CN117697464A - Control method and system of high-precision numerical control machine tool - Google Patents
Control method and system of high-precision numerical control machine tool Download PDFInfo
- Publication number
- CN117697464A CN117697464A CN202410005560.XA CN202410005560A CN117697464A CN 117697464 A CN117697464 A CN 117697464A CN 202410005560 A CN202410005560 A CN 202410005560A CN 117697464 A CN117697464 A CN 117697464A
- Authority
- CN
- China
- Prior art keywords
- data
- real
- machine tool
- data acquisition
- numerical control
- 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
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000002159 abnormal effect Effects 0.000 claims abstract description 50
- 230000001105 regulatory effect Effects 0.000 claims abstract description 18
- 238000004519 manufacturing process Methods 0.000 claims abstract description 11
- 238000003064 k means clustering Methods 0.000 claims abstract description 10
- 230000001276 controlling effect Effects 0.000 claims abstract description 8
- 238000012549 training Methods 0.000 claims abstract description 6
- 238000012545 processing Methods 0.000 claims description 34
- 239000011159 matrix material Substances 0.000 claims description 26
- 238000010586 diagram Methods 0.000 claims description 14
- 230000005540 biological transmission Effects 0.000 claims description 11
- 238000009826 distribution Methods 0.000 claims description 9
- 238000005265 energy consumption Methods 0.000 claims description 9
- 238000009499 grossing Methods 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 6
- 230000033001 locomotion Effects 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 3
- 238000001816 cooling Methods 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 230000001050 lubricating effect Effects 0.000 claims description 2
- 238000003754 machining Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 8
- 238000003860 storage Methods 0.000 description 8
- 238000005299 abrasion Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 206010033799 Paralysis Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000000110 cooling liquid Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005461 lubrication Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000009022 nonlinear effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Numerical Control (AREA)
Abstract
The invention relates to the technical field of numerically-controlled machine tools, in particular to a control method and a control system of a high-precision numerically-controlled machine tool, wherein real-time data in a characteristic database are clustered through a K-means clustering algorithm, and a clustering result is corrected based on a contour coefficient to obtain a plurality of cluster groups; acquiring historical characteristic data of each variable of the numerical control machine tool in a normal state and an abnormal state, constructing a state prediction model, and training the state prediction model according to the historical characteristic data to obtain a trained state prediction model; and importing real-time data corresponding to the plurality of cluster groups into the trained state prediction model for prediction to obtain a prediction result, generating corresponding regulation and control measures according to the prediction result, and regulating and controlling the numerical control machine tool based on the regulation and control measures. And each operation parameter of the numerical control machine tool can be regulated and controlled in time, so that the reliability and stability of the system are improved, and the manufacturing precision of products is effectively improved.
Description
Technical Field
The invention relates to the technical field of numerical control machine tools, in particular to a control method and a control system of a high-precision numerical control machine tool.
Background
With the development of economy and the progress of society, automatic processing and production have become necessary and development directions. Various numerical control machine tools are increasingly developed towards the characteristics of convenient use, space saving, cost reduction, safety, high efficiency, multiple functions of one machine, automatic production and the like. In the long-time operation of the numerical control machine, the accuracy of the system may be reduced due to the abrasion of parts, and in addition, the high-accuracy control of the machine may be negatively affected by the stray in the environment, such as vibration and temperature change. And high precision machine tools are often subject to some nonlinear effects, such as friction, bending, deformation, etc., which may introduce errors during movement, affecting the control accuracy of the machine tool. For a high-precision numerical control machine tool, the development of the running condition of a system is monitored and diagnosed in real time, the intelligent degree of the numerical control machine tool is low, potential problems can be found and corrected in time, the reliability and stability of the system can be improved, and the manufacturing precision of products can be improved.
Disclosure of Invention
The invention overcomes the defect of low intelligent degree of the existing numerical control machine tool and provides a control method and a control system of a high-precision numerical control machine tool.
The technical scheme adopted by the invention for achieving the purpose is as follows:
the invention discloses a high-precision numerical control machine tool system, which comprises:
the machine tool comprises a machine tool body, a machine tool body and a cooling device, wherein the machine tool body comprises a machine tool body, a base, a lubricating part and a chip removing part;
the transmission system comprises a main shaft, a variable box, a guide rail, a sliding table and a servo motor;
the control system comprises a numerical control device, a controller, an interpolator, input equipment and a communication interface;
the data acquisition system comprises a sensor arranged at a preset position in the numerical control machine tool and an industrial camera;
a data processing system including a data receiver, a data processor, and a data memory.
The invention also discloses a control method of the high-precision numerical control machine tool system, which is applied to the high-precision numerical control machine tool system and comprises the following steps:
s102: acquiring position node information of a data acquisition system and a data processing system, and initializing a plurality of data acquisition position nodes and data receiving position nodes according to the position node information of the data acquisition system and the data processing system; planning according to a plurality of data acquisition position nodes and data receiving position nodes to obtain an optimal wireless data acquisition network;
S104: collecting real-time data in each sensor at a preset time point, importing the collected real-time data into a database, performing anomaly detection processing to obtain processed real-time data, and generating a characteristic database;
s106: clustering real-time data in a characteristic database by a K-means clustering algorithm, and correcting a clustering result based on a contour coefficient to obtain a plurality of cluster groups;
s108: acquiring historical characteristic data of each variable of the numerical control machine tool in a normal state and an abnormal state, constructing a state prediction model, and training the state prediction model according to the historical characteristic data to obtain a trained state prediction model;
s110: and importing real-time data corresponding to the plurality of cluster groups into the trained state prediction model for prediction to obtain a prediction result, generating corresponding regulation and control measures according to the prediction result, and regulating and controlling the numerical control machine tool based on the regulation and control measures.
