CN115091283A - Control and adjustment method and system for efficiently grinding crankshaft - Google Patents
Control and adjustment method and system for efficiently grinding crankshaft Download PDFInfo
- Publication number
- CN115091283A CN115091283A CN202210790158.8A CN202210790158A CN115091283A CN 115091283 A CN115091283 A CN 115091283A CN 202210790158 A CN202210790158 A CN 202210790158A CN 115091283 A CN115091283 A CN 115091283A
- Authority
- CN
- China
- Prior art keywords
- crankshaft
- information
- grinding
- parameter
- ground
- 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.)
- Granted
Links
Images
Classifications
-
- 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
- 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
-
- 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)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Quality & Reliability (AREA)
- Robotics (AREA)
- Grinding Of Cylindrical And Plane Surfaces (AREA)
Abstract
The invention discloses a control and adjustment method and a control and adjustment system for efficiently grinding a crankshaft, which relate to the technical field of artificial intelligence, and the method comprises the following steps: classifying multi-dimensional data information of the crankshafts through a crankshaft characteristic decision tree to obtain crankshaft characteristic information; carrying out finite element segmentation on the crankshaft image information to obtain crankshaft image segmentation information; performing ensemble learning based on the crankshaft characteristic information and the crankshaft image segmentation information, and constructing a crankshaft grinding parameter ensemble analysis model; inputting crankshaft data information to be ground and crankshaft image information to be ground into the crankshaft grinding parameter integrated analysis model to obtain crankshaft grinding parameter information; and acquiring error parameters of the grinding device, and controlling and adjusting the crankshaft grinding based on the error parameters of the grinding device and the crankshaft grinding parameter information. The technical effects that crankshaft grinding parameters are determined by constructing a crankshaft grinding parameter integrated analysis model, the crankshaft grinding precision and the grinding efficiency are improved, and the crankshaft grinding quality is further ensured are achieved.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a control and adjustment method and system for efficiently grinding a crankshaft.
Background
The crankshaft is the core part for ensuring the normal operation of the engine, is the key part of the piston engine, bears the force transmitted by the connecting rod, converts the force into torque, outputs the torque through the crankshaft and drives other accessories on the engine to work, and plays an important role in bearing impact load and transmitting power in the engines of cars, trucks, motorcycles, ships, aeromodelling and lawnmowers. For this purpose, each point on the crankshaft, such as the flange end, the head end, the main journal and the connecting rod journal, must be precisely ground.
However, the prior art has the technical problems that the grinding precision of the crankshaft is low, the time consumption is long, and the grinding quality of the crankshaft is influenced.
Disclosure of Invention
The application solves the technical problems that the grinding precision of the crankshaft is low and the time consumption is long, and the grinding quality of the crankshaft is affected in the prior art, and achieves the technical effects that the grinding precision and the grinding efficiency of the crankshaft are improved by establishing a crankshaft grinding parameter integrated analysis model to determine the grinding parameters of the crankshaft, and further the grinding quality of the crankshaft is ensured.
In view of the above problems, the present invention provides a control and adjustment method and system for efficiently grinding a crankshaft.
In a first aspect, the present application provides a control and adjustment method for efficiently grinding a crankshaft, the method comprising: acquiring crankshaft acquisition data information, wherein the crankshaft acquisition data information comprises crankshaft multi-dimensional data information and crankshaft image information; constructing a crankshaft characteristic decision tree, and classifying the crankshaft multi-dimensional data information through the crankshaft characteristic decision tree to obtain crankshaft characteristic information; carrying out finite element segmentation on the crankshaft image information 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, and constructing a crankshaft grinding parameter integration analysis model; acquiring data information and image information of a crankshaft to be ground; inputting the crankshaft data information to be ground and the crankshaft image information to be ground into the crankshaft grinding parameter integrated analysis model to obtain crankshaft grinding parameter information; and acquiring error parameters of the grinding device, and controlling and adjusting the crankshaft grinding based on the error parameters of the grinding device and the crankshaft grinding parameter information.
In another aspect, the present application further provides a control adjustment system for efficiently grinding a crankshaft, the system comprising: the data acquisition module is used for acquiring crankshaft acquisition data information, wherein the crankshaft acquisition data information comprises crankshaft multi-dimensional data information and crankshaft image information; the characteristic classification module is used for constructing a crankshaft characteristic decision tree, and classifying the crankshaft multi-dimensional data information through the crankshaft characteristic decision tree to obtain crankshaft characteristic information; the image segmentation module is used for carrying out finite element segmentation on the crankshaft image information to obtain crankshaft image segmentation information; the model building module is used for uploading the crankshaft characteristic information and the crankshaft image segmentation information to a data integration training platform for learning and building a crankshaft grinding parameter integration analysis model; the data acquisition module is used for acquiring and acquiring data information of the crankshaft to be ground and image information of the crankshaft to be ground; the model output module is used for inputting the crankshaft to be ground data information and the crankshaft image information to be ground into the crankshaft grinding parameter integrated analysis model to obtain crankshaft grinding parameter information; and the control adjustment module is used for acquiring error parameters of the grinding device and controlling and adjusting the crankshaft grinding based on the error parameters of the grinding device and the crankshaft grinding parameter information.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
the crankshaft multi-dimensional data information is classified through a crankshaft characteristic decision tree to obtain crankshaft characteristic information, finite element segmentation is carried out on the crankshaft image information to obtain crankshaft image segmentation information, a crankshaft grinding parameter integrated analysis model is constructed based on crankshaft characteristic information and crankshaft image segmentation information integrated training, and crankshaft data information to be ground and crankshaft image information to be ground are input into the crankshaft grinding parameter integrated analysis model to obtain crankshaft grinding parameter information; and controlling and adjusting the crankshaft grinding based on the error parameters of the grinding device and the crankshaft grinding parameter information. And then, the technical effects of determining the grinding parameters of the crankshaft by constructing a crankshaft grinding parameter integrated analysis model, improving the grinding precision and the grinding efficiency of the crankshaft and further ensuring the grinding quality of the crankshaft are achieved.
