CN116401960A - Optimization method and device for grain compression molding process - Google Patents
Optimization method and device for grain compression molding process Download PDFInfo
- Publication number
- CN116401960A CN116401960A CN202310654954.3A CN202310654954A CN116401960A CN 116401960 A CN116401960 A CN 116401960A CN 202310654954 A CN202310654954 A CN 202310654954A CN 116401960 A CN116401960 A CN 116401960A
- Authority
- CN
- China
- Prior art keywords
- grain
- compression molding
- model
- data
- parameters
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 243
- 230000008569 process Effects 0.000 title claims abstract description 194
- 238000000748 compression moulding Methods 0.000 title claims abstract description 87
- 238000005457 optimization Methods 0.000 title claims abstract description 48
- 238000004519 manufacturing process Methods 0.000 claims abstract description 86
- 238000003825 pressing Methods 0.000 claims abstract description 62
- 238000004088 simulation Methods 0.000 claims abstract description 29
- 230000006872 improvement Effects 0.000 claims abstract description 15
- 238000004458 analytical method Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 10
- 239000003814 drug Substances 0.000 claims description 39
- 238000005516 engineering process Methods 0.000 claims description 30
- 239000002360 explosive Substances 0.000 claims description 20
- 230000006870 function Effects 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 16
- 230000000694 effects Effects 0.000 claims description 11
- 238000007906 compression Methods 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 7
- 230000009471 action Effects 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000013386 optimize process Methods 0.000 claims description 4
- 238000003860 storage Methods 0.000 claims description 3
- 238000005303 weighing Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 230000005856 abnormality Effects 0.000 abstract description 3
- 238000013523 data management Methods 0.000 abstract description 3
- 230000008859 change Effects 0.000 description 10
- 238000004364 calculation method Methods 0.000 description 9
- 229940079593 drug Drugs 0.000 description 9
- 238000001514 detection method Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 6
- 230000006835 compression Effects 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 238000007711 solidification Methods 0.000 description 4
- 230000008023 solidification Effects 0.000 description 4
- 238000001228 spectrum Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 230000005484 gravity Effects 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000002360 preparation method Methods 0.000 description 3
- 238000003908 quality control method Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000003070 Statistical process control Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 2
- 238000012098 association analyses Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000000704 physical effect Effects 0.000 description 2
- 238000004886 process control Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000007493 shaping process Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000010259 detection of temperature stimulus Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000007905 drug manufacturing Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000002620 method output Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000007794 visualization technique Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- C—CHEMISTRY; METALLURGY
- C06—EXPLOSIVES; MATCHES
- C06B—EXPLOSIVES OR THERMIC COMPOSITIONS; MANUFACTURE THEREOF; USE OF SINGLE SUBSTANCES AS EXPLOSIVES
- C06B21/00—Apparatus or methods for working-up explosives, e.g. forming, cutting, drying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G06N3/0455—Auto-encoder networks; Encoder-decoder networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention relates to the field of grain pressing and manufacturing, and discloses a method and a device for optimizing grain pressing and forming process, wherein production element information of each device in the grain pressing and forming process is collected; the method is input into a pre-built digital twin model, and based on the efficiency improvement of a core process and the reasonable optimization of process data, the optimization parameters in the grain compression molding process are output and sent to grain compression molding equipment, so that the simulation optimization of the grain compression molding process is realized. The intelligent monitoring of the whole process of the compression molding of the grain is realized, the improvement of the quality and the efficiency of grain production is facilitated, and the intelligent control degree of the compression molding process of the grain is effectively improved; after the processing analysis of the data management, the possible abnormality and safety risk of the production site are predicted, so that workers can process the abnormality and safety risk in time, and the safety degree of the production process is improved.
Description
Technical Field
The invention relates to the field of grain pressing manufacture, in particular to a method and a device for optimizing a grain pressing forming process.
Background
With the development demands of weaponry, the use and the loading of composite medicaments are correspondingly increased. The energy of the compound medicament is continuously increased, so that the danger coefficient is increased. In the optimized control of the drug pressing process, the drug column pressing technology has the defects of undefined product material situation, fuzzy production efficiency lifting principle and even potential safety hazard due to limited on-site data acquisition and control participation means, so that the drug column pressing technology falls into a development bottleneck.
In the prior art, a traditional oil press is used for unidirectional pressing, the press is used for unidirectional pressure feeding for a plurality of times, pressure is maintained for a period of time after each feeding, and the technological parameters during the pressure maintaining are all empirical values. Because the different batches of medicaments have obvious characteristics, when the compression quality of the grains using the batch of medicaments is checked or the process is improved, each detection can be carried out on the grains only after the compression is finished, and whether the compression process is reasonable or the effect of the process is confirmed.
However, in the process of implementing the technical solution of the embodiment of the present application, the present inventors have found that the above technical solution has at least the following technical problems:
because the automatic information acquisition capability of the grain pressing production process is low, a complete relation curve cannot be formed due to the lack of the mapping, association and comparison analysis between the pressure change and the dwell time of the grain pressing and the quality of the grain; the physical data and the information data of the grain in the pressing process are not effectively fused, so that optimized parameters cannot be generated, and technological parameters capable of improving production efficiency cannot be adjusted; therefore, the assembly efficiency is low, the assembly quality is low, the instantaneity is poor, and the intelligent control degree is low in the grain pressing process.
