Design method, device, electronic equipment and storage medium for coal mill moving and static ring

Abstract

The present application provides a method, device, electronic device and storage medium for designing the dynamic and static rings of a coal mill, and relates to the technical field of designing the dynamic and static rings of a coal mill. The key points of the technical solution are: receiving the dynamic and static ring design data output by the design platform; obtaining the design scheme identifier of the current design; selecting and loading the rule set corresponding to the design scheme from the preset data mapping rule library; if the application conditions of the rule are met, executing the conversion function defined in the rule, converting the data format of the design platform into the format required by the performance verification tool, and mapping the converted data to the corresponding fields of the performance verification tool data format; after completing the conversion of all applicable rules, automatically sending the final converted data to the performance verification tool. The method, device, electronic device and storage medium for designing the dynamic and static rings of a coal mill provided by the present application have the advantages of improving design efficiency, reducing human errors and shortening the product development cycle.

Description

Technical Field

[0001] The present application relates to the technical field of design of a coal mill movable and stationary ring, and in particular to a design method, device, electronic equipment and storage medium for a coal mill movable and stationary ring. Background Art

[0002] In the field of large-scale industrial equipment manufacturing, design and development platforms are widely used in the design of complex components such as the dynamic and static rings of coal mills. To shorten the R&D cycle, reduce R&D costs, and improve design efficiency, companies usually build unified design and development platforms and tend to reuse existing mature design solutions. For the development of a new generation of coal mill products, the company plans to use the existing multi-series design solutions for the dynamic and static rings of coal mills and adjust and optimize them based on the subtle performance parameter differences of the new products. However, after designers adjust the dynamic and static ring parameters on the design platform, they need to use performance verification tools to evaluate the performance of the adjusted design solution.

[0003] Currently, there are data interface incompatibilities between the performance verification tools established earlier in the enterprise and the new design and development platform. There is a barrier between the design data format output by the design platform and the data format accepted by the performance verification tool. This incompatibility leads to a series of serious problems:

[0004] First, to conduct performance verification, designers had to manually export design platform data and spend a considerable amount of time converting it into a format that the performance verification tool could understand. This manual data conversion process was not only tedious and time-consuming, but also prone to human error. This was especially true when dealing with complex dynamic and static ring design data. The risk of misoperation increased significantly, potentially leading to incorrect transfer of key parameters, thus affecting subsequent performance evaluation results.

[0005] Secondly, to avoid the risks of manual conversion, some companies choose to use multiple verification tools for repeated analysis. However, this approach is also inefficient, increasing software licensing and maintenance costs and prolonging the design cycle. The use of multiple tools also increases the difficulty of managing data consistency, potentially leading to inconsistent results between tools and increasing the complexity of decision-making.

[0006] Furthermore, data format incompatibility severely restricts design efficiency and increases the risk of design errors. This problem is particularly acute when companies frequently reuse and adapt existing designs to accommodate new product models. Designers must repeatedly perform data conversions or multi-tool verification, which not only delays product development but also risks missing market opportunities.

[0007] Furthermore, incompatible data formats limit companies’ ability to fully utilize historical design data. Unable to directly import design data from legacy platforms into new verification tools, companies struggle to quickly evaluate and optimize historical design solutions, reducing the efficiency of design asset reuse and increasing unnecessary duplication of effort.

[0008] In view of the above problems, the existing technology is in urgent need of improvement. Summary of the Invention

[0009] The purpose of this application is to provide a design method, device, electronic equipment and storage medium for a coal mill moving and static ring, which has the advantages of improving design efficiency, reducing human errors and shortening product development cycle.

[0010] In the first aspect, the present application provides a design method for the moving and stationary rings of a coal mill, the technical solution of which is as follows:

[0011] The method is used to convert the design data of the dynamic and static rings of a coal mill between a design and development platform and a performance verification tool, and comprises: receiving the dynamic and static ring design data output by the design platform; obtaining a design scheme identifier of the current design based on the received dynamic and static ring design data output by the design platform; selecting and loading a rule set corresponding to the design scheme from a preset data mapping rule library based on the obtained design scheme identifier; traversing each rule in the loaded rule set and checking whether the application condition of the current rule is satisfied; if the application condition of the rule is satisfied, executing the conversion function defined in the rule, converting the data format of the design platform into the format required by the performance verification tool, and mapping the converted data to the corresponding fields of the data format of the performance verification tool; after completing the conversion of all applicable rules, automatically sending the final converted data to the performance verification tool.

[0012] Furthermore, the present application also proposes that if the application conditions of the rules are met, the conversion function defined in the rules is executed to convert the data format of the design platform into the format required by the performance verification tool, and the converted data is mapped to the corresponding field of the performance verification tool data format. The steps include: if the application conditions of the rules are met, analyzing the data field type and numerical range of the data to be converted; establishing a mapping relationship between the data field and the conversion function, and determining the priority of the conversion function; matching the data field and the conversion function according to the data field type, numerical range, and conversion function priority; executing the matched conversion function, converting the design platform data format into the performance verification tool format, and mapping the converted data to the performance verification tool field.

[0013] Furthermore, the present application also proposes that the steps of establishing a mapping relationship between data fields and conversion functions and determining the priority of conversion functions include: obtaining the error rate records of each conversion function for the data field during the historical conversion process; obtaining the version identifier of the current performance verification tool, and matching the conversion function compatibility constraints corresponding to the version identifier; determining the error transfer weight of each conversion function for the data field based on the error rate records and the compatibility constraints; generating a dynamic priority ranking based on the error transfer weight, the compatibility constraints and the error rate records; and updating the dynamic priority ranking to the corresponding rule set in the data mapping rule library.

[0014] Furthermore, the present application also proposes that the steps of generating dynamic priority ranking based on error transfer weights, compatible constraints and error rate records include: analyzing the parameter sensitivity distribution in historical conversion scenarios according to the error rate records; obtaining the constraint type corresponding to the performance verification tool version identifier, and establishing an association mapping between compatible constraints and parameter sensitivity; generating a multi-dimensional weight allocation coefficient based on the parameter sensitivity distribution, association mapping and error transfer weights; applying the weight allocation coefficient to perform normalized weighted calculations on the error transfer weights, compatible constraints and error rate records to generate a dynamic priority ranking; and associating the dynamic priority ranking with the conversion function identifier in the data mapping rule library.

[0015] Furthermore, the present application also proposes that the steps of mapping the converted data to the fields of the performance verification tool include: analyzing the data to be mapped and identifying missing fields and redundant fields; establishing field mapping rules and defining data completion strategies and redundant elimination strategies; according to the field mapping rules, for the identified missing fields, using preset default values ​​or calculation results based on related fields to complete the data and eliminate redundant fields; mapping the data after completion and elimination to the corresponding fields of the performance verification tool.

[0016] Furthermore, the present application also proposes that the step of obtaining the design scheme identification of the current design based on the dynamic and static ring design data output by the received design platform includes: parsing the dynamic and static ring design data output by the design platform, and extracting metadata fields containing design scheme category information; establishing design scheme identification priority judgment rules, including at least one weight factor of the version newness and parameter coverage; according to the priority judgment rules, filtering out the valid identification with the highest priority from the extracted metadata fields; according to the valid identification with the highest priority, filtering out the rule subset related to it from the preset data mapping rule library; constructing a key parameter feature vector, which includes the range characteristics of dynamic and static ring geometric parameters; calculating the similarity between the feature vector and the preset identification definition in the rule subset; based on the similarity calculation result, selecting the best matching design scheme identification as the unique identification of the current design.

[0017] Furthermore, the present application also proposes that the steps of constructing a key parameter characteristic vector, which includes the range characteristics of the dynamic and static ring geometric parameters, include: obtaining the current operating parameters, dynamic and static ring material properties and coal mill model data; determining the sensitivity of each dynamic and static ring geometric parameter to the design scheme identification based on the obtained operating parameters, dynamic and static ring material properties and coal mill model data; based on the determined sensitivity, selecting several dynamic and static ring geometric parameters with the highest sensitivity; and constructing a characteristic vector including the selected dynamic and static ring geometric parameter range.

