Operation recommendation method for machining equipment, numerical control system and machining equipment

Abstract

The invention provides an operation recommendation method for machining equipment, a numerical control system, the machining equipment and a computer program product. At least a next step of operation is recommended by a trained recommendation model based on the current operation situation data by obtaining the current operation situation data. The problems that an existing numerical control system is not intelligent enough in operation, low in operation efficiency and incapable of well meeting the requirements of users are solved, and the operation efficiency and the satisfaction degree of machining are improved.

Description

Technical Field

[0001] The present application relates to the field of machining, and in particular to an operation recommendation method for machining equipment, a numerical control system, machining equipment and a computer program product. Background Art

[0002] Computer Numerical Control (CNC) plays an important role in modern manufacturing. Its performance and reliability directly affect production efficiency and product quality. In order to improve the usability and operation efficiency of CNC systems, the design of user interfaces and the optimization of operation processes are crucial. Existing CNC systems are often not intelligent enough, have low operating efficiency, and cannot adapt well to user needs.

[0003] To address the above problems, no effective solution has been proposed yet. Summary of the invention

[0004] In view of this, the present application proposes an operation recommendation method for machining equipment, a numerical control system, machining equipment and a computer program product. By obtaining current operation scenario data, a trained recommendation model is used to recommend at least the next operation based on the current operation scenario data to solve the above-mentioned problem.

[0005] According to one aspect of the present application, there is provided an operation recommendation method for machining equipment, comprising:

[0006] Obtain current operating situation data of machining equipment;

[0007] Based on the current operation context data, a trained recommendation model recommends at least the next operation.

[0008] Optionally, it also includes:

[0009] Collect historical operation situation data of machining equipment;

[0010] The recommendation model is trained by using the historical operation context data.

[0011] Optionally, where:

[0012] The operation context data includes: user operation behavior data and state data of the machining equipment corresponding to the operation behavior.

[0013] Optionally, the user operation behavior data includes at least one of the following: operation time, operation steps, operation parameters, and processing parameters.

[0014] The state data of the machining equipment includes at least one of the following: spindle speed, tool coordinates, and workpiece coordinates.

[0015] Optionally, wherein

[0016] Training the recommendation model by using the historical operation context data includes:

[0017] Train a recommendation model for each user based on each user's historical operation context data;

[0018] The trained recommendation model recommends at least one next action, including:

[0019] At least a next action is recommended based on the current user identity by a recommendation model attributed to the current user identity.

[0020] Optionally, where:

[0021] Training the recommendation model by using the historical operation context data includes:

[0022] Train a general recommendation model through historical operation context data of multiple users;

[0023] The trained recommendation model recommends at least one next action, including:

[0024] In response to identifying that the current user is a new user,

[0025] At least a next operation is recommended by the general recommendation model.

[0026] Optionally, it also includes:

[0027] Collect user feedback on recommendation results, and optimize the recommendation model based on the feedback.

[0028] Optionally, where:

[0029] The recommendation model further includes recommending processing parameters associated with the at least next operation.

[0030] Optionally, it also includes:

[0031] The recommended results are presented in the display interface of the machining equipment.

[0032] According to another aspect of the present application, a numerical control system is provided, comprising a processor and a memory, wherein the memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions, and the program / instructions implement the above method when executed by the processor.

[0033] According to yet another aspect of the present application, there is provided a machining device, comprising a machining body and the numerical control system as described above.

[0034] According to another aspect of the present application, a computer program product is provided, comprising a computer program / instruction, and the above method is implemented when the computer program / instruction in the computer program product is executed by a processor.

[0035] According to the present application, an operation recommendation method for machining equipment, a numerical control system, machining equipment and a computer program product are proposed. By obtaining the current operation scenario data, a trained recommendation model recommends at least the next operation based on the current operation scenario data. The problem that the current numerical control system operation is not intelligent enough, the operation efficiency is low, and it cannot adapt well to the needs of users is solved, and the operation efficiency and satisfaction of machining are improved.

[0036] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application and implement it according to the contents of the specification, the following is a detailed description of the preferred embodiments of the present application in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:

[0038] Figure 1 A schematic diagram showing an embodiment of a recommended operation method for machining equipment according to the present application.

[0039] Figure 2 A schematic diagram of an embodiment of an intelligent recommendation process for machining equipment of the present application is shown.

