CN111208782A - Data processing method and device for machine tool spindle state prediction - Google Patents
Data processing method and device for machine tool spindle state prediction Download PDFInfo
- Publication number
- CN111208782A CN111208782A CN201911387279.2A CN201911387279A CN111208782A CN 111208782 A CN111208782 A CN 111208782A CN 201911387279 A CN201911387279 A CN 201911387279A CN 111208782 A CN111208782 A CN 111208782A
- Authority
- CN
- China
- Prior art keywords
- machine tool
- current
- mode
- machining
- analyzed
- 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
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
- G05B19/408—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by data handling or data format, e.g. reading, buffering or conversion of data
- G05B19/4083—Adapting programme, configuration
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/35—Nc in input of data, input till input file format
- G05B2219/35356—Data handling
Abstract
The application relates to a data processing method and a data processing device for predicting the state of a main shaft of a machine tool, wherein the data processing method comprises the following steps: acquiring current machining state parameters of a machine tool spindle to be analyzed; acquiring a current processing mode of a machine tool spindle to be analyzed; determining a prediction model corresponding to the current machining mode; and inputting the current machining state parameters into the prediction model to obtain a corresponding fault prediction result. Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages: the method can acquire the real-time processing state of the machine tool spindle to be analyzed according to the processing state parameters of the machine tool spindle to be analyzed when the machine tool spindle to be analyzed starts to work, and can call a corresponding prediction model to predict with strong pertinence according to the processing state of the machine tool spindle to be analyzed, so that the method has the advantage of high prediction accuracy.
Description
Technical Field
The application relates to the field of intelligent manufacturing, in particular to a data processing method and device for predicting the state of a machine tool spindle.
Background
The existing methods adopted for predicting the state of the machine tool spindle include a neural network method, a rough set theory, a least square support vector machine and the like.
In the prior art, when the state of a machine tool main shaft is predicted, the fault prediction method which is applied to the state of the machine tool main shaft is different when different products are processed and when different positions of the same product are processed.
In addition, the existing methods for predicting the state of the spindle of the machine tool basically train a neural network model through parameters, and production state information is not added, so that the parameter information based on prediction is one-sided and incomplete, and the prediction result is not accurate enough.
In view of the technical problems in the related art, no effective solution is provided at present.
Disclosure of Invention
In order to solve the technical problems or at least partially solve the technical problems, the application provides a data processing method and device for predicting the state of a main shaft of a machine tool.
In a first aspect, the present application provides a data processing method for predicting the state of a spindle of a machine tool, comprising:
acquiring current machining state parameters of a machine tool spindle to be analyzed;
acquiring a current processing mode of the machine tool spindle to be analyzed;
determining a prediction model corresponding to the current machining mode;
and inputting the current machining state parameters into the prediction model to obtain a corresponding fault prediction result.
Optionally, as in the foregoing data processing method, the acquiring a current machining mode of a spindle of a machine tool to be analyzed includes:
determining the current machining mode corresponding to the current machining state parameter according to a preset machining state corresponding relationship, wherein the machining state corresponding relationship comprises: and the corresponding relation between the machining state parameters and the machining modes.
Optionally, as in the foregoing data processing method, the determining the current processing mode corresponding to the current processing state parameter according to a preset processing state corresponding relationship includes:
determining a current machining product of the machine tool spindle to be analyzed;
determining the current processing mode corresponding to first information according to a preset processing state corresponding relationship, wherein the first information comprises the current processing state parameters and the current processing product, and the processing state corresponding relationship comprises: and the processing state parameters and the corresponding relation between the processed product and the processing mode.
Optionally, as in the foregoing data processing method, the method for building the prediction model includes:
acquiring training parameters corresponding to a preset processing mode;
and training the neural network model to be trained through the training parameters to obtain a prediction model corresponding to the preset processing mode.
Optionally, as in the foregoing data processing method, the acquiring of the training parameter corresponding to the preset processing mode includes:
acquiring historical machining state parameters of the machine tool spindle to be analyzed;
and determining a training parameter corresponding to the preset machining mode according to the historical machining state parameter corresponding to the preset machining mode.