Drawings
FIG. 1 is a schematic flow chart illustrating a control and adjustment method for efficiently grinding a crankshaft according to the present application;
FIG. 2 is a schematic flow chart illustrating the construction of a crankshaft grinding parameter integrated analysis model in the control and adjustment method for efficiently grinding the crankshaft according to the present application;
FIG. 3 is a schematic flow chart illustrating the process of obtaining crankshaft grinding parameter information in the control and adjustment method for efficiently grinding the crankshaft according to the present invention;
FIG. 4 is a schematic structural diagram of a control and adjustment system for efficiently grinding a crankshaft according to the present application;
description of reference numerals: the system comprises a data acquisition module 11, a feature classification module 12, an image segmentation module 13, a model construction module 14, a data acquisition module 15, a model output module 16 and a control adjustment module 17.
Detailed Description
The application provides a control adjustment method system for efficiently grinding the crankshaft, solves the technical problems that the grinding precision of the crankshaft is low and the time consumption is long, and the grinding quality of the crankshaft is affected in the prior art, and achieves the technical effects that the grinding precision and the grinding efficiency of the crankshaft are improved by establishing a crankshaft grinding parameter integrated analysis model to determine the grinding parameters of the crankshaft, and further the grinding quality of the crankshaft is ensured.
Example one
As shown in fig. 1, the present application provides a control adjustment method for efficiently grinding a crankshaft, the method comprising:
step S100: acquiring crankshaft acquisition data information, wherein the crankshaft acquisition data information comprises crankshaft multi-dimensional data information and crankshaft image information;
specifically, the crankshaft is a core component for ensuring the normal operation of the engine, is a key component of a piston engine, bears the force transmitted by a connecting rod, converts the force into torque, outputs the torque through the crankshaft, drives other accessories on the engine to work, and plays an important role in bearing impact load and transmitting power in the engines of cars, trucks, motorcycles, ships, models and lawnmowers. For this purpose, each point on the crankshaft, such as the flange end, the head end, the main journal and the connecting rod journal, must be precisely ground.
The method comprises the steps of acquiring crankshaft data information, wherein the crankshaft acquired data information comprises crankshaft multi-dimensional data information and crankshaft image information, the crankshaft multi-dimensional data information comprises various information such as crankshaft types, materials, structure sizes and application purposes, the crankshaft image information comprises information such as crankshaft colors, structures and surface features, the crankshaft data information is comprehensively acquired, and the follow-up model training result is guaranteed to be more accurate.
Step S200: constructing a crankshaft characteristic decision tree, and classifying the crankshaft multi-dimensional data information through the crankshaft characteristic decision tree to obtain crankshaft characteristic information;
further, in the step S200 of constructing a crankshaft feature decision tree, the method further includes:
step S210: obtaining a crankshaft structural form attribute, and taking the crankshaft structural form attribute as a first crankshaft classification feature;
step S220: obtaining crankshaft process material attributes, and taking the crankshaft process material attributes as second crankshaft classification features;
step S230: obtaining crankshaft application type attributes, and taking the crankshaft application type attributes as third crankshaft classification features;
step S240: constructing the crankshaft feature decision tree based on the first crankshaft classification feature, the second crankshaft classification feature, and the third crankshaft classification feature.
Specifically, to construct a crankshaft feature decision tree in particular, crankshaft classification features are first determined. The structural form attributes of the crankshafts are used as first crankshaft classification features, the structural form attributes of the crankshafts are classified according to the crankshaft structure, the main structure of the crankshaft comprises a crankshaft main journal, a connecting rod journal, a crankshaft arm, a front journal, a rear journal and the like, and the crankshafts can be divided into an integral crankshaft, a combined crankshaft, a disc type crankshaft and the like according to the structural composition types. And taking the technological material attribute of the crankshaft as a second crankshaft classification characteristic, wherein the technological material attribute of the crankshaft is a manufacturing material of the crankshaft, including forged steel crankshafts, cast iron crankshafts and the like, and the material properties and the grinding force are correspondingly different.
And taking the crankshaft application type attribute as a third crankshaft classification characteristic, wherein 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 the like, and different application attributes and crankshaft requirements are different. The decision tree is a decision analysis method for calculating the probability that the expected value of the net present value is greater than or equal to zero by forming the decision tree on the basis of the known occurrence probability of various conditions and judging the feasibility of the decision tree, is a graphical method for intuitively applying probability analysis, can give correct classification to newly-appeared objects, and consists of a root node, an internal node and a leaf node.
