A method for sensing and analyzing characteristic parameters of granular materials during forming process

Abstract

This invention discloses a method for sensing and analyzing characteristic parameters of bulk particles during the molding process. This method can construct a secure and reliable data acquisition and sensing system based on Industrial Ethernet, forming a data transmission method with low-latency synchronous communication. This method ensures the efficient real-time operation of digital twin models, enables real-time understanding of the changing patterns of process parameters during the compaction molding of bulk explosives, and enables comprehensive monitoring and prediction of production operation status. By precisely controlling key process parameters during the production process, it effectively improves product quality, performance, and consistency, ensuring the quality stability of mass-produced products and meeting the precision damage requirements of future advanced ammunition.

Description

Technical Field

[0001] The present invention relates to the technical field of compression molding of explosive granular particles, and in particular to a method for sensing and analyzing characteristic parameters of granular particles during a molding process. Background Art

[0002] The compaction of granular explosive particles is crucial for press-fitting warhead charges. This involves molding the particles into a dense, compacted charge and imparting functional properties. Real-time acquisition and simultaneous analysis of dynamic data, including process parameters and process parameters, directly impacts the quality of the compacted particles.

[0003] To achieve precise control of molding quality and reduce grain defects, online sensing and rapid analysis of various process and process data are necessary. However, due to the limitations of traditional detection methods, the complexity of molding process conditions, and the heterogeneity of material process parameters, dynamic real-time sensing of process and process parameters is difficult to achieve and rapid analysis is difficult.

[0004] Therefore, how to provide a real-time data perception and low-latency synchronous analysis method for the characteristic parameters of the explosive bulk compaction molding process to obtain real-time perception and centralized monitoring of the production operation status of the bulk compaction molding is a technical problem that urgently needs to be solved by technical personnel in this field. Summary of the Invention

[0005] In view of the above problems, the present invention provides a method for perceiving and analyzing characteristic parameters of granular bodies in a molding process, which is used to overcome the above problems or at least partially solve the above problems. By accurately characterizing characteristic parameters such as the molding process technology and process and perceiving and fusing multi-source heterogeneous data, the dynamic capture and correlation processing of the characteristic parameters of the molding process are realized, and by online judgment and correction of data quality, rapid synchronous analysis of multimodal data is realized, effectively protecting the accuracy and synchronization of characteristic parameters, providing key technical support for the real-time acquisition and synchronous analysis of characteristic parameters of the granular body particle pressing molding process, and laying the foundation for precise control of molding quality.

[0006] The present invention provides the following solutions:

[0007] A method for sensing and analyzing characteristic parameters of granular materials during a forming process, comprising:

[0008] Applied to a UA server, the UA server is arranged in a field control system and is communicatively connected to field equipment; the method comprises:

[0009] Obtain on-site data and equipment information of the medicine pressing workshop;

[0010] Converting the field data and the device information into source data supporting the OPC UA protocol, and performing data management and logic operation on the source data to obtain target data;

[0011] The target data is sent to the UA client so that the digital twin system of the explosive pressing production process deployed on the UA client can use the target data to update the real-time production data of various factors. The real-time production data is used to determine the change law of the process parameters of the explosive granular pressing process and monitor and predict the production operation status.

[0012] Preferably: the source data is saved as a source database and the target data is saved as a target database;

[0013] Receive the synchronization data file sent by the UA client, parse the data in the source database to create SQL statements according to the synchronization rules in the synchronization data file, and update the data to the target database.

[0014] Preferably, the UA client scans the changes of the specified data table of the source database, captures the changed data and performs data conversion according to the declaration in the synchronization rule to generate the synchronization data file in XML format.

[0015] Preferably, the field data and the device information include heterogeneous multi-source multi-modal perception data, and the quality of the heterogeneous multi-source multi-modal perception data is determined and corrected in real time to improve the data quality of the heterogeneous multi-source multi-modal perception data.

[0016] Preferably, the heterogeneous multi-source multi-modal perception data quality assessment process adopts a mathematical model based on a sensor network and sensor acquisition through a machine vision optimization algorithm to achieve edge quality determination and correction of the heterogeneous multi-source multi-modal perception data.

[0017] Preferably: the heterogeneous multi-source multi-modal perception data is associated and fused to realize the association mapping between the digital twin information and the model of the explosive granular pressing and molding process; synchronous information data is obtained for detection, data association, data fusion, and filtering estimation, and relevant judgments on the target trajectory are made to obtain the position and specific information description of the measured model target.