[0018] Furthermore, the present application also proposes a design device for the dynamic and static rings of a coal mill, which is used to convert the design data of the dynamic and static rings of a coal mill between a design and development platform and a performance verification tool. The device includes: a data receiving module, which is used to receive the dynamic and static ring design data output by the design platform; an identification acquisition module, which is used to obtain the design scheme identification of the current design based on the received dynamic and static ring design data output by the design platform; a rule set selection module, which is used to select and load the rule set corresponding to the design scheme from a preset data mapping rule library based on the acquired design scheme identification; a rule traversal module, which is used to traverse each rule in the loaded rule set and check whether the application conditions of the current rule are met; a data conversion module, which is used to execute the conversion function defined in the rule if the application conditions of the rule are met, convert the data format of the design platform into the format required by the performance verification tool, and map the converted data to the corresponding field of the data format of the performance verification tool; a data sending module, which is used to automatically send the final converted data to the performance verification tool after completing the conversion of all applicable rules.

[0019] Furthermore, the present application also proposes an electronic device, comprising a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the above method are executed.

[0020] Furthermore, the present application also proposes a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the above method are executed.

[0021] From the above, it can be seen that the present application provides a design method, device, electronic device and storage medium for the dynamic and static ring of a coal mill, which are used to convert the design data of the dynamic and static ring of a coal mill between a design and development platform and a performance verification tool. The method includes receiving the dynamic and static ring design data output by the design platform, obtaining the design scheme identifier of the current design, selecting and loading the corresponding rule set, traversing the rules and executing the conversion function that meets the conditions, converting the data format of the design platform into the format required by the performance verification tool, and automatically sending the converted data to the performance verification tool. Through the automated data conversion process, manual operations are reduced, design efficiency is improved, human errors are reduced, and the product development cycle is shortened. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic flow chart of a design method for the moving and stationary rings of a coal mill provided in this application.

[0023] Figure 2 This is a structural schematic diagram of a design device for the moving and stationary rings of a coal mill provided in this application.

[0024] In the figure: 210, data receiving module; 220, identification acquisition module; 230, dynamic and static ring design data; 240, rule set selection module; 250, rule traversal module; 260, data conversion module; 270, data sending module. DETAILED DESCRIPTION

[0025] The technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of the embodiments. The components of the present application generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application for which protection is claimed, but merely represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of this application.

[0026] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and should not be understood as indicating or implying relative importance.

[0027] In the field of large-scale industrial equipment manufacturing, design and development platforms are widely used in the design of complex components such as the moving and static rings of coal mills. In order to shorten the R&D cycle, reduce R&D costs, and improve design efficiency, companies usually build a unified design and development platform and tend to reuse existing mature design solutions. However, there is a problem of data interface incompatibility between the performance verification tools established earlier by companies and the new design and development platform. There is a barrier between the design data format output by the design platform and the data format accepted by the performance verification tool. This forces designers to manually export the design platform data and spend a lot of time converting it into a format that can be recognized by the performance verification tool, or use multiple sets of verification tools for repeated analysis. In this case, how to convert the design data of the moving and static rings of coal mills between the design and development platform and the performance verification tool has become a technical problem that needs to be solved urgently.

[0028] This data format incompatibility issue seriously affects the efficiency of design iterations. During a design cycle, engineers may need to make dozens of design adjustments and performance verifications. If each verification requires several hours of data conversion, the cumulative effect may extend the entire project cycle by weeks or even months. What's more serious is that human errors are easily introduced during the manual data conversion process. For example, during an important design verification, due to a unit conversion error, the CFD analysis results deviated seriously from the actual situation, resulting in major adjustments to the design plan, which directly affected the project schedule and cost. In addition, this inefficient data conversion process also limits engineers' attempts at more innovative designs, because every minor parameter adjustment requires tedious data processing for verification. This not only reduces design flexibility, but may also lead to the loss of potential performance optimization opportunities.

[0029] In this regard, refer to Figure 1 This application proposes a design method for a coal mill movable and stationary ring, which is used to convert coal mill movable and stationary ring design data between a design and development platform and a performance verification tool. The method includes:

[0030] S110, receiving dynamic and static ring design data output by the design platform;

[0031] S120, obtaining a design scheme identifier of the current design based on the received dynamic and static ring design data output by the design platform;

[0032] S130, selecting and loading a rule set corresponding to the design scheme from a preset data mapping rule library according to the obtained design scheme identifier;

[0033] S140, traverse each rule in the loaded rule set and check whether the application condition of the current rule is met;

[0034] S150. If the application condition of the rule is met, executing the conversion function defined in the rule, converting the data format of the design platform into the format required by the performance verification tool, and mapping the converted data to the corresponding field of the performance verification tool data format;

[0035] S160. After completing the conversion of all applicable rules, the final converted data is automatically sent to the performance verification tool.

[0036] The design platform refers to a software tool used for the design of the moving and static rings of a coal mill. Specifically, it can be implemented using a CAD system or dedicated parametric design software. It generates and outputs design data such as the geometric parameters and material properties of the moving and static rings. In this application, the design platform serves as the data source, providing the original design information that needs to be converted.

[0037] The performance verification tool refers to analysis software used to evaluate the performance of the coal mill's moving and static rings. This can be implemented using CFD analysis tools or finite element analysis software, requiring input data in a specific format for performance simulation and evaluation. In this application, the performance verification tool serves as the target of data conversion and has specific requirements for the data format.

[0038] The design scheme identifier is an identifier used to uniquely identify the current design scheme. Specifically, it can be implemented as a version number, project code, or a combination of characteristic parameters. It is used to determine the applicable data conversion rules. In this application, the design scheme identifier serves as the key basis for selecting the correct conversion rules, ensuring the targeted data conversion.

[0039] The data mapping rule base refers to a database that stores data conversion rules corresponding to various design solutions. Specifically, it can be implemented using a relational database or structured files. It contains data format conversion rules for different design solutions. In this application, the data mapping rule base provides a flexible and scalable set of conversion rules.

[0040] A conversion function is a program module that performs specific data format conversion operations. It can be implemented in a scripting language or programming language and is responsible for converting the data format of the design platform into the format required by the performance verification tool. In this application, the conversion function is the key component that actually performs data conversion and ensures the correct conversion of data formats.

[0041] The core innovation of this application lies in the proposed method of automatically converting data formats between the design platform and performance verification tools by establishing a data mapping rule library and dynamically selecting applicable rules. This approach not only resolves the issue of data format incompatibility but also offers high flexibility and scalability, adapting to different design solutions and verification tool requirements.

[0042] The working principle of this application can be described in detail as follows:

[0043] First, the dynamic and static ring design data is received from the design platform. This data usually contains information such as geometric parameters and material properties.

[0044] Next, the received data is analyzed to extract key features to identify the current design. This can involve examining specific metadata fields, analyzing parameter combinations, or using predefined identification algorithms. The identification process takes into account version information, project codes, and key parameter values ​​to accurately determine the design identity.

[0045] Then, based on the identified design scheme, the corresponding rule set is selected from a pre-established data mapping rule library. The rule library is a structured data store containing conversion rules for different design schemes. Each rule set is targeted to a specific design scheme and data format combination, ensuring a targeted conversion process.

[0046] The selected rule set is then iterated over, checking each rule's application conditions. These conditions may include the existence of a data field, a value range, or a specific logical relationship. Only rules that meet the application conditions are executed, ensuring the accuracy and applicability of the conversion process.

[0047] For rules that meet the conditions, the corresponding conversion functions are executed. These functions can perform operations such as unit conversion, data structure reorganization, parameter calculation, or format conversion. The conversion process takes into account the data format differences between the design platform and the performance verification tool, ensuring that the converted data meets the verification tool's requirements.

[0048] Finally, all converted data are integrated and automatically sent to the performance verification tool to ensure that the data can be correctly received and recognized by the verification tool.

[0049] As a preferred embodiment:

[0050] In a coal mill design department, engineers used the latest CAD system to design the rotor and stator ring assemblies. The CAD system output data in XML format, containing parameters such as the rotor ring inner diameter, stator ring outer diameter, and blade angle, all in millimeters and degrees. However, the company's CFD analysis software required CSV input, with parameters in inches and radians.

[0051] The system of the present application first receives an XML file output by the CAD system through a network interface. The system then parses the XML file, extracts the project code "MWGP-2023A" and the version number "V2.1", and identifies the current design solution as "MWGP2023A-V2.1".

[0052] The system then loads the rule set corresponding to "MWGP2023A-V2.1" from the data mapping rule library. This rule set contains data conversion rules for this specific design solution, such as unit conversion rules and parameter mapping rules.

