A real-time monitoring method and system for additive layer height based on dual laser coupling

Abstract

The present invention belongs to the field of additive manufacturing, and specifically discloses a method and system for real-time monitoring of additive layer height based on dual laser coupling, which includes: obtaining a first height sequence corresponding to the current printing point based on a first laser probe, the first height sequence at least including the first height corresponding to the current printing point and multiple preceding printing points; obtaining a second height sequence corresponding to the current printing point based on a second laser probe, the second height sequence at least including the second height corresponding to the current printing point and multiple preceding printing points; aligning the first height sequence and the second height sequence data; obtaining the layer height increment corresponding to the current printing point based on the aligned height sequence; the second laser probe is set in front and behind the first laser probe in the direction of the additive gun's travel, and moves with the additive gun so that its corresponding measurement points are respectively located in front and behind the additive melt pool. The present invention uses dual lasers to obtain the additive layer height point by point, which can realize real-time acquisition of layer height data.

Description

Technical Field

[0001] The present invention belongs to the field of additive manufacturing, and more specifically, relates to a method and system for real-time monitoring of additive layer height based on dual laser coupling. Background Art

[0002] Additive Manufacturing (AM) is a bottom-up, direct, rapid stacking technology based on three-dimensional models. With its unique advantages of short product design and development cycles, high production efficiency, and the ability to form complex parts, it has great application prospects in aerospace, ships, automobiles, weapons and equipment, and biomedicine.

[0003] Wire additive manufacturing technology refers to the use of high-energy beam heat sources, such as electric arcs, lasers, and electron beams, to melt filamentary raw materials, and then stack them layer by layer according to a set forming path until the forming is completed. Due to its high energy density, this additive manufacturing method often has a high stacking efficiency. However, high stacking efficiency also brings large dimensional errors, which makes it difficult to control the distance between the additive gun and the printed workpiece, and maintain parameter consistency, affecting the stability of the forming process, the surface quality of the formed part, and the dimensional accuracy. Therefore, for wire additive manufacturing technology, real-time monitoring of the additive layer height is essential. Summary of the Invention

[0004] In response to the above-mentioned defects or improvement needs of the prior art, the present invention provides a method and system for real-time monitoring of additive layer height based on dual laser coupling, the purpose of which is to quickly determine the layer height increment of the current printing point and realize real-time monitoring of the additive layer height.

[0005] To achieve the above objectives, according to one aspect of the present invention, a method for real-time monitoring of additive layer height based on dual laser coupling is proposed, comprising the following steps:

[0006] Acquire a first height sequence corresponding to a current printing point based on a first laser probe, wherein the first height sequence includes at least first heights corresponding to the current printing point and a plurality of previous printing points;

[0007] Acquire, based on a second laser probe, a second height sequence corresponding to the current printing point, where the second height sequence includes at least second heights corresponding to the current printing point and a plurality of preceding printing points;

[0008] Aligning the first height sequence with the second height sequence data;

[0009] Get the layer height increment corresponding to the current printing point based on the aligned height sequence;

[0010] Among them, the second laser probe and the first laser probe are arranged in front and behind each other in the direction of the additive gun's travel, and move with the additive gun. The measurement points corresponding to the second laser probe and the first laser probe are respectively located in front and behind the additive melt pool, and are at a certain distance from the melt pool.

[0011] As further preferred, the first laser probe and the second laser probe perform sampling based on the same sampling interval; and aligning the first height sequence data with the second height sequence data includes:

[0012] Acquire an alignment deviation, where the alignment deviation represents a difference in the number of bits stored in a database between the first height sequence and the second height sequence;

[0013] Based on the alignment deviation, the first height sequence data is aligned with the second height sequence data in a database.

[0014] As further preferred, obtaining the alignment deviation further includes:

[0015] Obtaining the relative distance and relative angle between the first laser probe and the second laser probe;

[0016] acquiring a height level of a current printing point based on the first height sequence and the second height sequence;

[0017] Determine the distance between the measurement point of the first laser probe and the measurement point of the second laser probe on the height horizontal plane, i.e., the measurement spacing, based on the height horizontal plane, the relative distance and relative angle between the first laser probe and the second laser probe;

[0018] The alignment deviation is determined based on the measurement distance, the additive gun speed, and the sampling interval.