[0018] Preferably, the heterogeneous multi-source multi-modal perception data is preprocessed, and the preprocessing includes standardization and compression.

[0019] Preferably, the standardization and compression include:

[0020] The first level of processing is configured as detection fusion to produce the final detection output;

[0021] The second level of processing is configured as position fusion, wherein the position fusion includes data registration, trajectory association, trajectory fusion and filter prediction;

[0022] The third level of processing is configured as target recognition, which includes estimating the attributes and identity of the target based on pattern recognition related technologies;

[0023] The fourth level of fine processing is configured as optimized correction processing, which optimizes the control and evaluation of the feedback of other levels of processing.

[0024] Preferably, the heterogeneous multi-source multi-modal perception data is judged and corrected in real time; the real-time judgment and correction includes multi-source sensor data quality assessment processing; the quality assessment processing includes a mathematical model based on a sensor network and sensor machine vision optimization; including:

[0025] Perform mean square error statistics on sensor sampling data and real data based on probability to establish an estimation model;

[0026] Using an edge computing algorithm to perform filtering calculations on the sensor collected data and the estimated data calculated by the estimation model to correct the perception data;

[0027] Based on the accumulated data, data analysis and fusion correction are carried out to improve the data quality of the perception data.

[0028] Preferably: receiving a query request sent by a target data query terminal through a multi-threaded WEB server; the target data query terminal is a data query terminal that has been verified by the WEB server;

[0029] The target data is sent to the target data query in ciphertext form.

[0030] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0031] The embodiments of this application provide a method for sensing and analyzing characteristic parameters of bulk particles during the molding process. This method can build a secure and reliable data acquisition and sensing system based on Industrial Ethernet, forming a data transmission method with low-latency synchronous communication. This method can ensure the efficient real-time operation of digital twin models, and can grasp the changing patterns of process parameters during the compaction molding process of bulk explosives in real time, allowing for comprehensive monitoring and prediction of production operation status. By precisely controlling key process parameters during the production process, product quality, performance, and consistency can be effectively improved, ensuring the quality stability of mass-delivered products and meeting the precision damage requirements of future advanced ammunition.

[0032] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be derived from these drawings without inventive effort.

[0034] Figure 1 This is a schematic diagram of a data acquisition network structure for explosive granular body compression molding provided by an embodiment of the present invention;

[0035] Figure 2 Schematic diagram of data collection technology for explosive granular body compression molding provided by an embodiment of the present invention;

[0036] Figure 3 This is a framework diagram of a distributed heterogeneous database data synchronization system for explosive bulk compaction provided by an embodiment of the present invention;

[0037] Figure 4 This is a diagram of the architecture of the explosive granular body compression molding data fusion function model provided by an embodiment of the present invention;

[0038] Figure 5 It is a schematic diagram of the secure dynamic transmission process of explosive bulk compaction data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of the present invention.

[0040] An embodiment of the present invention provides a method for sensing and analyzing characteristic parameters of a granular body during a molding process, which is applied to a UA server. The UA server is provided in a field control system and is communicatively connected to field equipment. The method includes:

[0041] Obtain on-site data and equipment information of the medicine pressing workshop;

[0042] Converting the field data and the device information into source data supporting the OPC UA protocol, and performing data management and logic operation on the source data to obtain target data;

[0043] The target data is sent to the UA client so that the digital twin system of the explosive pressing production process deployed on the UA client can use the target data to update the real-time production data of various factors. The real-time production data is used to determine the change law of the process parameters of the explosive granular pressing process and monitor and predict the production operation status.

[0044] Further, the source data is saved as a source database and the target data is saved as a target database;

[0045] Receive the synchronization data file sent by the UA client, parse the data in the source database to create SQL statements according to the synchronization rules in the synchronization data file, and update the data to the target database.

[0046] The UA client scans the changes of the specified data table of the source database, captures the changed data and performs data conversion according to the declaration method in the synchronization rule, and generates the synchronization data file in XML format.

[0047] The field data and the device information include heterogeneous multi-source multi-modal perception data, and the quality of the heterogeneous multi-source multi-modal perception data is determined and corrected in real time to improve the data quality of the heterogeneous multi-source multi-modal perception data.

