A Visual Production Management System and Method

Abstract

The present application provides a visual production management system and method, which relates to the field of intelligent production management. By analyzing in real time the motor temperature value, motor current value, and total equipment operation duration of all production equipment in the production workshop, the operation state characteristics of the production equipment in the workshop are obtained. Then, the operation state characteristics of the production equipment in the workshop are passed through a generator to obtain a state diagram of the production equipment in the workshop, and the state diagram of the production equipment in the workshop is displayed on the large screen of the production workshop to achieve visual management of the production equipment in the workshop. In this way, workshop management personnel can comprehensively and intuitively understand the operation of the production equipment in the entire workshop in real time, which is conducive to their making scientific management decisions, thereby reducing the risks of production stagnation and economic losses.

Description

Technical Field

[0001] This application relates to the field of intelligent production management, and more specifically, to a visual production management system and method. Background Art

[0002] In traditional production management, there is a lack of real-time and accurate grasp of the operating status of production equipment. Workshop managers often understand the equipment status through regular inspections or feedback after a failure occurs. This has a large lag and it is difficult to detect and handle problems in the initial stage of equipment anomalies in a timely manner. Moreover, the operation data of different equipment is scattered in their respective control systems or records, making it difficult to integrate and analyze, resulting in the inability to comprehensively and intuitively evaluate the operation status of the entire workshop equipment. When equipment suddenly fails, production scheduling is difficult to be scientific and reasonable due to the lack of accurate knowledge of the real-time status of the equipment, resulting in uneven equipment utilization and affected production efficiency. At the same time, equipment failures will also cause production stagnation, resulting in economic losses, and production management decisions are also somewhat blind due to the lack of reliable data support.

[0003] Therefore, a visual production management solution is needed. Summary of the Invention

[0004] To solve the above technical problems, this application is proposed. Embodiments of this application provide a visual production management system and method, which obtain the operating status characteristics of all production equipment in the production workshop by analyzing the motor temperature value, motor current value, and total equipment operation duration in real time, and then obtain the production equipment status diagram of the workshop production equipment through a generator based on the operating status characteristics of the workshop production equipment, and display the production equipment status diagram of the workshop on the production large screen of the workshop to achieve visual management of the workshop production equipment. In this way, workshop management personnel can comprehensively and intuitively understand the operation of all production equipment in the workshop in real time, which is conducive to their making scientific management decisions, thereby reducing the risks of production stagnation and economic losses.

[0005] According to one aspect of this application, a visual production management system is provided, which includes:

[0006] A production equipment operating status monitoring parameter collection module, configured to obtain the operating status monitoring parameters of all production equipment in the production workshop at multiple predetermined time points within a predetermined time period, where the operating status monitoring parameters include motor temperature values, motor current values, and total equipment operation duration;

[0007] A production equipment operating status monitoring parameter structuring module, configured to perform data regularization on the operating status monitoring parameters of all production equipment in the production workshop at the multiple predetermined time points to obtain a production equipment operating status monitoring time series input tensor;

[0008] A production equipment operation status monitoring parameter encoding module for performing temporal feature encoding on the temporal input tensor of the production equipment operation status monitoring to obtain a temporal feature map of the production equipment operation status;

[0009] A production equipment operation status feature enhancement module for enhancing the features of the temporal feature map of the production equipment operation status monitoring to obtain a workshop production equipment operation status feature map;

[0010] A production equipment visualization result generation module for obtaining a workshop production equipment operation status map that can be used for display on a workshop production large screen based on the workshop production equipment operation status feature map.

[0011] According to another aspect of the present application, there is provided a visualization production management method, which includes:

[0012] Obtaining the operation status monitoring parameters of all production equipment in the production workshop at multiple predetermined time points within a predetermined time period, where the operation status monitoring parameters include motor temperature values, motor current values, and total equipment operation duration;

[0013] Regularizing the operation status monitoring parameters of all production equipment in the production workshop at the multiple predetermined time points to obtain a temporal input tensor of the production equipment operation status monitoring;

[0014] Performing temporal feature encoding on the temporal input tensor of the production equipment operation status monitoring to obtain a temporal feature map of the production equipment operation status monitoring;

[0015] Enhancing the features of the temporal feature map of the production equipment operation status monitoring to obtain a workshop production equipment operation status feature map;

[0016] Based on the workshop production equipment operation status feature map, obtaining a workshop production equipment operation status map that can be used for display on a workshop production large screen.