[0019] As a further preferred embodiment, the first height sequence and the second height sequence further include position tags corresponding to the current printing point and a plurality of previous printing points, and the position tags are acquired by a motion platform during sampling, and the motion platform drives the additive gun, the first laser probe, and the second laser probe to move synchronously; and aligning the first height sequence with the second height sequence data includes:

[0020] The first height sequence and the second height sequence are aligned based on the position tags.

[0021] As a further preferred embodiment, obtaining the layer height increment corresponding to the current printing point based on the aligned height sequence includes:

[0022] Obtain the height measurement value corresponding to the current printing point, the height measurement value includes a first height and a second height;

[0023] Obtain historical height measurement values ​​corresponding to multiple printing points preceding the current printing point, where the historical height measurement values ​​also include a first height and a second height;

[0024] Based on the historical height measurement values ​​corresponding to the previous plurality of printing points, the height measurement value corresponding to the current printing point is corrected;

[0025] The layer height increment corresponding to the current printing point is determined based on the height measurement value corresponding to the current printing point after correction.

[0026] As a further preferred embodiment, based on the historical height measurement values ​​corresponding to the previous plurality of printing points, the height measurement value corresponding to the current printing point is corrected, including:

[0027] A weighted sum is performed on the height measurement value corresponding to the current printing point and the historical height measurement values ​​corresponding to one or more previous printing points, and the height measurement value corresponding to the current printing point is corrected.

[0028] As a further preferred embodiment, before obtaining the layer height increment corresponding to the current printing point based on the aligned height sequence, the aligned data is denoised.

[0029] As a further preferred embodiment, the denoising of the aligned data includes:

[0030] fitting to obtain a first height curve corresponding to the first height sequence and a second height curve corresponding to the first height sequence;

[0031] Noise is identified based on a difference between the first height curve and the second height curve, thereby removing the noise from the alignment data.

[0032] As a further preferred embodiment, the denoising of the aligned data includes:

[0033] The aligned data is subjected to noise removal based on a noise removal model, wherein the noise removal model is a pre-trained CNN convolutional neural network.

[0034] According to another aspect of the present invention, a real-time monitoring system for additive layer height based on dual laser coupling is provided, comprising:

[0035] A first height sequence acquisition module is configured to acquire a first height sequence corresponding to a current printing point based on a first laser probe, wherein the first height sequence includes at least first heights corresponding to the current printing point and a plurality of preceding printing points;

[0036] A second height sequence acquisition module, configured to acquire a second height sequence corresponding to the current printing point based on a second laser probe, wherein the second height sequence includes at least second heights corresponding to the current printing point and a plurality of preceding printing points;

[0037] A sequence data alignment module, configured to align the first height sequence with the second height sequence data;

[0038] The current printing point layer height increment acquisition module is used to obtain the layer height increment corresponding to the current printing point based on the aligned height sequence;

[0039] Among them, the second laser probe and the first laser probe are arranged in front and behind each other in the direction of the additive gun's travel, and move with the additive gun. The measurement points corresponding to the second laser probe and the first laser probe are respectively located in front and behind the additive melt pool, and are at a certain distance from the melt pool.

[0040] In general, the above technical solutions conceived by the present invention have the following technical advantages compared with the existing technology:

[0041] 1. Based on dual lasers to collect layer height data before and after additive manufacturing, the additive layer height can be quickly obtained point by point, and real-time acquisition of layer height data can be achieved, which provides a basis for real-time adjustment of additive manufacturing and can operate in a strong arc light environment.

[0042] 2. A data alignment method for the additive manufacturing process was constructed, which achieved fast alignment of asynchronous data and reduced the time required for system processing.

[0043] 3. Based on the noise characteristics of additive manufacturing and the principle of background consistency, the rapid flattening of abnormal data points with the same background is achieved, avoiding large coupling errors while not occupying a large amount of computing power to serve the denoising process. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 Schematic diagram of a real-time monitoring system for additive layer height based on dual laser coupling according to an embodiment of the present invention;

[0045] Figure 2 This is a flow chart of a method for real-time monitoring of additive layer height based on dual laser coupling according to an embodiment of the present invention;

[0046] Figure 3 Schematic diagram of a data alignment method according to an embodiment of the present invention;

[0047] Figure 4 Schematic diagram of storage format of the aligned first height sequence and the second height sequence in a database according to an embodiment of the present invention;

[0048] Figure 5 This is a schematic diagram of data correction based on historical altitude data according to an embodiment of the present invention.

