LU502681B1 - Control adjustment method and system for high-efficiency grinding crankshaft - Google Patents
Control adjustment method and system for high-efficiency grinding crankshaft Download PDFInfo
- Publication number
- LU502681B1 LU502681B1 LU502681A LU502681A LU502681B1 LU 502681 B1 LU502681 B1 LU 502681B1 LU 502681 A LU502681 A LU 502681A LU 502681 A LU502681 A LU 502681A LU 502681 B1 LU502681 B1 LU 502681B1
- Authority
- LU
- Luxembourg
- Prior art keywords
- crankshaft
- grinding
- information
- parameter
- characteristic
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B49/00—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation
- B24B49/02—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation according to the instantaneous size and required size of the workpiece acted upon, the measuring or gauging being continuous or intermittent
- B24B49/04—Measuring or gauging equipment for controlling the feed movement of the grinding tool or work; Arrangements of indicating or measuring equipment, e.g. for indicating the start of the grinding operation according to the instantaneous size and required size of the workpiece acted upon, the measuring or gauging being continuous or intermittent involving measurement of the workpiece at the place of grinding during grinding operation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B24—GRINDING; POLISHING
- B24B—MACHINES, DEVICES, OR PROCESSES FOR GRINDING OR POLISHING; DRESSING OR CONDITIONING OF ABRADING SURFACES; FEEDING OF GRINDING, POLISHING, OR LAPPING AGENTS
- B24B5/00—Machines or devices designed for grinding surfaces of revolution on work, including those which also grind adjacent plane surfaces; Accessories therefor
- B24B5/36—Single-purpose machines or devices
- B24B5/42—Single-purpose machines or devices for grinding crankshafts or crankpins
-
- 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
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/098—Distributed learning, e.g. federated learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/0014—Image feed-back for automatic industrial control, e.g. robot with camera
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/35—Nc in input of data, input till input file format
- G05B2219/35017—Finite elements analysis, finite elements method FEM
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20076—Probabilistic image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Mechanical Engineering (AREA)
- Robotics (AREA)
- Quality & Reliability (AREA)
- Automation & Control Theory (AREA)
- Grinding Of Cylindrical And Plane Surfaces (AREA)
Abstract
A control adjustment method and a system for a high-efficiency grinding crankshaft are provided, belonging to the field of artificial intelligence. The method includes the following steps of: classifying crankshaft multi-dimensional data information through a crankshaft characteristic decision-making tree, so as to obtain crankshaft characteristic information; performing finite element segmentation on crankshaft image information, so as to obtain crankshaft image segmentation information; performing integrated learning based on the crankshaft characteristic information and the crankshaft image segmentation information, so as to build a crankshaft grinding parameter integrated analysis model; inputting data information of the crankshaft to be ground and image information of the crankshaft to be ground in the crankshaft grinding parameter integrated analysis model, so as to obtain crankshaft grinding parameter information; and obtaining an error parameter of a grinding device, and controlling and adjusting the crankshaft grinding based on the error parameter of the grinding device and the crankshaft grinding parameter information. The technical effects of confirming the crankshaft grinding parameters by building the crankshaft grinding parameter integrated analysis model, improving the crankshaft grinding precision and grinding efficiency, and then ensuring the crankshaft grinding quality are achieved.
Description
CONTROL ADJUSTMENT METHOD AND SYSTEM FOR HIGH- 7502681
EFFICIENCY GRINDING CRANKSHAFT
The present disclosure relates to the field of artificial intelligence, in particular to a control adjustment method and a system for a high-efficiency grinding crankshaft.
As a core component for ensuring the normal operation of an engine, and a key component of a piston engine, a crankshaft bears force from a connecting rod, transforms the force into torque, outputs the torque and drives other accessories on the engine to work; and the crankshaft plays an important role in bearing impact load and transferring power in engines of a car, a truck, a motorcycle, a ship, a model airplane and a lawn mower. Therefore, each part, such as a flange end, a spindle head end, a main journal and a connecting rod neck on the crankshaft must be subjected to accurate grinding.
However, the prior art has the technical problem of grinding quality of the crankshaft affected by the low crankshaft grinding precision and long time.
By providing a control adjustment method and a system for a high-efficiency grinding crankshaft, this application solves the technical problem of grinding quality of the crankshaft affected by the low crankshaft grinding precision and long time in the prior art, and achieves the technical effects of confirming the crankshaft grinding parameters by building a crankshaft grinding parameter integrated analysis model, improving the crankshaft grinding precision and grinding efficiency, and then ensuring the crankshaft grinding quality.
In view of the above problems, the present disclosure provides a control adjustment method and a system for a high-efficiency grinding crankshaft.
On the one hand, this application provides a control adjustment method for a high- efficiency grinding crankshaft, and the method includes the following steps of: obtaining crankshaft collecting data information, which includes crankshaft multi-dimensional data information and crankshaft image information; building a crankshaft characteristic decision- making tree, and classifying the crankshaft multi-dimensional data information through the crankshaft characteristic decision-making tree, so as to obtain crankshaft characteristic information; performing finite element segmentation on the crankshaft image information, so as to obtain crankshaft image segmentation information; uploading the crankshaft characteristic information and the crankshaft image segmentation information to a data integration training platform for learning, so as to build a crankshaft grinding parameter integrated analysis model; collecting and obtaining data information of the crankshaft to be ground and image information of the crankshaft to be ground; inputting the data information of the crankshaft to be ground and the image information of the crankshaft to be ground in the crankshaft grinding parameter integrated analysis model, so as to obtain crankshaft grinding parameter information; and obtaining an error parameter of a grinding device, and controlling and adjusting the crankshaft grinding based on the error parameter of the grinding device and the crankshaft grinding parameter information.