[0017] Compared with the prior art, the visualization production management system and method provided by the present application perform real-time analysis on the motor temperature values, motor current values, and total equipment operation duration of all production equipment in the production workshop to obtain the operation status features of the workshop production equipment, and then obtain the workshop production equipment status map through a generator with the operation status features of the workshop production equipment, and display the workshop production equipment status map on the workshop production large screen to achieve the visualization management of the workshop production equipment. In this way, workshop management personnel can comprehensively and intuitively understand the operation conditions of all production equipment in the entire workshop in real time, which is conducive to their making scientific management decisions, thereby reducing the risks of production stagnation and economic losses. Description of the Drawings

[0018] The above and other objects, features, and advantages of the present application will become more apparent by describing the embodiments of the present application in more detail with reference to the accompanying drawings. The drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation to the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0019] Figure 1 It is a system block diagram of a visual production management system according to an embodiment of the present application.

[0020] Figure 2 It is a block diagram of a production equipment operation status monitoring parameter coding module in a visual production management system according to an embodiment of the present application.

[0021] Figure 3 It is a block diagram of a production equipment operation status feature emphasizing module in a visual production management system according to an embodiment of the present application.

[0022] Figure 4 It is a block diagram of a production equipment visualization result generation module in a visual production management system according to an embodiment of the present application.

[0023] Figure 5 It is a flowchart of a visual production management method according to an embodiment of the present application. Detailed implementation manners

[0024] Hereinafter, exemplary embodiments of the present application will be described in detail with reference to the drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited by the exemplary embodiments described herein.

[0025] As mentioned in the above background art, in traditional production management practices, the real-time status monitoring of production equipment is not accurate. Usually, it relies on periodic inspections or reports after equipment failures to obtain equipment information. This method has obvious delays, making it difficult to detect and take countermeasures in a timely manner when abnormal signs appear in the equipment. In addition, since the operation data of different equipment is scattered in their respective control units or recording systems, it is difficult to perform effective integration and analysis, which hinders the comprehensive and intuitive assessment of the operation status of the equipment in the entire workshop. When an unexpected equipment failure occurs, due to the lack of accurate understanding of the current state of the equipment, it is difficult to make reasonable and scientific production scheduling, which not only affects the use efficiency of the equipment but also may lead to production interruptions and cause economic losses. At the same time, due to the lack of reliable data support, production management decisions often have a certain degree of arbitrariness. Therefore, a visual production management solution is expected.

[0026] In recent years, deep learning and neural networks have been widely applied in fields such as computer vision, natural language processing, and text signal processing. In addition, deep learning and neural networks have also demonstrated levels close to or even exceeding those of humans in fields such as image classification, object detection, semantic segmentation, and text translation. The development of deep learning and neural networks has provided new solutions and ideas for visual production management.

[0027] Figure 1 It is a system block diagram of a visual production management system according to an embodiment of the present application. As Figure 1 shown, in the visual production management system 100, it includes: a production equipment operation status monitoring parameter collection module 110, which is used to obtain the operation status monitoring parameters of all production equipment in the production workshop at multiple predetermined time points within a predetermined time period, where the operation status monitoring parameters include motor temperature values, motor current values, and the total equipment operation duration; a production equipment operation status monitoring parameter structuring module 120, which is used to regularize the operation status monitoring parameters of all production equipment in the production workshop at the multiple predetermined time points to obtain a production equipment operation status monitoring time series input tensor; a production equipment operation status monitoring parameter encoding module 130, which is used to perform time series feature encoding on the production equipment operation status monitoring time series input tensor to obtain a production equipment operation status monitoring time series feature map; a production equipment operation status feature emphasizing module 140, which is used to emphasize the features of the production equipment operation status monitoring time series feature map to obtain a workshop production equipment operation status feature map; a production equipment visualization result generation module 150, which is used to obtain a workshop production equipment operation status map that can be used for display on the workshop production large screen based on the workshop production equipment operation status feature map.

[0028] Specifically, in the technical solution of the present application, first, the operation status monitoring parameters of all production equipment in the production workshop at multiple predetermined time points within a predetermined time period are obtained. Among them, the operation status monitoring parameters include the motor temperature value, the motor current value, and the total equipment operation duration. It should be understood that the motor temperature is one of the important indicators reflecting the equipment operation status. During operation, the motor generates heat. If the motor temperature is too high, it may indicate that the motor is overloaded, which is likely to cause a decline in motor performance or even damage. Monitoring the motor temperature can timely detect potential motor failures and avoid production interruptions and equipment damage. The motor current is a direct parameter reflecting the motor load and working efficiency. When the motor is operating normally, its current value should fluctuate within a certain range. If the motor current increases abnormally, it may indicate faults such as excessive motor load or internal short circuit in the motor. The total equipment operation duration is an important basis for evaluating the equipment life and maintenance requirements. The degree of wear and aging of the equipment is closely related to its operation time. Long-term operation may lead to a decline in equipment performance and an increase in the failure rate. By recording the total equipment operation duration, preventive equipment maintenance and replacement can be carried out to avoid equipment failures at critical moments and affect the production progress. Generally speaking, by obtaining these three key indicators of the motor temperature, the motor current, and the total equipment operation duration, the operation status of the production equipment can be comprehensively evaluated.