And respectively taking the first crankshaft classification characteristic, the second crankshaft classification characteristic and the third crankshaft classification characteristic as internal nodes of the crankshaft characteristic decision tree, and performing information entropy calculation on the internal nodes to preferentially classify the characteristic with the minimum entropy value, so as to recursively construct the crankshaft characteristic decision tree. And classifying the crankshaft multi-dimensional data information through the crankshaft characteristic decision tree to obtain corresponding crankshaft characteristic information, namely a crankshaft characteristic classification result, which comprises structural form characteristics, process material characteristics, application type characteristics and the like. Crankshaft multi-dimensional data classification is carried out through the accuracy construction of the crankshaft characteristic decision tree, so that the accuracy and the specificity of a crankshaft data processing result are improved.
Step S300: carrying out finite element segmentation on the crankshaft image information to obtain crankshaft image segmentation information;
specifically, the crankshaft image information is subjected to finite element segmentation, the crankshaft image information is segmented into a plurality of image grids according to the image structure size attribute of the crankshaft, the more the grids are segmented, the richer the detail display of the image is, the crankshaft image segmentation information is obtained, and the more accurate and efficient the subsequent analysis on the image appearance characteristics is facilitated.
Step S400: uploading the crankshaft characteristic information and the crankshaft image segmentation information to a data integration training platform for learning, and constructing a crankshaft grinding parameter integration analysis model;
as shown in fig. 2, further, uploading the crankshaft feature information and the crankshaft image segmentation information to a data integration training platform for learning, and constructing a crankshaft grinding parameter integration analysis model, in which step S400 of the present application further includes:
step S410: inputting the crankshaft characteristic information and the crankshaft image segmentation information into a deep convolution neural network for training, and constructing a crankshaft grinding parameter analysis model;
step S420: acquiring multi-part crankshaft acquisition data information, and respectively inputting the multi-part crankshaft acquisition data information into the deep convolution neural network for distributed training to acquire a multi-part crankshaft grinding parameter analysis model;
step S430: extracting training model parameters of the one-side crankshaft grinding parameter analysis model and the multi-side crankshaft grinding parameter analysis model;
step S440: and the data integration training platform performs combined training on the training model parameters to obtain the crankshaft grinding parameter integration analysis model.
Specifically, the crankshaft feature information and the crankshaft image segmentation information are uploaded to a data integration training platform for learning, and the data integration training platform is used for training a plurality of source data models, so that the final model construction is more reasonable and accurate. Firstly, the crankshaft feature information and the crankshaft image segmentation information are input into a deep convolutional neural network for training, the deep convolutional neural network is a feed-forward neural network which comprises convolution calculation and has a deep structure, and the feature recognition stability is high. And a crankshaft grinding parameter analysis model is constructed according to the training and is used for crankshaft data processing in the platform or the enterprise so as to analyze the crankshaft grinding parameter information. In order to more accurately and comprehensively analyze the crankshaft grinding parameters, similarly, crankshaft data acquisition is carried out on other platforms or enterprises, and the multi-part crankshaft acquisition data information is respectively input into the deep convolutional neural network for distributed training to obtain a multi-part crankshaft grinding parameter analysis model corresponding to the multi-part crankshaft grinding parameter analysis model.
And extracting training model parameters of the one-side crankshaft grinding parameter analysis model and the multi-side crankshaft grinding parameter analysis model, wherein the training model parameters comprise crankshaft parameters, crankshaft grinding types, grinding speeds, grinding force parameters, corresponding weights of the models and the like. The data integration training platform is right training model parameters carry out the joint training, establish behind the integrated training of federal crankshaft grinding parameter integrated analysis model, training process factor of safety is high for after carrying out parameter federal study crankshaft grinding parameter integrated analysis model's output result is reasonable more accurate, and application scope is more comprehensive, and then guarantees bent axle grinding quality.
Step S500: acquiring data information and image information of a crankshaft to be ground;
specifically, in order to ensure the grinding accuracy of the crankshaft to be ground, the data information of the crankshaft to be ground and the image information of the crankshaft to be ground are acquired and obtained, wherein the data information comprises various information such as the type, the material, the structure size, the application purpose, the structure of the crankshaft, the surface characteristics and the like of the crankshaft to be ground, so that the accuracy of the model for outputting grinding parameters is ensured.
Step S600: inputting the crankshaft data information to be ground and the crankshaft image information to be ground into the crankshaft grinding parameter integrated analysis model to obtain crankshaft grinding parameter information;
as shown in fig. 3, further, the step S600 of obtaining the crankshaft grinding parameter information by inputting the crankshaft data information to be ground and the crankshaft image information to be ground into the crankshaft grinding parameter integrated analysis model further includes:
step S610: the crankshaft grinding parameter integrated analysis model comprises an input layer, an image convolution logic layer, a hidden layer and an output layer;
step S620: inputting the image information of the crankshaft to be ground into the image convolution logic layer through an input layer, and outputting the appearance characteristics of the crankshaft to be ground;
step S630: inputting the data information of the crankshaft to be ground and the appearance characteristic of the crankshaft to be ground into the hidden layer, and outputting the grinding parameter information of the crankshaft;
step S640: and outputting the crankshaft grinding parameter information as a model output result through the output layer.