Further, in a preferred embodiment of the present invention, position node information of the data acquisition system and the data processing system is obtained, and a plurality of data acquisition position nodes and data receiving position nodes are initialized according to the position node information of the data acquisition system and the data processing system; the optimal wireless data acquisition network is obtained according to planning of a plurality of data acquisition position nodes and data receiving position nodes, specifically:
Acquiring engineering drawing information of a numerical control machine tool, constructing a three-dimensional model diagram of the numerical control machine tool according to the engineering drawing information, acquiring position nodes of all sensors in a data acquisition system according to the three-dimensional model diagram, and acquiring position nodes of a data receiver in a data processing system;
constructing a virtual grid space, importing a three-dimensional model diagram of a numerical control machine tool into the virtual grid space, initializing a plurality of data acquisition position nodes in the virtual grid space according to position nodes of each sensor, and initializing data receiving position nodes according to position nodes of a data receiver;
planning and obtaining a plurality of wireless data acquisition paths between each data acquisition position node and each data receiving position node in the virtual grid space according to the plurality of data acquisition position nodes and the data receiving position nodes by combining a ray tracing method;
calculating the transmission energy consumption value of each wireless data acquisition path between each data acquisition position node and each data receiving position node, screening out the wireless data acquisition paths with the transmission energy consumption value larger than a preset energy consumption value to obtain residual wireless data acquisition paths, and outputting the residual wireless data acquisition paths between each data acquisition position node and each data receiving position node;
Calculating the path distance value of the residual wireless data acquisition path between each data acquisition position node and each data receiving position node, and sorting the path distance values of the residual wireless data acquisition paths to obtain the residual wireless data acquisition path with the shortest path distance value;
and converging the residual wireless data acquisition paths of the shortest path distance value between each data acquisition position node and each data receiving position node, generating an optimal wireless data acquisition network, and outputting the optimal wireless data acquisition network.
Further, in a preferred embodiment of the present invention, real-time data in each sensor is collected at a preset time point, and the collected real-time data is imported into a database and is subjected to anomaly detection processing, so as to obtain processed real-time data, and a characteristic database is generated, specifically:
acquiring various standard data to be acquired in each sensor, and extracting the characteristics of each standard data to obtain standard characteristic information corresponding to each standard data;
acquiring real-time data in each sensor at a preset time point, and transmitting the real-time data in each sensor to a data receiver based on the optimal wireless data acquisition network;
Constructing a database, and importing real-time data received by a data receiver into the database; extracting the characteristics of each real-time data in the database to obtain the actual characteristic information corresponding to each real-time data;
calculating hash values between actual characteristic information corresponding to each real-time data and standard characteristic information corresponding to each standard data in a database through a local sensitive hash algorithm;
sorting hash values between actual characteristic information corresponding to each real-time data and standard characteristic information corresponding to each standard data, and extracting the maximum hash value of each real-time data;
if the maximum hash value of a certain real-time data is not greater than the preset hash value, screening the real-time data from the database; and updating the residual real-time data in the database to obtain a characteristic database.
Further, in a preferred embodiment of the present invention, the real-time data in the characteristic database is clustered by a K-means clustering algorithm, and the clustering result is corrected based on the contour coefficient to obtain a plurality of cluster groups, which specifically includes:
s202: initializing a plurality of clustering centers according to various standard data required to be acquired in each sensor, introducing a Euclidean distance algorithm, and calculating Euclidean distances between each real-time data in the characteristic database and each clustering center through the Euclidean distance algorithm;
S204: sorting the Euclidean distance between each real-time data and each cluster center to obtain a sorting result, and distributing each real-time data into the cluster center with the minimum Euclidean distance according to the sorting result; after distribution is finished, updating real-time data existing in each cluster center to obtain a plurality of cluster groups;
s206: calculating the contour coefficient of each cluster group, and presetting a contour coefficient threshold range; comparing the contour coefficients of each cluster group with a preset contour coefficient threshold range;
s208: if the contour coefficient of a certain cluster group is within the preset contour coefficient threshold range, directly outputting the cluster group;
s210: if the contour coefficient of a certain class cluster group is not in the preset contour coefficient threshold range, marking the class cluster group with the contour coefficient not in the preset contour coefficient threshold range as an abnormal class cluster group; calculating Euclidean distances between all real-time data in the abnormal cluster group and the clustering centers of the abnormal cluster group, and screening out real-time data corresponding to the maximum Euclidean distance between the clustering centers of the abnormal cluster group;
s212: recalculating the contour coefficient of the abnormal cluster group, and repeating the step S210 if the contour coefficient of the abnormal cluster group is still not in the preset contour coefficient threshold range; and converting the abnormal cluster group into a normal cluster group and outputting the cluster group until the profile coefficient of the abnormal cluster group is within a preset profile coefficient threshold range.
Further, in a preferred embodiment of the present invention, historical characteristic data of each variable of the numerical control machine tool in a normal state and an abnormal state is obtained, a state prediction model is constructed, and the state prediction model is trained according to the historical characteristic data, so as to obtain a trained state prediction model, which specifically includes:
determining variables of all sub-components in each system of the numerical control machine tool to be monitored, constructing a Bayesian network according to the variables, wherein nodes of the Bayesian network represent the variables, and edges represent the dependency relationship among the variables; wherein the variables include temperature, vibration, current, voltage, shaft movement speed, shaft runout, and thermal deformation;
acquiring variable corresponding historical characteristic data of each sub-component in each system of the numerical control machine tool in a normal state and an abnormal state, defining conditional probability among nodes based on the variable corresponding historical characteristic data of each sub-component in each system of the numerical control machine tool in the normal state and the abnormal state, and constructing a conditional probability matrix according to the conditional probability among the nodes;
retrieving elements in the conditional probability matrix one by one, judging whether zero elements exist in the conditional probability matrix, if so, smoothing the zero elements in the conditional probability matrix based on a Laplacian smoothing method to obtain smoothed probabilities, and replacing the smoothed probabilities with the zero elements in the conditional probability matrix to obtain a processed conditional probability matrix;
The method comprises the steps of constructing a state prediction model, importing a processed conditional probability matrix into the state prediction model, carrying out structural learning on the state prediction model based on a deep learning algorithm by combining the processed conditional probability matrix, and outputting a trained state prediction model after parameters of the state prediction model meet preset requirements.