[0029] The operation status of the production equipment is a dynamic process. To effectively capture the equipment status changes at different time points and facilitate the analysis of the equipment health status, it is necessary to arrange the data of the production equipment at multiple time points in the time dimension. At the same time, in a modern production environment, the workshop usually contains various types of production equipment. Considering the convenient management and analysis of the status information of different equipment, it is necessary to arrange the data of all equipment in the production workshop in the production equipment dimension. That is, in the technical solution of the present application, the operation status monitoring parameters of all production equipment in the production workshop at the multiple predetermined time points are arranged in the time dimension and the production equipment dimension to obtain the production equipment operation status monitoring time series input tensor. By integrating the data of multiple equipment at multiple time points into a three-dimensional tensor, unified processing and analysis of the data can be achieved, which helps to simplify the data processing process and thus improve the efficiency and accuracy of data processing.

[0030] Figure 2 It is a block diagram of the production equipment operation status monitoring parameter encoding module in the visual production management system according to an embodiment of the present application. As Figure 2As shown, the production equipment operation status monitoring parameter encoding module 130 includes: a first-scale monitoring time-series feature generation unit 131, configured to obtain a first-scale production equipment operation status monitoring time-series feature map by passing the production equipment operation status monitoring time-series input tensor through a first three-dimensional production equipment operation status feature encoder; a second-scale monitoring time-series feature generation unit 132, configured to obtain a second-scale production equipment operation status monitoring time-series feature map by passing the production equipment operation status monitoring time-series input tensor through a second three-dimensional production equipment operation status feature encoder; a multi-scale monitoring time-series feature fusion unit 133, configured to fuse the first-scale production equipment operation status monitoring time-series feature map and the second-scale production equipment operation status monitoring time-series feature map to obtain the production equipment operation status monitoring time-series feature map.

[0031] The original production equipment operation status monitoring time-series input tensor usually contains a large amount of raw data. In order to identify the factors that have the greatest impact on the change of the equipment status from the raw data, such as the change patterns of temperature, current, etc., so as to better characterize the health status of the production equipment, it is necessary to pass the production equipment operation status monitoring time-series input tensor through a first three-dimensional production equipment operation status feature encoder to obtain a first-scale production equipment operation status monitoring time-series feature map. In this application, the first three-dimensional production equipment operation status feature encoder is a convolutional neural network model using a first-scale three-dimensional convolutional kernel. It should be well understood that the three-dimensional convolutional kernel can operate in three dimensions (channels, height, and width), and can capture both the spatial features and time features in the production equipment status data at the same time. This spatio-temporal correlation is beneficial to analyzing the dynamically changing production equipment status information, thereby enhancing the expression ability of the features in the raw data.

[0032] In an embodiment of this application, an implementable manner of passing the production equipment operation status monitoring time-series input tensor through a first three-dimensional production equipment operation status feature encoder to obtain a first-scale production equipment operation status monitoring time-series feature map can be: using each layer of the first three-dimensional production equipment operation status feature encoder to perform the following operations on the input data respectively during the forward pass of the layer: using the convolutional units of each layer of the first three-dimensional production equipment operation status feature encoder to perform convolutional processing on the input data based on a first-scale three-dimensional convolutional kernel to obtain a convolutional feature map; using the pooling units of each layer of the first three-dimensional production equipment operation status feature encoder to perform pooling processing on the convolutional feature map based on a local feature matrix to obtain a pooling feature map; using the activation units of each layer of the first three-dimensional production equipment operation status feature encoder to perform non-linear activation on the feature values at each position in the pooling feature map to obtain an activation feature map; wherein, the output of the last layer of the first three-dimensional production equipment operation status feature encoder is the first-scale production equipment operation status monitoring time-series feature map.

[0033] Meanwhile, input the production equipment operation status monitoring time series input tensor into the second three-dimensional production equipment operation status feature encoder to obtain the second-scale production equipment operation status monitoring time series feature map. In this application, the second three-dimensional production equipment operation status feature encoder is a convolutional neural network model using a second-scale three-dimensional convolutional kernel, and the first scale is different from the second scale. The scale of the three-dimensional convolutional kernel refers to the size of the convolutional kernel in three dimensions, and this size determines the window range for the convolutional operation to slide on the input tensor, thereby affecting the fineness and range of feature extraction. In this application, introducing the second three-dimensional production equipment operation status feature encoder to extract features from the input tensor can capture richer production equipment status feature information at different scales, thereby improving the sensitivity and recognition ability of the model to equipment status changes.