[0053] Iterate through each rule in the rule set. For example, for the inner diameter conversion rule for a moving ring, the system checks the XML for the presence of the "inner_diameter" field and verifies that its value is within a valid range (e.g., 500-2000mm). If the conditions are met, the system executes the corresponding conversion function: converting millimeters to inches (dividing by 25.4) and saving the result to a new data structure.

[0054] Similarly, the system processes other parameters such as the outer diameter of the static ring and the blade angle. For the blade angle, the system not only converts the units (degrees to radians) but also adjusts the parameter representation according to the requirements of the CFD software (such as converting from absolute angles to relative angles).

[0055] Finally, the system organizes all converted parameters into CSV format and automatically sends them to the CFD analysis software through a predefined interface. The entire process is fully automated, greatly improving design efficiency while eliminating the risk of human error.

[0056] In some of the above-mentioned embodiments of the present application, it is proposed that if the application conditions of the rule are met, the conversion function defined in the rule is executed to convert the data format of the design platform into the format required by the performance verification tool, and the converted data is mapped to the corresponding fields of the performance verification tool data format to realize the conversion of the design platform data to the performance verification tool data. However, in this process, since different data fields may require different conversion methods, and the conversion process may involve complex data processing and mapping relationships, if there is no systematic method to handle these conversions and mappings, it may lead to low efficiency and high error rate in the conversion process, or even failure to correctly complete the data conversion.

[0057] In this regard, the present application further proposes that if the application conditions of the rules are met, the data field type and numerical range of the data to be converted are analyzed; a mapping relationship between the data field and the conversion function is established, and the priority of the conversion function is determined; the data field and the conversion function are matched according to the data field type, numerical range, and conversion function priority; the matched conversion function is executed, the design platform data format is converted to the performance verification tool format, and the converted data is mapped to the performance verification tool field.

[0058] This technical solution achieves the systematization and optimization of the data conversion and mapping process through a series of steps. First, by analyzing the field type and numerical range of the data to be converted, a basis is provided for the subsequent selection of conversion functions. Specifically, data type recognition algorithms, such as regular expression matching or machine learning classification models, can be used to automatically identify the type of data fields, for example, classifying fields as numeric, string, date, etc. At the same time, for numerical data, statistical methods can be used to calculate its range, such as minimum, maximum, mean, and standard deviation.

[0059] Furthermore, establishing a mapping relationship between data fields and conversion functions and determining a priority helps select the most appropriate conversion function from multiple possible conversion functions. This mapping relationship can be maintained in a configuration file or database, which contains a list of possible conversion functions for each data field. Priority can be determined based on various factors, such as the conversion function's historical success rate, computational complexity, and compatibility with the target format. For example, each conversion function can be assigned a weight, with a higher weight value indicating a higher priority.

[0060] Next, data fields and conversion functions are matched based on the previously obtained information (field type, value range, and function priority). This ensures that the most appropriate conversion method is found for each field. The matching process can be implemented using a decision tree or rule engine, taking multiple factors into consideration for comprehensive judgment. For example, for a numeric field representing an angle, if its range is between 0 and 360 degrees, a function specifically designed for angle conversion may be preferred over a general numeric conversion function.

[0061] Finally, the matching transformation function is executed and the results are mapped to the target field, completing the entire transformation process. Parallel processing can be used during transformation function execution to process multiple data fields simultaneously, improving transformation efficiency. The transformed data is then precisely placed into the corresponding fields in the performance verification tool according to predefined mapping rules.

[0062] This approach effectively addresses the complexity and diversity of data conversion through a systematic analysis and matching process. It selects the most appropriate conversion method based on the specific characteristics of the data, improving both accuracy and efficiency. Furthermore, by establishing mapping relationships and a priority mechanism, this approach provides flexibility to accommodate diverse data conversion needs.

[0063] As a preferred embodiment, the technical solution of this application can be applied to the conversion of design data for the dynamic and static rings of a coal mill. For example, assume that the dynamic and static ring design data output by the design platform contains the following fields: static ring inner diameter (mm), dynamic ring outer diameter (mm), dynamic and static ring clearance (mm), dynamic ring speed (rpm), etc.

[0064] First, the system analyzes the data field types and ranges. For example, the inner diameter of the static ring and the outer diameter of the dynamic ring are both numeric data, and their ranges may be between 500mm and 2000mm; the gap between the static and dynamic rings is also numeric data, and its range may be between 0.1mm and 10mm; and the rotational speed of the dynamic ring is also numeric data, and its range may be between 100rpm and 1000rpm.

[0065] The system then maps these data fields to available conversion functions. For example, for the inner and outer diameters of the stationary and rotating rings, there might be a unit conversion function (e.g., millimeters to inches) and a rounding function; for the clearance between the stationary and rotating rings, there might be a precision adjustment function; and for the rotating ring speed, there might be a unit conversion function (e.g., rpm to rad / s). The system prioritizes these functions based on historical conversion success rates, computational complexity, and other factors.

[0066] The system then matches the data field based on its specific characteristics and the priority of the conversion function. For example, if the performance verification tool requires imperial units, the system will select a millimeter-to-inch conversion function for the inner diameter of the static ring and the outer diameter of the dynamic ring. If the performance verification tool requires higher accuracy for the gap between the dynamic and static rings, the system will select a precision adjustment function that retains more decimal places.

[0067] Finally, the system executes the corresponding conversion function to convert the design platform data into the format required by the performance verification tool. For example, a stationary ring inner diameter of 1000mm might be converted to 39.37 inches, a dynamic and static ring gap of 2.5mm might be converted to 0.0984 inches (with four decimal places), and a dynamic ring speed of 500rpm might be converted to 52.36rad / s. The converted data is then accurately mapped to the corresponding fields in the performance verification tool.

[0068] In this way, the technical solution of the present application can efficiently and accurately complete the conversion of the design data of the coal mill moving static ring from the design platform to the performance verification tool, greatly improving the design efficiency and reducing the risk of data conversion errors.

[0069] In some of the above-mentioned embodiments of the present application, it is proposed to establish a mapping relationship between data fields and conversion functions, and determine the priority of conversion functions to realize the conversion from the design platform data format to the performance verification tool format. However, in this process, since different conversion functions may have different processing effects on data fields, and the version update of the performance verification tool may cause compatibility issues, how to dynamically optimize the selection and application order of conversion functions has become an urgent problem to be solved. This directly affects the accuracy and efficiency of data conversion, and thus affects the quality and efficiency of the entire coal mill moving and static ring design process.

[0070] In this regard, the present application further proposes obtaining the error rate records of each conversion function for the data field during the historical conversion process; obtaining the version identifier of the current performance verification tool, and matching the conversion function compatibility constraints corresponding to the version identifier; determining the error transfer weight of each conversion function for the data field based on the error rate records and the compatibility constraints; generating a dynamic priority ranking based on the error transfer weight, the compatibility constraints and the error rate records; and updating the dynamic priority ranking to the corresponding rule set in the data mapping rule library.

[0071] This application achieves dynamic adjustment of conversion function priorities by introducing multi-dimensional factors such as historical error rate records, version compatibility constraints, and error propagation weights. Specifically, the error rate records of each conversion function for the data field during the historical conversion process are first obtained. This step can be achieved by establishing an error rate database to record the performance of each conversion function during each conversion process. The error rate can be calculated by comparing the data differences before and after the conversion, for example, using indicators such as root mean square error or mean absolute error.

[0072] Next, obtain the version identifier of the current performance verification tool and match the conversion function compatibility constraints corresponding to the version identifier. The version identifier can be a version number or a specific code, while the compatibility constraints may include the availability of specific functions, parameter requirements, or output formats. This step can be achieved by maintaining a version-compatibility mapping table to ensure that the selected conversion function works properly with the current tool version.

[0073] Furthermore, based on the error rate record and compatibility constraints, the error propagation weights of each conversion function on the data field are determined. These error propagation weights reflect the degree of influence of different conversion functions on the overall conversion result. The calculation method can take into account the error rate, the importance of the data field, and the strictness of the compatibility constraints. For example, a weighted average method can be used to multiply the error rate, the field importance coefficient, and the compatibility coefficient to obtain a comprehensive weight.

