CN116009480B - Fault monitoring method, device and equipment of numerical control machine tool and storage medium - Google Patents
Fault monitoring method, device and equipment of numerical control machine tool and storage medium Download PDFInfo
- Publication number
- CN116009480B CN116009480B CN202310296718.9A CN202310296718A CN116009480B CN 116009480 B CN116009480 B CN 116009480B CN 202310296718 A CN202310296718 A CN 202310296718A CN 116009480 B CN116009480 B CN 116009480B
- Authority
- CN
- China
- Prior art keywords
- machine tool
- fault
- numerical control
- detected
- state data
- 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.)
- Active
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
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Numerical Control (AREA)
Abstract
The invention provides a fault monitoring method, device, equipment and storage medium of a numerical control machine tool, which relate to the technical field of numerical control machining and are characterized in that operation state data of a plurality of preset monitoring points of the numerical control machine tool to be monitored in the numerical control machining process are obtained, and abnormal operation state data in the operation state data are determined; taking machine tool components corresponding to preset monitoring points corresponding to the abnormal running state data as machine tool components to be detected; determining the machine tool parts to be detected which are mutually influenced according to the first association relation of the machine tool parts to be detected; taking the abnormal operation state data corresponding to the mutually-influenced machine tool parts to be detected as a group to obtain one or more abnormal data groups; and determining a predicted machine tool fault component corresponding to the abnormal data set through the abnormal data set and a trained target fault detection model corresponding to the numerical control machine tool to be monitored. By the aid of the scheme, fault components in the numerical control machine tool can be accurately positioned, and fault monitoring accuracy of the numerical control machine tool is improved.
Description
Technical Field
The present invention relates to the field of numerically controlled processing technologies, and in particular, to a fault monitoring method, device, equipment and storage medium for a numerically controlled machine tool.
Background
The numerical control machine tool is short for numerical control machine tool, and is an automatic machine tool with a program control system. The numerical control machine tool can solve the problems of complex, precise, small batch and multiple kinds of part processing, is widely applied to various fields, such as national defense aviation, automobile industry, mould manufacturing, machining, part construction and the like, and can be applied to the numerical control machine tool only if the mechanical industry exists.
Meanwhile, the numerical control machine tool is complex in structure and high in price, various faults are often accompanied in the numerical control machining process, the numerical control machine tool is damaged, and the production efficiency of a machined part is affected. Therefore, fault monitoring of the numerical control machine becomes critical during numerical control machining.
However, in the prior art, related operation data of the numerical control machine tool in the numerical control machining process are often collected, the data machine tool is monitored through simple data analysis, and the monitoring accuracy is low, so that the numerical control machine tool cannot be effectively maintained accurately and timely.
Disclosure of Invention
The invention provides a fault monitoring method, device, equipment and storage medium for a numerical control machine tool, which are used for solving the defect of low fault monitoring accuracy of the numerical control machine tool in the prior art and realizing accurate positioning of fault components in the numerical control machine tool.
The invention provides a fault monitoring method of a numerical control machine tool, which comprises the following steps:
acquiring operation state data of a plurality of preset monitoring points of a numerical control machine tool to be monitored in a numerical control machining process, and determining abnormal operation state data in the operation state data, wherein the abnormal operation state data is operation state data with similarity with preset standard operation state data lower than a preset threshold value;
taking machine tool components corresponding to preset monitoring points corresponding to the abnormal operation state data as machine tool components to be detected;
determining the mutually-influenced machine tool parts to be detected according to the first association relation of the machine tool parts to be detected, wherein the first association relation of the machine tool parts to be detected reflects the machine tool parts mechanically connected with the machine tool parts to be detected;
taking the abnormal operation state data corresponding to the machine tool parts to be detected, which are mutually influenced, as a group to obtain one or more abnormal data groups;
And determining a predicted machine tool fault component corresponding to the abnormal data set through the abnormal data set and a trained target fault detection model corresponding to the numerical control machine tool to be monitored.
According to the fault monitoring method of the numerical control machine tool, the target fault detection model is obtained by the following steps:
acquiring a plurality of source domain training sample sets, wherein each source domain training sample set corresponds to a sample numerical control machine tool of one equipment type;
wherein each source domain training sample set comprises a plurality of source domain training samples; each source domain training sample comprises: a sample abnormal data set and a corresponding machine tool fault component label; each sample abnormal data set consists of a plurality of sample abnormal operation state data, and machine tool parts corresponding to the sample abnormal operation state data in each sample abnormal data set are mutually influenced machine tool parts;
obtaining a predicted machine tool fault component corresponding to the source domain training sample through a sample abnormal data set in the source domain training sample and a preset neural network model;
adjusting model parameters of the preset neural network model according to the machine tool fault component labels of the source domain training samples and the predicted machine tool fault components, and continuously executing the steps of obtaining predicted machine tool fault components corresponding to the next source domain training samples through a sample abnormal data set in the next source domain training samples and the preset neural network model until the preset neural network model meets a first preset condition to obtain a trained general fault detection model;
Acquiring a target domain training sample set, and performing model parameter adjustment on the general fault detection model through each target domain training sample in the target domain training sample set to obtain a target fault detection model corresponding to a target domain;
the target domain training sample set corresponds to a sample numerical control machine tool of one equipment type.
According to the fault monitoring method of the numerical control machine provided by the invention, after the predicted machine fault component corresponding to the abnormal data set is determined, the method further comprises the following steps:
acquiring a three-dimensional diagram of the numerical control machine tool to be monitored, and marking the fault parts of the predictive machine tool on the three-dimensional diagram to obtain a marked three-dimensional diagram;
the marked three-dimensional graph is sent to a user terminal, so that the user terminal displays the marked three-dimensional graph to a machine tool manager corresponding to the user terminal;
receiving user feedback information from the user terminal, and generating an optimized training sample according to the user feedback information of the user terminal and the corresponding abnormal data set;
wherein, the user feedback information includes: whether the predicted machine tool fault component is a fault component or not, and a corresponding real fault component when the predicted machine tool fault component is a non-fault component;
And training and optimizing the target fault detection model according to the optimized training sample to obtain the optimized target fault detection model.