[0034] Three-dimensional convolutional kernels of different scales can capture different levels of feature information in the original production equipment data. Small-scale three-dimensional convolutional kernels can capture short-term minute changes and local operation patterns in the production equipment data, while large-scale three-dimensional convolutional kernels can capture long-term changes and overall operation patterns of the production equipment. In order to form a more comprehensive and accurate description of the equipment status of all equipment in the workshop, in the technical solution of this application, it is necessary to fuse the first-scale production equipment operation status monitoring time series feature map and the second-scale production equipment operation status monitoring time series feature map to obtain the production equipment operation status monitoring time series feature map. By fusing multi-scale features, the levels and diversity of features can be enriched, and the feature expression ability can be improved. This rich feature representation helps to better understand and identify the operation status of the equipment, thereby improving the accuracy of generating the production equipment status map.

[0035] In an embodiment of this application, an implementable way to fuse the first-scale production equipment operation status monitoring time series feature map and the second-scale production equipment operation status monitoring time series feature map to obtain the production equipment operation status monitoring time series feature map can be: use the following fusion formula to fuse the first-scale production equipment operation status monitoring time series feature map and the second-scale production equipment operation status monitoring time series feature map to obtain the production equipment operation status monitoring time series feature map; where, the fusion formula is:

[0036] F c =αF a ⊕βF b

[0037] where, F c is the production equipment operation status monitoring time series feature map, F a is the first-scale production equipment operation status monitoring time series feature map, F bFor the time - series feature map of the operation status monitoring of the second - scale production equipment, ⊕ represents the addition of elements at corresponding positions of the time - series feature map of the operation status monitoring of the first - scale production equipment and the time - series feature map of the operation status monitoring of the second - scale production equipment, and α and β are weighted parameters used to control the balance between the time - series feature map of the operation status monitoring of the first - scale production equipment and the time - series feature map of the operation status monitoring of the second - scale production equipment in the time - series feature map of the operation status monitoring of the production equipment.

[0038] Figure 3 It is a block diagram of a production equipment operation status feature emphasis module in a visual production management system according to an embodiment of the present application. As Figure 3 shown, the production equipment operation status feature emphasis module 140 includes: a feature map channel feature emphasis unit 141, which is used to obtain a time - series feature enhanced map of the operation status monitoring of the production equipment by passing the time - series feature map of the operation status monitoring of the production equipment through an operation status time - series feature emphasis device based on a channel attention mechanism; a feature map spatial feature emphasis unit 142, which is used to obtain the operation status feature map of the workshop production equipment by passing the time - series feature enhanced map of the operation status monitoring of the production equipment through an operation status feature device emphasis device based on a spatial attention mechanism.

[0039] In order to strengthen the understanding of the operation status of workshop production equipment at different time points, the time - series feature map of the operation status monitoring of the production equipment is passed through an operation status time - series feature emphasis device based on a channel attention mechanism to obtain a time - series feature enhanced map of the operation status monitoring of the production equipment. In the present application, the operation status time - series feature emphasis device based on a channel attention mechanism is a convolutional neural network model using a channel attention mechanism. A channel attention module is added after the convolutional layer of the convolutional neural model. The purpose of this module is to dynamically adjust the weights of different channels (in this application, it refers to different time points) so as to pay more attention to important channels and ignore unimportant channels during the feature extraction process. The feature map strengthened by the channel attention mechanism can more accurately reflect the operation status of the production equipment at different time points, reducing the interference of noise and irrelevant information.

[0040] To enhance the understanding of the operating states of all production equipment in the workshop and highlight equipment with abnormal operating states or impending failures, it is necessary to obtain the operating state feature map of workshop production equipment by emphasizing the time-series feature enhancement map of the operating states of the production equipment through an operating state feature equipment enhancer based on a spatial attention mechanism. In this application, the operating state feature equipment enhancer based on the spatial attention mechanism is a convolutional neural network model using the spatial attention mechanism. The spatial attention mechanism can dynamically adjust the weights of different spatial positions (i.e., different production equipment and different monitoring indicators) in the input time-series feature enhancement map of the operating states of the production equipment, enabling the convolutional neural network model to pay more attention to these important regions. By emphasizing important spatial features, the generated operating state feature map of workshop production equipment can more intuitively display the operating conditions of each piece of equipment, helping workshop managers quickly identify abnormal production equipment. That is, the introduction of the spatial attention mechanism makes the operating state map of production equipment more data-driven, and managers can make decisions based on more scientific analysis results, thereby improving the intelligent level of workshop management.