[0040] Figure 3 It is a schematic diagram of an embodiment of a structural block diagram of a numerical control system of the present application. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0042] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0043] CNC is a technology that uses computer programs to control machine tools and other machining equipment for precise machining. Machining is the process of changing the size or performance of a workpiece through mechanical equipment. Traditional machining equipment such as machine tools require manual operation to control the relative movement of the tool and the workpiece, while CNC machining equipment automates the machining process through pre-written program instructions.

[0044] Figure 1 A schematic diagram showing an embodiment of a recommended operation method for machining equipment according to the present application.

[0045] As shown in the figure, the method includes:

[0046] Step S1, obtaining current operation situation data of machining equipment.

[0047] Step S2, based on the current operation context data, the trained recommendation model recommends at least the next operation.

[0048] Next, taking the machining equipment as a machine tool as an example, the specific process of the above steps is introduced.

[0049] In step S1, various sensors are arranged on or around the machine tool to obtain the current operation context data of the operator (user). The operation context data includes user operation behavior data and state data of machining equipment such as a machine tool corresponding to the operation behavior. The sensor may include at least one of a visual sensor, a position sensor, an acceleration sensor, a force sensor, a current sensor, etc. A visual sensor, such as an industrial camera, can be installed at an appropriate position of the machine tool to perform real-time shooting and image acquisition of the machining process, and can be particularly used to obtain user operation behavior data (of course, it is not limited to using a visual sensor to obtain user operation behavior data), for example, including at least one of operation time, operation steps (such as in the tool setting task, the operation steps include: 1. hand wheel operation; 2. spindle forward rotation; 3. workpiece coordinate system setting, etc.), operation parameters, and processing parameters. Position sensors, current sensors, etc. can detect machine tool axis position, axis load, axis acceleration, etc. to reflect the state of machining equipment such as a machine tool, such as spindle forward / reverse speed, coordinate data, etc. The state data of the machine tool includes the corresponding actions made by the machine tool in response to the above-mentioned operation behavior of the user and the corresponding state reached, such as coordinate state adjustment, etc.

[0050] The current operation context data obtained is not limited to data associated with only one current operation behavior, and may be data associated with several current operation behaviors, such as several operation behaviors within a predetermined time period, or data associated with several operation behaviors that are performed continuously and are associated with the current processing task (for example, the current processing task is: tool setting task, and the several operation behaviors that are performed continuously are: handwheel operation, spindle forward rotation, first round operation again, etc., and the current operation context data obtained is shown in Table 1)

[0051]

[0052] Table 1

[0053] In step S2, in order to recommend at least the next operation, it is necessary to obtain a recommendation model in advance. This can be done by collecting historical operation scenario data of machining equipment such as machine tools in advance; then these historical operation scenario data are used as samples and input into the artificial intelligence model for training to obtain the recommendation model.

[0054] As mentioned above, the content contained in the operation context data has been described. The historical operation context data is also a kind of operation context data, so it meets the same definition and contains the same content. Unlike the current operation context data, the time source of the historical operation context data is different. One is the current operation and the other is the historical operation. In most cases, the historical operation context data should have collected the complete operation steps and corresponding data of at least one processing task. For example, for the tool setting task, it includes three complete operation steps: handwheel operation, spindle forward rotation, and workpiece coordinate system setting. Then, in the historical operation context data, it is highly likely that these three complete operation steps and their corresponding data have been collected, while in the current operation context data, the current operation may not have reached the step of workpiece coordinate system setting. Therefore, the operation steps collected in the current operation context data only include handwheel operation and spindle forward rotation, and do not include the step of workpiece coordinate system setting. Of course, it can be understood that as the user's operation proceeds, the operation steps are also a changing process, and the current operation context data will also change accordingly. In addition, the historical operation context data can come from this machine tool, or from other machine tools, or even be obtained through purchase.

[0055] The artificial intelligence model in this step uses a deep neural network (such as RNN) to model the user operation behavior data, and the collected user operation behavior data and machine tool status data are input into the model as training set data for training, so as to train a recommendation model that can recommend at least the next operation. For example, based on the handwheel operation and spindle forward rotation of the tool setting step included in the currently obtained operation scenario data, the recommendation model of this application can recommend the next step as: workpiece coordinate system setting. Of course, the recommended steps may not be limited to one step, but may also be, for example, more than two steps.

