Batch production process optimization system for axial plunger pump based on digital twinning

Abstract

The application discloses an axial plunger pump batch production process optimization system based on digital twinning, belongs to the field of digital twinning, and comprises: a data acquisition module, which is used for obtaining a plurality of sensing data sets; a model construction module, which is used for constructing a statistical submodel; a twinning integration module, which is used for constructing a digital twinning model of a target axial plunger pump; a simulation execution module, which is used for simulating the target axial plunger pump to generate a plurality of batch simulation results; a scheme evaluation module, which is used for optimizing and evaluating a plurality of batch production schemes to generate a production batch optimization scheme; and a process optimization module, which is used for intelligently optimizing the batch production process of the target axial plunger pump. The application solves the technical problems of low production efficiency and unstable product quality in the existing axial plunger pump batch production process, achieves the technical effects of improving the axial plunger pump batch production efficiency and ensuring the product quality stability by constructing a digital twinning model and performing simulation optimization.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of digital twinning, in particular to an axial plunger pump batch production process optimization system based on digital twinning. BACKGROUND

[0002] The performance and quality of the axial plunger pump are largely dependent on the machining accuracy and assembly quality of the internal components. However, in the batch production process of the axial plunger pump, due to factors such as changes in production environment, wear and tear of equipment, and differences in operation, it is difficult to ensure that the machining and assembly of the components of each pump can reach the ideal state, thereby causing instability in product performance and quality. The traditional production mode uses pre-set process parameters, which cannot be adjusted in a timely manner according to the actual production situation. Therefore, in the batch production process, due to the lack of real-time monitoring and dynamic optimization of the physical properties of the pump and the production process, the production efficiency of the batch production of the axial plunger pump is affected, and the consistency of the product quality cannot be guaranteed. SUMMARY

[0003] The present application provides an axial plunger pump batch production process optimization system based on digital twinning, which aims to solve the technical problems of low production efficiency and unstable product quality caused by the lack of real-time monitoring and dynamic optimization of the physical properties of the pump and the production process in the existing batch production process of the axial plunger pump.

[0004] The axial plunger pump batch production process optimization system based on digital twinning disclosed in the present application comprises: a data acquisition module for obtaining a plurality of sensing data sets, the plurality of sensing data sets comprising a first sensing data set and a second sensing data set; a model construction module for constructing a physical sub-model based on the first sensing data set and a statistical sub-model based on the second sensing data set; a twin integration module for integrating the physical sub-model and the statistical sub-model to construct a digital twin model of a target axial plunger pump; a simulation execution module for simulating the target axial plunger pump through the digital twin model by executing a plurality of batch production schemes to generate a plurality of batch simulation results; a scheme evaluation module for optimizing and evaluating the plurality of batch production schemes according to the plurality of batch simulation results to generate a production batch optimization scheme; and a process optimization module for intelligently optimizing the batch production process of the target axial plunger pump according to the production batch optimization scheme for the target production batch.

[0005] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0006] The technical scheme is characterized in that: the data acquisition module is used to obtain a plurality of sensing data sets, including a first sensing data set and a second sensing data set, to lay a data foundation for subsequent construction of a digital twin model; the model construction module is used to construct a physical submodel based on the first sensing data set and construct a statistical submodel based on the second sensing data set, to realize comprehensive digital modeling of the axial piston pump and the production process thereof; the twin integration module is used to integrate the physical submodel and the statistical submodel, to construct the digital twin model of the axial piston pump, which comprehensively reflects the physical characteristics and production process characteristics of the axial piston pump, and provides an integrated digital platform for subsequent production process optimization; the simulation execution module is used to simulate a plurality of batch production schemes through the digital twin model, to generate corresponding batch simulation results, to quickly and low-costly evaluate the feasibility and effect of different production schemes, and to provide decision support for production process optimization; the scheme evaluation module is used to optimize and evaluate the plurality of batch production schemes according to the batch simulation results, to generate an optimal production batch optimization scheme, and to find an optimal production batch and process parameter combination; and the process optimization module is used to execute the production batch optimization scheme according to the target production batch, to intelligently optimize the batch production process of the axial piston pump, to realize dynamic optimization control of the production process, and to ensure the quality and efficiency of batch production, thereby solving the technical problems of low production efficiency and unstable product quality in the existing batch production process of the axial piston pump due to the lack of real-time monitoring and dynamic optimization of the physical characteristics of the pump and the production process, and achieving the technical effects of improving the batch production efficiency of the axial piston pump and ensuring the stability of product quality through construction of a digital twin model and simulation optimization.

[0007] The above description is only a summary of the technical scheme of the present application. In order to more clearly understand the technical means of the present application, the above and other purposes, characteristics and advantages of the present application can be implemented in accordance with the content of the specification, and in order to make the above and other purposes, characteristics and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0008] Figure 1 A structural schematic diagram of an axial piston pump batch production process optimization system based on digital twinning is provided for the embodiments of the present application.