[0041] Figure 4 The block diagram of the production equipment visualization result generation module in the visual production management system according to an embodiment of the present application. As Figure 4 shown, the production equipment visualization result generation module 150 includes: a feature map pooling and dimensionality reduction unit 151 for performing global pooling based on a feature matrix on the operating state feature map of the workshop production equipment to obtain an operating state feature vector of the workshop production equipment; a feature vector optimization unit 152 for performing backpropagation probability optimization of relevant information on the operating state feature vector of the workshop production equipment to obtain an optimized operating state feature vector of the workshop production equipment; a feature vector analysis unit 153 for passing the optimized operating state feature vector of the workshop production equipment through a generator to obtain a generation result, and the generation result is an operating state map of the workshop production equipment.

[0042] Considering that the operating state feature map of workshop production equipment has a high dimension, in order to reduce the dimension of the data, reduce the complexity of subsequent calculations and storage requirements, it is necessary to perform global pooling based on a feature matrix on the operating state feature map of the workshop production equipment to obtain an operating state feature vector of the workshop production equipment. The global pooling operation can integrate all position information of the feature map into a global feature vector, thereby significantly reducing the spatial dimension of the data and making subsequent data processing more efficient.

[0043] Specifically, in the technical solution of this application, a production equipment status diagram generator is used to process the feature vectors to generate a workshop production equipment operation status diagram. Considering that the weights of the generator are learned during the model training process, these weights determine how the model extracts information from the workshop production equipment operation status feature vectors to generate the status diagram. If the weights do not match the input feature vectors, the generator may not accurately reflect the operation status of the equipment. During the process of generating the status diagram, if the distribution of the weights of the generator is inconsistent with the input feature vectors, it may cause some features to be wrongly emphasized or ignored, resulting in coherent interference. This interference may affect the accuracy and reliability of the status diagram. To avoid coherent interference, in the technical solution of this application, the relevant information backward propagation probability of the workshop production equipment operation status feature vectors is optimized to obtain optimized workshop production equipment operation status feature vectors.

[0044] Specifically, in the embodiments of this application, optimizing the relevant information backward propagation probability of the workshop production equipment operation status feature vectors to obtain optimized workshop production equipment operation status feature vectors includes: calculating the product between the workshop production equipment operation status feature vectors and their transposed vectors to obtain a workshop production equipment operation status autocorrelation expression matrix; calculating the coherent interference phase between the decoding weight matrix of the generator and the workshop production equipment operation status autocorrelation expression matrix to obtain a workshop production equipment operation status-feature weight fine-grained coupling representation matrix; performing probabilistic processing on the workshop production equipment operation status-feature weight fine-grained coupling representation matrix based on the Sigmoid activation function to obtain a workshop production equipment operation status-feature weight fine-grained coupling probabilistic representation matrix; performing backward propagation expression compensation on the workshop production equipment operation status feature vectors based on the workshop production equipment operation status-feature weight fine-grained coupling probabilistic representation matrix to obtain a relevant compensation representation vector; calculating the position-wise weighted sum between the relevant compensation representation vector and the workshop production equipment operation status feature vectors to obtain the optimized workshop production equipment operation status feature vectors.

[0045] More specifically, in the embodiments of this application, calculating the coherent interference phase between the decoding weight matrix of the generator and the workshop production equipment operation status autocorrelation expression matrix to obtain a workshop production equipment operation status-feature weight fine-grained coupling representation matrix includes: calculating the coherent interference phase between the decoding weight matrix of the generator and the workshop production equipment operation status autocorrelation expression matrix with the following formula to obtain the workshop production equipment operation status-feature weight fine-grained coupling representation matrix; where the formula is:

[0046]

[0047] Where, V1i represents the i-th row vector of the decoding weight matrix of the generator, V 2j represents the j-th row vector of the autocorrelation expression matrix of the operating state characteristics of the workshop production equipment, ∑ represents the covariance matrix of the datasets to which the i-th row vector of the decoding weight matrix of the generator and the j-th row vector of the autocorrelation expression matrix of the operating state characteristics of the workshop production equipment belong, ∑ -1 represents the inverse matrix of the covariance matrix, A(V 1i ,V 2j ) represents the eigenvalue at the (i, j) position of the operating state characteristics-weight fine-grained coupling representation matrix of the workshop production equipment.

[0048] More specifically, in the embodiment of the present application, backward propagation expression compensation is performed on the operating state characteristic vector of the workshop production equipment based on the operating state characteristics-weight fine-grained coupling probabilistic representation matrix to obtain a relevant compensation representation vector, including: performing backward propagation expression compensation on the operating state characteristic vector of the workshop production equipment based on the operating state characteristics-weight fine-grained coupling probabilistic representation matrix according to the following formula to obtain the relevant compensation representation vector; where the formula is:

[0049]

[0050] where, V r represents the relevant compensation representation vector, A represents the operating state characteristics-weight fine-grained coupling probabilistic representation matrix of the workshop production equipment, V c represents the operating state characteristic vector of the workshop production equipment, represents matrix multiplication.

