CN117032080A - Implementation method and application of algorithm for improving state monitoring capability of numerical control machine tool - Google Patents
Implementation method and application of algorithm for improving state monitoring capability of numerical control machine tool Download PDFInfo
- Publication number
- CN117032080A CN117032080A CN202311045187.2A CN202311045187A CN117032080A CN 117032080 A CN117032080 A CN 117032080A CN 202311045187 A CN202311045187 A CN 202311045187A CN 117032080 A CN117032080 A CN 117032080A
- Authority
- CN
- China
- Prior art keywords
- data
- model
- numerical control
- state
- control machine
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000013527 convolutional neural network Methods 0.000 claims description 21
- 238000012360 testing method Methods 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 17
- 238000013136 deep learning model Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 12
- 125000004122 cyclic group Chemical group 0.000 claims description 10
- 238000005457 optimization Methods 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000003745 diagnosis Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 238000002360 preparation method Methods 0.000 claims description 3
- 238000012098 association analyses Methods 0.000 claims description 2
- 238000004140 cleaning Methods 0.000 claims description 2
- 230000009467 reduction Effects 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
- G05B19/408—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by data handling or data format, e.g. reading, buffering or conversion of data
- G05B19/4086—Coordinate conversions; Other special calculations
-
- 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
- G05B2219/35356—Data handling
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Manufacturing & Machinery (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the field of numerically-controlled machine tools, and discloses an implementation method and application of an algorithm for improving the state monitoring capability of the numerically-controlled machine tools. The implementation method and the application of the algorithm for improving the state monitoring capability of the numerical control machine tool have the advantages that the feature can be automatically extracted from the original data without manually designing the feature, so that the algorithm has universality and can adapt to the monitoring requirements of different machine tools.
Description
Technical Field
The invention relates to the field of numerical control machine tools, in particular to an implementation method and application of an algorithm for improving the state monitoring capability of a numerical control machine tool.
Background
The numerical control machine is an automatic machine, which inputs the information carrier into the numerical control device, and through the operation processing of the numerical control device, the numerical control machine can logically process and decode the program specified by the control code or other symbol instructions, and the program is expressed by the coded number, thereby controlling the action of the machine and automatically processing the parts. The numerical control machine tool well solves the problems of complex, precise, small batch and multiple kinds of part processing, is a flexible and high-efficiency automatic machine tool, represents the development direction of the modern machine tool control technology, and is a typical electromechanical integrated product.
The improvement of the state monitoring capability of the numerical control machine tool has important significance for enterprises, not only can the production efficiency and the equipment utilization rate be improved and the maintenance cost be reduced, but also the safety and the promotion of the intelligent level can be enhanced, and the state monitoring capability of the numerical control machine tool also has a lifting space at present, so that the implementation method and the application of the algorithm for improving the state monitoring capability of the numerical control machine tool are provided.
Disclosure of Invention
(one) solving the technical problems
Aiming at the defects of the prior art, the invention provides an implementation method and application of an algorithm for improving the state monitoring capability of a numerical control machine tool, so as to solve the problems.
(II) technical scheme
In order to achieve the above purpose, the present invention provides the following technical solutions: an algorithm for improving the state monitoring capability of a numerical control machine comprises a deep learning algorithm, wherein the state of the numerical control machine is monitored by using a deep learning model such as a Convolutional Neural Network (CNN) or a cyclic neural network (RNN).
Preferably, the Convolutional Neural Network (CNN) is mainly used for processing image data, in the state monitoring of a numerically-controlled machine tool, the image data acquired by a sensor of the machine tool is used as input, firstly, spatial features of the image are extracted through a convolutional layer, then the dimensionality of a feature map is reduced through a pooling layer, then the low-dimensional features are mapped onto a prediction result of a target state through a full-connection layer, finally, the prediction result and the real state are compared by using a loss function, and parameter optimization is performed.
Preferably, the cyclic neural network (RNN) is mainly used for processing sequence data, time sequence data is used as input for monitoring the state of the numerical control machine, the RNN has memory capacity, historical states are modeled and predicted, in the monitoring of the state of the numerical control machine, a long and short memory network (LSTM) or a gate control cyclic unit (GRU) is used for processing the sequence data, a time sequence relation between the states of the machine is learned from past state data, and prediction and diagnosis are performed according to the current state.