[0074] Based on these factors, a dynamic priority ranking is generated. This step can employ a multi-objective optimization algorithm, such as a genetic algorithm or a particle swarm optimization algorithm, to determine the optimal order for applying the transformation functions, taking into account error propagation weights, compatibility constraints, and error rate records. The optimization objective can be set to minimize the overall error rate while satisfying compatibility constraints.

[0075] Finally, the dynamic priority ranking is updated to the corresponding rule set in the data mapping rule library. This ensures that the subsequent transformation process can use the latest optimization results, achieving continuous improvement of the transformation strategy.

[0076] Through this approach, this application achieves intelligent and adaptive conversion function selection. Dynamically adjusting the order in which conversion functions are applied effectively improves the accuracy and efficiency of data conversion. It can adapt to changing requirements across different tool versions and continuously optimize itself based on historical performance, significantly improving the conversion quality of coal mill moving and static ring design data across different platforms.

[0077] When implementing it, you can take the following steps:

[0078] Build an error rate database: For each transformation function, record its historical error rates for different data fields. For example, you can use a two-dimensional matrix, where rows represent transformation functions, columns represent data fields, and matrix elements represent corresponding error rates.

[0079] Version compatibility mapping: Create a version compatibility table to record the compatibility of each performance verification tool version with the conversion function. Boolean values ​​can be used to indicate compatibility (1) or incompatibility (0).

[0080] Error propagation weight calculation: For each conversion function f and data field d, calculate the weight W(f,d) = E(f,d)*I(d)*C(f,v), where E(f,d) is the error rate, I(d) is the field importance coefficient, and C(f,v) is the compatibility coefficient between function f and the current version v.

[0081] Dynamic Prioritization: Genetic Algorithm is used to generate an optimized sequence of transformation functions. The chromosome encoding can be expressed as the order in which the transformation functions are applied, and the fitness function is the inverse of the overall error rate.

[0082] Rule set update: Convert the optimized conversion function sequence into the rule set format and update it to the data mapping rule base.

[0083] Through this implementation, the present application can dynamically adjust conversion strategies in practical applications to adapt to different data features and tool versions, thereby improving the accuracy and efficiency of data conversion for the design of the moving and static rings of coal mills. The advantage of this method is that it can automatically adapt to changes in data and tools, reducing the need for manual intervention. For example, there are three conversion functions: F1: millimeters to inches, F2: degrees to radians, and F3: unit rounding. Analysis of historical data revealed that F1 has an error rate of only 0.1% when processing dimensional data, F2 has an error rate of 0.5% when processing angular data, and F3 has a large error rate fluctuation (1%-5%) for various data types. Furthermore, the currently used CFD tool version 3.2 requires extremely high accuracy for angular data.

[0084] The system automatically adjusts so that F1 prioritizes dimensional data, F2 prioritizes angular data (and may be given a higher precision setting), and F3 may be deprioritized or used only for less important fields.

[0085] The next time engineers need to convert new coal mill design data, this optimized conversion strategy will be automatically applied to improve conversion accuracy and efficiency.

[0086] In some of the above-mentioned embodiments of the present application, a step of generating a dynamic priority ranking based on error transfer weights, compatibility constraints, and error rate records is proposed to determine the priority of the conversion function. However, in this process, relying solely on these factors may not fully take into account the sensitivity differences of different parameters in different scenarios, as well as the new constraints brought about by the version update of the performance verification tool. This may result in the generated priority ranking being inaccurate and inflexible, and unable to adapt to complex and changing design environments and verification requirements.

[0087] In this regard, the present application further proposes to analyze the parameter sensitivity distribution in historical conversion scenarios based on error rate records; obtain the constraint type corresponding to the performance verification tool version identifier, and establish an association mapping between compatible constraint conditions and parameter sensitivity; generate a multi-dimensional weight allocation coefficient based on the parameter sensitivity distribution, association mapping and error transfer weight; apply the weight allocation coefficient to perform normalized weighted calculation on the error transfer weight, compatible constraint conditions and error rate records to generate a dynamic priority ranking; and associate the dynamic priority ranking with the conversion function identifier in the data mapping rule library.

[0088] This application significantly improves the accuracy and adaptability of dynamic priority sorting by introducing parameter sensitivity analysis and multi-dimensional weight allocation. Specifically, the parameter sensitivity distribution in historical conversion scenarios is first analyzed based on error rate records. This step can be achieved by statistically analyzing the impact of each parameter on the conversion results in historical data. For example, statistical methods such as variance analysis or sensitivity index can be used to calculate the contribution of each parameter to the conversion result in different scenarios.

[0089] Furthermore, the constraint types corresponding to the performance verification tool version are obtained, and a mapping is established between compatible constraints and parameter sensitivities. This step can be achieved by creating a mapping table or matrix that lists the constraint types for different tool versions and associates them with the parameter sensitivities obtained in the previous analysis. For example, a specific version of the verification tool may have stricter accuracy requirements for certain geometric parameters, so the weight of these parameters in the sensitivity distribution needs to be increased.

[0090] Based on the parameter sensitivity distribution, correlation mapping, and error propagation weights, a multi-dimensional weight allocation coefficient is generated. This step can be implemented using a weighted average or multi-objective optimization algorithm. Specifically, parameter sensitivity, constraint stringency, and historical error propagation weights can be used as inputs for different dimensions. By setting appropriate weight coefficients, a comprehensive weight allocation coefficient can be calculated.

[0091] The weight distribution coefficients are applied to normalize and weight the error propagation weights, compatibility constraints, and error rate records to generate a dynamic priority ranking. This step can use normalization methods such as min-max normalization or z-score normalization to convert indicators of different scales to the same dimension. The weight distribution coefficients obtained in the previous step are then applied to perform a weighted summation of these normalized indicators to obtain the final priority score for each conversion function.

[0092] Finally, the dynamic priority ranking is associated with the transformation function identifier in the data mapping rule base. This step can be achieved by updating the priority field in the database to ensure that the latest priority ranking is used every time data is transformed.

[0093] Through the above steps, the technical solution of this application can generate dynamic priority rankings more accurately and flexibly. By considering the distribution of parameter sensitivity, this method can identify which parameters have a greater impact on the results in different design situations, thus providing an important basis for subsequent weight allocation. At the same time, by establishing an associated mapping between compatible constraints and parameter sensitivities, it ensures that the generated priority rankings can adapt to the specific requirements of different versions of the tool, improving the compatibility and scalability of the system.

[0094] The introduction of multi-dimensional weighting coefficients makes the final priority ranking more reasonable and accurate. This approach more comprehensively considers various influencing factors, including parameter performance in historical scenarios, the specific requirements of the current tool version, and historical error propagation data. Through normalized weighted calculations, the impact of different factors is balanced while ensuring the comparability and consistency of the calculated results.

[0095] By associating dynamic prioritization with the transformation function identifiers in the data mapping rule base, we ensure the effective application and continuous updating of prioritization results. This means that each time data is transformed, the system uses the latest, most appropriate prioritization for the current scenario, improving both accuracy and efficiency.

[0096] As a preferred embodiment, the parameter sensitivity distribution analysis can be performed using the following steps: First, the value range of each parameter and the corresponding conversion results are extracted from historical data. Then, a large number of sample points are randomly generated within the value range of each parameter using Monte Carlo simulation. Next, each sample point is converted, and the changes in the conversion results are recorded. Finally, the parameter sensitivity distribution is obtained by calculating the contribution of each parameter to the changes in the conversion results.

[0097] For example, suppose that when analyzing the geometric parameters of the static and dynamic rings, it is found that the inner diameter of the static ring is the most sensitive to the conversion results, followed by the outer diameter of the dynamic ring. Then, when generating the multi-dimensional weight distribution coefficients, these two parameters will be assigned higher weights. Specifically, if the sensitivity of the static ring inner diameter is 0.8, the sensitivity of the dynamic ring outer diameter is 0.6, and the sensitivity of other parameters is less than 0.5, then when assigning weights, the weight coefficients of the static ring inner diameter and the dynamic ring outer diameter may be set to 1.5 and 1.2, while the weight coefficients of other parameters may remain around 1.0.

[0098] When mapping compatible constraints to parameter sensitivities, a matrix can be used. For example, a two-dimensional matrix can be created, with rows representing different parameters and columns representing different versions of the performance verification tool. Each element of the matrix represents the constraint strength for a specific parameter under a specific tool version. This mapping approach allows the system to quickly find and update constraints, improving data processing efficiency.