[0051] In the technical solution of the present application, when the operation state feature vector of the workshop production equipment is generated by a generator, since the weights of the generator also need to be adapted to the operation state feature vector of the workshop production equipment, class coherence interference with the operation state feature vector of the workshop production equipment may occur. Based on this, in the technical solution of the present application, backward propagation probability optimization of relevant information of the operation state feature vector of the workshop production equipment is performed. First, the autocorrelation interference feature spectrogram is represented by the autocorrelation matrix of the operation state feature vector of the workshop production equipment, and then the correlation measure between the autocorrelation matrix of the operation state feature vector of the workshop production equipment and the decoding weight matrix of the generator is calculated to simulate the fine-grained feature-category label coherence interference phase between the operation state feature of the workshop production equipment and the weight matrix of the generator. Furthermore, backward propagation expression compensation is performed on the operation state feature vector of the workshop production equipment with the operation state-weight fine-grained coupling representation matrix to reversely compensate and restore the equivalent probability intensity characterization of the operation state feature vector of the workshop production equipment in the case of no interference, and the optimized operation state feature vector of the workshop production equipment is obtained to improve the accuracy of the generation result.

[0052] Finally, the optimized operation state feature vector of the workshop production equipment is passed through the generator to obtain a generation result, which is the operation state diagram of the workshop production equipment. It should be understood that the generator is mainly responsible for converting complex feature vector data into intuitive and easy-to-understand visualization charts. Specifically, the optimized operation state feature vector of the workshop production equipment contains a large amount of equipment state feature information, and the generator can decode this feature information and present the state of the workshop production equipment in a structured and hierarchical manner, enabling production management personnel to quickly grasp the key points and understand the overall situation. The operation state diagram of the workshop production equipment can identify the operation state of the equipment through different colors, such as normal operation, warning, failure, etc. In this way, production management personnel can clearly see which equipment is in a normal state, which equipment needs attention or handling, and take timely measures, thereby reducing production interruptions and downtime, and further improving production efficiency and resource utilization.

[0053] In summary, the visualization production management system 100 according to the embodiments of the present application is described. It obtains the operating state characteristics of the production equipment in the workshop by analyzing the motor temperature value, motor current value, and total operating duration of all production equipment in the production workshop in real time. Then, the operating state characteristics of the production equipment in the workshop are processed by a generator to obtain a state diagram of the production equipment in the workshop, and the state diagram of the production equipment in the workshop is displayed on the large screen in the production workshop to achieve the visualization management of the production equipment in the workshop. In this way, the workshop management personnel can comprehensively and intuitively understand the operating conditions of all production equipment in the workshop in real time, which is conducive to their making scientific management decisions, thereby reducing the risks of production stagnation and economic losses.

[0054] As described above, the visualization production management system 100 according to the embodiments of the present application can be implemented in various terminal devices, such as a server for visualization production management. In one example, the visualization production management system 100 according to the embodiments of the present application can be integrated into the terminal device as a software module and / or a hardware module. For example, the visualization production management system 100 can be a software module in the operating system of the terminal device, or can be an application program developed for the terminal device; of course, the visualization production management system 100 can also be one of many hardware modules of the terminal device.

[0055] Alternatively, in another example, the visualization production management system 100 and the terminal device can also be separate devices, and the visualization production management system 100 can be connected to the terminal device through a wired and / or wireless network and transmit interaction information in accordance with a predefined data format.

[0056] In other embodiments of the present application, a visual production management system is further provided. It collects various types of data during the production process through various sensors, device data collectors, etc., such as equipment operation data, production progress data, quality inspection data, etc., integrates and summarizes these data, and then uses technologies such as two-dimensional modeling and virtual reality to present the production site, equipment, process flow, etc. in an intuitive two-dimensional form, enabling managers to more clearly understand the production situation, realizing real-time monitoring of the production site conditions, which is beneficial for managers to promptly discover abnormal situations and give feedback so that relevant personnel can quickly take measures. It can also use data analysis algorithms and models to deeply analyze various types of data collected during the production process to provide decision-making support for aspects such as production plan formulation, optimal allocation of resources, and traceability of quality problems. In addition, this visual production management system can also be interconnected with the enterprise's ERP (Enterprise Resource Planning) system, SCADA (Supervisory Control and Data Acquisition) system, etc. to form a complete production management system, realize information sharing and collaborative work, and then help the enterprise achieve full-process management and control in aspects such as production planning, material management, and production execution, thereby improving production efficiency and product quality and reducing production costs.