Further, the step S620 of inputting the image information of the crankshaft to be ground into the image convolution logic layer through the input layer and outputting the appearance characteristics of the crankshaft to be ground further includes:
step S621: acquiring a crankshaft application standard, and acquiring a preset convolution characteristic set according to the crankshaft application standard, wherein the preset convolution characteristic set comprises a crankshaft curvature characteristic, a smoothness characteristic and a burr value characteristic;
step S622: inputting the crankshaft image information to be ground into the image convolution logic layer through an input layer for feature extraction;
step S623: and obtaining output information of the image convolution logic layer, wherein the output information comprises the appearance characteristics of the crankshaft to be ground, which accord with the preset convolution characteristic set.
Specifically, 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, and the crankshaft grinding parameter integrated analysis model specifically comprises an input layer, an image convolution logic layer, a hidden layer and an output layer. And inputting the image information of the crankshaft to be ground into the image convolution logic layer through an input layer, wherein the image convolution logic layer is used for extracting image characteristics.
Specifically, a crankshaft application standard is obtained firstly, the crankshaft application standard is an appearance standard which can be practically applied to a crankshaft, and a preset convolution characteristic set is obtained according to the crankshaft application standard and comprises a crankshaft curvature characteristic, a surface smoothness characteristic and a surface burr value characteristic requirement standard. Inputting the to-be-ground crankshaft image information into the image convolution logic layer through an input layer for feature extraction, namely performing convolution operation on image features to obtain output information of the image convolution logic layer, wherein the output information comprises the to-be-ground crankshaft appearance features which accord with the preset convolution feature set, namely the image appearance features which accord with application standards.
And inputting the data information of the crankshaft to be ground and the appearance characteristics of the crankshaft to be ground into the hidden layer, wherein the hidden layer is used for carrying out crankshaft grinding parameter analysis through crankshaft multidimensional data characteristics and image characteristics, training can be carried out through historical data, and crankshaft grinding parameter information is output. The crankshaft grinding parameter information comprises grinding force, grinding speed, grinding route, grinding angle and the like, and is output through the output layer as a model output result. Crankshaft grinding parameters are determined by constructing a crankshaft grinding parameter integrated analysis model, so that the crankshaft grinding parameters output by the model are more reasonable and accurate, and the crankshaft grinding precision and the grinding efficiency are improved.
Step S700: and acquiring error parameters of the grinding device, and controlling and adjusting the crankshaft grinding based on the error parameters of the grinding device and the crankshaft grinding parameter information.
Further, acquiring an error parameter of the wear device, and controlling and adjusting the crankshaft grinding based on the error parameter of the wear device and the crankshaft grinding parameter information, step S700 further includes:
step S710: acquiring error parameters of the grinding device through an acoustic emission sensor;
step S720: obtaining a crankshaft grinding compensation parameter according to the error parameter of the grinding device;
step S730: iteratively updating the crankshaft grinding parameter integrated analysis model based on the crankshaft grinding compensation parameters to obtain a crankshaft grinding parameter integrated optimization analysis model;
step S740: and correcting the error parameters of the abrasion device based on the output parameter information of the crankshaft grinding parameter integrated optimization analysis model.
Specifically, during the grinding of the crankshaft, wear of the grinding device, such as a grinding machine or a grinding wheel, inevitably occurs, and it is necessary to detect the change in diameter or the amount of wear of the grinding wheel in time in order to ensure machining accuracy. The method is characterized in that an acoustic emission sensor is used for obtaining the error parameters of the grinding device, wherein the acoustic emission phenomenon is elastic waves generated by rapid release of strain energy of a solid material caused by structural change, and based on the principle, the acoustic emission sensor is considered to be arranged on a grinding carriage and used for measuring acoustic emission signals in the grinding process of a grinding wheel, so that the abrasion error parameters generated in the grinding process of the grinding wheel are obtained.
According to the error parameters of the grinding device, the error compensation needs to be carried out on the grinding precision of the crankshaft in the grinding process, so that crankshaft grinding compensation parameters, such as parameters of increasing grinding feed amount, increasing grinding force and the like, are obtained. And iteratively updating the crankshaft grinding parameter integrated analysis model based on the crankshaft grinding compensation parameters to obtain an updated crankshaft grinding parameter integrated optimization analysis model, and correcting the error parameters of the abrasion device based on the output parameter information of the crankshaft grinding parameter integrated optimization analysis model. The crankshaft grinding is controlled and adjusted through the corrected grinding parameters, so that the output parameters are more fit with the practical application effect, the output accuracy and the updating real-time performance of the grinding parameters are improved, and the grinding precision quality of the crankshaft is further ensured.
Further, step S740 of the present application further includes:
step S741: analyzing generation reasons of the error parameters of the grinding device to obtain error generation reason information;
step S742: constructing a crankshaft grinding solution list, wherein the crankshaft grinding solution list is arranged according to an error generation type;
step S743: matching the error generation reason information with the crankshaft grinding solution list to obtain a crankshaft error solution;
step S744: and if the error generation reason information is a limitation error, eliminating the error parameter of the grinding device based on the crankshaft error solution.
Specifically, the generation cause analysis is performed on the grinding device error parameters to obtain error generation cause information, such as an improper grinding wheel grain size, an insufficient balance degree, grinding wheel wear, grinding wheel surface cracks, machine tool vibration, and the like. And constructing a crankshaft grinding solution list, wherein the crankshaft grinding solution list is arranged according to error generation types, and different error generation types correspond to corresponding solutions, and illustratively, the roundness of the grinding wheel can be controlled, the feeding amount can be reduced, the grinding wheel can be replaced, the working parameters of the grinding wheel can be trimmed, and the like.
