there are abnormal fluctuations, abnormal equipment performance, or process deviations in the current production cycle, thereby providing data support for subsequent anomaly analysis, risk assessment, and optimization decisions.

[0126] In one embodiment, weights can be set according to different types of production parameters, and the differences of each parameter can be weighted and calculated to obtain more accurate periodic anomaly indicators, thereby improving the sensitivity and reliability of anomaly detection.

[0127] S133. Calculate and adjust the acquisition frequency according to the periodic anomaly index, and control the sensor to acquire data from the production line equipment at the adjusted acquisition frequency.

[0128] For example, the acquisition frequency is adjusted based on the periodic anomaly index. The periodic anomaly index is a quantitative indicator reflecting production anomalies or deviations, obtained by comparing the historical average of historical production data with the periodic average of periodic production data. It is used to assess the stability or degree of anomaly in the production line's status. The acquisition frequency refers to the time interval at which sensors collect data from production line equipment, used to control the timeliness and accuracy of data collection. Subsequently, the sensors are controlled to collect production line equipment data at an adjusted acquisition frequency. The sensors are hardware modules installed on the production line equipment to collect equipment operating parameters, production indicators, or status information. Adjusting the acquisition frequency can increase data acquisition density when abnormal fluctuations are high and decrease the acquisition frequency when production is stable, thereby optimizing data storage and processing resources.

[0129] In one embodiment, the sampling frequency can be calculated by adjusting the sensor sampling interval proportionally based on the comparison between the periodic anomaly index and a preset threshold, so that the sampling frequency automatically increases or decreases with the degree of anomaly.

[0130] In one embodiment, the method of controlling sensor acquisition can be: sending instructions to the sensor module through an edge gateway or controller to adjust the acquisition interval in real time, thereby realizing a dynamic data acquisition strategy and improving the sensitivity and accuracy of production line status monitoring.

[0131] In one embodiment, the adjusted acquisition frequency can be linked with production line status data analysis, anomaly detection, and fluctuation monitoring to support intelligent production management and rapid response to abnormal events.

[0132] Optionally, the step of adjusting the sampling frequency based on the periodic anomaly index includes:

[0133] Obtain standard anomaly indicators, calculate the deviation ratio between the periodic anomaly indicators and the standard anomaly indicators, and determine the adjustment of the sampling frequency based on the preset sampling frequency and the deviation ratio.

[0134] For example, a standard anomaly index is acquired, where the standard anomaly index refers to a pre-set reference anomaly level relative to production line parameters or equipment status, used as a benchmark to determine whether anomalies exist in the current production cycle. Subsequently, a deviation ratio is calculated based on the cycle anomaly index and the standard anomaly index. The cycle anomaly index is a quantitative indicator reflecting the degree of production deviation, obtained by comparing historical averages with cycle averages. The deviation ratio is the ratio of the cycle anomaly index to the standard anomaly index, used to characterize the degree of deviation of the current production status from the expected standard. The acquisition frequency is adjusted based on a preset acquisition frequency and deviation ratio. The acquisition frequency refers to the time interval at which sensors acquire data from production line equipment. Adjusting the acquisition frequency involves dynamically increasing or decreasing the sensor acquisition density according to the deviation ratio to improve data acquisition accuracy when anomaly fluctuations are significant, reduce the acquisition load when production is stable, and optimize data processing and storage resources.

[0135] In one embodiment, the method for determining the adjustment of the acquisition frequency can be: mapping the deviation ratio to a preset threshold, and shortening or extending the sensor acquisition interval proportionally according to the mapping result to achieve dynamic acquisition control.

[0136] In one embodiment, commands are sent to the sensor module via an edge gateway or controller to adjust the acquisition frequency in real time, thereby linking the production line data acquisition strategy with production status fluctuations and improving monitoring sensitivity and anomaly response capabilities.

[0137] Optionally, Figure 7 A system architecture diagram of a production line data visualization method provided in an embodiment of this application is given. (Reference) Figure 7 The system architecture specifically includes: production line equipment 41, edge gateway 42, SCADA system 43, and third-party platform 44.

