Concurrent analysis driven production line monitoring system

Abstract

The invention provides a concurrency analysis driven production line monitoring system, and relates to the technical field of production line monitoring, and the system comprises the steps: interacting the equipment operation and control characteristics of a target machine tool production line; performing hierarchical analysis to determine multiple control logics; a penalty function is introduced, a micro-processing block is determined, node packaging is carried out, and a machine tool monitoring module is constructed; a programmable logic device is introduced to realize automatic configuration and resource management; continuous monitoring: pre-processing data at the edge of the equipment, returning the pre-processed data to a monitoring module, performing concurrent analysis based on pre-monitoring task nodes, and integrating production line monitoring single columns; and identifying an abnormal sequence, and carrying out visual early warning on a human-computer interaction interface. According to the method and the device, the technical problems that the change on the production line cannot be responded in time and the abnormal event is difficult to accurately recognize and early warn due to insufficient real-time performance and single control logic can be solved, the complex and changeable machine tool production line is efficiently and accurately dynamically monitored, and the working efficiency is improved. And the recognition and early warning accuracy of the abnormal event is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of production line monitoring, and in particular to a concurrent analysis driven production line monitoring system. BACKGROUND

[0002] With the rapid development of manufacturing industry and the intensification of market competition, the efficient and stable operation of machine tool production lines is of great significance to ensure product quality, improve production efficiency and reduce production cost. However, with the continuous expansion and increasing complexity of machine tool production lines, traditional machine tool production line monitoring methods have been difficult to meet the needs of modern manufacturing industry. Traditional machine tool production line monitoring methods often lack real-time performance and have single control logic, which makes it difficult to respond to changes on the production line in a timely manner and adapt to complex and variable production line environments, resulting in inaccurate identification and early warning of abnormal events, which poses a potential risk to production safety and quality stability. SUMMARY

[0003] The purpose of the present application is to provide a concurrent analysis driven production line monitoring system to solve the technical problem of being unable to respond to changes on the production line in a timely manner and being difficult to accurately identify and warn abnormal events due to lack of real-time performance and single control logic.

[0004] In view of the above problems, the present application provides a concurrent analysis driven production line monitoring system.

[0005] The present application provides a concurrent analysis driven production line monitoring system, which comprises: a production line interaction unit for interacting with the equipment operation and control characteristics of the target machine tool production line, wherein the equipment operation and control characteristics are marked with machine tool codes; a hierarchical control analysis unit for performing hierarchical control analysis based on the equipment operation and control characteristics to determine multiple control logics, wherein the multiple control logics interact and are associated with machine tool codes; a node packaging unit for introducing a penalty function based on the multiple control logics, performing distributed deployment and supervised training, determining micro-processing blocks and packaging nodes, and determining machine tool monitoring modules; an introduction logic unit for introducing a programmable logic device, which is used for automatic configuration and resource configuration management of the machine tool monitoring module, and the programmable logic device can be updated; a concurrent analysis management unit for continuously monitoring the production line, preprocessing multi-source production line data at the edge of the equipment, returning to the machine tool monitoring module, and performing node concurrent analysis management based on pre-monitoring tasks based on the programmable logic device, and integrating to determine a production line monitoring single column; an abnormal warning unit for identifying the production line monitoring single column and determining an abnormal monitoring sequence, and performing visualization and abnormal warning based on a human-computer interaction interface.

[0006] The technical solution provided in the present application has at least the following technical effects or advantages: The aforementioned concurrent analysis-driven production line monitoring system analyzes the operational characteristics of machine tool production lines to understand equipment operating patterns and demands, and then performs hierarchical control analysis to determine multiple control logics. These control logics ensure appropriate regulation of the production line under different operating conditions. Subsequently, a penalty function is introduced to optimize the control strategy. Through distributed deployment and supervised training, microprocessor blocks are identified and node encapsulated to form independent machine tool monitoring modules. These modules are responsible for monitoring tasks in their respective areas and can respond quickly to problems. Next, a programmable logic device (PLD) is introduced. This PLD can automatically configure and manage resource allocation for the machine tool monitoring modules as needed, and it can also be updated to adapt to production line changes or new monitoring requirements. During production line operation, continuous monitoring is performed, and multi-source production line data is preprocessed at the equipment edge. This preprocessed data is then fed back to the machine tool monitoring modules for further analysis and judgment. Finally, based on the PLD, multiple monitoring tasks are processed concurrently and integrated to determine a single production line monitoring column, providing a comprehensive view of the production line monitoring. Once an abnormal monitoring sequence is identified in the production line monitoring column, an anomaly warning is immediately issued. These warnings are visualized through a human-machine interface. This system achieves comprehensive, efficient, and intelligent monitoring of production line equipment, not only responding to changes in the production line in real time but also accurately identifying and issuing warnings for anomalies, thereby improving production line stability and production efficiency.