And matching the error generation reason information with the crankshaft grinding solution list to obtain a crankshaft error solution corresponding to the error generation type, wherein if the error generation reason information is a limitation error, the limitation error is an error which can be eliminated by adjusting the working parameters or the use type of the grinding device, and the error parameters of the grinding device are eliminated based on the crankshaft error solution. The error parameters of the grinding device are eliminated by matching a proper crankshaft error solution, so that the technical effects of reducing grinding errors, improving the grinding precision and the grinding efficiency of the crankshaft and further ensuring the grinding quality of the crankshaft are achieved.
In summary, the control and adjustment method and system for efficiently grinding the crankshaft provided by the present application have the following technical effects:
the crankshaft multi-dimensional data information is classified through a crankshaft characteristic decision tree to obtain crankshaft characteristic information, finite element segmentation is carried out on the crankshaft image information to obtain crankshaft image segmentation information, a crankshaft grinding parameter integrated analysis model is constructed based on crankshaft characteristic information and crankshaft image segmentation information integrated training, and crankshaft data information to be ground and crankshaft image information to be ground are input into the crankshaft grinding parameter integrated analysis model to obtain crankshaft grinding parameter information; and controlling and adjusting the crankshaft grinding based on the error parameters of the grinding device and the crankshaft grinding parameter information. And then, the technical effects that the crankshaft grinding parameters are determined by constructing a crankshaft grinding parameter integrated analysis model, the crankshaft grinding precision and the grinding efficiency are improved, and the crankshaft grinding quality is further ensured are achieved.
Example two
Based on the same inventive concept as the control and adjustment method for the high-efficiency grinding crankshaft in the previous embodiment, the invention further provides a control and adjustment system for the high-efficiency grinding crankshaft, as shown in fig. 4, the system comprises:
the data acquisition module 11 is configured to acquire crankshaft acquisition data information, where the crankshaft acquisition data information includes crankshaft multidimensional data information and crankshaft image information;
the characteristic classification module 12 is configured to construct a crankshaft characteristic decision tree, and classify the crankshaft multi-dimensional data information through the crankshaft characteristic decision tree to obtain crankshaft characteristic information;
the image segmentation module 13 is configured to perform finite element segmentation on the crankshaft image information to obtain crankshaft image segmentation information;
the model construction module 14 is used for uploading the crankshaft characteristic information and the crankshaft image segmentation information to a data integration training platform for learning and constructing a crankshaft grinding parameter integration analysis model;
the data acquisition module 15 is used for acquiring and acquiring data information of the crankshaft to be ground and image information of the crankshaft to be ground;
the model output module 16 is used for inputting the crankshaft data information to be ground and the crankshaft image information to be ground into the crankshaft grinding parameter integrated analysis model to obtain crankshaft grinding parameter information;
and the control adjusting module 17 is used for acquiring error parameters of the grinding device and controlling and adjusting the crankshaft grinding based on the error parameters of the grinding device and the crankshaft grinding parameter information.
Further, the model building module further comprises:
the data training unit is used for inputting the crankshaft characteristic information and the crankshaft image segmentation information into a deep convolution neural network for training and constructing a crankshaft grinding parameter analysis model;
the model training unit is used for acquiring data information acquired by a plurality of crankshafts, and respectively inputting the data information acquired by the plurality of crankshafts into the deep convolution neural network for distributed training to acquire a grinding parameter analysis model of the plurality of crankshafts;
the parameter extraction unit is used for extracting training model parameters of the one-side crankshaft grinding parameter analysis model and the multi-side crankshaft grinding parameter analysis model;
and the model combined training unit is used for performing combined training on the training model parameters by the data integrated training platform to obtain the crankshaft grinding parameter integrated analysis model.
Further, the model output module further includes:
the model forming unit is used for the crankshaft grinding parameter integrated analysis model to comprise an input layer, an image convolution logic layer, a hidden layer and an output layer;
the model input unit is used for inputting the image information of the crankshaft to be ground into the image convolution logic layer through an input layer and outputting the appearance characteristics of the crankshaft to be ground;
the parameter output unit is used for inputting the data information of the crankshaft to be ground and the appearance characteristic of the crankshaft to be ground into the hidden layer and outputting the grinding parameter information of the crankshaft;
and the model output unit is used for outputting the crankshaft grinding parameter information as a model output result through the output layer.
Further, the model input unit further includes:
the characteristic acquisition unit is used for acquiring a crankshaft application standard and acquiring a preset convolution characteristic set according to the crankshaft application standard, wherein the preset convolution characteristic set comprises a crankshaft curvature characteristic, a smoothness characteristic and a burr value characteristic;
the characteristic extraction unit is used for inputting the image information of the crankshaft to be ground into the image convolution logic layer through an input layer for characteristic extraction;
and the image characteristic output unit is used for obtaining the output information of the image convolution logic layer, and the output information comprises the appearance characteristic of the crankshaft to be ground which is in accordance with the preset convolution characteristic set.