According to the fault monitoring method of the numerical control machine provided by the invention, after the predicted machine fault component corresponding to the abnormal data set is determined, the method further comprises the following steps:
determining the fault grade of the numerical control machine to be monitored according to the predicted machine fault component;
determining the available time of the predicted machine tool fault component according to the running state data corresponding to the predicted machine tool fault component under the condition that the fault level meets a second preset condition;
acquiring processing task information of the numerical control machine tool to be monitored in a preset time period;
wherein the processing task information includes: workpiece material, workpiece processing time and workpiece processing quantity;
determining maintenance time of the predicted machine tool fault component according to the available time of the predicted machine tool fault component and processing task information;
generating fault prompt information according to the maintenance time and the corresponding predicted machine tool fault component and sending the fault prompt information to a maintenance center so that the maintenance center distributes corresponding maintenance personnel according to the fault prompt information.
According to the fault monitoring method of the numerical control machine provided by the invention, before the machine tool component corresponding to the preset monitoring point corresponding to each abnormal operation state data is used as the machine tool component to be detected, the method further comprises:
determining a three-dimensional diagram of the numerical control machine to be monitored from a preset diagram library according to the equipment type of the numerical control machine to be monitored;
determining the mechanical connection relation between all the machine tool components in the numerical control machine tool to be monitored according to the three-dimensional graph;
generating a first association relation of each machine tool part according to the mechanical connection relation and storing the first association relation to a cloud server;
the first association relationship is used for representing the mechanical connection relationship of the machine tool components.
According to the fault monitoring method of the numerical control machine provided by the invention, before determining the mutually-affected machine tool parts to be detected according to the first association relation of the machine tool parts to be detected, the fault monitoring method specifically comprises the following steps:
acquiring a first association relation of each machine tool part to be detected from a cloud server;
according to the first association relation, determining the machine tool component to be detected with a mechanical connection relation;
and taking the machine tool parts to be detected with the mechanical connection relationship as the mutually-influenced machine tool parts to be detected.
According to the fault monitoring method of the numerical control machine tool provided by the invention, after the obtained target fault detection model, the method further comprises the following steps:
acquiring equipment types corresponding to the target domain training sample set;
generating a second association relationship between the equipment type corresponding to the target domain training sample set and the target fault detection model, and storing the second association relationship to a local area; storing the target fault detection model to a cloud server;
before determining the predicted machine tool fault component corresponding to the abnormal data set through the trained target fault detection model corresponding to the abnormal data set and the numerical control machine tool to be monitored, the method further comprises:
and calling a target fault detection model corresponding to the numerical control machine to be monitored from a cloud server according to the second association relation between the equipment type of the numerical control machine to be monitored and the locally stored equipment type.
The invention also provides a fault monitoring device of the numerical control machine tool, which comprises:
the data acquisition module is used for acquiring the running state data of a plurality of preset monitoring points of the numerical control machine tool to be monitored in the numerical control machining process, and determining abnormal running state data in the running state data, wherein the abnormal running state data is the running state data with the similarity with the preset standard running state data lower than a preset threshold value;
The first determining module is used for taking machine tool components corresponding to preset monitoring points corresponding to the abnormal operation state data as machine tool components to be detected;
the second determining module is used for determining the to-be-detected machine tool parts which are mutually influenced according to the first association relation of the to-be-detected machine tool parts, and the first association relation of the to-be-detected machine tool parts reflects the machine tool parts mechanically connected with the to-be-detected machine tool parts;
the grouping module is used for taking the abnormal operation state data corresponding to the machine tool parts to be detected, which are mutually influenced, as a group to obtain one or more abnormal data groups;
and the fault judging module is used for determining a predicted machine tool fault component corresponding to the abnormal data set through the abnormal data set and the trained target fault detection model corresponding to the numerical control machine tool to be monitored.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the fault monitoring method of the numerical control machine tool when executing the program.
The invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a fault monitoring method for a numerical control machine as described in any one of the above.
According to the fault monitoring method, device, equipment and storage medium of the numerical control machine, operation state data of a plurality of preset monitoring points of the numerical control machine to be monitored in the numerical control machining process are acquired, abnormal operation state data in the operation state data are determined, machine tool parts corresponding to the abnormal operation state data are used as machine tool parts to be detected, then the machine tool parts to be detected which are mutually influenced are determined according to a first association relation of the machine tool parts to be detected, so that the abnormal operation state data corresponding to the machine tool parts to be detected which are mutually influenced are used as a group, one or more abnormal data sets are obtained, and a predicted machine tool fault part corresponding to the abnormal data sets is determined through the abnormal data sets and a target fault detection model corresponding to the numerical control machine to be monitored.
In the scheme, the acquired running state data is subjected to data analysis to determine the abnormal running state data, so that machine tool parts which are likely to fail are primarily determined, and compared with the direct fault monitoring of all the acquired running state data, the method has the advantage that the calculation resources can be saved to a certain extent; in the invention, through the first association relation of the predetermined machine tool parts to be detected, the mutually influenced machine tool parts to be detected are determined and the corresponding abnormal operation state data are taken as a group, so that the machine tool parts with faults are accurately positioned through the obtained abnormal data group and the corresponding target fault detection model, the accuracy of fault monitoring of the numerical control machine tool is improved, and the numerical control machine tool is timely and effectively maintained.
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 fault monitoring method of a numerical control machine tool provided by the invention;
fig. 2 is a schematic structural diagram of a fault monitoring device of a numerical control machine tool provided by the invention;
fig. 3 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 fault monitoring method of the present invention is described below with reference to fig. 1, and as shown in fig. 1, the fault monitoring method of the present invention may at least include the following steps:
s100, acquiring operation state data of a plurality of preset monitoring points of the numerical control machine tool to be monitored in the numerical control machining process, and determining abnormal operation state data in the operation state data.
Wherein the abnormal operation state data is operation state data with similarity with preset standard operation state data lower than a preset threshold value; the preset monitoring points correspond to key components in the numerical control machine tool to be monitored. Because the mechanical structure in the numerically-controlled machine tool is relatively complicated, the key components can be components with the minimum unit mechanical structure in the numerically-controlled machine tool, such as a motor, a nut, a screw rod and the like in a feeding transmission system of the numerically-controlled machine tool.