[0099] Through this method, the technical solution of this application can adaptively adjust the priority of the conversion function according to the characteristics of different design scenarios and verification tool versions. This not only solves the problem of imprecise and inflexible priority sorting in the original method, but also provides strong support for the efficient conversion and verification of coal mill moving and static ring design data. This solution can better adapt to complex and changing design environments, improve the accuracy of data conversion, and reduce the need for human intervention, thereby significantly improving design efficiency and reducing the risk of design errors.

[0100] This application further proposes that the steps of generating multi-dimensional weight distribution coefficients based on parameter sensitivity distribution, association mapping and error propagation weights include:

[0101] The parameter sensitivity distribution vector S = (s1, s2, ..., sn) is defined, where si represents the sensitivity of the i-th parameter and n is the total number of parameters. This vector reflects the influence of each parameter on the design result. Furthermore, the association mapping matrix M is defined, where Mij represents the degree of association between the i-th parameter and the j-th constraint. This matrix accounts for the complex relationship between parameters and constraints. Furthermore, the error propagation weight vector W = (w1, w2, ..., wn) is defined, where wi represents the error propagation weight for the i-th parameter. This vector emphasizes the importance of error propagation in weight distribution.

[0102] To adapt to the needs of different versions, this application introduces a version constraint factor V = (v1, v2, ..., vn), where vi represents the applicability of the i-th parameter to the current version. This factor ensures that the generated weight distribution coefficient is compatible with the current version.

[0103] To more accurately capture the complex interactions between various factors, this application defines three functions: f(x) = 1 / (1 + e^(-kx)), g(x) = ln(1 + x), and h(x) = x^p, where k and p are adjustable parameters used to control the degree of nonlinearity. These nonlinear functions are used to handle parameter sensitivity, correlation mapping, and error propagation weights, respectively.

[0104] Based on the above definitions, this application calculates a multi-dimensional weight distribution coefficient vector C = (c1, c2, ..., cn), where ci = vi*[α*f(si)+β*g(Σj Mij)+γ*h(wi)]. α, β, and γ are adjustment coefficients, and α+β+γ=1. This formula comprehensively considers multiple factors, including parameter sensitivity, correlation mapping, error propagation weights, and version constraints, and can fully reflect the complex relationships in the design process of the coal mill's moving and static rings.

[0105] This application uses historical data to calculate the sensitivity distribution of each parameter. Where Yt represents the output result in the tth historical record, Xi,t represents the value of the i-th parameter in the tth historical record, and T is the total number of historical records. This method can more accurately reflect the actual impact of parameters on design results.

[0106] To ensure the rationality of the calculation results, this application sets a series of constraints: 0≤si,wi,ci,vi≤1(i=1,2,...,n), 0≤Mij≤1(i=1,2,...,n; j=1,2,...,m), 0≤α,β,γ≤1, α+β+γ=1, k>0, p>0. These constraints ensure that all parameters and coefficients are within a reasonable range.

[0107] In practical applications, the method of the present application can be implemented by the following steps:

[0108] First, by analyzing historical data, the sensitivity distribution of each parameter is calculated. For example, for the design of the moving and static rings of a coal mill, the past 100 design records can be analyzed to calculate the impact of each geometric parameter (such as ring diameter and groove depth) on the final performance indicators (such as coal mill efficiency and energy consumption).

[0109] Then, a correlation mapping matrix is ​​established. By analyzing design specifications and expert experience, the degree of correlation between each parameter and the constraints (such as strength requirements and machining accuracy) is determined. For example, ring diameter may be highly correlated with strength requirements, while groove depth may be more closely related to coal grinding efficiency.

[0110] Next, based on the error data from historical designs, the error propagation weight for each parameter is determined. For example, if it is found that a small error in the ring diameter causes a large performance fluctuation, the error propagation weight for the ring diameter should be higher.

[0111] Considering that different versions of performance verification tools may have different requirements, this application introduces a version constraint factor. For example, a new version of a verification tool may place more emphasis on certain parameters, so the version constraint factor for these parameters should be higher.

[0112] After determining all necessary vectors and matrices, this application uses the defined nonlinear function and multi-dimensional weight distribution coefficient formula for calculation. For example, assuming that for the ring diameter parameter, the calculated sensitivity is 0.8, the association mapping sum is 2.5, the error propagation weight is 0.6, and the version constraint factor is 0.9, then its weight distribution coefficient may be: 0.9*[0.4*f(0.8)+0.3*g(2.5)+0.3*h(0.6)].

[0113] By using this method, the present application can generate a weight distribution coefficient vector that comprehensively considers multiple factors. This vector can be used for subsequent dynamic priority sorting, thereby optimizing the design process of the coal mill moving and static rings.

[0114] By comprehensively considering multiple factors and introducing nonlinear functions, the proposed technical solution can more accurately reflect the complex relationships in the design of the moving and static rings of a coal mill. Compared to traditional linear weighting methods, the proposed method can better capture the nonlinear interactions between parameters, thereby generating more accurate multi-dimensional weight distribution coefficients.

[0115] By introducing nonlinear functions and multiple influencing factors, the method of the present application can more accurately reflect the importance of each parameter in actual design. By introducing version constraint factors, the method of the present application can better adapt to the requirements of different versions of performance verification tools, and improve the versatility and scalability of the method. Through more accurate weight distribution, designers can optimize key parameters more specifically, thereby improving design efficiency. By considering error transfer weights, the method of the present application can better control design errors and reduce design risks. The multi-dimensional weight distribution coefficient provides more comprehensive information support for design decisions, which helps designers make more reasonable decisions.

[0116] In some of the above-mentioned embodiments of the present application, it is proposed to map the converted data to the performance verification tool fields to map the converted data to the corresponding fields of the performance verification tool data format. However, in this process, there may be problems with missing or redundant data fields, which may cause the performance verification tool to be unable to correctly read or process the converted data, thereby affecting the accuracy of the verification results. In addition, direct mapping may not be able to handle the differences in field definitions between the design platform and the performance verification tool, and a more flexible and intelligent mapping method is needed.

[0117] In this regard, the present application further proposes the steps of mapping the converted data to the fields of the performance verification tool, including: analyzing the data to be mapped, identifying missing fields and redundant fields; establishing field mapping rules, defining data completion strategies and redundant elimination strategies; according to the field mapping rules, for the identified missing fields, using preset default values ​​or calculation results based on related fields to complete the data and eliminate redundant fields; mapping the data after completion and elimination to the corresponding fields of the performance verification tool.

[0118] The technical solution proposed in this application addresses the issues of missing and redundant fields that may arise during the data mapping process through a series of steps. First, the data to be mapped is analyzed to identify missing and redundant fields, laying the foundation for subsequent processing. Specifically, a data structure comparison method can be used to compare the fields of the data to be mapped with the fields required by the performance verification tool, thereby identifying which fields are missing and which fields are redundant.

[0119] Missing fields can be identified by creating a complete list of fields required by the performance verification tool and then checking each field individually to see if they exist in the data to be mapped. If a field does not exist in the data to be mapped, it is marked as missing. For example, if the performance verification tool requires the "Inner Diameter of the Rotating Ring" field but it is not found in the data to be mapped, the "Inner Diameter of the Rotating Ring" field is marked as missing.

[0120] Redundant fields can be identified by performing a reverse check: checking whether each field in the data to be mapped is present in the performance verification tool's required fields list. If a field is not present in the performance verification tool's required fields list, it is marked as redundant. For example, if the data to be mapped contains a "Designer Name" field, but the performance verification tool does not require this information, the "Designer Name" field is marked as redundant.

[0121] Next, establish field mapping rules, including data completion and redundancy elimination strategies, which provide a flexible framework for handling different types of data inconsistencies. Field mapping rules can take the form of key-value pairs, where the key is the field name of the design platform and the value is the corresponding performance verification tool field name. Data completion strategies can include using default values, calculating based on other fields, or inferring from historical data. Redundancy elimination strategies can simply exclude fields marked as redundant from the mapping process.

[0122] Furthermore, actual operations are performed according to established rules: missing fields are supplemented with preset default values ​​or calculated based on related fields, ensuring data integrity. For example, if the "Moving Ring Material Density" field is missing, the preset material density value can be found in the "Moving Ring Material Type" field to supplement it. Alternatively, if the "Moving Ring Volume" field is missing, it can be calculated based on existing moving ring dimension data (such as inner diameter, outer diameter, and height).