Alternatively, the data processing method, as described previously,
after obtaining the prediction model corresponding to the preset machining mode, the method further includes:
establishing a corresponding relation between the prediction model and a machining mode;
storing the prediction model into a model database according to the corresponding relation;
determining a prediction model corresponding to the current machining mode, including:
determining a prediction model corresponding to the current machining mode in the model database according to the corresponding relation and the current machining mode;
and calling a prediction model corresponding to the current machining mode from the model database.
Optionally, as in the foregoing data processing method, after obtaining the corresponding failure prediction result, the method further includes:
determining a processing instruction corresponding to the fault prediction result according to a preset fault processing strategy;
sending the processing instruction to the machine tool main shaft to be analyzed, and enabling the machine tool main shaft to be analyzed to execute the processing instruction;
generating corresponding alarm information according to the fault prediction result;
and sending the alarm information to a preset terminal.
In a second aspect, the present application provides a data processing apparatus for predicting the state of a spindle of a machine tool, comprising:
the first acquisition module is used for acquiring the current machining state parameters of the machine tool spindle to be analyzed;
the second acquisition module is used for acquiring the current processing mode of the machine tool spindle to be analyzed;
the determining module is used for determining a prediction model corresponding to the current machining mode;
and the prediction module is used for inputting the current machining state parameters into the prediction model to obtain a corresponding fault prediction result.
In a third aspect, the present application provides an electronic device, comprising: the system comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
the memory is used for storing a computer program;
the processor is configured to implement the processing method according to any one of the preceding claims when executing the computer program.
In a fourth aspect, the present application provides a non-transitory computer-readable storage medium, characterized in that the non-transitory computer-readable storage medium stores computer instructions that cause the computer to perform the processing method according to any one of the preceding claims.
The embodiment of the application provides a data processing method and a data processing device for predicting the state of a machine tool spindle, and the data processing method and the data processing device comprise the following steps: acquiring current machining state parameters of a machine tool spindle to be analyzed; acquiring a current processing mode of a machine tool spindle to be analyzed; determining a prediction model corresponding to the current machining mode; and inputting the current machining state parameters into the prediction model to obtain a corresponding fault prediction result. Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages: the method can acquire the real-time processing state of the machine tool spindle to be analyzed according to the processing state parameters of the machine tool spindle to be analyzed when the machine tool spindle to be analyzed starts to work, and can call a corresponding prediction model to predict with strong pertinence according to the processing state of the machine tool spindle to be analyzed, so that the method has the advantage of high prediction accuracy.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a schematic flowchart of a data processing method for predicting a state of a spindle of a machine tool according to an embodiment of the present disclosure;
fig. 2 is a schematic flow chart of a data processing method for predicting the state of a spindle of a machine tool according to another embodiment of the present disclosure;
fig. 3 is a schematic flow chart of a data processing method for predicting the state of a spindle of a machine tool according to another embodiment of the present disclosure;
fig. 4 is a block diagram of a data processing apparatus for predicting a state of a spindle of a machine tool according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Fig. 1 is a first aspect of an embodiment of the present application, and the present application provides a data processing method for predicting a state of a spindle of a machine tool, including the following steps S1 to S4:
s1, obtaining current machining state parameters of a machine tool spindle to be analyzed;
specifically, because the state parameters of the machine tool are many, the machine tool is difficult to monitor one by one, but in the product processing process, the parameters such as the current, the power, the temperature and the like of the machine tool spindle change obviously, the health state of the machine tool can be well reflected by monitoring the machine tool spindle, and therefore the state of the machine tool spindle is selected to be detected. The main shaft of the machine tool to be analyzed is equipment for processing products; the current machining state parameters can be state parameters of a machine tool spindle to be analyzed, which are acquired in real time in the machining process, within a time period, and optionally, working state information and working parameter data of the machine tool can be acquired in real time through an OPC service (OPC is a currently applied and most widely used data connection standard and is used for communication among controllers, equipment, application programs and other server-based systems without entering a custom driver of data transmission) of a machine tool numerical control system; wherein, the working state information includes: standby, rough grinding wheel trimming, grinding process trimming, automatic tool setting/learning, after-grinding measurement, grinding and other states; the operating parameter data includes: spindle current, power and temperature.