[0057] Figure 5 FIG. is a flowchart of a visual production management method according to an embodiment of the present application. As Figure 5 shown, in the visual production management method, it includes: S110, obtaining the operation state monitoring parameters of all production equipment in the production workshop at multiple predetermined time points within a predetermined time period, where the operation state monitoring parameters include motor temperature values, motor current values, and total equipment operation duration; S120, performing data regularization on the operation state monitoring parameters of all production equipment in the production workshop at the multiple predetermined time points to obtain a production equipment operation state monitoring time series input tensor; S130, performing time series feature encoding on the production equipment operation state monitoring time series input tensor to obtain a production equipment operation state monitoring time series feature map; S140, performing feature emphasis on the production equipment operation state monitoring time series feature map to obtain a workshop production equipment operation state feature map; S150, based on the workshop production equipment operation state feature map, obtaining a workshop production equipment operation state map that can be used for display on the workshop production large screen.

[0058] Here, those skilled in the art can understand that the specific operations of each step in the above visual production management method have been introduced in detail in the description of the above Figures 1 to 4 visual production management system, and therefore, the repeated description thereof will be omitted.

[0059] In summary, the visualization production management method based on the embodiments of the present application is elucidated. It obtains the operation state characteristics of the production equipment in the workshop by analyzing the motor temperature value, motor current value, and total equipment operation duration of all production equipment in the production workshop in real time. Furthermore, the operation state characteristics of the production equipment in the workshop are obtained through a generator to obtain the state diagram of the production equipment in the workshop, and the state diagram of the production equipment in the workshop is displayed on the large production screen in the workshop to achieve the visualization management of the production equipment in the workshop. In this way, workshop managers can comprehensively and intuitively understand the operation of all production equipment in the workshop in real time, which is conducive to their making scientific management decisions, thereby reducing the risk of production stagnation and economic losses.

[0060] For those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present application, the present application can be implemented in other specific forms.

[0061] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-limiting. The scope of the present application is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present application. Any associated drawing marks in the claims should not be regarded as limiting the claims involved.

[0062] In addition, it is obvious that the word "including" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units or devices stated in the system claims can also be implemented by one unit or device through software or hardware. The terms such as second are used to represent names and do not represent any specific order.

[0063] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and not to limit them. Although the present application has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present application can be modified or equivalently replaced without departing from the spirit of the technical solutions of the present application.

Claims

1. A visualization production management system, characterized in that, Including: A production equipment operation status monitoring parameter collection module, configured to obtain operation status monitoring parameters of all production equipment in a production workshop at multiple predetermined time points within a predetermined time period. Among them, the operation status monitoring parameters include motor temperature values, motor current values, and total equipment operation duration. A production equipment operation status monitoring parameter structuring module, configured to regularize the operation status monitoring parameters of all production equipment in the production workshop at the multiple predetermined time points to obtain a production equipment operation status monitoring time series input tensor. A production equipment operation status monitoring parameter encoding module, configured to perform time series feature encoding on the production equipment operation status monitoring time series input tensor to obtain a production equipment operation status monitoring time series feature map. A production equipment operation status feature emphasizing module, configured to emphasize features of the production equipment operation status monitoring time series feature map to obtain a workshop production equipment operation status feature map. A production equipment visualization result generation module, configured to obtain a workshop production equipment operation status map that can be used for display on a workshop production large screen based on the workshop production equipment operation status feature map. Among them, the production equipment operation status feature emphasizing module includes: A feature map channel feature emphasizing unit, configured to pass the production equipment operation status monitoring time series feature map through an operation status time series feature enhancer based on a channel attention mechanism to obtain a production equipment operation status monitoring time series feature enhanced map. A feature map spatial feature emphasizing unit, configured to pass the production equipment operation status monitoring time series feature enhanced map through an operation status feature equipment enhancer based on a spatial attention mechanism to obtain the workshop production equipment operation status feature map.

2. The visualization production management system according to claim 1, wherein The production equipment operation status monitoring parameter structuring module is configured to: arrange the operation status monitoring parameters of all production equipment in the production workshop at the multiple predetermined time points according to the time dimension and the production equipment dimension to obtain the production equipment operation status monitoring time series input tensor.

3. The visual production management system according to claim 2, characterized in that, The production equipment operation status monitoring parameter encoding module includes: A first-scale monitoring time series feature generation unit, configured to pass the production equipment operation status monitoring time series input tensor through a first three-dimensional production equipment operation status feature encoder to obtain a first-scale production equipment operation status monitoring time series feature map. A second-scale monitoring time series feature generation unit, configured to pass the production equipment operation status monitoring time series input tensor through a second three-dimensional production equipment operation status feature encoder to obtain a second-scale production equipment operation status monitoring time series feature map. A multi-scale monitoring time series feature fusion unit, configured to fuse the first-scale production equipment operation status monitoring time series feature map and the second-scale production equipment operation status monitoring time series feature map to obtain the production equipment operation status monitoring time series feature map.