[0009] Figure 2 A flowchart of generating a plurality of batch simulation results in an axial piston pump batch production process optimization system based on digital twinning is provided for the embodiments of the present application.

[0010] Explanation of reference signs: data acquisition module 11, model construction module 12, twin integration module 13, simulation execution module 14, scheme evaluation module 15, process optimization module 16. DETAILED DESCRIPTION

[0011] The technical scheme provided in the application has the following general idea:

[0012] The embodiment of the application provides an axial plunger pump batch production process optimization system based on digital twinning, realizes digital and intelligent optimization of the whole production process by constructing a digital twinning model of the axial plunger pump.

[0013] Specifically, first, the physical property data and the production process data of the axial plunger pump are acquired through the data acquisition module, then the physical sub-model and the statistical sub-model are constructed through the model construction module, and finally the two types of sub-models are integrated into a complete digital twinning model through the twinning integration module. On this basis, the simulation execution module simulates different batch production schemes by using the digital twinning model to generate multiple batch simulation results. The scheme evaluation module optimizes and evaluates the production schemes according to the multiple batch simulation results to generate an optimal production batch optimization scheme. Then, the process optimization module intelligently optimizes and dynamically controls the batch production process according to the production batch optimization scheme.

[0014] To sum up, the application realizes the intelligentization of the whole process of the axial plunger pump batch production from data acquisition, modeling simulation to process optimization, effectively improves the production efficiency and the stability of product quality, and realizes efficient and high-quality axial plunger pump batch production.

[0015] After introducing the basic principle of the application, the non-limiting embodiments of the application will be specifically introduced in combination with the drawings of the specification.

[0016] As shown in Figure 1 The embodiment of the application provides an axial plunger pump batch production process optimization system based on digital twinning, which comprises:

[0017] The data acquisition module 11 is used to obtain a plurality of sensing data sets, and the plurality of sensing data sets include a first sensing data set and a second sensing data set.

[0018] Specifically, first, a plurality of types of sensors such as pressure sensors, temperature sensors, and flow sensors are deployed on the batch production site of the axial plunger pump to collect various data in the production process in real time. In the process of collecting data, the data acquisition module 11 divides the collected data into two parts, i.e., the first sensing data set and the second sensing data set, according to the types and purposes of the data. The first sensing data set includes data related to the physical properties of the axial plunger pump, such as the geometric dimensions of the pump and the material properties. The second sensing data set mainly includes data related to the production process, such as the operating parameters of the production equipment and the environmental conditions.

[0019] Through the classification and management of the collected sensor data, the data acquisition module 11 provides high-quality, multi-dimensional data support for subsequent digital twin model construction and production process optimization, laying a data foundation for the intelligent optimization of the batch production process of the axial piston pump.

[0020] The model construction module 12 is configured to construct a physical sub-model based on the first set of sensor data and a statistical sub-model based on the second set of sensor data.

[0021] Specifically, first, the model construction module 12 parses the first set of sensor data acquired by the data acquisition module 11 and extracts information related to the physical characteristics of the axial piston pump, such as geometric structure data and material attribute data of the pump. Then, based on the extracted geometric structure data and material attribute data, combined with pre-set boundary conditions and constraints, a physical sub-model that can reflect the real physical characteristics of the axial piston pump is constructed through finite element analysis, multi-body dynamics simulation, etc., simulating the stress, deformation, fatigue, etc. behavior of the axial piston pump under actual working conditions, providing a basis for subsequent production process optimization. At the same time, the model construction module 12 parses the second set of sensor data acquired by the data acquisition module 11 and extracts information related to the production process, such as process parameters of production equipment. Based on these data, through data mining, machine learning, etc. technology, a statistical sub-model that can reflect the internal relationship between various factors in the batch production process of the axial piston pump is constructed, quantifying the influence of various factors in the production process on the performance of the axial piston pump, providing data-driven decision support for the optimization of production process parameters.

[0022] Through the synergistic effect of the physical sub-model and the statistical sub-model, the model construction module 12 can comprehensively and accurately describe the physical characteristics and production process of the axial piston pump, providing support for subsequent digital twin model integration and production process optimization.

[0023] The twin integration module 13 is configured to integrate the physical sub-model and the statistical sub-model to construct a digital twin model of the target axial piston pump.

[0024] Specifically, first, the twin integrated module 13 standardizes the physical sub-model and the statistical sub-model built by the model building module 12, unifies the data format and interface specification, so as to facilitate seamless integration and data interaction between models. Then, through multi-level and multi-granularity model fusion technology, the physical sub-model and the statistical sub-model are deeply integrated to build a digital twin model that can fully reflect the actual characteristics of the target axial piston pump. During the integration process, attention is paid to the matching and synchronization of data flow and information flow between models to ensure that simulation analysis at the physical level and statistical modeling at the data level can be closely combined, verified and dynamically updated. Through model integration, the digital twin model reflects all characteristics of the target axial piston pump in the virtual space, such as geometry, material properties, and operating state, and can be dynamically corrected and optimized based on real-time production data, so that it always maintains high consistency with the physical entity. Through the high-precision and dynamically updated digital twin model, a reliable and efficient digital test platform is provided for subsequent production process simulation and optimization, and tool support is provided for the whole process optimization of the axial piston pump batch production.