Further, in a preferred embodiment of the present invention, real-time data corresponding to a plurality of cluster groups is imported into the trained state prediction model to predict, so as to obtain a prediction result, and corresponding regulation measures are generated according to the prediction result, and the numerical control machine tool is regulated based on the regulation measures, specifically:
the real-time data corresponding to the plurality of cluster groups are imported into the trained state prediction model, so that the current running state of the numerical control machine tool is predicted through the trained state prediction model, and a prediction result is obtained;
acquiring the fault probability of each sub-component in the numerical control machine based on the prediction result, and comparing the fault probability of each sub-component with a preset fault probability one by one;
if the fault probability of a certain sub-component is larger than the preset fault probability, acquiring the fault type information of the sub-component, and judging whether the fault type information of the sub-component is the preset fault type or not;
If yes, the numerical control machine tool is controlled to stop production based on the control system, the position information of the sub-component is obtained, an early warning report is generated based on the fault type information and the position information of the sub-component, and the early warning report is transmitted to a preset platform for display;
if not, the large data network is searched based on the fault type information of the sub-component to obtain a corresponding regulation scheme, and the corresponding regulation scheme is sent to a control system to regulate and control the parameters of the corresponding sub-component in the numerical control machine tool through the control system.
The invention solves the technical defects existing in the background technology, and has the following beneficial effects: clustering real-time data in a characteristic database by a K-means clustering algorithm, and correcting a clustering result based on a contour coefficient to obtain a plurality of cluster groups; acquiring historical characteristic data of each variable of the numerical control machine tool in a normal state and an abnormal state, constructing a state prediction model, and training the state prediction model according to the historical characteristic data to obtain a trained state prediction model; and importing real-time data corresponding to the plurality of cluster groups into the trained state prediction model for prediction to obtain a prediction result, generating corresponding regulation and control measures according to the prediction result, and regulating and controlling the numerical control machine tool based on the regulation and control measures. By monitoring and diagnosing the running condition of the numerical control machine in real time, potential problems are corrected in time according to the running condition of the numerical control machine, and various running parameters of the numerical control machine are regulated and controlled in time, so that the reliability and stability of a system are improved, and the manufacturing precision of products is effectively improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other embodiments of the drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of the overall structure of the numerical control machine;
FIG. 2 is a block diagram of the system in the numerical control machine;
FIG. 3 is a first method flow chart of the present numerical control machine tool control method;
fig. 4 is a second method flowchart of the control method of the numerical control machine.
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.
As shown in fig. 1 and 2, the present invention discloses a high-precision numerically-controlled machine tool system, which includes:
a machine tool body 10 including a bed, a base, a lubrication and chip removal part, and a heat radiation part;
the transmission system 20 comprises a main shaft, a variable box, a guide rail, a sliding table and a servo motor;
a control system 30 including a numerical control device, a controller, an interpolator, an input device, and a communication interface;
the data acquisition system 40 comprises a sensor and an industrial camera which are arranged at preset positions in the numerical control machine tool;
a data processing system 50 including a data receiver, a data processor and a data memory.
The bed table is fixed to one side of the bed, and the position is set while securing a safe distance between both sides on the one side. The guide rail is fixed behind the machine tool table and is placed in a stepped form. The motor is fixed at a corresponding position in the saddle and is connected with the lathe bed, the saddle is used as a part for bearing the trolley body and the main shaft box, a more stable casting process and design are needed, and the high stability and high precision of the lathe are ensured while the high-speed work is ensured. The tool magazine placement position and the motor are positioned at the same level. Under the condition of electrifying, after a command is sent to a machine tool system, a guide rail is used as an auxiliary and guiding function, and a motor can drive a gear to rotate, so that the machine tool can rapidly and accurately process a target. The numerical control machine tool has small occupied area and lighter overall weight; the machining surface of the workbench, the guide rail surface and the rack surface are subjected to finish machining, so that the machine tool has high machining precision; the advantages of high overlap ratio and good meshing performance of the helical gear and the rack are utilized, so that the working efficiency of the machine tool can be improved while the machine tool is high in precision; the matching between the transmission parts enables the machine tool to almost reach zero noise in the whole processing process; the design of the bottom of the lathe bed ensures that the lathe can timely dissipate heat during operation, thereby prolonging the service life of the lathe bed.
As shown in fig. 3, another aspect of the present invention discloses a control method of a high-precision numerically-controlled machine tool system, which is applied to the high-precision numerically-controlled machine tool system, and includes the following steps:
s102: acquiring position node information of a data acquisition system and a data processing system, and initializing a plurality of data acquisition position nodes and data receiving position nodes according to the position node information of the data acquisition system and the data processing system; planning according to a plurality of data acquisition position nodes and data receiving position nodes to obtain an optimal wireless data acquisition network;
s104: collecting real-time data in each sensor at a preset time point, importing the collected real-time data into a database, performing anomaly detection processing to obtain processed real-time data, and generating a characteristic database;
s106: clustering real-time data in a characteristic database by a K-means clustering algorithm, and correcting a clustering result based on a contour coefficient to obtain a plurality of cluster groups;
s108: acquiring historical characteristic data of each variable of the numerical control machine tool in a normal state and an abnormal state, constructing a state prediction model, and training the state prediction model according to the historical characteristic data to obtain a trained state prediction model;
S110: and importing real-time data corresponding to the plurality of cluster groups into the trained state prediction model for prediction to obtain a prediction result, generating corresponding regulation and control measures according to the prediction result, and regulating and controlling the numerical control machine tool based on the regulation and control measures.
Further, in a preferred embodiment of the present invention, position node information of the data acquisition system and the data processing system is obtained, and a plurality of data acquisition position nodes and data receiving position nodes are initialized according to the position node information of the data acquisition system and the data processing system; the optimal wireless data acquisition network is obtained according to planning of a plurality of data acquisition position nodes and data receiving position nodes, specifically:
acquiring engineering drawing information of a numerical control machine tool, constructing a three-dimensional model diagram of the numerical control machine tool according to the engineering drawing information, acquiring position nodes of all sensors in a data acquisition system according to the three-dimensional model diagram, and acquiring position nodes of a data receiver in a data processing system;
constructing a virtual grid space, importing a three-dimensional model diagram of a numerical control machine tool into the virtual grid space, initializing a plurality of data acquisition position nodes in the virtual grid space according to position nodes of each sensor, and initializing data receiving position nodes according to position nodes of a data receiver;
Planning and obtaining a plurality of wireless data acquisition paths between each data acquisition position node and each data receiving position node in the virtual grid space according to the plurality of data acquisition position nodes and the data receiving position nodes by combining a ray tracing method;
calculating the transmission energy consumption value of each wireless data acquisition path between each data acquisition position node and each data receiving position node, screening out the wireless data acquisition paths with the transmission energy consumption value larger than a preset energy consumption value to obtain residual wireless data acquisition paths, and outputting the residual wireless data acquisition paths between each data acquisition position node and each data receiving position node;
calculating the path distance value of the residual wireless data acquisition path between each data acquisition position node and each data receiving position node, and sorting the path distance values of the residual wireless data acquisition paths to obtain the residual wireless data acquisition path with the shortest path distance value;
and converging the residual wireless data acquisition paths of the shortest path distance value between each data acquisition position node and each data receiving position node, generating an optimal wireless data acquisition network, and outputting the optimal wireless data acquisition network.
The sensor includes a temperature sensor, a current sensor, a voltage sensor, a speed sensor, an acceleration sensor, and the like. And according to engineering drawing information of the numerical control machine, combining with three-dimensional modeling software such as UG, solidWorks and the like to construct a three-dimensional model diagram of the numerical control machine. The basic idea of the ray tracing method is that the ray tracing method simulates the transmission of light rays from an observer (viewpoint), passes through objects in a scene and finally reaches a light source, so as to simulate the propagation path of a wireless signal, to evaluate algorithms of signal coverage, attenuation and multipath effect.
Further, in a preferred embodiment of the present invention, real-time data in each sensor is collected at a preset time point, and the collected real-time data is imported into a database and is subjected to anomaly detection processing, so as to obtain processed real-time data, and a characteristic database is generated, specifically:
Acquiring various standard data to be acquired in each sensor, and extracting the characteristics of each standard data to obtain standard characteristic information corresponding to each standard data;
acquiring real-time data in each sensor at a preset time point, and transmitting the real-time data in each sensor to a data receiver based on the optimal wireless data acquisition network;
constructing a database, and importing real-time data received by a data receiver into the database; extracting the characteristics of each real-time data in the database to obtain the actual characteristic information corresponding to each real-time data;
calculating hash values between actual characteristic information corresponding to each real-time data and standard characteristic information corresponding to each standard data in a database through a local sensitive hash algorithm;
sorting hash values between actual characteristic information corresponding to each real-time data and standard characteristic information corresponding to each standard data, and extracting the maximum hash value of each real-time data;
if the maximum hash value of a certain real-time data is not greater than the preset hash value, screening the real-time data from the database; and updating the residual real-time data in the database to obtain a characteristic database.
It should be noted that, by acquiring various standard data to be acquired in each sensor and extracting features of each standard data, standard feature information corresponding to each standard data is obtained, and feature information of the standard data to be acquired by different sensors is different, for example, features of current data and voltage data are different. After the real-time data in each sensor are collected at a plurality of preset time points, calculating the hash value between the actual characteristic information corresponding to each real-time data and the standard characteristic information corresponding to each standard data in the database through a local sensitive hash algorithm, and if the maximum hash value of one real-time data is not greater than the preset hash value, indicating that the data is invalid data, such as noise data, and the like, the real-time data needs to be screened out in the database. By the method, invalid data caused by the influence of the acquisition environment and the influence of the acquisition precision of the sensor can be rapidly screened out, so that the data reliability is improved, the data quality is improved, and the control precision is further improved.
As shown in fig. 4, in a further preferred embodiment of the present invention, the real-time data in the characteristic database is clustered by a K-means clustering algorithm, and the clustering result is modified based on the contour coefficient to obtain a plurality of cluster groups, specifically:
S202: initializing a plurality of clustering centers according to various standard data required to be acquired in each sensor, introducing a Euclidean distance algorithm, and calculating Euclidean distances between each real-time data in the characteristic database and each clustering center through the Euclidean distance algorithm;
s204: sorting the Euclidean distance between each real-time data and each cluster center to obtain a sorting result, and distributing each real-time data into the cluster center with the minimum Euclidean distance according to the sorting result; after distribution is finished, updating real-time data existing in each cluster center to obtain a plurality of cluster groups;
s206: calculating the contour coefficient of each cluster group, and presetting a contour coefficient threshold range; comparing the contour coefficients of each cluster group with a preset contour coefficient threshold range;
s208: if the contour coefficient of a certain cluster group is within the preset contour coefficient threshold range, directly outputting the cluster group;
s210: if the contour coefficient of a certain class cluster group is not in the preset contour coefficient threshold range, marking the class cluster group with the contour coefficient not in the preset contour coefficient threshold range as an abnormal class cluster group; calculating Euclidean distances between all real-time data in the abnormal cluster group and the clustering centers of the abnormal cluster group, and screening out real-time data corresponding to the maximum Euclidean distance between the clustering centers of the abnormal cluster group;
S212: recalculating the contour coefficient of the abnormal cluster group, and repeating the step S210 if the contour coefficient of the abnormal cluster group is still not in the preset contour coefficient threshold range; and converting the abnormal cluster group into a normal cluster group and outputting the cluster group until the profile coefficient of the abnormal cluster group is within a preset profile coefficient threshold range.
It should be noted that, when the real-time data acquired by each sensor is stored in the characteristic database, at this time, each real-time data is still disordered, at this time, the type of each data is not known in the system, for example, which is the current data, the voltage data, the rotation speed data and the like in the servo motor is not known, so that the state of the corresponding sub-component cannot be estimated according to the data of each sub-component in the numerically-controlled machine tool, therefore, in this step, the real-time data in the characteristic database is classified by the K-means clustering algorithm and the contour coefficient, so as to obtain a plurality of cluster groups, and the real-time data corresponding to different sub-components are obtained by classification. The contour coefficient is an index for evaluating the clustering result, can measure the compactness of the data points in the clusters and the separation degree of the data points from other clusters, and can evaluate and correct the K-means clustering result through the contour coefficient, so that the clustering effect and the robustness can be improved, and the clustering result is more reasonable and interpretable. The method can effectively improve the data clustering precision, avoid the occurrence of the phenomenon of clustering errors and improve the reliability.
Further, in a preferred embodiment of the present invention, historical characteristic data of each variable of the numerical control machine tool in a normal state and an abnormal state is obtained, a state prediction model is constructed, and the state prediction model is trained according to the historical characteristic data, so as to obtain a trained state prediction model, which specifically includes:
determining variables of all sub-components in each system of the numerical control machine tool to be monitored, constructing a Bayesian network according to the variables, wherein nodes of the Bayesian network represent the variables, and edges represent the dependency relationship among the variables; wherein the variables include temperature, vibration, current, voltage, shaft movement speed, shaft runout, and thermal deformation;
acquiring variable corresponding historical characteristic data of each sub-component in each system of the numerical control machine tool in a normal state and an abnormal state, defining conditional probability among nodes based on the variable corresponding historical characteristic data of each sub-component in each system of the numerical control machine tool in the normal state and the abnormal state, and constructing a conditional probability matrix according to the conditional probability among the nodes;
retrieving elements in the conditional probability matrix one by one, judging whether zero elements exist in the conditional probability matrix, if so, smoothing the zero elements in the conditional probability matrix based on a Laplacian smoothing method to obtain smoothed probabilities, and replacing the smoothed probabilities with the zero elements in the conditional probability matrix to obtain a processed conditional probability matrix;
The method comprises the steps of constructing a state prediction model, importing a processed conditional probability matrix into the state prediction model, carrying out structural learning on the state prediction model based on a deep learning algorithm by combining the processed conditional probability matrix, and outputting a trained state prediction model after parameters of the state prediction model meet preset requirements.
It should be noted that the bayesian network is a graph model, which is used to represent probability dependency relationships between variables, and may be used to infer probability distributions of unknown variables, and by determining variables of the operation data of the numerical control machine to be monitored, the variables may include temperature, vibration, current, axis motion speed, and the like, and the structure of the bayesian network is designed according to domain knowledge and data analysis. Nodes of the network represent variables and edges represent dependencies between variables. For example, temperature may be affected by current and environmental conditions. In numerically controlled machine tools, many factors may lead to uncertainty in the state, such as sensor noise, environmental changes, etc. Bayesian networks can efficiently handle these uncertainties, providing probabilistic inference of system state.
In practical applications, there are many combinations of events that occur rarely or not at all, which results in many zero elements in the conditional probability matrix, forming a sparse matrix, which may lead to inaccuracy in the model prediction results. The laplace smoothing method is a method for processing zero elements, and is particularly often used in probability estimation, and the purpose of the laplace smoothing method is to solve the problem that when a probability is calculated, the probability is zero because some events are not observed. The state prediction model of the numerical control machine tool constructed by combining the Bayesian network with the Laplace smoothing method has strong modeling and deducing capability, is suitable for processing uncertainty and relevance in a complex system, and is beneficial to improving the reliability of the system, thereby improving the regulation and control precision.
Further, in a preferred embodiment of the present invention, real-time data corresponding to a plurality of cluster groups is imported into the trained state prediction model to predict, so as to obtain a prediction result, and corresponding regulation measures are generated according to the prediction result, and the numerical control machine tool is regulated based on the regulation measures, specifically:
the real-time data corresponding to the plurality of cluster groups are imported into the trained state prediction model, so that the current running state of the numerical control machine tool is predicted through the trained state prediction model, and a prediction result is obtained;
acquiring the fault probability of each sub-component in the numerical control machine based on the prediction result, and comparing the fault probability of each sub-component with a preset fault probability one by one;
if the fault probability of a certain sub-component is larger than the preset fault probability, acquiring the fault type information of the sub-component, and judging whether the fault type information of the sub-component is the preset fault type or not;
if yes, the numerical control machine tool is controlled to stop production based on the control system, the position information of the sub-component is obtained, an early warning report is generated based on the fault type information and the position information of the sub-component, and the early warning report is transmitted to a preset platform for display;
If not, the large data network is searched based on the fault type information of the sub-component to obtain a corresponding regulation scheme, and the corresponding regulation scheme is sent to a control system to regulate and control the parameters of the corresponding sub-component in the numerical control machine tool through the control system.
It should be noted that the preset fault types include, but are not limited to, a main shaft jump fault, a serious abrasion of a guide rail, loosening of a screw, paralysis of a cooling system, and the like, which have a great influence on the quality of the product. If the fault type information of the sub-component is a preset fault type, the situation that the numerical control machine tool has serious faults in the working process is indicated, the risk coefficient is high, and the numerical control machine tool is controlled to stop production based on the control system, so that the safety is improved, and the phenomenon of producing a large number of defective products is avoided; and the position information of the sub-component is acquired, an early warning report is generated based on the fault type information and the position information of the sub-component, and the early warning report is transmitted to a preset platform for display, so that maintenance staff can be informed of the pointed maintenance of the sub-component, the maintenance efficiency can be effectively improved, the shutdown time is reduced, and the production efficiency is improved.
If the fault type information of the sub-component is not the preset fault type, although the numerical control machine tool has serious faults, the fault type of the machine tool is a slight fault, the product quality is not greatly affected, such as slight abrasion of a cutter, small-amplitude vibration or noise and the like, and the risk coefficient is low, if the fault occurs, a corresponding regulation scheme is searched through a big data network and is sent to a control system, so that parameters of the corresponding sub-component in the numerical control machine tool are regulated and controlled through the control system. If when the cutter is found to be slightly worn, the temperature of the cutter can be effectively reduced, the wear speed is slowed down, the service life of the cutter is prolonged, the machining precision of a product can be ensured, and intelligent control of the numerical control machine tool is realized by adjusting the flow of cooling liquid according to the wear condition of the cutter.
Furthermore, the method comprises the following steps:
acquiring real-time temperature information of a node of a preset position of a processing product of the numerical control machine tool in the processing process, and constructing a real-time temperature distribution diagram according to the real-time temperature information;
introducing a region growing algorithm, selecting one or more seed points in a real-time temperature distribution map, determining a region growing criterion, and adding the selected seed points into a queue according to the region growing criterion to serve as a starting point of growth;
taking out a seed point from the queue, checking whether the adjacent pixels meet the growth criterion, adding the adjacent pixels meeting the condition into the queue, marking the adjacent pixels as accessed, and repeating the process until the queue is empty;
selecting new seed points, repeating the growth process until the whole image is covered or a sufficient number of isotherms are extracted, and obtaining a real-time isotherm map;
calculating the coincidence ratio between the real-time isothermal line graph and a preset isothermal line graph through an Euclidean distance algorithm;
if the overlap ratio is larger than the preset overlap ratio, the machining working condition is normal, and the numerical control machine tool is not regulated; and if the contact ratio is not greater than the preset contact ratio, indicating that the machining working condition is abnormal, regulating and controlling the numerical control machine tool.
It should be noted that, the real-time temperature distribution map is divided by the region growing algorithm to form a relatively continuous isotherm so as to convert the temperature distribution map into a relatively simple and clear isotherm map, so that the calculation difficulty of the subsequent Euclidean distance algorithm is reduced, and the response speed of the system is improved. If the overlap ratio is larger than the preset overlap ratio, the machining working condition is normal, and the numerical control machine tool is not regulated. And if the contact ratio is not greater than the preset contact ratio, indicating that the machining working condition is abnormal, regulating and controlling the numerical control machine tool. The method can judge whether the processing working condition is normal according to the temperature distribution condition of the processed product in the processing process, and can timely formulate corresponding regulation and control measures to improve the production quality of the product.
Specifically, if the overlap ratio is not greater than the preset overlap ratio, indicating that the machining working condition is abnormal, regulating and controlling the numerical control machine tool, specifically comprising the following steps:
acquiring a historical abnormal isothermal diagram corresponding to abnormal conditions of various machining working conditions of the numerical control machine tool through a big data network, and acquiring a historical regulation and control scheme corresponding to the abnormal conditions of various machining working conditions;
sorting the regulation and control success rates of the history regulation and control schemes under abnormal conditions of various processing working conditions to obtain a history regulation and control scheme with the highest regulation and control success rate, and binding the history regulation and control scheme with the highest regulation and control success rate with a corresponding history abnormal isothermal map to obtain a plurality of paired data packets;
Constructing a pairing database, and importing a plurality of pairing data packets into the pairing database for storage;
if the coincidence ratio is not greater than the preset coincidence ratio, calculating the coincidence ratio between the real-time isothermal line graph and the historical abnormal isothermal line graph of each pairing data packet in each pairing database through a Euclidean distance algorithm to obtain a plurality of coincidence ratios;
sequencing the multiple coincidence rates, extracting the maximum coincidence rate, acquiring a historical abnormal isothermal line graph corresponding to the maximum coincidence rate, and extracting a corresponding historical regulation and control scheme according to a pairing data packet of the historical abnormal isothermal line graph corresponding to the maximum coincidence rate;
and sending the extracted corresponding historical regulation and control scheme to a control system so as to regulate and control the parameters of the numerical control machine tool through the control system according to the extracted corresponding historical regulation and control scheme.
If the machining working condition is abnormal, the corresponding regulation and control scheme is quickly matched through the method, the numerical control machine tool is regulated and controlled in time, a complex algorithm is not needed in the pairing process, the pairing efficiency is effectively improved, the regulation and control scheme is quickly obtained, the machine tool is regulated and controlled in time, and the reject ratio of products is reduced.
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 of 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 embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the technical scope of the present invention, and the invention should be covered. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (7)
1. A high precision numerically controlled machine tool system, comprising:
the machine tool comprises a machine tool body, a machine tool body and a cooling device, wherein the machine tool body comprises a machine tool body, a base, a lubricating part and a chip removing part;
the transmission system comprises a main shaft, a variable box, a guide rail, a sliding table and a servo motor;
the control system comprises a numerical control device, a controller, an interpolator, input equipment and a communication interface;
the data acquisition system comprises a sensor arranged at a preset position in the numerical control machine tool and an industrial camera;
a data processing system including a data receiver, a data processor, and a data memory.
2. A control method of a high-precision numerically-controlled machine tool system, characterized by being applied to the high-precision numerically-controlled machine tool system of claim 1, comprising the steps of:
S102: acquiring position node information of a data acquisition system and a data processing system, and initializing a plurality of data acquisition position nodes and data receiving position nodes according to the position node information of the data acquisition system and the data processing system; planning according to a plurality of data acquisition position nodes and data receiving position nodes to obtain an optimal wireless data acquisition network;
s104: collecting real-time data in each sensor at a preset time point, importing the collected real-time data into a database, performing anomaly detection processing to obtain processed real-time data, and generating a characteristic database;
s106: clustering real-time data in a characteristic database by a K-means clustering algorithm, and correcting a clustering result based on a contour coefficient to obtain a plurality of cluster groups;
s108: acquiring historical characteristic data of each variable of the numerical control machine tool in a normal state and an abnormal state, constructing a state prediction model, and training the state prediction model according to the historical characteristic data to obtain a trained state prediction model;
s110: and importing real-time data corresponding to the plurality of cluster groups into the trained state prediction model for prediction to obtain a prediction result, generating corresponding regulation and control measures according to the prediction result, and regulating and controlling the numerical control machine tool based on the regulation and control measures.
3. The control method of a high-precision numerical control machine system according to claim 2, wherein position node information of a data acquisition system and a data processing system is obtained, and a plurality of data acquisition position nodes and data receiving position nodes are initialized according to the position node information of the data acquisition system and the data processing system; the optimal wireless data acquisition network is obtained according to planning of a plurality of data acquisition position nodes and data receiving position nodes, specifically:
acquiring engineering drawing information of a numerical control machine tool, constructing a three-dimensional model diagram of the numerical control machine tool according to the engineering drawing information, acquiring position nodes of all sensors in a data acquisition system according to the three-dimensional model diagram, and acquiring position nodes of a data receiver in a data processing system;
constructing a virtual grid space, importing a three-dimensional model diagram of a numerical control machine tool into the virtual grid space, initializing a plurality of data acquisition position nodes in the virtual grid space according to position nodes of each sensor, and initializing data receiving position nodes according to position nodes of a data receiver;
planning and obtaining a plurality of wireless data acquisition paths between each data acquisition position node and each data receiving position node in the virtual grid space according to the plurality of data acquisition position nodes and the data receiving position nodes by combining a ray tracing method;
Calculating the transmission energy consumption value of each wireless data acquisition path between each data acquisition position node and each data receiving position node, screening out the wireless data acquisition paths with the transmission energy consumption value larger than a preset energy consumption value to obtain residual wireless data acquisition paths, and outputting the residual wireless data acquisition paths between each data acquisition position node and each data receiving position node;
calculating the path distance value of the residual wireless data acquisition path between each data acquisition position node and each data receiving position node, and sorting the path distance values of the residual wireless data acquisition paths to obtain the residual wireless data acquisition path with the shortest path distance value;
and converging the residual wireless data acquisition paths of the shortest path distance value between each data acquisition position node and each data receiving position node, generating an optimal wireless data acquisition network, and outputting the optimal wireless data acquisition network.