The operation state data can comprise vibration signals, pressure signals, temperature signals, humidity signals, current signals, voltage signals and the like, and different data information acquisition devices (such as sensors) are adopted for corresponding operation state data acquisition for different preset monitoring points. That is, the types of the operation state data collected by different preset monitoring points are different, in the prior art, according to which operation state data are required to be collected for machine tool components of different numerical control machine tools, the operation state data are collected in the same manner, and in the embodiment of the present invention, no description is given.
In the embodiment of the invention, key components and components which are easy to damage in the numerical control machine tool can be used as the preset monitoring points, such as a cutter, a main shaft and the like, and can be adjusted according to the actual condition of the numerical control machine tool to be monitored, and the embodiment of the invention is not particularly limited.
Further, the task duration of the numerical control machining task can be determined according to the machining task information of the numerical control machine tool to be monitored, so that a preset time interval is determined according to the task duration, and in the numerical control machining process of the machining task, the running state data of a plurality of preset monitoring points of the numerical control machine tool to be monitored are acquired according to the preset time interval, so that whether the numerical control machine tool to be monitored has faults in the preset time interval is determined.
In the practical application process, the numerical control processing task time of the workpieces in the same batch is longer, because the corresponding preset time interval can be determined according to the task time length, so that fault monitoring can be carried out on the numerical control machine tool to be monitored in different time periods, and the computing resources and the communication resources can be reduced as much as possible on the basis of ensuring the fault monitoring effect of the numerical control machine tool.
It is understood that the execution main body of the fault monitoring method of the numerical control machine tool provided by the invention can be a local server, a computer and other devices, and the embodiment of the invention is not particularly limited.
Further, according to preset monitoring points corresponding to the running state data, standard state data corresponding to the running state data are determined from a preset database, comparison is carried out respectively, similarity of the standard state data and the standard state data is determined, and the running state data are used as abnormal running state data under the condition that the similarity is smaller than a corresponding preset threshold value.
The standard state data refers to operation state data acquired when the numerical control machine tool has no fault, and the operation state data can be stored in a preset database according to the equipment type of the numerical control machine tool and the corresponding machine tool components.
It can be understood that the operation state data can be determined to be normal operation state data when the error allowable range, that is, the similarity is greater than or equal to the corresponding preset threshold. Different preset thresholds can be set for different running state data, and the preset thresholds can be adjusted according to actual conditions, and are not particularly limited in the embodiment of the invention.
And S200, taking machine tool parts corresponding to preset monitoring points corresponding to the abnormal running state data as machine tool parts to be detected.
From the above, different preset monitoring points correspond to different machine tool components. In the embodiment of the invention, the machine tool parts corresponding to the abnormal running state data are used as the machine tool parts to be detected. That is, among these machine tool parts to be detected, there are machine tool parts whose operation state data is abnormal due to other faulty machine tool parts.
S300, determining the machine tool components to be detected which are mutually influenced according to the first association relation of the machine tool components to be detected.
The first association relationship is used to indicate another machine tool component mechanically connected to the machine tool component in the numerical control machine tool.
In the numerical control machine, a certain mechanical connection relation exists in machine tool parts, and a feeding transmission system in the numerical control machine is taken as an example, and a motor, a nut and a screw rod in the feeding transmission system form the feeding transmission system through corresponding mechanical connection, at the moment, if the motor fails, the running state data of the nut and the screw rod are influenced at the same time.
Specifically, the step S300 specifically includes the following steps: acquiring a first association relation of each machine tool part to be detected from a cloud server; determining a machine tool part to be detected with a mechanical connection relation according to the first association relation; and taking the machine tool parts to be detected with the mechanical connection relationship as the mutually-influenced machine tool parts to be detected.
Further, the cloud server stores first association relations of machine tool components of the numerical control machine tools of different equipment types. Therefore, in the embodiment of the invention, the first association relation of each machine tool part to be detected can be obtained from the cloud server through the equipment type of the numerical control machine tool to be monitored and the machine tool parts to be detected.
For example, the machine tool part to be detected is A, B, C, wherein the machine tool part A and the machine tool part B are mechanically connected, and the machine tool part A and the machine tool part B are mutually influenced; and C and A, B are not mechanically connected, and C is the machine tool part with the fault.
In the fault monitoring method of the numerical control machine tool provided by the invention, the first association relation of machine tool components can be generated at least through the following modes: according to the equipment type of the numerical control machine to be monitored, acquiring a three-dimensional diagram of the numerical control machine to be monitored from a preset diagram library; determining the mechanical connection relation of all machine tool components in the numerical control machine tool to be monitored according to the three-dimensional diagram; and generating a first association relation of each machine tool part according to the mechanical connection relation, and storing the first association relation to a cloud server.
The first association relationship is used to indicate another machine tool component mechanically connected to the machine tool component. The three-dimensional map is used to represent the positions and connection relationships of the machine tool components in the numerical control machine tool.
The preset map library is pre-stored with three-dimensional maps of numerical control machine tools of various equipment types. Therefore, the corresponding three-dimensional map can be found from the preset map library according to the equipment type of the numerical control machine tool to be monitored.
Further, the mechanical connection relation between the machine tool parts can be determined by carrying out image recognition through the three-dimensional graph of the numerical control machine tool.
Further, the first association of each machine tool component may be stored in a cloud server. When fault monitoring is carried out on the numerical control machine to be monitored, the first association relation of all machine tool parts of the numerical control machine to be monitored can be obtained from a cloud server through the equipment type of the numerical control machine to be monitored.
According to the scheme, the mechanical connection relation of each machine tool part in the numerical control machine tool can be determined through the three-dimensional graph of the numerical control machine tool so as to generate the first association relation of each machine tool part, and compared with the method of directly recording through a manual mode, the efficiency can be improved and the labor cost can be reduced through image identification of the three-dimensional image. In addition, in order to reduce the utilization of local storage resources, the first association relation of each machine tool part is stored to the cloud server, so that the local operation efficiency is ensured.
S400, taking abnormal operation state data corresponding to the mutually-influenced machine tool parts to be detected as a group, and obtaining one or more abnormal data groups.
In the embodiment of the invention, abnormal operation state data corresponding to the machine tool components to be detected, which are mutually influenced, are taken as a group, so that one or more abnormal data groups are obtained. Wherein each abnormal data group at least comprises one abnormal operation state data.