[0025] The simulation execution module 14 is configured to execute a plurality of batch production schemes on the target axial piston pump through the digital twin model to generate a plurality of batch simulation results.

[0026] Specifically, first, according to the production requirements and equipment capacity of the axial piston pump, a plurality of batch production schemes are formulated, each corresponding to a different combination of production batch, production rhythm, equipment configuration, etc. Then, the simulation execution module 14 inputs the plurality of batch production schemes into the digital twin model, and through parameter mapping and logic control, constructs a simulation scene in the virtual space that highly corresponds to the physical production environment. The digital twin model simulates each batch production scheme realistically based on these simulation scenes, virtually reproducing the entire production process of the axial piston pump under different production schemes. During the simulation process, the digital twin model simulates the machining, assembly, testing, etc. of the axial piston pump product in real time, and dynamically presents the equipment operating state, material flow, product quality, etc. key information. At the same time, it monitors and records various parameters and performance indicators in the simulation process to form a complete simulation result data set. After high-fidelity simulation, the simulation execution module 14 generates batch simulation results corresponding to each batch production scheme, obtaining a plurality of batch simulation results, which not only include prediction data of the quality and performance of the axial piston pump product, but also include production management-related statistical information such as production efficiency, equipment utilization, and material consumption, fully reflecting the execution effect and optimization space of each batch production scheme.

[0027] By executing the batch simulation function of the simulation execution module 14, the feasibility and advantages and disadvantages of different batch production schemes can be quickly and low-cost evaluated and compared in a virtual space, greatly reducing the risk and iteration cost of physical trial production, and providing decision basis for optimization of the batch production process of the axial piston pump.

[0028] The scheme evaluation module 15 is used for optimizing and evaluating the plurality of batch production schemes according to the plurality of batch simulation results, and generating a production batch optimization scheme.

[0029] Specifically, first, the scheme evaluation module 15 summarizes and analyzes the plurality of batch simulation results generated by the simulation execution module 14, extracts key data and indicators related to production scheme optimization, such as production efficiency, product qualification rate, energy consumption, etc. Then, the scheme evaluation module 15 quantitatively evaluates and sorts the advantages and disadvantages of each batch production scheme based on these key data and indicators. Through the set evaluation rules and weight factors, the influence degree of each indicator on the production scheme optimization is comprehensively considered, and the comprehensive score and ranking of each scheme are calculated. On the basis of evaluation and sorting, the top-ranking high-quality schemes are further analyzed, and the common characteristics and optimization rules of the production batch, process parameter setting, etc. are summarized, and the optimization strategy and improvement direction are generated accordingly, guiding the dynamic adjustment and optimization of the production batch and process parameters. Then, the scheme evaluation module 15 applies the optimization strategy to the original plurality of batch production schemes, corrects and optimizes the key parameters, and continuously improves the performance and reliability of the optimization scheme through repeated iteration and simulation verification, until an optimized production batch scheme is generated, which serves as a basis for improving the batch production process of the axial piston pump.

[0030] Through the optimization evaluation of the scheme evaluation module 15, the advantages and disadvantages of different batch production schemes are objectively and efficiently evaluated, and a practical optimization scheme is automatically generated according to the evaluation results, providing intelligent decision support for the batch production of the axial piston pump, effectively improving the production efficiency and product quality, and reducing the production cost and resource consumption.

[0031] The process optimization module 16 is used for intelligently optimizing the target axial piston pump batch production process according to the target production batch and the production batch optimization scheme.

[0032] Specifically, first, the production batch optimization scheme generated by the scheme evaluation module 15 is matched with the target production batch to ensure that the optimization scheme can be applied to the current production task and requirements. Then, the process optimization module 16 extracts the key parameters and setting values in the production batch optimization scheme, such as production rhythm, equipment parameters, process parameters, etc., and issues them to the control system and execution equipment in the production field to optimize and dynamically adjust the axial plunger pump batch production process in real time. During the optimization process, the execution effect of the production batch optimization scheme is monitored and predicted in real time, and the optimization parameters are dynamically corrected according to the feedback data to ensure that the production process is always in the optimal state.

[0033] Through the intelligent optimization of the process optimization module 16, the digital twin technology is deeply integrated with the field production control, realizing the full-process optimization and dynamic adjustment of the axial plunger pump batch production process, and improving the production efficiency and product quality.

[0034] Further, the embodiments of the present application also include:

[0035] A plurality of sensing devices are arranged according to the production process of the target axial plunger pump to determine a sensing device group;

[0036] The sensing device group is divided according to the sensing target to generate a first sensing device group and a second sensing device group;

[0037] Production batch data is retrieved to determine a plurality of production batches, and a target axial plunger pump is matched based on the plurality of production batches to determine a target production batch;

[0038] According to the target production batch and the physical characteristics of the target axial plunger pump, the first sensing device group is used to perform batch traversal on the target axial plunger pump to generate a first sensing data set;

[0039] According to the target production batch and the production process, the second sensing device group is used to perform batch traversal on the target axial plunger pump to generate a second sensing data set.

