CN117390960A - Intelligent analysis method for machining precision of numerical control machine tool - Google Patents
Intelligent analysis method for machining precision of numerical control machine tool Download PDFInfo
- Publication number
- CN117390960A CN117390960A CN202311385538.4A CN202311385538A CN117390960A CN 117390960 A CN117390960 A CN 117390960A CN 202311385538 A CN202311385538 A CN 202311385538A CN 117390960 A CN117390960 A CN 117390960A
- Authority
- CN
- China
- Prior art keywords
- data
- model
- machine tool
- numerical control
- 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
- 238000003754 machining Methods 0.000 title claims abstract description 51
- 238000004458 analytical method Methods 0.000 title claims abstract description 33
- 238000012545 processing Methods 0.000 claims abstract description 55
- 238000000034 method Methods 0.000 claims abstract description 40
- 238000005457 optimization Methods 0.000 claims abstract description 37
- 238000005516 engineering process Methods 0.000 claims abstract description 21
- 238000012549 training Methods 0.000 claims abstract description 20
- 230000008569 process Effects 0.000 claims abstract description 15
- 238000013135 deep learning Methods 0.000 claims abstract description 12
- 239000002131 composite material Substances 0.000 claims abstract description 4
- 238000012795 verification Methods 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000007726 management method Methods 0.000 claims description 9
- 238000004519 manufacturing process Methods 0.000 claims description 9
- 238000005265 energy consumption Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 7
- 238000012544 monitoring process Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000007405 data analysis Methods 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000003062 neural network model Methods 0.000 claims description 5
- 230000006872 improvement Effects 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 2
- 230000007547 defect Effects 0.000 abstract description 5
- 238000013528 artificial neural network Methods 0.000 description 11
- 238000013527 convolutional neural network Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000005520 cutting process Methods 0.000 description 3
- 230000000306 recurrent effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 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
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000003746 surface roughness Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- 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
- G06N3/0985—Hyperparameter optimisation; Meta-learning; Learning-to-learn
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Geometry (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Numerical Control (AREA)
Abstract
The invention provides an intelligent analysis method for machining precision of a numerical control machine tool, and relates to the technical field of machining. The method specifically comprises the following steps: s1, collecting and processing data, namely collecting processing conventional parameters through a sensor, collecting holographic data and control data of a machine tool or a workpiece by utilizing the sensor besides collecting data on the aspect of processing the conventional parameters of a numerical control machine tool, establishing a data pool through a big data technology to record, store and process all the collected data, and adding a supervised learning method to improve analysis precision; s2, constructing a model, and extracting more abundant and detailed characteristic parameters based on collected data in an analysis data pool; s3, model training and optimization are carried out, characteristic parameters and actual machining precision are compared and analyzed, a composite model based on a deep learning technology is constructed, and prediction and optimization with higher precision are carried out. The method can improve the machining precision of the numerical control machine tool, reduce machining defects and rejection rate, and improve the product quality and competitiveness.
Description
Technical Field
The invention relates to the technical field of machining, in particular to an intelligent analysis method for machining precision of a numerical control machine tool.
Background
The numerical control machine (Numerical Control Machine Tool) is a machine tool controlled by a computer, and is capable of automatically performing machining operations based on numerical instructions input in advance. The numerical control machine tool processes the workpiece through the control system, and has the characteristics of high precision, high efficiency and high automation degree.
The intelligent analysis of the machining precision of the numerical control machine tool is a method for analyzing and judging the data in the machining process by utilizing an artificial intelligence technology so as to monitor and optimize the machining precision.
The intelligent analysis method can be used for carrying out data mining and analysis through technologies such as machine learning, deep learning, pattern recognition and the like based on information such as sensor data, processing parameters and technical regulations of the numerical control machine tool, so that real-time monitoring and prediction of processing precision are realized.
Through data acquisition and processing, accurate model construction and intelligent production management implementation, the machining precision of the numerical control machine tool can be improved, machining defects and rejection rate can be reduced, and therefore the product quality and competitiveness can be improved. However, there may be drawbacks in terms of data accuracy, model construction, overfitting, verification method selection, optimization adjustments, and the like, requiring attention and appropriate measures to improve.