And S2, acquiring the current machining mode of the machine tool spindle to be analyzed.
Specifically, the present application judges the current machining state parameter based on the prediction models corresponding to different machining states, so that the current machining mode is: and the machining mode corresponding to the current machining state parameter. Optionally, the current machining mode may be obtained through manual judgment or through analysis of a system or a program according to the current machining state parameter.
And S3, determining a prediction model corresponding to the current machining mode.
Specifically, each machining mode may correspond to one prediction model, or a plurality of continuously operating machining modes may correspond to one prediction model, and the specific corresponding manner may be adaptively adjusted according to the use or training manner of the prediction model. The matching of the prediction model may be performed by keyword matching, for example, after the current processing mode is obtained, a keyword corresponding to the current processing mode may be determined, for example: grinding; then, according to the keyword 'grinding', matching a prediction model with a name including or equivalent to 'grinding' in a database storing the prediction model; the above description is only an example of obtaining a corresponding prediction model, and is not intended to be a specific limitation of the present application.
And S4, inputting the current machining state parameters into a prediction model to obtain a corresponding fault prediction result.
Specifically, after a prediction model for predicting the current state of the machine tool spindle to be analyzed is determined, the current machining state parameters may be input into the prediction model, optionally, when the current machining state parameters are collected, only the parameters required by the prediction model may be collected, or the prediction model may be selected from the current machining state parameters according to the required parameters. The fault prediction result can be a result obtained by the prediction model according to the current machining state parameters, and the result can be a fault type and/or fault time predicted to have faults; by way of example: the XX controller will fail after 2 minutes.
Therefore, by the method in the embodiment, when the machine tool spindle to be analyzed starts to work, the real-time machining state of the machine tool spindle to be analyzed can be obtained according to the machining state parameters of the machine tool spindle to be analyzed, and the corresponding prediction model can be called to predict with strong pertinence according to the machining state of the machine tool spindle to be analyzed, so that the method has the advantage of high prediction accuracy.
In some embodiments, as in the foregoing data processing method, the step S2 of acquiring the current machining mode of the spindle of the machine tool to be analyzed specifically includes:
determining a current machining mode corresponding to the current machining state parameter through a preset machining state corresponding relationship, wherein the machining state corresponding relationship comprises: and the corresponding relation between the machining state parameters and the machining modes.
Specifically, the processing state correspondence may be stored in a database, and generally, since the processing state parameters may have a plurality of types, a specific storage manner may be as shown in the following table:
| parameter a | Parameter b | Parameter c | Parameter d | Machining mode |
| (10～20) | (20～25) | (20～40) | (35～40) | I |
| (10～20) | (10～15) | (20～25) | II | |
| ...... | ...... | ...... | ...... | ...... |
As shown in the above table, when the machining state parameters a, b, c and d have specific values, which are 10, 20, 30 and 40 respectively, the corresponding machining mode is I; when the machining state parameters a, b and c have specific values, respectively 15, 13 and 20, the machining state parameter d has no specific value; the corresponding processing mode is obtained as II.
The above example content is only an example for implementing the present embodiment to obtain the current machining mode packet of the machine tool spindle to be analyzed, and is not intended to be a specific limitation of the present application.
Therefore, by the method in the embodiment, the corresponding processing mode can be automatically analyzed and obtained without manually judging the processing mode, so that the configuration of related personnel can be further reduced, the labor cost is reduced, and the efficiency is improved.
As shown in fig. 2, in some embodiments, the data processing method determines the current processing mode corresponding to the current processing state parameter according to the preset processing state correspondence relationship, including the following steps P1 and P2:
and P1, determining the current machining product of the main shaft of the machine tool to be analyzed.
Specifically, the currently processed product is the type of the processed product corresponding to the current processing state parameter; since the same processing flow may exist when different products are processed, but the set parameters, the operating parameters and the like of the machine tool may change along with the change of the products in the specific processing process, the classification of the processing modes can be further refined by determining the current processed product, and then different analysis models with stronger pertinence are obtained, so as to obtain a more accurate analysis result.
Step P2, determining a current processing mode corresponding to first information through a preset processing state corresponding relation, wherein the first information comprises current processing state parameters and a current processing product, and the processing state corresponding relation comprises the following steps: and the processing state parameters and the corresponding relation between the processed product and the processing mode.