[0040] In a feasible implementation, first, according to the key processes and links in the production process of the axial piston pump, various types of sensors such as pressure sensors, temperature sensors, flow sensors, displacement sensors, etc. are installed at corresponding positions on the production line to form a complete sensing device group, realizing comprehensive monitoring and data collection of the whole production process. Then, according to the sensing target, the first sensing device group and the second sensing device group are generated. The first sensing device group monitors the physical characteristic parameters of the axial piston pump, such as pump body geometric dimensions, material properties, etc., and obtains relevant data through optical size measurement, ultrasonic detection, etc. The second sensing device group monitors the production process parameters, such as equipment running state, process parameter execution, etc., and obtains relevant data through vibration monitoring, process parameter collection, etc. Subsequently, production batch data is called to determine multiple production batches, and the target axial piston pump is matched based on the multiple production batches to determine the target production batch. The production batch data records the total production quantity and batch production plan of the axial piston pump, and the target axial piston pump is located in a certain specific production batch. By analyzing the production batch data, the target production batch where the target axial piston pump is located is determined, providing batch reference for subsequent data collection and analysis.

[0041] Subsequently, the first sensing device group is controlled to collect and record the physical characteristic parameters of each target axial piston pump during the production process of the target production batch, and data on pump body geometric structure, material properties, etc. are obtained and summarized to form a first sensing data set. At the same time, the second sensing device group is controlled to collect and record the production process parameters of each target axial piston pump during the production process of the target production batch, and data on equipment running state, process parameter execution, etc. are obtained and summarized to form a second sensing data set.

[0042] Through effective collection and classification of multi-source, heterogeneous data in the batch production process of the target axial piston pump, a data foundation is laid for subsequent digital twin model construction. The first sensing data set and the second sensing data set respectively depict the key attributes and behaviors of the axial piston pump from the two dimensions of physical characteristics and production process, providing necessary data support for fully reflecting its production and manufacturing panorama.

[0043] Further, the embodiments of the application also include:

[0044] analyzing the first sensing data set to obtain geometric structure data and material attribute data of the target axial piston pump;

[0045] setting boundary conditions, performing dynamics analysis based on the geometric structure data and the material attribute data, and constructing the physical sub-model;

[0046] analyzing the second set of sensing data to obtain operation performance data and production sensing data of the target axial piston pump;

[0047] performing regression analysis based on the operation performance data and the production sensing data to construct the statistical sub-model.

[0048] In a feasible implementation, first, the first set of sensing data is preprocessed by data cleaning, feature extraction and the like to extract key data related to physical properties of the target axial piston pump, such as three-dimensional size of the pump body, surface roughness, material density, elastic modulus and the like, to provide accurate parameter input for subsequent physical modeling. Then, based on the obtained geometric structure and material attribute data of the pump body, boundary conditions and constraint conditions are set according to actual working conditions of the target axial piston pump, such as pump inlet pressure, outlet pressure, rotating speed, load and the like. Subsequently, numerical simulation methods such as multi-body dynamics simulation and finite element analysis are used to perform stress analysis, stress and strain calculation, fatigue life prediction and the like on the pump body, to construct a mathematical model that can accurately reflect the physical behavior of the pump body, i.e., the physical sub-model.

[0049] Meanwhile, the second set of sensing data is preprocessed and features are extracted to obtain key data related to actual operation performance and production process of the target axial piston pump, such as pump outlet flow, efficiency, vibration spectrum, production rhythm, equipment working condition and the like, to provide real and reliable sample data for subsequent statistical modeling. Then, based on the obtained operation performance and production process data of the axial piston pump, data mining methods such as multiple regression and time series analysis are used to establish quantitative relationships between various performance indicators and production parameters, to depict key factors and laws affecting pump performance in the production process. Through regression analysis, a statistical prediction model, i.e., the statistical sub-model, is generated to predict and optimize the production and manufacturing process of the axial piston pump.

[0050] Through construction of the physical sub-model and the statistical sub-model, the internal properties and behavior characteristics of the axial piston pump are depicted from mechanism level and data level respectively. Among them, the physical sub-model is based on the first set of sensing data, uses physical laws and numerical simulation techniques to accurately simulate the structural characteristics and mechanical behavior of the pump body, to provide a reliable theoretical tool for product design optimization and performance prediction. The statistical sub-model is based on the second set of sensing data, uses data mining and machine learning techniques to reveal the influence laws of various factors on pump performance in the production process, to provide data-driven decision support for process optimization and quality control. The collaborative integration of the physical sub-model and the statistical sub-model improves the accuracy and practicality of the digital twin model, and lays a foundation for process optimization of batch production of the axial piston pump.