Disclosure of Invention
(one) solving the technical problems
Aiming at the defects of the prior art, the invention provides an intelligent analysis method for processing precision of a numerical control machine tool, which solves the problem that defects are easy to exist in the aspects of data accuracy, model construction, over-fitting, verification method selection and optimization adjustment during the processing of the numerical control machine tool.
(II) technical scheme
In order to achieve the above purpose, the invention is realized by the following technical scheme: the intelligent analysis method for the machining precision of the numerical control machine tool specifically comprises the following steps:
s1, data acquisition and processing
Collecting processing conventional parameters through a sensor, collecting holographic data and control data of a machine tool or a workpiece by using the sensor besides collecting data of the processing conventional parameters of the numerical control machine tool, establishing a data pool through a big data technology to record, store and process all collected data, and adding a supervised learning method to improve analysis precision;
s2, model construction
Based on the collected data in the analysis data pool, extracting more abundant and detailed characteristic parameters;
s3, model training and optimization
Comparing and analyzing the characteristic parameters and the actual machining precision, constructing a composite model based on a deep learning technology, and carrying out prediction and optimization with higher precision;
s4, model verification
The extracted characteristic parameters, super parameters during model construction and a large amount of historical data are used for model training and optimization;
s5, intelligent optimization and adjustment
The trained model is applied to actual processing data for verification, improvement and upgrading, so that the reliability of data analysis is ensured;
s6, real-time monitoring and auxiliary management
And the obtained analysis visual result penetrates through the key link of the processing and production process, and intelligent production management is implemented.
Preferably, the multi-layer neural network model is composed of an input layer for receiving input data, a hidden layer for processing the data, and an output layer for outputting a final result.
Preferably, the model formula is:
y＝f 2 (v*f 1 (w*x)
wherein x is the input feature vector, w is the weight matrix from the input layer to the hidden layer, f 1 V is the weight matrix from the hidden layer to the output layer, f 2 Is the activation function of the output layer, y is the output of the model.
Preferably, the root mean square error and the average absolute error are used as regression evaluation indexes of numerical control machining precision:
4.1. root Mean Square Error (RMSE): RMSE represents the average error between the predicted value and the true value, and the calculation formula includes the following:
where n is the number of samples, yi is the true value,is a predicted value. The smaller the RMSE value is, the smaller the deviation of the model prediction result relative to the true value is, and the higher the prediction precision of the model is;
4.2. mean Absolute Error (MAE): MAE represents the mean absolute error between the predicted and actual values, and the calculation formula includes the following:
where n is the number of samples, yi is the true value,is a predicted value. The smaller the MAE value, the smaller the deviation of the model prediction result from the true value, and the higher the prediction precision of the model.
Preferably, the training and optimizing of the S3 model comprises the following steps:
5.1. and (3) data processing: firstly, data needs to be processed, including data cleaning, data preprocessing and data dividing;
5.2. model selection and design: selecting a proper model according to specific tasks and requirements;
5.3. optimizing the learning rate: the learning rate determines the parameter change of the model in the training process;
5.4. regularization technique: through regularization technology comprising dropout and weight decade, the overfitting is reduced, and the generalization capability of the model is improved;
5.5. model integration: integrating a plurality of different models through a model integration technology comprising integrated learning and cross verification, so as to reduce the variance of the models;
5.6. and (3) empirical parameter adjustment: finally, the experimental parameter adjustment is needed to be realized, namely, all parameters in the model are optimized, so that the prediction accuracy of the model is improved.
Preferably, a grid search method or a random search method is adopted to automatically adjust parameters for optimization.
Preferably, the intelligent optimization and adjustment of the S5 is mainly to optimize and adjust working parameters of the machine tool in real time through an optimization algorithm and a deep learning technology, and comprehensively consider machining precision, efficiency and energy consumption factors.
(III) beneficial effects
The invention provides an intelligent analysis method for machining precision of a numerical control machine tool. The beneficial effects are as follows:
the invention provides a processing precision intelligent analysis method for a numerical control machine, which is characterized in that data acquisition and processing are carried out, processing conventional parameters are acquired and processed through a sensor, a data pool is established by utilizing a big data technology, the analysis precision is improved, abundant and fine characteristic parameters are extracted on the basis of acquired data through model construction, a multi-layer neural network model is constructed, model training and optimization are carried out through a deep learning technology, high-precision prediction and optimization are realized, model verification is carried out at the same time, accuracy and reliability of a historical data verification model are utilized, intelligent optimization and adjustment are carried out, the trained model is applied to actual processing data for real-time optimization and adjustment, comprehensive consideration of processing precision, efficiency and energy consumption is improved, monitoring and auxiliary management are carried out in real time at the same time, the analysis result is visualized to be applied to key links of a processing production process, intelligent production management is implemented, the processing precision of the numerical control machine is improved, processing defects and rejection rate are reduced, and product quality and competitive power are improved.