According to still another aspect of the embodiment of the present invention, there is provided a method for implementing an algorithm for improving the state monitoring capability of a numerically-controlled machine tool, including the steps of:
data collection and preparation: collecting and preparing machine tool state data for training and testing, ensuring the accuracy and the integrity of the data, and preprocessing;
labeling and dividing data: labeling the collected data, constructing a supervised learning model, adding corresponding labels to each sample data according to a specific monitoring task, dividing the data into a training set, a verification set and a test set, and dividing the data according to proportion to ensure the sufficiency and representativeness of the data;
model selection and construction: selecting a corresponding deep learning model to process a state monitoring task of the numerical control machine tool, selecting a CNN model for image data, selecting an RNN model for time series data, and adjusting the layer number and parameters of the model according to the complexity degree of the problem and the data set scale;
model training and optimizing: training a deep learning model by using a training set, updating the weight and bias of the model by using a back propagation algorithm through iterative optimization loss function, adopting common optimization algorithms such as random gradient descent (SGD), adam and the like, setting proper learning rate and batch size super-parameters, and evaluating the model on a verification set so as to avoid overfitting and select the optimal model.
Model test and verification: and testing and verifying the trained model by using the test set, and calculating performance indexes of the model on the test set, such as accuracy, recall rate, precision rate and the like. And adjusting a model threshold according to actual requirements or adopting other evaluation indexes to balance the accuracy and fault detection capability of the model.
Deployment and real-time monitoring: the trained model is deployed into an actual numerical control machine environment to be monitored in real time, real-time sensor data or image data are received, and state prediction and anomaly detection are carried out by using a deep learning model.
Preferably, the machine tool state data includes sensor data, image data, and time series data.
Preferably, the preprocessing includes data cleaning, normalization, and noise reduction.
Preferably, the tag includes a normal state and a fault state.
Preferably, the CNN model includes a classical convolutional neural network structure (LeNet, alexNet, VGG, etc.) or a deeper model of ResNet, inception, etc.
According to still another aspect of the embodiment of the present invention, there is provided an application of an algorithm for improving a state monitoring capability of a numerically-controlled machine tool, including:
and analyzing data information required to be acquired by state monitoring of the numerical control machine, carrying out association analysis and data annotation on machine data and related states, designing a proper artificial intelligent model for the acquired state data, optimizing an algorithm, and completing model training.
(III) beneficial effects
Compared with the prior art, the invention provides an implementation method and application of an algorithm for improving the state monitoring capability of a numerical control machine tool, and the implementation method has the following beneficial effects:
the implementation method and the application of the algorithm for improving the state monitoring capability of the numerical control machine tool, which are disclosed by the invention, use a deep learning model such as a Convolutional Neural Network (CNN) or a cyclic neural network (RNN) to monitor the state of the numerical control machine tool, and have the advantages that the method can automatically extract the characteristics from the original data without manually designing the characteristics, so that the algorithm has universality, can adapt to the monitoring requirements of different machine tools, has stronger expression capability and generalization capability, can handle complex nonlinear problems, and generally has better performance under a large-scale data set.
Detailed Description
The technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be understood that in the present invention, "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements that are expressly listed or inherent to such process, method, article, or apparatus.
Firstly, determining an algorithm, wherein the algorithm for improving the state monitoring capability of the numerical control machine comprises a deep learning algorithm, and is characterized in that the state of the numerical control machine is monitored by using a deep learning model such as a Convolutional Neural Network (CNN) or a cyclic neural network (RNN). The Convolutional Neural Network (CNN) is mainly used for processing image data, in the state monitoring of a numerical control machine tool, the image data acquired by a sensor of the machine tool is used as input, firstly, the spatial features of the image are extracted through a convolutional layer, then the dimensionality of a feature map is reduced through a pooling layer, then the low-dimensional features are mapped onto a prediction result of a target state through a full-connection layer, finally, the prediction result and the real state are compared by using a loss function, and parameter optimization is carried out. The cyclic neural network (RNN) is mainly used for processing sequence data, time sequence data is used as input for monitoring the state of a numerical control machine tool, the RNN has memory capacity, historical states are modeled and predicted, in the monitoring of the state of the numerical control machine tool, a long and short memory network (LSTM) or a gating cyclic unit (GRU) is used for processing the sequence data, a time sequence relation between the states of the machine tool is learned from past state data, and prediction and diagnosis are performed according to the current state.