Further, the control adjustment module further includes:
the error parameter obtaining unit is used for obtaining the error parameters of the grinding device through an acoustic emission sensor;
the compensation parameter obtaining unit is used for obtaining crankshaft grinding compensation parameters according to the error parameters of the grinding device;
the model updating unit is used for iteratively updating the crankshaft grinding parameter integrated analysis model based on the crankshaft grinding compensation parameters to obtain a crankshaft grinding parameter integrated optimization analysis model;
and the parameter correcting unit is used for correcting the error parameters of the abrasion device based on the output parameter information of the crankshaft grinding parameter integrated optimization analysis model.
Further, the system further comprises:
the error generating unit is used for analyzing generation reasons of the error parameters of the grinding device to obtain error generation reason information;
a scheme construction unit for constructing a crankshaft grinding solution list, the crankshaft grinding solution list being arranged according to an error generation type;
the scheme matching unit is used for matching the error generation reason information with the crankshaft grinding solution list to obtain a crankshaft error solution;
and the error elimination unit is used for eliminating the error parameters of the grinding device based on the crankshaft error solution if the error generation reason information is a limitation error.
Further, the feature classification module further includes:
the structure classification unit is used for obtaining the attribute of the structural form of the crankshaft and taking the attribute of the structural form of the crankshaft as a first crankshaft classification feature;
the material classification unit is used for obtaining crankshaft process material attributes, and the crankshaft process material attributes are used as second crankshaft classification features;
the application classification unit is used for obtaining crankshaft application type attributes, and the crankshaft application type attributes are used as third crankshaft classification features;
a decision tree construction unit, configured to construct the crankshaft feature decision tree based on the first crankshaft classification feature, the second crankshaft classification feature, and the third crankshaft classification feature.
The application provides a control and adjustment method for efficiently grinding a crankshaft, which comprises the following steps: acquiring crankshaft acquisition data information, wherein the crankshaft acquisition data information comprises crankshaft multi-dimensional data information and crankshaft image information; constructing a crankshaft characteristic decision tree, and classifying the crankshaft multi-dimensional data information through the crankshaft characteristic decision tree to obtain crankshaft characteristic information; carrying out finite element segmentation on the crankshaft image information 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, and constructing a crankshaft grinding parameter integration analysis model; acquiring data information and image information of a crankshaft to be ground; inputting the crankshaft data information to be ground and the crankshaft image information to be ground into the crankshaft grinding parameter integrated analysis model to obtain crankshaft grinding parameter information; and acquiring error parameters of the grinding device, and controlling and adjusting the crankshaft grinding based on the error parameters of the grinding device and the crankshaft grinding parameter information. The technical problem of prior art bent axle grinding precision low, consuming time long, lead to influencing bent axle grinding quality is solved. The technical effects that crankshaft grinding parameters are determined by constructing a crankshaft grinding parameter integrated analysis model, the crankshaft grinding precision and the grinding efficiency are improved, and the crankshaft grinding quality is further ensured are achieved.
The specification and drawings are merely illustrative of the present application, and it is intended that the present invention cover modifications and variations of this invention provided they come within the scope of the invention and their equivalents.
Claims (8)
1. A method of controlling and adjusting for efficient grinding of a crankshaft, the method comprising:
acquiring crankshaft acquisition data information, wherein the crankshaft acquisition data information comprises crankshaft multi-dimensional data information and crankshaft image information;
constructing a crankshaft characteristic decision tree, and classifying the crankshaft multi-dimensional data information through the crankshaft characteristic decision tree to obtain crankshaft characteristic information;
carrying out finite element segmentation on the crankshaft image information 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, and constructing a crankshaft grinding parameter integration analysis model;
acquiring data information and image information of a crankshaft to be ground;
inputting the crankshaft data information to be ground and the crankshaft image information to be ground into the crankshaft grinding parameter integrated analysis model to obtain crankshaft grinding parameter information;
and acquiring error parameters of the grinding device, and controlling and adjusting the crankshaft grinding based on the error parameters of the grinding device and the crankshaft grinding parameter information.
2. The method of claim 1, wherein the building of the crankshaft grinding parameter integrated analysis model based on uploading the crankshaft feature information and the crankshaft image segmentation information to a data integrated training platform for learning comprises:
inputting the crankshaft characteristic information and the crankshaft image segmentation information into a deep convolution neural network for training, and constructing a crankshaft grinding parameter analysis model;
acquiring multi-part crankshaft acquisition data information, and respectively inputting the multi-part crankshaft acquisition data information into the deep convolution neural network for distributed training to acquire a multi-part crankshaft grinding parameter analysis model;
extracting training model parameters of the one-side crankshaft grinding parameter analysis model and the multi-side crankshaft grinding parameter analysis model;
and the data integration training platform performs combined training on the training model parameters to obtain the crankshaft grinding parameter integration analysis model.
3. The method of claim 1, wherein the inputting the crankshaft data information to be ground and the crankshaft image information to be ground into the crankshaft grinding parameter integrated analysis model to obtain crankshaft grinding parameter information comprises:
the crankshaft grinding parameter integrated analysis model comprises an input layer, an image convolution logic layer, a hidden layer and an output layer;
inputting the image information of the crankshaft to be ground into the image convolution logic layer through an input layer, and outputting the appearance characteristics 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 into the hidden layer, and outputting the grinding parameter information of the crankshaft;
and outputting the crankshaft grinding parameter information as a model output result through the output layer.