Disclosure of Invention
The invention aims to improve the grain pressing efficiency, grain quality and intelligent control degree.
The aim of the invention is mainly achieved by the following technical scheme:
in a first aspect, a method of optimizing a grain compression molding process includes:
the production element information of each production device in the process of the compression molding of the explosive column is acquired and tracked in real time through various sensors, and the attribute information and the production state information of the production device are accurately and timely acquired; inputting the production element information into a pre-constructed digital twin model, wherein the digital twin model is constructed based on physical, geometric and motion characteristics of grain compression molding equipment, so as to realize fusion of the production equipment model, compression molding process flow, sensor real-time data and equipment attribute data; based on the improvement of the efficiency of the core working procedure and the reasonable optimization of the process data, the process parameters in the grain compression molding process are optimized, and the obtained optimized parameters are sent to production equipment in the grain compression molding process, so that intelligent simulation optimization of the grain compression molding process is realized.
In a second aspect, an apparatus for optimizing a compression molding process for a grain, comprises:
the production element acquisition module is used for acquiring production element information of each device in the process of compression molding of the explosive column;
the compression molding optimization module is used for inputting the production element information into a pre-constructed digital twin model, outputting optimization parameters in the grain compression molding process according to the efficiency improvement of a core process and the reasonable optimization of process data, and sending the optimization parameters to grain compression molding equipment so as to simulate and optimize the grain compression molding process; the digital twin model is constructed based on physical, geometric and kinematic characteristics of the grain compression molding apparatus.
In a third aspect, an electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of a method of optimizing a grain press forming process according to the first aspect when the computer program is executed.
In a fourth aspect, a computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of a method of optimizing a grain press forming process as described in the first aspect.
In a fifth aspect, a computer program product comprising a computer program which, when executed by a processor, implements the steps of a method of optimizing a grain press forming process according to the first aspect.
Compared with the prior art, the beneficial effects are that:
the invention is based on the digital twin technology and based on the improvement of the efficiency of core working procedures and the reasonable optimization of process data, reasonably optimizes the on-line process parameters of medicaments in different batches in the process of compression molding of the explosive column, sends the obtained optimized parameters to production equipment in the process of compression molding of the explosive column, realizes intelligent simulation optimization of the compression molding process of the explosive column, realizes intelligent monitoring of the whole compression molding process of the explosive column, is beneficial to improving the quality and efficiency of the production of the explosive column and effectively improves the intelligent control degree of the compression molding process of the explosive column; after the processing analysis of the data management, the possible abnormality and safety risk of the production site are predicted, so that the staff can process in time; the technical problems of low assembly efficiency, low assembly quality, poor real-time performance and low intelligent control degree in the existing grain pressing process are solved.
Drawings
FIG. 1 shows a schematic flow chart of a method of optimizing a grain compression molding process in accordance with the present invention;
FIG. 2 shows a schematic diagram of the self-encoder network architecture of the present invention;
FIG. 3 shows a schematic structural view of an optimizing apparatus for a grain compression molding process according to the present invention;
fig. 4 shows a schematic structural diagram of an electronic device according to the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
The traditional explosive column production process has low information automatic acquisition capability, more detection links, poor real-time performance, low efficiency and low accuracy; the key technological parameters of the grain production process have poor autonomous decision control capability and lack of an active, accurate and timely intelligent control means; the multiple working procedures adopt a traditional mode of manual operation; the safety of equipment and personnel cannot be ensured in the process of optimizing the production process and improving the process, so that the process optimizing work and the new process flow cannot be operated efficiently, and the quality and the preparation efficiency of the product are directly affected.
Therefore, the invention combines the concept of intelligent manufacturing, provides the connotation of the safe and intelligent manufacturing decision-making environment for grain pressing production based on the digital twin technology and the key realization technology thereof, combines the process improvement and quality improvement requirements of the grain, and initially builds the safe and intelligent manufacturing decision-making environment for grain pressing based on the connotation. And intelligent components such as advanced simulation analysis software, advanced sensors, special detection equipment, special controllers and the like are comprehensively applied, intelligent technologies such as data analysis, self-adaptive control and the like are combined, intelligent system software such as virtual production environment of a press, physical property analysis of medicaments, intelligent information processing decision-making, intelligent quality control, intelligent control of a manufacturing unit and the like is independently developed, and construction of a safe and intelligent manufacturing decision-making environment for grain pressing production is realized. Through a digital simulation technology, according to the process standard and the physical characteristics and density characteristics of medicaments in different batches, a data model for medicament column pressing is established, a medicament column pressing intelligent manufacturing decision system based on a digital twin technology is developed, data analysis processing is carried out on the production process, real-time intelligent analysis and judgment are carried out, and the loading quantity of the medicament column reaches the maximum quantity and optimal selection and matching of safety. In the development process of the system, an optimized solution is provided in the virtual environment of the pressed grain and the virtual pressing process, and the pressing process is divided into: data measurement, pressure process selection and pressure maintaining solidification control, and constructing a database comprising a grain, a pressure value and pressure maintaining solidification time according to the structure. Under the virtual process optimization environment based on the numerical twin technology, an intelligent manufacturing decision basis for medicament press-fitting is provided. Through research and actual development of the intelligent matching algorithm, the system can complete the matching work of the working parameters of the medicine and the press in real time, and according to the optimized structure characteristic of the algorithm, the system can obtain the selection result obtained by different situations of various medicines, and an optimized solution is formed by the selection result, and the result can complete the optimal matching requirement of the parameters of the medicine and the press and the optimal matching requirement of the parameters of the medicine and the press. Through implementation of the digital twin technology, the system effectively solves the defects of complicated and time-consuming trial-error process in the original process, so that the selection and matching result is more scientific and reasonable, correspondingly, manufacturers are liberated from the trial-error process, manpower and material resources are saved, the working efficiency is effectively improved, the working time is saved, and the press-fitting and test product process is more accurate and efficient.