Specifically, the processing state parameters corresponding to different processing modes are different from the processed product, for example: the working state of the gear grinding machine is divided into standby state, rough grinding wheel trimming, grinding process trimming, automatic tool setting/automatic tool setting learning, after-grinding measurement, grinding and other states.
The method in this embodiment may be implemented by adding the processed product as a matching factor on the basis of the example given in step a1, and further matching to obtain the processing states corresponding to different processed products in different working states; therefore, the purpose of determining the current machining mode corresponding to the first information through the preset machining state corresponding relation can be achieved.
For example, machine spindle current, power, and temperature typically vary between different products. Carrying out one-to-one correspondence between the processed product and the working mode, for example, when the processed product processed by the main shaft of the machine tool to be analyzed has a product A and a product B; the processing state may include: product A + standby (namely, the corresponding processed product is product A, and the processing state parameter corresponds to the parameter of the standby state), product A + rough grinding wheel, product A + grinding process trimming, product A + automatic tool setting, product A + after-grinding measurement, and product A + grinding; b product + standby, B product + rough grinding wheel, B product + grinding process finishing, B product + automatic tool setting, B product + after-grinding measurement, B product + grinding. As can be seen from the above, the naming mode of the processing mode may be named by product name + operating state.
By the method in the embodiment, the accurate machining state can be obtained through the machine tool spindle machining product to be analyzed, and then the corresponding prediction model with stronger pertinence can be called for fault prediction, so that better accuracy can be obtained.
As shown in fig. 3, in some embodiments, as the aforementioned data processing method, the method for establishing the prediction model includes the following steps T1 and T2:
and T1, acquiring training parameters corresponding to the preset processing mode.
Specifically, the preset processing mode is as follows: the complete processing flow of a certain processing product is divided into one or more processing modes. The training parameters corresponding to different preset processing modes are different. For example: in the standby state, the corresponding training parameters may include: machine tool spindle current and temperature; in the grinding state, the corresponding training parameters may include: machine tool spindle current, power and temperature; furthermore, the difference of the training parameters in different states is not only reflected in different categories, but also the specific parameters have different values; when the preset processing mode is further added with a processed product factor, the situation that the training parameter types are the same but the numerical values of specific training parameters are different also exists.
And T2, training the neural network model to be trained through the training parameters to obtain a prediction model corresponding to the preset processing mode.
Specifically, the neural network model may be an LSTM neural network (Long Short-Term Memory network). For example, the specific training method may include:
1) each time 20 sets of data were entered (optionally, one set of data was collected per second), each set of data comprising 2 parameters (e.g.: current and voltage) and then from the data a 2 x 20 matrix is obtained;
2) inputting the matrix into a first layer of LSTM in the LSTM network, and mapping to 128 LSTM neurons in the first layer of LSTM network; then mapping the processed data to 64 neurons in a second LSTM layer after being weighted by a coefficient and the like, and inputting the processed data to a dense layer (one of all-connected layers);
3) the output of the dense layer is shrunk to 10, optionally, the output data can be one of the original parameters, for example, only the data of the current parameter is output, that is, the current value of the next 10 seconds is predicted, the current trend of the next 10 seconds can be obtained, and then the network parameter is adjusted according to the current trend in the actual production.
Furthermore, after the model obtained by training in the embodiment is obtained, the trend of a certain parameter in a certain time period in the future is predicted through the model, and then the time point when the parameter is abnormal is judged according to the normal interval of the parameter.
In some embodiments, as in the foregoing data processing method, the step T1 of obtaining the training parameters corresponding to the preset processing mode includes the following steps T11 and T12:
t11, acquiring historical machining state parameters of the machine tool spindle to be analyzed;
optionally, the working state data, the working parameter data, and the like of the machine tool spindle to be analyzed can be acquired through OPC service of the machine tool numerical control system.
And T12, determining a training parameter corresponding to the preset machining mode according to the historical machining state parameter corresponding to the preset machining mode.
Specifically, the complete processing flow is divided according to the selection to obtain a plurality of preset processing modes; then determining historical processing state parameters corresponding to each preset processing mode, namely dividing the historical processing state parameters into different data sets according to different preset processing modes; so as to be used in the later training.