4. The method according to claim 3, wherein the step of inputting the image information of the crankshaft to be ground into the image convolution logic layer through an input layer and outputting the appearance characteristics of the crankshaft to be ground comprises the following steps:
acquiring a crankshaft application standard, and acquiring a preset convolution characteristic set according to the crankshaft application standard, wherein the preset convolution characteristic set comprises a crankshaft curvature characteristic, a smoothness characteristic and a burr value characteristic;
inputting the crankshaft image information to be ground into the image convolution logic layer through an input layer for feature extraction;
and obtaining output information of the image convolution logic layer, wherein the output information comprises the appearance characteristics of the crankshaft to be ground, which accord with the preset convolution characteristic set.
5. The method of claim 1, wherein said obtaining wear assembly error parameters, and wherein said controlling adjustments to crankshaft grinding based on said wear assembly error parameters and said crankshaft grinding parameter information comprises:
acquiring error parameters of the grinding device through an acoustic emission sensor;
obtaining a crankshaft grinding compensation parameter according to the grinding device error parameter;
iteratively updating the crankshaft grinding parameter integrated analysis model based on the crankshaft grinding compensation parameters to obtain a crankshaft grinding parameter integrated optimization analysis model;
and correcting the error parameters of the abrasion device based on the output parameter information of the crankshaft grinding parameter integrated optimization analysis model.
6. The method of claim 5, wherein the method comprises:
analyzing generation reasons of the grinding device error parameters to obtain error generation reason information;
constructing a crankshaft grinding solution list, wherein the crankshaft grinding solution list is arranged according to an error generation type;
matching the error generation reason information with the crankshaft grinding solution list to obtain a crankshaft error solution;
and if the error generation reason information is a limit error, eliminating the error parameter of the grinding device based on the crankshaft error solution.
7. The method of claim 1, wherein constructing a crankshaft feature decision tree comprises:
obtaining crankshaft structure form attributes, and taking the crankshaft structure form attributes as first crankshaft classification features;
obtaining crankshaft process material attributes, and taking the crankshaft process material attributes as second crankshaft classification features;
obtaining crankshaft application type attributes, and taking the crankshaft application type attributes as third crankshaft classification features;
constructing the crankshaft feature decision tree based on the first crankshaft classification feature, the second crankshaft classification feature, and the third crankshaft classification feature.
8. A control and adjustment system for efficiently grinding a crankshaft, said system comprising:
the data acquisition module is used for acquiring crankshaft acquisition data information, wherein the crankshaft acquisition data information comprises crankshaft multi-dimensional data information and crankshaft image information;
the characteristic classification module is used for constructing a crankshaft characteristic decision tree, and classifying the crankshaft multi-dimensional data information through the crankshaft characteristic decision tree to obtain crankshaft characteristic information;
the image segmentation module is used for carrying out finite element segmentation on the crankshaft image information to obtain crankshaft image segmentation information;
the model building module is used for uploading the crankshaft characteristic information and the crankshaft image segmentation information to a data integration training platform for learning and building a crankshaft grinding parameter integration analysis model;
the data acquisition module is used for acquiring and acquiring data information of the crankshaft to be ground and image information of the crankshaft to be ground;
the model output module is used for inputting the crankshaft data information to be ground and the crankshaft image information to be ground into the crankshaft grinding parameter integrated analysis model to obtain crankshaft grinding parameter information;
and the control adjustment module is used for acquiring error parameters of the grinding device and controlling and adjusting the crankshaft grinding based on the error parameters of the grinding device and the crankshaft grinding parameter information.
Priority Applications (2)
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 |
LU502681A LU502681B1 (en) | 2022-07-06 | 2022-08-18 | Control adjustment method and system for high-efficiency grinding crankshaft |
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 (2)
Publication Number | Publication Date |
---|---|
CN115091283A true CN115091283A (en) | 2022-09-23 |
CN115091283B CN115091283B (en) | 2023-08-22 |
Family
ID=83297736
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210790158.8A Active CN115091283B (en) | 2022-07-06 | 2022-07-06 | Control and adjustment method and system for efficient grinding of crankshaft |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN115091283B (en) |
LU (1) | LU502681B1 (en) |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB2061554A (en) * | 1979-10-18 | 1981-05-13 | Gfm Fertigungstechnik | Control System for Producing Crankshafts |
WO1998010891A1 (en) * | 1996-09-13 | 1998-03-19 | Unova U.K. Limited | Improvements in and relating to workpiece grinding |
WO2000064632A1 (en) * | 1999-04-23 | 2000-11-02 | Unova U.K. Limited | Method and apparatus for controlling a workrest |