[0049] In all drawings, the same reference numerals are used to denote the same elements or structures, where: 100 - control system, 161 - first laser probe, 162 - second laser probe, 170 - additive gun. DETAILED DESCRIPTION

[0050] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely for the purpose of explaining the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.

[0051] Figure 1 Schematic diagram of a real-time monitoring system for additive layer height based on dual laser coupling according to some embodiments of this specification.

[0052] like Figure 1 As shown, the system includes: a control system 100, a first laser probe 161, a second laser probe 162, an additive gun 170, and a motion actuator (not shown). The motion actuator can be a truss robot, a robotic arm, or the like with three, four, five, six, or seven axes, and this specification does not limit this.

[0053] In some embodiments, the additive gun 170 can be any one of an arc additive gun, a laser powder feeding additive gun, and an electron beam additive gun. In some embodiments, the additive gun 170 is connected to the motion actuator and is driven by the motion actuator to perform trajectory motion.

[0054] The second laser probe 162 and the first laser probe 161 are respectively positioned in front and behind the additive gun 170 and move with the gun, with front and back referring to the direction of the gun's travel. The corresponding measurement points of the second laser probe 162 and the first laser probe 161 are located in front of and behind the additive melt pool, respectively, and at a certain distance from the melt pool. The first and second laser probes 161 and 162 use infrared ranging to measure the distance between the workpiece surface and the probes, and are designed to be adjustable based on the mounting position of the laser probes relative to the additive gun 170.

[0055] In some embodiments, the first laser probe 161 and the second laser probe 162 are fixedly connected to the additive gun 170 and move along with the motion actuator. In some embodiments, the first laser probe 161 and the second laser probe 162 are detachably or adjustably connected to the additive gun 170.

[0056] The control system 100 may include a computer device capable of processing programs, such as a PC or a PLC, and may include a first height sequence acquisition module 110 , a second height sequence acquisition module 120 , a sequence data alignment module 130 , and a current print dot layer height increment acquisition module 150 .

[0057] The first height sequence acquisition module 110 is configured to acquire a first height sequence corresponding to a current printing point based on a first laser probe, wherein the first height sequence includes at least first heights corresponding to the current printing point and a plurality of preceding printing points.

[0058] The second height sequence acquisition module 120 is configured to acquire a second height sequence corresponding to the current printing point based on a second laser probe, where the second height sequence includes at least the second heights corresponding to the current printing point and a plurality of preceding printing points.

[0059] The sequence data alignment module 130 is configured to align the first height sequence data with the second height sequence data.

[0060] The current printing point layer height increment acquisition module 150 is configured to acquire the layer height increment corresponding to the current printing point based on the aligned height sequence.

[0061] In some embodiments, the first laser probe and the second laser probe perform sampling based on the same sampling interval, and the sequence data alignment module 130 is further configured to: obtain an alignment deviation, wherein the alignment deviation represents the difference in the number of bits stored in the database between the first height sequence and the second height sequence; and align the first height sequence and the second height sequence data in the database based on the alignment deviation. In some embodiments, the sequence data alignment module 130 is further configured to: obtain the relative distance and relative angle between the first and second laser probes; obtain the height plane of the current printing point based on the first and second height sequences; determine the distance of the measurement points on the height plane based on the relative distance and relative angle between the first and second laser probes; and determine the alignment deviation based on the distance of the measurement points and the sampling interval.

[0062] In some embodiments, the first height sequence and the second height sequence also include position tags corresponding to the current printing point and the preceding multiple printing points, and the position tags are acquired by the mechanical motion platform during sampling. In this embodiment of the scenario, the sequence data alignment module 130 is further configured to align the first height sequence with the second height sequence based on the position tags.