In some embodiments, a data processing method, such as the aforementioned data processing method,
after the step T2 obtains the prediction model corresponding to the preset machining mode, the method further includes the following steps T3 and T4:
and T3, establishing a corresponding relation between the prediction model and the machining mode.
Specifically, the correspondence may be implemented by setting a keyword corresponding to the name of the machining mode for each prediction model; the prediction models corresponding to the respective machining modes can be further obtained by matching the keyword.
And T4, storing the prediction model into a model database according to the corresponding relation.
Specifically, in addition to step T3, since the keyword and the storage location of each prediction model are stored in the form of a data table during storage, the storage location of a prediction model can be obtained after matching a keyword with a prediction model, and the corresponding prediction model can be retrieved from the model database according to the machining mode during use.
The step S3 determines a prediction model corresponding to the current machining mode, including the steps S31 and S32 as follows:
and S31, determining a prediction model corresponding to the current machining mode in the model database according to the corresponding relation and the current machining mode.
And S32, calling a prediction model corresponding to the current machining mode from the model database.
Based on steps T21 and T22, the keyword of the current machining mode may be determined, then the storage location corresponding to the keyword of the current machining mode is obtained in the data table according to the matching relationship, and finally the prediction model corresponding to the current machining mode may be retrieved from the model database according to the storage location.
In some embodiments, the data processing method as described above further includes the following steps S51 to S54 after obtaining the corresponding failure prediction result:
and S51, determining a processing instruction corresponding to the fault prediction result according to a preset fault processing strategy.
And S52, sending the processing instruction to the machine tool main shaft to be analyzed to enable the machine tool main shaft to be analyzed to execute the processing instruction.
Specifically, the fault handling policy includes: the corresponding relation between the failure prediction result and the candidate processing instruction; generally, different fault prediction results and candidate processing instructions are different from each other, and the candidate processing instructions are suitable for predicting faults obtained by the fault prediction results which can be avoided through software system control; and when the fault prediction result is matched with the candidate processing instruction according to the preset fault processing strategy, taking the candidate processing instruction as the processing instruction. And then sending the command to the machine tool spindle to be analyzed, wherein the processing command is generally executed by a control system of the machine tool spindle to be analyzed, so as to achieve the purpose of controlling the operation of each controllable component in the machine tool spindle to be analyzed, and avoid the predicted fault.
And S53, generating corresponding alarm information according to the fault prediction result.
And S54, sending the alarm information to a preset terminal.
Specifically, after the failure prediction result is obtained, the failure type and/or the failure time at which the failure is expected to occur may be obtained, and thus the alarm information may also include the failure type and/or the failure time. The preset terminal can be a control system of a main shaft of the machine tool to be analyzed, and can also be terminal equipment of a manager (such as a computer or an intelligent mobile terminal), so that the control system can send an alarm or the manager can know a fault expected to occur in advance. And related personnel can maintain the main shaft of the machine tool to be analyzed in time, so that faults are avoided.
As shown in fig. 4, according to another aspect of the present application, there is provided a data processing apparatus for predicting a state of a spindle of a machine tool, comprising:
the first acquisition module 1 is used for acquiring the current machining state parameters of the machine tool spindle to be analyzed;
the second obtaining module 2 is used for obtaining the current processing mode of the machine tool spindle to be analyzed;
the determining module 3 is used for determining a prediction model corresponding to the current machining mode;
and the prediction module 4 is used for inputting the current machining state parameters into the prediction model to obtain a corresponding fault prediction result.
Specifically, the specific process of implementing the functions of each module in the apparatus according to the embodiment of the present invention may refer to the related description in the method embodiment, and is not described herein again.
According to another embodiment of the present application, there is also provided an electronic apparatus including: as shown in fig. 5, the electronic device may include: the system comprises a processor 1501, a communication interface 1502, a memory 1503 and a communication bus 1504, wherein the processor 1501, the communication interface 1502 and the memory 1503 complete communication with each other through the communication bus 1504.
A memory 1503 for storing a computer program;
the processor 1501 is configured to implement the steps of the above-described method embodiments when executing the program stored in the memory 1503.