[0138] For example, production line equipment includes sensors, smart meters, PLCs, and other auxiliary equipment, providing basic data for the production line to reflect production status, such as output, temperature, and humidity. The edge gateway collects data from the production line equipment via OPCUA, Modbus, and mainstream PLC protocols such as Siemens, AB, and Beckhoff. It preprocesses and temporarily caches the collected data using pre-built JavaScript code, and uploads the processed data to the SCADA system via the OPC UA protocol. The SCADA system receives the data from the edge gateway, performs advanced processing and analysis, and provides various processing and display methods. The SCADA system has built-in data storage, data visualization, remote monitoring, and data forwarding modules. The data storage module stores the analyzed data in a MySQL database for historical data retrieval and analysis; the data visualization module designs production line dashboards and displays them on a local monitor; the remote monitoring module publishes the visualization dashboards to a web server, accessible to users via computers, tablets, or mobile phones; and the data forwarding module transmits data to internal enterprise systems such as MES and ERP via protocols such as MQTT, TCP, and UDP, enabling interaction and integration. Third-party platforms include MySQL databases, local displays, web browsers, MES, ERP, etc., which interact with various modules of the SCADA system to achieve data storage, visualization, remote monitoring, and data integration.

[0139] In one embodiment, industrial field devices establish a physical connection with an edge gateway and configure a communication network. The edge gateway communicates with production line devices via handshake, acquiring data through polling or batch reading. The data is preprocessed and temporarily cached using pre-built JavaScript code on the edge gateway. The edge gateway uploads the processed data to the SCADA system via the OPC UA protocol. The SCADA system's built-in data analysis module performs advanced processing on the received data. The analyzed data is written to a MySQL database through a data storage module for historical data management. A visualization module designs advanced production line dashboards and displays the production line status on a local monitor. A remote monitoring module publishes the dashboards to a web server for remote access. A data forwarding module transmits the processed information to third-party platforms such as MES and ERP via MQTT, TCP, and UDP protocols, enabling system interaction and integration. The industrial control computer periodically cleans up historical data in the database using pre-built JavaScript code to release storage resources and ensure long-term stable system operation.

[0140] Based on the above embodiments, Figure 8 This is a structural block diagram of a production line data visualization device provided in an embodiment of this application. (Reference) Figure 8 The production line data visualization device provided in this embodiment specifically includes: acquisition module 21, edge module 22, and visualization module 23.

[0141] The acquisition module 21 is configured to acquire production line equipment data using sensors installed on the production line equipment and transmit the production line equipment data to an edge gateway; the edge module 22 is configured to control the edge gateway to process the production line equipment data to obtain production line status data and transmit the production line status data to a cloud platform; the visualization module 23 is configured to drive the cloud platform to determine production line production data based on the production line status data, extract production data features from the production line production data, match the production data features with a target visualization method, and display the production line production data using the target visualization method.

[0142] Based on the above embodiments, the acquisition module 21 includes a candidate gateway unit configured to determine a number of candidate gateways from a preset gateway list; a candidate feature unit configured to acquire network data, processing speed, and queue cache corresponding to each candidate gateway; a candidate score unit configured to acquire network performance score, processing performance score, and queue cache score of the candidate gateway based on the network data, processing speed, and queue cache, respectively; and a gateway filtering unit configured to filter edge gateways from the candidate gateways according to the network performance score, processing performance score, and queue cache score, and transmit the production line equipment data to the edge gateways.

[0143] Based on the above embodiments, the gateway filtering unit includes: a performance weighting subunit, configured to acquire the data type of the production line equipment data, and determine the network performance weight, processing performance weight, and queue cache weight corresponding to the network performance score, processing performance score, and queue cache score respectively based on the data type; and a gateway determination subunit, configured to calculate the gateway score of the candidate gateway based on the network performance score, the processing performance score, and the queue cache score and their corresponding network performance weight, processing performance weight, and queue cache weight, and determine the candidate gateway with the highest gateway score as the edge gateway.

[0144] Based on the above embodiments, the visualization module 23 includes: an abnormal data unit, configured to determine abnormal state data based on the production line status data and preset standard status data; a processing model unit, configured to match the corresponding abnormal type according to the abnormal state data and determine the corresponding parameter processing model based on the abnormal type; and a production data unit, configured to input the production line status data into the parameter processing model to obtain production line production data.

[0145] Based on the above embodiments, the visualization module 23 further includes: an adjacent data unit, configured to acquire adjacent production data from the previous collection cycle of the production line production data; a fluctuation data unit, configured to calculate the fluctuation amplitude between the production line production data and the adjacent production data, and determine the production line production data with a fluctuation amplitude greater than a preset fluctuation amplitude threshold as fluctuation state data; and a highlighting unit, configured to display the production line production data in a target visualization manner and highlight the fluctuation state data in the display interface.