[0007] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0009] Figure 1 This is a schematic diagram of the structure of the concurrent analysis-driven production line monitoring system of this application.

[0010] Figure 2 This is a flowchart illustrating the hierarchical control analysis process of the concurrent analysis-driven production line monitoring system described in this application.

[0011] Explanation of reference signs: line interaction unit 1, hierarchical control analysis unit 2, node packaging unit 3, introduction logic unit 4, concurrent analysis management unit 5, and abnormality early warning unit 6. DETAILED DESCRIPTION

[0012] The present application provides a concurrent analysis driven production line monitoring system, which solves the technical problem that changes on the production line cannot be responded in time and abnormal events cannot be accurately identified and warned due to insufficient real-time performance and single control logic, and achieves the technical effect of efficiently and accurately dynamically monitoring complex and changeable machine tool production lines and improving the accuracy of identification and warning of abnormal events.

[0013] The technical solutions in the present application will be described clearly and completely below with reference to the accompanying drawings. Obviously, the described embodiments are only some of the embodiments of the present application, not all embodiments of the present application. It should be understood that the present application is not limited by the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application. In addition, it should be noted that, for convenience of description, only parts related to the present application are shown in the drawings, not all.

[0014] Embodiment, please refer to the accompanying Figure 1 The present application provides a concurrent analysis driven production line monitoring system, which specifically includes the following modules: The line interaction unit 1 is used to interact with the equipment operation and control features of the target machine tool production line, wherein the equipment operation and control features are identified by machine tool codes.

[0015] In the embodiments of the present application, the system terminal interacts with the target machine tool production line to understand and identify the operation and control features of each equipment. The operation and control features refer to various states, parameters and performance characteristics exhibited by the equipment during operation. These features have a machine tool code, which corresponds to the machine tool equipment one by one, and is used to distinguish the equipment operation and control features of different machine tool equipment, providing basic data for subsequent control and monitoring.

[0016] The hierarchical control analysis unit 2 is used to perform hierarchical control analysis based on the equipment operation and control features, and determine multiple control logics, wherein the multiple control logics interact and have machine tool code association.

[0017] In one embodiment, after obtaining the operation and control characteristics of the machine tool equipment, the system terminal performs hierarchical control analysis. This process is to decompose complex control requirements into multiple levels based on different dimensions and different working methods according to the characteristics of the equipment and the working requirements, and to determine different control logics at each level. These multiple control logics are connected through inter-layer correlation and intra-layer correlation, which makes different control logics coordinate with each other according to the actual operation situation, ensuring the smooth operation of the entire production line. At the same time, these control logics are also associated with machine tool codes, ensuring that the system terminal can accurately control each machine tool equipment individually.

[0018] Further, as shown in Figure 2 The present application provides hierarchical control analysis and determination of multiple control logics, including: based on static dimensions and dynamic dimensions, determine a first logic layer, and combine the equipment operation and control characteristics to mine a one-layer logic multi-element set; based on independent control and cooperative control, determine a second logic layer, and combine the equipment operation and control characteristics to mine a two-layer logic multi-element set, wherein cooperation includes synchronous cooperation and sequential cooperation, and the number of logic layers is expandable; based on inter-layer correlation and intra-layer correlation, associate and distribute the one-layer logic multi-element set and the two-layer logic multi-element set to determine the multiple control logics.

[0019] Preferably, in constructing the control logic of the machine tool production line, the system terminal determines the first logic layer from both static and dynamic dimensions. The static dimension focuses on the fixed attributes and basic configurations of the equipment, while the dynamic dimension focuses on the running state and real-time data of the equipment. In determining the first logic layer, the system terminal first collects the basic attribute information of the machine tool equipment, such as model, specification, manufacturer, design parameters, etc. These information are inherent attributes of the equipment, which do not change with the change of the equipment running state. Then extract the static features related to operation and control from the collected equipment attributes. These features include physical properties, performance indicators, design limitations, etc. Subsequently, during the operation of the machine tool, real-time running state data such as temperature, pressure, speed, acceleration, current, voltage, etc. are collected. Then the collected real-time data are analyzed and processed to extract dynamic features related to operation and control. These features reflect the real-time state, change trend and potential problems of the equipment during operation. Then, the system terminal fuses the static features and dynamic features to determine the first logic layer. After determining the first logic layer, the system terminal determines the main problems that the first layer logic needs to solve according to the production line requirements and equipment operation and control features, such as basic operation control, safety protection, etc. Then, based on the logic requirement analysis, combined with the equipment operation and control features, the control logic rules of the first logic layer are formulated. These rules define how the equipment should respond to different inputs and conditions under the basic running state. Then, the system terminal combines and associates the logic rules to form a one-layer logic multi-element group. This one-layer logic multi-element group refers to a data structure unit used to represent the internal relationship and response mechanism of the control logic layer. Each multi-element group is composed of a feature vector, a logic rule, a trigger condition, a response action, and a feedback variable. The feature vector is used to describe the static and dynamic attribute parameters of the equipment; the logic rule is used to define the judgment relationship of the control decision logic; the trigger condition is used to determine under what running state the corresponding logic is executed; the response action refers to the specific control instruction executed by the system; the feedback variable is used to record the state information after execution to realize closed-loop control. The one-layer logic multi-element group can be stored in table structure or key-value mapping structure, and can be associated in the system in the form of graph nodes or matrices, supporting calculation and reasoning, used to achieve specific control objectives, representing the preliminary control strategy based on the basic attributes and running state of the equipment.