Example 1
The embodiment of the invention provides an optimization method for a grain compression molding process, which is shown in fig. 1 and comprises the following steps:
and step 1, collecting production element information of each device in the process of compression molding of the grain.
The core of the invention is a virtual manufacturing system of the drug pressing system, namely, a digital twin model is constructed. The intelligent manufacturing equipment established on the basis of the core is a basic production unit for realizing intelligent production of the explosive pressing column, and can effectively improve the production efficiency and the safe manufacturing quality of the explosive pressing column. The intelligent manufacturing method has the advantages that the intelligent manufacturing concept is combined, the production or trial production speed of the explosive column is greatly improved, the core and the connotation of the intelligent manufacturing equipment for the safety of the explosive column are reflected, and the intelligent manufacturing process for the safety of the explosive column pressing is comprehensively optimized based on the digital twin technology.
To determine and analyze the core process and data of the production process, for example: detecting the real-time temperature of the press-fit die in the pressing process by an irradiation means and collecting data; acquiring the pressure change condition and data collection in the pressing process through a pressure sensor; the state change of the equipment in the pressing process is observed through a vision acquisition system, and analysis data and the like are formed. Through the confirmation of the data acquisition type and the data acquisition type, a data basis is provided for the establishment of a digital twin system in a virtual environment, and a comparison environment is provided for the effect of optimizing the judging process.
Production element information of each device is acquired by installing various sensors (e.g., a weight sensor, a temperature sensor, a humidity sensor, a vacuum sensor, a pressure sensor, and a positioning sensor) on each production device of the grain press forming process.
In a possible embodiment, the production element information includes: attribute data of the device, operating state data of the device, and operating environment data of the device.
Specifically, a data acquisition module is arranged in a key process link (i.e. a core process) of the assembly of the manufacturing unit, a corresponding analog quantity detection sensor is adopted, a non-contact sensor is adopted for detection of temperature and the like, and process parameters and online data of the manufacturing process are automatically acquired. The data real-time acquisition of the whole production process is realized.
In a possible implementation manner, the method further comprises checking and denoising the acquired data.
Based on collected data of the medicament pressing process equipment, a prediction model is established by using a trend analysis method, and parameter changes of medicaments and equipment in the pressing process are researched according to physical and chemical characteristics of medicaments in different batches, so that various parameter change trends are determined.
Checking the perceived information by adopting a data checking method, timely finding errors in the perceived data by adopting a parity checking method, a CRC checking method and the like, further processing the perceived data by adopting a filtering method, and filtering out overlapping and noise in the data; aiming at the isomerism of the perceived data from different elements in the format, grammar and semantics, a data conversion model is constructed, the perceived data in structured, semi-structured and unstructured formats is uniformly modeled into a uniform format, multi-source data are fused together, and the integrated data are uniformly distributed through a standard interface and protocol.
Aiming at the physical actual collected data, the collected original data is not suitable for being directly used for data analysis because of the characteristics of high collection frequency and huge data volume of physical world noise and data. After preliminary pretreatment such as vacancy value removal and data type regulation is performed on the signal data, data characteristics of the data are required to be extracted. Aiming at the characteristics of time sequence and period of the signal, the feature extraction mainly comprises two aspects of time domain and frequency domain extraction. On the basis of completing feature extraction of multiple dimensions, further dimension reduction and fusion processing are required to be carried out on the extracted features.
(1) Time domain feature extraction
The time domain features are mainly used for describing the change rule of the signal in the time domain, mainly reflect the change of the time domain features such as the average amplitude, the maximum amplitude, the signal deviation degree and the like of the signal along with the increase of the pressing time, and are mainly based on the thought of mathematical statistics to carry out statistical analysis on signal feature parameters.
The average MV (mean value) describes the average amplitude of the signal, N is the number of samples, and the formula is as follows:
the mean square error MSE (mean square error) reflects the offset strength of the signal and is calculated as follows:
maximum MAX (max value) describes the maximum amplitude of the signal in the time domain, calculated as:
root mean square RMS (root mean squre) describes the effective energy of the signal and is calculated as follows:
the skewness factor SF (skewness factor) describes the distribution symmetry characteristics of the signal, and is calculated as follows:
kurtosis factor KF (Kurtosis factor) describes the degree of smoothness of the signal, calculated as follows:
the peak factor CF (crest factor) describes the extremes of the signal, MA is the peak of the signal, calculated as follows:
(2) Frequency domain feature extraction
When the height of the medicine column is gradually reduced, the signal characteristics of the pressure are more reflected on the domain characteristics such as the maximum amplitude, the average amplitude, the deviation degree and the like of the pressure. The original signals of the collected pressure signals and the grain height signals are decomposed into sine waves with a plurality of frequencies through Fourier transformation, and characteristic quantities such as center of gravity frequency, frequency variance and the like are extracted.