[0146] Based on the above embodiments, the production line data visualization device further includes: a periodic data module configured to acquire historical production data and periodic production data within a preset time window; an anomaly indicator module configured to calculate a periodic anomaly indicator based on the historical average value of the historical production data and the periodic average value of the periodic production data; and a frequency adjustment module configured to calculate and adjust the acquisition frequency according to the periodic anomaly indicator, and control the sensor to acquire data from the production line equipment at the adjusted acquisition frequency.

[0147] Based on the above embodiments, the frequency adjustment module includes: a frequency adjustment unit configured to acquire a standard abnormality index, calculate a deviation ratio based on the periodic abnormality index and the standard abnormality index, and determine an adjustment acquisition frequency based on a preset acquisition frequency and the deviation ratio.

[0148] The production line data visualization device provided in this application integrates key functions such as data acquisition, edge processing, and cloud visualization to construct an automated analysis architecture centered on production line status perception, production data feature extraction, and visualization. This device is composed of functional units such as an acquisition module, an edge module, and a visualization module, forming a closed-loop control chain from production line equipment data acquisition, status data processing, production data feature extraction to visualization, significantly improving the timeliness, accuracy, and display effect of production line data analysis.

[0149] The production line data visualization device provided in this application embodiment can be used to execute the production line data visualization method provided in the above embodiment, and has corresponding functions and beneficial effects.

[0150] Figure 9 This is a schematic diagram of the structure of a production line data visualization device provided in an embodiment of this application, with reference to... Figure 9The production line data visualization device includes a processor 31, a memory 32, a communication device 33, an input device 34, and an output device 35. The number of processors 31 and the number of memories 32 in the production line data visualization device can be one or more. The processor 31, memory 32, communication device 33, input device 34, and output device 35 of the production line data visualization device can be connected via a bus or other means.

[0151] The memory 32, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as program instructions / modules corresponding to the production line data visualization method in any embodiment of this application (e.g., acquisition module 21, edge module 22, and visualization module 23 in the production line data visualization device). The memory 32 may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a function; the data storage area may store data created based on the use of the device, etc. Furthermore, the memory 32 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the device via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0152] The communication device 33 is used for data transmission.

[0153] The processor 31 executes various functional applications and data processing of the device by running software programs, instructions and modules stored in the memory 32, thereby realizing the above-mentioned production line data visualization method.

[0154] Input device 34 can be used to receive input digital or character information, and to generate key signal inputs related to user settings and function control of the device. Output device 35 may include display devices such as a display screen.

[0155] The production line data visualization equipment provided above can be used to execute the production line data visualization method provided in the above embodiments, and has corresponding functions and beneficial effects.

[0156] This application embodiment also provides a storage medium containing computer-executable instructions. When executed by a computer processor, the computer-executable instructions are used to execute a production line data visualization method. The production line data visualization method includes: collecting production line equipment data using sensors installed on the production line equipment, and transmitting the production line equipment data to an edge gateway; controlling the edge gateway to process the production line equipment data to obtain production line status data, and transmitting the production line status data to a cloud platform; driving the cloud platform to determine production line production data based on the production line status data, extracting production data features from the production line production data, matching the production data features to a target visualization method, and displaying the production line production data using the target visualization method.

[0157] Storage medium – any type of memory device or storage apparatus. The term “storage medium” is intended to include: mounting media, such as CD-ROMs, floppy disks, or magnetic tape devices; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, etc.; non-volatile memory, such as flash memory, magnetic media (e.g., hard disks or optical storage); registers or other similar types of memory elements, etc. Storage medium may also include other types of memory or combinations thereof. Furthermore, storage medium may reside in a first computer system in which a program is executed, or it may reside in a different second computer system connected to the first computer system via a network (such as the Internet). The second computer system can provide program instructions to the first computer for execution. The term “storage medium” can include two or more storage media residing in different locations (e.g., in different computer systems connected via a network). Storage medium may store program instructions (e.g., specifically implemented as a computer program) executable by one or more processors.

[0158] Of course, the computer-executable instructions provided in the embodiments of this application are not limited to the production line data visualization method described above, but can also execute related operations in the production line data visualization method provided in any embodiment of this application.