[0123] At the same time, redundant fields are eliminated, improving data accuracy and efficiency. This can be achieved by simply not including these fields in the final mapping results. This ensures that only the data truly required by the performance verification tool is transmitted, reducing the burden of data transmission and processing.

[0124] Finally, the processed data is mapped to the corresponding fields of the performance verification tool, completing the entire mapping process. This step can be done by traversing the processed data and assigning the value of each field to the corresponding field of the performance verification tool according to the previously established field mapping rules.

[0125] Thus, the technical solution of this application effectively solves the problems of missing and redundant fields in the data mapping process through an intelligent and adaptive approach. By identifying and addressing data inconsistencies, this method can effectively bridge the data format differences between design platforms and performance verification tools, greatly improving the accuracy and efficiency of data conversion.

[0126] As a preferred embodiment, the technical solution of the present application can be applied to a specific coal mill dynamic and static ring design scenario. Assume that the dynamic and static ring design data output by the design platform contains the following fields: dynamic ring inner diameter, dynamic ring outer diameter, dynamic ring height, static ring inner diameter, static ring outer diameter, static ring height, dynamic ring material type, static ring material type, designer's name, and design date. The fields required by the performance verification tool include: dynamic ring inner diameter, dynamic ring outer diameter, dynamic ring height, static ring inner diameter, static ring outer diameter, static ring height, dynamic ring material density, static ring material density, dynamic ring surface roughness, and static ring surface roughness.

[0127] In this scenario, the system first identifies missing fields (dynamic ring material density, static ring material density, dynamic ring surface roughness, static ring surface roughness) and redundant fields (designer name, design date). Then, the system establishes field mapping rules, for example:

[0128] For the dynamic ring material density and the static ring material density, look for the preset density values ​​according to the material type.

[0129] For the surface roughness of the rotating ring and the surface roughness of the stationary ring, use the default value of 3.2μm.

[0130] Simply remove the designer name and design date fields.

[0131] Next, the system will execute these rules. Assuming that the material type of the dynamic ring is "high chromium cast iron" and the material type of the static ring is "wear-resistant steel", the system will look for the preset material density value. For example, the density of high chromium cast iron is 7.2g / cm 3 , the density of wear-resistant steel is 7.8g / cm 3 The system will use these values ​​to complete the missing density field and the default value of 3.2μm to complete the surface roughness field. At the same time, the system will remove the redundant fields of designer name and design date.

[0132] Finally, the system maps the processed data to the corresponding fields of the performance verification tool, generating a complete and compatible dataset that contains all the fields required by the performance verification tool, with appropriate values ​​for each field.

[0133] In this way, the technical solution of the present application can effectively solve the problems of missing and redundant fields in the data mapping process, and improve the accuracy and efficiency of data conversion. This not only reduces the possibility of human error, but also greatly improves the degree of automation of the design verification process. By ensuring the integrity and accuracy of the data, this method can also improve the reliability of the performance verification results and provide a more reliable basis for the design optimization of the moving and static rings of the coal mill. In addition, the flexibility of this method enables it to adapt to the differences in different types of data structures, enhances the versatility and scalability of the system, and can better cope with new data formats or field requirements that may arise in the future.

[0134] In some of the above-mentioned embodiments of the present application, it is proposed to obtain the design scheme identifier of the current design based on the dynamic and static ring design data output by the received design platform to select and load the rule set corresponding to the design scheme from the preset data mapping rule library. However, in this process, since the dynamic and static ring design data output by the design platform may contain multiple versions or multiple types of design scheme information, it may be difficult to directly obtain a unique design scheme identifier therefrom. In addition, different design schemes may have similar features, making it difficult to ensure the accuracy and uniqueness of the identifier. These problems may affect the selection and loading of subsequent rule sets, and thus affect the accuracy and efficiency of the entire data conversion process.

[0135] In this regard, the present application further proposes to parse the dynamic and static ring design data output by the design platform, extract metadata fields containing design scheme category information; establish design scheme identification priority judgment rules, including at least one weight factor of the version age and parameter coverage range; according to the priority judgment rules, filter out the valid identification with the highest priority from the extracted metadata fields; according to the valid identification with the highest priority, filter out the rule subset related to it from the preset data mapping rule library; construct a key parameter feature vector, which includes the range characteristics of the geometric parameters of the dynamic and static rings; calculate the similarity between the feature vector and the preset identification definition in the rule subset; based on the similarity calculation result, select the best matching design scheme identification as the unique identification of the current design.

[0136] This technical solution addresses the problem of design solution identification through multi-layered screening and precise matching. First, the design data is parsed and metadata fields are extracted to ensure that key information is captured from the source data. This step can be achieved using predefined parsing algorithms, such as regular expression matching or structured data parsing techniques to extract metadata fields containing design solution category information.

[0137] Furthermore, priority judgment rules can be established to consider version recency and parameter coverage to improve the accuracy of identifier selection. Priority judgment rules can use a weighted scoring system, where version recency can be scored based on timestamps or version numbers, and parameter coverage can be scored based on the number and importance of included parameters. For example, version recency can be weighted as 0.6 and parameter coverage as 0.4, and then each candidate identifier can be scored accordingly.

[0138] Use the priority rule to filter the valid identifiers to ensure that the most appropriate candidate identifier is selected. This step can be achieved by comparing the weighted scores of the candidate identifiers and selecting the identifier with the highest score as the valid identifier with the highest priority.

[0139] This allows the relevant rule subsets to be filtered from the rule base, narrowing the scope of subsequent matches. This can be achieved by using the highest-priority valid identifier as a key to quickly index and filter within the pre-set data mapping rule base. For example, a hash table or index tree structure can be used to improve filtering efficiency.

[0140] Specifically, a feature vector is constructed, containing key geometric parameter features, providing the basis for accurate matching. The feature vector can include key geometric parameters such as the inner diameter, outer diameter, height, and angle of the dynamic and static rings. These parameters can be normalized to ensure that parameters of different dimensions can be effectively compared.

[0141] Calculate the similarity between the feature vector and the preset identifier to achieve accurate identifier matching. Similarity calculations can use methods such as cosine similarity or Euclidean distance. For example, when using cosine similarity, the dot product of the feature vector and the vector defined by the preset identifier can be performed, and then divided by the product of the two vectors' moduli to obtain the similarity value.

[0142] Finally, the most matching identifier is selected based on the similarity results to ensure uniqueness and accuracy. A similarity threshold can be set, and only matches exceeding this threshold are considered valid. If multiple matches exceed the threshold, the one with the highest similarity is selected as the final design identifier.

[0143] This method effectively addresses the accuracy and uniqueness of design solution identifiers through multi-layered screening and precise matching. It not only considers the version and coverage of the design data but also leverages geometric parameter features for precise matching, significantly improving the accuracy of identifier selection. The innovation of this method lies in its combination of priority determination and feature similarity calculation, ensuring both efficiency and accuracy.

[0144] This approach effectively avoids subsequent data conversion errors caused by improper identifier selection, improving the reliability and efficiency of the entire design and verification process. For example, when processing multiple versions of static and dynamic ring design data, this method accurately identifies the latest and most relevant design solution, avoiding the use of outdated or inappropriate data for subsequent conversion. Furthermore, through precise feature matching, it can distinguish between seemingly similar but subtly different design solutions, ensuring that the selected identifier truly represents the current design intent.

[0145] As a preferred embodiment, the method of the present application can establish an intelligent middle layer between the design platform and the performance verification tool. This middle layer not only performs the above-mentioned identification acquisition and data conversion process, but also maintains a dynamically updated design solution library and rule set. Each successful identification match and data conversion can be recorded and analyzed to optimize future matching processes. For example, the weight factors of the priority judgment rules can be automatically adjusted based on the matching success rate, or the dimension of the feature vector can be dynamically expanded based on the emergence of new design features.

[0146] Specifically, a feedback mechanism can be set up to allow designers to evaluate the results after each data conversion. If a mismatch or inaccurate conversion occurs, the system can automatically analyze the cause of the error and adjust the identification acquisition strategy accordingly. For example, if certain geometric parameters are found to be more discernible in a specific type of design, the weight of these parameters in the feature vector can be dynamically increased.