The vibration and acoustic emission signals mainly adopt a power spectrum method. During the pressure change, the frequency component of the signal also changes with the accumulation of the decrease in the height of the drug column. For the power spectrum, the following five frequency domain indexes are obtained by extracting the main frequency change characteristics.
The center of gravity frequency FC is:
the mean square frequency MSF is:
the root mean square frequency is:
the frequency variance is:
the mean square error of the frequency is:
s (f) is a power spectrum function, wherein two characteristic quantities of frequency variance and standard deviation represent the degree of dispersion of frequency energy. The center of gravity frequency and the like describe the change of the signal energy of the main frequency band, and f is the frequency of the power spectrum.
(3) Self-encoder based data fusion
Self-coding is commonly used for data dimension reduction, and is essentially an unsupervised deep learning network. The self-encoder structure includes three layers of input, hidden and output. The first input layer is used for inputting original data, the second one is used for data coding, namely data abstract feature extraction, the dimension of the abstract data feature after fusion is determined by the hidden layer dimension of the self-encoder, and the abstract feature can be decoded at the output layer to reconstruct the original signal; as shown in fig. 2.
The dimension of the data input in the figure is
Dimension, encoded abstract feature after compression by matrix operation of hidden layer, dimension is +.>
Wherein the formula of the code is as follows:
wherein the method comprises the steps of
，/>
，/>
Representing the weights of the hidden layers, respectively, the bias of the hidden layers, the symbol g representing the activation function. Whereas the decoding and encoding process is exactly opposite, abstract feature +.>
The data dimension is
Reconstructing by matrix operation, and obtaining the dimension of +.>
Data of->
The decoding formula is as follows:
wherein the method comprises the steps of
，/>
，/>
Representing the weight of the output layer and the bias of the output layer, respectively,/->
Representing an activation function.
The loss function reflects the original input data x and the output data obtained after reconstruction
The error between them is calculated as follows:
wherein: k represents the data magnitude;
neuron weights for the ith neuron of the first layer connected to the jth input; />
Is an L2 regular term coefficient; />
Representing the number of layers of the self-encoder->
And->
The number of neuronal nodes in layer l and layer l+1, respectively. The polynomial of the second term in the formula represents a weight penalty term whose main function is to avoid the occurrence of overfitting.
And 2, inputting the production element information into a pre-constructed digital twin model, and outputting optimized parameters in the grain compression molding process according to the efficiency improvement of a core process and reasonable optimization of process data, wherein the digital twin model is constructed based on physical, geometric and motion characteristics of grain compression molding equipment.
Judging and determining core processes and data for improving the compression efficiency of the explosive column and ensuring safe production by carrying out process analysis on the medicament compression process and the pressure-maintaining curing process and process analysis on the explosive column demoulding and detection processes, and providing a cutting-in point for optimizing the quality and the efficiency in the production process; meanwhile, the effect of the digital twin technology on optimizing the grain pressing process is judged on the basis of efficiency improvement of the core process and reasonable optimization of data.
In one possible embodiment, the grain pressing process mainly comprises 19 process points, wherein the grain manufacturing core process comprises weighing, unidirectional pressing, pressure maintaining, curing and demolding.
Based on the process requirement of the grain forming in the real characterization virtual environment, a digital twin model of the grain pressing production equipment is constructed by researching the physical, geometric and motion characteristics of the grain pressing production equipment according to the characteristics and the functions of the grain pressing production equipment.
Through the omnibearing simulation of the medicament pressing process, a running environment for virtual simulation production is provided for intelligent optimization of the medicament pressing process. And (5) performing online simulation on the simulation model meeting the requirement of the drug pressing process.
In a possible embodiment, constructing the digital twin model comprises:
acquiring part characteristic information of the grain compression molding equipment and associated characteristics among all parts based on a digital twin technology, constructing a three-dimensional characteristic model of the grain compression molding equipment according to the part characteristic information and the associated characteristics among all parts, and creating three-dimensional process information of the three-dimensional characteristic model to obtain a three-dimensional process geometric model of the grain compression molding equipment;
determining parts to be dynamically analyzed according to part characteristic information and associated characteristics among all parts, combining the parts to be dynamically analyzed into a system, carrying out stress analysis on the system, checking whether the functions of the parts to be dynamically analyzed are complete, and constructing a physical entity model of the grain compression molding equipment;
endowing the physical entity model with motion attribute and action form among the motion modules, and constructing to obtain a motion function model of the grain compression molding equipment;
performing data processing based on action forms among all the motion function models, and constructing a rule model of the grain compression molding equipment;
the three-dimensional process geometric model, the physical entity model, the motion function model and the rule model form the digital twin model.
The physical layer is analyzed and processed in real time, a state identification basis is established, and a foundation is established for realizing accurate process control and process simulation verification.
The invention establishes the identification basis of the safety state of the explosive column by utilizing the data obtained by on-line detection and provides means for the accurate process control and the verification of process simulation of the virtual manufacture in the virtual environment under the digital twin technology.
And the quality data and the production management data are stored in a database according to a certain data format, and the data in the database are accessed in real time according to the data required by the software functions of the equipment production management and control system in the running process.
For environmental parameters, the temperature, the humidity, the dust concentration and the like of the equipment can be known by a remote control end through visual monitoring of the sensor, the data conversion and data transmission equipment.
The acquisition system consists of an industrial personal computer and various intelligent acquisition sensors or meters, analog information is communicated with the computer through a multi-path data acquisition card, and digital quantity which can be identified by the computer is obtained through data conversion, so that the real-time acquisition and data processing of the digital twin system on the data of the whole production line are realized.
Based on the data subjected to data verification and noise removal filtration, the feasibility of pressure parameter, pressure maintaining solidification parameter and parameter optimization in the virtual pressing process of the grain by using a digital twin technology is analyzed, and the effects of simulation verification and various schemes are analyzed by combining abnormal safety signal data. And comparing and analyzing the optimized process parameters with original parameters of grain molding process analysis, and finally realizing grain pressing process optimization based on a digital twin technology.
And determining an automatic intelligent process and safety related parameters, reducing the contact of the medicament, determining the optimal pressure value of the medicament, optimizing the dwell time and cleaning the clamping scraps on the shaping site, so that the dangerous coefficient of the dangerous operation environment is greatly reduced under the controllable condition.
In a possible implementation manner, based on the improvement of efficiency of the core process and reasonable optimization of process data, the method outputs optimization parameters in the process of compression molding of the grains, and comprises the following steps: according to the physical and chemical characteristics of medicaments in different batches and the production element information, a control model is established for the core working procedures of the compression molding process of the explosive column, and the control model controls the digital twin model to optimize the technological parameters of each core working procedure on line in real time so as to improve the efficiency of the core working procedure and the rationality of technological data; and outputting the finally obtained optimized parameters by the digital twin model.
In a possible implementation manner, the digital twin model optimizes the process parameters on line for each core process in real time, and includes: the digital twin model performs virtual pressing simulation on each core process, analyzes the feasibility of pressure parameters, pressure maintaining curing parameters and parameter optimization in the virtual pressing process, and analyzes simulation verification and effects of various schemes by combining abnormal safety signal data; and comparing and analyzing the optimized process parameters with original process parameters of the grain compression molding, and finally determining optimized parameters so as to realize real-time online optimization of core procedures in the grain compression process.
The theory and basis of the grain pressing process are defined as follows:
according to the physical and chemical characteristics of medicaments in different batches, based on collected equipment data in a grain pressing process, respectively establishing different control models aiming at process links such as pressure, pressure maintaining, solidification, shaping and the like in the grain pressing process, and according to intelligent quality prediction results of various stages in a virtual manufacturing process by a digital twin technology, adjusting online process parameters in real time; the method combines the acquisition of the key process parameters by a data acquisition system in the actual manufacturing process, and carries out self-adaptive control on the key process parameters by means of self-adaptive control model construction, fuzzy rule design, control simulation and the like, thereby improving the manufacturing efficiency and quality of the grain.
And establishing different batches of medicament processing workflow models, executing workflows according to certain rules and flows generated by a digital twin technology, monitoring quality problem processing processes, and realizing control and information management optimization design of a grain pressing process.
Establishing a digital twin technology virtual model:
and performing grain pressing system simulation in a virtual simulation environment. Firstly, a grain pressing equipment model needs to be established, a simulation application object, a resource object and the like are established, the medicament characteristics and the technological parameter configuration scheme in the grain pressing process are verified through a simulation means, the actual pressing effect is simulated, and the production time and the manufacturing effect are obtained.
And analyzing and evaluating bottleneck process points and faults, and providing a foundation for process planning and parameter formulation and adjustment in the grain pressing process.
And secondly, analyzing the feasibility of pressure parameter, pressure maintaining curing parameter and parameter optimization in the grain pressing process by using a digital twin technology, and performing simulation verification and effect analysis of various schemes.
Finally, analyzing the virtual model data to optimize the grain pressing process:
and (5) performing pressure configuration and optimization of technological parameters by using a simulation method. And analyzing influencing factors in the grain pressing process according to the characteristics of different batches and novel medicaments. And selecting key process parameters such as a grain pressing pressure value, pressure maintaining curing time, temperature control and the like, and obtaining digital simulation design key parameters of the charging process.
Obtaining physical property parameters required in a simulation calculation model and characteristic parameters of a contact material, such as pressure maintaining pressure, phase transition temperature, heat conduction coefficient and the like, through database query and experimental methods; then, according to the technological characteristics of the warhead grain pressing process in the pressing, pressure maintaining and curing processes, a simulation calculation model is established, the calculation result is compared with the experimental test result, if the calculation result and the experimental test result are matched, the technological simulation calculation model of the warhead grain pressing process can be obtained, and if the calculation model is not matched, the calculation model is corrected until the calculation model and the experimental test result are matched; finally, according to the simulation calculation model, the change rule of the technological parameters along with the technological conditions is obtained. The optimization of the grain pressing process is achieved.
And step 3, sending the optimized parameters to grain compression molding equipment so as to simulate and optimize the grain compression molding process.
In summary, the invention uses digital twin technology to simulate the trial production effect of different batches of medicaments in advance, and directly determines the optimal technological parameters. Aiming at the related data of the digital twin technology, a visualization method based on a data association relation is virtually established, all attribute information and characteristics of high-dimensional quality data are reflected in a two-dimensional or three-dimensional visual space as much as possible, the most valuable mapping relation is highlighted to improve the data display strength, and the data mining, data analysis and data modeling processes of the product manufacturing problem are assisted.
And secondly, the digital twin technology is utilized to carry out process improvement simulation of the grain pressing process, so that the preparation quality and efficiency are improved. The quality data association analysis based on the digital twin technology aims at the characteristics of multiple sources of quality data, high dimensionality and high nonlinearity of a quality model of the compressed drug manufacturing unit, improves the structuring degree of the quality data, avoids information flooding, researches the quality data association analysis based on the digital twin technology, automatically identifies the most significant mapping relation in a quality data space, and highlights the data with larger value.
Furthermore, the safety coefficient boundary of the equipment is simulated by utilizing a digital twin technology, so that the safety of the preparation process is ensured. An online quality risk early warning strategy method based on a statistical process control theory is adopted, a quality risk early warning strategy is provided according to a quality state obtained by a quality problem prediction model in combination with the statistical process control theory, and a corresponding quality control method (such as process parameter adjustment according to a quality problem association model) is formulated so as to avoid or eliminate possible safety problem risks, and active quality management is realized.
Furthermore, a convenient and effective safe control environment for the grain pressing production process is formed by utilizing a digital twin technology. The research is based on a digital twin technology, a unified data integration platform is fully utilized, defect reasons are searched for safety and quality problems, closed-loop data management is provided for product safety and quality problem prediction and risk early warning, and quality control and safety problems of a compressed drug column manufacturing unit are solved.
Example two
The embodiment of the invention also provides an optimizing device for the compression molding process of the grain, as shown in fig. 3, the device 200 comprises:
a production element collection module 210, configured to collect production element information of each device in the process of compression molding of the grain;
the compression molding optimization module 220 is configured to input the production element information into a digital twin model constructed in advance, and output optimization parameters in the process of compression molding of the grain according to the improvement of efficiency of a core process and reasonable optimization of process data; the optimized parameters are sent to grain compression molding equipment so as to simulate and optimize the grain compression molding process; the digital twin model is constructed based on physical, geometric and kinematic characteristics of the grain compression molding apparatus.
In a preferred embodiment, the production element information includes: attribute data, operating state data, and work environment data.
In a preferred embodiment, the core process comprises: weighing, one-way pressing, pressure maintaining, solidifying and demoulding.
In a preferred embodiment, the compression molding optimization module 220 includes a model building unit, configured to build the digital twin model, obtain part feature information of the grain compression molding device and associated features between parts based on a digital twin technology, build a three-dimensional feature model of the grain compression molding device according to the part feature information and the associated features between parts, and create three-dimensional process information of the three-dimensional feature model to obtain a three-dimensional process geometric model of the grain compression molding device; determining parts to be dynamically analyzed according to part characteristic information and associated characteristics among all parts, combining the parts to be dynamically analyzed into a system, carrying out stress analysis on the system, checking whether the functions of the parts to be dynamically analyzed are complete, and constructing a physical entity model of the grain compression molding equipment; endowing the physical entity model with motion attribute and action form among the motion modules, and constructing to obtain a motion function model of the grain compression molding equipment; performing data processing based on action forms among all the motion function models, and constructing a rule model of the grain compression molding equipment; the three-dimensional process geometric model, the physical entity model, the motion function model and the rule model form the digital twin model.
In a preferred embodiment, the compression molding optimization module 220 includes an optimization unit, and establishes a control model for the core process of the grain compression molding process according to the physical and chemical characteristics of the medicines in different batches and the production factor information, and the control model controls the digital twin model to optimize the process parameters for each core process in real time on line so as to improve the efficiency of the core process and the rationality of the process data; and outputting the finally obtained optimized parameters by the digital twin model.
In a preferred embodiment, the optimization unit is specifically configured to: the digital twin model performs virtual pressing simulation on each core process, analyzes the feasibility of pressure parameters, pressure maintaining curing parameters and parameter optimization in the virtual pressing process, and analyzes simulation verification and effects of various schemes by combining abnormal safety signal data; and comparing and analyzing the optimized process parameters with original process parameters of the grain compression molding, and finally determining optimized parameters so as to realize real-time online optimization of core procedures in the grain compression process.
The optimizing device for the grain compression molding process in the embodiment of the invention is an optimizing method for the grain compression molding process corresponding to the embodiment, and realizes corresponding functions. Since the foregoing embodiments have described an embodiment of an optimization method for the compression molding process of the grain in detail, the detailed description thereof will be omitted.
Example III
The embodiment of the invention also provides an electronic device 3, as shown in fig. 4, comprising a memory 31, a processor 32 and a computer program 33 stored in the memory and executable on the processor, which when executing the computer program implements the steps of the method for optimizing a grain compression moulding process according to the above embodiment.
