A method, device, equipment and medium for automatically stopping heating of a 3D printer

Abstract

The present invention discloses a method, device, equipment and medium for automatically stopping heating of a 3D printer. The method comprises: obtaining the current operating status information and the previous operating status information of the target 3D printer; wherein the operating status information includes the working mode, material remaining amount, nozzle temperature and the number of printed layers; determining the current operating change information based on the current operating status information and the previous operating status information; inputting the current operating change information into a pre-trained fault diagnosis model to obtain a fault diagnosis result; wherein the fault diagnosis result is normal or abnormal; if the fault diagnosis result is abnormal, controlling the target 3D printer to stop heating. This solution can efficiently and accurately diagnose 3D printer faults through the fault diagnosis model, and automatically stop heating when the 3D printer is working abnormally, thereby improving the efficiency of 3D printer fault diagnosis, reducing labor costs, and avoiding the problem of 3D printer damage caused by abnormal heating.

Description

Technical Field

[0001] The present invention relates to the field of automatic control technology, and in particular to a method, device, equipment and medium for automatically stopping heating of a 3D printer. Background Art

[0002] Current 3D printing devices all have a machine parameter detection function in the host computer, which can read the parameters of each component of the current device and inform the user in the form of a pop-up window or notification list on the interface. The user can then adjust the device to keep the 3D printer in normal working condition.

[0003] As 3D printers are used in industrial production, the number of devices increases, making it difficult for operators to monitor anomalies in multiple machines simultaneously, resulting in inefficient fault detection. Furthermore, not all users understand the various parameters of the equipment, leading to some anomalies being overlooked. Since most 3D printers include components with heating functions, anomalies in the heating area can easily cause damage to the machine and even threaten fire safety. Summary of the Invention

[0004] The present invention provides a method, device, equipment and medium for automatically stopping heating of a 3D printer, which can efficiently and accurately diagnose 3D printer faults through a fault diagnosis model and automatically stop heating when the 3D printer is operating abnormally, thereby improving the efficiency of 3D printer fault diagnosis, reducing labor costs, and avoiding the problem of 3D printer damage caused by abnormal heating.

[0005] According to one aspect of the present invention, a method for automatically stopping heating of a 3D printer is provided, the method comprising:

[0006] Obtaining the current and previous operating status information of the target 3D printer; wherein the operating status information includes the operating mode, material remaining, nozzle temperature, and number of printed layers;

[0007] Determining current operation change information according to the current operation state information and the previous operation state information;

[0008] Inputting the current operation change information into a pre-trained fault diagnosis model to obtain a fault diagnosis result; wherein the fault diagnosis result is normal or abnormal;

[0009] If the fault diagnosis result is abnormal, the target 3D printer is controlled to stop heating.

[0010] According to another aspect of the present invention, there is provided an automatic heating stop device for a 3D printer, the device comprising:

[0011] An operating status information acquisition module is used to obtain the current operating status information and the previous operating status information of the target 3D printer; wherein the operating status information includes the working mode, material remaining amount, nozzle temperature and number of printed layers;

[0012] An operation change information determining module, configured to determine current operation change information based on the current operation state information and the previous operation state information;

[0013] A fault diagnosis result determination module is used to input the current operation change information into a pre-trained fault diagnosis model to obtain a fault diagnosis result; wherein the fault diagnosis result is normal or abnormal;

[0014] The heating stop control module is used to control the target 3D printer to stop heating if the fault diagnosis result is abnormal.

[0015] According to another aspect of the present invention, an electronic device is provided, comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program executable by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the method for automatically stopping heating of a 3D printer according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for automatically stopping heating of a 3D printer according to any embodiment of the present invention when executed.

[0020] The technical solution of the embodiment of the present invention first obtains the current operating status information and the previous operating status information of the target 3D printer; wherein the operating status information includes the working mode, material remaining amount, nozzle temperature, and the number of printed layers; then, the current operating change information is determined based on the current operating status information and the previous operating status information; and then the current operating change information is input into a pre-trained fault diagnosis model to obtain a fault diagnosis result; wherein the fault diagnosis result is normal or abnormal; if the fault diagnosis result is abnormal, the target 3D printer is controlled to stop heating. This technical solution can efficiently and accurately diagnose 3D printer faults through the fault diagnosis model and automatically stop heating when the 3D printer is operating abnormally, thereby improving the efficiency of 3D printer fault diagnosis, reducing labor costs, and avoiding the problem of 3D printer damage caused by abnormal heating.