On the other hand, this application further provides a control adjustment system for a high-efficiency grinding crankshaft, and the system includes a data acquisition module, which is configured to obtain crankshaft collecting data information, and the crankshaft collecting data information includes crankshaft multi-dimensional data information and crankshaft image information; a characteristic classifying module, which is configured to build a crankshaft characteristic decision-making tree, and to classify the crankshaft multi-
dimensional data information through the crankshaft characteristic decision-making tree, so LUS02681 as to obtain crankshaft characteristic information; an image segmentation module, which is configured to perform finite element segmentation on the crankshaft image information, so as to obtain crankshaft image segmentation information; a model building module, which is configured to upload the crankshaft characteristic information and the crankshaft image segmentation information to a data integration training platform for learning, so as to build a crankshaft grinding parameter integrated analysis model; a data acquisition module, which is configured to collect and obtain data information of the crankshaft to be ground and image information of the crankshaft to be ground; a model output module, which is configured to input the data information of the crankshaft to be ground and the image information of the crankshaft to be ground in the crankshaft grinding parameter integrated analysis model, so as to obtain crankshaft grinding parameter information; and a control adjustment module, which is configured to obtain an error parameter of a grinding device, and to control and adjust the crankshaft grinding based on the error parameter of the grinding device and the crankshaft grinding parameter information.
One or more technical solutions provided in this application at least have the following technical effects or advantages:
Due to adopting the following technical solution: the crankshaft multi-dimensional data information is classified through the crankshaft characteristic decision-making tree, so as to obtain the crankshaft characteristic information; the crankshaft image information is subjected to finite element segmentation, so as to obtain the crankshaft image segmentation information; the crankshaft grinding parameter integrated analysis model is built based on the integrated training of the crankshaft characteristic information and the crankshaft image segmentation information, the data information of the crankshaft to be ground and the image information of the crankshaft to be ground are input into the crankshaft grinding parameter integrated analysis model, so as to obtain the crankshaft grinding parameter information; and the crankshaft grinding is controlled and adjusted based on the error parameter of the grinding device and the crankshaft grinding parameter information, the technical effects of confirming the crankshaft grinding parameters by building the crankshaft grinding parameter integrated analysis model, improving the crankshaft grinding precision and grinding efficiency, and then ensuring the crankshaft grinding quality are achieved.
FIG. 1 1s a flow diagram of a control adjustment method for a high-efficiency grinding crankshaft provided in this application.
FIG. 2 is a flow diagram of a crankshaft grinding parameter integrated analysis model built in a control adjustment method for a high-efficiency grinding crankshaft provided in this application.
FIG. 3 is a flow diagram of crankshaft grinding parameter information obtained in a control adjustment method for a high-efficiency grinding crankshaft provided in this application.
FIG. 4 is a structure diagram of a control adjustment system for a high-efficiency grinding crankshaft provided in this application.
Reference signs: data acquisition module 11, characteristic classifying module 12, image segmentation module 13, model building module 14, data collecting module 15, model output module 16 and control adjustment module 17.
By providing a control adjustment method and a system for a high-efficiency grinding crankshaft, this application solves the technical problem of grinding quality of the crankshaft affected by the low crankshaft grinding precision and long time, and achieves the technical LUS02681 effects of confirming the crankshaft grinding parameters by building the crankshaft grinding parameter integrated analysis model, improving the crankshaft grinding precision and grinding efficiency, and then ensuring the crankshaft grinding quality.
Embodiment I
As shown in FIG. 1, this application provides a control adjustment method for a high- efficiency grinding crankshaft, and the method includes the following steps of:
S100: obtaining crankshaft collecting data information, which includes crankshaft multi-dimensional data information and crankshaft image information; specifically, as a core component for ensuring the normal operation of an engine, and a key component of a piston engine, a crankshaft bears force from a connecting rod, transforms the force into torque, outputs the torque and drives other accessories on the engine to work; and the crankshaft plays an important role in bearing impact load and transferring power in engines of a car, a truck, a motorcycle, a ship, a model airplane and a lawn mower. Therefore, each part, such as a flange end, a spindle head end, a main journal and a connecting rod neck on the crankshaft must be subjected to accurate grinding.
Collecting and obtaining crankshaft data information, wherein the crankshaft collecting data information includes the crankshaft multi-dimensional data information and the crankshaft image information, the crankshaft multi-dimensional data information includes crankshaft type, material, structure size, application, etc.; the crankshaft image information includes crankshaft color, structure, surface characteristic, etc.; and the crankshaft data information is completely collected, so as to ensure that a follow-up model has more accurate training result.
S200: building a crankshaft characteristic decision-making tree, and classifying the crankshaft multi-dimensional data information through the crankshaft characteristic decision-making tree, so as to obtain crankshaft characteristic information; further, S200 of building the crankshaft characteristic decision-making tree in this application includes the following steps of:
S210: obtaining a crankshaft structural form attribute, which is used as a first crankshaft classification characteristic;
S220: obtaining a crankshaft process material attribute, which is used as a second crankshaft classification characteristic;
S230: obtaining a crankshaft application type attribute, which is used as a third crankshaft classification characteristic;
S240: building the crankshaft characteristic decision-making tree based on the first crankshaft classification characteristic, the second crankshaft classification characteristic and the third crankshaft classification characteristic.
Specifically, in order to build the crankshaft characteristic decision-making tree, the crankshaft classification characteristic is confirmed first. The crankshaft structural form attribute is used as the first crankshaft classification characteristic and classified according to the crankshaft structure. The main structure of the crankshaft includes a crankshaft main journal, a connecting rod journal, a crank arm, a front journal, a rear journal, etc. The crankshaft may be divided into a one-piece crankshaft, an assembled crankshaft, a disc crankshaft and the like according to the structural composition type. The crankshaft process material attribute is used as the second crankshaft classification characteristic. The crankshaft process material attribute is the crankshaft manufacturing material and includes a forged steel crankshaft, a cast iron crankshaft and the like, and the grinding force is accordingly different due to different material properties.
The crankshaft application type attribute is used as the third crankshaft classification characteristic. The crankshaft application type attribute is the application type of the crankshaft in an engine, such as a gasoline engine crankshaft, a diesel engine crankshaft and LUS02681 the like, and the crankshaft has different requirements due to different application attributes.
The decision-making tree is a decision-making analysis method for judging feasibility of various situations by building the decision-making tree to solve the probability that an expected value is greater than or equal to 0 based on the known probability of occurrence of various situations, and it is a graphical method for applying the probability analysis intuitively. This classifier can accurately classify an emerging object and is composed of a root node, an internal node and a leaf node.
The first crankshaft classification characteristic, the second crankshaft classification characteristic and the third crankshaft classification characteristic are respectively used as the internal nodes of the crankshaft characteristic decision-making tree. By performing the information entropy calculation on the first crankshaft classification characteristic, the second crankshaft classification characteristic and the third crankshaft classification characteristic, the characteristic with the minimum entropy may be classified preferentially, and the crankshaft characteristic decision-making tree can be subjected to recursive building through this method. The crankshaft characteristic decision-making tree classifies the crankshaft multi-dimensional data information, so as to obtain the corresponding crankshaft characteristic information, namely, the crankshaft characteristic classifying result, including the structural form characteristic, the process material characteristic and the application type characteristic, etc. The crankshaft multi-dimensional data is classified by accurately building the crankshaft characteristic decision-making tree, so as to improve the accuracy and specificity of the crankshaft data processing result.
S300: performing finite element segmentation on the crankshaft image information, so as to obtain crankshaft image segmentation information; specifically, the crankshaft image information is subjected to the finite element segmentation, the crankshaft image information is divided into a plurality of image grids according to the image structural size attribute of the crankshaft. More grid segmentation makes richer image detail display, so as to obtain the crankshaft image segmentation information, which is beneficial to more accurate and efficient follow-up image appearance characteristic analysis.
S400: uploading the crankshaft characteristic information and the crankshaft image segmentation information to a data integration training platform for learning, so as to build a crankshaft grinding parameter integrated analysis model,
As shown in FIG. 2, the S400 of uploading the crankshaft characteristic information and the crankshaft image segmentation information to the data integration training platform for learning, so as to build the crankshaft grinding parameter integrated analysis model in this application further includes the following steps of:
S410: inputting the crankshaft characteristic information and the crankshaft image segmentation information into a deep convolutional neural network for training, so as to build a one-party crankshaft grinding parameter analysis model;
S420: obtaining multi-party crankshaft collecting data information, which is respectively input into the deep convolutional neural network for distributed training, so as to obtain a multi-party crankshaft grinding parameter analysis model,
S430: extracting training model parameters of the one-party crankshaft grinding parameter analysis model and the multi-party crankshaft grinding parameter analysis model;
S440: performing joint training on the training model parameters through the data integration training platform, so as to obtain the crankshaft grinding parameter integrated analysis model.
Specifically, the crankshaft characteristic information and the crankshaft image segmentation information are uploaded to the data integration training platform for learning;
and the data integration training platform is configured to train the data model with a plurality LUS02681 of sources, so that the final model building is more reasonable and accurate. First, the crankshaft characteristic information and the crankshaft image segmentation information are input into the deep convolutional neural network for training, and the deep convolutional neural network 1s a class of feedforward neural network with convolutional calculation, a depth structure and high stability of characteristic identification. The one-party crankshaft grinding parameter analysis model is built based on this training for crankshaft data processing in a platform or an enterprise, so as to analyze the crankshaft grinding parameter information. In order to analyze the crankshaft grinding parameter more accurately and completely, and carry out crankshaft data collection for a plurality of other platforms or enterprises, the multi-party crankshaft collecting data information is respectively input into the deep convolutional neural network for distributed training, so as to obtain the corresponding multi-party crankshaft grinding parameter analysis model.
The training model parameters of the one-party crankshaft grinding parameter analysis model and the multi-party crankshaft grinding parameter analysis model are extracted; and the training model parameters include a crankshaft parameter, a crankshaft grinding type, a grinding speed, a grinding force parameter and a corresponding model weight, etc. The data integration training platform performs joint training on the training model parameters, so as to build the crankshaft grinding parameter integrated analysis model after the federated integration training. With a high safety factor during the training process, the output result of the crankshaft grinding parameter integrated analysis model after the federated integration training is more reasonable and accurate, the range of application is more comprehensive, thereby ensuring the crankshaft grinding quality.