[0056] In the case of a factory, a machining equipment such as a machine tool usually has more than one operator user. In order to better adapt to each user and provide personalized recommendations, the present application also proposes to train a recommendation model for each user based on the historical operation context data of each user, and then identify the current user identity before or after obtaining the current operation context data (for example, through the logged-in account information, or through face recognition, but not limited to this), and then recommend at least the next operation based on the current user identity by the recommendation model belonging to the current user identity. Of course, if the current user is identified as a new user, when the new user does not have his own recommendation model, a general recommendation model can be used to recommend at least the next operation. The general recommendation model is, for example, a general recommendation model trained by historical operation context data of multiple users of this machine tool and / or other machine tools.

[0057] Optionally, user feedback on the recommendation results can also be collected, and the recommendation model can be adjusted and optimized based on the feedback. That is, the user feedback on the recommendation results, such as rejection, or performing an operation different from the recommended operation, or adjusting the recommended operation, the data generated by these operation behaviors will be used as new training data to further train the recommendation model to optimize the recommendation model.

[0058] Optionally, the recommendation model further includes recommending processing parameters related to the at least next operation. The training data used to train the recommendation model may include operation parameters and processing parameters, and therefore, the recommendation result of the recommendation model may also include processing parameters related to the at least next operation to further improve machining efficiency.

[0059] In one embodiment, the recommendation results given by the recommendation model are presented in the display interface of the machining equipment so that the operator user can understand the recommendation situation. Optionally, the user can also provide feedback on the recommendation results through the display interface or manual operation, and the feedback includes acceptance and / or adjustment.

[0060] Figure 2 A schematic diagram of an embodiment of an intelligent recommendation process for machining equipment of the present application is shown.

[0061] The following describes the illustrated steps using a machine tool as an example.

[0062] Step S201, user behavior data (i.e. user operation behavior data) and machine tool status data collection:

[0063] Through embedded sensors and log records, the user's behavior data and machine status data when operating CNC machine tools are collected, including operation time, operation steps, operation parameters, processing parameters, machine status, etc.

[0064] For example, when setting the tool, the user's operating steps (1, handwheel operation 2, spindle forward rotation, etc.) and the corresponding machine tool status (machine tool speed, coordinates, etc.) are collected.

[0065] Step S202: The user clicks to enter the smart recommendation interface.

[0066] Step S203: the neural network model predicts the next operation.

[0067] The implementation of this step depends on the prior user behavior analysis and recommendation model training:

[0068] Use deep neural networks (such as RNN) to model user behavior data, and use the collected user behavior data and machine tool status data as training set data input.

[0069] For example, certain operation steps and machine tool states often appear together. For example, in a tool setting task, the three operation steps of handwheel operation, spindle forward rotation, and workpiece coordinate system setting and the state of the spindle approaching the worktable often appear together. Therefore, these operations and machine tool states can be associated with the workpiece coordinate system setting operation in the tool setting task.

[0070] The training set data input format is shown in Table 2, including operation time, operation steps, operation parameters, processing parameters, machine tool status, etc., and some specific operations are used as work task boundaries such as "workpiece coordinate system setting":

[0071]

[0072] Table 2

[0073] Intelligent recommendation generation:

[0074] Based on user behavior analysis, a personalized model of user behavior can be derived, as well as real-time user behavior data and machine status data, to generate personalized intelligent recommendations and predict the next operation.

[0075] Step S204, generating the relevant text of the next operation according to the numerical control help document, and step S205, setting the production recommended parameter settings according to the commonly used next operation parameters.

[0076] For example, when the user completes tool setting and opens the NC file (CNC program file), click to enter the intelligent recommendation interface, and the system will analyze the most likely next operation, such as machining parameter settings. The system reads the relevant information about this operation in the help document (not limited to this, the recommendation model can also predict whether it is necessary to configure the machining parameters corresponding to the predicted next operation based on historical machining data). If machining parameters are involved, the system will also recommend machining parameters related to the next operation based on historical machining parameters, and finally generate intelligent recommendation results and present them in the interface.

[0077] Step S206: Render and display the intelligent recommendation results. For example, through the intelligent recommendation interface of the numerical control system, the recommended content is displayed in real time to help the user complete the operation quickly.

[0078] Step S207: the user evaluates the recommendation result.

[0079] Provide a real-time feedback mechanism to allow users to evaluate and provide feedback on recommendation results.

[0080] For example, users can rate the accuracy of recommended operation steps in the smart recommendation interface, and the system will adjust the recommendation algorithm based on the score.

[0081] Step S208, further optimizing the neural network model based on the evaluation.

[0082] Record user feedback data for further training and optimization of the recommendation model.

[0083] About user personalization settings:

[0084] Each user has his or her own recommendation model. For each new user, a general recommendation model can be provided, for example, based on test data collected or purchased during the development process. Subsequent models will be continuously optimized based on user behavior analysis and real-time feedback adjustments, and ultimately generate a personalized recommendation model for each user.

[0085] Allow users to customize recommended content and display methods according to their needs and habits.

[0086] For example, the user can choose to display recommended parameter settings, operating procedures, or troubleshooting suggestions.

[0087] Meet the needs of different users. Save the user's personalized settings and automatically apply them the next time you log in.

[0088] Regarding multi-user support:

[0089] Supports multi-user login and personalized recommendations, each user has his or her own independent recommendation model and settings.

[0090] For example, administrators can add, delete, and manage user accounts, and each user can see their own recommended content after logging in.

[0091] Protect user privacy and ensure the security and confidentiality of user data.

[0092] Figure 3 300 is a schematic diagram of an embodiment of a structural block diagram of a numerical control system of the present application. The components of the numerical control system 300 include but are not limited to a memory 301 and a processor 302. The processor 302 is connected to the memory 301, the memory is used to store computer programs / instructions, the processor is used to execute the computer programs / instructions, and the programs / instructions are executed by the processor to implement the aforementioned method.

[0093] One embodiment of the present application also provides a computer program product, which stores a computer program / instruction, and the program / instruction implements the aforementioned method when executed by a processor. The computer program / instruction includes a computer program code, and the computer program code may be in source code form, object code form, executable file or some intermediate form, etc. The computer program product may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electric carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer program product can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer program products do not include electric carrier signals and telecommunication signals.

[0094] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0095] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0096] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict. Any simple modifications, equivalent changes and modifications made to the above embodiments according to the technical essence of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. An operation recommendation method for machining equipment, comprising: Obtain current operating situation data of machining equipment; Based on the current operation context data, a trained recommendation model recommends at least the next operation.

2. The method of claim 1, further comprising: Collect historical operation situation data of machining equipment; The recommendation model is trained by using the historical operation context data.

3. The method according to claim 1 or 2, wherein: The operation context data includes: user operation behavior data and state data of the machining equipment corresponding to the operation behavior.

4. The method of claim 3, wherein: The user operation behavior data includes at least one of the following: operation time, operation steps, operation parameters, and processing parameters; The state data of the machining equipment includes at least one of the following: spindle speed, tool coordinates, and workpiece coordinates.

5. The method of claim 2, wherein: Training the recommendation model by using the historical operation context data includes: Train a recommendation model for each user based on each user's historical operation context data; The trained recommendation model recommends at least one next action, including: At least a next action is recommended based on the current user identity by a recommendation model attributed to the current user identity.

6. The method of claim 7, wherein: Training the recommendation model by using the historical operation context data includes: Train a general recommendation model through historical operation context data of multiple users; The trained recommendation model recommends at least one next action, including: In response to identifying that the current user is a new user, At least a next operation is recommended by the general recommendation model.

7. The method of claim 1, further comprising: Collect user feedback on recommendation results, and optimize the recommendation model based on the feedback.

8. The method of claim 1, wherein: The recommendation model further includes recommending processing parameters associated with the at least next operation.

9. The method of claim 1, further comprising: The recommended results are presented in the display interface of the machining equipment.

10. A numerical control system, comprising a processor and a memory, wherein the memory is used to store computer programs / instructions, and the processor is used to execute the computer programs / instructions, and when the programs / instructions are executed by the processor, the method according to any one of claims 1 to 9 is implemented.

11. A machining device comprising a machining body and the numerical control system according to claim 10.

12. A computer program product, comprising a computer program / instruction, which implements the method according to any one of claims 1 to 9 when the computer program / instruction in the computer program product is executed by a processor.

Images