4. The control method of a high-precision numerically-controlled machine tool system according to claim 2, wherein real-time data in each sensor is collected at a preset time point, the collected real-time data is imported into a database and is subjected to anomaly detection processing, the processed real-time data is obtained, and a characteristic database is generated, specifically:
Acquiring various standard data to be acquired in each sensor, and extracting the characteristics of each standard data to obtain standard characteristic information corresponding to each standard data;
acquiring real-time data in each sensor at a preset time point, and transmitting the real-time data in each sensor to a data receiver based on the optimal wireless data acquisition network;
constructing a database, and importing real-time data received by a data receiver into the database; extracting the characteristics of each real-time data in the database to obtain the actual characteristic information corresponding to each real-time data;
calculating hash values between actual characteristic information corresponding to each real-time data and standard characteristic information corresponding to each standard data in a database through a local sensitive hash algorithm;
sorting hash values between actual characteristic information corresponding to each real-time data and standard characteristic information corresponding to each standard data, and extracting the maximum hash value of each real-time data;
if the maximum hash value of a certain real-time data is not greater than the preset hash value, screening the real-time data from the database; and updating the residual real-time data in the database to obtain a characteristic database.
5. The control method of the high-precision numerical control machine tool system according to claim 2, wherein the method is characterized in that the real-time data in the characteristic database is clustered by a K-means clustering algorithm, and the clustering result is corrected based on the contour coefficient to obtain a plurality of cluster groups, specifically:
s202: initializing a plurality of clustering centers according to various standard data required to be acquired in each sensor, introducing a Euclidean distance algorithm, and calculating Euclidean distances between each real-time data in the characteristic database and each clustering center through the Euclidean distance algorithm;
s204: sorting the Euclidean distance between each real-time data and each cluster center to obtain a sorting result, and distributing each real-time data into the cluster center with the minimum Euclidean distance according to the sorting result; after distribution is finished, updating real-time data existing in each cluster center to obtain a plurality of cluster groups;
s206: calculating the contour coefficient of each cluster group, and presetting a contour coefficient threshold range; comparing the contour coefficients of each cluster group with a preset contour coefficient threshold range;
s208: if the contour coefficient of a certain cluster group is within the preset contour coefficient threshold range, directly outputting the cluster group;
S210: if the contour coefficient of a certain class cluster group is not in the preset contour coefficient threshold range, marking the class cluster group with the contour coefficient not in the preset contour coefficient threshold range as an abnormal class cluster group; calculating Euclidean distances between all real-time data in the abnormal cluster group and the clustering centers of the abnormal cluster group, and screening out real-time data corresponding to the maximum Euclidean distance between the clustering centers of the abnormal cluster group;
s212: recalculating the contour coefficient of the abnormal cluster group, and repeating the step S210 if the contour coefficient of the abnormal cluster group is still not in the preset contour coefficient threshold range; and converting the abnormal cluster group into a normal cluster group and outputting the cluster group until the profile coefficient of the abnormal cluster group is within a preset profile coefficient threshold range.
6. The control method of a high-precision numerically-controlled machine tool system according to claim 2, wherein the method comprises the steps of obtaining historical characteristic data of variables of the numerically-controlled machine tool in a normal state and an abnormal state, constructing a state prediction model, and training the state prediction model according to the historical characteristic data to obtain a trained state prediction model, specifically comprising the following steps:
Determining variables of all sub-components in each system of the numerical control machine tool to be monitored, constructing a Bayesian network according to the variables, wherein nodes of the Bayesian network represent the variables, and edges represent the dependency relationship among the variables; wherein the variables include temperature, vibration, current, voltage, shaft movement speed, shaft runout, and thermal deformation;
acquiring variable corresponding historical characteristic data of each sub-component in each system of the numerical control machine tool in a normal state and an abnormal state, defining conditional probability among nodes based on the variable corresponding historical characteristic data of each sub-component in each system of the numerical control machine tool in the normal state and the abnormal state, and constructing a conditional probability matrix according to the conditional probability among the nodes;
retrieving elements in the conditional probability matrix one by one, judging whether zero elements exist in the conditional probability matrix, if so, smoothing the zero elements in the conditional probability matrix based on a Laplacian smoothing method to obtain smoothed probabilities, and replacing the smoothed probabilities with the zero elements in the conditional probability matrix to obtain a processed conditional probability matrix;
the method comprises the steps of constructing a state prediction model, importing a processed conditional probability matrix into the state prediction model, carrying out structural learning on the state prediction model based on a deep learning algorithm by combining the processed conditional probability matrix, and outputting a trained state prediction model after parameters of the state prediction model meet preset requirements.
7. The control method of the high-precision numerical control machine system according to claim 2, wherein real-time data corresponding to a plurality of cluster groups are imported into the trained state prediction model for prediction to obtain a prediction result, corresponding regulation measures are generated according to the prediction result, and the numerical control machine is regulated based on the regulation measures, specifically:
the real-time data corresponding to the plurality of cluster groups are imported into the trained state prediction model, so that the current running state of the numerical control machine tool is predicted through the trained state prediction model, and a prediction result is obtained;
acquiring the fault probability of each sub-component in the numerical control machine based on the prediction result, and comparing the fault probability of each sub-component with a preset fault probability one by one;
if the fault probability of a certain sub-component is larger than the preset fault probability, acquiring the fault type information of the sub-component, and judging whether the fault type information of the sub-component is the preset fault type or not;
if yes, the numerical control machine tool is controlled to stop production based on the control system, the position information of the sub-component is obtained, an early warning report is generated based on the fault type information and the position information of the sub-component, and the early warning report is transmitted to a preset platform for display;
If not, the large data network is searched based on the fault type information of the sub-component to obtain a corresponding regulation scheme, and the corresponding regulation scheme is sent to a control system to regulate and control the parameters of the corresponding sub-component in the numerical control machine tool through the control system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410005560.XA CN117697464A (en) | 2024-01-03 | 2024-01-03 | Control method and system of high-precision numerical control machine tool |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410005560.XA CN117697464A (en) | 2024-01-03 | 2024-01-03 | Control method and system of high-precision numerical control machine tool |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117697464A true CN117697464A (en) | 2024-03-15 |
Family
ID=90157104
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410005560.XA Pending CN117697464A (en) | 2024-01-03 | 2024-01-03 | Control method and system of high-precision numerical control machine tool |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117697464A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110347116A (en) * | 2019-07-17 | 2019-10-18 | 重庆大学 | A kind of conditions of machine tool monitoring system and monitoring method based on operation data stream |
| CN110428020A (en) * | 2019-08-13 | 2019-11-08 | 树根互联技术有限公司 | Cutter health evaluation model training method, device and electronic equipment |
| CN110647943A (en) * | 2019-09-26 | 2020-01-03 | 西北工业大学 | Cutting tool wear monitoring method based on evolutionary data cluster analysis |
| US20200026262A1 (en) * | 2018-07-18 | 2020-01-23 | Hitachi, Ltd. | Machine-tool-state determination system and machine-tool-state determination method |
| CN115641302A (en) * | 2022-09-30 | 2023-01-24 | 浙江大学 | Machine vision-based numerical control machine tool operation fault detection system and method |
| CN117116290A (en) * | 2023-08-03 | 2023-11-24 | 中科航迈数控软件(深圳)有限公司 | Method and related equipment for positioning defects of numerical control machine tool parts based on multidimensional characteristics |
| CN117182653A (en) * | 2023-09-07 | 2023-12-08 | 重庆大学 | Sense and calculate accuse integrated intelligent cutter system |
-
2024
- 2024-01-03 CN CN202410005560.XA patent/CN117697464A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200026262A1 (en) * | 2018-07-18 | 2020-01-23 | Hitachi, Ltd. | Machine-tool-state determination system and machine-tool-state determination method |
| CN110347116A (en) * | 2019-07-17 | 2019-10-18 | 重庆大学 | A kind of conditions of machine tool monitoring system and monitoring method based on operation data stream |
| CN110428020A (en) * | 2019-08-13 | 2019-11-08 | 树根互联技术有限公司 | Cutter health evaluation model training method, device and electronic equipment |
| CN110647943A (en) * | 2019-09-26 | 2020-01-03 | 西北工业大学 | Cutting tool wear monitoring method based on evolutionary data cluster analysis |
| CN115641302A (en) * | 2022-09-30 | 2023-01-24 | 浙江大学 | Machine vision-based numerical control machine tool operation fault detection system and method |
| CN117116290A (en) * | 2023-08-03 | 2023-11-24 | 中科航迈数控软件(深圳)有限公司 | Method and related equipment for positioning defects of numerical control machine tool parts based on multidimensional characteristics |
| CN117182653A (en) * | 2023-09-07 | 2023-12-08 | 重庆大学 | Sense and calculate accuse integrated intelligent cutter system |
Non-Patent Citations (5)
| Title |
|---|
| 刘献礼 等；: "双转台五轴数控机床主轴热误差测量与建模", 《哈尔滨理工大学学报》, vol. 24, no. 6, 31 December 2019 (2019-12-31) * |
| 周建民 等；: "基于非线性降维和模糊均值聚类的滚动轴承的性能退化在线评估方法", 《机械设计与研究》, vol. 33, no. 6, 20 December 2017 (2017-12-20) * |
| 张龙 等；: "基于Renyi熵和K-medoids聚类的轴承性能退化评估", 《振动与冲击》, vol. 39, no. 20, 27 October 2020 (2020-10-27) * |
| 杨岚 等；: "基于大数据的多工序产品质量预测", 《西南科技大学学报》, vol. 35, no. 1, 31 March 2020 (2020-03-31), pages 82 - 86 * |
| 高宏力 等；: "数控机床故障预测与健康管理系统关键技术", 《计算机集成制造系统》, vol. 16, no. 10, 15 October 2010 (2010-10-15) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115578015B (en) | Sewage treatment whole process supervision method, system and storage medium based on Internet of things | |
| CN113569903B (en) | Method, system, equipment, medium and terminal for predicting cutter abrasion of numerical control machine tool | |
| CN112085261B (en) | Enterprise production status diagnosis method based on cloud fusion and digital twin technology | |
| CN114237155B (en) | Error prediction and compensation method, system and medium for multi-axis numerical control machining | |
| KR101948604B1 (en) | Method and device for equipment health monitoring based on sensor clustering | |
| CN111774931A (en) | On-line monitoring method for abrasion of numerical control turning batch machining tools | |
| Liu et al. | Establishing a reliable mechanism model of the digital twin machining system: An adaptive evaluation network approach | |
| CN111881574B (en) | Wind turbine generator set key component reliability modeling method based on distribution function optimization | |
| KR20180131246A (en) | Method for production control system through processing mining | |
| CN114326593B (en) | Cutter life prediction system and method | |
| CN116757648B (en) | Production and manufacturing management system and method based on artificial intelligence | |
| CN110555058A (en) | Power communication equipment state prediction method based on improved decision tree | |
| CN117494072A (en) | Method and system for monitoring operation state of battery-changing cabinet based on data fusion | |
| CN114789364A (en) | Multi-index drilling quality control method, device and equipment | |
| CN117697464A (en) | Control method and system of high-precision numerical control machine tool | |
| CN111859039A (en) | Workshop disturbance decision method and device based on improved case reasoning technology | |
| Park et al. | Prediction of the CNC tool wear using the machine learning technique | |
| CN117555287B (en) | CAE-based numerical control machine tool machining dynamic performance monitoring method and system | |
| CN117311295B (en) | Production quality improving method and system based on wireless network equipment | |
| CN117370824B (en) | Intelligent monitoring method and system for air inlet state of air compressor | |
| CN112560234B (en) | Calculation method and device of residual life estimation probability of numerical control machine tool and network side server | |
| CN118093304A (en) | On-line monitoring method and system for screw machine locking | |
| CN117474710B (en) | Hollow glass whole-process informationized management system | |
| CN114881101B (en) | Bionic search-based power system typical scene association feature selection method | |
| CN116135421A (en) | Welding processing path optimization method and system based on artificial intelligence |
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 |