[0048] The heterogeneous multi-source multi-modal perception data quality assessment process adopts a mathematical model based on a sensor network and sensor acquisition through a machine vision optimization algorithm to achieve edge quality judgment and correction of the heterogeneous multi-source multi-modal perception data.

[0049] The heterogeneous multi-source and multi-modal perception data are associated and fused to realize the association mapping between the digital twin information and the model of the explosive granular compression molding process; synchronous information data is obtained for detection, data association, data fusion, and filtering estimation, and relevant judgments on the target trajectory are made to obtain the position and specific information description of the measured model target.

[0050] The heterogeneous multi-source multi-modal perception data is preprocessed, and the preprocessing includes standardization and compression.

[0051] The standardization and compression include:

[0052] The first level of processing is configured as detection fusion to produce the final detection output;

[0053] The second level of processing is configured as position fusion, wherein the position fusion includes data registration, trajectory association, trajectory fusion and filter prediction;

[0054] The third level of processing is configured as target recognition, which includes estimating the attributes and identity of the target based on pattern recognition related technologies;

[0055] The fourth level of fine processing is configured as optimized correction processing, which optimizes the control and evaluation of the feedback of other levels of processing.

[0056] Performing real-time determination and correction on the heterogeneous multi-source multi-modal perception data; the real-time determination and correction includes multi-source sensor data quality assessment processing; the quality assessment processing includes a mathematical model based on a sensor network and sensor machine vision optimization; including:

[0057] Perform mean square error statistics on sensor sampling data and real data based on probability to establish an estimation model;

[0058] Using an edge computing algorithm to perform filtering calculations on the sensor collected data and the estimated data calculated by the estimation model to correct the perception data;

[0059] Based on the accumulated data, data analysis and fusion correction are carried out to improve the data quality of the perception data.

[0060] In order to implement encrypted query, the embodiment of the present application may further provide a method for receiving a query request sent by a target data query end through a multi-threaded WEB server; the target data query end is a data query end that has been verified by the WEB server;

[0061] The target data is sent to the target data query in ciphertext form.

[0062] The embodiment of the present application provides a method for sensing and analyzing characteristic parameters of granular bodies during the molding process. Through data sensing and synchronous analysis methods, a safe and reliable data acquisition and sensing system can be established, forming a data transmission method with low-latency synchronous communication. This method can grasp the changing patterns of process parameters during the compaction molding process of explosive granular bodies in real time, and fully monitor and predict the production operation status.

[0063] Adopting the data network structure based on OPC UA, establishing a unified standardized virtual-real communication framework and protocol, and using customized HTTP, Webservice and other data exchange interface methods, we can realize the real-time identification and collection of the working status, material distribution, and quality inspection data of the process equipment, testing equipment, sensors and other production equipment in the granular pressing process.

[0064] Through the data bus provided by the on-site Internet of Things, networking with equipment and data transmission are realized.

[0065] The use of data synchronization tools facilitates users to collect multi-source and multi-modal data. At the same time, a unified parsing engine is used to effectively decouple data sources and users, solve problems such as high concurrency and high throughput, and obtain synchronized information data for association and fusion processing to obtain the status and specific location information description of the target model under test.

[0066] The virtual-reality communication network architecture is constructed to establish a unified and standardized virtual-reality communication framework protocol to solve the problem that there are a large number of equipment from different technologies and manufacturers in the explosive granular pressing and molding workshop, and their interface protocols are different. A data network architecture based on OPC UA is adopted.

[0067] The explosives bulk pressing and molding workshop houses a large number of devices from different technologies and manufacturers, each with its own unique interface protocols. Therefore, an OPC UA-based data network architecture is adopted. The UA server is placed in the workshop production control system and connected to field devices via fieldbus or industrial Ethernet to obtain data from the IO ports of controllers such as PLCs and sensors, enabling data collection from the underlying equipment in the pressing workshop. The UA server aggregates field data and device information, converts it into data that supports the OPC UA protocol, and provides services to the UA client through data management and logical operations.

[0068] The multi-source heterogeneous data synchronization adopts a client-side and server-side mode. The client functions include synchronization rule definition, initialization, data synchronization processing, synchronization data file processing, and FTP file transfer module. The server also includes the above modules, but the data synchronization processing is different from the client.