[0021] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 This is a flow chart of a method for automatically stopping heating of a 3D printer provided according to the first embodiment of the present invention;

[0024] Figure 2 This is a schematic diagram of the composition of an automatic stop heating system for a 3D printer provided according to a second embodiment of the present invention;

[0025] Figure 3 This is a workflow diagram of an automatic heating stop system for a 3D printer provided according to a second embodiment of the present invention;

[0026] Figure 4 This is a schematic structural diagram of an automatic heating stop device for a 3D printer provided according to a third embodiment of the present invention;

[0027] Figure 5 The present invention is a schematic structural diagram of an electronic device for implementing a method for automatically stopping heating of a 3D printer according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", "target", etc. in the description 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 numbers 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 clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] Example 1

[0031] Figure 1 This is a flow chart of a method for automatically stopping heating of a 3D printer provided in the first embodiment of the present invention. This embodiment is applicable to the case where the 3D printer is automatically controlled to stop heating when a fault diagnosis model diagnoses that the 3D printer is in an abnormal working state. This method can be executed by the automatic heating stop device of the 3D printer. The automatic heating stop device of the 3D printer can be implemented in the form of hardware and / or software. The automatic heating stop device of the 3D printer can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes:

[0032] S110 , obtaining current operating status information and previous operating status information of a target 3D printer.

[0033] Among them, the target 3D printer may refer to a 3D printer that needs to be fault-detected, such as a wax-type 3D printer. Wax material, as a phase change material, needs to be in liquid state under heating conditions before it can be sprayed and printed, so it needs to be preheated in advance. The operating status information includes the working mode, material margin, nozzle temperature and the number of printed layers. Exemplarily, the working status may include a preheating state (represented by 0) and a standby state (represented by 1), etc. The current operating status information and the previous operating status information may refer to the operating status information corresponding to the current detection moment and the previous detection moment, respectively. Exemplarily, the time length between the current detection moment and the previous detection moment can be set to 1 hour, that is, information collection is performed every 1 hour. It should be noted that before collecting information, it is necessary to ask and obtain the user's consent to avoid privacy-related disputes.

[0034] S120: Determine current operation change information according to the current operation status information and the previous operation status information.

[0035] The current operation change information may refer to the change information of various operation status information between the current detection moment and the previous detection moment. Exemplarily, the operation change information may include the change in operating mode, material consumption, nozzle temperature change value, and the change in the number of printed layers. The operating mode change at the current detection moment can be directly set to the operating mode value at the current detection moment. The material consumption, nozzle temperature change value, and printed layer change value at the current detection moment need to be determined based on the difference between the corresponding parameters at the current detection moment and the previous detection moment.

[0036] Furthermore, after determining the current operation change information, an operation change vector can be generated according to the current operation change information, for example, it can be expressed as Among them, w1 represents the working mode at the current detection moment, and its value is a non-negative number. The meaning of the value can be set in advance according to the working mode of the 3D printer; w2 represents the material consumption corresponding to the current detection moment, w3 represents the nozzle temperature change value corresponding to the current detection moment, and w4 represents the change value of the number of printed layers corresponding to the current detection moment.

[0037] S130: Input the current operation change information into a pre-trained fault diagnosis model to obtain a fault diagnosis result.

[0038] Among them, the fault diagnosis model can be used to predict whether the working state of the 3D printer is normal or abnormal. Exemplarily, the fault diagnosis model can be obtained based on the model training of the support vector machine. In this embodiment, the current operation change information can be directly input into the pre-trained fault diagnosis model, or the operation change vector generated according to the current operation change information can be input into the pre-trained fault diagnosis model, and the fault diagnosis result can be determined according to the model output result. Among them, the fault diagnosis result is normal or abnormal. It should be noted that the input parameter form when the model is used needs to be consistent with the input parameter form set during model training.

[0039] S140: If the fault diagnosis result is abnormal, the target 3D printer is controlled to stop heating.

[0040] In this embodiment, if the fault diagnosis model predicts that the target 3D printer is in an abnormal working state, in order to avoid the problem of serious damage to the target 3D printer due to the abnormality in the heating part, it is necessary to control the target 3D printer to stop heating, thereby realizing the function of automatically stopping heating of the 3D printer.

[0041] The technical solution of the embodiment of the present invention first obtains the current operating status information and the previous operating status information of the target 3D printer; wherein the operating status information includes the working mode, material remaining amount, nozzle temperature, and the number of printed layers; then, the current operating change information is determined based on the current operating status information and the previous operating status information; and then the current operating change information is input into a pre-trained fault diagnosis model to obtain a fault diagnosis result; wherein the fault diagnosis result is normal or abnormal; if the fault diagnosis result is abnormal, the target 3D printer is controlled to stop heating. This technical solution can efficiently and accurately diagnose 3D printer faults through the fault diagnosis model and automatically stop heating when the 3D printer is operating abnormally, thereby improving the efficiency of 3D printer fault diagnosis, reducing labor costs, and avoiding the problem of 3D printer damage caused by abnormal heating.

[0042] In this embodiment, the training process of the fault diagnosis model optionally includes the following steps A1-A4:

[0043] A1. Obtain historical operating status information of candidate 3D printers at different historical detection moments.

[0044] Among them, the candidate 3D printer may refer to one or more 3D printer devices used for data collection during model training. The historical detection moment may refer to the data detection moment before the current moment. It should be noted that the historical detection moment usually includes multiple detection moments, and the time length between adjacent detection moments may be the same or different, which can be pre-set according to actual needs. For example, it can be set to collect data from the candidate 3D printer once every hour, and the time length between adjacent historical detection moments is the same and is 1 hour. The historical operation status information may refer to the operation status information corresponding to the historical detection moment.

[0045] A2. Determine a print information vector based on historical operating status information at adjacent historical detection moments.

[0046] The print information vector is used to represent the changes in the historical operation status information. Specifically, the historical operation change information is first determined based on the differences in the historical operation status information corresponding to adjacent historical detection moments, and then the print information vector is generated based on the historical operation change information to represent the changes in the historical operation status information. For example, the print information vector is represented as Among them, v1 represents the working mode at a certain historical detection moment, v2 represents the material consumption corresponding to a certain historical detection moment, v3 represents the nozzle temperature change value corresponding to a certain historical detection moment, and v4 represents the change value of the number of printed layers corresponding to a certain historical detection moment.

[0047] A3. Determine the fault label corresponding to the printed information vector.

[0048] Among them, the fault label is used to indicate whether the candidate 3D printer is in normal working condition. Specifically, by manually labeling, whether the candidate 3D printer corresponding to each printing information vector is in normal working condition at the historical detection moment is determined, thereby determining the fault label corresponding to the printing information vector. Exemplarily, the fault label can be represented based on a numerical value, a letter, or other symbol, and can be pre-set according to actual needs. This embodiment does not limit this. For example, a fault label of 0 indicates an abnormal working state, and a fault label of 1 indicates a normal working state.

[0049] A4. Train a preset support vector machine model according to the printing information vector and the fault label. When the preset support vector machine model converges, determine the preset support vector machine model as the fault diagnosis model.

[0050] The preset support vector machine model refers to a pre-set support vector machine model, which exists as the basic framework for model training. The model is a generalized linear classifier that performs binary classification on data in a supervised learning manner. Its decision boundary is the maximum margin hyperplane solved for the learning sample. Specifically, assuming that the print information vector is represented as Each print information vector Marked as a point in four-dimensional space, the goal of model training is to find a hyperplane Ax1+Bx2+Cx3+Dx4+E=0 (the normal vector of the hyperplane is ), so that the hyperplane can print the information vector as much as possible The vector in normal working condition and vectors in abnormal working state To make effective distinctions, that is, to make as many and Able to meet

[0051] In this embodiment, optionally, step A4 specifically includes the following steps A41-A44:

[0052] A41. Determine, according to the fault label, a printing information vector in an abnormal working state as a first vector, and determine a printing information vector in a normal working state as a second vector.

[0053] Specifically, it is possible to determine which printing information vectors are in an abnormal working state or a normal working state according to the fault label, and determine the printing information vector in the abnormal working state as the first vector The printing information vector in normal working state is determined as the second vector

[0054] A42. Determine a target hyperplane associated with the printing information vector based on the first vector and the second vector.

[0055] The target hyperplane is used to divide the linear space where the printing information vector is located into two non-intersecting linear subspaces, and the first vector and the second vector are respectively in different linear subspaces. Specifically, first, according to the first vector Find a hyperplane α:Ax1+Bx2+Cx3+Dx4+E=0 (ABCDE are all constants and not all 0) and calculate its normal vector Make all are all on the same side of α, that is, for all make Then calculate the second vector that falls on the same side of α The number of the second vector The proportion P of the total number is then adjusted using the least squares method to find the parameter values ​​that increase P and gradually converge to determine the target hyperplane. It should be noted that if the linear space where the printed information vector resides is n-dimensional, then the two non-intersecting linear subspaces after the split are also n-dimensional, and the corresponding target hyperplane is n-1-dimensional space.

[0056] A43. Determine the predicted diagnosis result of the printing information vector based on the target hyperplane.

[0057] Specifically, after determining the target hyperplane, the model output result corresponding to each print information vector can be determined based on the target hyperplane, and the model output result can be used as the predicted diagnosis result, wherein the predicted diagnosis result is normal or abnormal.

[0058] A44. Determine a loss value based on the predicted diagnosis result and the fault label corresponding to the printed information vector, and train a preset support vector machine model based on the loss value.

[0059] Specifically, after determining the predicted diagnosis result of the print information vector, a loss value can be calculated using a loss function based on the predicted diagnosis result and the fault label corresponding to the print information vector. The preset support vector machine model is then trained and adjusted based on the loss value until the loss value stabilizes, indicating model convergence. When the preset support vector machine model reaches convergence, the preset support vector machine model can be determined as the fault diagnosis model, which can implement 3D printer fault diagnosis.

[0060] In this embodiment, the fault diagnosis model training process optionally further includes: after determining a print information vector based on historical operating status information at adjacent historical detection moments, determining the sum of each data element in the print information vector as a reference data element; and for each candidate data element in the print information vector, normalizing the print information vector based on a ratio between the candidate data element and the reference data element. Accordingly, training a preset support vector machine model based on the print information vector and the fault label includes: training the preset support vector machine model based on the normalized print information vector and the fault label.

[0061] It should be noted that the ranges allowed by different operating status information are inconsistent, and even have large differences. In order to facilitate subsequent model training, the print information vector needs to be normalized so that each data element in the print information vector is in the same range. For example, the formula Print information vector Normalize the data elements in to get the updated print information vector Among them, v i is a candidate data element, In the subsequent model training, the preset support vector machine model is trained based on the normalized printing information vector and fault label.

[0062] In this embodiment, optionally, after the preset support vector machine model is determined as the fault diagnosis model, the following steps B1-B4 are further included:

[0063] B1. Determine the model evaluation parameters based on the predicted diagnosis results and the fault labels corresponding to the printed information vector.

[0064] Among them, model evaluation parameters can be used to evaluate the performance of the model (i.e., the effectiveness of the model). Optionally, model evaluation parameters include accuracy, precision, and recall. Specifically, first, based on the standards for model performance evaluation in machine learning, the meanings of the four indicators TP, FP, FN, and TN are defined, as shown in Table 1:

[0065] Table 1 Meaning of TP, FP, FN and TN

[0066] Predicted as positive sample Predicted as negative sample Actually positive sample TP FN Actually negative samples FP TN

[0067] The prediction is determined by the prediction diagnosis result, and the actual situation is determined by the fault label corresponding to the printed information vector. Then, based on the four indicators TP, FP, FN and TN, the accuracy, precision and recall are calculated respectively. These three parameters can be used to evaluate the effect of a single training of the model. The accuracy can be expressed as The accuracy can be expressed as The recall rate can be expressed as

[0068] In this embodiment, the model evaluation parameter may also include an F1 value, which is determined based on the precision and recall rate. Specifically, the F1 value (F1Score) may be calculated based on the precision and recall rate, and is expressed as The F1 score is designed to consider both precision and recall, avoiding situations where one is too high while the other is too low. As an important comprehensive evaluation metric, the F1 score can be used for model comparison (for example, comparing the performance of different models or comparing the performance of models after different rounds of training).

[0069] B2. Verify the performance of the fault diagnosis model based on the model evaluation parameters.

[0070] After obtaining multiple model evaluation parameters, the performance of the fault diagnosis model can be verified based on the model evaluation parameters. Exemplarily, the accuracy threshold, precision threshold and recall threshold can be set in advance, and then the calculated accuracy Acc, precision Pre and recall Rec are compared with the accuracy threshold, precision threshold and recall threshold respectively. If Acc is greater than the accuracy threshold, Pre is greater than the precision threshold and Rec is greater than the recall threshold, then it can be determined that the fault diagnosis model has passed the performance verification, otherwise it will be determined that the fault diagnosis model has not passed the performance verification. Further, on the basis of satisfying Acc is greater than the accuracy threshold, Pre is greater than the precision threshold and Rec is greater than the recall threshold, it can also be determined whether the calculated F1 value is greater than the preset F1 reference value. If so, it can be determined that the fault diagnosis model has passed the performance verification, otherwise it will be determined that the fault diagnosis model has not passed the performance verification.

[0071] B3. If the fault diagnosis model fails the performance verification, obtain incremental operation data of the candidate 3D printer.

[0072] Incremental operating data may refer to historical operating status information of the candidate 3D printer at other historical testing moments. It is understood that if the fault diagnosis model is determined to have failed performance verification, it indicates that the model training effect is poor, and the accuracy of the model prediction cannot be guaranteed. Therefore, it is necessary to obtain incremental operating data of the candidate 3D printer and continue to train the model based on this incremental operating data to adjust and update the model so that it can pass performance verification.

[0073] B4. Adjust and update the fault diagnosis model based on the incremental operating data until the fault diagnosis model passes the performance verification.

[0074] Through such a setting, this solution adds a model performance verification link, which can efficiently and accurately diagnose 3D printer faults based on the fault diagnosis model that has passed performance verification. On the basis of effectively improving fault diagnosis efficiency and reducing labor costs, it helps to further improve the diagnostic accuracy of the fault diagnosis model.

[0075] Example 2

[0076] Figure 2 This is a schematic diagram of the composition of an automatic stop heating system for a 3D printer provided in the second embodiment of the present invention. The system can implement the automatic stop heating method for a 3D printer provided in any embodiment of the present invention. Figure 2 As shown in the figure, the system includes: a 3D printer, a host computer, a server, and a cloud platform. The 3D printer is connected to the host computer, which serves as a data collection terminal. With the user's permission, the host computer collects operating status information during the 3D printer's working hours and packages the historical operating status information at different historical detection times and sends it to the server. The server serves as a model training center and can use the collected historical operating status information to train a support vector machine to obtain a fault diagnosis model, which is then sent to the cloud platform. The cloud platform (here, the 3D printer manufacturer's cloud platform) serves as a publishing center and is responsible for publishing the trained fault diagnosis model. Users can select, download, and apply models from the cloud platform as needed. The data flow path of the entire system forms a closed loop, which not only prevents data leakage but also facilitates system updates and iterations.

[0077] Figure 3 This is a workflow diagram of an automatic heating stop system for a 3D printer provided in Example 2 of the present invention. Figure 3 As shown, first, a data collection request is sent through the host computer connected to the 3D printer. After the user agrees to the privacy terms, the host computer collects the operating status information during the 3D printer's working hours, and the historical operating status information at different historical detection times is packaged and uploaded to the server for model training. The trained fault diagnosis model is published to the cloud platform so that more users can update and download it as needed, and use the downloaded or updated fault diagnosis model to perform printer fault detection. Specifically, users can select the model and download it to the host computer of the 3D printer as needed. The model will extract the device's parameter information at regular intervals, generate the device parameter vector, and input it into the model. The model predicts whether the machine is operating normally based on the input, so that users can take corresponding protective measures in advance based on the prediction results.

[0078] Example 3

[0079] Figure 4This is a schematic diagram of the structure of a 3D printer automatic heating stop device provided by the third embodiment of the present invention. The device can execute the 3D printer automatic heating stop method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. Figure 4 As shown, the device includes:

[0080] The operating status information acquisition module 310 is used to obtain the current operating status information and the previous operating status information of the target 3D printer; wherein the operating status information includes the working mode, material remaining amount, nozzle temperature and the number of printed layers;

[0081] An operation change information determining module 320 is configured to determine current operation change information based on the current operation state information and the previous operation state information;

[0082] The fault diagnosis result determination module 330 is used to input the current operation change information into a pre-trained fault diagnosis model to obtain a fault diagnosis result; wherein the fault diagnosis result is normal or abnormal;

[0083] The heating stop control module 340 is configured to control the target 3D printer to stop heating if the fault diagnosis result is abnormal.

[0084] Optionally, the device further includes a model training module, and the model training module includes:

[0085] A historical operation status information acquisition unit, configured to acquire historical operation status information of the candidate 3D printer at different historical detection moments;

[0086] A printing information vector determining unit, configured to determine a printing information vector based on historical operating status information at adjacent historical detection moments; wherein the printing information vector is used to represent changes in the historical operating status information;

[0087] a fault label determination unit, configured to determine a fault label corresponding to the printing information vector; wherein the fault label is used to indicate whether the candidate 3D printer is in a normal working state;

[0088] The model training unit is used to train a preset support vector machine model according to the printing information vector and the fault label, and when the preset support vector machine model converges, determine the preset support vector machine model as a fault diagnosis model.

[0089] Optionally, the model training module further includes a vector normalization unit, configured to:

[0090] After determining a print information vector based on historical operating state information at adjacent historical detection moments, determining a sum of data elements in the print information vector as a reference data element;

[0091] For each candidate data element in the printing information vector, normalizing the printing information vector according to a ratio of the candidate data element to the reference data element;

[0092] Accordingly, the model training unit is used to:

[0093] The preset support vector machine model is trained according to the normalized printing information vector and the fault label.

[0094] Optionally, the model training unit is specifically used to:

[0095] Determine, according to the fault label, a printing information vector in an abnormal working state as a first vector, and determine a printing information vector in a normal working state as a second vector;

[0096] determining a target hyperplane associated with the printing information vector based on the first vector and the second vector; wherein the target hyperplane is used to split the linear space in which the printing information vector is located into two non-intersecting linear subspaces, and the first vector and the second vector are respectively located in different linear subspaces;

[0097] Determining a predicted diagnosis result of the printing information vector based on the target hyperplane;

[0098] A loss value is determined according to the predicted diagnosis result and the fault label corresponding to the printing information vector, and the preset support vector machine model is trained based on the loss value.

[0099] Optionally, the model training module further includes a model performance verification unit, which is used to:

[0100] After determining the preset support vector machine model as the fault diagnosis model, determining a model evaluation parameter according to the predicted diagnosis result and the fault label corresponding to the printing information vector;

[0101] Performing performance verification on the fault diagnosis model based on the model evaluation parameters;

[0102] If the fault diagnosis model fails the performance verification, obtaining incremental operation data of the candidate 3D printer;

[0103] The fault diagnosis model is adjusted and updated based on the incremental operating data until the fault diagnosis model passes performance verification.

[0104] Optionally, the model evaluation parameters include accuracy, precision and recall.

[0105] Optionally, the model evaluation parameter further includes an F1 value, and the F1 value is determined based on the precision and the recall.

[0106] An automatic heating stop device for a 3D printer provided by an embodiment of the present invention can execute an automatic heating stop method for a 3D printer provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects of the execution method.

[0107] Example 4

[0108] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0109] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0110] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0111] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the automatic heating stop method for a 3D printer.

[0112] In some embodiments, the automatic heating stop method for a 3D printer can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the automatic heating stop method for a 3D printer described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the automatic heating stop method for a 3D printer by any other appropriate means (e.g., by means of firmware).

[0113] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0114] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0115] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0116] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0117] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0118] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0119] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0120] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for automatically stopping heating of a 3D printer, characterized in that: The method comprises: Obtaining the current and previous operating status information of the target 3D printer; wherein the operating status information includes the operating mode, material remaining, nozzle temperature, and number of printed layers; Determining current operation change information according to the current operation state information and the previous operation state information; Inputting the current operation change information into a pre-trained fault diagnosis model to obtain a fault diagnosis result; wherein the fault diagnosis result is normal or abnormal; If the fault diagnosis result is abnormal, the target 3D printer is controlled to stop heating.

2. The method according to claim 1, characterized in that The training process of the fault diagnosis model includes: Obtain historical operating status information of candidate 3D printers at different historical detection moments; Determine a print information vector based on historical operating status information at adjacent historical detection moments; wherein the print information vector is used to represent changes in the historical operating status information; Determining a fault label corresponding to the printing information vector; wherein the fault label is used to indicate whether the candidate 3D printer is in a normal working state; A preset support vector machine model is trained according to the printing information vector and the fault label, and when the preset support vector machine model converges, the preset support vector machine model is determined as a fault diagnosis model.

3. The method according to claim 2, characterized in that After determining the printing information vector based on the historical operating state information at adjacent historical detection moments, the method includes: determining a sum of the data elements in the printing information vector as a reference data element; For each candidate data element in the printing information vector, normalizing the printing information vector according to a ratio of the candidate data element to the reference data element; Accordingly, the preset support vector machine model is trained according to the printing information vector and the fault label, including: The preset support vector machine model is trained according to the normalized printing information vector and the fault label.

4. The method according to claim 2, characterized in that Training a preset support vector machine model according to the printing information vector and the fault label includes: Determine, according to the fault label, a printing information vector in an abnormal working state as a first vector, and determine a printing information vector in a normal working state as a second vector; determining a target hyperplane associated with the printing information vector based on the first vector and the second vector; wherein the target hyperplane is used to split the linear space in which the printing information vector is located into two non-intersecting linear subspaces, and the first vector and the second vector are respectively located in different linear subspaces; Determining a predicted diagnosis result of the printing information vector based on the target hyperplane; A loss value is determined according to the predicted diagnosis result and the fault label corresponding to the printing information vector, and the preset support vector machine model is trained based on the loss value.

5. The method according to claim 4, characterized in that After determining the preset support vector machine model as the fault diagnosis model, the method further includes: Determining a model evaluation parameter according to the predicted diagnosis result and the fault label corresponding to the printing information vector; Performing performance verification on the fault diagnosis model based on the model evaluation parameters; If the fault diagnosis model fails the performance verification, obtaining incremental operation data of the candidate 3D printer; The fault diagnosis model is adjusted and updated based on the incremental operating data until the fault diagnosis model passes performance verification.

6. The method according to claim 5, characterized in that The model evaluation parameters include accuracy, precision and recall.

7. The method according to claim 6, characterized in that The model evaluation parameters further include an F1 value, which is determined based on the precision and the recall.

8. An automatic stop heating device for a 3D printer, characterized in that: The device comprises: An operating status information acquisition module is used to obtain the current operating status information and the previous operating status information of the target 3D printer; wherein the operating status information includes the working mode, material remaining amount, nozzle temperature and number of printed layers; An operation change information determining module, configured to determine current operation change information based on the current operation state information and the previous operation state information; A fault diagnosis result determination module is used to input the current operation change information into a pre-trained fault diagnosis model to obtain a fault diagnosis result; wherein the fault diagnosis result is normal or abnormal; The heating stop control module is used to control the target 3D printer to stop heating if the fault diagnosis result is abnormal.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor. The computer program is executed by the at least one processor to enable the at least one processor to execute the method for automatically stopping heating of the 3D printer according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for automatically stopping heating of a 3D printer according to any one of claims 1 to 7 when executed.

Images