4. The visualization production management system according to claim 3, wherein The first three-dimensional production equipment operation status feature encoder is a convolutional neural network model using a first-scale three-dimensional convolutional kernel, and the second three-dimensional production equipment operation status feature encoder is a convolutional neural network model using a second-scale three-dimensional convolutional kernel, where the first scale is different from the second scale.

5. The visualization production management system according to claim 4, wherein The operating state time-series feature intensifier based on the channel attention mechanism is a convolutional neural network model using the channel attention mechanism, and the operating state feature device intensifier based on the spatial attention mechanism is a convolutional neural network model using the spatial attention mechanism.

6. The visualization production management system according to claim 5, characterized in that, The production equipment visualization result generation module includes: A feature map pooling and dimensionality reduction unit, configured to perform global pooling based on a feature matrix on the operating state feature map of the workshop production equipment to obtain an operating state feature vector of the workshop production equipment; A feature vector optimization unit, configured to perform relevant information backward propagation probability optimization on the operating state feature vector of the workshop production equipment to obtain an optimized operating state feature vector of the workshop production equipment; A feature vector analysis unit, configured to obtain a generation result by passing the optimized operating state feature vector of the workshop production equipment through a generator, where the generation result is an operating state map of the workshop production equipment.

7. The visualization production management system according to claim 6, wherein The feature vector optimization unit is configured to: Calculate the product between the operating state feature vector of the workshop production equipment and its transposed vector to obtain an operating state feature autocorrelation expression matrix of the workshop production equipment; Calculate the coherent interference phase state between the decoding weight matrix of the generator and the operating state feature autocorrelation expression matrix of the workshop production equipment to obtain an operating state feature-weight fine-grained coupling representation matrix of the workshop production equipment; Perform probabilistic processing based on the Sigmoid activation function on the operating state feature-weight fine-grained coupling representation matrix of the workshop production equipment to obtain an operating state feature-weight fine-grained coupling probabilistic representation matrix of the workshop production equipment; Perform backward propagation expression compensation on the operating state feature vector of the workshop production equipment based on the operating state feature-weight fine-grained coupling probabilistic representation matrix of the workshop production equipment to obtain a relevant compensation representation vector; Calculate the position-wise weighted sum between the relevant compensation representation vector and the operating state feature vector of the workshop production equipment to obtain the optimized operating state feature vector of the workshop production equipment.

8. A visual production management method, characterized in that, It includes: Obtain the operating state monitoring parameters of all production equipment in the production workshop at multiple predetermined time points within a predetermined time period, where the operating state monitoring parameters include motor temperature values, motor current values, and total equipment operating duration; Regularize the operating state monitoring parameters of all production equipment in the production workshop at the multiple predetermined time points to obtain an operating state monitoring time-series input tensor of the production equipment; Perform time-series feature encoding on the operating state monitoring time-series input tensor of the production equipment to obtain an operating state monitoring time-series feature map of the production equipment; Perform feature emphasis on the operating state monitoring time-series feature map of the production equipment to obtain an operating state feature map of the workshop production equipment; Based on the operating state feature map of the workshop production equipment, obtain an operating state map of the workshop production equipment that can be used for display on the workshop production large screen; Among them, performing feature emphasis on the operating state monitoring time-series feature map of the production equipment to obtain an operating state feature map of the workshop production equipment includes: The time-series feature map of the production equipment operation status is passed through an operation status time-series feature enhancer based on a channel attention mechanism to obtain a reinforced time-series feature map of the production equipment operation status; The reinforced time-series feature map of the production equipment operation status is passed through an operation status feature equipment enhancer based on a spatial attention mechanism to obtain the operation status feature map of the workshop production equipment.

9. The visualization production management method according to claim 8, wherein, Performing time-series feature encoding on the time-series input tensor of the production equipment operation status monitoring to obtain a time-series feature map of the production equipment operation status monitoring, including: Passing the time-series input tensor of the production equipment operation status monitoring through a first three-dimensional production equipment operation status feature encoder to obtain a time-series feature map of the production equipment operation status monitoring at a first scale; Passing the time-series input tensor of the production equipment operation status monitoring through a second three-dimensional production equipment operation status feature encoder to obtain a time-series feature map of the production equipment operation status monitoring at a second scale; Fusing the time-series feature map of the production equipment operation status monitoring at the first scale and the time-series feature map of the production equipment operation status monitoring at the second scale to obtain the time-series feature map of the production equipment operation status monitoring.

Images