[0020] After obtaining the first logical layer, the system terminal proceeds to determine the second logical layer, which focuses on independent control and collaborative control. Independent control optimizes individual equipment or process steps, while collaborative control considers the interactions between multiple equipment or process steps. Within collaborative control, the system terminal differentiates between synchronous collaboration, where multiple equipment or steps work simultaneously, and sequential collaboration, where equipment or steps work in a certain order. In determining the second logical layer, the system terminal analyzes which equipment or steps require independent control and which require collaborative control based on the results of the first logical layer. For example, when a machine tool undergoes emergency shutdown due to safety reasons, independent control is used to ensure a quick response and reduce potential losses. Subsequently, the system terminal determines the scope, relationship, and interaction method of independent control and collaborative control based on the analysis results, thereby determining the second logical layer. Then, from the operational control characteristics of the equipment, the system terminal extracts key operational control characteristics related to the second logical layer. These characteristics involve the performance, state, response speed, and other aspects of the equipment. Based on the extracted key operational control characteristics, the system terminal formulates logical rules for independent control and collaborative control. For collaborative control, the system terminal further considers the rules for synchronous collaboration and sequential collaboration. Then, the system terminal combines and associates the formulated logical rules to form a two-layer logical tuple, which is similar to the one-layer logical tuple. Each two-layer logical tuple also contains a set of related logical rules, conditions, and other elements, which are used to achieve specific control objectives. These tuples are more complex and take into account the interdependence and collaboration between equipment. When designing the second logical layer, the system terminal also reserves extension interfaces to add new logical layers as needed.

[0021] After determining the first and second logical layers, the system terminal analyzes the logical coherence between the one-layer logical tuples and the two-layer logical tuples. This includes determining the dependency relationship, influencing factors, and the direction of information flow between them, and evaluating the functional complementarity of the two logical layers. For example, one-layer logical tuples may focus on basic control and stability, while two-layer logical tuples may focus more on optimization and coordination. Subsequently, within each logical layer, the logical relationship between tuples is analyzed, which includes inter-layer correlation analysis and intra-layer correlation analysis between tuples. For inter-layer correlation analysis, the output variables of one-layer logical tuples are matched with the input parameters of two-layer logical tuples by establishing a parameter mapping matrix, and the Pearson correlation coefficient is calculated. If the Pearson correlation coefficient exceeds a preset threshold, such as 0.7, it is determined that there is strong inter-layer correlation. For intra-layer correlation analysis, the shared feature parameters, control objectives, and constraint conditions between each tuple are quantified using feature weight analysis and logical coupling degree calculation methods, for example, by calculating the feature overlap degree or rule co-occurrence frequency between tuples, an intra-layer correlation matrix is obtained to distinguish independent tuples from strongly coupled tuples. Based on the analysis of inter-layer correlation and intra-layer correlation, the association distribution operation is performed, that is, using a graph model or tensor distribution algorithm, each logical tuple is taken as a node, the inter-layer or intra-layer correlation is taken as a weighted connection edge, and the distribution position and connection strength of the logical node are determined by minimizing the global coupling error or maximizing the information flow efficiency, thereby forming an association network between one-layer and two-layer. The intra-layer relationship in this association network reflects the coupling structure of local control logic, and the inter-layer relationship reflects the logical transmission path between different levels, which can clearly reflect the information flow and control relationship between the two logical layers. Then, the system terminal integrates the inter-layer association network and the intra-layer logical relationship to form a complete multi-control logic. This multi-control logic can cover all aspects from basic control to collaborative optimization, and can be dynamically adjusted according to the real-time state of the equipment and the demand of the production line to achieve efficient and stable production line operation.

[0022] The node packaging unit 3 is used to introduce a penalty function based on the multi-control logic, perform distributed deployment and supervised training, determine micro-processing blocks and perform node packaging, and determine the machine tool monitoring module.