[0063] In some embodiments, the current printing point layer height increment acquisition module 150 is also used to: obtain the layer height measurement value corresponding to the current printing point; obtain the historical layer height measurement values ​​corresponding to multiple printing points preceding the current printing point; and determine the layer height increment corresponding to the current printing point based on the weighted sum of the layer height measurement value corresponding to the current printing point and the one or more historical layer height measurement values.

[0064] In some embodiments, the control system 100 further includes a denoising module 140 , which is configured to denoise noise data based on a signal processing method before obtaining the layer height increment corresponding to the current printing point based on the aligned height sequence.

[0065] In some embodiments, the denoising module 140 fits a height curve corresponding to the first height sequence and a height curve corresponding to the second height sequence; and removes noise data based on the difference between the height curves.

[0066] In some embodiments, the denoising module 140 is further configured to: obtain a noise removal model, and perform noise removal based on the noise removal model, wherein the noise removal model is a convolutional neural network (CNN). In some embodiments, the denoising module 140 performs noise removal model training, specifically including the following training process: obtaining multiple noise data under typical noise conditions; generating multiple noise spectra based on the multiple noise data; and training an initial noise removal model based on the multiple noise spectra, iterating layer by layer until the model converges.

[0067] It should be understood that the systems and modules in one or more embodiments of this specification can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of software and hardware. The hardware portion can be implemented using dedicated logic; the software portion can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated hardware. Those skilled in the art will understand that the above methods and systems can be implemented using computer-executable instructions and / or contained in processor control code, for example, such code is provided on a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of this specification can be implemented not only by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, but can also be implemented by software executed by various types of processors, or by a combination of the above hardware circuits and software (for example, firmware).

[0068] It should be noted that the above description of the processing device and its modules is for convenience only and does not limit this specification to the scope of the embodiments described. It is understood that those skilled in the art, after understanding the principles of the system, may arbitrarily combine the modules or form subsystems connected to other modules without departing from these principles.

[0069] Figure 2 2 is a flow chart of a method for real-time monitoring of additive layer height based on dual laser coupling according to some embodiments of this specification. In some embodiments, the method 200 may be further executed by the system 100.

[0070] Step 210 : Acquire a first height sequence corresponding to the current printing point based on the first laser probe.

[0071] In some embodiments, step 210 may be performed by the first height sequence acquisition module 110 .

[0072] The first height sequence acquisition module 110 can be connected to the first laser probe based on a communication interconnection method to obtain the height data obtained by the first laser probe in real time. The first laser probe can be a point laser measuring device to obtain the positional relationship between the laser probe and the printing surface. In some embodiments, in order to prevent the influence of strong light on the detection accuracy during the additive manufacturing process, a light baffle or a strong light shielding device can be installed on the surface of the first laser probe to shield the strong light. The strong light shielding device can be a different setting for the additive manufacturing process. For example, for arc additive manufacturing, the strong light shielding device can be an 808nm oscillator to shield other light except 808nm.

[0073] Step 220: Acquire a second height sequence corresponding to the current printing point based on a second laser probe.

[0074] In some embodiments, step 220 may be performed by the second height sequence acquisition module 120 .

[0075] Similarly, the second height sequence acquisition module 120 can be connected to the second laser probe based on a communication interconnection method to obtain the height data obtained by the second laser probe in real time, which will not be described in detail here.

[0076] Step 230: align the first height sequence data with the second height sequence data.

[0077] In some embodiments, step 230 may be performed by the sequence data alignment module 130 .

[0078] In some embodiments, the first laser probe and the second laser probe perform sampling based on the same sampling interval. For example, the sampling interval is 0.4 ms. In an embodiment of this scenario, the sequence data alignment module 130 can obtain an alignment deviation, which represents the difference in the number of bits stored in the database between the first height sequence and the second height sequence; based on the alignment deviation, the first height sequence and the second height sequence data are aligned in the database.

[0079] Specifically, if Figure 3 The data alignment method in one or more embodiments involved in this specification is shown. For example, 310 in the figure represents a first height sequence, and 320 represents a second height sequence. Since the first laser and the second laser probe are distributed on the front and back sides of the molten pool, there is a relative distance between the two probes. Based on this, there will be a storage bit deviation in the data of the two in the cache. In order to quickly obtain the height information of the current additive point, the difference in the number of bits stored in the cache of the data of the two, that is, the alignment deviation, can be obtained, and then the first height sequence and the second height sequence data can be aligned in the database. In some embodiments, this alignment deviation can be manually obtained or calibrated before printing begins.