[0069] The real-time multi-source, heterogeneous data quality assessment and correction technology improves the quality of heterogeneous, multi-source, and multi-modal sensory data. It includes multi-source sensor data quality assessment and dynamic quality assurance during data transmission. This multi-source sensor data quality assessment is based on a mathematical model of the sensor network and sensor acquisition, using optimization algorithms such as machine vision to achieve edge quality assessment and correction for multi-source, multi-modal, heterogeneous data.

[0070] The dynamic data transmission process quality assurance technology adopts an end-to-end dynamic encryption control method to protect the security of data during dynamic transmission.

[0071] The method provided in the embodiments of the present application is described in detail below.

[0072] like Figure 1 As shown in the figure, it is the overall technical architecture. In order to obtain the production information of the whole process of explosive bulk compaction, the real-time acquisition technology of multi-source and multi-modal data of the explosive bulk compaction process is carried out, and its twin system network architecture is built to realize data synchronization and associated fusion processing. It can grasp the change law of the process parameters of the explosive bulk compaction process in real time, and fully monitor and predict the production operation status.

[0073] To address the complex process flow and specific requirements of explosive granular compaction, such as explosion protection, corrosion resistance, operating temperature, and anti-static properties, this system supports the sharing of structural descriptions and operations, using encapsulation concepts to provide a basis for developing data operations and multiple protocols. This allows for data to support iterative exploratory design, storage and management of various design result versions, interactive multi-user collaboration, and concurrent design. Leveraging a unified parsing engine, this system effectively decouples data sources from users, improving data collection and transmission capabilities and enabling real-time acquisition of multi-source and multi-modal data. This system collects online and offline equipment data and process data. Data sources primarily come from production line control systems, image detection systems, and various on-site sensors, including product batches, key parameter information, production plans, and material information. Customized HTTP and Web services are used for data exchange. Table 1 lists the data required for compaction and their accuracy.

[0074] Table 1 Data collected during the pressing process and their accuracy

[0075]

[0076]

[0077] In order to solve the problem of virtual-real data interaction and fusion in digital twins for heterogeneous devices, a unified standardized virtual-real communication framework and protocol should be established. Figure 2 As shown, it supports complex data built-in, cross-platform operations, and provides a unified address space and services.

[0078] The data network architecture based on OPC UA is adopted. In the data communication network architecture, the UA server is placed in the field control system. The field devices are connected through fieldbus or industrial Ethernet to obtain IO port data of control processor PLC, sensors, etc., thereby realizing data collection of the bottom-level equipment in the workshop.

[0079] The UA server aggregates field data and device information, converts it into data that supports the OPC UA protocol, and provides corresponding services to the UA client through data management and logical operations.

[0080] As an OPC UA client, the digital twin system of the medicine pressing production process obtains corresponding real-time data from the server for data reading, writing, storage, analysis and calculation. On this basis, it can drive various factor models, update the real-time production data of various factors, and further perform analysis and intelligent decision-making.

[0081] The main contradictions in multi-source heterogeneous data are naming conflicts, format conflicts, and structural conflicts. The synchronization requirements and solutions between the source database and the target database need to be synchronized. Secondly, it is necessary to effectively detect and capture data changes. Finally, the captured data needs to be transferred to the target database for data update and completion of data synchronization. Based on the above ideas, the client-server model is adopted. The client function includes five modules: synchronization rule definition, initialization, data synchronization processing, synchronization data file processing, and FTP file transfer. The server also includes the above modules, but its data synchronization processing is different from the client. The distributed heterogeneous database data synchronization system framework is as follows: Figure 3 shown.

[0082] The client's data synchronization processing includes data scanning, data conversion, and data file generation. It scans the changes in the specified data tables of the source database, captures the changed data, and converts the data according to the declarations in the synchronization rules to generate a synchronization data file in XML format.

[0083] The data synchronization processing on the server includes data parsing and data synchronization operations. For the synchronized data files from the client, the server parses the data and creates SQL statements according to the synchronization rules, and updates the data to the target database. The client compresses and encrypts the synchronized data files, and the server decrypts and decompresses the files. File transfer realizes the transmission of synchronized data files from the client to the server.

[0084] Before the digital twin information of the explosive granular pressing process is associated with the model, data fusion is required to obtain the state and specific location information description of the measured model target. The data fusion function framework is as follows: Figure 4 shown.