Detailed Description
The following description of the technical solutions in the embodiments of the present invention will be clear and complete, and it is obvious that the described embodiments are only some embodiments of the present invention, but 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.
Examples:
the embodiment of the invention provides an intelligent analysis method for machining precision of a numerical control machine tool, which specifically comprises the following steps:
s1, data acquisition and processing
Collecting processing conventional parameters through a sensor, collecting holographic data and control data of a machine tool or a workpiece by utilizing the sensor besides collecting data of the processing conventional parameters (including processing speed and cutter rotating speed) of the numerical control machine tool, establishing a data pool through a big data technology to record, store and process all collected data, and adding a supervised learning method to improve analysis precision;
s2, model construction
Based on the collected data in the analysis data pool, more abundant and detailed characteristic parameters are extracted, and in the new model, the characteristic parameters cover more fields including sound, vibration, friction and environment, for example, so as to improve the comprehensive analysis of the processing precision
1/1, data preprocessing: after the processing data are collected and collected, normalization and standardization pretreatment operation is required to be carried out on the data so as to ensure the quality and reliability of the data;
2/2, feature extraction: extracting useful characteristic parameters from the machining data, wherein the parameters comprise machining speed, tool rotating speed, cutting force, vibration and machining precision related parameters, and also comprise geometric characteristics and material characteristic factors of a machined part;
3/3. Data segmentation: and dividing the processing data according to a time sequence, and predicting and optimizing the follow-up data according to the previous data. This process needs to ensure data continuity and data balance;
4/4. Model construction: a predictive model is constructed using deep learning techniques, one common model being a deep neural network (Deep Neural Network, DNN). The DNN model is a multi-layer neural network and is used for processing various different types of problems of classification, regression and clustering. The DNN model adopts various algorithm structures, including a full-connection layer, a convolutional neural network and a long-term and short-term memory network;
5/5. Model evaluation: in order to evaluate the effect and performance of the model, the trained model needs to be input into a test set for predicting machining accuracy. The evaluation index comprises a mean square error, an average absolute error and a training error;
s3, model training and optimization
Comparing and analyzing the characteristic parameters and the actual machining precision, constructing a composite model based on a deep learning technology, and carrying out prediction and optimization with higher precision;
s4, model verification
The extracted characteristic parameters, super parameters during model construction and a large amount of historical data are used for model training and optimization. Meanwhile, the neural network deep learning method is adopted to identify and extract the characteristics of the image data, so that the real-time monitoring of the imaging process is realized, and the stability and the sustainable development of the processing precision are ensured;
s5, intelligent optimization and adjustment
The trained model is applied to actual processing data for verification, improvement and upgrading, and reliability of data analysis is ensured. Meanwhile, by comparing the data history with the current data, deducing an evolution rule of the processing process, adjusting model parameters in real time, and better supporting the continuous optimization and improvement of the precision analysis model;
s6, real-time monitoring and auxiliary management
The obtained analysis visual result penetrates through the key links of the processing and production process, intelligent production management is implemented, and the effect of 'seeing and managing is achieved'. Meanwhile, a big data analysis, intelligent diagnosis and fault prediction module is arranged in the data analysis platform, the running state of the processing equipment is judged according to the data monitored in real time, and effective measures are taken in time to maintain the processing precision.
The multi-layer neural network model consists of an input layer, a hidden layer and an output layer, wherein the input layer is used for receiving input data, the hidden layer is used for processing the data, and the output layer is used for outputting a final result. In the neural network model, each layer is composed of a plurality of neurons, and connection relations among nodes are formed among the neurons through connection weights. And through the training process of the model, the adjustment of the weight value is optimized to minimize the difference between the result output by the model and the actual data.
The model formula is:
y＝f 2 (v*f 1 (w*x)
where x is the input feature vector and w is the input layer to hidden layerWeight matrix f of (2) 1 V is the weight matrix from the hidden layer to the output layer, f 2 Is the activation function of the output layer, y is the output of the model.
Note that: * Represented is a multiplication of a matrix.
The root mean square error and the average absolute error are used as regression evaluation indexes of numerical control machining precision:
4.1. root Mean Square Error (RMSE): RMSE represents the average error between the predicted value and the true value, and the calculation formula includes the following:
where n is the number of samples, yi is the true value,is a predicted value. The smaller the RMSE value, the smaller the deviation of the model prediction result from the true value, and the higher the prediction accuracy of the model.
And comparing the actual machining parameters obtained by measuring the machining precision of the numerical control machine tool with the predicted values, and calculating the RMSE value to evaluate the prediction precision and accuracy of the model. And according to the RMSE value, the processing environment and the process parameters are adjusted and optimized to meet the requirement of higher processing precision.
4.2. Mean Absolute Error (MAE): MAE represents the mean absolute error between the predicted and actual values, and the calculation formula includes the following:
where n is the number of samples, yi is the true value,is a predicted value. The smaller the MAE value, the smaller the deviation of the model prediction result from the true value, and the higher the prediction precision of the model.
S3, training and optimizing the model, wherein the training and optimizing the model comprises the following steps:
5.1. and (3) data processing: the data needs to be processed firstly, including data cleaning, data preprocessing and data dividing, so that the quality of the data is improved, and the influence on model training is reduced.
5.2. Model selection and design: depending on the specific task and requirements, suitable models are selected, including deep neural networks (Deep Neural Network, DNN), convolutional neural networks (Convolutional Neural Network, CNN), or recurrent neural networks (Recurrent Neural Network, RNN). For specific tasks and problems, some specialized model structures are also selected, including residual neural networks (res net), recurrent neural networks (Recursive Neural Network, recNN).
5.3. Optimizing the learning rate: the learning rate determines the variation of the parameters of the model during the training process. Too much learning rate may result in too fast convergence, affecting the generalization ability of the model, while too little learning rate may result in too slow convergence, making the model ineffective to be optimized during training. Therefore, the learning rate needs to be optimized, and a learning rate scheduling strategy and a self-adaptive learning rate method are adopted.
5.4. Regularization technique: through regularization technology including dropout and weight decade, the overfitting is reduced, the generalization capability of the model is improved, and the method has good effects of reducing error rate and enhancing robustness.
5.5. Model integration: through a model integration technology, including integrated learning and cross verification, a plurality of different models are integrated, the variance of the models is reduced, and the accuracy and the robustness of the models are improved.
5.6. And (3) empirical parameter adjustment: finally, the experimental parameter adjustment is needed to be realized, namely, all parameters in the model are optimized, so that the prediction accuracy of the model is improved.
The parameter optimization is carried out by adopting a grid search method or a random search method automatic parameter adjustment method, the S5 intelligent optimization and adjustment is mainly carried out by optimizing algorithm and deep learning technology, the working parameters of the machine tool are optimized and adjusted in real time, and the machining precision, efficiency and energy consumption factors are comprehensively considered, so that the controllability and intelligent optimization of the machine tool are realized. Specifically, the method is realized from the following aspects:
7.1. and (3) constructing a parameter model: firstly, a model of machining parameters of a numerical control machine tool is required to be established, wherein the model comprises cutting force, cutter temperature, surface roughness and machining quality factors, and modeling is carried out by adopting a deep learning and support vector machine algorithm, so that real-time monitoring and control of the machining parameters are realized.
7.2. Parameter optimization algorithm: on the basis of the established model, a parameter optimization algorithm is adopted to optimize machining parameters, and parameters of cutter speed, feeding speed and machining depth are adjusted according to machining tasks so as to achieve optimal machining efficiency, accuracy and energy consumption.
7.3. Multi-objective optimization: aiming at the processing requirement of multiple targets, a multi-target optimization algorithm is adopted for adjustment, and the optimization of the comprehensive effect is achieved by balancing the factors of processing efficiency, processing quality, energy consumption and cutting force.
7.4. Real-time feedback and adjustment: real-time machine tool operation data and processing data are collected, real-time feedback and adjustment are carried out based on the result output by the optimization algorithm, and real-time adjustment and optimization of parameters of the numerical control machine tool are realized in the processing process.
7.5. Misprediction and correction: based on the prediction model, the error prediction and judgment in the processing process are carried out, and the parameters are corrected and adjusted in time when the error occurs, so that the occurrence of the processing error is reduced.
By applying the technical means, the real-time optimization and adjustment of the working parameters of the machine tool are realized in the machining process, the machining quality and efficiency are improved, the machining loss and quality problems caused by errors and abnormal changes are reduced, meanwhile, the energy consumption and loss are effectively reduced, and the aim of intelligent machining is fulfilled.
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 spirit and scope of the invention as defined by the appended claims and their equivalents.
Claims (7)
1. The intelligent analysis method for the machining precision of the numerical control machine tool is characterized by comprising the following steps of:
s1, data acquisition and processing
Collecting processing conventional parameters through a sensor, collecting holographic data and control data of a machine tool or a workpiece by using the sensor besides collecting data of the processing conventional parameters of the numerical control machine tool, establishing a data pool through a big data technology to record, store and process all collected data, and adding a supervised learning method to improve analysis precision;
s2, model construction
Based on the collected data in the analysis data pool, extracting more abundant and detailed characteristic parameters;
s3, model training and optimization
Comparing and analyzing the characteristic parameters and the actual machining precision, constructing a composite model based on a deep learning technology, and carrying out prediction and optimization with higher precision;
s4, model verification
The extracted characteristic parameters, super parameters during model construction and a large amount of historical data are used for model training and optimization;
s5, intelligent optimization and adjustment
The trained model is applied to actual processing data for verification, improvement and upgrading, so that the reliability of data analysis is ensured;
s6, real-time monitoring and auxiliary management
And the obtained analysis visual result penetrates through the key link of the processing and production process, and intelligent production management is implemented.
2. The intelligent analysis method for machining precision of a numerical control machine tool according to claim 1, characterized by comprising the steps of: the multi-layer neural network model consists of an input layer, a hidden layer and an output layer, wherein the input layer is used for receiving input data, the hidden layer is used for processing the data, and the output layer is used for outputting a final result.
3. The intelligent analysis method for machining precision of a numerical control machine tool according to claim 1, characterized by comprising the steps of: the model formula is:
y＝f 2 (v*f 1 (w*x)
wherein x is the input feature vector, w is the weight matrix from the input layer to the hidden layer, f 1 V is the weight matrix from the hidden layer to the output layer, f 2 Is the activation function of the output layer, y is the output of the model.
4. The intelligent analysis method for machining precision of a numerical control machine tool according to claim 1, characterized by comprising the steps of: the root mean square error and the average absolute error are used as regression evaluation indexes of numerical control machining precision:
4.1. root Mean Square Error (RMSE): RMSE represents the average error between the predicted value and the true value, and the calculation formula includes the following:
where n is the number of samples, yi is the true value,is a predicted value. The smaller the RMSE value is, the smaller the deviation of the model prediction result relative to the true value is, and the higher the prediction precision of the model is;
4.2. mean Absolute Error (MAE): MAE represents the mean absolute error between the predicted and actual values, and the calculation formula includes the following:
where n is the number of samples, yi is the true value,is a predicted value. The smaller the MAE value, the smaller the deviation of the model prediction result from the true value, and the prediction of the modelThe higher the accuracy.
5. The intelligent analysis method for machining precision of a numerical control machine tool according to claim 1, characterized by comprising the steps of: s3, training and optimizing the model, wherein the training and optimizing the model comprises the following steps:
5.1. and (3) data processing: firstly, data needs to be processed, including data cleaning, data preprocessing and data dividing;
5.2. model selection and design: selecting a proper model according to specific tasks and requirements;
5.3. optimizing the learning rate: the learning rate determines the parameter change of the model in the training process;
5.4. regularization technique: through regularization technology comprising dropout and weight decade, the overfitting is reduced, and the generalization capability of the model is improved;
5.5. model integration: integrating a plurality of different models through a model integration technology comprising integrated learning and cross verification, so as to reduce the variance of the models;
5.6. and (3) empirical parameter adjustment: finally, the experimental parameter adjustment is needed to be realized, namely, all parameters in the model are optimized, so that the prediction accuracy of the model is improved.
6. The intelligent analysis method for machining precision of a numerical control machine tool according to claim 5, wherein: and (5) carrying out parameter optimization by adopting a grid search method or a random search method and an automatic parameter adjustment method.
7. The intelligent analysis method for machining precision of a numerical control machine tool according to claim 1, characterized by comprising the steps of: s5, intelligent optimization and adjustment are mainly carried out by optimizing algorithm and deep learning technology, the working parameters of the machine tool are optimized and adjusted in real time, and the machining precision, efficiency and energy consumption factors are comprehensively considered.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311385538.4A CN117390960A (en) | 2023-10-25 | 2023-10-25 | Intelligent analysis method for machining precision of numerical control machine tool |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311385538.4A CN117390960A (en) | 2023-10-25 | 2023-10-25 | Intelligent analysis method for machining precision of numerical control machine tool |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117390960A true CN117390960A (en) | 2024-01-12 |
Family
ID=89466263
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311385538.4A Pending CN117390960A (en) | 2023-10-25 | 2023-10-25 | Intelligent analysis method for machining precision of numerical control machine tool |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117390960A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117762113A (en) * | 2024-02-22 | 2024-03-26 | 宁波数益工联科技有限公司 | Automatic monitoring iterative parameter adjusting method and system based on integrated model |
-
2023
- 2023-10-25 CN CN202311385538.4A patent/CN117390960A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117762113A (en) * | 2024-02-22 | 2024-03-26 | 宁波数益工联科技有限公司 | Automatic monitoring iterative parameter adjusting method and system based on integrated model |
| CN117762113B (en) * | 2024-02-22 | 2024-05-10 | 宁波数益工联科技有限公司 | Automatic monitoring iterative parameter adjusting method and system based on integrated model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107967542B (en) | Long-short term memory network-based electricity sales amount prediction method | |
| CN109472057B (en) | Product processing quality prediction device and method based on cross-process implicit parameter memory | |
| CN111178553A (en) | Industrial equipment health trend analysis method and system based on ARIMA and LSTM algorithms | |
| CN114048600A (en) | Digital twin-driven multi-model fusion industrial system anomaly detection method | |
| CN117390960A (en) | Intelligent analysis method for machining precision of numerical control machine tool | |
| CN111258984B (en) | Product quality end-edge-cloud collaborative forecasting method under industrial big data environment | |
| CN114595623A (en) | XGboost algorithm-based unit equipment reference value prediction method and system | |
| CN115081585B (en) | Man-machine object cooperative abnormal state detection method for reinforced heterographic neural network | |
| CN115828754A (en) | Cutter wear state monitoring method based on multi-scale space-time fusion network model | |
| CN116520772A (en) | Sheet part numerical control machining quality prediction method based on multitasking transfer learning | |
| CN112288157A (en) | Wind power plant power prediction method based on fuzzy clustering and deep reinforcement learning | |
| CN110231808B (en) | Production process energy efficiency trans-scale intelligent cooperative control system and method | |
| Qin et al. | A novel online tool condition monitoring method for milling titanium alloy with consideration of tool wear law | |
| CN114239396A (en) | Fan gear box state prediction method and system | |
| CN116020879B (en) | Technological parameter-oriented strip steel hot continuous rolling space-time multi-scale process monitoring method and device | |
| CN111142488B (en) | Process industrial optimization method based on working condition comparison driving | |
| CN117113086A (en) | Energy storage unit load prediction method, system, electronic equipment and medium | |
| CN116880201A (en) | Water network channel state control system based on fuzzy neural network | |
| CN116401545A (en) | Multimode fusion type turbine runout analysis method | |
| Raptodimos et al. | An artificial neural network approach for predicting the performance of ship machinery equipment | |
| CN110837959A (en) | Method for balancing and fixing welding dispatching working hours based on welding quantity and operation mode | |
| Wang et al. | Quality–efficiency coupling prediction and monitoring-based process optimization of thin plate parts with multi-machining feature | |
| Ak et al. | Ensemble neural network model for predicting the energy consumption of a milling machine | |
| CN112990601B (en) | Worm wheel machining precision self-healing system and method based on data mining | |
| CN111814861B (en) | Online cooling control method based on double self-learning models |
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 |