[0080] In some embodiments, the sequence data alignment module 130 may also calculate the alignment deviation based on the relative position between the first laser probe and the second laser probe. Specifically, the steps include:

[0081] 1) Obtaining the relative distance and relative angle between the first laser probe and the second laser probe. The relative distance and relative angle can be obtained based on measurement. In some embodiments, the first laser probe and the second laser probe are connected using an automatic displacement device. The corresponding parameters can be obtained based on the displacement angle of the automatic displacement device.

[0082] 2) Obtaining the height plane of the current printing point based on the first height sequence and the second height sequence. Because the measured heights of the first laser probe and the second laser probe are different, the height plane can be determined by taking a weighted average of the heights measured by the first laser probe and the second laser probe. Preferably, the weighting of the two laser probes can be set to 0.5:0.5.

[0083] 3) Based on the height level, the relative distance and relative angle between the first laser probe and the second laser probe are determined to determine the distance between the two laser probe measurement points on the height level, that is, the measurement spacing.

[0084] S4) Determining the alignment deviation based on the measurement spacing and the sampling interval. After determining the distance between the measurement points on the height plane, the difference in the number of measurement points between the two is calculated based on the sampling interval and the speed of the additive gun. This difference is the alignment deviation.

[0085] For example, if the sampling interval between the first laser probe and the second laser probe is 0.4ms, the moving speed of the additive gun is 40mm / s, and the corresponding measurement interval between the first laser probe and the second laser probe is 10mm, then the corresponding number of measurement points can be Calculation. The alignment deviation between the first and second laser probes is 625. This method allows for rapid data alignment between the first and second height sequences. This data alignment is achieved within the industrial control system's cache, significantly reducing data processing time and enabling instant response to height data.

[0086] In some embodiments, the first and second height sequences also include position tags corresponding to the current print point and the preceding multiple print points. These position tags are acquired by a processor system corresponding to the mechanical motion platform (motion actuator) during sampling. In an embodiment of this scenario, the control system 100, while recording the first and second height sequences, also records the position coordinates of the motion platform (such as the relative encoder coordinates or absolute encoder coordinates corresponding to the motion platform). Based on this calculation, the distance between the first and second laser probes in the height plane is directly calculated, and the relationship between the two laser probes in the motion platform position coordinates is directly obtained. The first and second height sequences are aligned based on the position coordinate relationship. In an embodiment of this scenario, the first and second height sequences can use different sampling frequencies. This allows the first and second laser probes to use products with different parameters. For example, the second laser probe at the front end of the additive gun, which is directly affected by the strong arc light, can use a device with a higher anti-interference level, while the first laser probe at the rear end of the arc has relatively lower requirements and can use a device with a lower anti-interference level. However, in comparison, this method requires more time to perform data alignment because it involves coordinate comparison.

[0087] Step 250 : Obtain the layer height increment corresponding to the current printing point based on the aligned height sequence.

[0088] In some embodiments, step 250 may be performed by the current printing dot layer height increment acquisition module 150 .

[0089] The current printing point layer height increment acquisition module 150 can calculate the height of the current point based on the compared first height sequence and the second height sequence. Figure 3For point 1 shown in the figure, the second laser probe measures the part height X1' before additive manufacturing, while the first laser probe measures the part height X1 after additive manufacturing. The incremental layer height at point 1 after additive manufacturing is calculated based on the aligned (X1'-X1) in the database. This method achieves the most accurate incremental layer height with extremely high computational efficiency, virtually eliminating any computational delays and lags, making it suitable for real-time adjustment of additive manufacturing travel mechanisms.

[0090] In some embodiments, before executing step 250 , process 200 further includes step 240 , denoising the noise data based on a signal processing method.

[0091] In some embodiments, step 240 may be performed by the denoising module 140 .

[0092] During the additive manufacturing printing process, due to the influence of strong light, splashing, etc., some ambiguous points and jump points are prone to appear in the height detection process. These ambiguous points and jump points will significantly affect the measurement results and cause large errors in height detection.

[0093] In some embodiments, the denoising module 140 can perform data processing based on wavelet analysis. Wavelet analysis for signal and image compression is an important aspect of its application. It is characterized by high compression ratios, fast compression speeds, the ability to preserve signal and image characteristics after compression, and resistance to interference during transmission. Exemplary methods include the wavelet packet best basis method, the wavelet domain texture model method, wavelet transform zerotree compression, and wavelet transform vector compression.

[0094] In some embodiments, the denoising module 140 may also implement noise filtering using a Kalman filter. Kalman filtering is an algorithm that uses the system state equation and system input and output observation data to optimally estimate the system state. In some embodiments, Kalman filtering methods include, but are not limited to, one or more of the following filter estimation methods: linear Kalman filtering, extended Kalman filtering, progressive extended Kalman filtering, and unscented Kalman filtering.

[0095] In some embodiments, the denoising method further includes: performing noise removal based on a noise removal model, wherein the noise removal model is constructed based on a CNN convolutional neural network. In an embodiment of this scenario, the noise removal model is trained based on the following method: obtaining multiple noise data under typical noise conditions, generating multiple noise maps based on the multiple noise data, and identifying noise locations from the noise maps to construct a data set; training the CNN convolutional neural network based on the data set, iterating layer by layer until the model converges, thereby obtaining the noise removal model.

[0096] It is understandable that while the above noise removal method can obtain relatively accurate measurements, the noise removal method takes a certain amount of time, resulting in a significant data delay in the final, real-time floor height measurement data. Therefore, one or more embodiments of this specification also relate to a data processing method that processes data values ​​sampled simultaneously by two laser probes to achieve rapid output processing and calculation.

[0097] like Figure 4 The diagram shows how the aligned first and second height sequences are stored in a database of a processing system (e.g., control system 100) in some embodiments. The alignment deviation is 2. In this scenario, X3 (the height of print point 3) in the second height sequence and X1' (the height of print point 1) in the first height sequence are data collected by the second laser probe and the first laser probe, respectively, when the motion actuator moves to the same point. In other words, X3 in the second height sequence and X1' in the first height sequence are data collected at the same time and under the same conditions, with the same background (e.g., light intensity, splashing, etc.) and similar noise.

[0098] In an embodiment of this scenario, historical data can be processed to obtain a noise deviation value corresponding to the current printing point. Furthermore, layer height data can be corrected based on the noise deviation value, including the following steps:

[0099] 1) Obtaining a height measurement value corresponding to the current printing point, including a height measurement value corresponding to the first height sequence and a height measurement value corresponding to the second height sequence;

[0100] 2) Obtaining historical height measurement values ​​corresponding to a plurality of printing points preceding the current printing point, the historical height measurement values ​​also including height measurement values ​​corresponding to the first height sequence and height measurement values ​​corresponding to the second height sequence;

[0101] 3) Based on the historical height measurement values ​​corresponding to the multiple printing points preceding the current printing point, data processing is performed to obtain the data deviation;

[0102] 4) Correct the data deviation of the current printing point based on the data deviation;

[0103] 5) Determine the layer height of the current printing point based on the height measurement value after data deviation.

[0104] Specifically, if Figure 5 The figure shows a typical schematic diagram of data correction based on historical height data.

[0105] Figure 5In the example, the splashing during printing causes a large data deviation at point 5. For example, the alignment deviation is 2. Therefore, according to the above method, subtracting the second height data Y3 corresponding to point 3 from the first height data Y5' collected at point 5 (where a point refers to a storage location, i.e., Y5' and Y3 are height data acquired by two probes at the same location) will result in a large data error. In the real-time example of this scenario, historical data can be used to smooth the peaks to reduce the error. The specific steps are as follows:

[0106] 1) Determine the deviation type of the error point. Calculate the pseudo-height of the current point point by point. The pseudo-height is obtained based on the absolute value of the difference between the first height sequence and the second height sequence of each point. Figure 5 For point 5 in the figure, use |Y5'-Y5|. It can be understood that Y5' and Y5 are the height data obtained by the two probes at the same time. Because the first laser probe and the second laser probe do not measure the same printed point at the same time, the value of this point can only reflect the degree of coupling error of the data, and cannot reflect the actual value of the error. If the pseudo-layer height of point 5 is not much different from the pseudo-layer height of the other points, it proves that the error comes from accidental errors caused by factors such as background and metal splash, and subsequent calculations can be performed. Otherwise, that is, the pseudo-layer height of point 5 is significantly different from the pseudo-layer height of the other points, exceeding the preset threshold, it means that the error does not come from accidental reasons such as background, but is an accidental true value (such as a sudden increase in melting height caused by the jump of the welder, or an increase in welder voltage caused by voltage changes in the entire experimental environment), then Y5' is used to directly calculate the layer height.

[0107] 2) Calculate the new corrected height value of point 5 by weighted averaging the height measurements of the first height sequence in point 5. For example, Y5" = w1*Y5' + w2*Y4' + w3*Y3' + w4*Y2' + w5*Y1', where w1-w5 represent weights, and their sum is 1. In some embodiments, to enhance the accuracy of the calculation, the weight of w1 is greater than 0.8.

[0108] 3) Use the corrected Y5" and the second height data Y3 corresponding to point 3 to obtain the floor height data.

[0109] It is understandable that although there will be height fluctuations during the additive manufacturing process, the overall height will not have too large a difference. Based on this principle, this method uses pseudo-layer height to determine the error type, and then realizes peak processing of height data based on historical height measurement values ​​to avoid excessive layer height measurement deviations. This method ensures a certain degree of detection accuracy while taking into account ultra-fast calculation results.

[0110] In some embodiments, denoising module 140 can also implement the aforementioned outlier peak smoothing method based on a fitting approach. For example, a height curve corresponding to the first height sequence and a height curve corresponding to the second height sequence are fitted, and noise data is removed based on the difference between the height curves. While fitting achieves a more effective peak smoothing effect, it consumes a certain amount of computational time to achieve curve fitting, which reduces the response time of the floor height data.

[0111] This specification uses specific terms to describe the embodiments of this specification. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that the mention of "one embodiment," "an embodiment," or "an alternative embodiment" two or more times in different places in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics of one or more embodiments of this specification may be appropriately combined.

[0112] Aspects of this specification may be illustrated and described in terms of several patentable categories or situations, including any new and useful process, machine, product or combination of substances, or any new and useful improvement thereof. Accordingly, various aspects of this specification may be performed entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as "data blocks", "modules", "engines", "units", "components" or "systems". In addition, various aspects of this specification may be represented as a computer product located in one or more computer-readable media, which includes computer-readable program code.

[0113] A computer storage medium may include a propagated data signal embodying the computer program code, for example, in baseband or as part of a carrier wave. The propagated signal may be in a variety of forms, including electromagnetic, optical, or any suitable combination thereof. A computer storage medium may be any computer-readable medium other than a computer-readable storage medium that can be connected to an instruction execution system, apparatus, or device to communicate, propagate, or transfer the program for use. The program code on the computer storage medium may be transmitted via any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of these.

[0114] The computer program codes required for the operation of the various parts of this specification can be written in any one or more programming languages, including object-oriented programming languages ​​such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages ​​such as C, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages ​​such as Python, Ruby and Groovy, or other programming languages. The program code can be run entirely on the device computer, or as a separate software package on the device computer, or partly on the device computer and partly on a remote computer, or entirely on a remote computer or processing device. In the latter case, the remote computer can be connected to the device computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0115] It will be easily understood by those skilled in the art that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for real-time monitoring of additive layer height based on dual laser coupling, characterized in that: The steps include: Acquire a first height sequence corresponding to a current printing point based on a first laser probe, wherein the first height sequence includes at least first heights corresponding to the current printing point and a plurality of previous printing points; Acquire, based on a second laser probe, a second height sequence corresponding to the current printing point, where the second height sequence includes at least second heights corresponding to the current printing point and a plurality of preceding printing points; Aligning the first height sequence with the second height sequence data; Get the layer height increment corresponding to the current printing point based on the aligned height sequence; Among them, the second laser probe and the first laser probe are arranged in front and behind each other in the direction of the additive gun's travel, and move with the additive gun. The measurement points corresponding to the second laser probe and the first laser probe are respectively located in front and behind the additive melt pool, and are at a certain distance from the melt pool.