S500: collecting and obtaining data information of the crankshaft to be ground and image information of the crankshaft to be ground, specifically, in order to ensure the grinding accuracy of the crankshaft to be ground, the step of collecting and obtaining the data information of the crankshaft to be ground and the image information of the crankshaft to be ground includes various information, such as the type of the crankshaft to be ground, the material, the structural size, the application, the crankshaft structure and the surface characteristic, so as to ensure the accuracy of the model output grinding parameter.
S600: inputting the data information of the crankshaft to be ground and the image information of the crankshaft to be ground in the crankshaft grinding parameter integrated analysis model, so as to obtain crankshaft grinding parameter information;
As shown in FIG. 3, S600 of inputting the data information of the crankshaft to be ground and the image information of the crankshaft to be ground in the crankshaft grinding parameter integrated analysis model, so as to obtain crankshaft grinding parameter information in this application further includes the following steps of:
S610: the crankshaft grinding parameter integrated analysis model including an input layer, an image convolutional logic layer, a hidden layer and an output layer;
S620: inputting the image information of the crankshaft to be ground in the image convolutional logic layer through the input layer, so as to output the appearance characteristic of the crankshaft to be ground;
S630: inputting the data information of the crankshaft to be ground and the appearance characteristic of the crankshaft to be ground in the hidden layer, so as to output the crankshaft grinding parameter information;
S640: outputting the crankshaft grinding parameter information through the output layer as the model output result.
Further, S620 of inputting the image information of the crankshaft to be ground in the image convolutional logic layer through the input layer, so as to output the appearance characteristic of the crankshaft to be ground in this application further includes the following LUS02681 steps of:
S621: obtaining a crankshaft application standard, obtaining a predetermined convolutional characteristic set according to the crankshaft application standard, and the predetermined convolutional characteristic set including a crankshaft curvature characteristic, a smoothness characteristic and a burr value characteristic;
S622: inputting the image information of the crankshaft to be ground in the image convolutional logic layer for characteristic extraction through the input layer;
S623: obtaining the output information of the image convolutional logic layer, and the output information including the appearance characteristic of the crankshaft to be ground that conforms to the predetermined convolutional characteristic set.
Specifically, the data information of the crankshaft to be ground and the image information of the crankshaft to be ground are input in the crankshaft grinding parameter integrated analysis model, and the crankshaft grinding parameter integrated analysis model specifically includes an input layer, an image convolutional logic layer, a hidden layer and an output layer. The image information of the crankshaft to be ground is input in the image convolutional logic layer through the input layer; and the image convolutional logic layer is configured to extract the image characteristic.
Specifically, the crankshaft application standard is obtained first, the crankshaft application standard is the appearance standard capable of applying the crankshaft actually, the predetermined convolutional characteristic set is obtained according to the crankshaft application standard, and the predetermined convolutional characteristic set includes a crankshaft curvature characteristic, a smoothness characteristic and a surface burr value characteristic requirement standard; the image information of the crankshaft to be ground is input in the image convolutional logic layer for characteristic extraction through the input layer, namely, the image characteristic is subjected to convolutional calculation to obtain the output information of the image convolutional logic layer, and the output information includes the appearance characteristic of the crankshaft to be ground that conforms to the predetermined convolutional characteristic set, namely, conforms to the image appearance characteristic of the application standard.
The data information of the crankshaft to be ground and the appearance characteristic of the crankshaft to be ground are input in the hidden layer, the hidden layer is configured to perform the crankshaft grinding parameter analysis through the crankshaft multi-dimensional data characteristic and the image characteristic, and training may be carried out by the historical data, so as to output the crankshaft grinding parameter information. The crankshaft grinding parameter information includes grinding force, a grinding speed, a grinding line, a grinding angle and the like, and the crankshaft grinding parameter information is output through the output layer as a model output result. The crankshaft grinding parameters are confirmed by building the crankshaft grinding parameter integrated analysis model, so that the crankshaft grinding parameter output by the model is more reasonable and accurate, thereby improving the crankshaft grinding precision and grinding efficiency.
S700: obtaining an error parameter of a grinding device, and controlling and adjusting the crankshaft grinding based on the error parameter of the grinding device and the crankshaft grinding parameter information.
Further, S700 of obtaining the error parameter of the grinding device, and controlling and adjusting the crankshaft grinding based on the error parameter of the grinding device and the crankshaft grinding parameter information in this application further includes the following steps of:
S710: obtaining the error parameter of the grinding device through an acoustic emission sensor;
S720: obtaining a crankshaft grinding compensation parameter according to the error LUS02681 parameter of the grinding device;
S730: performing iterative updating on the crankshaft grinding parameter integrated analysis model based on the crankshaft grinding compensation parameter, so as to obtain a crankshaft grinding parameter integrated optimization analysis model;
S740: amending the error parameter of the grinding device based on the output parameter information of the crankshaft grinding parameter integrated optimization analysis model.
Specifically, during the crankshaft grinding process, wearing phenomenon, such as a grinding machine and a grinding wheel, of the grinding device will inevitably generate. In order to ensure the processing accuracy, it is necessary to detect the diameter change or wearing capacity of the grinding wheel in time. The error parameter of the grinding device is obtained through the acoustic emission sensor. An acoustic emission phenomenon is an elastic wave produced by the rapid release of strain energy caused by the structural change of solid materials. Based on this principle, the acoustic emission sensor is considered to be installed on a grinding carriage, so as to measure an acoustic emission signal during the grinding process of the grinding wheel, thereby obtaining the grinding error parameter produced during the grinding process.