[0023] In one embodiment, in order to ensure the stability of monitoring, the system terminal introduces a penalty function. The penalty function is a mechanism for measuring the deviation of system performance, which is constructed based on the positioning of the interpretation disturbance points of multiple control logics. When the system terminal deviates during actual operation, the penalty function will give corresponding punishment to guide the system terminal to correct the deviation of data analysis. Subsequently, the system terminal distributes the correlation distribution of multiple control logics in a distributed manner. Distributed deployment means that the control logics of the system terminal are dispersed to different physical locations to achieve better load balancing and scalability. By distributing the multiple control logics, the system terminal determines the micro-processing block distribution, which refers to the smallest computing unit divided for data processing tasks, that is, the independently executable computing logic node or lightweight task container, which can be an embedded processing core, a virtual computing thread or a lightweight task instance on a programmable logic unit. Then, based on the distributed deployment, the system terminal uses sample data to supervise the training of the micro-processing block distribution, so that it can learn and adapt to various working conditions and scenarios. Through continuous iteration and optimization, its monitoring and control capabilities for machine tool equipment can be gradually improved. As the training progresses, the system terminal can determine the micro-processing block that meets the convergence condition and perform node encapsulation. Through node encapsulation, the complexity and dependency of the system terminal can be reduced, and the maintainability and scalability of the system terminal can be improved. Then, the system terminal connects these encapsulated nodes to determine the machine tool monitoring module. The machine tool monitoring module is the core part of the entire system terminal, responsible for receiving data and information from various nodes and performing comprehensive analysis and processing. Based on the guidance of multiple control logics and penalty functions, the machine tool monitoring module can monitor the running state of the machine tool equipment in real time, predict potential problems, to ensure the stable operation and efficient production of the machine tool equipment.

[0024] Further, the application provides the introduction of a penalty function for data interpretation main line deviation return, comprising: traversing the multiple control logics to determine a data interpretation main line, the data interpretation main line corresponding to the multiple control logics one by one; based on the data interpretation main line, locating interpretation disturbance points based on multi-source production line data; for the interpretation disturbance points, constructing and triggering the application of the penalty function.

[0025] Preferably, in order to ensure the accuracy of data interpretation and avoid the partial data bias guide, the system terminal performs logical analysis to assess the monitoring state. In this process, the system terminal first traverses the multiple control logic to identify the key nodes that have a direct impact on the system state, behavior or performance. These nodes are turning points or decision points in the logic chain. Then, analyze the data sources and data types relied on by each key control node. These data are necessary for executing control logic and are the basis for data interpretation. After that, according to the control logic and data dependency, the data interpretation path from the data source to the control output is constructed. These paths describe how data flows in the system terminal and how it is processed, analyzed and interpreted in different control nodes. Then, among all the constructed data interpretation paths, the main data interpretation path, i.e. the data interpretation main line, is identified, which refers to the dominant data flow path from the original multi-source production line data input to the result output, that is, the core transmission and operation route of data among multiple control layers and algorithms. They correspond to multiple control logic one by one, ensuring that data can be accurately interpreted according to the predetermined logic path. Then, based on these determined data interpretation main lines, the system terminal locates the interpretation interference points that may occur in the multi-source production line data interpretation process. These interpretation interference points may be caused by the diversity of data sources, the instability of data quality or logic conflicts, etc. They may cause data interpretation to deviate from the correct main line and present a turning effect, i.e. turning point, which can be detected and identified by residual analysis, such as the deviation between actual output and predicted output exceeding the set threshold. In order to deal with these interpretation interference points, the system terminal will construct a penalty function and trigger management. The form of the penalty function can be customized according to specific circumstances, for example, simple weight adjustment, loss function increase, or more complex nonlinear mapping, etc. Its goal is to correct the deviation of data interpretation when it deviates from the main line, that is, when the data interpretation main line deviates, the weight of the main line node is adjusted by the feedback mechanism of the penalty function, so as to pull the calculation result of data flow back to the main line track. This bias correction mechanism can ensure the accuracy and consistency of data interpretation, avoid incorrect results caused by partial data bias guide, and ensure the accuracy and reliability of data analysis.

[0026] Further, the application provides the determination of machine tool monitoring module, comprising: Based on the associated distribution of the multiple control logic, distributed deployment is performed to determine the micro-processing block distribution; industrial big data retrieval is performed to determine sample data and segmentation, mapping to the micro-processing block distribution for supervised training and cross-validation to determine the micro-processing block that meets the convergence condition; encapsulate the single micro-processing block as a node, and establish a fast interaction channel based on the associated distribution to generate the machine tool monitoring module.

[0027] Preferably, the system terminal divides the control logics into different micro-processing blocks according to the association distribution among the multiple control logics, i.e., which control logics are dependent on each other and which can operate independently, to realize distributed deployment. Distributed deployment helps to improve the scalability, flexibility and fault tolerance of the system. Subsequently, using industrial big data retrieval technology, sample data related to machine tool monitoring is extracted from massive data. These sample data will be divided into multiple parts for subsequent training and verification of micro-processing block distribution. Then, the system terminal maps the segmented sample data into a determined micro-processing block distribution and performs supervised training on each micro-processing block. Specifically, taking a random micro-processing block as an example, the system terminal sets appropriate hyperparameters for this micro-processing block, such as learning rate, iteration number, batch size, etc. Subsequently, the mapped sample data is divided into k equal subsets, where k is determined by considering the stability, accuracy and computational cost of evaluation, and common k values are 5, 10, etc. Then, the system terminal randomly selects one of the k subsets as the validation set and the rest as the training set, and uses the training set to train the corresponding micro-processing block. Each micro-processing block learns the mapping relationship from input data to output results, and through continuous iteration and optimization of the parameters of the micro-processing block, the prediction results of the micro-processing block gradually approach the true results. Then, the validation set is used to verify the trained micro-processing block, and the accuracy is calculated. Repeat the above steps until each subset has been used as a validation set. After training is completed, the system terminal extracts the accuracy of k times of training and compares them, and selects the training result with the highest accuracy and compares it with the preset convergence condition. If the convergence condition is met, the system terminal takes this training result as the final micro-processing block. If the convergence condition is not met, the system terminal re-divides the subsets and repeats the above training and verification process until the convergence condition is met.

[0028] After the micro-processing blocks are trained, the system terminal encapsulates each micro-processing block that meets the convergence condition as an independent node for easy management and integration. At the same time, based on the association distribution of multiple control logics, the dependency relationship and communication requirements between micro-processing blocks are determined. Then, according to the actual requirements, a suitable communication protocol is selected to establish a fast interaction channel. For example, if the actual requirement is to ensure real-time performance, the system terminal selects UDP to establish a fast interaction channel because UDP is a connectionless protocol that does not establish a connection before transmitting data, thus having lower latency. After that, the system terminal integrates the encapsulated micro-processing blocks and the fast interaction channel to generate a machine tool monitoring module. This module can monitor the running state of the machine tool in real time and predict potential failures. Through distributed deployment and the collaborative work of micro-processing blocks, the machine tool monitoring module can realize efficient and accurate data processing and analysis, improving the reliability and production efficiency of the machine tool.

[0029] Further, the application provides the convergence condition, including: The verification sample of the micro-processing block mapping satisfies the upper limit of the verification accuracy, and the verification sample of any block of the micro-processing block non-mapping satisfies the lower limit of the verification accuracy as the convergence condition.

[0030] Optionally, in order to more accurately evaluate the trained micro-processing block, the system terminal pre-sets a convergence condition, the upper limit of the convergence condition is determined according to the verification accuracy of the mapping verification sample, and the lower limit is determined according to the verification accuracy of the non-mapping verification sample. The setting of the convergence condition can make the sample verification accuracy of the block large enough, and the sample verification accuracy of the non-block small enough, improve the pertinence of the block, and ensure the differentiation between the blocks. When the trained micro-processing block satisfies the convergence interval, it represents that the data processing and analysis in the block can accurately reflect the actual situation, thereby ensuring the effectiveness and accuracy of the block function.

[0031] The logic unit 4 is introduced for introducing a programmable logic device, the programmable logic device is used for automatic configuration and resource configuration management of the machine tool monitoring module, and the programmable logic device is updateable.

[0032] In one embodiment, the system terminal introduces the programmable logic device, performs corresponding configuration, and takes the configured programmable logic device as a management tool of the machine tool monitoring module, aiming to realize automatic configuration and resource configuration management oriented to monitoring dimensions and production line processing tasks. The programmable logic device has the characteristics of being updateable, and can efficiently and flexibly perform global overall planning and automatic control of the machine tool monitoring. Through this tool, the system terminal can more conveniently perform configuration update, resource allocation and performance optimization of the machine tool monitoring module to meet the needs of different production line processing tasks, and improve the automation level and efficiency of the entire production line.

[0033] Further, the application provides the introduction of the programmable logic device, including: Reading the monitoring standard of the target machine tool production line based on the work order production task; determining a logic flow based on the monitoring standard based on the architecture of the machine tool monitoring module, and setting a cycle control program, wherein the cycle is a module processing cycle of single-phase monitoring, and the time zone monitoring cycle of the work order product processing; and configuring the programmable logic device based on the cycle control program.

[0034] Preferably, in order to effectively monitor the work order production tasks of the target machine tool production line, the system terminal first reads the monitoring standards based on which these tasks are based. These standards include specific requirements in terms of production quality, efficiency, safety, etc. Subsequently, based on the existing architecture of the machine tool monitoring module, a logical flow is determined, which will follow the previously read monitoring standards and will be able to cover the entire monitoring process from data collection, processing to result output, response, etc. Then, in order to ensure the real-time and accuracy of the monitoring, the system terminal sets a cycle control program. Here, the cycle includes two aspects: one is the module processing cycle of single phase monitoring, which represents that each monitoring module will perform data collection and processing once every certain time, which is based on the frequency of data update and the complexity of processing; the other is the time zone monitoring cycle related to the work order product processing, which is based on the actual process and time requirements of product processing. With this cycle control program, the system terminal configures the programmable logic device. Through the configuration, the programmable logic device will be able to automatically monitor and manage the machine tool production line according to the predetermined logical flow and cycle control program, ensuring the smooth progress of the production tasks. This process combines monitoring standards with the architecture of the machine tool monitoring module, sets a cycle control program, and configures the programmable logic device to achieve automatic monitoring and management of the work order production tasks of the target machine tool production line.

[0035] The concurrent analysis management unit 5 is used for continuously monitoring the production line, preprocessing multi-source production line data at the edge of the equipment, returning to the machine tool monitoring module, and based on the programmable logic device, performing node concurrent analysis management based on pre-monitoring tasks, and integrating to determine the production line monitoring single column.

[0036] In one embodiment, in the process of continuously monitoring the production line, the system terminal preprocesses multi-source production line data at the edge of the equipment. That is, before the data is transmitted to the central machine tool monitoring module, the edge device will first perform preliminary processing and screening on the data from different sources to ensure the accuracy and effectiveness of the data. Then, the edge device transmits the processed data to the machine tool monitoring module through the set network communication protocol. Subsequently, based on the programmable logic device, the system terminal performs node concurrent analysis management based on pre-monitoring tasks, that is, the system terminal divides and activates the nodes of the multi-source production line data with the help of the programmable logic device, and performs multi-node concurrent processing and result combination, so as to quickly respond to various situations on the production line and determine the production line monitoring single column. The production line monitoring single column is a comprehensive display of the overall operation status of the production line, which contains real-time data and state information of each key monitoring node, so that the system terminal can understand the operation status of the production line and make corresponding decisions accordingly.

[0037] Further, the application provides that the machine tool monitoring module at the edge of the equipment and the back end interact based on a network communication protocol, including: The system terminal traverses the multi-source production line data, performs data isomorphism processing and multi-source feature fitting based on a preprocessing model, determines effective production line data, wherein the isomorphic data structure is any one of the multi-source data structures; the system terminal returns the effective production line data, performs node activation and concurrent analysis management based on the programmable logic device, and determines the production line monitoring single column; the system terminal identifies the production line monitoring single column, performs binary processing of the single column coefficient based on a mapping monitoring threshold, identifies inferior binary data and marks the same, and the monitoring threshold corresponds one-to-one to the production line monitoring single column.

[0038] Preferably, in the process of continuous monitoring of the production line, the system terminal traverses the multi-source production line data from different types of sensors, monitoring devices, etc. In order to make full use of these data and avoid data redundancy, the system terminal will perform isomorphism processing and multi-source feature fitting on these multi-source data based on a preprocessing model. This preprocessing model is customized according to the specific needs, data types and purposes of the production line, that is, the required preprocessing algorithms are integrated. Isomorphic processing means that different sources of data are converted into a unified data structure, which is to select one of these multi-source data structures as a reference to convert the rest of the data, ensuring the consistency and comparability of the data. Through multi-source feature fitting, the system terminal can integrate and optimize different source data for the same target, thereby screening out effective production line data. This process not only improves the efficiency of data transmission, but also ensures the accuracy and reliability of the data. Subsequently, the system terminal returns these effective production line data to the machine tool monitoring module. Here, based on the programmable logic device, the system terminal activates the nodes and performs concurrent analysis management of the data, processes multiple monitoring nodes at the same time, and responds and analyzes quickly according to the set logic rules. In this way, the system terminal can master the running status of the production line in real time and determine the production line monitoring single column, that is, the comprehensive display of each key monitoring point of the production line. Then, the maximum-minimum normalization processing is performed on each monitoring parameter in each production line monitoring single column, such as temperature, pressure, current, speed, etc., to eliminate the dimensional difference, and then the single column coefficient of each production line monitoring single column is obtained by weighted summation according to the preset weight. The higher the single column coefficient, the greater the running deviation of the monitoring single column. Once the single column coefficient is determined, the system terminal performs binary processing of the single column coefficient based on the mapping monitoring threshold, that is, the normal fluctuation interval is determined as the threshold baseline through statistical analysis, such as mean plus or minus one standard deviation, and then the calculated single column coefficient is compared with the corresponding threshold baseline. When the single column coefficient is within the threshold baseline, the logical value 1 is output, indicating a normal state, and when the single column coefficient exceeds the threshold range, the logical value 0 is output, indicating an abnormal state. In this way, the system terminal can quickly identify abnormal conditions on the production line and take appropriate measures to handle them, ensuring the stable operation of the production line.