According to still another aspect of the embodiment of the present invention, there is provided a method for implementing an algorithm for improving the state monitoring capability of a numerically-controlled machine tool, including the steps of:
data collection and preparation: collecting and preparing machine tool state data for training and testing, ensuring the accuracy and the integrity of the data, and preprocessing;
labeling and dividing data: labeling the collected data, constructing a supervised learning model, adding corresponding labels to each sample data according to a specific monitoring task, dividing the data into a training set, a verification set and a test set, and dividing the data according to proportion to ensure the sufficiency and representativeness of the data;
model selection and construction: selecting a corresponding deep learning model to process a state monitoring task of the numerical control machine tool, selecting a CNN model for image data, selecting an RNN model for time series data, and adjusting the layer number and parameters of the model according to the complexity degree of the problem and the data set scale;
model training and optimizing: training a deep learning model by using a training set, updating the weight and bias of the model by using a back propagation algorithm through iterative optimization loss function, adopting common optimization algorithms such as random gradient descent (SGD), adam and the like, setting proper learning rate and batch size super-parameters, and evaluating the model on a verification set so as to avoid overfitting and select the optimal model.
Model test and verification: and testing and verifying the trained model by using the test set, and calculating performance indexes of the model on the test set, such as accuracy, recall rate, precision rate and the like. And adjusting a model threshold according to actual requirements or adopting other evaluation indexes to balance the accuracy and fault detection capability of the model.
Deployment and real-time monitoring: the trained model is deployed into an actual numerical control machine environment to be monitored in real time, real-time sensor data or image data are received, and state prediction and anomaly detection are carried out by using a deep learning model.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (9)
1. An algorithm for improving the state monitoring capability of a numerical control machine tool comprises a deep learning algorithm and is characterized in that a deep learning model such as a Convolutional Neural Network (CNN) or a cyclic neural network (RNN) is used for monitoring the state of the numerical control machine tool.
2. The algorithm for improving the state monitoring capability of the numerical control machine according to claim 1, wherein: the Convolutional Neural Network (CNN) is mainly used for processing image data, in the state monitoring of a numerical control machine tool, the image data acquired by a sensor of the machine tool is used as input, firstly, spatial features of an image are extracted through a convolutional layer, then the dimensionality of a feature map is reduced through a pooling layer, then the low-dimensional features are mapped onto a prediction result of a target state through a full-connection layer, finally, the prediction result and the real state are compared by using a loss function, and parameter optimization is carried out.
3. The algorithm for improving the state monitoring capability of the numerical control machine according to claim 1, wherein: the cyclic neural network (RNN) is mainly used for processing sequence data, time sequence data is used as input for monitoring the state of a numerical control machine tool, the RNN has memory capacity, historical states are modeled and predicted, in the monitoring of the state of the numerical control machine tool, a long and short memory network (LSTM) or a gating cyclic unit (GRU) is used for processing the sequence data, a time sequence relation between the states of the machine tool is learned from past state data, and prediction and diagnosis are performed according to the current state.
4. The implementation method of the algorithm for improving the state monitoring capability of the numerical control machine tool is characterized by comprising the following steps of:
data collection and preparation: collecting and preparing machine tool state data for training and testing, ensuring the accuracy and the integrity of the data, and preprocessing;
labeling and dividing data: labeling the collected data, constructing a supervised learning model, adding corresponding labels to each sample data according to a specific monitoring task, dividing the data into a training set, a verification set and a test set, and dividing the data according to proportion to ensure the sufficiency and representativeness of the data;
model selection and construction: selecting a corresponding deep learning model to process a state monitoring task of the numerical control machine tool, selecting a CNN model for image data, selecting an RNN model for time series data, and adjusting the layer number and parameters of the model according to the complexity degree of the problem and the data set scale;
model training and optimizing: training a deep learning model by using a training set, updating the weight and bias of the model by using a back propagation algorithm through iterative optimization loss function, adopting common optimization algorithms such as random gradient descent (SGD), adam and the like, setting proper learning rate and batch size super-parameters, and evaluating the model on a verification set so as to avoid overfitting and select the optimal model.
Model test and verification: and testing and verifying the trained model by using the test set, and calculating performance indexes of the model on the test set, such as accuracy, recall rate, precision rate and the like. And adjusting a model threshold according to actual requirements or adopting other evaluation indexes to balance the accuracy and fault detection capability of the model.
Deployment and real-time monitoring: the trained model is deployed into an actual numerical control machine environment to be monitored in real time, real-time sensor data or image data are received, and state prediction and anomaly detection are carried out by using a deep learning model.
5. The method for implementing the algorithm for improving the state monitoring capability of the numerical control machine according to claim 4, wherein the method comprises the following steps: the machine tool state data includes sensor data, image data, and time series data.