According to the error parameter of the grinding device, the crankshaft grinding precision is subjected to the error compensation during the grinding process, thereby obtaining the crankshaft grinding compensation parameter, for example, increasing grinding feed amount and increasing grinding force. The crankshaft grinding parameter integrated analysis model is subjected to iterative updating based on the crankshaft grinding compensation parameter, so as to obtain the updated crankshaft grinding parameter integrated optimization analysis model; and the error parameter of the grinding device is amended based on the output parameter information of the crankshaft grinding parameter integrated optimization analysis model. The crankshaft grinding is controlled and adjusted through the amended grinding parameter, so that the output parameter is closer to the actual application result, and the output accuracy and updating timeliness of the grinding parameter are improved, thereby ensuring the crankshaft grinding precision quality.
Further, S740 of this application includes the following steps of:
S741: analyzing a formation reason of the error parameter of the grinding device, so as to obtain error formation reason information;
S742: building a crankshaft grinding solution list, which is arranged according to the error formation type;
S743: matching the error formation reason information with the crankshaft grinding solution list, so as to obtain a crankshaft error solution;
S744: eliminating the error parameter of the grinding device based on the crankshaft error solution if the error formation reason information is a limited error.
Specifically, the formation reason of the error parameter of the grinding device is analyzed, so as to obtain error formation reason information, for example, inappropriate grinding wheel granularity, insufficient balance, wearing of the grinding wheel, surface crack of the grinding wheel, vibration of a machine tool. The crankshaft grinding solution list is built and arranged according to the error formation type; different error formation types correspond to the corresponding solution, for example, it may control the roundness of the grinding wheel, reduce the feed amount, replace the grinding wheel, and trim the working parameter of the grinding wheel, etc.
The error formation reason information is matched with the crankshaft grinding solution list, so as to obtain the crankshaft error solution corresponding to the error formation type. If the error formation reason information is a limited error, which can be eliminated by adjusting the working parameter or the using type of the grinding device, the error parameter LUS02681 of the grinding device can be eliminated based on the crankshaft error solution. The error parameter of the grinding device is eliminated by matching a suitable crankshaft error solution, so as to achieve the technical effects of reducing the grinding error, improving the crankshaft grinding precision and grinding efficiency, and then ensuring the crankshaft grinding quality.
In conclusion, this application provides a control adjustment method and a system for a high-efficiency grinding crankshaft, which have the following technical effects: due to adopting the following technical solution: the crankshaft multi-dimensional data information 1s classified through the crankshaft characteristic decision-making tree, so as to obtain the crankshaft characteristic information; the crankshaft image information is subjected to finite element segmentation, so as to obtain the crankshaft image segmentation information; the crankshaft grinding parameter integrated analysis model is built based on the integrated training of the crankshaft characteristic information and the crankshaft image segmentation information, the crankshaft data information to be ground and the crankshaft image information to be ground are input into the crankshaft grinding parameter integrated analysis model, so as to obtain the crankshaft grinding parameter information; and the crankshaft grinding is controlled and adjusted based on the error parameter of the grinding device and the crankshaft grinding parameter information, the technical effects of confirming the crankshaft grinding parameters by building the crankshaft grinding parameter integrated analysis model, improving the crankshaft grinding precision and grinding efficiency, and then ensuring the crankshaft grinding quality are achieved.
Embodiment II
Based on the inventive concept same as the control adjustment method for the high- efficiency grinding crankshaft in the embodiment I, the present disclosure further provides a control adjustment system for a high-efficiency grinding crankshaft, as shown in FIG. 4, the system includes: a data acquisition module 11, which is configured to obtain crankshaft collecting data information, wherein the crankshaft collecting data information includes crankshaft multi- dimensional data information and crankshaft image information; a characteristic classifying module 12, which is configured to build a crankshaft characteristic decision-making tree, and to classify the crankshaft multi-dimensional data information through the crankshaft characteristic decision-making tree, so as to obtain crankshaft characteristic information; an image segmentation module 13, which is configured to perform finite element segmentation on the crankshaft image information, so as to obtain crankshaft image segmentation information; a model building module 14, which is configured to upload the crankshaft characteristic information and the crankshaft image segmentation information to a data integration training platform for learning, so as to build a crankshaft grinding parameter integrated analysis model; a data collecting module 15, which is configured to collect and obtain data information of the crankshaft to be ground and image information of the crankshaft to be ground; a model output module 16, which is configured to input the data information of the crankshaft to be ground and the image information of the crankshaft to be ground in the crankshaft grinding parameter integrated analysis model, so as to obtain crankshaft grinding parameter information; and a control adjustment module 17, which is configured to obtain an error parameter of a grinding device, and to control and adjust the crankshaft grinding based on the error parameter of the grinding device and the crankshaft grinding parameter information.
Further, the model building module further includes: LUS02681 a data training unit, which is configured to input the crankshaft characteristic information and the crankshaft image segmentation information into a deep convolutional neural network for training, so as to build a one-party crankshaft grinding parameter analysis model; a model training unit, which 1s configured to obtain a multi-party crankshaft collecting data information, the multi-party crankshaft collecting data information 1s respectively input into the deep convolutional neural network for distributed training, so as to obtain a multi- party crankshaft grinding parameter analysis model; a parameter extraction unit, which 1s configured to extract training model parameters of the one-party crankshaft grinding parameter analysis model and the multi-party crankshaft grinding parameter analysis model; a model joint training unit, which is configured to perform joint training on the training model parameters through the data integration training platform, so as to obtain the crankshaft grinding parameter integrated analysis model.
Further, the model output module further includes: a model forming unit, which is configured to enable the crankshaft grinding parameter integrated analysis model to include an input layer, an image convolutional logic layer, a hidden layer and an output layer; a model input unit, which is configured to input the image information of the crankshaft to be ground in the image convolutional logic layer through the input layer, so as to output the appearance characteristic of the crankshaft to be ground; a parameter output unit, which is configured to input the data information of the crankshaft to be ground and the appearance characteristic of the crankshaft to be ground in the hidden layer, so as to output the crankshaft grinding parameter information; a model output unit, which is configured to output the crankshaft grinding parameter information through the output layer as a model output result.
Further, the model input unit includes: a characteristic obtaining unit, which is configured to obtain a crankshaft application standard and obtain a predetermined convolutional characteristic set according to the crankshaft application standard, and the predetermined convolutional characteristic set includes a crankshaft curvature characteristic, a smoothness characteristic and a burr value characteristic; a characteristic extraction unit, which is configured to input the image information of the crankshaft to be ground in the image convolutional logic layer for characteristic extraction through the input layer; an image characteristic output unit, which is configured to obtain the output information of the image convolutional logic layer, and the output information includes the appearance characteristic of the crankshaft to be ground that conforms to the predetermined convolutional characteristic set.
Further, the control adjustment module includes: an error parameter obtaining unit, which is configured to obtain the error parameter of the grinding device through an acoustic emission sensor; a compensation parameter obtaining unit, which is configured to obtain a crankshaft grinding compensation parameter according to the error parameter of the grinding device; a model updating unit, which is configured to perform iterative updating on the crankshaft grinding parameter integrated analysis model based on the crankshaft grinding compensation parameter, so as to obtain a crankshaft grinding parameter integrated optimization analysis model; and a parameter amending unit, which is configured to amend the error parameter of the grinding device based on the output parameter information of the crankshaft grinding LUS02681 parameter integrated optimization analysis model.
Further, the system includes: an error formation unit, which is configured to analyze a formation reason of the error parameter of the grinding device, so as to obtain error formation reason information; a scheme building unit, which is configured to build a crankshaft grinding solution list, and the crankshaft grinding solution list is arranged according to the error formation type; a scheme matching unit, which is configured to match the error formation reason information with the crankshaft grinding solution list, so as to obtain a crankshaft error solution; and an error eliminating unit, which is configured to eliminate the error parameter of the grinding device based on the crankshaft error solution if the error formation reason information is a limited error.
Further, the characteristic classifying module includes: a structure classifying unit, which is configured to obtain a crankshaft structural form attribute, and the crankshaft structural form attribute is used as a first crankshaft classification characteristic; a material classifying unit, which is configured to obtain a crankshaft process material attribute, and the crankshaft process material attribute is used as a second crankshaft classification characteristic; an application classifying unit, which is configured to obtain a crankshaft application type attribute, and the crankshaft application type attribute is used as a third crankshaft classification characteristic; and a decision-making tree building unit, which is configured to build the crankshaft characteristic decision-making tree based on the first crankshaft classification characteristic, the second crankshaft classification characteristic and the third crankshaft classification characteristic.
This application provides a control adjustment method for a high-efficiency grinding crankshaft, and the method includes the following steps of: obtaining the crankshaft collecting data information, which includes the crankshaft multi-dimensional data information and the crankshaft image information; building the crankshaft characteristic decision-making tree, and classifying the crankshaft multi-dimensional data information through the crankshaft characteristic decision-making tree, so as to obtain the crankshaft characteristic information; performing finite element segmentation on the crankshaft image information, so as to obtain the crankshaft image segmentation information; uploading the crankshaft characteristic information and the crankshaft image segmentation information to the data integration training platform for learning, so as to build the crankshaft grinding parameter integrated analysis model; collecting and obtaining the data information of the crankshaft to be ground and the image information of the crankshaft to be ground; inputting the data information of the crankshaft to be ground and the image information of the crankshaft to be ground in the crankshaft grinding parameter integrated analysis model, so as to obtain the crankshaft grinding parameter information; and obtaining the error parameter of the grinding device, and controlling and adjusting the crankshaft grinding based on the error parameter of the grinding device and the crankshaft grinding parameter information.
The technical problem of grinding quality of the crankshaft affected by the low crankshaft grinding precision and long time is solved; and the technical effects of confirming the crankshaft grinding parameters by building the crankshaft grinding parameter integrated analysis model, improving the crankshaft grinding precision and grinding efficiency, and then ensuring the crankshaft grinding quality are achieved.
The specification and the drawings are merely the illustrative description of this application.
If these modifications and variations of the present disclosure belong to the scope LU502681 of equivalent technology thereof of the present disclosure, the present disclosure is intended to include these modifications and variations.
Claims (8)
1. A control adjustment method for a high-efficiency grinding crankshaft, wherein the method comprises the following steps of: obtaining crankshaft collecting data information, which comprises crankshaft multi- dimensional data information and crankshaft image information; building a crankshaft characteristic decision-making tree, and classifying the crankshaft multi-dimensional data information through the crankshaft characteristic decision-making tree, so as to obtain crankshaft characteristic information; performing finite element segmentation on the crankshaft image information, so as to obtain crankshaft image segmentation information; uploading the crankshaft characteristic information and the crankshaft image segmentation information to a data integration training platform for learning, so as to build a crankshaft grinding parameter integrated analysis model; collecting and obtaining data information of the crankshaft to be ground and image information of the crankshaft to be ground; inputting the data information of the crankshaft to be ground and the image information of the crankshaft to be ground in the crankshaft grinding parameter integrated analysis model, so as to obtain crankshaft grinding parameter information; and obtaining an error parameter of a grinding device, and controlling and adjusting the crankshaft grinding based on the error parameter of the grinding device and the crankshaft grinding parameter information.