Further, after step S400, the number of abnormal operation state data in each abnormal data group may be determined. When the number of the abnormal operation state data of the abnormal data set is 1, determining that the machine tool component to be detected corresponding to the abnormal operation state is a fault component, and not executing the following steps. In the case where the number of abnormal operation state data of the abnormal data group is greater than or equal to 2, step S500 is continued to be performed.
It can be understood that if the number of abnormal operation state data of the abnormal data set is 1, it is indicated that the machine tool component to be detected corresponding to the abnormal operation state data in the current numerical control machine tool to be monitored is self-failure, and is not affected by other failure components. Therefore, when the number of the abnormal operation state data of the abnormal data set is 1, the machine tool part to be detected corresponding to the abnormal operation state is determined to be the fault part, subsequent calculation is not needed, calculation resources are further saved, and the fault monitoring efficiency of the numerical control machine tool is further improved.
S500, determining a predicted machine tool fault component corresponding to the abnormal data set through the abnormal data set and a trained target fault detection model corresponding to the numerical control machine tool to be monitored.
The target fault detection model is a trained neural network model. The abnormal data group in step S500 may be an abnormal data group in which the number of abnormal operation state data is greater than or equal to 2.
Specifically, feature extraction can be performed on each abnormal operation state data in the abnormal data set, for example, feature extraction is performed through a convolutional neural network, the extracted abnormal operation state features are input into a target fault detection model corresponding to the numerical control machine to be monitored, and a predicted machine tool fault component corresponding to the abnormal data set is output.
In some embodiments of the present invention, the target fault detection model may be obtained at least by: acquiring a plurality of source domain training sample sets; obtaining a predicted machine tool fault component corresponding to the source domain training sample through a sample abnormal data set in the source domain training sample and a preset neural network model; according to the machine tool fault component label of the original training sample and the predicted machine tool fault component, adjusting model parameters of a preset neural network model, and continuously executing the step of obtaining the predicted machine tool fault component corresponding to the next source domain training sample through a sample abnormal data set in the next source domain training sample and the preset neural network model until the preset neural network model meets a first preset condition, so as to obtain a trained general fault detection model; acquiring a target domain training sample set; and carrying out model parameter adjustment on the general fault detection model according to each target domain training sample in the target domain training sample set to obtain a target fault detection model of the target domain.
Each source domain training sample set corresponds to a sample numerical control machine tool of one equipment type. Each source domain training sample set includes a plurality of source domain training samples; each source domain training sample includes: sample abnormal data set and machine tool fault part label; each sample abnormal data set consists of a plurality of sample abnormal operation state data, and machine tool parts corresponding to the sample abnormal operation state data in the sample abnormal data sets are mutually affected machine tool parts. The target domain is the equipment type corresponding to the target domain training sample set.
The first preset condition may include that the number of training times satisfies a preset number of times and/or that the loss function is less than or equal to a preset threshold.
It should be noted that, the source domain training samples may include both positive samples and negative samples, which are not specifically limited in the embodiment of the present invention.
In addition, the target domain training sample set corresponds to a sample numerical control machine tool of a device type. And, the number of the target field training samples is much smaller than the training samples.
The target domain training sample set includes a plurality of target domain training samples, and each target domain training sample includes: sample abnormal data set and machine tool fault part label; each sample abnormal data set consists of a plurality of sample abnormal operation state data sets, and machine tool parts corresponding to the sample abnormal operation state data in each sample abnormal data set are mutually affected machine tool parts. Wherein the number includes at least one.
In addition, in the embodiment of the present invention, the preset neural network model may be a neural network model including an attention module.
Further, firstly, extracting features of source domain sample abnormal state data of a sample abnormal data set in a source domain training sample, then inputting the extracted features into a preset neural network model, and outputting a predicted machine tool fault component corresponding to the sample abnormal data set to obtain the predicted machine tool fault component corresponding to the source domain training sample.
Similarly, feature extraction may be performed on the sample abnormal operation state data of the target domain training sample, and the extracted features may be input into the general fault detection model to output the predicted machine tool fault component corresponding to the target domain training sample.
In some embodiments of the present invention, the device type corresponding to the target domain training sample set may be obtained first, and the second association relationship between the device type corresponding to the target domain training sample set and the target fault detection model may be regenerated and stored locally; and storing the target fault detection model to a cloud server.
Therefore, after the abnormal data set of the numerical control machine to be monitored is obtained, the target fault detection model corresponding to the numerical control machine to be monitored can be called from the cloud server according to the second association relation between the equipment type of the numerical control machine to be monitored and the local storage.
In a practical scene, a plurality of numerical control machine tools with different equipment types exist, but sample data of the numerical control machine tools with the same type can be collected to be limited, so that the accuracy of a fault detection model is affected. Therefore, in the embodiment of the invention, through the scheme, a plurality of training samples of the source domain are firstly used for model training to obtain a general fault detection model, and the general fault detection model has low detection accuracy on the numerical control machine tool of a specific equipment type, so that parameters of the general fault detection model are adjusted through a small number of training samples of the target domain, thereby obtaining the target fault detection model aiming at the target domain, namely, the target fault detection models of different equipment types can be obtained through the scheme, and the accuracy of fault detection is improved.
In some embodiments of the present invention, the fault monitoring method for a numerically-controlled machine tool provided by the present invention after step S500 may further include at least the following steps: acquiring a three-dimensional diagram of a numerical control machine tool to be monitored, and marking a predicted machine tool fault component on the three-dimensional diagram to obtain a marked three-dimensional diagram; the marked three-dimensional graph is sent to a user terminal, so that the user terminal displays the marked three-dimensional graph to a machine tool manager corresponding to the user terminal; receiving user feedback information from a user terminal, and generating an optimized training sample according to the user feedback information and a corresponding abnormal data set; and training and optimizing the target fault detection model according to the optimized training sample to obtain an optimized target fault detection model.
The marks may be marked by colors, characters, and lines, and are not particularly limited in the embodiment of the present invention. That is, the effect of marking the predicted machine tool failure component on the three-dimensional map is to prompt the user to predict the position of the machine tool failure component in the numerical control machine tool to be monitored and which machine tool component, and the marking mode is not required to be limited.
The user terminal may be a terminal device such as a mobile phone or a tablet computer, which is not particularly limited in the embodiment of the present invention. In addition, the user terminal and the machine tool manager may be in one-to-one correspondence.