[0147] Furthermore, this method can be combined with machine learning algorithms to continuously optimize the accuracy of identifier matching by analyzing large amounts of historical design data and conversion records. For example, algorithms such as support vector machines (SVMs) or random forests can be used to train a classification model based on historical data to predict the most likely design identifier for a given design. This approach can further enhance the intelligence and adaptability of identifier acquisition.

[0148] By implementing the technical solution of this application, designers can significantly reduce the time and effort spent on data format conversion. For example, in a typical coal mill static ring design project, data conversion work that once required several hours of manual processing can now be completed automatically in minutes. This not only improves work efficiency but also greatly reduces the risk of human error. At the same time, due to the improved accuracy of the identification acquisition process, subsequent performance verification becomes more reliable, reducing the number of repeated verifications and design modifications caused by data mismatches.

[0149] In some of the above embodiments of the present application, it is proposed to construct a key parameter feature vector to include the range characteristics of the dynamic and static ring geometric parameters. However, there are some problems in this process. First, how to determine which dynamic and static ring geometric parameters are highly sensitive to the design scheme identification and should be included in the feature vector. Secondly, how to effectively use relevant data such as current operating parameters, dynamic and static ring material properties and coal mill model to guide the construction of the feature vector. Finally, how to ensure that the constructed feature vector can accurately reflect the key features of the design scheme, so as to facilitate subsequent similarity calculation and identification matching.

[0150] In this regard, the present application further proposes to construct a key parameter feature vector, which includes the steps of constructing the range characteristics of the dynamic and static ring geometric parameters, including: obtaining the current operating parameters, dynamic and static ring material properties and coal mill model data; determining the sensitivity of each dynamic and static ring geometric parameter to the design scheme identification based on the obtained operating parameters, dynamic and static ring material properties and coal mill model data; based on the determined sensitivity, selecting several dynamic and static ring geometric parameters with the highest sensitivity; and constructing a feature vector containing the selected dynamic and static ring geometric parameter range.

[0151] This application uses a series of steps to construct a key parameter feature vector containing the characteristics of the range of geometric parameters of the dynamic and static rings. First, the current operating parameters, material properties of the dynamic and static rings, and coal mill model data are obtained. These data provide the basis for subsequent analysis. Then, these data are used to determine the sensitivity of each dynamic and static ring geometric parameter to the design scheme identification. This step can identify which parameters have the greatest impact on the design scheme. Then, based on the determined sensitivity, several dynamic and static ring geometric parameters with the highest sensitivity are selected, which ensures that the feature vector contains the most critical parameters. Finally, a feature vector containing the selected dynamic and static ring geometric parameter range is constructed. This feature vector can accurately reflect the key characteristics of the design scheme.

[0152] There are various ways to obtain current operating parameters, material properties of the dynamic and static rings, and mill model data. For example, this information can be directly extracted from the design platform's database, or acquired in real time from the mill's operating system via a dedicated data acquisition interface. Operating parameters may include mill speed, load, and feed rate; material properties of the dynamic and static rings may include hardness, wear resistance, and thermal expansion coefficient; and mill model data may include basic information such as mill size, capacity, and power.

[0153] Determining the sensitivity of each of the dynamic and static ring geometric parameters to the design signature is a critical step. This can be achieved through mathematical modeling or machine learning algorithms. Specifically, partial differential analysis can be used to quantify sensitivity by calculating the impact of small changes in each geometric parameter on the overall design performance.

[0154] When selecting parameters based on a defined sensitivity, a sensitivity threshold can be set, such as selecting parameters in the top 30% of sensitivity, or selecting parameters with a sensitivity greater than a certain value (e.g., 0.5). This selection process can be dynamic, adjusting to varying design requirements and operating conditions. For example, under certain special operating conditions, it may be necessary to select more parameters to ensure a comprehensive feature vector.

[0155] When constructing eigenvectors, it's important to include not only the specific values ​​of the selected parameters but also their range of variation. For example, for the inner diameter of a dynamic ring, the eigenvector might include its nominal value and the permitted upper and lower range. This approach better captures the flexibility and adaptability of the design.

[0156] The technical solution of this application provides a systematic solution to the problem of constructing characteristic vectors for key parameters. By acquiring comprehensive relevant data, this solution can analyze parameter sensitivity based on actual operating conditions and material properties, which is more accurate and flexible than relying solely on experience or fixed rules. The introduction of sensitivity analysis provides a scientific basis for parameter selection and avoids the potential bias caused by subjective judgment.

[0157] Selecting the most sensitive parameters to construct the eigenvector ensures that the information contained in the vector is the most critical and representative. This not only improves the accuracy of subsequent similarity calculations but also reduces computational complexity by excluding irrelevant or low-sensitivity parameters. Furthermore, by including parameter ranges rather than just fixed values, the eigenvector can better express the variability and adaptability of the design solution, which is particularly important for handling diverse operating conditions and changing requirements.

[0158] A key advantage of this approach is its adaptability. As new data accumulates and operating conditions change, the sensitivity analysis can be regularly updated, dynamically adjusting the composition of the eigenvectors. This allows the system to be continuously optimized to adapt to new design requirements and technological developments.

[0159] As a preferred embodiment, the present application can be implemented as follows: First, the operating data of the past week is obtained from the coal mill operation system, including the average speed (e.g., 980 rpm), average load (e.g., 85%), and average feed rate (e.g., 50 tons / hour). At the same time, the key properties of the dynamic and static ring materials are extracted from the material database, such as hardness (e.g., HRC60), wear resistance coefficient (e.g., 0.95), and thermal expansion coefficient (e.g., 11.5×10^-6 / °C). The coal mill model data includes its rated power (e.g., 500 kW) and maximum processing capacity (e.g., 80 tons / hour).

[0160] Next, using this data, a sensitivity analysis method was used to calculate the sensitivity of the geometric parameters of the dynamic and static rings. The results showed that the sensitivities of the three parameters (dynamic ring inner diameter, static ring outer diameter, and dynamic and static ring clearance) were 0.85, 0.78, and 0.72, respectively, far exceeding those of the other parameters.

[0161] Based on this result, the three most sensitive parameters are selected to construct the feature vector. The feature vector may be in the following form: [dynamic ring inner diameter: 1200mm±5mm, static ring outer diameter: 1500mm±8mm, dynamic and static ring gap: 2.5mm±0.2mm].

[0162] This approach not only considers the specific values ​​of the parameters but also their allowable range of variation, thereby more comprehensively reflecting the characteristics and flexibility of the design solution. The feature vector constructed in this way accurately captures the key characteristics of the design solution, providing a reliable foundation for subsequent similarity calculations and identity matching, thereby improving the efficiency and accuracy of the entire coal mill moving and static ring design process.

[0163] Secondly, refer to Figure 2 The present application also proposes a design device for a coal mill movable and stationary ring, which is used to convert the design data of the coal mill movable and stationary ring between the design and development platform and the performance verification tool. The device includes:

[0164] The data receiving module 210 is used to receive the dynamic and static ring design data output by the design platform;

[0165] The identification acquisition module 220 is used to obtain the design scheme identification of the current design based on the received dynamic and static ring design data output by the design platform;

[0166] A rule set selection module 230 is configured to select and load a rule set corresponding to the design scheme from a preset data mapping rule library according to the acquired design scheme identifier;

[0167] The rule traversal module 240 is used to traverse each rule in the loaded rule set and check whether the application condition of the current rule is met;

[0168] The data conversion module 250 is configured to execute the conversion function defined in the rule if the application condition of the rule is met, convert the data format of the design platform into the format required by the performance verification tool, and map the converted data to the corresponding fields of the performance verification tool data format;

[0169] The data sending module 260 is used to automatically send the final converted data to the performance verification tool after completing the conversion of all applicable rules.

[0170] By automating the data conversion process, manual operations are reduced, design efficiency is improved, human errors are reduced, and thus the product development cycle is shortened.

[0171] In addition, in some preferred embodiments, the design device for the moving and stationary rings of a coal mill proposed in this application can perform any one of the steps in the above method.

[0172] In a third aspect, the present application also provides an electronic device comprising a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps in the above method are executed.