[0051] Further, the embodiments of the application also include:

[0052] constructing a LASSO regression expression:

[0053] ;

[0054] in, To minimize the loss function, The number of samples for operational performance data or production sensor data. The number of features for operational performance data or production sensor data. For the first The true target value of each sample For the first The first sample 1 eigenvalue, For the regression intercept, for The weighting coefficients, For regularization parameters, and Let them be two positive integers that can be incremented.

[0055] The LASSO regression expression is used to perform regression analysis on the operational performance data and the production sensor data respectively to obtain the minimized loss function;

[0056] The regularization parameters are cross-validated based on the minimized loss function to construct the statistical sub-model.

[0057] In a preferred embodiment, a statistical sub-model is constructed using the LASSO regression algorithm. First, the LASSO regression expression is constructed as follows:

[0058] ;

[0059] in, To minimize the loss function, The number of samples for operational performance data or production sensor data. The number of features for operational performance data or production sensor data. For the first The true target value of each sample For the first The first sample 1 eigenvalue, For the regression intercept, for The weighting coefficients, For regularization parameters, and These are two positive integers that can increase incrementally. The first term in the LASSO regression expression characterizes the sum of squared errors between the model's predicted and actual values, and the second term is the weighted sum of the absolute values ​​of the weight coefficients. The goal of LASSO regression is to find an optimal set of weight coefficients. and intercept such that the loss function is minimized.

[0060] Then, the obtained operating performance data and production sensing data are substituted into the LASSO regression expression respectively, and the weight coefficients and the regression intercept of each feature are estimated by minimizing the loss function . The operating performance data and production sensing data are substituted into the expression in turn to obtain different loss functions and regression coefficients. In order to select the optimal regularization parameter , cross-validation is used to divide the data set into a training set and a validation set, and regression analysis is repeated under different values to calculate the prediction error on the validation set, and the with the smallest prediction error is selected as the optimal parameter. Then, the optimal is used to perform LASSO regression on all data to obtain the final statistical submodel, including the weight coefficients of each feature and the regression intercept.

[0061] Through the construction of the statistical submodel based on LASSO regression, the operating performance data and production sensing data of the axial piston pump are effectively utilized, and the internal relationship between the performance indicators and the production parameters is revealed, providing a basis for the optimization of production process parameters.

[0062] Further, as shown in Figure 2 , the embodiments of the present application further include:

[0063] retrieve historical production data records archives, obtain batch production trends based on the historical production data archives;

[0064] perform production demand analysis according to the batch production trends, determine the plurality of batch production schemes based on the demand analysis results and the batch production capacity of the production equipment;

[0065] perform production environment analysis on the plurality of batch production schemes, construct a plurality of simulation scenarios, and the plurality of simulation scenarios have a corresponding relationship with the plurality of batch production schemes;

[0066] synchronize the plurality of simulation scenarios to the digital twin model, execute the plurality of batch production schemes to perform simulation, generate a plurality of batch simulation results, and the plurality of batch simulation results have a corresponding relationship with the plurality of simulation scenarios.

[0067] In a feasible implementation, first, historical production data records of the axial piston pump are extracted from a production management system such as MES, ERP, etc., such as production plan, order delivery, capacity utilization, etc., and statistical analysis is performed on these data to mine potential trends and rules such as seasonal changes in yield, dynamic adjustment of production rhythm, etc., to form a trend curve or trend model reflecting the batch production characteristics of the axial piston pump, and to obtain the batch production trend. Then, based on the obtained batch production trend, combined with market forecast, customer order and other production demand information, the production demand of the axial piston pump in the future period of time is analyzed and predicted to obtain a quantitative demand target as the demand analysis result. Next, considering the design capacity of the existing production line, equipment performance, process level and other factors, the batch production capacity is evaluated, and a plurality of feasible batch production schemes are generated based thereon, to obtain a plurality of batch production schemes, each corresponding to different production batches, production plans, equipment configurations, etc. Then, for each batch production scheme, the production environment involved is comprehensively analyzed, including production line layout, logistics path, personnel configuration, tooling fixture, environmental parameters, etc., and a virtual production scene is constructed based thereon, so that it can dynamically simulate the batch production process of the axial piston pump under the scheme in the virtual space, to obtain a plurality of simulation scenes. After completing the construction of the plurality of simulation scenes, they are integrated with the digital twin model to form a complete virtual production system. Then, according to each batch production scheme, a complete production process simulation is performed in the corresponding simulation scene, including virtual assembly, virtual machining, virtual detection and other links, and real-time statistics of various production indicators and quality data such as yield, pass rate, rhythm, energy consumption, etc. are obtained, thereby obtaining a plurality of batch simulation results.

[0068] By utilizing digital twin, rapid, low-cost and high-fidelity simulation verification of the batch production scheme of the axial piston pump is realized, the cycle of scheme evaluation and optimization is shortened, and the scientificity and accuracy of decision-making are improved, thereby providing a reliable decision basis for subsequent process optimization.

[0069] Further, the embodiments of the application also include:

[0070] Based on the production process, a plurality of production equipment information and a plurality of production process information are determined.