In an actual application scene, a manufacturer of the numerical control machine tool sells the numerical control machine tool produced by the manufacturer to different buyers, and the buyers process workpieces according to the purchased numerical control machine tool. Thus, the purchaser may set different machine tool operators, which may be numerical control machine tool operators, for different numerical control machines, at a relatively close distance from the numerical control machine.
In addition, after the user terminal sends the marked three-dimensional graph to a corresponding machine tool manager, the machine tool manager checks a predicted machine tool fault component of the numerical control machine tool to be monitored according to the marked three-dimensional graph, confirms whether the predicted machine tool fault component has faults or not and a machine tool fault component label when the predicted machine tool fault component does not have faults, inputs the checking result into the corresponding user terminal, and enables the user terminal to generate user feedback information according to the checking result and send the user feedback information.
And after receiving the user feedback information from the user terminal, generating an optimized training sample according to the user feedback information and the corresponding abnormal data set.
Wherein, the optimizing training sample comprises: an anomaly data set and a corresponding machine tool fault component signature.
Further, feature extraction can be performed on abnormal operation state data in an abnormal data set in an optimization training sample, the extracted features are input into a target fault detection model, so that a corresponding predicted machine tool fault component is obtained, training and optimization are performed on the target fault detection model according to a predicted machine tool fault component and a machine tool fault component label of the optimization training sample, namely model parameter adjustment is performed, and therefore an optimized target fault detection model is obtained.
In the embodiment of the invention, whether the fault monitoring result is correct or not is determined through the feedback of the machine tool manager of the numerical control machine tool to the predicted machine tool fault component, and the corresponding training optimization sample can be generated according to the first feedback information, so that the target fault detection model is continuously trained and optimized, and the accuracy of the target fault detection model is improved.
In addition, in some embodiments of the present invention, different electronic accounts may be set for the nc manager, and after the nc manager feeds back based on the marked three-dimensional map, a preset point is allocated to the nc manager and added to the corresponding electronic account, where the point in the electronic account may be used for exchange of a commodity (electronic commodity or physical commodity), so as to improve enthusiasm of the nc manager, and obtain more training optimization samples.
In some embodiments of the present invention, the fault monitoring method for a numerically-controlled machine tool provided by the present invention after step S500 may further include at least the following steps: determining the fault grade of the numerical control machine to be monitored according to the predicted machine fault component; under the condition that the fault level meets a second preset condition, determining the available time of the predicted machine tool fault component according to the running state data corresponding to the predicted machine tool fault component; acquiring processing task information of a numerical control machine tool to be monitored within a preset time period; determining maintenance time of the predicted machine tool fault component according to the available time of the predicted machine tool fault component and the processing task information; generating fault prompt information according to the maintenance time and the corresponding predicted machine tool fault component, and sending the fault prompt information to a maintenance center so that the maintenance center distributes corresponding maintenance personnel according to the fault prompt information.
Wherein, the processing task information includes: workpiece information, workpiece processing time, and workpiece processing number.
The workpiece information may at least include workpiece materials, and the workpiece processing time is used to represent processing time required by a single workpiece, where the number of workpieces processed is the number of workpieces processed required by the current processing task.
In an actual application scene, different machine tool parts correspond to different risk levels when the machine tool parts are in failure, some machine tool parts need to stop numerical control machining immediately when the machine tool parts are in failure, and some machine tool parts can be used for a period of time when the machine tool parts are in failure. Thus, in an embodiment of the invention, different fault levels are set for different machine tool fault components, for example: first, second, third, etc., wherein the first is highest and the third is lowest.
It will be appreciated that if there are multiple predicted machine fault components for the numerically controlled machine to be monitored, then multiple fault classes may be associated.
In addition, when the fault level meets the second preset condition, the predicted machine tool fault component does not need to stop working immediately. Thus, the available time of the predicted machine tool fault component can be determined from the operation state data corresponding to the predicted machine tool fault component.
In an actual scene, the fault of part of the machine tool components does not need to be immediately maintained, so that the maintenance time of the predicted machine tool fault components is determined by predicting the available time of the machine tool fault components and the processing task information of the numerical control machine tool to be monitored in a preset time period, and the maintenance center can flexibly distribute corresponding maintenance personnel.
According to the fault monitoring method of the numerical control machine tool, the abnormal operation state data are determined by acquiring the operation state data of a plurality of preset monitoring points of the numerical control machine tool to be monitored in the numerical control machining process, machine tool parts corresponding to the abnormal operation state data are used as machine tool parts to be detected, then the machine tool parts to be detected which are mutually influenced are determined according to the first association relation of the machine tool parts to be detected, so that the abnormal operation state data corresponding to the machine tool parts to be detected which are mutually influenced are used as a group, one or more abnormal data groups are obtained, and the predicted machine tool fault parts corresponding to the abnormal data groups are determined through the abnormal data groups and a target fault detection model corresponding to the numerical control machine tool to be monitored. In the scheme, the acquired running state data is subjected to data analysis to determine the abnormal running state data, so that machine tool parts which are likely to fail are primarily determined, and compared with the direct fault monitoring of all the acquired running state data, the method has the advantage that the calculation resources can be saved to a certain extent; in the invention, through the first association relation of the predetermined machine tool parts to be detected, the mutually influenced machine tool parts to be detected are determined and the corresponding abnormal operation state data are taken as a group, so that the machine tool parts with faults are accurately judged through the obtained abnormal data group and the corresponding target fault detection model, the accuracy of fault monitoring of the numerical control machine tool is improved, and the numerical control machine tool is timely and effectively maintained.
The fault monitoring device of the numerical control machine tool provided by the invention is described below, and the fault monitoring device and the fault monitoring method described above can be correspondingly referred to each other.
As shown in fig. 2, the fault monitoring device of the numerically-controlled machine tool provided by the invention at least comprises: a data acquisition module 210, a first determination module 220, a second determination module 230, a grouping module 240, and a failure determination module 250.
The data acquisition module 210 is configured to acquire operation state data of a plurality of preset monitoring points of the numerical control machine tool to be monitored in the numerical control machining process, and determine abnormal operation state data in each operation state data;
the abnormal operation state data are operation state data with similarity with preset standard operation state data lower than a preset threshold value;
the first determining module 220 is configured to use machine tool components corresponding to preset monitoring points corresponding to the abnormal operation state data as machine tool components to be detected;
the second determining module 230 is configured to determine the machine tool components to be detected that affect each other according to the first association relationship of each machine tool component to be detected;
the grouping module 240 is configured to take the abnormal operation state data corresponding to the machine tool components to be detected that affect each other as a group, to obtain one or more abnormal data groups;
The fault determination module 250 is configured to determine a predicted machine tool fault component corresponding to the abnormal data set according to the abnormal data set and a trained target fault detection model corresponding to the numerical control machine tool to be monitored.
Fig. 3 illustrates a physical schematic diagram of an electronic device, as shown in fig. 3, where the electronic device may include: processor 310, communication interface (Communications Interface) 320, memory 330 and communication bus 340, wherein processor 310, communication interface 320, memory 330 accomplish communication with each other through communication bus 340. The processor 310 may call logic instructions in the memory 330 to perform a fault monitoring method for a numerically controlled machine tool, the method comprising: acquiring operation state data of a plurality of preset monitoring points of a numerical control machine tool to be monitored in the numerical control machining process, and determining abnormal operation state data in the operation state data; the abnormal operation state data are operation state data with similarity with preset standard operation state data lower than a preset threshold value; taking machine tool components corresponding to preset monitoring points corresponding to the abnormal operation state data as machine tool components to be detected; determining the machine tool parts to be detected which are mutually influenced according to the first association relation of the machine tool parts to be detected; taking the abnormal operation state data corresponding to the machine tool parts to be detected, which are mutually influenced, as a group to obtain one or more abnormal data groups; and determining a predicted machine tool fault component corresponding to the abnormal data set through the abnormal data set and a trained target fault detection model corresponding to the numerical control machine tool to be monitored.
Further, the logic instructions in the memory 330 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 fault monitoring method of the numerical control machine provided by the above methods, and the method includes: acquiring operation state data of a plurality of preset monitoring points of a numerical control machine tool to be monitored in the numerical control machining process, and determining abnormal operation state data in the operation state data; the abnormal operation state data are operation state data with similarity with preset standard operation state data lower than a preset threshold value; taking machine tool components corresponding to preset monitoring points corresponding to the abnormal operation state data as machine tool components to be detected; determining the machine tool parts to be detected which are mutually influenced according to the first association relation of the machine tool parts to be detected; taking the abnormal operation state data corresponding to the machine tool parts to be detected, which are mutually influenced, as a group to obtain one or more abnormal data groups; and determining a predicted machine tool fault component corresponding to the abnormal data set through the abnormal data set and a trained target fault detection model corresponding to the numerical control machine tool to be monitored.
The system and apparatus embodiments described above are merely illustrative, in which the elements illustrated as separate elements may or may not be physically separate, and 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 (7)
1. A fault monitoring method for a numerically-controlled machine tool, the method comprising:
acquiring operation state data of a plurality of preset monitoring points of a numerical control machine tool to be monitored in a numerical control machining process, and determining abnormal operation state data in the operation state data, wherein the abnormal operation state data is operation state data with similarity with preset standard operation state data lower than a preset threshold value;
taking machine tool components corresponding to preset monitoring points corresponding to the abnormal operation state data as machine tool components to be detected;
determining the mutually-influenced machine tool parts to be detected according to the first association relation of the machine tool parts to be detected, wherein the first association relation of the machine tool parts to be detected reflects the machine tool parts mechanically connected with the machine tool parts to be detected;
Taking the abnormal operation state data corresponding to the machine tool parts to be detected, which are mutually influenced, as a group to obtain one or more abnormal data groups;
determining a predicted machine tool fault component corresponding to the abnormal data set through the abnormal data set and a trained target fault detection model corresponding to the numerical control machine tool to be monitored;
the target fault detection model is obtained by the following steps:
acquiring a plurality of source domain training sample sets, wherein each source domain training sample set corresponds to a sample numerical control machine tool of one equipment type;
wherein each source domain training sample set comprises a plurality of source domain training samples; each source domain training sample comprises: a sample abnormal data set and a corresponding machine tool fault component label; each sample abnormal data set consists of a plurality of sample abnormal operation state data, and machine tool parts corresponding to the sample abnormal operation state data in each sample abnormal data set are mutually influenced machine tool parts;
obtaining a predicted machine tool fault component corresponding to the source domain training sample through a sample abnormal data set in the source domain training sample and a preset neural network model;
Adjusting model parameters of the preset neural network model according to the machine tool fault component labels of the source domain training samples and the predicted machine tool fault components, and continuously executing the steps of obtaining predicted machine tool fault components corresponding to the next source domain training samples through a sample abnormal data set in the next source domain training samples and the preset neural network model until the preset neural network model meets a first preset condition to obtain a trained general fault detection model;
acquiring a target domain training sample set, and performing model parameter adjustment on the general fault detection model through each target domain training sample in the target domain training sample set to obtain a target fault detection model corresponding to a target domain;
the target domain training sample set corresponds to a sample numerical control machine tool of a device type, and the number of samples in the target domain training sample set is smaller than that of samples in the source domain training sample set;
before the mutual influence of the machine tool components to be detected is determined according to the first association relation of the machine tool components to be detected, the method further comprises:
acquiring a first association relation of each machine tool part to be detected from a cloud server;
According to the first association relation, determining the machine tool component to be detected with a mechanical connection relation;
taking the machine tool parts to be detected with the mechanical connection relationship as the machine tool parts to be detected which are mutually influenced;
after the target fault detection model corresponding to the target domain is obtained, the method further comprises:
acquiring equipment types corresponding to the target domain training sample set;
generating a second association relationship between the equipment type corresponding to the target domain training sample set and the target fault detection model, and storing the second association relationship to a local area; storing the target fault detection model to a cloud server;
before determining the predicted machine tool fault component corresponding to the abnormal data set through the trained target fault detection model corresponding to the abnormal data set and the numerical control machine tool to be monitored, the method further comprises:
and calling a target fault detection model corresponding to the numerical control machine to be monitored from a cloud server according to the second association relation between the equipment type of the numerical control machine to be monitored and the locally stored equipment type.
2. The fault monitoring method of a numerically controlled machine tool according to claim 1, wherein after said determining the predicted machine tool fault component for which the abnormal data set corresponds, the method further comprises:
Acquiring a three-dimensional diagram of the numerical control machine tool to be monitored, and marking the fault parts of the predictive machine tool on the three-dimensional diagram to obtain a marked three-dimensional diagram;
the marked three-dimensional graph is sent to a user terminal, so that the user terminal displays the marked three-dimensional graph to a machine tool manager corresponding to the user terminal;
receiving user feedback information from the user terminal, and generating an optimized training sample according to the user feedback information of the user terminal and the corresponding abnormal data set;
wherein, the user feedback information includes: whether the predicted machine tool fault component is a fault component or not, and a corresponding real fault component when the predicted machine tool fault component is a non-fault component;
and training and optimizing the target fault detection model according to the optimized training sample to obtain the optimized target fault detection model.
3. The fault monitoring method of a numerically controlled machine tool according to claim 1, wherein after said determining the predicted machine tool fault component for which the abnormal data set corresponds, the method further comprises:
determining the fault grade of the numerical control machine to be monitored according to the predicted machine fault component;
Determining the available time of the predicted machine tool fault component according to the running state data corresponding to the predicted machine tool fault component under the condition that the fault level meets a second preset condition;
acquiring processing task information of the numerical control machine tool to be monitored in a preset time period;
wherein the processing task information includes: workpiece material, workpiece processing time and workpiece processing quantity;
determining maintenance time of the predicted machine tool fault component according to the available time of the predicted machine tool fault component and processing task information;
generating fault prompt information according to the maintenance time and the corresponding predicted machine tool fault component and sending the fault prompt information to a maintenance center so that the maintenance center distributes corresponding maintenance personnel according to the fault prompt information.
4. The fault monitoring method of a numerically controlled machine tool according to claim 1, wherein before using a machine tool component corresponding to a preset monitoring point corresponding to each abnormal operation state data as a machine tool component to be detected, the method further comprises:
according to the equipment type of the numerical control machine to be monitored, acquiring a three-dimensional diagram of the numerical control machine to be monitored from a preset diagram library;
Determining the mechanical connection relation between all the machine tool components in the numerical control machine tool to be monitored according to the three-dimensional graph;
and generating a first association relation of each machine tool part according to the mechanical connection relation, and storing the first association relation to a cloud server.
5. A fault monitoring device for a numerically controlled machine tool, the device comprising:
the data acquisition module is used for acquiring the running state data of a plurality of preset monitoring points of the numerical control machine tool to be monitored in the numerical control machining process and determining abnormal running state data in the running state data, wherein the abnormal running state data is the running state data with the similarity with the preset standard running state data lower than a preset threshold value;
the first determining module is used for taking machine tool components corresponding to preset monitoring points corresponding to the abnormal operation state data as machine tool components to be detected;
the second determining module is used for determining the to-be-detected machine tool parts which are mutually influenced according to the first association relation of the to-be-detected machine tool parts, and the first association relation of the to-be-detected machine tool parts reflects the machine tool parts mechanically connected with the to-be-detected machine tool parts;
the grouping module is used for taking the abnormal operation state data corresponding to the machine tool parts to be detected, which are mutually influenced, as a group to obtain one or more abnormal data groups;
The fault judging module is used for determining a predicted machine tool fault component corresponding to the abnormal data set through the abnormal data set and a trained target fault detection model corresponding to the numerical control machine tool to be monitored;
the target fault detection model is obtained by the following steps:
acquiring a plurality of source domain training sample sets, wherein each source domain training sample set corresponds to a sample numerical control machine tool of one equipment type;
wherein each source domain training sample set comprises a plurality of source domain training samples; each source domain training sample comprises: a sample abnormal data set and a corresponding machine tool fault component label; each sample abnormal data set consists of a plurality of sample abnormal operation state data, and machine tool parts corresponding to the sample abnormal operation state data in each sample abnormal data set are mutually influenced machine tool parts;
obtaining a predicted machine tool fault component corresponding to the source domain training sample through a sample abnormal data set in the source domain training sample and a preset neural network model;
adjusting model parameters of the preset neural network model according to the machine tool fault component labels of the source domain training samples and the predicted machine tool fault components, and continuously executing the steps of obtaining predicted machine tool fault components corresponding to the next source domain training samples through a sample abnormal data set in the next source domain training samples and the preset neural network model until the preset neural network model meets a first preset condition to obtain a trained general fault detection model;
Acquiring a target domain training sample set, and performing model parameter adjustment on the general fault detection model through each target domain training sample in the target domain training sample set to obtain a target fault detection model corresponding to a target domain;
the target domain training sample set corresponds to a sample numerical control machine tool of a device type, and the number of samples in the target domain training sample set is smaller than that of the source domain training samples;
before determining the mutually-affected machine tool parts to be detected according to the first association relation of the machine tool parts to be detected, the method further comprises the following steps:
acquiring a first association relation of each machine tool part to be detected from a cloud server;
according to the first association relation, determining the machine tool component to be detected with a mechanical connection relation;
taking the machine tool parts to be detected with the mechanical connection relationship as the machine tool parts to be detected which are mutually influenced;
after the target fault detection model corresponding to the target domain is obtained, the method further comprises the following steps:
acquiring equipment types corresponding to the target domain training sample set;
generating a second association relationship between the equipment type corresponding to the target domain training sample set and the target fault detection model, and storing the second association relationship to a local area; storing the target fault detection model to a cloud server;
Before determining the predicted machine tool fault component corresponding to the abnormal data set through the trained target fault detection model corresponding to the abnormal data set and the numerical control machine tool to be monitored, the method further comprises:
and calling a target fault detection model corresponding to the numerical control machine to be monitored from a cloud server according to the second association relation between the equipment type of the numerical control machine to be monitored and the locally stored equipment type.
6. 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 fault monitoring method of the numerical control machine of any one of claims 1 to 4 when the program is executed by the processor.
7. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the fault monitoring method of the numerical control machine according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310296718.9A CN116009480B (en) | 2023-03-24 | 2023-03-24 | Fault monitoring method, device and equipment of numerical control machine tool and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310296718.9A CN116009480B (en) | 2023-03-24 | 2023-03-24 | Fault monitoring method, device and equipment of numerical control machine tool and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116009480A CN116009480A (en) | 2023-04-25 |
| CN116009480B true CN116009480B (en) | 2023-06-09 |
Family
ID=86033923
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310296718.9A Active CN116009480B (en) | 2023-03-24 | 2023-03-24 | Fault monitoring method, device and equipment of numerical control machine tool and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116009480B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116502166B (en) * | 2023-04-28 | 2024-02-02 | 天宇正清科技有限公司 | Method, device, equipment and medium for predicting faults of target equipment |
| CN116449770B (en) * | 2023-06-15 | 2023-09-15 | 中科航迈数控软件(深圳)有限公司 | Machining method, device and equipment of numerical control machine tool and computer storage medium |
| CN116820026B (en) * | 2023-07-07 | 2024-09-06 | 中科航迈数控软件(深圳)有限公司 | Numerical control machine tool cluster monitoring method and related equipment |
| CN117092933B (en) * | 2023-07-26 | 2024-04-16 | 天津通信广播集团有限公司 | Rotating machinery control method, apparatus, device and computer readable medium |
| CN117032147B (en) * | 2023-09-19 | 2024-02-09 | 昆山纽杰伦智能机器科技有限公司 | Production line machine tool digital regulation system and method based on artificial intelligence |
| CN117557244B (en) * | 2023-09-27 | 2024-07-02 | 国网江苏省电力有限公司信息通信分公司 | Electric power operation and maintenance warning system based on knowledge graph |
| CN117495338B (en) * | 2023-09-30 | 2024-06-25 | 国网江苏省电力有限公司信息通信分公司 | System fault diagnosis and repair method based on automatic operation and maintenance |
| CN117421679B (en) * | 2023-10-08 | 2024-06-18 | 宁波创基机械股份有限公司 | Injection molding machine period management and control method and device, electronic equipment and storage medium |
| CN117707050B (en) * | 2023-12-25 | 2024-05-07 | 上海滨捷机电有限公司 | Cloud computing-based numerical control machine tool real-time monitoring and data analysis system and method |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105278460B (en) * | 2015-08-03 | 2018-02-09 | 吉林大学 | Numerically-controlled machine tool system assembly reliability evaluation method based on cascading failure analysis |
| CN106406229B (en) * | 2016-12-20 | 2018-04-03 | 吉林大学 | A kind of diagnosing faults of numerical control machine method |
| CN109947086B (en) * | 2019-04-11 | 2020-07-28 | 清华大学 | Mechanical fault migration diagnosis method and system based on counterstudy |
| CN112330060B (en) * | 2020-11-25 | 2024-01-12 | 新奥新智科技有限公司 | Equipment fault prediction method and device, readable storage medium and electronic equipment |
| CN112883569B (en) * | 2021-02-05 | 2022-05-17 | 吉林大学 | Method for analyzing fault propagation diffusion behavior of numerical control machine tool |
| CN112947305B (en) * | 2021-02-05 | 2023-10-20 | 吉林大学 | Reliability evaluation method of numerical control machine tool considering fault correlation |
| CN113128561A (en) * | 2021-03-22 | 2021-07-16 | 南京航空航天大学 | Machine tool bearing fault diagnosis method |
| CN113076834B (en) * | 2021-03-25 | 2022-05-13 | 华中科技大学 | Rotating machine fault information processing method, processing system, processing terminal, and medium |
| CN115542067A (en) * | 2021-06-30 | 2022-12-30 | 华为技术有限公司 | Fault detection method and device |
| CN113723632B (en) * | 2021-08-27 | 2024-03-05 | 北京邮电大学 | Industrial equipment fault diagnosis method based on knowledge graph |
| CN114675597B (en) * | 2022-05-30 | 2022-08-26 | 中科航迈数控软件(深圳)有限公司 | Fault prediction visualization method for numerical control machine tool |
| CN115225460B (en) * | 2022-07-15 | 2023-11-28 | 北京天融信网络安全技术有限公司 | Fault determination method, electronic device, and storage medium |
-
2023
- 2023-03-24 CN CN202310296718.9A patent/CN116009480B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN116009480A (en) | 2023-04-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116009480B (en) | Fault monitoring method, device and equipment of numerical control machine tool and storage medium | |
| JPWO2017090098A1 (en) | Equipment management apparatus and method | |
| WO2006110246A2 (en) | Diagnostic and prognostic method and system | |
| CN111665806A (en) | Blade air film hole machining method and device based on management system and management system | |
| CN111338876B (en) | Decision method, system and storage medium for fault mode and influence analysis | |
| CN115981240B (en) | Method, device, equipment and medium for determining fault cause of numerical control machine tool | |
| CN116184930B (en) | Fault prediction method, device, equipment and storage medium for numerical control machine tool | |
| CN113282000A (en) | Fault diagnosis method and device of data center and dynamic loop monitoring system | |
| CN115147236A (en) | Processing method, processing device and electronic equipment | |
| CN113554324B (en) | Production process withdrawal method, system, equipment and storage medium | |
| CN114418418A (en) | Work order information transfer method, system, equipment and medium based on process conversion ratio | |
| CN116226676B (en) | Machine tool fault prediction model generation method suitable for extreme environment and related equipment | |
| CN113348473B (en) | Management artificial intelligence module installation foundation | |
| CN114341814A (en) | Efficient fault analysis by simulating faults in digital twinning | |
| CN114192583B (en) | Scada platform-based strip steel rolling process quality monitoring method and system | |
| CN116167200A (en) | Service life detection method and device for power distribution cabinet | |
| CN114446027A (en) | Equipment fault alarm method, system, equipment and medium based on Internet of things | |
| CN110716101B (en) | Power line fault positioning method and device, computer and storage medium | |
| CN116820026B (en) | Numerical control machine tool cluster monitoring method and related equipment | |
| CN112379656A (en) | Processing method, device, equipment and medium for detecting abnormal data of industrial system | |
| CN117707050B (en) | Cloud computing-based numerical control machine tool real-time monitoring and data analysis system and method | |
| CN115826503B (en) | Machine tool remote diagnosis method based on industrial internet big data | |
| CN117387925B (en) | Damper performance continuous test method and system | |
| CN116330041B (en) | Fault detection method, device, equipment and medium for numerical control machining transmission device | |
| CN113900865B (en) | Intelligent power grid equipment automatic test method, system and readable storage medium |
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 |