[0173] Through the above technical solution, the processor and the memory are interconnected and communicate with each other through a communication bus and / or other forms of connection mechanisms (not marked), and the memory stores computer-readable instructions executable by the processor. When the electronic device is running, the processor executes the computer-readable instructions to execute the method in any optional implementation method of the above embodiment to achieve the following functions: receiving the dynamic and static ring design data output by the design platform; obtaining the design scheme identifier of the current design based on the received dynamic and static ring design data output by the design platform; selecting and loading the rule set corresponding to the design scheme from the preset data mapping rule library based on the obtained design scheme identifier; traversing each rule in the loaded rule set and checking whether the application condition of the current rule is met; if the application condition of the rule is met, executing the conversion function defined in the rule, converting the data format of the design platform into the format required by the performance verification tool, and mapping the converted data to the corresponding field of the data format of the performance verification tool; after completing the conversion of all applicable rules, the final converted data is automatically sent to the performance verification tool.

[0174] In a fourth aspect, the present application also provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method are executed.

[0175] Through the above technical solution, when the computer program is executed by the processor, the method in any optional implementation method of the above embodiment is executed to achieve the following functions: receiving the dynamic and static ring design data output by the design platform; obtaining the design scheme identifier of the current design based on the received dynamic and static ring design data output by the design platform; selecting and loading the rule set corresponding to the design scheme from the preset data mapping rule library based on the obtained design scheme identifier; traversing each rule in the loaded rule set, and checking whether the application condition of the current rule is met; if the application condition of the rule is met, executing the conversion function defined in the rule, converting the data format of the design platform into the format required by the performance verification tool, and mapping the converted data to the corresponding field of the data format of the performance verification tool; after completing the conversion of all applicable rules, the final converted data is automatically sent to the performance verification tool.

[0176] Among them, the computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0177] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0178] In addition, the units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, and may be located in one place or distributed across multiple network units. Some or all of these units may be selected based on actual needs to achieve the purpose of the solution of this embodiment.

[0179] Furthermore, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0180] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, various modifications and variations of the present application are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A design method for a coal mill movable and stationary ring, for converting design data of a coal mill movable and stationary ring between a design and development platform and a performance verification tool, the method comprising: Receive dynamic and static ring design data output by the design platform; Obtaining a design scheme identifier of the current design based on the received dynamic and static ring design data output by the design platform; According to the obtained design scheme identifier, a rule set corresponding to the design scheme is selected and loaded from a preset data mapping rule library; Traverse each rule in the loaded rule set and check whether the application conditions of the current rule are met; If the application conditions of the rule are met, the conversion function defined in the rule is executed to convert the data format of the design platform into the format required by the performance verification tool, and the converted data is mapped to the corresponding fields of the performance verification tool data format; After completing the conversion of all applicable rules, the final converted data is automatically sent to the performance verification tool; If the application condition of the rule is met, the conversion function defined in the rule is executed to convert the data format of the design platform into the format required by the performance verification tool, and the converted data is mapped to the corresponding field of the performance verification tool data format. The steps include: If the application conditions of the rule are met, analyze the data field type and value range of the data to be converted; Establish the mapping relationship between data fields and conversion functions, and determine the priority of conversion functions; Match data fields and conversion functions based on data field type, value range, and conversion function priority; Execute the matching conversion function, convert the design platform data format to the performance verification tool format, and map the converted data to the performance verification tool field; The steps of establishing a mapping relationship between data fields and conversion functions and determining the priority of the conversion functions include: Obtain the error rate records of each conversion function on the data field during the historical conversion process; Obtain the version ID of the current performance verification tool and match the conversion function compatibility constraint corresponding to the version ID; According to the error rate record and compatibility constraints, the error transfer weight of each conversion function to the data field is determined; Generate dynamic priority ranking based on error propagation weights, compatibility constraints and error rate records; Update the dynamic priority sorting to the corresponding rule set in the data mapping rule base.

2. According to the design method of the coal mill movable and static ring according to claim 1, the step of generating a dynamic priority ranking based on the error transfer weight, the compatibility constraint condition and the error rate record comprises: Analyze parameter sensitivity distributions in historical conversion scenarios based on error rate records; Obtain the constraint type corresponding to the performance verification tool version identifier and establish an association mapping between compatible constraint conditions and parameter sensitivity; Generate multi-dimensional weight allocation coefficients based on parameter sensitivity distribution, correlation mapping and error transfer weights; Apply weight distribution coefficients to perform normalized weighted calculations on error transfer weights, compatibility constraints, and error rate records to generate dynamic priority rankings; Associate the dynamic priority ordering with the transformation function identifier in the data mapping rule base.

3. The method for designing the dynamic and static rings of a coal mill according to claim 1, wherein the step of mapping the converted data to the performance verification tool field comprises: Analyze the data to be mapped and identify missing and redundant fields; Establish field mapping rules and define data completion strategies and redundant elimination strategies; According to the field mapping rules, for the missing fields identified, data is completed using preset default values ​​or calculation results based on related fields, and redundant fields are eliminated; Map the completed and eliminated data to the corresponding fields of the performance verification tool.

4. According to the method for designing the dynamic and static rings of a coal mill according to claim 1, the step of obtaining the design scheme identifier of the current design based on the received dynamic and static ring design data output by the design platform comprises: Parse the dynamic and static ring design data output by the design platform and extract metadata fields containing design scheme category information; Establishing a design solution identification priority judgment rule, including at least one of the weight factors of version newness and parameter coverage; According to the priority judgment rules, the valid identifier with the highest priority is filtered out from the extracted metadata fields; According to the valid identifier with the highest priority, a rule subset related to the identifier is screened out from a preset data mapping rule library; Construct key parameter feature vectors, including the range characteristics of the dynamic and static ring geometric parameters; Calculating the similarity between the feature vector and the preset identification definition in the rule subset; Based on the similarity calculation results, the design scheme identifier with the best match is selected as the unique identifier of the current design.

5. According to the design method of the coal mill dynamic and static rings according to claim 4, the step of constructing the key parameter characteristic vector containing the range characteristics of the geometric parameters of the dynamic and static rings comprises: Obtain current operating parameters, dynamic and static ring material properties, and coal mill model data; Based on the acquired operating parameters, material properties of the dynamic and static rings, and coal mill model data, the sensitivity of each dynamic and static ring geometric parameter to the design scheme identification is determined; Based on the determined sensitivity, several geometric parameters of the dynamic and static rings with the highest sensitivity are selected; Construct a feature vector containing the selected range of geometric parameters of the dynamic and static rings.

6. A design device for a coal mill moving and stationary ring, used for converting design data of a coal mill moving and stationary ring between a design and development platform and a performance verification tool, characterized in that: The device includes: A data receiving module is used to receive the dynamic and static ring design data output by the design platform; The identification acquisition module is used to obtain the design scheme identification of the current design based on the dynamic and static ring design data output by the received design platform; A rule set selection module is used to select and load a rule set corresponding to the design scheme from a preset data mapping rule library according to the obtained design scheme identifier; The rule traversal module is used to traverse each rule in the loaded rule set and check whether the application conditions of the current rule are met; A data conversion module is used to execute the conversion function defined in the rule if the application condition of the rule is met, convert the data format of the design platform into the format required by the performance verification tool, and map the converted data to the corresponding field of the performance verification tool data format; A data sending module is used to automatically send the final converted data to the performance verification tool after completing the conversion of all applicable rules; If the application condition of the rule is met, the conversion function defined in the rule is executed to convert the data format of the design platform into the format required by the performance verification tool, and the converted data is mapped to the corresponding field of the performance verification tool data format. The steps include: If the application conditions of the rule are met, analyze the data field type and value range of the data to be converted; Establish the mapping relationship between data fields and conversion functions, and determine the priority of conversion functions; Match data fields and conversion functions based on data field type, value range, and conversion function priority; Execute the matching conversion function, convert the design platform data format to the performance verification tool format, and map the converted data to the performance verification tool field; The steps of establishing a mapping relationship between data fields and conversion functions and determining the priority of the conversion functions include: Obtain the error rate records of each conversion function on the data field during the historical conversion process; Obtain the version ID of the current performance verification tool and match the conversion function compatibility constraint corresponding to the version ID; According to the error rate record and compatibility constraints, the error transfer weight of each conversion function to the data field is determined; Generate dynamic priority ranking based on error propagation weights, compatibility constraints and error rate records; Update the dynamic priority sorting to the corresponding rule set in the data mapping rule base.

7. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps of the method according to any one of claims 1 to 5 are executed.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are executed.

Images