[0071] According to the plurality of production equipment information and the plurality of production process information, the batch production capacity of the target axial piston pump is evaluated, and a batch production evaluation result is generated.

[0072] Based on the batch production evaluation result, cost-benefit analysis is performed to determine production cost-benefit data.

[0073] According to the production cost-benefit data, the feasibility of the batch production evaluation result is determined, and the plurality of batch production schemes are formulated according to the feasible evaluation result.

[0074] In a feasible implementation, first, the production process of the axial plunger pump is analyzed in detail, the key information such as the type of equipment required by each process link, machining precision, process parameters, and the performance parameters, processing capacity, and process range of each equipment are determined, and a structured plurality of production equipment information and a plurality of production process information are formed to provide basic data for subsequent production capacity assessment. Then, on the basis of the plurality of production equipment information and the plurality of production process information, factors such as the number and performance of the equipment, and factors such as the rationality of the process route and the beat balance degree are comprehensively considered, the production capacity of the production line under different batch levels is evaluated, such as maximum capacity, bottleneck process, and average beat, and a quantitative batch production evaluation result is generated to determine the achievable yield and constraint factors of each batch scheme.

[0075] Then, on the basis of obtaining the batch production capacity evaluation result, further cost-benefit analysis is carried out, such as fixed cost accounting, variable cost accounting, economic benefit analysis, etc. Among them, the fixed cost accounting is to calculate the fixed costs related to batch production, such as equipment depreciation, factory rent, management personnel wages, etc.; the variable cost accounting is to calculate the variable costs directly related to the batch size, such as raw material cost, direct labor cost, energy consumption, etc.; the economic benefit analysis is to calculate the total cost, unit cost, gross profit, and return on investment of different batch schemes on the basis of fixed cost and variable cost, combined with product sales price and market demand forecast. Through cost-benefit analysis, quantitative production cost-benefit data is obtained to reflect the economic value and risk level of different batch production schemes. Then, the obtained batch production evaluation result and the obtained production cost-benefit data are comprehensively judged to screen out batch production schemes with matching capacity and benefit and controllable risk, and to prioritize. From among them, several schemes with the highest feasibility are selected as a plurality of batch production schemes for subsequent simulation verification and optimization decision.

[0076] Through the generation and optimization of the batch production scheme, the influencing factors in multiple dimensions such as production capacity, cost-benefit, and risk control are fully considered to improve the scientificity and accuracy of the scheme making and provide a basis for subsequent simulation verification.

[0077] Further, the embodiments of the application also include:

[0078] Synchronize the plurality of simulation scenarios to the digital twin model to set a time step, determine a simulation step and a simulation time length;

[0079] According to the simulation time length and the simulation step, sequentially execute the plurality of batch production schemes for cluster computing to generate a plurality of parallel simulation results;

[0080] The plurality of parallel simulation results are dynamically updated in combination with the simulation step length, simulation compensation is performed on the plurality of parallel simulation results according to a dynamic updating result, and the plurality of batch simulation results are generated.

[0081] In a preferred embodiment, first, the plurality of simulation scenarios constructed are integrated with the digital twin model, so that they can be jointly simulated in a unified virtual environment. At the same time, in order to balance the simulation accuracy and the calculation efficiency, the concept of time step length is introduced, that is, the simulation process is discretized into a plurality of time segments, each segment is called a simulation step length. According to the actual needs of the batch production of the axial piston pump, the length of the simulation step length is set. In addition, the simulation duration of the entire simulation experiment is determined, covering a complete production cycle or several batches, so as to ensure the representativeness and reliability of the simulation results.

[0082] After the simulation step length and the simulation duration are determined, the plurality of batch production schemes are simulated in parallel by using a high-performance computing cluster. Each batch production scheme is split into a plurality of discrete events corresponding to the simulation step length, and then these events are distributed to different computing nodes, so as to simultaneously simulate the execution of a plurality of production schemes in each time segment by means of parallel computing. Each computing node independently runs an instance of the digital twin model, is responsible for processing the assigned production events, and generates corresponding simulation result data. Since the cluster parallel computing is adopted, the speed and efficiency of the simulation are improved, so that the system can complete large-scale production scheme simulation experiments within an acceptable time.

[0083] After the parallel simulation is completed, the simulation result data distributed on different nodes is summarized and synchronized. Specifically, the simulation data generated by each node in the current time segment is collected in units of simulation step length, and is stored in a database to form a complete and dynamically updated simulation result set. At the same time, since there may be communication delays and data inconsistencies between nodes in parallel simulation, necessary compensation and correction, such as time stamp alignment and data interpolation, are performed on the summarized simulation results, so as to ensure the continuity and accuracy of the simulation results. Then, the compensated simulation result data is classified and arranged according to the batch production scheme, to generate complete batch simulation results corresponding to each scheme, and a plurality of batch simulation results are obtained.

[0084] Through the efficient parallel simulation of the batch production scheme of the axial piston pump, the digital twin model and the high-performance computing technology are fully utilized, the simulation time is shortened, the simulation scale and accuracy are improved, and high-quality data support is provided for subsequent production decision-making.