[0039] Further, the application provides node activation and concurrent analysis management based on the programmable logic, including: Based on the pre-monitoring task, the effective production line data is segmented and activated for node, and multi-node concurrent processing and result combination are performed to determine the production line monitoring single column, wherein the concurrent processing includes multi-task concurrency and single-task multi-node concurrent processing; if it is multi-task concurrency, node processing domain overrun is determined based on task time limit; if it is overrun, the micro-processing block is temporarily re-allocated resources based on operator utilization.

[0040] Optionally, in the production line monitoring, after the system terminal obtains the production line data that has been preprocessed and determined to be effective, the next step is to process these data according to the pre-monitoring task. This process includes data segmentation, node activation, and multi-node concurrent processing. First, the system terminal segments these effective production line data according to the requirements of the pre-monitoring task, that is, allocates the data to different processing units or nodes. Then, activate these nodes so that these nodes can start processing their respective data. In order to improve processing efficiency, the system terminal adopts multi-node concurrent processing. This means that multiple nodes can process data at the same time, greatly speeding up the processing speed. This concurrent processing can be multi-task concurrency, that is, processing multiple different tasks at the same time; it can also be single-task multi-node concurrent processing, that is, a task is segmented into multiple sub-tasks and processed by different nodes at the same time. After each node completes data processing, the system terminal combines the processing results of these nodes to form a complete production line monitoring single column. This monitoring single column is a comprehensive reflection of the running state of the entire production line. In multi-task concurrent processing, since each task has its specific processing time limit, the system terminal monitors the processing progress of the nodes. If the processing time of a node exceeds its task time limit, that is, the processing domain is overrun, the system terminal temporarily reallocates resources based on the operator utilization. This operator utilization is the ratio of the number of operator calls in the task execution process of the monitoring node to the maximum number of supported calls, which is used to measure the real-time computing load of the node. Based on this operator utilization, the system terminal can temporarily allocate part of the resources of other relatively idle nodes to the overrun node. The allocation rules can be to preferentially select idle or lightly loaded nodes with a current operator utilization rate below a set threshold as resource providers; select the node with the lowest cost for collaborative sharing according to the data channel bandwidth and topology location between nodes; set an upper limit to the resource reallocation frequency, allowing only one resource reallocation within the same task cycle, etc., so as to help it complete the task as soon as possible and ensure the stability and processing efficiency of the entire system.

[0041] The abnormal early warning unit 6 is used to identify the production line monitoring single column and determine the abnormal monitoring sequence, and perform visualization and abnormal early warning based on the human-computer interaction interface.

[0042] In one embodiment, in line monitoring, after the effective line data is segmented, node activated and multi-node concurrent processed, one or more line monitoring single columns are obtained. These single columns are a specific reflection of the running state of the line and contain a large amount of data and information. Subsequently, the system terminal identifies possible abnormal monitoring sequences from these monitoring single columns and visualizes and gives an early warning through the human-computer interaction interface. In order to identify abnormal monitoring sequences, the system terminal compares each line monitoring single column with the standard line monitoring single column, identifies data points or data segments that do not conform to the normal operation mode, and judges whether there is an abnormality. Once an abnormal monitoring sequence is identified, the system terminal presents these abnormal information in a visualized way through the human-computer interaction interface. Visualization includes various forms such as charts and curves, aiming to intuitively show the running state and abnormal situation of the line. Through visualization, the overall situation of the line can be quickly understood, and potential problems can be discovered and handled in time. When the system terminal detects an abnormal monitoring sequence, it will also automatically trigger the early warning function and send warning information to the user through sound, light, email or SMS, etc. In this way, the user can know about the abnormal situation in the first time and take corresponding measures to handle it. Abnormal warning can help users discover and handle potential risks in time, ensuring the stable operation of the line.

[0043] In summary, the concurrent analysis driven production line monitoring system provided by the present application has the following technical effects: The present application collects the equipment operation and control characteristics of the target machine tool line, and determines multiple control logics based on these characteristics. Then, a penalty function is introduced to distribute and supervise the training of the multiple control logics, form micro-processing blocks and node encapsulation, and build machine tool monitoring modules. After that, programmable logic is introduced, which enables automatic configuration and management of machine tool monitoring modules to adapt to the changing needs of the line. Then, preprocess multi-source line data on the edge side of the equipment, and manage node concurrent analysis through programmable logic to integrate and determine line monitoring single columns. Finally, by identifying abnormal sequences in the monitoring single columns and visualizing and warning, users can discover and handle potential problems in time. These technical effects collectively solve the technical problems of being unable to respond to changes on the line in time, being difficult to accurately identify and warn abnormal events due to insufficient real-time performance and single control logic, achieve efficient and accurate dynamic monitoring of complex and variable machine tool lines, and improve the accuracy of identifying and warning abnormal events.

[0044] The foregoing description of the disclosed embodiments enables a person skilled in the art to make or use the application. Numerous modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other embodiments without the use of the inventive faculty. Therefore, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0045] It will be readily apparent to one skilled in the art that varying substitutions and modifications can be made to the application disclosed herein without departing from the scope and spirit of the application. Accordingly, it is intended that all such alterations and modifications be considered as within the scope of the application.

Claims

1. A concurrent analysis driven production line monitoring system, characterized in that, The system comprises: a production line interaction unit for interacting with equipment operation and control features of a target machine tool production line, wherein the equipment operation and control features are identified by machine tool codes; a hierarchical control analysis unit for hierarchical control analysis based on the equipment operation and control features to determine multiple control logics, wherein the multiple control logics interact and are associated with machine tool codes; a node packaging unit for introducing a penalty function based on the multiple control logics, conducting distributed deployment and supervised training, determining micro-processing blocks and packaging nodes, and determining machine tool monitoring modules; an introduction logic unit for introducing a programmable logic device, which is used for automatic configuration and resource configuration management of the machine tool monitoring module, and the programmable logic device is updatable; a concurrent analysis management unit for continuous production line monitoring, preprocessing multi-source production line data at the edge of the equipment, returning to the machine tool monitoring module, and based on the programmable logic device, conducting node concurrent analysis management based on pre-monitoring tasks, and integrating to determine production line monitoring single columns; an abnormal early warning unit for identifying the production line monitoring single column and determining an abnormal monitoring sequence, and conducting visualization and abnormal early warning based on a human-computer interaction interface.

2. The concurrent analytics-driven production line monitoring system of claim 1, wherein, The hierarchical control analysis determines multiple control logics, including: based on static and dynamic dimensions, a first logic layer is determined, and a one-layer logic multivariate group is mined in combination with the equipment operation and control features; based on independent control and collaborative control, a second logic layer is determined, and a two-layer logic multivariate group is mined in combination with the equipment operation and control features, wherein collaboration includes synchronous collaboration and sequential collaboration, and the number of logic layers is expandable; based on inter-layer correlation and intra-layer correlation, the one-layer logic multivariate group and the two-layer logic multivariate group are associated and distributed to determine the multiple control logics.

3. The concurrent analytics-driven production line monitoring system of claim 1, wherein, The introduction of the penalty function is used for data interpretation main line biasing and back introduction, including: traversing the multiple control logics to determine a data interpretation main line, which corresponds one-to-one to the multiple control logics; based on the data interpretation main line, locating an interpretation interference point based on multi-source production line data; for the interpretation interference point, constructing the penalty function and conducting trigger application management.

4. The concurrent analytics-driven production line monitoring system of claim 1, wherein, The determination of the machine tool monitoring module includes: based on the associated distribution of the multiple control logics, conducting distributed deployment to determine micro-processing block distribution; conducting industrial big data retrieval to determine sample data and segmentation, mapping to the micro-processing block distribution for supervised training and cross-validation to determine the micro-processing blocks that meet the convergence conditions; encapsulating single micro-processing blocks as nodes and establishing a fast interaction channel based on the associated distribution to generate the machine tool monitoring module.

5. The concurrent analytics-driven production line monitoring system of claim 4, wherein, The verification sample mapped by the micro-processing block meets the upper limit of the verification accuracy, and any block verification sample that is not mapped by the micro-processing block meets the lower limit of the verification accuracy as the convergence condition.

6. The concurrent analytics-driven production line monitoring system of claim 1, wherein, The introduction of the programmable logic device includes: reading the monitoring standards of the target machine tool production line based on work order production tasks; Determine a logic flow based on the monitoring standard and set a cycle control program based on the architecture of the machine tool monitoring module, wherein the cycle is a single-phase monitoring module processing cycle and a time zone monitoring cycle of a work order product processing; Configure the programmable logic device based on the cycle control program.

7. The concurrent analytics-driven production line monitoring system of claim 1, wherein, The machine tool monitoring module on the device edge side and the backend interacts based on a network communication protocol, including: Iterate through the multi-source production line data, perform data isomorphism processing and multi-source feature fitting based on a preprocessing model, determine effective production line data, wherein the isomorphic data structure is any one of the multi-source data structures; Return the effective production line data, perform node activation and concurrent analysis management based on the programmable logic device, and determine the production line monitoring single column; Identify the production line monitoring single column, perform binary processing of single column coefficients based on a mapping monitoring threshold, identify inferior binary data and mark, and the monitoring threshold corresponds one-to-one to the production line monitoring single column.

8. The concurrent analytics-driven production line monitoring system of claim 7, wherein, Perform node activation and concurrent analysis management based on the programmable logic device, including: Based on the pre-monitoring task, segment and activate the nodes of the effective production line data, perform multi-node concurrent processing and result combination, and determine the production line monitoring single column, wherein concurrent processing includes multi-task concurrency and single-task multi-node concurrent processing; If it is multi-task concurrency, perform node processing domain over-limit determination based on a task time limit; If it is over-limit, temporarily re-allocate resources to the micro-processing block based on operator utilization.

Images