2. The method according to claim 1, wherein the step of uploading the crankshaft characteristic information and the crankshaft image segmentation information to the data integration training platform for learning, so as to build the crankshaft grinding parameter integrated analysis model comprises the following steps of: inputting the crankshaft characteristic information and the crankshaft image segmentation information into a deep convolutional neural network for training, so as to build a one-party crankshaft grinding parameter analysis model; obtaining multi-party crankshaft collecting data information, which is respectively input into the deep convolutional neural network for distributed training, so as to obtain a multi-party crankshaft grinding parameter analysis model; extracting training model parameters of the one-party crankshaft grinding parameter analysis model and the multi-party crankshaft grinding parameter analysis model; and performing joint training on the training model parameters through the data integration training platform, so as to obtain the crankshaft grinding parameter integrated analysis model.
3. The method according to claim 1, wherein the step of inputting the data information of the crankshaft to be ground and the image information of the crankshaft to be ground in the crankshaft grinding parameter integrated analysis model, so as to obtain the crankshaft grinding parameter information comprises the following steps of: the crankshaft grinding parameter integrated analysis model comprising an input layer, an image convolutional logic layer, a hidden layer and an output layer; inputting the image information of the crankshaft to be ground in the image convolutional logic layer through the input layer, so as to output the appearance characteristic of the crankshaft to be ground; inputting the data information of the crankshaft to be ground and the appearance characteristic of the crankshaft to be ground in the hidden layer, so as to output the crankshaft grinding parameter information; and outputting the crankshaft grinding parameter information through the output layer as a model output result.
4. The method according to claim 3, wherein the step of inputting the image information LUS02681 of the crankshaft to be ground in the image convolutional logic layer through the input layer, so as to output the appearance characteristic of the crankshaft to be ground comprises the following steps of: obtaining a crankshaft application standard, obtaining a predetermined convolutional characteristic set according to the crankshaft application standard, wherein the predetermined convolutional characteristic set comprises a crankshaft curvature characteristic, a smoothness characteristic and a burr value characteristic: inputting the image information of the crankshaft to be ground in the image convolutional logic layer for characteristic extraction through the input layer; and obtaining the output information of the image convolutional logic layer, wherein the output information comprises the appearance characteristic of the crankshaft to be ground that conforms to the predetermined convolutional characteristic set.
5. The method according to claim 1, wherein the step of obtaining the error parameter of the grinding device, and controlling and adjusting the crankshaft grinding based on the error parameter of the grinding device and the crankshaft grinding parameter information comprises the following steps of: obtaining the error parameter of the grinding device through an acoustic emission sensor; obtaining a crankshaft grinding compensation parameter according to the error parameter of the grinding device; performing iterative updating on the crankshaft grinding parameter integrated analysis model based on the crankshaft grinding compensation parameter, so as to obtain a crankshaft grinding parameter integrated optimization analysis model; and amending the error parameter of the grinding device based on output parameter information of the crankshaft grinding parameter integrated optimization analysis model.
6. The method according to claim 5, wherein the method further comprises the following steps of: analyzing a formation reason of the error parameter of the grinding device, so as to obtain error formation reason information; building a crankshaft grinding solution list, which is arranged according to an error formation type; matching the error formation reason information with the crankshaft grinding solution list, so as to obtain a crankshaft error solution; and eliminating the error parameter of the grinding device based on the crankshaft error solution if the error formation reason information is a limited error.
7. The method according to claim 1, wherein the steps of building the crankshaft characteristic decision-making tree comprises the following steps of: obtaining a crankshaft structural form attribute, which is used as a first crankshaft classification characteristic; obtaining a crankshaft process material attribute, which is used as a second crankshaft classification characteristic; obtaining a crankshaft application type attribute, which is used as a third crankshaft classification characteristic; and building the crankshaft characteristic decision-making tree based on the first crankshaft classification characteristic, the second crankshaft classification characteristic and the third crankshaft classification characteristic.