[0085] Further, the embodiments of the application also include:

[0086] Optimization evaluation is performed on the plurality of batch simulation results, and simulation optimization evaluation results are generated.

[0087] generating optimization suggestions according to the simulation optimization evaluation results;

[0088] constructing a multi-index optimization channel based on the optimization suggestions to perform optimization analysis on the multiple batch production schemes and generate optimization feedback data;

[0089] traversing the multiple batch production schemes using the optimization feedback data as an index, verifying the schemes based on the traversal results, and outputting the production batch optimization scheme.

[0090] In a preferred embodiment, first, the generated multiple batch simulation results are analyzed and evaluated, focusing on the performance differences of each scheme in terms of production efficiency, product quality, cost-effectiveness, and other key indicators. A combination of quantitative scoring and qualitative description is used to comprehensively diagnose the strengths and weaknesses of each scheme, forming a structured simulation optimization evaluation result. Then, based on the simulation optimization evaluation result, further optimization clues and improvement directions implied in the simulation optimization evaluation result are mined to generate a series of practical optimization suggestions for guiding the adjustment and optimization of batch production schemes. For example, adjusting the production batch to match market demand and capacity constraints; optimizing resource allocation to improve equipment utilization and personnel efficiency; improving process parameters to shorten the production cycle and improve product quality; optimizing the logistics path to reduce work-in-process inventory and shorten the delivery cycle, etc.

[0091] After obtaining the optimization suggestions, a multi-index optimization channel is first constructed to evaluate the comprehensive effects of different optimization suggestion combinations. Specifically, the optimization suggestions are divided into several optimization dimensions, such as production batch, process parameters, equipment configuration, etc., and each dimension corresponds to a set of optional optimization actions. Then, intelligent optimization algorithms such as heuristic search and evolutionary computation are used to search for the optimal combination strategy in multiple optimization dimensions, and the effects of each strategy are evaluated through simulation experiments to generate corresponding optimization feedback data, including optimized key indicator prediction values, optimization action lists, optimization revenue estimates, etc. After completing the multi-index optimization analysis, the original batch production scheme is modified and updated using the optimization feedback data to form an optimized production scheme. Then, the simulation verification is performed again according to the optimized production scheme to evaluate and confirm the optimization effect. If the verification result meets the expectation, the scheme is output as the final production batch optimization scheme; if the verification result still has room for improvement, the optimization strategy is further adjusted until a satisfactory production batch optimization scheme is obtained.

[0092] Through closed-loop optimization of the batch production scheme of the axial piston pump, the simulation results and artificial intelligence algorithms are fully utilized to automatically generate optimization suggestions, and the best strategy combination is searched through the multi-index optimization channel, improving the optimization efficiency and effect.

[0093] In summary, the axial plunger pump batch production process optimization system based on digital twinning provided by the embodiment has the following technical effects:

[0094] The data acquisition module is configured to obtain a plurality of sensing data sets, including a first sensing data set and a second sensing data set, to provide a data basis for constructing the digital twinning model. The model construction module is configured to construct a physical sub-model based on the first sensing data set and construct a statistical sub-model based on the second sensing data set, to realize digital modeling of the axial plunger pump and its production process. The twinning integration module is configured to integrate the physical sub-model and the statistical sub-model to construct a digital twinning model of the target axial plunger pump, to provide an integrated digital platform for production process optimization. The simulation execution module is configured to simulate the target axial plunger pump through the digital twinning model by executing a plurality of batch production schemes, to generate a plurality of batch simulation results, to provide decision support for production process optimization. The scheme evaluation module is configured to optimize and evaluate the plurality of batch production schemes according to the plurality of batch simulation results, to generate a production batch optimization scheme, and to determine an optimal process parameter combination. The process optimization module is configured to execute the production batch optimization scheme to intelligently optimize the batch production process of the target axial plunger pump according to the target production batch, to ensure the quality and efficiency of batch production.

[0095] Any step of the system described above can be stored as computer instructions or programs in an unlimited computer memory and can be called and recognized by an unlimited computer processor to implement any system in the embodiment of the present application. No redundant limitations are made here.