WO2001066305A1 (en) * | 2000-03-06 | 2001-09-13 | Marposs Società per Azioni | Apparatus and methods for measuring the pins diameter of a crankshaft at the place of grinding |
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 |
CN108763803A (en) * | 2018-06-04 | 2018-11-06 | 东华大学 | The grinding machine analysis method decomposed based on crank-shaft link neck follow grinding profile errors |
CN112884770A (en) * | 2021-04-28 | 2021-06-01 | 腾讯科技(深圳)有限公司 | Image segmentation processing method and device and computer equipment |
CN114037709A (en) * | 2021-11-05 | 2022-02-11 | 复旦大学附属肿瘤医院 | Segmentation method and device for grinded glass pulmonary 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 |
CN114161240A (en) * | 2021-12-15 | 2022-03-11 | 清华大学 | Grinding surface shape prediction method, grinding system and terminal equipment |
CN114536110A (en) * | 2022-03-03 | 2022-05-27 | 华辰精密装备(昆山)股份有限公司 | Error real-time compensation method and system for grinding complex profile of non-circular component |
CN114571326A (en) * | 2022-01-20 | 2022-06-03 | 上海交通大学 | Method, device and system for grinding deformed curved surface based on computer vision |
-
2022
- 2022-07-06 CN CN202210790158.8A patent/CN115091283B/en active Active
- 2022-08-18 LU LU502681A patent/LU502681B1/en active IP Right Grant
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB2061554A (en) * | 1979-10-18 | 1981-05-13 | Gfm Fertigungstechnik | Control System for Producing Crankshafts |
WO1998010891A1 (en) * | 1996-09-13 | 1998-03-19 | Unova U.K. Limited | Improvements in and relating to workpiece grinding |
WO2000064632A1 (en) * | 1999-04-23 | 2000-11-02 | Unova U.K. Limited | Method and apparatus for controlling a workrest |
WO2001066305A1 (en) * | 2000-03-06 | 2001-09-13 | Marposs Società per Azioni | Apparatus and methods for measuring the pins diameter of a crankshaft at the place of grinding |
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 |
CN108763803A (en) * | 2018-06-04 | 2018-11-06 | 东华大学 | The grinding machine analysis method decomposed based on crank-shaft link neck follow grinding profile errors |
CN112884770A (en) * | 2021-04-28 | 2021-06-01 | 腾讯科技(深圳)有限公司 | Image segmentation processing method and device and computer equipment |
CN114037709A (en) * | 2021-11-05 | 2022-02-11 | 复旦大学附属肿瘤医院 | Segmentation method and device for grinded glass pulmonary 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 |
CN114161240A (en) * | 2021-12-15 | 2022-03-11 | 清华大学 | Grinding surface shape prediction method, grinding system and terminal equipment |
CN114571326A (en) * | 2022-01-20 | 2022-06-03 | 上海交通大学 | Method, device and system for grinding deformed curved surface based on computer vision |
CN114536110A (en) * | 2022-03-03 | 2022-05-27 | 华辰精密装备(昆山)股份有限公司 | Error real-time compensation method and system for grinding complex profile of non-circular component |
Non-Patent Citations (3)
Title |
---|
乔培平;: "用切点跟踪磨削法磨削曲轴的研究与应用", 航空精密制造技术, no. 02 * |
侯立丹;张宇;: "轴类零件的磨损分析与检测***设计", 山东理工大学学报(自然科学版), no. 02 * |
李静;高华钰;沈南燕;黄海涛;方明伦;: "基于切深模型的汽车曲轴轴颈巴厘线磨削精度控制", 机械工程学报, no. 05 * |
Also Published As
Publication number | Publication date |
---|---|
CN115091283B (en) | 2023-08-22 |
LU502681B1 (en) | 2023-02-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108405941B (en) | Efficient precise milling method for blade body profile of aero-engine blade | |
JP2013186899A (en) | Method and system for monitoring structure | |
CN112765732B (en) | Aviation blade topology optimization design method based on selective laser melting process | |
CN108629137B (en) | Optimization design method for structural parameters of mechanical structural part | |
Ramnath et al. | Implementation of reverse engineering for crankshaft manufacturing industry | |
CN113239461B (en) | Deformation control method for asymmetric structure complex thin-wall part | |
CN113538378A (en) | Bearing size online detection system based on deep learning | |
CN115091283B (en) | Control and adjustment method and system for efficient grinding of crankshaft | |
CN114491863B (en) | Threaded connection pair reliability simulation analysis method for main bearing seat of engine | |
CN112115555A (en) | Method for monitoring instantaneous oil consumption of automobile in intelligent networking environment | |
CN111075647A (en) | ELM-based maximum wind energy capture method for variable-speed wind turbine generator | |
CN114509991A (en) | Numerical control machine tool cutting stability prediction and optimization method considering parameter uncertainty | |
CN114781245A (en) | Transient automobile oil consumption estimation method and system based on high oil consumption related parameter correction | |
CN108073074B (en) | Assembly quality control method based on motion characteristics of machine tool feeding system | |
CN113569453A (en) | Migration method of digital twin product model for machining | |
CN113486561A (en) | Engine rotor dynamic characteristic improving method based on strain energy distribution | |
CN113128120A (en) | Method for constructing typical running condition of automobile crane | |
CN111241752A (en) | Centrifugal impeller comprehensive optimization method based on digital twinning and reinforcement learning | |
CN116910513A (en) | Centrifugal pump rotor fault diagnosis method based on CWGAN-GP and double-flow CNN model | |
CN111274698A (en) | Aeroelastic patrol pneumatic parameter modeling method based on factorial test method | |
CN116213800A (en) | Digital twin milling interference real-time prediction system and method | |
CN109117597B (en) | Processing key factor grading method based on corresponding analysis method | |
CN110633521B (en) | Multistage rotor assembly phase optimization method for revolving body | |
CN114905515A (en) | Robot control method and system based on flexible perception neural network | |
CN111709160B (en) | Driving dynamic performance analysis optimization method and system based on truck chassis |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |