CN116010833A - Numerical control machine tool health state evaluation method and device based on missing data completion - Google Patents
Numerical control machine tool health state evaluation method and device based on missing data completion Download PDFInfo
- Publication number
- CN116010833A CN116010833A CN202310303801.4A CN202310303801A CN116010833A CN 116010833 A CN116010833 A CN 116010833A CN 202310303801 A CN202310303801 A CN 202310303801A CN 116010833 A CN116010833 A CN 116010833A
- Authority
- CN
- China
- Prior art keywords
- missing
- state information
- data
- machine tool
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- 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
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Numerical Control (AREA)
Abstract
The invention relates to the technical field of numerically-controlled machine tools, and provides a method and a device for evaluating the health state of a numerically-controlled machine tool based on missing data completion. The method comprises the following steps: acquiring the running state information of each mechanical part of the numerical control machine; determining to-be-processed missing data in the running state information based on the running state information, wherein the to-be-processed missing data is data of missing parts of the running state information in the signal transmission process; inputting the missing data to be processed into a pre-trained diffusion interpolation model to obtain filling data output by the diffusion interpolation model; inputting the filling data and the complete data into a health state evaluation model to obtain the health state of the numerical control machine tool output by the health state evaluation model; the signal transmission process is all links included in each transmission or processing node of the running state information after the running state information is acquired. The invention improves the accuracy of the health state evaluation of the numerical control machine tool.
Description
Technical Field
The invention relates to the technical field of numerically-controlled machine tools, in particular to a method and a device for evaluating the health state of a numerically-controlled machine tool based on missing data completion.
Background
Along with the development of science and technology, the application of automatic production equipment such as numerical control machine tools is also becoming wider and wider. As a key device in the cutting and manufacturing process of parts (especially metal parts), the operation condition of the numerical control machine tool has a great influence on the production process. Therefore, it is necessary to monitor the operation process of the numerical control machine, for example, to evaluate the state of the numerical control machine.
The existing machine tool state evaluation method is driven by sensor data, most of the machine tool state evaluation method has complete data in a multi-aspect mode, the machine manufacturing environment is complex, and the problems of signal jump, signal packet loss, transmission loss and the like often exist, so that the accuracy of the numerical control machine tool state evaluation is reduced.
Disclosure of Invention
The invention provides a method and a device for evaluating the health state of a numerical control machine based on missing data completion, which are used for solving the defect that the accuracy of evaluating the health state of the machine is low in the prior art and improving the accuracy of evaluating the health state of the numerical control machine.
The invention provides a numerical control machine tool health state assessment method based on missing data completion, which comprises the following steps:
acquiring the running state information of each mechanical part of the numerical control machine;
Determining to-be-processed missing data in the running state information based on the running state information, wherein the to-be-processed missing data is data of missing parts of each running state information in a signal transmission process;
inputting the missing data to be processed into a pre-trained diffusion interpolation model to obtain filling data output by the diffusion interpolation model, wherein the diffusion interpolation model is used for filling the missing data to be processed;
inputting the filling data and the complete data in the running state information into a health state evaluation model to obtain the health state of the numerical control machine tool output by the health state evaluation model;
the signal transmission process is all links included in each transmission or processing node of the running state information after the running state information is acquired.
According to the numerical control machine tool health state assessment method based on missing data completion, the signal transmission process comprises a parameter detection process, a parameter analysis process, a parameter adjustment process and a data transmission process of the running state information; the determining missing data to be processed in the running state information based on the running state information comprises the following steps:
Determining running state information missing in any process in the signal transmission process as target missing information;
determining a second state parameter corresponding to a signal transmission process in which the target missing information is missing based on a first state parameter, wherein the first state parameter is state information corresponding to an un-missing signal transmission process of the target missing information;
and combining the first state parameter and the second state parameter according to the information transmission sequence corresponding to the state parameters to obtain the missing data to be processed.
According to the method for evaluating the health state of the numerical control machine tool based on the completion of missing data, the method for determining the second state parameter corresponding to the signal transmission process missing by the target missing information based on the first state parameter comprises the following steps:
determining the data deletion rate of the target deletion information in the signal transmission process based on the ratio of the number of deletion parameters corresponding to the first state parameters to the total number of parameters of the running state information in the target deletion information;
if the loss rate is greater than or equal to a preset threshold value, determining a processed workpiece corresponding to the target loss information and standard processing technological parameters corresponding to the processed workpiece;
And determining a second state parameter corresponding to the signal transmission process in which the target missing information is missing based on the standard processing technological parameter and the first state parameter.
According to the method for evaluating the health state of the numerical control machine tool based on the completion of missing data, the second state parameter corresponding to the signal transmission process missing by the target missing information is determined based on the standard processing technological parameter and the first state parameter, and the method comprises the following steps:
determining standard operation state information generated correspondingly by the standard processing technological parameters;
taking a gain value between the first state parameter and a corresponding state parameter in the standard running state information as a weighting coefficient, carrying out poisson distribution weighting on the standard running state information based on the weighting coefficient, and determining a second state parameter corresponding to a signal transmission process in which the target missing information is missing.
According to the numerical control machine tool health state assessment method based on missing data completion, the health state assessment model comprises a residual life prediction module and a classifier module; inputting the filling data and the complete data in the running state information into a health state evaluation model to obtain the health state of the numerical control machine tool output by the health state evaluation model, wherein the method comprises the following steps:
Inputting the filling data and the complete data in the running state information to the residual life prediction module to obtain the residual life of the numerical control machine tool output by the residual life prediction module;
inputting the residual life into the classifier module to obtain the health state evaluation grade output by the classifier module;
wherein the health status of the numerically-controlled machine tool is determined based on the health status evaluation level of the numerically-controlled machine tool.
According to the method for evaluating the health state of the numerical control machine based on missing data completion, the method for acquiring the running state information of each mechanical part of the numerical control machine comprises the following steps:
determining a plurality of groups of processing technological parameters of the numerical control machine tool on a plurality of processed workpieces, wherein one processed workpiece corresponds to the plurality of groups of processing technological parameters;
controlling the numerical control machine tool to process the processed workpiece based on the multiple groups of processing technological parameters so as to acquire the running state information of each mechanical part when the numerical control machine tool processes the processed workpiece;
wherein the operating state information includes at least one of vibration, rotational speed, temperature, current, or humidity.
According to the numerical control machine tool health state assessment method based on missing data completion, the running state information comprises first running state information and second running state information, the first running state information is acquired when the numerical control machine tool processes different processing devices based on the same processing technological parameters, and the second running state information is acquired when the numerical control machine tool processes the same processing devices based on multiple groups of different processing technological parameters.
The invention also provides a numerical control machine tool health state assessment device based on missing data completion, which comprises:
the running state acquisition module is used for acquiring running state information of each mechanical component of the numerical control machine tool;
the to-be-processed missing data determining module is used for determining to-be-processed missing data in the running state information based on the running state information, wherein the to-be-processed missing data are data of missing parts of the running state information in the signal transmission process;
the data interpolation module is used for inputting the missing data to be processed into a pre-trained diffusion interpolation model to obtain complete data output by the diffusion interpolation model, and the diffusion interpolation model is used for complementing the missing data to be processed;
The health state evaluation module is used for inputting the complete data into a health state evaluation model to obtain the health state of the numerical control machine tool output by the health state evaluation model;
the signal transmission process is all links included in each transmission or processing node of the running state information after the running state information is acquired.
The invention also provides electronic equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the numerical control machine health state evaluation method based on the missing data completion when executing the program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method for assessing the health status of a numerically controlled machine tool based on missing data complementation as described in any one of the above.
According to the method and the device for evaluating the health state of the numerical control machine based on the missing data completion, the missing part of each mechanical part of the numerical control machine in the signal transmission process is analyzed through the running state information of the links included in each transmission or processing node, and the missing part is completed, so that the health state of the numerical control machine can be predicted according to the filling data obtained by the completed missing part. Considering the problems of complex machine manufacturing environment, such as signal jump, signal packet loss, transmission loss and the like, the health state evaluation of the numerical control machine is carried out by filling the missing running state information of each mechanical part at each transmission or processing node, and the machine state evaluation under the condition of considering missing samples is favorable for retaining data information, so that the sample utilization rate can be improved on one hand, and the accuracy of the health state evaluation of the numerical control machine can be improved on the other hand.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for evaluating the health state of a numerical control machine based on missing data complementation;
FIG. 2 is a second flow chart of the method for evaluating the health status of a numerical control machine based on missing data complementation provided by the invention;
FIG. 3 is a third flow chart of the method for evaluating the health status of a numerical control machine based on missing data complementation provided by the invention;
FIG. 4 is a schematic flow chart of a method for evaluating the health status of a numerical control machine based on missing data complementation provided by the invention;
FIG. 5 is a schematic flow chart of a method for evaluating the health status of a numerical control machine based on missing data complementation provided by the invention;
FIG. 6 is a flowchart of a method for evaluating the health status of a numerical control machine based on missing data complementation according to the present invention;
Fig. 7 is a schematic structural diagram of a numerical control machine tool health state evaluation device based on missing data complementation provided by the invention;
fig. 8 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The method for evaluating the health state of the numerical control machine tool based on missing data complementation according to the present invention is described below with reference to fig. 1 to 6.
Referring to fig. 1, the method for evaluating the health state of a numerical control machine tool based on missing data completion provided by the invention comprises the following steps:
the numerical control machine tool is externally connected with an external sensing sensor, the numerical control system can monitor the running state information of each mechanical part of the numerical control machine tool in real time through the external sensing sensor, and the mechanical parts of the numerical control machine tool can comprise a main shaft, a motor, a cutter and the like. The operating state information may include at least one of a vibration signal, a rotational speed, a temperature, a current, or a humidity, and the external sensing sensor may include a temperature sensor, a vibration sensor, a power sensor, and the like.
The running state information is used for carrying out health state assessment on the numerical control machine, a machine tool health state assessment model is built according to complete data in the running state information and filling data obtained after the running state information of all mechanical parts is filled in a missing part of a signal transmission process, the current health state of the numerical control machine is assessed by using the health state assessment model, and the health state of the numerical control machine can be assessed through health degree or health index.
after the running state information of each mechanical part of the numerical control machine tool is obtained, the running state information comprises complete data and missing data, the complete data refers to the data without missing of all the data of each processing or transmission node in the signal transmission process in the acquired running state information, and the missing data to be processed refers to the data with missing part in all the processing or transmission nodes in the signal transmission process in the acquired running state information. In this step, each signal transmission process in the operation state information is analyzed, the missing part in the operation state information is determined, and the data of the missing part in the operation state information is extracted to obtain the missing data to be processed.
Therefore, in the step of analyzing the running state information, the data with the missing part in the running state information is actually distinguished from the complete data, the data with the missing part in the running state information is extracted, the missing data to be processed is obtained, and the complete data and the missing data in the running state information are divided.
Step 30, inputting the missing data to be processed into a pre-trained diffusion interpolation model to obtain filling data output by the diffusion interpolation model, wherein the diffusion interpolation model is used for filling the missing data to be processed;
after the missing data in the running state information is obtained, the missing data to be processed is input into a diffusion interpolation model trained in advance, so that the diffusion interpolation model can conduct diffusion dimension and interpolation on missing parts in the missing data to be processed, filling data output by the diffusion interpolation model are obtained, and the missing parts in the signal transmission process of the missing data to be processed are completed.
The diffusion interpolation model comprises a diffusion module and an interpolation module, wherein the diffusion module is used for further diffusing or dispersing the dimension of a missing part or a missing supplemented part in missing data to be processed, and the diffusion module can comprise a variational self-encoder (VAE), a generation countermeasure network, a normalization stream, an autoregressive model and an energy-based model; the interpolation module is used for combining the dimension diffused by the diffusion model and the missing data to be processed to generate filling data, and the interpolation module can comprise a diffusion model CSDI model based on a conditional score, wherein the diffusion interpolation model is used for interpolating the missing part in the missing data to be processed.
In a possible embodiment, the diffusion module in the diffusion interpolation model is configured to determine a missing dimension of the missing data to be processed based on a target missing flow corresponding to the missing data to be processed, and determine a missing parameter corresponding to the missing dimension, and the interpolation module in the diffusion interpolation model is configured to interpolate the missing data to be processed based on the missing parameter corresponding to the missing dimension, so as to obtain complete data. The dimension of the missing data to be processed is expanded through the diffusion interpolation model, interpolation is carried out on the missing data to be processed according to the corresponding dimension, accurate and effective interpolation on the missing data to be processed is achieved, and the sample size of training data is improved.
Step 40, inputting the filling data and the complete data in the running state information into a health state evaluation model to obtain the health state of the numerical control machine tool output by the health state evaluation model;
the signal transmission process is all links included in each transmission or processing node of the running state information after the running state information is acquired.
After the missing part in the missing data is complemented, the filling data and the complete data in the running state information are input into a health state evaluation model of the numerical control machine, so that the health state of the numerical control machine is predicted through the health state evaluation model, and a health state prediction result of the numerical control machine is obtained. The complete data can be used as a training sample for health state evaluation, and the health state evaluation model can be built through training, so that the sample utilization rate can be improved, and the performance of the health state evaluation model can be improved. The complete data refers to the data without loss of all the data of each processing or transmitting node in the signal transmission process in the acquired running state information.
Further, an attention mechanism is added in the model training process of constructing the health state evaluation model to learn the time and characteristic dependence in the machine tool perception sensor data. And the model training process can be accelerated by adopting a knowledge distillation method in a mode that a teacher guides students, so that the problem that the diffusion model is slow in sampling and long in training time is solved.
According to the method for evaluating the health state of the numerical control machine based on the missing data completion, the missing part of each mechanical part of the numerical control machine in the signal transmission process is analyzed through the running state information of links included in each transmission or processing node, and the missing part is completed, so that the health state of the numerical control machine can be predicted according to the filling data obtained by the completion of the missing part. Considering the problems of complex machine manufacturing environment, such as signal jump, signal packet loss, transmission loss and the like, the health state evaluation of the numerical control machine is carried out by filling the missing running state information of each mechanical part at each transmission or processing node, and the machine state evaluation under the condition of considering missing samples is favorable for retaining data information, so that the sample utilization rate can be improved on one hand, and the accuracy of the health state evaluation of the numerical control machine can be improved on the other hand.
In one possible embodiment, referring to fig. 2, the signal transmission process includes a parameter detection process, a parameter analysis process, a parameter adjustment process, and a data transmission process of the operation state information; step 20, determining missing data to be processed in the running state information based on the running state information, including:
and step 23, combining the first state parameter and the second state parameter according to the information transmission sequence corresponding to the state parameters to obtain the missing data to be processed.
In the signal transmission process, the data of all the processes of the data are not deleted in the parameter detection process, the parameter analysis process, the parameter adjustment process and the data transmission process, and are used as a set of complete data; the data of all processes in which data is missing in any one of the parameter detection process, the parameter analysis process, the parameter adjustment process and the data transmission process is defined as target missing information as a set of missing data. That is, there is, as the target missing information, the running state information in which any one of the signal transmission processes is missing.
Since the signal transmission process includes a parameter detection process, a parameter analysis process, a parameter adjustment process, and a data transmission process of the operation state information, that is, the signal transmission process of the target missing information is determined, it is possible to easily obtain the information transmission process of the operation state information missing in the signal transmission process by detecting whether the state information exists according to the parameter detection of the operation state information in different signal transmission processes, and obtain the target missing information. And then, based on the first state parameters corresponding to the non-missing process in all the signal transmission processes in the target missing information, estimating the second state parameters corresponding to the missing signal transmission processes in the target missing information, namely, for the target missing information, estimating the missing part according to the non-missing part in the signal transmission process, so as to improve the accuracy of the missing part data estimation.
In this embodiment, in the process of estimating missing data in which a missing portion exists in running state information, the missing state parameter is estimated according to a state parameter that is not missing in a signal transmission process, so that accuracy of the missing state parameter in target missing information is improved, accuracy of the missing data to be processed is improved, and accuracy of health state assessment of the numerically-controlled machine tool is further improved.
In one embodiment, referring to fig. 3, step 22, determining, based on the first state parameter, a second state parameter corresponding to the signal transmission process in which the target missing information is missing includes:
Wherein the deletion rate is the specific gravity of the parameter deleted by the target deletion information in all parameters of the signal transmission process.
In this embodiment, according to the number of missing parameters corresponding to the target missing information and the total number of parameters of the running state information corresponding to each signal transmission process, the missing rate of the data of the target missing information in the signal transmission process is calculated. Wherein the deletion rate characterizes the degree of data deletion in the target deletion information. If the missing rate is greater than or equal to a preset threshold value, indicating that the degree of missing data in the target missing information is too high, and the amount of missing data is too large, estimating that the accuracy of missing part parameters is too low only through the un-missing part, and estimating and calculating a second state parameter corresponding to the signal transmission process of the missing of the target missing information by using standard processing process parameters corresponding to the processed workpiece corresponding to the target missing information. If the loss rate is smaller than the preset threshold value, the second state parameter can be estimated directly according to the first state parameter in the target loss information without combining the standard processing technological parameters of the processed workpiece.
In this embodiment, when the missing rate is too high, the second state parameter corresponding to the signal transmission process in which the missing target missing information is missing is calculated by combining the standard processing technological parameter corresponding to the processed workpiece corresponding to the target missing information and the first state parameter which is not the missing part parameter, so that the accuracy of the missing state parameter in the target missing information is improved, the accuracy of the missing data to be processed is improved, and the accuracy of the health state evaluation of the numerical control machine tool is further improved.
In one embodiment, referring to fig. 4, step 223, determining, based on the standard processing parameters and the first state parameters, a second state parameter corresponding to the signal transmission process in which the target missing information is missing includes:
In this embodiment, when the loss rate is too high, the second state parameter corresponding to the signal transmission process in which the target loss information is lost is estimated and calculated by combining the standard processing technological parameter corresponding to the processed workpiece corresponding to the target loss information and the first state parameter which is the non-lost part parameter, and the poisson distribution weighting can be performed on the standard operation state information by taking the gain value between the first state parameter and the state parameter corresponding to the standard operation state information as the weighting coefficient, so as to determine the second state parameter corresponding to the signal transmission process in which the target loss information is lost. The purpose of this step is to take into account the randomness of the poisson distribution, so that the reliability of the measured second state parameter is improved.
In one embodiment, referring to fig. 5, the health status assessment model includes a remaining life prediction module and a classifier module; step 40, inputting the filling data and the complete data in the running state information to a health state evaluation model to obtain the health state of the numerical control machine tool output by the health state evaluation model, including:
wherein the health status of the numerically-controlled machine tool is determined based on the health status evaluation level of the numerically-controlled machine tool.
In this embodiment, the health state evaluation model predicts the remaining life and evaluates the health state of the numerically-controlled machine tool according to the remaining life.
Specifically, complete data is input through a residual life prediction module in the health state evaluation model to obtain the residual life of the numerical control machine tool, and then the residual life of the numerical control machine tool is input to a classifier module in the health state evaluation model to divide the health state evaluation grade of the numerical control machine tool according to the residual life of the numerical control machine tool and a preset clustering algorithm deployed in the classifier module, wherein the grade category comprises near new, good, medium, scrapped and the like. The preset clustering algorithm may be a KNN clustering algorithm.
In one embodiment, referring to fig. 6, step 10, the obtaining the operation status information of each mechanical component of the numerically controlled machine tool includes:
wherein the operating state information includes at least one of vibration, rotational speed, temperature, current, or humidity.
The operation state information comprises first operation state information and second operation state information, the first operation state information is obtained by monitoring when the numerical control machine tool processes different processing devices based on the same processing technological parameters, and the second operation state information is obtained when the numerical control machine tool processes the same processing devices based on multiple groups of different processing technological parameters.
In this embodiment, by setting the numerically-controlled machine tool to perform operation according to a plurality of sets of processing technological parameters of a plurality of processing workpieces, when the numerically-controlled machine tool performs cutting processing on the processing technological parameters corresponding to different processing workpieces, current operation state information of each mechanical part is collected, and the operation state information includes a plurality of processing workpieces and a plurality of sets of operation state information corresponding to a plurality of sets of processing technological parameters corresponding to the same processing workpiece.
By arranging the numerical control machine tool to operate according to a plurality of processing workpieces and a plurality of groups of processing technological parameters when different processing workpieces are processed, a plurality of groups of operation state information are acquired, the diversity of data samples is realized, and the performance of a health state evaluation model of the numerical control machine tool can be effectively improved.
The invention provides a numerical control machine tool health state evaluation device based on missing data completion, and the numerical control machine tool health state evaluation device based on missing data completion and the numerical control machine tool health state evaluation method based on missing data completion, which are described below, can be referred to correspondingly.
Referring to fig. 7, the device for evaluating the health status of a numerically-controlled machine tool based on missing data complementation provided by the invention comprises:
an operation state acquisition module 710, configured to acquire operation state information of each mechanical component of the numerically-controlled machine tool;
the missing data to be processed determining module 720 is configured to determine missing data to be processed in the running state information based on the running state information, where the missing data to be processed is data of a missing portion of each running state information in a signal transmission process;
the data interpolation module 730 is configured to input the missing data to be processed into a pre-trained diffusion interpolation model, to obtain padding data output by the diffusion interpolation model, where the diffusion interpolation model is used to complement the missing data to be processed;
The health state evaluation module 740 is configured to input the filling data and the complete data in the running state information to a health state evaluation model, so as to obtain a health state of the numerical control machine tool output by the health state evaluation model;
the signal transmission process is all links included in each transmission or processing node of the running state information after the running state information is acquired.
Further, the signal transmission process comprises a parameter detection process, a parameter analysis process, a parameter adjustment process and a data transmission process of the running state information; the missing data to be processed determining module is further configured to:
determining running state information missing in any process in the signal transmission process as target missing information;
determining a second state parameter corresponding to a signal transmission process in which the target missing information is missing based on a first state parameter, wherein the first state parameter is state information corresponding to an un-missing signal transmission process of the target missing information;
and combining the first state parameter and the second state parameter according to the information transmission sequence corresponding to the state parameters to obtain the missing data to be processed.
Further, the missing data to be processed determining module is further configured to:
determining the data deletion rate of the target deletion information in the signal transmission process based on the ratio of the number of deletion parameters corresponding to the first state parameters to the total number of parameters of the running state information in the target deletion information;
if the loss rate is greater than or equal to a preset threshold value, determining a processed workpiece corresponding to the target loss information and standard processing technological parameters corresponding to the processed workpiece;
and determining a second state parameter corresponding to the signal transmission process in which the target missing information is missing based on the standard processing technological parameter and the first state parameter.
Further, the missing data to be processed determining module is further configured to:
determining standard operation state information generated correspondingly by the standard processing technological parameters;
taking a gain value between the first state parameter and a corresponding state parameter in the standard running state information as a weighting coefficient, carrying out poisson distribution weighting on the standard running state information based on the weighting coefficient, and determining a second state parameter corresponding to a signal transmission process in which the target missing information is missing.