6. The method for implementing the algorithm for improving the state monitoring capability of the numerical control machine according to claim 4, wherein the method comprises the following steps: the preprocessing comprises data cleaning, standardization and noise reduction.
7. The method for implementing the algorithm for improving the state monitoring capability of the numerical control machine according to claim 4, wherein the method comprises the following steps: the tag includes a normal state and a fault state.
8. The method for implementing the algorithm for improving the state monitoring capability of the numerical control machine according to claim 4, wherein the method comprises the following steps: the CNN model includes a classical convolutional neural network structure (LeNet, alexNet, VGG, etc.) or a deeper model of ResNet, inception, etc.
9. The use of an algorithm for improving the state monitoring capability of a numerically controlled machine tool according to claim 1, comprising:
and analyzing data information required to be acquired by state monitoring of the numerical control machine, carrying out association analysis and data annotation on machine data and related states, designing a proper artificial intelligent model for the acquired state data, optimizing an algorithm, and completing model training.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311045187.2A CN117032080A (en) | 2023-08-18 | 2023-08-18 | Implementation method and application of algorithm for improving state monitoring capability of numerical control machine tool |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311045187.2A CN117032080A (en) | 2023-08-18 | 2023-08-18 | Implementation method and application of algorithm for improving state monitoring capability of numerical control machine tool |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117032080A true CN117032080A (en) | 2023-11-10 |
Family
ID=88627826
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311045187.2A Pending CN117032080A (en) | 2023-08-18 | 2023-08-18 | Implementation method and application of algorithm for improving state monitoring capability of numerical control machine tool |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117032080A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117671379A (en) * | 2023-12-11 | 2024-03-08 | 南京熊猫电子制造有限公司 | Intelligent recognition system and method based on CCD visual detection |
-
2023
- 2023-08-18 CN CN202311045187.2A patent/CN117032080A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117671379A (en) * | 2023-12-11 | 2024-03-08 | 南京熊猫电子制造有限公司 | Intelligent recognition system and method based on CCD visual detection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111460728B (en) | Method and device for predicting residual life of industrial equipment, storage medium and equipment | |
| CN106951695A (en) | Plant equipment remaining life computational methods and system under multi-state | |
| CN117234785B (en) | Centralized control platform error analysis system based on artificial intelligence self-query | |
| CN112508053A (en) | Intelligent diagnosis method, device, equipment and medium based on integrated learning framework | |
| CN112884008B (en) | Prediction evaluation method and device for running state of power information acquisition system | |
| CN112000084B (en) | Intelligent BIT design method of controller module based on 1D-CNN and GRU-SVM | |
| CN114118673A (en) | Workshop intelligent fault diagnosis early warning method based on digital twin technology | |
| CN118154174B (en) | Intelligent operation and maintenance cloud platform for industrial equipment | |
| CN110757510B (en) | Method and system for predicting remaining life of robot | |
| CN117032080A (en) | Implementation method and application of algorithm for improving state monitoring capability of numerical control machine tool | |
| TWI794907B (en) | Prognostic and health management system for system management and method thereof | |
| CN113449919B (en) | Power consumption prediction method and system based on feature and trend perception | |
| CN113988210A (en) | Method and device for restoring distorted data of structure monitoring sensor network and storage medium | |
| CN118112937B (en) | Intelligent control system and method for micro-positive pressure of farm based on multisource fusion perception | |
| CN118469352B (en) | Deep learning driven power grid line loss dynamic prediction and optimization control method | |
| CN114548494B (en) | Visual cost data prediction intelligent analysis system | |
| CN116822115A (en) | Environment management method and system for intelligent park based on digital twin technology | |
| CN118386024A (en) | Machine tool based on artificial intelligence and fault detection method thereof | |
| CN114764538B (en) | Equipment sound signal mode identification method | |
| CN116821828A (en) | Multi-dimensional time sequence prediction method based on industrial data | |
| CN114926075B (en) | Machine part production scheduling method based on man-hour prediction | |
| CN117804811B (en) | Health diagnosis system and method for deep neural network port machinery equipment of attention mechanism | |
| CN118536410B (en) | Big data driven modeling-based energy consumption optimization decision analysis method and system | |
| CN118392255B (en) | Method, system and equipment for monitoring operation condition of electromechanical equipment of water plant | |
| CN115081304B (en) | Method and device for predicting shafting health performance trend interval of pumped storage unit |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |