Fault detection method, device and equipment for three-dimensional printing equipment

Abstract

The invention provides a fault detection method, device and equipment for three-dimensional printing equipment. The method comprises the steps that printing raw material stress data and printing platform pressure data of a feeding system of the three-dimensional printing equipment are obtained; the printing raw material is detected according to the printing raw material stress data and a preset stress threshold value, and a printing raw material detection result is obtained; a printing head is detected according to the printing platform pressure data, and a printing head detection result is obtained; and determining a fault detection result according to the printing raw material detection result and the printing head detection result. The printing raw material stress data and the printing platform pressure data are obtained, the printing raw material and the printing head are detected respectively, and the fault detection result is determined according to the obtained printing raw material detection result and the printing head detection result, so that the method has the advantages of being convenient to operate and simple; and whether the printing raw material and the printing head break down or not can be detected at the same time, and the detection result is comprehensive and accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of fault detection, and also to a fault detection method, device and equipment for three-dimensional printing equipment. Background Art

[0002] Fused deposition modeling 3D (three-dimensional) printing equipment is prone to technical faults such as material breakage and plugging during operation, resulting in molding failure. At present, the common 3D printing equipment material breakage detection method generally adopts a fault detection system based on photoelectric sensors. When a wire passes through the photoelectric sensor, it indicates that the material feeding is normal; when the wire is broken, no wire passes through the photoelectric sensor, which indicates that there is a feeding failure. However, when the print head is blocked or the wire leaves the position of the photoelectric sensor and breaks, the photoelectric sensor will not issue an alarm because it can detect the presence of wire at the location. In fact, the print head has been blocked or broken and cannot work normally. Therefore, this detection method has the disadvantage of low fault detection accuracy. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a fault detection method, device and equipment for a three-dimensional printing device, so as to improve the accuracy of fault detection when the three-dimensional printing device is printing.

[0004] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0005] A first aspect of the present invention provides a fault detection method for a three-dimensional printing device, comprising:

[0006] Obtaining the printing material force data and printing platform pressure data of the feeding system of the 3D printing device;

[0007] Detecting the printing material according to the printing material force data and a preset force threshold to obtain a printing material detection result;

[0008] Detecting the print head according to the printing platform pressure data to obtain a print head detection result;

[0009] A fault detection result is determined according to the printing material detection result and the print head detection result.

[0010] Optionally, obtaining the printing material force data and printing platform pressure data of the feeding system of the 3D printing device includes:

[0011] Obtaining the stress data of the printing material through a stress sensor installed at a first preset position; the first preset position includes any position on the printing material between the wire tray of the feeding system and the print head;

[0012] The pressure data of the printing platform is obtained by installing a stress sensor at a second preset position; the second preset position includes a position at the bottom of the printing platform corresponding to the print head.

[0013] Optionally, the printing material is detected according to the printing material force data and a preset force threshold to obtain a printing material detection result, including:

[0014] Obtaining the force data of the printing material under preset conditions;

[0015] Determining a preset force threshold according to the force data of the printing material under preset conditions;

[0016] Comparing the printing material force data with the preset force threshold to obtain a comparison result;

[0017] The supply status of the printing material is detected according to the comparison result to obtain a printing material detection result.

[0018] Optionally, the print head is tested according to the printing platform pressure data to obtain a print head test result, including:

[0019] Preprocessing the printing platform pressure data to obtain preprocessed printing platform pressure data;

[0020] Extracting features from the preprocessed printing platform pressure data to obtain feature data;

[0021] Inputting the characteristic data into a trained fault prediction model to obtain a fault prediction result; the fault prediction model is obtained by training a preset network model based on historical printing platform pressure data;

[0022] The print head is tested according to the fault prediction result and the preset safety threshold to obtain a print head test result.

[0023] Optionally, the feature data is input into a trained fault prediction model to obtain a fault prediction result, including:

[0024] Inputting the characteristic data into a fault prediction model to obtain multiple prediction results;

[0025] A fault prediction result is obtained according to the multiple prediction results.

[0026] Optionally, determining a fault detection result according to the printing material detection result and the print head detection result includes:

[0027] Determining a raw material processing strategy according to the printing raw material detection result;

[0028] Determining a print head processing strategy according to the print head detection result;

[0029] A fault detection result is determined according to the printing material detection result, the print head detection result, the material processing strategy and the print head processing strategy.

[0030] Optionally, the method further includes:

[0031] generating alarm information and control parameters according to the fault detection result;

[0032] The warning information is output, and the print head is controlled to move to a preset position according to the control parameters.

[0033] A second aspect of the present invention provides a fault detection device for a three-dimensional printing device, comprising:

[0034] An acquisition module, used to acquire the printing material force data and the printing platform pressure data of the feeding system of the three-dimensional printing device;

[0035] A first processing module, configured to detect the printing material according to the printing material force data and a preset force threshold, and obtain a printing material detection result;

[0036] A second processing module is used to detect the print head according to the printing platform pressure data to obtain a print head detection result;

[0037] The third processing module is used to determine a fault detection result according to the printing material detection result and the print head detection result.

[0038] According to a third aspect of the present invention, a computing device is provided, comprising: a processor and a memory storing a computer program, wherein when the computer program is executed by the processor, the method according to the first aspect is executed.

[0039] A fourth aspect of the present invention provides a computer-readable storage medium storing instructions, which, when executed on a computer, causes the computer to execute the method described in the first aspect.

[0040] The above solution of the present invention includes at least the following beneficial effects:

[0041] The above scheme of the present invention obtains the force data of the printing material and the pressure data of the printing platform, and detects the printing material and the print head respectively, and determines the fault detection result based on the obtained printing material detection results and the print head detection results. It not only has the advantages of convenient operation and simple method, but also can simultaneously detect whether the printing material and the print head have faults, and the detection results are relatively comprehensive and accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1is a flow chart of a fault detection method for a three-dimensional printing device in an embodiment of the present invention;

[0043] Figure 2 It is a schematic diagram of the structure of a fused deposition modeling 3D printing device;

[0044] Figure 3 Schematic diagram of the structure of a fault detection device for a three-dimensional printing device in an embodiment of the present invention.

[0045] Explanation of the reference numerals: 1-wire disk, 2-print head, 3-printing platform, 4-wire, 5-molding device. DETAILED DESCRIPTION

[0046] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0047] like Figure 1 As shown, an embodiment of the present invention provides a fault detection method for a three-dimensional printing device, comprising the following steps:

[0048] Step 101, obtaining printing material force data and printing platform pressure data of a feeding system of a three-dimensional printing device;

[0049] Step 102, detecting the printing material according to the printing material force data and a preset force threshold, and obtaining a printing material detection result;

[0050] Step 103, testing the print head according to the printing platform pressure data to obtain a print head testing result;

[0051] Step 104: Determine a fault detection result according to the printing material detection result and the print head detection result.

[0052] The fault detection of the three-dimensional printing device proposed in the embodiment of the present invention obtains the force data of the printing material and the pressure data of the printing platform, and detects the printing material and the print head respectively, and determines the fault detection result according to the obtained printing material detection results and the print head detection results. It not only has the advantages of convenient operation and simple method, but also can simultaneously detect whether the printing material and the print head have faults, and the detection results are relatively comprehensive and accurate.

[0053] In an optional embodiment of the present invention, step 101 includes:

[0054] Step 1011, obtaining the stress data of the printing material through a stress sensor installed at a first preset position; the first preset position includes any position on the printing material between the wire tray of the feeding system and the print head;

[0055] Specifically, you can choose stress sensors such as resistive strain sensors or optical fiber strain sensors. These sensors can sensitively capture the slight deformation of the printing material (such as printing wire) after being stressed. During installation, the stress sensor is embedded in the transmission path of the wire (i.e., any position of the printing wire between the wire reel and the print head), so that the wire must pass through the sensor's action area during the transmission process, which ensures that the sensor can accurately sense the stress state of the wire. Here, the stress sensor can be installed close to the print head to more accurately reflect the actual stress changes on the wire during the printing process; the stress sensor can also be installed at a position with a stable support point on the diameter between the wire and the print head to ensure that the sensor remains stable during the measurement process and is not disturbed by external vibration or displacement.

[0056] It should be noted that the printing material in this embodiment refers to the wire used for 3D printing, that is, a linear or non-linear object made of various materials (such as polylactic acid PLA or acrylonitrile-butadiene-styrene copolymer ABS, etc.), as long as the stress change can be detected by the stress sensor. Here, the printing material stress data mainly includes the stress state parameters of the wire (including the force magnitude, force direction, frequency and amplitude of the force change, etc.).

[0057] Step 1012, obtaining printing platform pressure data through a stress sensor installed at a second preset position; the second preset position includes a position at the bottom of the printing platform corresponding to the print head.

[0058] Specifically, you can choose a stress sensor such as a resistive strain sensor or an optical fiber strain sensor, and install the sensor at the bottom of the printing platform to ensure that it can accurately sense the force on the platform during printing. The stress sensor can be installed at the center of the bottom of the printing platform or in an area with greater force, such as near the support structure or at the position corresponding to the print head or the position corresponding to the printed molding device, which can more directly reflect the force on the platform during printing. It should be noted that the printing platform pressure data mainly includes the stress state parameters of the printing platform (including the magnitude of the force, the direction of the force, the frequency and amplitude of the force change, etc.).

[0059] In an optional embodiment of the present invention, step 102 includes:

[0060] Step 1021, obtaining force data of the printing material under preset conditions;

[0061] Specifically, the preset condition is that the fused deposition modeling 3D printing device is operating normally without any faults. A stress sensor installed at at least one position between the wire disc and the print head is used to collect the stress state parameters of the wire when the fused deposition modeling 3D printing device is operating normally (including the magnitude of the force, the direction of the force, the frequency and amplitude of the force change, etc.), which is used as the stress data of the printing material under the preset conditions, and is used as the basis for testing the printing material. Different printing devices and wires have different stress data when operating normally. Therefore, it is necessary to collect the stress data of the wire when the printing device and wire of the same model and wire type as the device to be tested are operating normally, so as to improve the accuracy and reliability of subsequent testing.

[0062] Step 1022, determining a preset force threshold according to the force data of the printing material under preset conditions;

[0063] Specifically, based on the force data of the printing material when the printing equipment is working normally, a range of force size, force direction, frequency and amplitude of force changes, etc. can be established as a preset force threshold for subsequent comparison with real-time force data, which is convenient for detecting whether the printing material has faults, and is conducive to improving detection efficiency.

[0064] Step 1023, comparing the printing material force data with the preset force threshold to obtain a comparison result;

[0065] Specifically, the magnitude of force, direction of force, frequency and amplitude of force changes in the force data of the printing material are compared with the magnitude of force, direction of force, frequency and amplitude of force changes in the preset force threshold. If all parameters in the force data of the printing material are within the range of the corresponding parameters in the preset force threshold, it means that the printing material is not faulty. Otherwise, it can be considered that the printing material is faulty. The comparison results include the specific values ​​of the magnitude of force, direction of force, frequency and amplitude of force changes in the force data of the printing material, and the specific values ​​of the magnitude of force, direction of force, frequency and amplitude of force changes in the preset force threshold. It also includes the comparison results of the corresponding parameters of the force data of the printing material and the preset force threshold, so as to facilitate the subsequent quick judgment of whether the printing material is faulty.

[0066] Step 1024: Detect the supply status of the printing material according to the comparison result to obtain a printing material detection result.

[0067] Specifically, according to the comparison result, it is possible to quickly determine whether the specific values ​​of various parameters such as the force magnitude, force direction, frequency and amplitude of force changes in the force data of the printing material are within the ranges of various parameters such as the force magnitude, force direction, frequency and amplitude of force changes corresponding to the preset force threshold. If they are all within the range (i.e., the force magnitude in the force data of the printing material is within the force magnitude range corresponding to the preset force threshold, the force direction in the force data of the printing material is within the force direction range corresponding to the preset force threshold, the frequency of force changes in the force data of the printing material is within the force frequency range corresponding to the preset force threshold, and the force changes in the force data of the printing material are ... If the magnitude of the force change is within the range of the force change corresponding to the preset force threshold), it indicates that the supply of printing materials is normal and there is no fault such as material breakage; if the comparison result shows any of the following situations: the magnitude of the force in the printing material force data is not within the range of the force magnitude corresponding to the preset force threshold, the force direction in the printing material force data is not within the range of the force direction corresponding to the preset force threshold, the frequency of the force change in the printing material force data is not within the range of the force change frequency corresponding to the preset force threshold, and the magnitude of the force change in the printing material force data is not within the range of the force change magnitude corresponding to the preset force threshold, it indicates that the supply of printing materials is abnormal and a fault has occurred. The printing material detection result includes the preset force threshold, the comparison result of the printing material force data and the preset force threshold, and the conclusion of whether a fault has occurred.

[0068] In an optional embodiment of the present invention, step 103 includes:

[0069] Step 1031, preprocessing the printing platform pressure data to obtain preprocessed printing platform pressure data;

[0070] Specifically, since the printing platform pressure data collected by the sensor may contain noise, such as electromagnetic interference, mechanical vibration, etc., the original printing platform pressure data needs to be filtered first to remove the noise component and retain the real and effective force data; if multiple sensors are installed at the bottom of the printing platform, in order to eliminate the measurement differences and errors between different sensors, the original printing platform pressure data needs to be standardized, that is, all data is converted to the same dimension and range for subsequent processing and analysis. Here, the preprocessing method can be filtering or standardization.

[0071] Step 1032, extracting features from the preprocessed printing platform pressure data to obtain feature data;

[0072] Specifically, the pre-processed printing platform pressure data includes some key features, such as the force magnitude, force direction, frequency and amplitude of force changes, etc. These key features can reflect the force exerted by the print head on the printing platform during operation; as well as the timestamp of recording the printing platform pressure data, and calculating the time series characteristics of force changes, such as the rate of force change, acceleration, etc. These features help to identify the time pattern and trend of force changes. Therefore, these key features can be extracted from the pre-processed printing platform pressure data as feature data for subsequent detection of the print head.

[0073] Step 1033, inputting the characteristic data into a trained fault prediction model to obtain a fault prediction result; the fault prediction model is obtained by training a preset network model based on historical printing platform pressure data;

[0074] Specifically, the preset network model used in this embodiment is:

[0075]

[0076] Among them, y is the predicted probability of each category given by the preset network model, t i is the i-th decision tree, 1≤i≤k, t i ×prob(x) is the prediction of x by the i-th tree. The output is the predicted probability of each category (row vector), and k is the forest size.

[0077] The training of the preset network model requires training multiple different weak trees, so that the preset network model can ensure a certain accuracy while making the final decision tree as simple as possible. Weak decision trees are constructed in the following ways:

[0078] Sample weakening: Each tree randomly selects only a part of the samples for training; each tree only selects a part of the variables for training;

[0079] Weakened tree structure: The depth of each tree is set as shallow as possible;

[0080] Specifically, the training process of the preset network model includes:

[0081] Collect historical printing platform pressure data as training samples;

[0082] Sample extraction: Draw n (number of training samples) samples with replacement.

[0083] Train weak trees: Use the extracted samples to train decision trees, using at most m features. M is the total number of features. Using at most m features can limit the depth of the tree while making each tree use different variables.

[0084] Keep training until k trees are found, where k is less than or equal to 100.

[0085] Through the above steps, k trees can be produced. Each tree uses random samples and fewer features. Then the k trees are combined together to form the preset network model after training.

[0086] Since only part of the samples are used in the training of each tree of the preset network model, the samples that are not involved in the training of this tree are called out-of-bag samples (OOB samples). The sampling of each sample in the training set of each tree is independent. OOB samples are used to evaluate the performance of each tree and calculate the out-of-bag error.

[0087] The out-of-bag error rate is a performance indicator that uses OOB samples to calculate the preset network model after training. For the preset network model after training, the prediction error of the preset network model after training is calculated using the OOB samples that have not been sampled, and then the out-of-bag errors of all models are averaged to obtain the out-of-bag error rate. Since the out-of-bag samples are used for prediction, the out-of-bag error rate can evaluate the generalization ability of the preset network model after training. The formula for the out-of-bag error rate is:

[0088]

[0089] Among them, OOB Error Rate is the out-of-bag error rate, N is the number of samples in the training sample, and n i is the number of decision trees from which the ith sample is sampled, e ij is the prediction error of the i-th sample on the j-th tree.

[0090] Here, if the out-of-bag error rate is less than the preset value, it means that the preset network model after training has achieved the expected effect. The preset network model after training can be used as a trained fault prediction model to process the feature data and output the fault prediction result.

[0091] Step 1034: Detect the print head according to the fault prediction result and the preset safety threshold to obtain a print head detection result.

[0092] Specifically, the preset safety threshold may be a specific safety threshold set based on experience regarding various parameters such as force magnitude, force direction, frequency and amplitude of force changes, rate of force changes, acceleration, etc., or it may be a safety threshold of the printing platform pressure data collected when the printing device is operating normally. If the probability value of the fault prediction result is greater than the preset probability value, it means that the print head may have a fault. At this time, it is necessary to compare the preprocessed printing platform pressure data with the preset safety threshold to confirm whether at least one of the following situations occurs: the force magnitude in the preprocessed printing platform pressure data is not within the force magnitude range in the preset safety threshold, the force direction in the preprocessed printing platform pressure data is not within the force direction range in the preset safety threshold, the frequency of force change in the preprocessed printing platform pressure data is not within the frequency range of force change in the preset safety threshold, the amplitude of force change in the preprocessed printing platform pressure data is not within the amplitude range of force change in the preset safety threshold, the rate of force change in the preprocessed printing platform pressure data is not within the rate range of force change in the preset safety threshold, and the acceleration of force change in the preprocessed printing platform pressure data is not within the acceleration range of force change in the preset safety threshold. If any of the following situations exist, it means that the print head does have a fault.

[0093] Here, the print head detection result includes the pre-processed printing platform pressure data, the fault prediction result, the comparison result of the pre-processed printing platform pressure data and the preset safety threshold, whether the print head has a fault, etc.

[0094] In an optional embodiment of the present invention, step 1033 includes:

[0095] The characteristic data is input into a fault prediction model to obtain a plurality of prediction results, and the plurality of prediction results are voted to obtain a fault prediction result.

[0096] Specifically, the feature data is input into the fault prediction model, which includes multiple weak trees, and each weak tree will give a prediction result based on the feature data. Here, taking a weak tree as an example, when processing feature data, the feature data will traverse the tree structure layer by layer according to the judgment conditions at the node. At each node, the feature data will be compared with the threshold at the node (the threshold is obtained by training based on historical feature data), and the comparison result will determine whether to enter the left child node or the right child node (if the feature data exceeds the threshold at the node, it will enter the left child node) until it reaches the leaf node. When traversing to the leaf node of the weak tree, the weak tree will give the final prediction result based on the information of the leaf node (the leaf node is the terminal node of the weak tree, no longer contains child nodes, and represents the final output result of the weak tree), such as the failure probability of the print head is 0.1. Therefore, multiple weak trees will give multiple prediction results, such as the failure probability of the print head is 0.1, the failure probability of the print head is 0.7, etc.

[0097] Then, the fault prediction model will count (vote) the prediction results given by all weak trees and calculate the number of votes obtained by each prediction result (that is, the number of identical prediction results). If the prediction results of n weak trees are all that the failure probability of the print head is 0.1, then the number of votes for the prediction result "the failure probability of the print head is 0.1" is n. If n is the largest number of votes, "the failure probability of the print head is 0.1" is used as the output of the fault prediction model, that is, the fault prediction result is "the failure probability of the print head is 0.1".

[0098] In an optional embodiment of the present invention, step 104 includes:

[0099] Step 1041, determining a material processing strategy according to the printing material detection result;

[0100] Specifically, if the printing material force data in the printing material detection results exceeds the preset force threshold, it may be caused by reasons such as print head blockage, nozzle wear, feed gear failure or improper tension adjustment. In this case, the wire may break due to excessive pulling, or bend or deform due to uneven force. If the force direction of the printing material force data in the printing material detection result suddenly changes or becomes unstable (that is, the force direction in the printing material force data exceeds the force direction in the preset force threshold), it may be caused by loose mechanical structure of the printer, wear of the guide wheel, or incorrect setting of the printing path. In this case, the wire may deviate from the predetermined path, resulting in printing failure or reduced printing quality. At this time, the corresponding material processing strategy is to check the mechanical structure, guide wheel and printing path of the printer; if the frequency and amplitude of the force change of the printing material force data in the printing material detection result exceed the frequency and amplitude of the force change in the preset force threshold (that is, the wire force fluctuates frequently and the fluctuation amplitude is large), it may be caused by unstable printer control system, power supply fluctuation or external environment interference. In this case, the wire may wear, break or reduce printing quality due to uneven force. At this time, the corresponding material processing strategy is to check the power supply of the printer to avoid interference of the external environment on the printing process. The above is only an example. Specifically, according to the printing material force data in the actual printing material detection results and the fault conditions in the printing material detection results, the corresponding material processing strategy can be called from the pre-stored strategy library to eliminate the fault as soon as possible and resume printing as soon as possible.

[0101] Step 1042, determining a print head processing strategy according to the print head detection result;

[0102] Specifically, the fault type is determined based on the comparison result between the pre-processed printing platform pressure data in the print head detection result and the preset safety threshold, and the relevant strategy in the pre-stored print head fault handling strategy library is retrieved according to the fault type as the print head handling strategy, which is provided for user reference in the subsequent user processing process, so that users can eliminate and handle faults as quickly as possible, thereby improving fault handling efficiency.

[0103] Here, if the force magnitude in the pre-processed printing platform pressure data exceeds the force magnitude in the preset safety threshold, the fault may be caused by nozzle blockage, improper adjustment of the distance between the print head and the platform, poor material supply, or wear of mechanical parts. In this case, the print head may be subjected to excessive pressure, resulting in increased wear or damage. At this time, the corresponding print head processing strategy can be to unclog the nozzle, adjust the distance between the print head and the platform, check the material supply, or replace the mechanical parts; if the force direction in the pre-processed printing platform pressure data exceeds the force direction in the preset safety threshold (that is, the force direction is offset or unstable), the fault may be caused by loose mechanical structure, misaligned guide system, or abnormal control signal. In this case, the print head may not be able to accurately print the material to the predetermined position, resulting in reduced printing quality. At this time, the corresponding print head processing strategy can be tightening the mechanical structure, adjusting the guide system or the control signal; if the frequency and amplitude of the force change in the pre-processed printing platform pressure data exceed the frequency and amplitude of the force change in the preset safety threshold (such as the frequency and amplitude of the force change abnormally increase), the fault may be caused by unstable material supply, print head vibration or mechanical component failure. In this case, the print head may not be able to maintain a stable printing state, affecting the printing quality and equipment life. At this time, the corresponding print head processing strategy can be tightening the mechanical structure, adjusting the guide system or the control signal; checking the material supply and print head, replacing mechanical components, etc.; if the rate and acceleration of the force change in the pre-processed printing platform pressure data exceed the rate and acceleration of the force change in the preset safety threshold (such as the rate and acceleration of the force change suddenly increase or decrease), the fault may be caused by control system failure, mechanical component damage or improper printing parameter setting, etc. In this case, the print head may not be able to print according to the predetermined trajectory and speed, resulting in reduced printing quality or equipment damage. At this time, the corresponding print head processing strategy can be checking and repairing the control system, replacing mechanical components, resetting printing parameters, etc.;

[0104] Step 1043, determining a fault detection result according to the printing material detection result, the print head detection result, the material processing strategy and the print head processing strategy.

[0105] Specifically, the printing material detection results, print head detection results, material processing strategies and print head processing strategies can be summarized and output as fault detection results in the form of a report or table, so that users can intuitively see the content and results of the fault detection. At the same time, it is convenient for users to eliminate and handle faults according to corresponding processing strategies, thereby improving fault handling efficiency.

[0106] In an optional embodiment of the present invention, the method further comprises:

[0107] Step 105, generating alarm information and control parameters according to the fault detection result;

[0108] Specifically, if the fault detection result includes a fault in the printing material or the print head, a corresponding alarm message, such as "printing material fault" or "print head fault", is generated. The alarm message can be output to the terminal for the management personnel to view, so that the fault detection result can be checked and the fault can be handled in time; or the management personnel can be reminded to handle it in the form of sound and light. In addition, it is also necessary to call out the preset control parameters when a fault occurs. The control parameters can be the moving path of the print head, so as to control the print head to move to the preset position according to the moving path.

[0109] Step 106: output the warning information, and control the print head to move to a preset position according to the control parameters.

[0110] Specifically, the alarm information can be sent to the management personnel or monitoring personnel by wired or wireless means, and the sound and light alarm information can also be issued according to the alarm information to remind the management personnel or monitoring personnel of the printing failure, so that the personnel can check and handle it in time. At the same time, it is also necessary to send the control parameters to the controller of the 3D printing device so that it controls the print head to move to a preset position (such as the origin) according to the control parameters and wait for the failure to be resolved. This is conducive to improving the safety of the method and saving production costs.

[0111] A specific embodiment of the fault detection method for a three-dimensional printing device proposed in an embodiment of the present invention is:

[0112] Step 111, obtaining data.

[0113] like Figure 2 As shown, it is a structural schematic diagram of a simple 3D printing device, wherein a stress sensor is installed between the wire disc 1 and the print head 2 near the print head 2 (the stress sensor can be installed on the print head 2, or on a key node that the wire may pass through during the process of being transported to the print head, such as a guide wheel, a tensioning device, or the strain sensor is installed on a mechanical component that is in direct contact with the wire, such as a roller, a clamp, and can be selected and installed according to actual conditions), which is used to collect the stress state parameters (including the magnitude of the force, the direction of the force, the frequency and amplitude of the force change, etc.) of the wire 4 (i.e., the printing material) as the stress data of the printing material. A stress sensor is installed at the center position of the bottom of the printing platform 3 or the area with greater force, which is used to collect the stress state parameters (including the magnitude of the force, the direction of the force, the frequency and amplitude of the force change, etc.) of the printing platform when printing the forming device 5, and together with the force rate and acceleration calculated therefrom as the pressure data of the printing platform.

[0114] Step 112, printing material detection.

[0115] First, it is necessary to obtain the stress state parameters of the wire when the fused deposition modeling 3D printing device is working normally and without any faults, and then use this as a benchmark to set a preset stress threshold as a basis for detecting whether the printing material has a fault. When the printing material is tested, the stress state parameters of the wire obtained in real time are compared with the preset stress threshold to obtain a comparison result of whether the stress state parameters of the wire exceed the preset stress threshold. If exceeded, the printing material detection result includes a fault in the printing material.

[0116] Step 113: print head detection.

[0117] The stress state parameters of the printing platform acquired in real time are filtered or standardized, and then the key features therein, such as the force magnitude, force direction, frequency and amplitude of force changes, rate of force changes, acceleration, etc. are extracted and input into the fault prediction model as feature data to obtain a fault prediction result. The fault prediction result is the probability value (a value from 0 to 1) that the print head may fail. If the probability value of the fault prediction result is greater than a preset probability value (such as 0.8), it indicates that the print head may fail. At this time, it is necessary to compare the preprocessed printing platform pressure data with the preset safety threshold to further confirm whether the print head may fail. If one item of the preprocessed printing platform pressure data exceeds the preset safety threshold, it indicates that the print head may fail.

[0118] Step 114, determining the fault detection result.

[0119] If the printing material detection result shows that the printing material is faulty, the corresponding material processing strategy is retrieved from the pre-stored strategy library according to the specific force parameters in the printing material force data; if the print head detection result shows that the print head is faulty, the corresponding print head processing strategy is retrieved from the pre-stored print head fault processing strategy library according to the specific force parameters in the printing platform pressure data; all data and processing strategies involved in the detection process are summarized to form a fault detection result for the user to view.

[0120] Step 115: output warning information.

[0121] If the printing material and / or printing platform fails, an alarm will be issued in the form of text or sound and light to remind the management staff to deal with it in time.

[0122] Step 116, controlling the print head to move to the origin.

[0123] Move the print head to the origin to facilitate management personnel to handle faults.

[0124] The fault detection method of the three-dimensional printing device proposed in the embodiment of the present invention uses a stress sensor installed at any position between the wire tray and the print head to detect the supply status of the wire. When the wire feeding is normal, the wire will be subjected to a driving force to move toward the print head. When the material is cut off or the print head is blocked, the driving force will disappear or become very small. At this time, the stress sensor can detect the change and judge the feeding fault through the change. The stress sensor installed at the bottom of the printing platform is also used to collect the force data of the printing platform. When the material feeding is normal, the printing platform will be subjected to the pressure of the print head. When the material is cut off or blocked, the print head does not contact the printing platform and the printing platform is not subjected to force. The stress sensor installed at the bottom of the printing platform can detect the change and judge the feeding fault through the change.

[0125] In addition, when a material feeding failure is detected, an alarm signal can be sent to the control system of the 3D printing device. The control system will judge to suspend printing according to the preset program, move the print head to the origin position, and send a fault signal. When the fault is resolved, the print head will move according to the feedback of the sensor to extrude the material again. In this process, the control system will control the drive device to move the print head to the appropriate position, restart the extruder, and start extruding the material. When the material is extruded and connected to the previous work, the control system will control the print head again to complete the remaining printing work.

[0126] like Figure 3 As shown, an embodiment of the present invention provides a fault detection device 200 for a three-dimensional printing device, comprising:

[0127] An acquisition module 201 is used to acquire the printing material force data and the printing platform pressure data of the feeding system of the three-dimensional printing device;

[0128] The first processing module 202 is used to detect the printing material according to the printing material force data and a preset force threshold to obtain a printing material detection result;

[0129] The second processing module 203 is used to detect the print head according to the printing platform pressure data to obtain a print head detection result;

[0130] The third processing module 204 is used to determine a fault detection result according to the printing material detection result and the print head detection result.

[0131] Optionally, obtaining the printing material force data and printing platform pressure data of the feeding system of the 3D printing device includes:

[0132] Obtaining the stress data of the printing material through a stress sensor installed at a first preset position; the first preset position includes any position on the printing material between the wire tray of the feeding system and the print head;

[0133] The pressure data of the printing platform is obtained by installing a stress sensor at a second preset position; the second preset position includes a position at the bottom of the printing platform corresponding to the print head.

[0134] Optionally, the printing material is detected according to the printing material force data and a preset force threshold to obtain a printing material detection result, including:

[0135] Obtaining the force data of the printing material under preset conditions;

[0136] Determining a preset force threshold according to the force data of the printing material under preset conditions;

[0137] Comparing the printing material force data with the preset force threshold to obtain a comparison result;

[0138] The supply status of the printing material is detected according to the comparison result to obtain a printing material detection result.

[0139] Optionally, the print head is tested according to the printing platform pressure data to obtain a print head test result, including:

[0140] Preprocessing the printing platform pressure data to obtain preprocessed printing platform pressure data;

[0141] Extracting features from the preprocessed printing platform pressure data to obtain feature data;

[0142] Inputting the characteristic data into a trained fault prediction model to obtain a fault prediction result; the fault prediction model is obtained by training a preset network model based on historical printing platform pressure data;

[0143] The print head is tested according to the fault prediction result and the preset safety threshold to obtain a print head test result.

[0144] Optionally, the feature data is input into a trained fault prediction model to obtain a fault prediction result, including:

[0145] Inputting the characteristic data into a fault prediction model to obtain multiple prediction results;

[0146] A fault prediction result is obtained according to the multiple prediction results.

[0147] Optionally, determining a fault detection result according to the printing material detection result and the print head detection result includes:

[0148] Determining a raw material processing strategy according to the printing raw material detection result;

[0149] Determining a print head processing strategy according to the print head detection result;

[0150] A fault detection result is determined according to the printing material detection result, the print head detection result, the material processing strategy and the print head processing strategy.

[0151] Optionally, the device further comprises:

[0152] The fourth processing module 205 is used to generate alarm information and control parameters according to the fault detection result;

[0153] The fifth processing module 206 is used to output the warning information and control the print head to move to a preset position according to the control parameters.

[0154] The fault detection device for a three-dimensional printing device proposed in an embodiment of the present invention obtains the force data of the printing material and the pressure data of the printing platform, and detects the printing material and the print head respectively. According to the obtained printing material detection results and the print head detection results, the fault detection result is determined. It can simultaneously detect whether the printing material and the print head have faults, and has the advantage of relatively comprehensive and accurate detection results.

[0155] It should be noted that the device is a device corresponding to the above method, and all implementations in the above method embodiment are applicable to the embodiment of the device and can achieve the same technical effect. This embodiment will not be repeated.

[0156] The embodiment of the present invention further provides a computing device, comprising: a processor, and a memory storing a computer program, wherein when the computer program is executed by the processor, the method described in any one of the above embodiments is executed. All implementations in the above method embodiments are applicable to the embodiments of the device, and can achieve the same technical effects. They will not be described in detail in this embodiment.

[0157] The embodiment of the present invention further provides a computer-readable storage medium on which instructions are stored. When the instructions are executed on a computer, the computer executes the method as described in any one of the above embodiments. All implementations in the above method embodiments are applicable to the embodiments of the device and can achieve the same technical effects. They will not be described in detail in this embodiment.

[0158] It should be noted that, in the above-mentioned embodiments, the description of the method and steps, the order of steps, the sequence number of steps, etc. according to the embodiments of the present invention is only exemplary and is not used to limit the present invention. The term "include", "comprise" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the method and device in the implementation of the above-mentioned embodiment is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0159] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A fault detection method for a three-dimensional printing device, characterized in that: include: Obtaining the printing material force data and printing platform pressure data of the feeding system of the 3D printing device; Detecting the printing material according to the printing material force data and a preset force threshold to obtain a printing material detection result; Detecting the print head according to the printing platform pressure data to obtain a print head detection result; A fault detection result is determined according to the printing material detection result and the print head detection result.

2. The fault detection method of a three-dimensional printing device according to claim 1, characterized in that: Obtain the printing material force data and printing platform pressure data of the feeding system of the 3D printing equipment, including: Obtaining the stress data of the printing material through a stress sensor installed at a first preset position; the first preset position includes any position on the printing material between the wire tray of the feeding system and the print head; The pressure data of the printing platform is obtained by installing a stress sensor at a second preset position; the second preset position includes a position at the bottom of the printing platform corresponding to the print head.

3. The fault detection method of a three-dimensional printing device according to claim 1, characterized in that: The printing material is detected according to the printing material force data and the preset force threshold to obtain a printing material detection result, including: Obtaining the force data of the printing material under preset conditions; Determining a preset force threshold according to the force data of the printing material under preset conditions; Comparing the printing material force data with the preset force threshold to obtain a comparison result; The supply status of the printing material is detected according to the comparison result to obtain a printing material detection result.

4. The fault detection method of a three-dimensional printing device according to claim 1, characterized in that: The print head is tested according to the printing platform pressure data to obtain a print head test result, including: Preprocessing the printing platform pressure data to obtain preprocessed printing platform pressure data; Extracting features from the preprocessed printing platform pressure data to obtain feature data; Inputting the characteristic data into a trained fault prediction model to obtain a fault prediction result; the fault prediction model is obtained by training a preset network model based on historical printing platform pressure data; The print head is tested according to the fault prediction result and the preset safety threshold to obtain a print head test result.

5. The fault detection method of a three-dimensional printing device according to claim 4, characterized in that: The characteristic data is input into the trained fault prediction model to obtain a fault prediction result, including: Inputting the characteristic data into a fault prediction model to obtain multiple prediction results; A fault prediction result is obtained according to the multiple prediction results.

6. The fault detection method of a three-dimensional printing device according to claim 1, characterized in that: Determining a fault detection result according to the printing material detection result and the print head detection result includes: Determining a raw material processing strategy according to the printing raw material detection result; Determining a print head processing strategy according to the print head detection result; A fault detection result is determined according to the printing material detection result, the print head detection result, the material processing strategy and the print head processing strategy.

7. The fault detection method of a three-dimensional printing device according to claim 1, characterized in that: Also includes: generating alarm information and control parameters according to the fault detection result; The warning information is output, and the print head is controlled to move to a preset position according to the control parameters.

8. A fault detection device for a three-dimensional printing device, characterized in that: include: An acquisition module, used to acquire the printing material force data and the printing platform pressure data of the feeding system of the three-dimensional printing device; A first processing module, configured to detect the printing material according to the printing material force data and a preset force threshold, and obtain a printing material detection result; A second processing module is used to detect the print head according to the printing platform pressure data to obtain a print head detection result; The third processing module is used to determine a fault detection result according to the printing material detection result and the print head detection result.

9. A computing device, characterized in that include: A processor and a memory storing a computer program, wherein when the computer program is executed by the processor, the method according to any one of claims 1 to 7 is performed.

10. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer is caused to execute the method according to any one of claims 1 to 7.

Images