Further, the health state assessment model includes a remaining life prediction module and a classifier module; the health state evaluation module is further configured to:
inputting the filling data and the complete data in the running state information to the residual life prediction module to obtain the residual life of the numerical control machine tool output by the residual life prediction module;
inputting the residual life into the classifier module to obtain the health state evaluation grade output by the classifier module;
wherein the health status of the numerically-controlled machine tool is determined based on the health status evaluation level of the numerically-controlled machine tool.
Further, the operation state acquisition module is further configured to:
determining a plurality of groups of processing technological parameters of the numerical control machine tool on a plurality of processed workpieces, wherein one processed workpiece corresponds to the plurality of groups of processing technological parameters;
controlling the numerical control machine tool to process the processed workpiece based on the multiple groups of processing technological parameters so as to acquire the running state information of each mechanical part when the numerical control machine tool processes the processed workpiece;
wherein the operating state information includes at least one of vibration, rotational speed, temperature, current, or humidity.
Further, the operation state information comprises first operation state information and second operation state information, the first operation state information is acquired when the numerical control machine tool processes different processing devices based on the same processing technological parameters, and the second operation state information is acquired when the numerical control machine tool processes the same processing devices based on multiple groups of different processing technological parameters.
Fig. 8 illustrates a physical structure diagram of an electronic device, as shown in fig. 8, which may include: processor 810, communication interface (Communications Interface) 820, memory 830, and communication bus 840, wherein processor 810, communication interface 820, memory 830 accomplish communication with each other through communication bus 840. The processor 810 may invoke logic instructions in the memory 830 to perform a numerically controlled machine tool health assessment method based on missing data completion, the method comprising: acquiring the running state information of each mechanical part of the numerical control machine; determining to-be-processed missing data in the running state information based on the running state information, wherein the to-be-processed missing data is data of missing parts of each running state information in a signal transmission process; inputting the missing data to be processed into a pre-trained diffusion interpolation model to obtain filling data output by the diffusion interpolation model, wherein the diffusion interpolation model is used for filling the missing data to be processed; inputting the filling data and the complete data in the running state information into a health state evaluation model to obtain the health state of the numerical control machine tool output by the health state evaluation model; the signal transmission process is all links included in each transmission or processing node of the running state information after the running state information is acquired.
Further, the logic instructions in the memory 830 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, where the computer program product includes a computer program, where the computer program can be stored on a non-transitory computer readable storage medium, and when the computer program is executed by a processor, the computer can execute the method for evaluating the health state of a numerically controlled machine tool based on missing data complement provided by the above methods, and the method includes: acquiring the running state information of each mechanical part of the numerical control machine; determining to-be-processed missing data in the running state information based on the running state information, wherein the to-be-processed missing data is data of missing parts of each running state information in a signal transmission process; inputting the missing data to be processed into a pre-trained diffusion interpolation model to obtain filling data output by the diffusion interpolation model, wherein the diffusion interpolation model is used for filling the missing data to be processed; inputting the filling data and the complete data in the running state information into a health state evaluation model to obtain the health state of the numerical control machine tool output by the health state evaluation model; the signal transmission process is all links included in each transmission or processing node of the running state information after the running state information is acquired.
In still another aspect, the present invention further provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the method for evaluating health status of a numerically controlled machine tool based on missing data completion provided by the above methods, the method comprising: acquiring the running state information of each mechanical part of the numerical control machine; determining to-be-processed missing data in the running state information based on the running state information, wherein the to-be-processed missing data is data of missing parts of each running state information in a signal transmission process; inputting the missing data to be processed into a pre-trained diffusion interpolation model to obtain filling data output by the diffusion interpolation model, wherein the diffusion interpolation model is used for filling the missing data to be processed; inputting the filling data and the complete data in the running state information into a health state evaluation model to obtain the health state of the numerical control machine tool output by the health state evaluation model; the signal transmission process is all links included in each transmission or processing node of the running state information after the running state information is acquired.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. The utility model provides a digit control machine tool health state evaluation method based on missing data completion which is characterized in that the method comprises the following steps:
acquiring the running state information of each mechanical part of the numerical control machine;
determining to-be-processed missing data in the running state information based on the running state information, wherein the to-be-processed missing data is data of missing parts of each running state information in a signal transmission process;
inputting the missing data to be processed into a pre-trained diffusion interpolation model to obtain filling data output by the diffusion interpolation model, wherein the diffusion interpolation model is used for filling the missing data to be processed;
Inputting the filling data and the complete data in the running state information into a health state evaluation model to obtain the health state of the numerical control machine tool output by the health state evaluation model;
the signal transmission process is all links included in each transmission or processing node of the running state information after the running state information is acquired.
2. The method for evaluating the health status of a numerically-controlled machine tool based on missing data completion according to claim 1, wherein the signal transmission process includes a parameter detection process, a parameter analysis process, and a parameter adjustment process of the operation status information, and a data transmission process; the determining missing data to be processed in the running state information based on the running state information comprises the following steps:
determining running state information missing in any process in the signal transmission process as target missing information;
determining a second state parameter corresponding to a signal transmission process in which the target missing information is missing based on a first state parameter, wherein the first state parameter is state information corresponding to an un-missing signal transmission process of the target missing information;
And combining the first state parameter and the second state parameter according to the information transmission sequence corresponding to the state parameters to obtain the missing data to be processed.
3. The method for evaluating the health status of a numerically-controlled machine tool based on missing data completion according to claim 2, wherein the determining, based on the first status parameter, a second status parameter corresponding to a signal transmission process in which the target missing information is missing includes:
determining the data deletion rate of the target deletion information in the signal transmission process based on the ratio of the number of deletion parameters corresponding to the first state parameters to the total number of parameters of the running state information in the target deletion information;
if the loss rate is greater than or equal to a preset threshold value, determining a processed workpiece corresponding to the target loss information and standard processing technological parameters corresponding to the processed workpiece;
and determining a second state parameter corresponding to the signal transmission process in which the target missing information is missing based on the standard processing technological parameter and the first state parameter.
4. The method for evaluating the health status of a numerically-controlled machine tool based on missing data complementation according to claim 3, wherein the determining the second status parameter corresponding to the signal transmission process missing the target missing information based on the standard processing technological parameter and the first status parameter comprises:
Determining standard operation state information generated correspondingly by the standard processing technological parameters;
taking a gain value between the first state parameter and a corresponding state parameter in the standard running state information as a weighting coefficient, carrying out poisson distribution weighting on the standard running state information based on the weighting coefficient, and determining a second state parameter corresponding to a signal transmission process in which the target missing information is missing.
5. The method for evaluating the health state of the numerical control machine tool based on missing data complementation according to claim 1, wherein the health state evaluation model comprises a residual life prediction module and a classifier module; inputting the filling data and the complete data in the running state information into a health state evaluation model to obtain the health state of the numerical control machine tool output by the health state evaluation model, wherein the method comprises the following steps:
inputting the filling data and the complete data in the running state information to the residual life prediction module to obtain the residual life of the numerical control machine tool output by the residual life prediction module;
inputting the residual life into the classifier module to obtain the health state evaluation grade output by the classifier module;
Wherein the health status of the numerically-controlled machine tool is determined based on the health status evaluation level of the numerically-controlled machine tool.
6. The method for evaluating the health status of a numerically-controlled machine tool based on missing data complementation according to claim 1, wherein the acquiring the operation status information of each mechanical component of the numerically-controlled machine tool comprises:
determining a plurality of groups of processing technological parameters of the numerical control machine tool on a plurality of processed workpieces, wherein one processed workpiece corresponds to the plurality of groups of processing technological parameters;
controlling the numerical control machine tool to process the processed workpiece based on the multiple groups of processing technological parameters so as to acquire the running state information of each mechanical part when the numerical control machine tool processes the processed workpiece;
wherein the operating state information includes at least one of vibration, rotational speed, temperature, current, or humidity.
7. The method for evaluating the health state of a numerical control machine tool based on missing data complementation according to claim 6, wherein the operation state information comprises first operation state information and second operation state information, the first operation state information is acquired when the numerical control machine tool processes different processing devices based on the same processing technological parameters, and the second operation state information is acquired when the numerical control machine tool processes the same processing devices based on multiple groups of different processing technological parameters.
8. The utility model provides a digit control machine tool health state evaluation device based on missing data is accomplished which characterized in that includes:
the running state acquisition module is used for acquiring running state information of each mechanical component of the numerical control machine tool;
the to-be-processed missing data determining module is used for determining to-be-processed missing data in the running state information based on the running state information, wherein the to-be-processed missing data are data of missing parts of the running state information in the signal transmission process;
the data interpolation module is used for inputting the missing data to be processed into a pre-trained diffusion interpolation model to obtain filling data output by the diffusion interpolation model, and the diffusion interpolation model is used for completing the missing data to be processed;
the health state evaluation module is used for inputting the filling data and the complete data in the running state information into a health state evaluation model to obtain the health state of the numerical control machine tool output by the health state evaluation model;
the signal transmission process is all links included in each transmission or processing node of the running state information after the running state information is acquired.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the numerically controlled machine tool health status assessment method based on missing data complementation of any one of claims 1 to 7 when executing the program.
10. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the numerically controlled machine tool health status assessment method based on missing data complementation according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310303801.4A CN116010833B (en) | 2023-03-27 | 2023-03-27 | Numerical control machine tool health state evaluation method and device based on missing data completion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310303801.4A CN116010833B (en) | 2023-03-27 | 2023-03-27 | Numerical control machine tool health state evaluation method and device based on missing data completion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116010833A true CN116010833A (en) | 2023-04-25 |
| CN116010833B CN116010833B (en) | 2023-06-09 |
Family
ID=86021361
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310303801.4A Active CN116010833B (en) | 2023-03-27 | 2023-03-27 | Numerical control machine tool health state evaluation method and device based on missing data completion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116010833B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012194741A (en) * | 2011-03-16 | 2012-10-11 | Nec Corp | Prediction device of missing value in matrix data, method for calculating missing value prediction, and missing value prediction program |
| CN113033011A (en) * | 2021-04-07 | 2021-06-25 | 大连海事大学 | Ship machinery health state assessment method and system |
| CN113487182A (en) * | 2021-07-06 | 2021-10-08 | 新智数字科技有限公司 | Equipment health state evaluation method and device, computer equipment and medium |
| CN113935562A (en) * | 2020-07-14 | 2022-01-14 | 东南大学 | Intelligent rating and automatic early warning method for health condition of power equipment |
| CN115145903A (en) * | 2022-07-01 | 2022-10-04 | 湖北博华自动化系统工程有限公司 | Data interpolation method based on production process |
-
2023
- 2023-03-27 CN CN202310303801.4A patent/CN116010833B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012194741A (en) * | 2011-03-16 | 2012-10-11 | Nec Corp | Prediction device of missing value in matrix data, method for calculating missing value prediction, and missing value prediction program |
| CN113935562A (en) * | 2020-07-14 | 2022-01-14 | 东南大学 | Intelligent rating and automatic early warning method for health condition of power equipment |
| CN113033011A (en) * | 2021-04-07 | 2021-06-25 | 大连海事大学 | Ship machinery health state assessment method and system |
| CN113487182A (en) * | 2021-07-06 | 2021-10-08 | 新智数字科技有限公司 | Equipment health state evaluation method and device, computer equipment and medium |
| CN115145903A (en) * | 2022-07-01 | 2022-10-04 | 湖北博华自动化系统工程有限公司 | Data interpolation method based on production process |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116010833B (en) | 2023-06-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112272763B (en) | Abnormality detection device, abnormality detection method, and computer-readable storage medium | |
| EP1958034B1 (en) | Use of sequential clustering for instance selection in machine condition monitoring | |
| US20210006481A1 (en) | Method and Apparatus for Determining Status of Network Device | |
| CN112529053A (en) | Short-term prediction method and system for time sequence data in server | |
| CN114326593B (en) | Cutter life prediction system and method | |
| CN115184193A (en) | Automatic testing method, device and equipment for cable and storage medium | |
| CN113505879B (en) | Prediction method and device based on multi-attention feature memory model | |
| CN116010833B (en) | Numerical control machine tool health state evaluation method and device based on missing data completion | |
| CN114564345A (en) | Server abnormity detection method, device, equipment and storage medium | |
| CN112783138B (en) | Intelligent monitoring and abnormity diagnosis method and device for processing stability of production line equipment | |
| CN112100067B (en) | Regression analysis-based test method, system and storage medium | |
| CN115705413A (en) | Method and device for determining abnormal log | |
| CN113743726A (en) | Safety management and control method and system for operation of cable trench of power transmission line based on edge calculation | |
| JP7251955B2 (en) | Detection device and machine learning method | |
| CN112419098B (en) | Power grid safety and stability simulation sample screening and expanding method based on safety information entropy | |
| CN116070734A (en) | Transformer fault prediction method, device, equipment and storage medium | |
| CN112395280B (en) | Data quality detection method and system | |
| CN113110972A (en) | Method, device and medium for detecting time sequence data abnormity | |
| CN112379656A (en) | Processing method, device, equipment and medium for detecting abnormal data of industrial system | |
| CN113433925B (en) | Predictive control method and device for heading machine motor equipment | |
| CN112083707A (en) | Industrial control physical signal processing method, controller and processing system | |
| CN116249943A (en) | Processing diagnosis device, learning device, estimation device, processing diagnosis method, and program | |
| CN111258866A (en) | Computer performance prediction method, device, equipment and readable storage medium | |
| CN116150666B (en) | Energy storage system fault detection method and device and intelligent terminal | |
| CN113742216B (en) | Method, device and storage medium for detecting efficiency of machine learning engine |
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 |