[0096] Further, the above-mentioned first or second may not only represent an order relationship, but also may represent a certain specific concept, and / or refer to the selection of multiple elements individually or collectively. Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the scope of the present application. Therefore, if these modifications and variations of the present application belong to the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. A digital-twin-based system for optimizing the batch production process of an axial piston pump, characterized in that, The system comprises: a data acquisition module for obtaining a plurality of sensing data sets, the plurality of sensing data sets comprising a first sensing data set and a second sensing data set; a model construction module for constructing a physical sub-model based on the first sensing data set and a statistical sub-model based on the second sensing data set; a twin integration module for integrating the physical sub-model and the statistical sub-model to construct a digital twin model of the target axial piston pump; a simulation execution module for simulating the target axial piston pump through the digital twin model based on a plurality of batch production schemes to generate a plurality of batch simulation results; a scheme evaluation module for optimizing and evaluating the plurality of batch production schemes based on the plurality of batch simulation results to generate an optimized production batch scheme; a process optimization module for intelligently optimizing the production process of the target axial piston pump based on the optimized production batch scheme according to a target production batch; The plurality of sensing data sets, the system comprises: a plurality of sensing devices are arranged according to the production process of the target axial piston pump, and a sensing device group is determined; the sensing device group is divided according to the sensing target to generate a first sensing device group and a second sensing device group; a plurality of production batches are determined based on the production batch data, and the target axial piston pump is matched based on the plurality of production batches to determine a target production batch; the first sensing device group is used to traverse the target axial piston pump according to the target production batch and the physical characteristics of the target axial piston pump to generate the first sensing data set; the second sensing device group is used to traverse the target axial piston pump according to the target production batch and the production process to generate the second sensing data set; the physical sub-model is constructed based on the first sensing data set, and the statistical sub-model is constructed based on the second sensing data set, the system comprises: the first sensing data set is analyzed to obtain geometric structure data and material attribute data of the target axial piston pump; boundary conditions are set, and dynamic analysis is performed based on the geometric structure data and the material attribute data to construct the physical sub-model; the second sensing data set is analyzed to obtain operation performance data and production sensing data of the target axial piston pump; regression analysis is performed based on the operation performance data and the production sensing data to construct the statistical sub-model; the digital twin model is used to simulate the target axial piston pump based on a plurality of batch production schemes to generate a plurality of batch simulation results, the system comprises: a historical production data record archive is called to obtain a batch production trend based on the historical production data archive; production demand analysis is performed based on the batch production trend, and the plurality of batch production schemes are determined based on the demand analysis results and the batch production capacity of the production equipment; production environment analysis is performed on the plurality of batch production schemes to construct a plurality of simulation scenarios, and the plurality of simulation scenarios correspond to the plurality of batch production schemes; Synchronize the plurality of simulation scenarios to the digital twin model, execute the plurality of batch production schemes for simulation, and generate a plurality of batch simulation results, wherein the plurality of batch simulation results correspond to the plurality of simulation scenarios.

2. The digital-twin-based bulk production process optimization system for an axial plunger pump of claim 1, wherein, Based on the operation performance data and the production sensing data, perform regression analysis to construct the statistical sub-model, and the system comprises: Construct a LASSO regression expression: ； in, To minimize the loss function, The number of samples for operational performance data or production sensor data. The number of features for operational performance data or production sensor data. For the first The true target value of each sample For the first The first sample 1 eigenvalue, For the regression intercept, for The weighting coefficients, For regularization parameters, and Let them be two positive integers that can be incremented. Use the LASSO regression expression to perform regression analysis on the operation performance data and the production sensing data respectively, and obtain a minimum loss function; Based on the minimum loss function, cross-validate the regularization parameter to construct the statistical sub-model.

3. The digital-twin-based bulk production process optimization system for an axial plunger pump of claim 1, wherein, According to the batch production trend, perform production demand analysis, and based on the demand analysis results and the batch production capacity of the production equipment, determine a plurality of batch production schemes, and the system comprises: Based on the production process, determine a plurality of production equipment information and a plurality of production process information; According to the plurality of production equipment information and the plurality of production process information, evaluate the batch production capacity of the target axial piston pump, and generate a batch production evaluation result; Based on the batch production evaluation result, perform cost-benefit analysis to determine production cost-benefit data; According to the production cost-benefit data, determine the feasibility of the batch production evaluation result, and according to the feasible evaluation result, formulate the plurality of batch production schemes.

4. The digital-twin-based bulk production process optimization system for an axial plunger pump of claim 1, wherein, Synchronize the plurality of simulation scenarios to the digital twin model, execute the plurality of batch production schemes for simulation, and generate a plurality of batch simulation results, and the system comprises: Synchronize the plurality of simulation scenarios to the digital twin model, set a time step, determine a simulation step and a simulation duration; According to the simulation duration and the simulation step, sequentially execute the plurality of batch production schemes for cluster computing, and generate a plurality of parallel simulation results; According to the simulation step, dynamically update the plurality of parallel simulation results, and according to the dynamic update result, perform simulation compensation on the plurality of parallel simulation results to generate the plurality of batch simulation results.

5. The digital-twin-based bulk production process optimization system for an axial plunger pump of claim 1, wherein, According to the plurality of batch simulation results, perform optimization evaluation on the plurality of batch production schemes, and generate a production batch optimization scheme, and the system comprises: Perform optimization evaluation on the plurality of batch simulation results to generate simulation optimization evaluation results; According to the simulation optimization evaluation results, generate optimization suggestions; Based on the optimization suggestions, construct a multi-index optimization channel to perform optimization analysis on the plurality of batch production schemes, and generate optimization feedback data; Use the optimization feedback data as an index to traverse the plurality of batch production schemes, verify the traversal results, and output the production batch optimization scheme.

Images