[0085] First, the data source information obtained by multiple sensors is preprocessed, mainly completing standardization and compression of the data to meet the computing requirements of the algorithm.

[0086] The first level of processing, detection fusion, is a distributed detection problem, which is the information fusion of the signal processing level. The optimal detection threshold is formed according to the selected detection criteria to produce the final detection output.

[0087] The second level of processing, position fusion, involves low-level data processing, including data registration, trajectory association, trajectory fusion, and filter prediction. Data registration involves spatial and temporal registration, aligning the data of different attributes from each sensor in both time and space to ensure that the data has the same time reference and a unified coordinate system. Data association, data fusion, and filter estimation are key steps in position-level data fusion. Data association determines whether the observations from each sensor are of the same target. Data fusion fuses different data from the same target to make the target data more accurate. State estimation uses a filtering algorithm to estimate the state information for the next moment based on the established trajectory. When the next measurement arrives, the trajectory is updated based on the estimated state information.

[0088] The third level of processing is target recognition. Target recognition belongs to identity-level data fusion. It uses pattern recognition-related technologies to complete the target's attribute and identity estimation, which facilitates subsequent data quality assessment.

[0089] The fourth level of fine processing involves optimization and correction. This level of processing is interconnected with the other levels, providing feedback, optimization, control, and evaluation of the other levels. To achieve adaptive system regulation, sensor feedback optimization is incorporated, closing the entire system. This functionally enables multi-objective state prediction and structurally implements closed-loop control.

[0090] In order to solve the uneven data quality in the explosive granular pressing process, the multi-source sensor data quality assessment and processing is based on the mathematical model of the sensor network and sensor acquisition through machine vision and other optimization algorithms to achieve edge quality judgment and correction of multi-source and multi-modal heterogeneous data. The details are as follows:

[0091] Perform mean square error statistics on sensor sampling data and real data based on probability to establish an estimation model;

[0092] Use edge computing algorithms to filter sensor data and estimated data calculated by the estimation model to correct the perception data;

[0093] Based on the accumulated data, data analysis and fusion correction are carried out to improve the data quality of the perception data.

[0094] In order to avoid the data resources such as process technology, process status, instructions, etc. of the explosive bulk compaction process from being lost, tampered with, or leaked during transmission and use, the data transmission process adopts dynamic quality assurance technology and end-to-end dynamic encryption control method to protect the security of data during dynamic transmission.

[0095] like Figure 5As shown in the figure, the implementation process is that the data acquisition end is composed of an initialization module and a data acquisition module. The initialization is responsible for completing the topology structure generation and data security fusion protocol initialization. The acquisition module establishes a secure connection with the server end and waits for update instructions from the server end to perform data acquisition and security fusion. The server end is composed of an initialization module, a data update module, a user registration module, a query module and a back-end database. The initialization module starts the main process, starts the data update module, regularly sends fusion data update requests to the data acquisition end, and responds to the registration and data query requirements of multiple terminals by establishing a multi-threaded Web server.

[0096] The data query end consists of a login module and a query module. After the user logs in through server-side verification, he can query and download the data for which he has permission. The entire network transmission process of the fused data from the collection end to the server and then to the query end is always presented in ciphertext form. The plaintext data only appears on the user end and is decrypted by introducing a local browser plug-in using JavaScript, ultimately achieving secure and dynamic transmission of the fused data.

[0097] The dynamic data transmission process quality assurance technology adopts an end-to-end dynamic encryption control method to protect the security of data during dynamic transmission. The implementation process is that the data acquisition end completes the security fusion of the collected data and establishes a secure connection with the server end. For data collection and security fusion, the server end regularly sends fusion data update requests to the data acquisition end, and responds to the registration and data query requirements of multiple terminals by establishing a multi-threaded Web server. On the data query end, users need to log in through the server end for verification before they can query and download the data they have permission to. The fusion data is always presented in ciphertext during the entire network transmission process from the acquisition end to the server end and then to the data query end, and the plaintext will only appear on the user end.

[0098] In summary, the method for sensing and analyzing characteristic parameters of bulk particles during the molding process provided by this application can build a secure and reliable data acquisition and sensing system based on industrial Ethernet, forming a data transmission method with low-latency synchronous communication. This can provide guarantees for the efficient real-time operation of digital twin models, and can grasp the changing patterns of process parameters during the compaction molding process of bulk explosives in real time, and fully monitor and predict the production operation status. By precisely controlling the key process parameters of the production process, the product quality, performance, and consistency can be effectively improved, ensuring the quality stability of mass-delivered products and meeting the precision damage requirements of future advanced ammunition.

[0099] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0100] Through the description of the above embodiments, it can be seen that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments or certain parts of the embodiments of the present application.

[0101] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for system or system embodiments, since they are basically similar to method embodiments, the description is relatively simple. For relevant parts, refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without expending creative work.

[0102] The above description is only a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention are included in the scope of protection of the present invention.

Claims

1. A method for sensing and analyzing characteristic parameters of granular materials during a forming process, characterized in that: Applied to a UA server, the UA server is arranged in a field control system and is communicatively connected to field equipment; the method comprises: Obtain on-site data and equipment information of the medicine pressing workshop; Converting the field data and the device information into source data supporting the OPC UA protocol, and performing data management and logic operation on the source data to obtain target data; The target data is sent to the UA client so that the digital twin system of the explosive production process deployed on the UA client can use the target data to update the real-time production data of various factors. The real-time production data is used to determine the change pattern of the process parameters of the explosive granular body compression molding process and monitor and predict the production operation status; Saving the source data as a source database and saving the target data as a target database; Receive the synchronization data file sent by the UA client, parse the data in the source database to create SQL statements according to the synchronization rules in the synchronization data file, and update the data to the target database; The UA client scans the changes of the specified data table of the source database, captures the changed data and performs data conversion according to the declaration method in the synchronization rule, and generates the synchronization data file in XML format.

2. The method for sensing and analyzing characteristic parameters of granular materials during molding according to claim 1, characterized in that: The field data and the device information include heterogeneous multi-source multi-modal perception data, and the quality of the heterogeneous multi-source multi-modal perception data is determined and corrected in real time to improve the data quality of the heterogeneous multi-source multi-modal perception data.

3. The method for sensing and analyzing characteristic parameters of granular materials during molding according to claim 2, characterized in that: The heterogeneous multi-source multi-modal perception data quality assessment process adopts a mathematical model based on a sensor network and sensor acquisition through a machine vision optimization algorithm to achieve edge quality judgment and correction of the heterogeneous multi-source multi-modal perception data.

4. The method for sensing and analyzing characteristic parameters of granular materials during molding according to claim 2, characterized in that: The heterogeneous multi-source and multi-modal perception data are associated and fused to realize the association mapping between the digital twin information and the model of the explosive granular compression molding process; synchronous information data is obtained for detection, data association, data fusion, and filtering estimation, and relevant judgments on the target trajectory are made to obtain the position and specific information description of the measured model target.

5. The method for sensing and analyzing characteristic parameters of granular materials during a molding process according to claim 4, characterized in that: The heterogeneous multi-source multi-modal perception data is preprocessed, and the preprocessing includes standardization and compression.

6. The method for sensing and analyzing characteristic parameters of granular materials during molding according to claim 5, characterized in that: The standardization and compression include: The first level of processing is configured as detection fusion to produce the final detection output; The second level of processing is configured as position fusion, wherein the position fusion includes data registration, trajectory association, trajectory fusion and filter prediction; The third level of processing is configured as target recognition, which includes estimating the attributes and identity of the target based on pattern recognition related technologies; The fourth level of fine processing is configured as optimized correction processing, which optimizes the control and evaluation of the feedback of other levels of processing.

7. The method for sensing and analyzing characteristic parameters of granular materials during molding according to claim 5, characterized in that: Performing real-time determination and correction on the heterogeneous multi-source multi-modal sensing data; the real-time determination and correction includes multi-source sensor data quality assessment processing; The quality assessment process includes a mathematical model based on the sensor network and sensor machine vision optimization; including: Perform mean square error statistics on sensor sampling data and real data based on probability to establish an estimation model; Using an edge computing algorithm to perform filtering calculations on the sensor collected data and the estimated data calculated by the estimation model to correct the perception data; Based on the accumulated data, data analysis and fusion correction are carried out to improve the data quality of the perception data.

8. The method for sensing and analyzing characteristic parameters of granular materials during a molding process according to claim 1, characterized in that: Receiving a query request sent by a target data query terminal through a multi-threaded WEB server; the target data query terminal is a data query terminal that has been verified by the WEB server; The target data is sent to the target data query in ciphertext form.

Images