8. A control adjustment system for a high-efficiency grinding crankshaft, wherein the system comprises: a data acquisition module, which is configured to obtain crankshaft collecting data information, wherein the crankshaft collecting data information comprises crankshaft multi-
dimensional data information and crankshaft image information; LU502681 a characteristic classifying module, which is configured to build a crankshaft characteristic decision-making tree, and to classify the crankshaft multi-dimensional data information through the crankshaft characteristic decision-making tree, so as to obtain crankshaft characteristic information;
an image segmentation module, which is configured to perform finite element segmentation on the crankshaft image information, so as to obtain crankshaft image segmentation information;
a model building module, which is configured to upload the crankshaft characteristic information and the crankshaft image segmentation information to a data integration training platform for learning, so as to build a crankshaft grinding parameter integrated analysis model;
a data collecting module, which is configured to collect and obtain data information of the crankshaft to be ground and image information of the crankshaft to be ground;
a model output module, which is configured to input the data information of the crankshaft to be ground and the image information of the crankshaft to be ground in the crankshaft grinding parameter integrated analysis model, so as to obtain crankshaft grinding parameter information; and a control adjustment module, which is configured to obtain an error parameter of a grinding device, and to control and adjust the crankshaft grinding based on the error parameter of the grinding device and the crankshaft grinding parameter information.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210790158.8A CN115091283B (en) | 2022-07-06 | 2022-07-06 | Control and adjustment method and system for efficient grinding of crankshaft |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| LU502681B1 true LU502681B1 (en) | 2023-02-20 |
Family
ID=83297736
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| LU502681A LU502681B1 (en) | 2022-07-06 | 2022-08-18 | Control adjustment method and system for high-efficiency grinding crankshaft |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115091283B (en) |
| LU (1) | LU502681B1 (en) |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2061554B (en) * | 1979-10-18 | 1984-02-01 | Gfm Fertigungstechnik | Control system for producing crankshafts |
| DE69704165T2 (en) * | 1996-09-13 | 2001-08-23 | Unova U.K. Ltd., Aylesbury | IMPROVEMENTS IN / OR REGARDING WORKPIECE GRINDING |
| GB9909279D0 (en) * | 1999-04-23 | 1999-06-16 | Unova Uk Ltd | Improvements in and relating to workrests |
| IT1321212B1 (en) * | 2000-03-06 | 2003-12-31 | Marposs Spa | PIN DIAMETER CONTROL EQUIPMENT. |
| CN108481102A (en) * | 2018-03-22 | 2018-09-04 | 天润曲轴股份有限公司 | A kind of method of interpolation grinding crankshaft fillet |
| CN108763803B (en) * | 2018-06-04 | 2021-09-10 | 东华大学 | Grinding machine analysis method based on crankshaft connecting rod neck follow-up grinding profile error decomposition |
| CN112884770B (en) * | 2021-04-28 | 2021-07-02 | 腾讯科技（深圳）有限公司 | Image segmentation processing method and device and computer equipment |
| CN114037709B (en) * | 2021-11-05 | 2023-06-16 | 复旦大学附属肿瘤医院 | Method and device for segmenting ground glass lung nodules |
| CN114153816A (en) * | 2021-11-25 | 2022-03-08 | 山东理工大学 | Remote grinding database management system with user-basis-process-knowledge progressive structure and high-efficiency and low-consumption intelligent grinding method |
| CN114161240B (en) * | 2021-12-15 | 2023-03-24 | 清华大学 | Grinding surface shape prediction method, grinding system and terminal equipment |
| CN114571326B (en) * | 2022-01-20 | 2023-04-07 | 上海交通大学 | Method, device and system for grinding deformed curved surface based on computer vision |
| CN114536110B (en) * | 2022-03-03 | 2023-03-24 | 华辰精密装备（昆山）股份有限公司 | Error real-time compensation method for non-circular component complex contour grinding |
-
2022
- 2022-07-06 CN CN202210790158.8A patent/CN115091283B/en active Active
- 2022-08-18 LU LU502681A patent/LU502681B1/en active IP Right Grant
Also Published As
| Publication number | Publication date |
|---|---|
| CN115091283A (en) | 2022-09-23 |
| CN115091283B (en) | 2023-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108907896B (en) | A kind of cutter remaining life on-line prediction method and system | |
| CN113688558B (en) | Automobile driving condition construction method and system based on large database sample | |
| CN109615113A (en) | A kind of marine diesel important Parts processing quality prediction technique twin based on number | |
| CN111633467B (en) | Cutter wear state monitoring method based on one-dimensional depth convolution automatic encoder | |
| CN114619292B (en) | Milling cutter wear monitoring method based on fusion of wavelet denoising and attention mechanism with GRU network | |
| CN110263474A (en) | A kind of cutter life real-time predicting method of numerically-controlled machine tool | |
| Wang et al. | A sequence-to-sequence model with attention and monotonicity loss for tool wear monitoring and prediction | |
| CN115422814B (en) | Digital twin-driven closed-loop optimization design method for complex electromechanical product | |
| CN113869208A (en) | Rolling bearing fault diagnosis method based on SA-ACWGAN-GP | |
| LU502681B1 (en) | Control adjustment method and system for high-efficiency grinding crankshaft | |
| CN111075647B (en) | ELM-based maximum wind energy capture method for variable-speed wind turbine generator | |
| CN110889239B (en) | Aviation gas turbine engine modeling method based on flight parameter data identification | |
| CN112487715A (en) | Method for optimizing reliability of process parameters of key hole system of marine diesel engine body | |
| CN114817371A (en) | XGboost-based vehicle driving condition identification method | |
| CN113569453B (en) | Migration method of digital twin product model oriented to processing | |
| CN111421386A (en) | Method for monitoring wear state of micro-milling cutter based on manifold learning method | |
| Li et al. | CNN-GRU network-based force prediction approach for variable working condition milling clamping points of deformable parts | |
| CN113128120A (en) | Method for constructing typical running condition of automobile crane | |
| CN111191510B (en) | Relation network-based remote sensing image small sample target identification method in complex scene | |
| CN114970049B (en) | Electric spindle thermal error prediction method with variable bearing pretightening force | |
| CN116910513A (en) | Centrifugal pump rotor fault diagnosis method based on CWGAN-GP and double-flow CNN model | |
| CN112861272A (en) | Digital twin-based method for analyzing process feasibility of complex parts of marine diesel engine | |
| CN115496107A (en) | Aero-engine main shaft bearing full life cycle analysis method based on digital twinning | |
| JP2003508841A (en) | Assembling based on features | |
| CN111581743A (en) | Defect risk assessment method based on casting simulation software |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FG | Patent granted |
Effective date: 20230220 |