Example IV
The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, which when being executed by a processor, implements the steps of the optimizing method of the grain press forming process according to the above embodiment.
Example five
The present invention also provides a computer program product comprising a computer program which when executed by a processor carries out the steps of a method of optimizing a grain press forming process as in the above embodiments.
The foregoing has outlined rather broadly the more detailed description of embodiments of the invention, wherein the principles and embodiments of the invention are explained in detail using specific examples, the above examples being provided solely to facilitate the understanding of the method and core concepts of the invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (10)
1. A method of optimizing a grain compression molding process, comprising:
collecting production element information of each device in the process of compression molding of the grain;
inputting the production element information into a pre-constructed digital twin model, outputting optimization parameters in the grain compression molding process according to the efficiency improvement of a core process and the reasonable optimization of process data, and sending the optimization parameters to grain compression molding equipment so as to simulate and optimize the grain compression molding process; the digital twin model is constructed based on physical, geometric and kinematic characteristics of the grain compression molding apparatus.
2. The method of optimizing a grain press forming process of claim 1, wherein the production element information includes: attribute data, operating state data, and work environment data.
3. The method of optimizing a grain compression molding process of claim 1, wherein the core process comprises: weighing, one-way pressing, pressure maintaining, solidifying and demoulding.
4. The method of optimizing a grain compression molding process of claim 1, wherein constructing the digital twin model comprises:
acquiring part characteristic information of the grain compression molding equipment and associated characteristics among all parts based on a digital twin technology, constructing a three-dimensional characteristic model of the grain compression molding equipment according to the part characteristic information and the associated characteristics among all parts, and creating three-dimensional process information of the three-dimensional characteristic model to obtain a three-dimensional process geometric model of the grain compression molding equipment;
determining parts to be dynamically analyzed according to part characteristic information and associated characteristics among all parts, combining the parts to be dynamically analyzed into a system, carrying out stress analysis on the system, checking whether the functions of the parts to be dynamically analyzed are complete, and constructing a physical entity model of the grain compression molding equipment;
endowing the physical entity model with motion attribute and action form among the motion modules, and constructing to obtain a motion function model of the grain compression molding equipment;
performing data processing based on action forms among all the motion function models, and constructing a rule model of the grain compression molding equipment;
the three-dimensional process geometric model, the physical entity model, the motion function model and the rule model form the digital twin model.
5. The method of optimizing a grain press forming process according to claim 1 or 4, wherein outputting optimization parameters in the grain press forming process based on the improvement of efficiency of the core process and reasonable optimization of the process data comprises:
according to the physical and chemical characteristics of medicaments in different batches and the production element information, a control model is established for the core working procedures of the compression molding process of the explosive column, and the control model controls the digital twin model to optimize the technological parameters of each core working procedure on line in real time so as to improve the efficiency of the core working procedure and the rationality of technological data; and outputting the finally obtained optimized parameters by the digital twin model.
6. The method of optimizing a grain compression molding process of claim 5, wherein the digital twin model optimizes process parameters on-line in real time for each core process comprising:
the digital twin model performs virtual pressing simulation on each core process, analyzes the feasibility of pressure parameters, pressure maintaining curing parameters and parameter optimization in the virtual pressing process, and analyzes simulation verification and effects of various schemes by combining abnormal safety signal data; and comparing and analyzing the optimized process parameters with original process parameters of the grain compression molding, and finally determining optimized parameters so as to realize real-time online optimization of core procedures in the grain compression process.
7. An optimizing apparatus for a press forming process of a grain, comprising:
the production element acquisition module is used for acquiring production element information of each device in the process of compression molding of the explosive column;
the compression molding optimization module is used for inputting the production element information into a pre-constructed digital twin model, outputting optimization parameters in the grain compression molding process according to the efficiency improvement of a core process and the reasonable optimization of process data, and sending the optimization parameters to grain compression molding equipment so as to simulate and optimize the grain compression molding process; the digital twin model is constructed based on physical, geometric and kinematic characteristics of the grain compression molding apparatus.
8. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program, carries out the steps of a method for optimizing a grain press forming process according to any one of claims 1-6.
9. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the steps of a method of optimizing a grain press forming process according to any one of claims 1 to 6.
10. A computer program product comprising a computer program which, when executed by a processor, implements the steps of a method of optimizing a grain press forming process according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310654954.3A CN116401960A (en) | 2023-06-05 | 2023-06-05 | Optimization method and device for grain compression molding process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310654954.3A CN116401960A (en) | 2023-06-05 | 2023-06-05 | Optimization method and device for grain compression molding process |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116401960A true CN116401960A (en) | 2023-07-07 |
Family
ID=87020148
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310654954.3A Pending CN116401960A (en) | 2023-06-05 | 2023-06-05 | Optimization method and device for grain compression molding process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116401960A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021169598A1 (en) * | 2020-02-27 | 2021-09-02 | 广东工业大学 | Digital twinning-based physical simulation method for production line and system thereof |
| US20220207206A1 (en) * | 2020-12-24 | 2022-06-30 | Beijing Institute Of Technology | Physical Digital Twin Modeling Method And Apparatus For Assembly, Electronic Device And Medium |
| CN114881289A (en) * | 2022-04-11 | 2022-08-09 | 中国兵器装备集团自动化研究所有限公司 | Fusion casting charge forming process parameter optimization method and system based on digital twinning |
| CN115374670A (en) * | 2022-08-11 | 2022-11-22 | 北京航空航天大学 | Powder pressing process technological parameter optimization method based on digital twinning |
| CN115618285A (en) * | 2022-09-28 | 2023-01-17 | 中国兵器装备集团自动化研究所有限公司 | Bad data identification method, device, equipment and storage medium |
| US20230123322A1 (en) * | 2021-04-16 | 2023-04-20 | Strong Force Vcn Portfolio 2019, Llc | Predictive Model Data Stream Prioritization |
| CN116129053A (en) * | 2023-02-15 | 2023-05-16 | 杭州电力设备制造有限公司 | Power equipment model construction method |
-
2023
- 2023-06-05 CN CN202310654954.3A patent/CN116401960A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021169598A1 (en) * | 2020-02-27 | 2021-09-02 | 广东工业大学 | Digital twinning-based physical simulation method for production line and system thereof |
| US20220207206A1 (en) * | 2020-12-24 | 2022-06-30 | Beijing Institute Of Technology | Physical Digital Twin Modeling Method And Apparatus For Assembly, Electronic Device And Medium |
| US20230123322A1 (en) * | 2021-04-16 | 2023-04-20 | Strong Force Vcn Portfolio 2019, Llc | Predictive Model Data Stream Prioritization |
| CN114881289A (en) * | 2022-04-11 | 2022-08-09 | 中国兵器装备集团自动化研究所有限公司 | Fusion casting charge forming process parameter optimization method and system based on digital twinning |
| CN115374670A (en) * | 2022-08-11 | 2022-11-22 | 北京航空航天大学 | Powder pressing process technological parameter optimization method based on digital twinning |
| CN115618285A (en) * | 2022-09-28 | 2023-01-17 | 中国兵器装备集团自动化研究所有限公司 | Bad data identification method, device, equipment and storage medium |
| CN116129053A (en) * | 2023-02-15 | 2023-05-16 | 杭州电力设备制造有限公司 | Power equipment model construction method |
Non-Patent Citations (4)
| Title |
|---|
| FEI TAO ET AL.: "Digital twin modeling", JOURNAL OF MANUFACTURING SYSTEMS, vol. 64 * |
| WENJIE JIA ET AL.: "From simple digital twin to complex digital twin Part I: A novel modelingmethod for multi-scale and multi-scenario digital twin", ADVANCED ENGINEERING INFORMATICS, vol. 53 * |
| YUCHEN WANG ET AL.: "Digital twin-driven complexity management in intelligent manufacturing", DIGITAL TWIN, vol. 1, no. 9 * |
| 宋玉萍: "粉末成型技术创新及其发展现状", 中国有色金属, no. 19 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112162519A (en) | Compound machine tool digital twin monitoring system | |
| CN112731887A (en) | Digital twin intelligent monitoring system and method for petrochemical unattended loading and unloading line | |
| CN112800668A (en) | Digital twin-based complex product operation, maintenance and manufacturing integrated overall model | |
| CN112016828B (en) | Industrial equipment health management cloud platform architecture based on streaming big data | |
| CN116822353A (en) | Digital twin model rapid construction method in manufacturing process | |
| CN114329849B (en) | Health management and control system and method for liquid filling forming equipment based on digital twinning | |
| CN109634233A (en) | Industrial big data intellectual analysis decision-making technique, readable storage medium storing program for executing and terminal | |
| CN114723285A (en) | Power grid equipment safety evaluation prediction method | |
| CN113887749A (en) | Cloud edge cooperation-based multi-dimensional monitoring and disposal method, device and platform for power internet of things | |
| CN115576293B (en) | Pressure-sensitive adhesive on-line production analysis method and system based on data monitoring | |
| CN114415607A (en) | Design process manufacturing integrated digital twin system based on data driving | |
| Li et al. | Framework and case study of cognitive maintenance in Industry 4.0 | |
| CN109614451A (en) | Industrial big data intellectual analysis decision making device | |
| CN110716520B (en) | Flight control servo actuator reliability evaluation modeling method based on multi-source information fusion | |
| CN116401960A (en) | Optimization method and device for grain compression molding process | |
| CN110794799A (en) | Big data system with fault diagnosis function applied to industrial production | |
| CN117172751A (en) | Construction method of intelligent operation and maintenance information analysis model | |
| CN115640980A (en) | Power grid engineering cost dynamic management system based on target control | |
| CN115730255A (en) | Motor fault diagnosis and analysis method based on transfer learning and multi-source information fusion | |
| Li et al. | Research on digital twin and collaborative cloud and edge computing applied in operations and maintenance in wind turbines of wind power farm | |
| Xiao et al. | A Construction Method of Intelligent Manufacturing System under Industry 4.0 Model | |
| CN113886355A (en) | Nuclear power structural material process data integration system and method | |
| CN113673952A (en) | Cloud service system based on industrial internet platform | |
| Yu et al. | Remaining useful life prognosis for rolling bearings based on Bi-ConvLSTM | |
| CN114417703B (en) | Photovoltaic module fault online diagnosis and analysis algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |