CN116300691A - State monitoring method and system for multi-axis linkage numerical control machining - Google Patents
State monitoring method and system for multi-axis linkage numerical control machining Download PDFInfo
- Publication number
- CN116300691A CN116300691A CN202310596232.7A CN202310596232A CN116300691A CN 116300691 A CN116300691 A CN 116300691A CN 202310596232 A CN202310596232 A CN 202310596232A CN 116300691 A CN116300691 A CN 116300691A
- Authority
- CN
- China
- Prior art keywords
- data
- axis
- numerical control
- working condition
- machining
- 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
- 238000003754 machining Methods 0.000 title claims abstract description 139
- 238000012544 monitoring process Methods 0.000 title claims abstract description 76
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 97
- 230000004927 fusion Effects 0.000 claims abstract description 20
- 238000013528 artificial neural network Methods 0.000 claims abstract description 18
- 238000000605 extraction Methods 0.000 claims abstract description 16
- 239000011159 matrix material Substances 0.000 claims description 30
- 230000007246 mechanism Effects 0.000 claims description 30
- 238000010586 diagram Methods 0.000 claims description 21
- 230000006870 function Effects 0.000 claims description 20
- 238000013506 data mapping Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 10
- 238000009826 distribution Methods 0.000 claims description 8
- 238000003064 k means clustering Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 230000002776 aggregation Effects 0.000 claims description 4
- 238000004220 aggregation Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 230000000712 assembly Effects 0.000 claims description 2
- 238000000429 assembly Methods 0.000 claims description 2
- 230000002159 abnormal effect Effects 0.000 abstract description 4
- 238000004519 manufacturing process Methods 0.000 abstract description 4
- 238000003860 storage Methods 0.000 description 9
- 238000012423 maintenance Methods 0.000 description 6
- 230000004913 activation Effects 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000012512 characterization method Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
Images
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
- G05B19/406—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 monitoring or safety
-
- 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
- G05B2219/31—From computer integrated manufacturing till monitoring
- G05B2219/31434—Zone supervisor, collects error signals from, and diagnoses different zone
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Manufacturing & Machinery (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Numerical Control (AREA)
Abstract
The invention discloses a state monitoring method and a system for multi-axis linkage numerical control machining, comprising the following steps: acquiring a three-dimensional model corresponding to a physical entity of a multi-axis machine tool in multi-axis numerical control machining, collecting operation data and multi-source monitoring data of the multi-axis machine tool, constructing a digital twin model of multi-axis numerical control machining to acquire twin data, and judging machining error information based on a theoretical machining track and an actual machining track; carrying out data fusion on the processing error information and the twin data, generating working condition data, carrying out feature extraction, and obtaining working condition features of the current time step; and constructing a state identification model of multi-axis numerical control machining based on the graph convolution neural network, taking the working condition characteristics as input, and identifying and judging faults of the machining state corresponding to the current time step. The invention conveniently and accurately monitors the abnormal state or fault information of the multi-axis machine tool through the multi-source monitoring data, thereby ensuring the machining precision of multi-axis linkage numerical control machining, reducing the occurrence rate of production accidents and improving the production and machining efficiency.
Description
Technical Field
The invention relates to the technical field of numerical control machining state monitoring, in particular to a state monitoring method and system for multi-axis linkage numerical control machining.
Background
In the performance evaluation and optimization design process of the numerical control machine tool, the machining precision has an important role, so that the improvement of the precision and the level of the machine tool is very critical. An important aspect of the machine tool level is whether the machine tool can control the machining process and monitor the machining performance of the machine tool, and timely process the monitored information, and effective measures are taken to ensure the safety, reliability and quality of machining.
The state monitoring of the multi-axis numerical control machine tool aims to master abnormal symptoms and degradation information before the machine tool breaks down, provide basic data for application works such as fault mode identification, fault prediction, fault diagnosis and predictive maintenance of the numerical control machine tool, can take targeted measures before the fault occurs, and realize the advance from post maintenance to predictive maintenance, thereby reducing maintenance cost and improving the use efficiency of the machine tool. At present, the working state of the multi-axis numerical control machine tool is usually tested in a related manner by adopting a traditional vibration tester, a temperature inspection instrument and the like, and the aim of real-time monitoring cannot be achieved, so that the problem that how to analyze the working state of multi-axis linkage numerical control machining and compensate for the abnormal working state is needed to be solved is urgent.
Disclosure of Invention
In order to solve the technical problems, the invention provides a state monitoring method and a state monitoring system for multi-axis linkage numerical control machining.
The first aspect of the invention provides a state monitoring method for multi-axis linkage numerical control machining, which comprises the following steps:
acquiring a three-dimensional model corresponding to a physical entity of a multi-axis machine tool in multi-axis numerical control machining, collecting operation data and multi-source monitoring data of the multi-axis machine tool, establishing data mapping with the three-dimensional model, and constructing a digital twin model of the multi-axis numerical control machining;
obtaining twin data according to the digital twin model, obtaining a processing task of current multi-axis combined numerical control processing, obtaining theoretical processing tracks of all axes through the processing task, and judging processing error information based on the theoretical processing tracks and the actual processing tracks;
performing data fusion on the processing error information and the twin data to generate working condition data, and performing feature extraction on the working condition data to obtain working condition features of the current time step;
and constructing a state identification model of multi-axis numerical control machining based on the graph convolution neural network, taking the working condition characteristics as the input of the state identification model, and identifying and judging faults of the machining state corresponding to the current time step.
In the scheme, a digital twin model of multi-axis numerical control machining is constructed, specifically:
acquiring the spatial position relation and description characteristics of each part of a multi-axis machine tool in multi-axis numerical control machining, classifying each part, and dividing the parts into multi-level assemblies according to classification results;
acquiring a three-dimensional geometric model of each part by utilizing data retrieval, assembling according to a space assembly relation and a motion characteristic relation among the parts, generating a digital twin geometric model of each hierarchical assembly, and parameterizing the characteristics of the digital twin geometric model of each hierarchical assembly;
based on the parameterized representation, carrying out parameter consistency adjustment on the digital twin geometric model of each level assembly, and assembling the digital twin geometric model of each level assembly to generate a three-dimensional model of the multi-axis machine tool;
acquiring multi-source monitoring data of each shaft in a multi-shaft machine tool through a sensor, transmitting the multi-source monitoring data by using a communication interface for transmission, and performing data mapping with a three-dimensional model of the multi-shaft machine tool after data cleaning;
and constructing a digital twin model of multi-axis numerical control machining based on the three-dimensional model of the multi-axis machine tool and the data mapping.
In the scheme, a processing task of current multi-axis combined numerical control processing is acquired, a theoretical processing track of each axis is acquired through the processing task, and processing error information is judged based on the theoretical processing track and the actual processing track, specifically:
extracting a processing task of current multi-axis combined numerical control processing, extracting processing tracks of the processing tasks corresponding to all axes, dividing the processing tracks into a plurality of sub-paths, acquiring key points in the sub-paths, and acquiring feeding speeds of the key points;
generating a path sequence of a theoretical machining path based on the machining path of each shaft and the feeding speed of the key point, acquiring the actual position and the actual speed of each shaft of the multi-shaft machine tool at the key point, and generating a path sequence of an actual machining path;
and judging the DTW distance between the path sequence of the theoretical machining path and the path sequence of the actual machining path of each shaft, acquiring error distribution of each shaft according to the DTW distance, and acquiring machining error information of each shaft according to the error distribution.
In this scheme, carry out the data fusion with processing error information and twin data, generate operating mode data, carry out the feature extraction to operating mode data, acquire the operating mode characteristic of current time step, specifically do:
Acquiring a mean square error in a preset time through historical monitoring data of multi-source monitoring data, acquiring a total mean square error according to the mean square error of each monitoring data, and acquiring a weighting weight of each monitoring data according to the principle that the total mean square error is minimum;
the multi-source monitoring data are subjected to data fusion by the weighting weights and imported into a digital twin model to generate twin data, a data tag of the twin data is set according to basic information of each shaft, and the twin data of each shaft are subjected to data fusion after being matched with corresponding processing error information, so that working condition data of each shaft are obtained;
the working condition data sequences of all the shafts in the preset time are imported into a convolutional neural network for feature extraction, the working condition data sequences are divided by utilizing a sliding window, and the working condition data sequences are divided into subsequences with preset lengths after one-dimensional convolution processing, and normalization processing is carried out;
encoding the normalized subsequence by a multi-head attention mechanism, and obtaining weighted attention results as output results by applying a self-attention mechanism to each head in the multi-head attention mechanism;
and performing matrix splicing on a plurality of output results obtained by the multi-head attention mechanism, projecting the output results to the length identical to the length of the working condition data sequence, and obtaining the working condition characteristics of the current time step after data decoding.
In the scheme, a state identification model of multi-axis numerical control machining is constructed based on a graph convolution neural network, and specifically comprises the following steps:
acquiring historical fault information of a multi-axis machine tool in multi-axis linkage numerical control machining, reading a preset number of fault categories, simulating working condition characteristics corresponding to each fault category through a digital twin body model, and carrying out characteristic coding on the working condition characteristics by utilizing a sub-encoder to construct a characteristic space;
clustering the coded features in the feature space by using K-means clustering to generate a clustering center, constructing a loss function by using a clustering error in the clustering process and a feature reconstruction error of feature coding, and training until the loss function converges;
outputting cluster centers, wherein the cluster centers correspond to fault categories, judging Euclidean distances between each cluster center and other cluster centers, sequencing the other cluster centers according to the Euclidean distances, presetting a distance threshold, and acquiring other cluster centers smaller than the preset distance threshold for connection;
and constructing a fault diagram of the multi-axis machine tool, learning and representing the fault diagram through a diagram convolution neural network, establishing a state identification model, acquiring a feature vector corresponding to the working condition feature of the current step length, and carrying out state and fault identification judgment.
In the scheme, a state identification model is established, a feature vector corresponding to the working condition feature of the current step length is obtained, and the state and fault identification judgment is carried out, specifically:
leading the working condition characteristics of the current step length into a state identification model, obtaining a corresponding graph structure, and obtaining initial vector representations corresponding to the working condition characteristics through graph convolution;
acquiring a neighbor matrix of a working condition characteristic corresponding graph structure, introducing a graph attention mechanism, setting attention weights for corresponding neighbor nodes in the neighbor matrix, and updating vector representations of the characteristics by using the attention weights through a neighbor aggregation mechanism;
and setting two graph roll layers, one graph attention layer and two full-connection layers in the state identification model to obtain an aggregated feature vector, and importing the feature vector into the full-connection layers to reduce the dimension and classify the nodes to obtain the identification classification results of states and faults.
The second aspect of the present invention also provides a state monitoring system for multi-axis linkage numerical control machining, the system comprising: the system comprises a memory and a processor, wherein the memory comprises a state monitoring method program of multi-axis linkage numerical control machining, and the state monitoring method program of the multi-axis linkage numerical control machining is executed by the processor to realize the following steps:
Acquiring a three-dimensional model corresponding to a physical entity of a multi-axis machine tool in multi-axis numerical control machining, collecting operation data and multi-source monitoring data of the multi-axis machine tool, establishing data mapping with the three-dimensional model, and constructing a digital twin model of the multi-axis numerical control machining;
obtaining twin data according to the digital twin model, obtaining a processing task of current multi-axis combined numerical control processing, obtaining theoretical processing tracks of all axes through the processing task, and judging processing error information based on the theoretical processing tracks and the actual processing tracks;
performing data fusion on the processing error information and the twin data to generate working condition data, and performing feature extraction on the working condition data to obtain working condition features of the current time step;
and constructing a state identification model of multi-axis numerical control machining based on the graph convolution neural network, taking the working condition characteristics as the input of the state identification model, and identifying and judging faults of the machining state corresponding to the current time step.
The invention discloses a state monitoring method and a system for multi-axis linkage numerical control machining, comprising the following steps: acquiring a three-dimensional model corresponding to a physical entity of a multi-axis machine tool in multi-axis numerical control machining, collecting operation data and multi-source monitoring data of the multi-axis machine tool, constructing a digital twin model of multi-axis numerical control machining to acquire twin data, and judging machining error information based on a theoretical machining track and an actual machining track; carrying out data fusion on the processing error information and the twin data, generating working condition data, carrying out feature extraction, and obtaining working condition features of the current time step; and constructing a state identification model of multi-axis numerical control machining based on the graph convolution neural network, taking the working condition characteristics as input, and identifying and judging faults of the machining state corresponding to the current time step. The invention conveniently and accurately monitors the abnormal state or fault information of the multi-axis machine tool through the multi-source monitoring data, thereby ensuring the machining precision of multi-axis linkage numerical control machining, reducing the occurrence rate of production accidents and improving the production and machining efficiency.
Drawings
FIG. 1 shows a flow chart of a state monitoring method of multi-axis linkage numerical control machining of the present invention;
FIG. 2 is a flow chart of a method of the present invention for obtaining operating characteristics of a current time step;
FIG. 3 shows a flow chart of a method for constructing a state recognition model of multi-axis numerical control machining based on a graph convolutional neural network;
fig. 4 shows a block diagram of a state monitoring system for multi-axis linkage numerical control machining according to the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
Fig. 1 shows a flow chart of a state monitoring method of multi-axis linkage numerical control machining of the invention.
As shown in fig. 1, a first aspect of the present invention provides a state monitoring method for multi-axis linkage numerical control machining, including:
S102, acquiring a three-dimensional model corresponding to a physical entity of a multi-axis machine tool in multi-axis numerical control machining, collecting operation data and multi-source monitoring data of the multi-axis machine tool, establishing data mapping with the three-dimensional model, and constructing a digital twin model of the multi-axis numerical control machining;
s104, obtaining twin data according to the digital twin model, obtaining a processing task of current multi-axis combined numerical control processing, obtaining theoretical processing tracks of all axes through the processing task, and judging processing error information based on the theoretical processing tracks and the actual processing tracks;
s106, carrying out data fusion on the processing error information and the twin data to generate working condition data, and carrying out feature extraction on the working condition data to obtain working condition features of the current time step;
s108, constructing a state identification model of multi-axis numerical control machining based on a graph convolution neural network, taking the working condition characteristics as the input of the state identification model, and identifying and judging faults of the machining state corresponding to the current time step.
The spatial position relationship and description characteristics of each part of the multi-axis machine tool in multi-axis numerical control machining are obtained, and each part is classified, for example: control systems, mechanical systems, electrical systems, etc.; dividing the parts into a plurality of layers of components according to the classification result; acquiring a three-dimensional geometric model of each part in a CAD model and a part standard by utilizing data retrieval, assembling according to a space assembly relation such as a coaxial relation or a parallel relation among the parts and a motion characteristic relation, generating a digital twin geometric model of each hierarchical assembly, and parameterizing the characteristics of the digital twin geometric model of each hierarchical assembly; based on the parameterized representation, carrying out parameter consistency adjustment on the digital twin geometric model of each level assembly, and assembling the digital twin geometric model of each level assembly to generate a three-dimensional model of the multi-axis machine tool; acquiring multi-source monitoring data of each shaft in a multi-shaft machine tool through a sensor, transmitting the multi-source monitoring data by using a communication interface for transmission, and performing data mapping with a three-dimensional model of the multi-shaft machine tool after data cleaning and data standardization processing; and constructing a digital twin model of multi-axis numerical control machining based on the three-dimensional model and data mapping of the multi-axis machine tool, wherein the digital twin model can be used for simulation of fault information, identification of machining state, three-dimensional visualization of fault information and the like.
It should be noted that, extracting a processing task of the current multi-axis combined numerical control processing, extracting a processing track of each axis corresponding to the processing task, dividing the processing track into a plurality of sub-paths, acquiring key points in the plurality of sub-paths, and acquiring a feeding speed planned in advance by the key points; acquiring extreme points of curvatures in the sub-paths as key points in each sub-path, and selecting the middle point of the sub-path as the key point if the curvatures of all points in the sub-path are equal; generating a path sequence of a theoretical machining path based on the machining path of each shaft and the feeding speed of the key point, acquiring the actual position and the actual speed of each shaft of the multi-shaft machine tool at the key point, and generating a path sequence of an actual machining path; the path sequence can be regarded as a time sequence of positions, a path sequence corresponding to a theoretical machining path is matched with a path sequence of an actual machining path by using a time warping algorithm (DTW), the DTW distance between the path sequence of the theoretical machining path and the path sequence of the actual machining path of each shaft is judged, the error distribution of each shaft is obtained according to the DTW distance, and the machining error information of each shaft is obtained according to the error distribution.
FIG. 2 illustrates a flow chart of a method of the present invention for obtaining operating characteristics of a current time step.
According to the embodiment of the invention, the processing error information and the twin data are subjected to data fusion to generate working condition data, and the working condition data is subjected to feature extraction to obtain working condition features of the current time step, wherein the working condition features are specifically as follows:
s202, acquiring a mean square error in a preset time through historical monitoring data of multi-source monitoring data, acquiring a total mean square error according to the mean square error of each monitoring data, and acquiring a weighting weight of each monitoring data according to the principle that the total mean square error is minimum;
s204, carrying out data fusion on the multi-source monitoring data through the weighted weights, importing the multi-source monitoring data into a digital twin model to generate twin data, setting a data tag of the twin data according to the basic information of each shaft, carrying out data fusion on the twin data of each shaft after matching with the corresponding processing error information, and obtaining the working condition data of each shaft;
s206, importing the working condition data sequences of all axes in a preset time into a convolutional neural network for feature extraction, dividing the working condition data sequences by utilizing a sliding window, dividing the working condition data sequences into subsequences with preset lengths after one-dimensional convolution processing, and carrying out normalization processing;
s208, coding the normalized subsequence through a multi-head attention mechanism, and obtaining weighted attention results as output results by applying a self-attention mechanism to each head in the multi-head attention mechanism;
And S210, performing matrix splicing on a plurality of output results obtained by the multi-head attention mechanism, projecting the output results to the same length as the working condition data sequence, and obtaining the working condition characteristics of the current time step after data decoding.
The data tag of the twin data is set according to the basic information of each axis, wherein the basic data comprises an axis attribute and an axis number, and the axis attribute is divided into a translational axis, a rotational axis and the like. Acquiring the weighting weight of each monitoring data according to the principle of minimum total mean square error, and acquiring the weighting weight according to the extremum taking method,/>Wherein->N is the total mean square error of the first data source and n is the total number of data sources. The query matrix Q, the key matrix K and the value matrix V input by the multi-head attention mechanism set the matrix size according to the sequence length, generate Q, K, V the same as the number of heads and input the Q, K, V into each head, and the ith head acquires the weighted attention result through the self-attention mechanism->,/>,/>Representing the number of sub-sequence items,/->Representing matrix size, +.>Respectively representing the ith subsequenceInquiring the matrix, the key matrix and the value matrix, and calculating the correlation degree by combining the previous subsequences by means of a self-attention mechanism so as to achieve the aim of extracting sequence features; the multi-head attention mechanism is composed of a plurality of attention blocks, each attention block is connected through a residual error, a convolution layer is arranged in each attention block, and a sequence is projected to the same length as the working condition data sequence for the next attention block to use.
Fig. 3 shows a flowchart of a method for constructing a state recognition model of multi-axis numerical control machining based on a graph convolutional neural network.
According to the embodiment of the invention, a state identification model of multi-axis numerical control processing is constructed based on a graph convolution neural network, and the model is specifically as follows:
s302, acquiring historical fault information of a multi-axis machine tool in multi-axis linkage numerical control machining, reading a preset number of fault categories, simulating working condition characteristics corresponding to each fault category through a digital twin body model, and carrying out characteristic coding on the working condition characteristics by utilizing a sub-encoder to construct a characteristic space;
s304, clustering the coded features in the feature space by using K-means clustering to generate a clustering center, constructing a loss function by using a clustering error in the clustering process and a feature reconstruction error of feature coding, and training until the loss function converges;
s306, outputting cluster centers, wherein the cluster centers correspond to fault categories, judging Euclidean distances between each cluster center and other cluster centers, sequencing the other cluster centers according to the Euclidean distances, presetting a distance threshold, and acquiring other cluster centers smaller than the preset distance threshold for connection;
s308, constructing a fault diagram of the multi-axis machine tool, learning and representing the fault diagram through a diagram convolution neural network, building a state identification model, acquiring a feature vector corresponding to the working condition feature of the current step length, and carrying out state and fault identification judgment.
It should be noted that, the encoder performs nonlinear mapping conversion on the working condition characteristics to perform dimension reduction on the data, where the parameter optimization is performed by minimizing the characteristic reconstruction error in the characteristic encoding, and the characteristic reconstruction errorLoss functionExpressed as: />Wherein x is the working condition characteristic, +.>Representing decoder activation function, +.>Representing a weight matrix, +.>Representing the encoder activation function, clustering the encoded features by using K-means clustering to generate a cluster center, calculating a cluster loss according to the cluster error, and obtaining a cluster error loss function->Expressed as->,Representing the number of data samples>Representing the number of clusters, +.>Indicate->The sample is at->The coded mapping feature of the clusters, d represents the super parameter, which is the preset distance information,/for each cluster>Indicate->The cluster center of each cluster constructs a loss function through the cluster error in the clustering process and the characteristic reconstruction error of the characteristic code, and the characteristic reconstruction error loss function is +.>And a cluster error loss function->And adding to obtain a loss function.
Constructing a fault diagram of the multi-axis machine tool, wherein fault categories are used as nodes in the fault diagram of the multi-axis machine tool, and connection relations among the fault category nodes are used as edge structures in the fault diagram. Selecting different fault sample data sets to train the state recognition model, wherein the fault sample data sets comprise normal states and various fault information, dividing training sets and test sets based on the fault sample data sets, carrying out iterative training on the state recognition model by using the training sets, and outputting the state recognition model when the test precision of the model reaches a preset standard; leading the working condition characteristics of the current step length into a state identification model, obtaining a corresponding graph structure, and obtaining initial vector representations corresponding to the working condition characteristics through graph convolution; acquiring a neighbor matrix of a working condition characteristic corresponding graph structure, introducing a graph attention mechanism, setting attention weights for corresponding neighbor nodes in the neighbor matrix, and updating vector representations of the characteristics by using the attention weights through a neighbor aggregation mechanism; and setting two graph roll layers, one graph attention layer and two full-connection layers in the state identification model to obtain an aggregated feature vector, and importing the feature vector into the full-connection layers to reduce the dimension and classify the nodes to obtain the identification classification results of states and faults.
According to the embodiment of the application, a fault knowledge graph of the multi-axis machine tool is constructed, specifically:
extracting historical fault information of the multi-axis machine tool, obtaining working condition characteristics, fault category information, fault characteristic information and fault operation and maintenance scheme corresponding to the historical fault information, constructing a triplet, and constructing a fault knowledge graph of the multi-axis machine tool based on the triplet;
acquiring current fault information of the multi-axis machine tool, extracting corresponding working condition characteristics, acquiring fault characterization of the current fault information in each component according to the working condition characteristics, and searching in a fault knowledge graph through the fault characterization of each component;
acquiring the mahalanobis distance between the feature data corresponding to the fault characterization and the working condition features corresponding to each piece of historical fault information, acquiring the similarity according to the mahalanobis distance, and marking the historical fault information when the similarity is larger than a preset similarity threshold;
generating a coupling fault list of the current fault information according to the marked historical fault information, acquiring an operation and maintenance scheme in the coupling fault list through a fault knowledge graph to acquire a key component, and generating an overhaul early warning of the key component.
Fig. 4 shows a block diagram of a state monitoring system for multi-axis linkage numerical control machining according to the present invention.
The second aspect of the present invention also provides a state monitoring system 4 for multi-axis linkage numerical control machining, the system comprising: the memory 41 and the processor 42, wherein the memory includes a state monitoring method program of multi-axis linkage numerical control machining, and the state monitoring method program of multi-axis linkage numerical control machining when executed by the processor realizes the following steps:
acquiring a three-dimensional model corresponding to a physical entity of a multi-axis machine tool in multi-axis numerical control machining, collecting operation data and multi-source monitoring data of the multi-axis machine tool, establishing data mapping with the three-dimensional model, and constructing a digital twin model of the multi-axis numerical control machining;
obtaining twin data according to the digital twin model, obtaining a processing task of current multi-axis combined numerical control processing, obtaining theoretical processing tracks of all axes through the processing task, and judging processing error information based on the theoretical processing tracks and the actual processing tracks;
performing data fusion on the processing error information and the twin data to generate working condition data, and performing feature extraction on the working condition data to obtain working condition features of the current time step;
and constructing a state identification model of multi-axis numerical control machining based on the graph convolution neural network, taking the working condition characteristics as the input of the state identification model, and identifying and judging faults of the machining state corresponding to the current time step.
The spatial position relationship and description characteristics of each part of the multi-axis machine tool in multi-axis numerical control machining are obtained, and each part is classified, for example: control systems, mechanical systems, electrical systems, etc.; dividing the parts into a plurality of layers of components according to the classification result; acquiring a three-dimensional geometric model of each part in a CAD model and a part standard by utilizing data retrieval, assembling according to a space assembly relation such as a coaxial relation or a parallel relation among the parts and a motion characteristic relation, generating a digital twin geometric model of each hierarchical assembly, and parameterizing the characteristics of the digital twin geometric model of each hierarchical assembly; based on the parameterized representation, carrying out parameter consistency adjustment on the digital twin geometric model of each level assembly, and assembling the digital twin geometric model of each level assembly to generate a three-dimensional model of the multi-axis machine tool; acquiring multi-source monitoring data of each shaft in a multi-shaft machine tool through a sensor, transmitting the multi-source monitoring data by using a communication interface for transmission, and performing data mapping with a three-dimensional model of the multi-shaft machine tool after data cleaning and data standardization processing; and constructing a digital twin model of multi-axis numerical control machining based on the three-dimensional model and data mapping of the multi-axis machine tool, wherein the digital twin model can be used for simulation of fault information, identification of machining state, three-dimensional visualization of fault information and the like.
It should be noted that, extracting a processing task of the current multi-axis combined numerical control processing, extracting a processing track of each axis corresponding to the processing task, dividing the processing track into a plurality of sub-paths, acquiring key points in the plurality of sub-paths, and acquiring a feeding speed planned in advance by the key points; acquiring extreme points of curvatures in the sub-paths as key points in each sub-path, and selecting the middle point of the sub-path as the key point if the curvatures of all points in the sub-path are equal; generating a path sequence of a theoretical machining path based on the machining path of each shaft and the feeding speed of the key point, acquiring the actual position and the actual speed of each shaft of the multi-shaft machine tool at the key point, and generating a path sequence of an actual machining path; the path sequence can be regarded as a time sequence of positions, a path sequence corresponding to a theoretical machining path is matched with a path sequence of an actual machining path by using a time warping algorithm (DTW), the DTW distance between the path sequence of the theoretical machining path and the path sequence of the actual machining path of each shaft is judged, the error distribution of each shaft is obtained according to the DTW distance, and the machining error information of each shaft is obtained according to the error distribution.
According to the embodiment of the invention, the processing error information and the twin data are subjected to data fusion to generate working condition data, and the working condition data is subjected to feature extraction to obtain working condition features of the current time step, wherein the working condition features are specifically as follows:
Acquiring a mean square error in a preset time through historical monitoring data of multi-source monitoring data, acquiring a total mean square error according to the mean square error of each monitoring data, and acquiring a weighting weight of each monitoring data according to the principle that the total mean square error is minimum;
the multi-source monitoring data are subjected to data fusion by the weighting weights and imported into a digital twin model to generate twin data, a data tag of the twin data is set according to basic information of each shaft, and the twin data of each shaft are subjected to data fusion after being matched with corresponding processing error information, so that working condition data of each shaft are obtained;
the working condition data sequences of all the shafts in the preset time are imported into a convolutional neural network for feature extraction, the working condition data sequences are divided by utilizing a sliding window, and the working condition data sequences are divided into subsequences with preset lengths after one-dimensional convolution processing, and normalization processing is carried out;
encoding the normalized subsequence by a multi-head attention mechanism, and obtaining weighted attention results as output results by applying a self-attention mechanism to each head in the multi-head attention mechanism;
and performing matrix splicing on a plurality of output results obtained by the multi-head attention mechanism, projecting the output results to the length identical to the length of the working condition data sequence, and obtaining the working condition characteristics of the current time step after data decoding.
It should be noted thatThe weighting weight of each monitoring data is obtained according to the principle of minimum total mean square error, and the weighting weight is obtained according to the extremum taking method,/>Wherein->N is the total mean square error of the first data source and n is the total number of data sources. The query matrix Q, the key matrix K and the value matrix V input by the multi-head attention mechanism set the matrix size according to the sequence length, generate Q, K, V the same as the number of heads and input the Q, K, V into each head, and the ith head acquires the weighted attention result through the self-attention mechanism->,/>,/>Representing the number of sub-sequence items,/->Representing matrix size, +.>Respectively representing a query matrix, a key matrix and a value matrix of the ith subsequence, and calculating the correlation degree by combining the previous subsequences by means of a self-attention mechanism so as to achieve the aim of extracting sequence features; the multi-head attention mechanism is composed of a plurality of attention blocks, each attention block is connected through a residual error, a convolution layer is arranged in each attention block, and a sequence is projected to the same length as the working condition data sequence for the next attention block to use.
According to the embodiment of the invention, a state identification model of multi-axis numerical control processing is constructed based on a graph convolution neural network, and the model is specifically as follows:
acquiring historical fault information of a multi-axis machine tool in multi-axis linkage numerical control machining, reading a preset number of fault categories, simulating working condition characteristics corresponding to each fault category through a digital twin body model, and carrying out characteristic coding on the working condition characteristics by utilizing a sub-encoder to construct a characteristic space;
Clustering the coded features in the feature space by using K-means clustering to generate a clustering center, constructing a loss function by using a clustering error in the clustering process and a feature reconstruction error of feature coding, and training until the loss function converges;
outputting cluster centers, wherein the cluster centers correspond to fault categories, judging Euclidean distances between each cluster center and other cluster centers, sequencing the other cluster centers according to the Euclidean distances, presetting a distance threshold, and acquiring other cluster centers smaller than the preset distance threshold for connection;
and constructing a fault diagram of the multi-axis machine tool, learning and representing the fault diagram through a diagram convolution neural network, establishing a state identification model, acquiring a feature vector corresponding to the working condition feature of the current step length, and carrying out state and fault identification judgment.
It should be noted that, the encoder performs nonlinear mapping conversion on the working condition characteristics to perform dimension reduction on the data, where the parameter optimization is performed by minimizing the characteristic reconstruction error in the characteristic encoding, and the characteristic reconstruction error loss functionExpressed as: />Wherein x is the working condition characteristic, +.>Representing decoder activation function, +.>Representing a weight matrix, +. >Representing encoder activation function, using K-means clustering to encode the encoded featuresClustering is performed to generate a clustering center, clustering loss is calculated according to clustering errors, and a clustering error loss function is +.>Denoted as->,Representing the number of data samples>Representing the number of clusters, +.>Indicate->The sample is at->The coded mapping feature of the clusters, d represents the super parameter, which is the preset distance information,/for each cluster>Indicate->The cluster center of each cluster constructs a loss function through the cluster error in the clustering process and the characteristic reconstruction error of the characteristic code, and the characteristic reconstruction error loss function is +.>And a cluster error loss function->And adding to obtain a loss function.
Constructing a fault diagram of the multi-axis machine tool, wherein fault categories are used as nodes in the fault diagram of the multi-axis machine tool, and connection relations among the fault category nodes are used as edge structures in the fault diagram. Selecting different fault sample data sets to train the state recognition model, wherein the fault sample data sets comprise normal states and various fault information, dividing training sets and test sets based on the fault sample data sets, carrying out iterative training on the state recognition model by using the training sets, and outputting the state recognition model when the test precision of the model reaches a preset standard; leading the working condition characteristics of the current step length into a state identification model, obtaining a corresponding graph structure, and obtaining initial vector representations corresponding to the working condition characteristics through graph convolution; acquiring a neighbor matrix of a working condition characteristic corresponding graph structure, introducing a graph attention mechanism, setting attention weights for corresponding neighbor nodes in the neighbor matrix, and updating vector representations of the characteristics by using the attention weights through a neighbor aggregation mechanism; and setting two graph roll layers, one graph attention layer and two full-connection layers in the state identification model to obtain an aggregated feature vector, and importing the feature vector into the full-connection layers to reduce the dimension and classify the nodes to obtain the identification classification results of states and faults.
The third aspect of the present invention also provides a computer readable storage medium, where the computer readable storage medium includes a state monitoring method program for multi-axis linkage numerical control machining, where the state monitoring method program for multi-axis linkage numerical control machining, when executed by a processor, implements the steps of the state monitoring method for multi-axis linkage numerical control machining as described in any one of the above.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (8)
1. The state monitoring method for the multi-axis linkage numerical control machining is characterized by comprising the following steps of:
acquiring a three-dimensional model corresponding to a physical entity of a multi-axis machine tool in multi-axis numerical control machining, collecting operation data and multi-source monitoring data of the multi-axis machine tool, establishing data mapping with the three-dimensional model, and constructing a digital twin model of the multi-axis numerical control machining;
obtaining twin data according to the digital twin model, obtaining a processing task of current multi-axis combined numerical control processing, obtaining theoretical processing tracks of all axes through the processing task, and judging processing error information based on the theoretical processing tracks and the actual processing tracks;
performing data fusion on the processing error information and the twin data to generate working condition data, and performing feature extraction on the working condition data to obtain working condition features of the current time step;
And constructing a state identification model of multi-axis numerical control machining based on the graph convolution neural network, taking the working condition characteristics as the input of the state identification model, and identifying and judging faults of the machining state corresponding to the current time step.
2. The state monitoring method for multi-axis linkage numerical control machining according to claim 1, wherein a digital twin model for multi-axis numerical control machining is constructed, specifically:
acquiring the spatial position relation and description characteristics of each part of a multi-axis machine tool in multi-axis numerical control machining, classifying each part, and dividing the parts into multi-level assemblies according to classification results;
acquiring a three-dimensional geometric model of each part by utilizing data retrieval, assembling according to a space assembly relation and a motion characteristic relation among the parts, generating a digital twin geometric model of each hierarchical assembly, and parameterizing the characteristics of the digital twin geometric model of each hierarchical assembly;
based on the parameterized representation, carrying out parameter consistency adjustment on the digital twin geometric model of each level assembly, and assembling the digital twin geometric model of each level assembly to generate a three-dimensional model of the multi-axis machine tool;
acquiring multi-source monitoring data of each shaft in a multi-shaft machine tool through a sensor, transmitting the multi-source monitoring data by using a communication interface for transmission, and performing data mapping with a three-dimensional model of the multi-shaft machine tool after data cleaning;
And constructing a digital twin model of multi-axis numerical control machining based on the three-dimensional model of the multi-axis machine tool and the data mapping.
3. The state monitoring method of multi-axis linkage numerical control machining according to claim 1, wherein a machining task of current multi-axis combination numerical control machining is obtained, a theoretical machining track of each axis is obtained through the machining task, and machining error information is judged based on the theoretical machining track and an actual machining track, specifically:
extracting a processing task of current multi-axis combined numerical control processing, extracting processing tracks of the processing tasks corresponding to all axes, dividing the processing tracks into a plurality of sub-paths, acquiring key points in the sub-paths, and acquiring feeding speeds of the key points;
generating a path sequence of a theoretical machining path based on the machining path of each shaft and the feeding speed of the key point, acquiring the actual position and the actual speed of each shaft of the multi-shaft machine tool at the key point, and generating a path sequence of an actual machining path;
and judging the DTW distance between the path sequence of the theoretical machining path and the path sequence of the actual machining path of each shaft, acquiring error distribution of each shaft according to the DTW distance, and acquiring machining error information of each shaft according to the error distribution.
4. The state monitoring method of multi-axis linkage numerical control machining according to claim 1, wherein the machining error information and twin data are subjected to data fusion to generate working condition data, the working condition data are subjected to feature extraction, and working condition features of a current time step are obtained, specifically:
acquiring a mean square error in a preset time through historical monitoring data of multi-source monitoring data, acquiring a total mean square error according to the mean square error of each monitoring data, and acquiring a weighting weight of each monitoring data according to the principle that the total mean square error is minimum;
the multi-source monitoring data are subjected to data fusion by the weighting weights and imported into a digital twin model to generate twin data, a data tag of the twin data is set according to basic information of each shaft, the twin data of each shaft are matched with corresponding processing error information and then subjected to data fusion, and working condition data of each shaft are obtained, wherein the basic information is a shaft body attribute and a shaft body number;
the working condition data sequences of all the shafts in the preset time are imported into a convolutional neural network for feature extraction, the working condition data sequences are divided by utilizing a sliding window, and the working condition data sequences are divided into subsequences with preset lengths after one-dimensional convolution processing, and normalization processing is carried out;
Encoding the normalized subsequence by a multi-head attention mechanism, and obtaining weighted attention results as output results by applying a self-attention mechanism to each head in the multi-head attention mechanism;
and performing matrix splicing on a plurality of output results obtained by the multi-head attention mechanism, projecting the output results to the length identical to the length of the working condition data sequence, and obtaining the working condition characteristics of the current time step after data decoding.
5. The state monitoring method for multi-axis linkage numerical control machining according to claim 1, wherein the state identification model for multi-axis numerical control machining is constructed based on a graph convolution neural network, specifically comprising:
acquiring historical fault information of a multi-axis machine tool in multi-axis linkage numerical control machining, reading a preset number of fault categories, simulating working condition characteristics corresponding to each fault category through a digital twin body model, and carrying out characteristic coding on the working condition characteristics by utilizing a sub-encoder to construct a characteristic space;
clustering the coded features in the feature space by using K-means clustering to generate a clustering center, constructing a loss function by using a clustering error in the clustering process and a feature reconstruction error of feature coding, and training until the loss function converges;
Outputting cluster centers, wherein the cluster centers correspond to fault categories, judging Euclidean distances between each cluster center and other cluster centers, sequencing the other cluster centers according to the Euclidean distances, presetting a distance threshold, and acquiring other cluster centers smaller than the preset distance threshold for connection;
and constructing a fault diagram of the multi-axis machine tool, learning and representing the fault diagram through a diagram convolution neural network, establishing a state identification model, acquiring a feature vector corresponding to the working condition feature of the current step length, and carrying out state and fault identification judgment.
6. The state monitoring method for multi-axis linkage numerical control machining according to claim 5, wherein a state identification model is established, a feature vector corresponding to the working condition feature of the current step length is obtained, and the state and fault identification and judgment are performed, specifically:
leading the working condition characteristics of the current step length into a state identification model, obtaining a corresponding graph structure, and obtaining initial vector representations corresponding to the working condition characteristics through graph convolution;
acquiring a neighbor matrix of a working condition characteristic corresponding graph structure, introducing a graph attention mechanism, setting attention weights for corresponding neighbor nodes in the neighbor matrix, and updating vector representations of the characteristics by using the attention weights through a neighbor aggregation mechanism;
And setting two graph roll layers, one graph attention layer and two full-connection layers in the state identification model to obtain an aggregated feature vector, and importing the feature vector into the full-connection layers to reduce the dimension and classify the nodes to obtain the identification classification results of states and faults.
7. A state monitoring system of multi-axis linkage numerical control machining is characterized in that the system comprises: the system comprises a memory and a processor, wherein the memory comprises a state monitoring method program of multi-axis linkage numerical control machining, and the state monitoring method program of the multi-axis linkage numerical control machining is executed by the processor to realize the following steps:
acquiring a three-dimensional model corresponding to a physical entity of a multi-axis machine tool in multi-axis numerical control machining, collecting operation data and multi-source monitoring data of the multi-axis machine tool, establishing data mapping with the three-dimensional model, and constructing a digital twin model of the multi-axis numerical control machining;
obtaining twin data according to the digital twin model, obtaining a processing task of current multi-axis combined numerical control processing, obtaining theoretical processing tracks of all axes through the processing task, and judging processing error information based on the theoretical processing tracks and the actual processing tracks;
performing data fusion on the processing error information and the twin data to generate working condition data, and performing feature extraction on the working condition data to obtain working condition features of the current time step;
And constructing a state identification model of multi-axis numerical control machining based on the graph convolution neural network, taking the working condition characteristics as the input of the state identification model, and identifying and judging faults of the machining state corresponding to the current time step.
8. The state monitoring system for multi-axis linkage numerical control machining according to claim 7, wherein the state recognition model for multi-axis numerical control machining is constructed based on a graph convolution neural network, specifically comprising:
acquiring historical fault information of a multi-axis machine tool in multi-axis linkage numerical control machining, reading a preset number of fault categories, simulating working condition characteristics corresponding to each fault category through a digital twin body model, and carrying out characteristic coding on the working condition characteristics by utilizing a sub-encoder to construct a characteristic space;
clustering the coded features in the feature space by using K-means clustering, and constructing a fault diagram of the multi-axis machine tool;
and establishing a state identification model through the graph convolution neural network, acquiring a feature vector corresponding to the working condition feature of the current step length, and carrying out state and fault identification judgment.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310596232.7A CN116300691B (en) | 2023-05-25 | 2023-05-25 | State monitoring method and system for multi-axis linkage numerical control machining |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310596232.7A CN116300691B (en) | 2023-05-25 | 2023-05-25 | State monitoring method and system for multi-axis linkage numerical control machining |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116300691A true CN116300691A (en) | 2023-06-23 |
CN116300691B CN116300691B (en) | 2023-08-04 |
Family
ID=86785512
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310596232.7A Active CN116300691B (en) | 2023-05-25 | 2023-05-25 | State monitoring method and system for multi-axis linkage numerical control machining |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116300691B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116520769A (en) * | 2023-07-05 | 2023-08-01 | 中科航迈数控软件(深圳)有限公司 | Monitoring method and device of numerical control machine tool, terminal equipment and computer storage medium |
CN116776289A (en) * | 2023-08-25 | 2023-09-19 | 中科航迈数控软件(深圳)有限公司 | Numerical control machine tool processing method, device, electronic equipment and readable storage medium |
CN116880341A (en) * | 2023-09-07 | 2023-10-13 | 上海泛腾电子科技有限公司 | High-precision motion control system based on industrial Ethernet bus |
CN117021118A (en) * | 2023-10-08 | 2023-11-10 | 中北大学 | Dynamic compensation method for digital twin track error of parallel robot |
CN117047556A (en) * | 2023-10-13 | 2023-11-14 | 南通百盛精密机械有限责任公司 | Optimized machining control method and system of numerical control machine tool |
CN117131425A (en) * | 2023-10-25 | 2023-11-28 | 广东德力宏展智能装备有限公司 | Numerical control machine tool processing state monitoring method and system based on feedback data |
CN117669384A (en) * | 2023-12-28 | 2024-03-08 | 深圳市敏创电子有限公司 | Intelligent monitoring method and system for temperature sensor production based on Internet of things |
CN117788203A (en) * | 2024-02-28 | 2024-03-29 | 西安华联电力电缆有限公司 | Improved high-efficiency production and preparation method of crosslinked polyethylene insulated power cable |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101315553A (en) * | 2008-07-04 | 2008-12-03 | 上海西马特机械制造有限公司 | Numerical control machine based on PC machine operation |
CN107748539A (en) * | 2017-09-25 | 2018-03-02 | 电子科技大学 | The multi-shaft interlocked Error Tracing & method of five-axis machine tool based on the identification of RTCP error characters |
CN108445838A (en) * | 2018-04-28 | 2018-08-24 | 华中科技大学 | A kind of numerically-controlled machine tool processing quality analysis method, grader and equipment |
JP2019197333A (en) * | 2018-05-08 | 2019-11-14 | 株式会社Ihi | Path correction method and control device of multiple spindle processing machine |
CN110865607A (en) * | 2019-11-07 | 2020-03-06 | 天津大学 | Five-axis numerical control machine tool control method based on digital twinning |
CN114037079A (en) * | 2021-11-25 | 2022-02-11 | 江苏科技大学 | Cylinder cover multi-fault integral diagnosis method based on graph neural network and knowledge graph |
CN115185234A (en) * | 2022-09-09 | 2022-10-14 | 中科航迈数控软件(深圳)有限公司 | Adaptive fault monitoring method and system for numerical control machine tool |
CN115328068A (en) * | 2022-09-22 | 2022-11-11 | 苏州君翔同创科技有限公司 | Digital twinning system applied to industrial production |
-
2023
- 2023-05-25 CN CN202310596232.7A patent/CN116300691B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101315553A (en) * | 2008-07-04 | 2008-12-03 | 上海西马特机械制造有限公司 | Numerical control machine based on PC machine operation |
CN107748539A (en) * | 2017-09-25 | 2018-03-02 | 电子科技大学 | The multi-shaft interlocked Error Tracing & method of five-axis machine tool based on the identification of RTCP error characters |
CN108445838A (en) * | 2018-04-28 | 2018-08-24 | 华中科技大学 | A kind of numerically-controlled machine tool processing quality analysis method, grader and equipment |
JP2019197333A (en) * | 2018-05-08 | 2019-11-14 | 株式会社Ihi | Path correction method and control device of multiple spindle processing machine |
CN110865607A (en) * | 2019-11-07 | 2020-03-06 | 天津大学 | Five-axis numerical control machine tool control method based on digital twinning |
CN114037079A (en) * | 2021-11-25 | 2022-02-11 | 江苏科技大学 | Cylinder cover multi-fault integral diagnosis method based on graph neural network and knowledge graph |
CN115185234A (en) * | 2022-09-09 | 2022-10-14 | 中科航迈数控软件(深圳)有限公司 | Adaptive fault monitoring method and system for numerical control machine tool |
CN115328068A (en) * | 2022-09-22 | 2022-11-11 | 苏州君翔同创科技有限公司 | Digital twinning system applied to industrial production |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116520769B (en) * | 2023-07-05 | 2023-09-15 | 中科航迈数控软件(深圳)有限公司 | Monitoring method and device of numerical control machine tool, terminal equipment and computer storage medium |
CN116520769A (en) * | 2023-07-05 | 2023-08-01 | 中科航迈数控软件(深圳)有限公司 | Monitoring method and device of numerical control machine tool, terminal equipment and computer storage medium |
CN116776289B (en) * | 2023-08-25 | 2023-11-17 | 中科航迈数控软件(深圳)有限公司 | Numerical control machine tool processing method, device, electronic equipment and readable storage medium |
CN116776289A (en) * | 2023-08-25 | 2023-09-19 | 中科航迈数控软件(深圳)有限公司 | Numerical control machine tool processing method, device, electronic equipment and readable storage medium |
CN116880341A (en) * | 2023-09-07 | 2023-10-13 | 上海泛腾电子科技有限公司 | High-precision motion control system based on industrial Ethernet bus |
CN116880341B (en) * | 2023-09-07 | 2023-12-05 | 上海泛腾半导体技术有限公司 | High-precision motion control system based on industrial Ethernet bus |
CN117021118A (en) * | 2023-10-08 | 2023-11-10 | 中北大学 | Dynamic compensation method for digital twin track error of parallel robot |
CN117021118B (en) * | 2023-10-08 | 2023-12-15 | 中北大学 | Dynamic compensation method for digital twin track error of parallel robot |
CN117047556A (en) * | 2023-10-13 | 2023-11-14 | 南通百盛精密机械有限责任公司 | Optimized machining control method and system of numerical control machine tool |
CN117047556B (en) * | 2023-10-13 | 2023-12-08 | 南通百盛精密机械有限责任公司 | Optimized machining control method and system of numerical control machine tool |
CN117131425A (en) * | 2023-10-25 | 2023-11-28 | 广东德力宏展智能装备有限公司 | Numerical control machine tool processing state monitoring method and system based on feedback data |
CN117131425B (en) * | 2023-10-25 | 2024-02-27 | 广东德力宏展智能装备有限公司 | Numerical control machine tool processing state monitoring method and system based on feedback data |
CN117669384A (en) * | 2023-12-28 | 2024-03-08 | 深圳市敏创电子有限公司 | Intelligent monitoring method and system for temperature sensor production based on Internet of things |
CN117788203A (en) * | 2024-02-28 | 2024-03-29 | 西安华联电力电缆有限公司 | Improved high-efficiency production and preparation method of crosslinked polyethylene insulated power cable |
CN117788203B (en) * | 2024-02-28 | 2024-05-10 | 西安华联电力电缆有限公司 | Improved high-efficiency production and preparation method of crosslinked polyethylene insulated power cable |
Also Published As
Publication number | Publication date |
---|---|
CN116300691B (en) | 2023-08-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116300691B (en) | State monitoring method and system for multi-axis linkage numerical control machining | |
CN115857447B (en) | Digital twinning-based complex industrial system operation monitoring method and system | |
CN108427720A (en) | System log sorting technique | |
CN113569903A (en) | Method, system, equipment, medium and terminal for predicting abrasion of numerical control machine tool cutter | |
CN112257263B (en) | Equipment residual life prediction system based on self-attention mechanism | |
CN113485863B (en) | Method for generating heterogeneous imbalance fault samples based on improved generation of countermeasure network | |
CN109871002B (en) | Concurrent abnormal state identification and positioning system based on tensor label learning | |
CN115524002B (en) | Operation state early warning method, system and storage medium of power plant rotating equipment | |
CN115099321B (en) | Bidirectional autoregressive non-supervision pretraining fine-tuning type pollution discharge abnormality monitoring method and application | |
CN115169430A (en) | Cloud network end resource multidimensional time sequence anomaly detection method based on multi-scale decoding | |
CN116340796A (en) | Time sequence data analysis method, device, equipment and storage medium | |
CN115859777A (en) | Method for predicting service life of product system in multiple fault modes | |
CN117124138A (en) | Automatic processing system and method for mold parts | |
CN117172753A (en) | Intelligent hydropower station inspection system and method based on mobile internet | |
CN116776270A (en) | Method and system for detecting micro-service performance abnormality based on transducer | |
CN117131425B (en) | Numerical control machine tool processing state monitoring method and system based on feedback data | |
CN113469247B (en) | Network asset abnormity detection method | |
Bai et al. | GAN-based bearing fault diagnosis method for short and imbalanced vibration signal | |
CN114626426A (en) | Industrial equipment behavior detection method based on K-means optimization algorithm | |
CN117251788A (en) | State evaluation method, device, terminal equipment and storage medium | |
CN114356743B (en) | Abnormal event automatic detection method and system based on sequence reconstruction | |
CN113706465B (en) | Pen defect detection method based on deep learning, computing equipment and storage medium | |
CN118503884B (en) | Equipment state identification method, equipment and medium | |
CN116125922B (en) | Complex industrial process monitoring method and system based on parallel dictionary learning | |
CN118053218A (en) | Method, device and system for detecting computer board card |
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 |