The bus mentioned in the electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The communication interface is used for communication between the electronic equipment and other equipment.
The Memory may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.
The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
Embodiments of the present application also provide a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the steps of the above-described method embodiments.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The foregoing are merely exemplary embodiments of the present invention, which enable those skilled in the art to understand or practice the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A data processing method for predicting the state of a spindle of a machine tool, comprising:
acquiring current machining state parameters of a machine tool spindle to be analyzed;
acquiring a current processing mode of the machine tool spindle to be analyzed;
determining a prediction model corresponding to the current machining mode;
and inputting the current machining state parameters into the prediction model to obtain a corresponding fault prediction result.
2. The data processing method according to claim 1, wherein said obtaining a current machining mode of a machine tool spindle to be analyzed comprises:
determining the current machining mode corresponding to the current machining state parameter according to a preset machining state corresponding relationship, wherein the machining state corresponding relationship comprises: and the corresponding relation between the machining state parameters and the machining modes.
3. The data processing method according to claim 2, wherein the determining the current machining mode corresponding to the current machining state parameter according to a preset machining state correspondence relationship includes:
determining a current machining product of the machine tool spindle to be analyzed;
determining the current processing mode corresponding to first information according to a preset processing state corresponding relationship, wherein the first information comprises the current processing state parameters and the current processing product, and the processing state corresponding relationship comprises: and the processing state parameters and the corresponding relation between the processed product and the processing mode.
4. The data processing method of claim 1, wherein the predictive model is built by:
acquiring training parameters corresponding to a preset processing mode;
and training the neural network model to be trained through the training parameters to obtain a prediction model corresponding to the preset processing mode.
5. The data processing method according to claim 4, wherein the obtaining of the training parameters corresponding to the preset machining mode comprises:
acquiring historical machining state parameters of the machine tool spindle to be analyzed;
and determining a training parameter corresponding to the preset machining mode according to the historical machining state parameter corresponding to the preset machining mode.
6. The data processing method of claim 4,
after obtaining the prediction model corresponding to the preset machining mode, the method further includes:
establishing a corresponding relation between the prediction model and a machining mode;
storing the prediction model into a model database according to the corresponding relation;
determining a prediction model corresponding to the current machining mode, including:
determining a prediction model corresponding to the current machining mode in the model database according to the corresponding relation and the current machining mode;
and calling a prediction model corresponding to the current machining mode from the model database.
7. The data processing method of claim 6, further comprising, after obtaining the corresponding failure prediction result:
determining a processing instruction corresponding to the fault prediction result according to a preset fault processing strategy;
sending the processing instruction to the machine tool main shaft to be analyzed, and enabling the machine tool main shaft to be analyzed to execute the processing instruction;
generating corresponding alarm information according to the fault prediction result;
and sending the alarm information to a preset terminal.
8. A data processing apparatus for machine tool spindle state prediction, comprising:
the first acquisition module is used for acquiring the current machining state parameters of the machine tool spindle to be analyzed;
the second acquisition module is used for acquiring the current processing mode of the machine tool spindle to be analyzed;
the determining module is used for determining a prediction model corresponding to the current machining mode;
and the prediction module is used for inputting the current machining state parameters into the prediction model to obtain a corresponding fault prediction result.
9. An electronic device, comprising: the system comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;
the memory is used for storing a computer program;
the processor, when executing the computer program, implementing the processing method of any one of claims 1-7.
10. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the processing method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911387279.2A CN111208782B (en) | 2019-12-26 | 2019-12-26 | Data processing method and device for machine tool spindle state prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911387279.2A CN111208782B (en) | 2019-12-26 | 2019-12-26 | Data processing method and device for machine tool spindle state prediction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111208782A true CN111208782A (en) | 2020-05-29 |
| CN111208782B CN111208782B (en) | 2021-06-22 |
Family
ID=70784358
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911387279.2A Active CN111208782B (en) | 2019-12-26 | 2019-12-26 | Data processing method and device for machine tool spindle state prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111208782B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111966045A (en) * | 2020-07-08 | 2020-11-20 | 航天科工深圳（集团）有限公司 | Machine tool crash monitoring method and device, terminal equipment and storage medium |
| CN112099438A (en) * | 2020-09-14 | 2020-12-18 | 南京简睿捷软件开发有限公司 | Machine tool energy-saving control method and device based on current signals |
| CN112486096A (en) * | 2020-12-09 | 2021-03-12 | 中国兵器装备集团自动化研究所 | Machine tool operation state monitoring method |
| CN113359610A (en) * | 2021-07-01 | 2021-09-07 | 中国工程物理研究院激光聚变研究中心 | Method, device, system and medium for monitoring state of ultraprecise diamond fly-cutting machine tool |
| CN116339239A (en) * | 2023-05-26 | 2023-06-27 | 中科航迈数控软件(深圳)有限公司 | Numerical control machine tool cooperative control method, device, equipment and computer storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102426623A (en) * | 2011-12-08 | 2012-04-25 | 河海大学 | Automatic failure fitting modeling method for power load modeling |
| CN103473407A (en) * | 2013-09-04 | 2013-12-25 | 重庆大学 | Machine tool equipment service capability modeling method in cloud manufacturing environment |
| CN105528504A (en) * | 2016-03-01 | 2016-04-27 | 哈尔滨理工大学 | Rolling bearing health condition evaluation method based on CFOA-MKHSVM |
| JP6087262B2 (en) * | 2013-11-27 | 2017-03-01 | 三菱電機株式会社 | Numerical controller |
| CN106484960A (en) * | 2016-09-20 | 2017-03-08 | 江苏科技大学 | A kind of suppression diesel engine closes the process parameter optimizing method of keyhole system machining deformation |
| CN106503350A (en) * | 2016-10-25 | 2017-03-15 | 北京航空航天大学 | A kind of spiral bevel gear long-life based on grinding and heat treatment is driven the method for designing of fatigue reliability |
| CN106527177A (en) * | 2016-10-26 | 2017-03-22 | 北京控制工程研究所 | Multi-functional and one-stop type remote control design, the simulation system and method thereof |
| JP6234187B2 (en) * | 2013-11-27 | 2017-11-22 | 三菱電機株式会社 | Numerical controller |
| CN108007464A (en) * | 2017-12-04 | 2018-05-08 | 国网山东省电力公司电力科学研究院 | Ultra-high-tension power transmission line inspection robot autonomous navigation method and system |
| CN108596341A (en) * | 2018-04-19 | 2018-09-28 | 中国电子科技集团公司第五十四研究所 | A kind of method for diagnosing faults based on expert system |
| CN110243297A (en) * | 2019-06-13 | 2019-09-17 | 上海交通大学 | Pipe screw thread central diameter measurement modification method, system and medium based on image measurement |
-
2019
- 2019-12-26 CN CN201911387279.2A patent/CN111208782B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102426623A (en) * | 2011-12-08 | 2012-04-25 | 河海大学 | Automatic failure fitting modeling method for power load modeling |
| CN103473407A (en) * | 2013-09-04 | 2013-12-25 | 重庆大学 | Machine tool equipment service capability modeling method in cloud manufacturing environment |
| JP6087262B2 (en) * | 2013-11-27 | 2017-03-01 | 三菱電機株式会社 | Numerical controller |
| JP6234187B2 (en) * | 2013-11-27 | 2017-11-22 | 三菱電機株式会社 | Numerical controller |
| CN105528504A (en) * | 2016-03-01 | 2016-04-27 | 哈尔滨理工大学 | Rolling bearing health condition evaluation method based on CFOA-MKHSVM |
| CN106484960A (en) * | 2016-09-20 | 2017-03-08 | 江苏科技大学 | A kind of suppression diesel engine closes the process parameter optimizing method of keyhole system machining deformation |
| CN106503350A (en) * | 2016-10-25 | 2017-03-15 | 北京航空航天大学 | A kind of spiral bevel gear long-life based on grinding and heat treatment is driven the method for designing of fatigue reliability |
| CN106527177A (en) * | 2016-10-26 | 2017-03-22 | 北京控制工程研究所 | Multi-functional and one-stop type remote control design, the simulation system and method thereof |
| CN108007464A (en) * | 2017-12-04 | 2018-05-08 | 国网山东省电力公司电力科学研究院 | Ultra-high-tension power transmission line inspection robot autonomous navigation method and system |
| CN108596341A (en) * | 2018-04-19 | 2018-09-28 | 中国电子科技集团公司第五十四研究所 | A kind of method for diagnosing faults based on expert system |
| CN110243297A (en) * | 2019-06-13 | 2019-09-17 | 上海交通大学 | Pipe screw thread central diameter measurement modification method, system and medium based on image measurement |
Non-Patent Citations (1)
| Title |
|---|
| 柴运东: "《高硬度涂层球面精密磨削加工参数优化技术研究》", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111966045A (en) * | 2020-07-08 | 2020-11-20 | 航天科工深圳（集团）有限公司 | Machine tool crash monitoring method and device, terminal equipment and storage medium |
| CN112099438A (en) * | 2020-09-14 | 2020-12-18 | 南京简睿捷软件开发有限公司 | Machine tool energy-saving control method and device based on current signals |
| CN112099438B (en) * | 2020-09-14 | 2021-10-29 | 南京简睿捷软件开发有限公司 | Machine tool energy-saving control method and device based on current signals |
| CN112486096A (en) * | 2020-12-09 | 2021-03-12 | 中国兵器装备集团自动化研究所 | Machine tool operation state monitoring method |
| CN113359610A (en) * | 2021-07-01 | 2021-09-07 | 中国工程物理研究院激光聚变研究中心 | Method, device, system and medium for monitoring state of ultraprecise diamond fly-cutting machine tool |
| CN116339239A (en) * | 2023-05-26 | 2023-06-27 | 中科航迈数控软件(深圳)有限公司 | Numerical control machine tool cooperative control method, device, equipment and computer storage medium |
| CN116339239B (en) * | 2023-05-26 | 2023-08-11 | 中科航迈数控软件(深圳)有限公司 | Numerical control machine tool cooperative control method, device, equipment and computer storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111208782B (en) | 2021-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111208782B (en) | Data processing method and device for machine tool spindle state prediction | |
| CN107305370B (en) | Production system for setting determination value of variable related to abnormality of product | |
| DE102016015017A1 (en) | Control device with learning function for detecting a cause of noise | |
| CN111861050A (en) | Apparatus and method for managing and controlling manufacturing process and computer readable storage medium | |
| US20190033839A1 (en) | Machining equipment system and manufacturing system | |
| KR20110115168A (en) | Use of prediction data in monitoring actual production targets | |
| CN111414999B (en) | Method and device for monitoring running state of equipment | |
| CN116009480A (en) | Fault monitoring method, device and equipment of numerical control machine tool and storage medium | |
| EP3405844B1 (en) | Methods and systems for root cause analysis for assembly lines using path tracking | |
| WO2023065584A1 (en) | Method and apparatus for determining remaining service life of device, and electronic device | |
| DE102019134312A1 (en) | SYSTEMS, METHODS AND DEVICES FOR IMPROVING PROCESS CONTROL WITH A VIRTUAL ASSISTANT | |
| CN113868953B (en) | Multi-unit operation optimization method, device and system in industrial system and storage medium | |
| CN108388237B (en) | Fault diagnosis method, device, equipment and medium for discrete manufacturing equipment | |
| CN115609112A (en) | Welding parameter determination method, device and medium thereof | |
| CN109409780B (en) | Change processing method, device, computer equipment and storage medium | |
| CN116448234A (en) | Power transformer running state voiceprint monitoring method and system | |
| CN114192583B (en) | Scada platform-based strip steel rolling process quality monitoring method and system | |
| CN115618746A (en) | Intelligent equipment diagnosis and analysis method and system based on cloud service | |
| CN113492583B (en) | Prediction of waste pages | |
| US20240094717A1 (en) | Method for a model-based determination of model parameters | |
| CN115046287B (en) | Equipment interaction control method, device and system, air conditioner and storage medium | |
| CN111866924B (en) | Performance index monitoring method and device, computing equipment and computer storage medium | |
| US11543813B2 (en) | Method and control system for controlling a real production process | |
| CN103942615A (en) | Noisy point removing method | |
| CN116594349B (en) | Machine tool prediction method, machine tool prediction device, terminal equipment and computer 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 |