[0159] The production line data visualization device, storage medium, and production line data visualization equipment provided in the above embodiments can execute the production line data visualization method provided in any embodiment of this application. For technical details not described in detail in the above embodiments, please refer to the production line data visualization method provided in any embodiment of this application.

[0160] The above description is merely a preferred embodiment and the technical principles employed in this application. This application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions that can be made by those skilled in the art will not depart from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of this application. The scope of this application is determined by the scope of the claims.

Claims

1. A method of production line data visualization, the method comprising: The method comprises the following steps: Collecting production line equipment data by using sensors arranged on the production line equipment, and transmitting the production line equipment data to an edge gateway; Controlling the edge gateway to process production line state data based on the production line equipment data, and transmitting the production line state data to a cloud platform; Driving the cloud platform to determine production line production data based on the production line state data, extract production data features of the production line production data, match a target visualization mode by using the production data features, and display the production line production data by using the target visualization mode.

2. The production line data visualization method of claim 1, wherein, The step of transmitting the production line equipment data to the edge gateway comprises the following steps: Determining a plurality of candidate gateways from a preset gateway list, and obtaining network data, processing speed and queue cache of each candidate gateway; Based on the network data, the processing speed and the queue cache, the network performance score, the processing performance score and the queue cache score of each candidate gateway are obtained respectively; According to the network performance score, the processing performance score and the queue cache score, the edge gateway is screened from the candidate gateways, and the production line equipment data is transmitted to the edge gateway.

3. The production line data visualization method of claim 2, wherein, The step of screening the edge gateway from the candidate gateways according to the network performance score, the processing performance score and the queue cache score comprises the following steps: Obtaining the data type of the production line equipment data, and determining the network performance weight, the processing performance weight and the queue cache weight corresponding to the network performance score, the processing performance score and the queue cache score based on the data type; According to the network performance score, the processing performance score and the queue cache score and the corresponding network performance weight, processing performance weight and queue cache weight, the gateway score of each candidate gateway is calculated, and the candidate gateway with the highest gateway score is determined as the edge gateway.

4. The production line data visualization method of claim 1, wherein, The step of driving the cloud platform to determine the production line production data based on the production line state data comprises the following steps: Determining abnormal state data based on the production line state data and preset standard state data; Matching the corresponding abnormal type according to the abnormal state data, and determining the corresponding parameter processing model based on the abnormal type; Inputting the production line state data into the parameter processing model to obtain the production line production data.

5. The production line data visualization method of claim 1, wherein, The step of displaying the production line production data by using the target visualization mode comprises the following steps: Obtaining adjacent production data of a previous collection period of the production line production data; Calculating the fluctuation amplitude of the production line production data and the adjacent production data, and determining the production line production data with a fluctuation amplitude greater than a preset fluctuation amplitude threshold as fluctuation state data; Displaying the production line production data by using the target visualization mode, and highlighting the fluctuation state data in the display interface.

6. The production line data visualization method according to any one of claims 1-5, characterized in that, After the step of displaying the production line production data by using the target visualization mode, the following steps are further included: Obtaining historical production data and periodic production data within a preset time window; Calculating a periodic abnormal index based on the historical average value of the historical production data and the periodic average value of the periodic production data; According to the periodic abnormal index, the adjustment collection frequency is calculated, and the sensor is controlled to collect the production line equipment data at the adjustment collection frequency.

7. The production line data visualization method of claim 6, wherein, The adjustment collection frequency is calculated according to the periodic abnormal index, comprising: Obtaining a standard abnormal index, calculating a deviation ratio according to the periodic abnormal index and the standard abnormal index, and determining an adjustment collection frequency based on a preset collection frequency and the deviation ratio.

8. A production line data visualization apparatus, characterized by, Comprising: A collection module configured to collect production line equipment data using a sensor arranged on a production line equipment, and transmit the production line equipment data to an edge gateway; An edge module configured to control the edge gateway to obtain production line state data based on processing of the production line equipment data, and transmit the production line state data to a cloud platform; A visualization module configured to drive the cloud platform to determine production line production data based on the production line state data, extract production data features of the production line production data, match a target visualization mode using the production data features, and display the production line production data using the target visualization mode.

9. A production line data visualization device, characterized by, Comprising: One or more processors; A memory storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the production line data visualization method according to any one of claims 1-7.

10. A storage medium containing computer-executable instructions, wherein: The computer executable instructions, when executed by a computer processor, are used to perform the production line data visualization method according to any one of claims 1-7.

Images