2. The method for real-time monitoring of additive layer height based on dual laser coupling according to claim 1, characterized in that: The first laser probe and the second laser probe perform sampling based on the same sampling interval; and aligning the first height sequence data with the second height sequence data includes: Acquire an alignment deviation, where the alignment deviation represents a difference in the number of bits stored in a database between the first height sequence and the second height sequence; Based on the alignment deviation, the first height sequence data is aligned with the second height sequence data in a database.

3. The method for real-time monitoring of additive layer height based on dual laser coupling according to claim 2, characterized in that: The obtaining of the alignment deviation further comprises: Obtaining the relative distance and relative angle between the first laser probe and the second laser probe; acquiring a height level of a current printing point based on the first height sequence and the second height sequence; Determine the distance between the measurement point of the first laser probe and the measurement point of the second laser probe on the height horizontal plane, i.e., the measurement spacing, based on the height horizontal plane, the relative distance and relative angle between the first laser probe and the second laser probe; The alignment deviation is determined based on the measurement distance, the additive gun speed, and the sampling interval.

4. The method for real-time monitoring of additive layer height based on dual laser coupling according to claim 1, characterized in that: The first height sequence and the second height sequence also include position tags corresponding to the current printing point and multiple previous printing points. The position tags are acquired by a motion platform during sampling, and the motion platform drives the additive gun, the first laser probe, and the second laser probe to move synchronously. Aligning the first height sequence with the second height sequence data includes: The first height sequence and the second height sequence are aligned based on the position tags.

5. The method for real-time monitoring of additive layer height based on dual laser coupling according to any one of claims 1 to 4, characterized in that: The step of obtaining the layer height increment corresponding to the current printing point based on the aligned height sequence includes: Obtain the height measurement value corresponding to the current printing point, the height measurement value includes a first height and a second height; Obtain historical height measurement values ​​corresponding to multiple printing points preceding the current printing point, where the historical height measurement values ​​also include a first height and a second height; Based on the historical height measurement values ​​corresponding to the previous plurality of printing points, the height measurement value corresponding to the current printing point is corrected; The layer height increment corresponding to the current printing point is determined based on the height measurement value corresponding to the current printing point after correction.

6. The method for real-time monitoring of additive layer height based on dual laser coupling according to claim 5, characterized in that: Correcting the height measurement value corresponding to the current printing point based on the historical height measurement values ​​corresponding to the previous plurality of printing points includes: A weighted sum is performed on the height measurement value corresponding to the current printing point and the historical height measurement values ​​corresponding to one or more previous printing points, and the height measurement value corresponding to the current printing point is corrected.

7. The method for real-time monitoring of additive layer height based on dual laser coupling according to any one of claims 1 to 4, characterized in that: Before obtaining the layer height increment corresponding to the current printing point based on the aligned height sequence, the aligned data is denoised.

8. The method for real-time monitoring of additive layer height based on dual laser coupling according to claim 7, characterized in that: The denoising of the aligned data includes: fitting to obtain a first height curve corresponding to the first height sequence and a second height curve corresponding to the first height sequence; Noise is identified based on the difference between the first height curve and the second height curve, thereby removing the noise from the alignment data.

9. The method for real-time monitoring of additive layer height based on dual laser coupling according to claim 7, characterized in that: The denoising of the aligned data includes: The aligned data is subjected to noise removal based on a noise removal model, wherein the noise removal model is a pre-trained CNN convolutional neural network.

10. A real-time monitoring system for additive layer height based on dual laser coupling, characterized in that: include: A first height sequence acquisition module is configured to acquire a first height sequence corresponding to a current printing point based on a first laser probe, wherein the first height sequence includes at least first heights corresponding to the current printing point and a plurality of preceding printing points; A second height sequence acquisition module, configured to acquire a second height sequence corresponding to the current printing point based on a second laser probe, wherein the second height sequence includes at least second heights corresponding to the current printing point and a plurality of preceding printing points; A sequence data alignment module, configured to align the first height sequence with the second height sequence data; The current printing point layer height increment acquisition module is used to obtain the layer height increment corresponding to the current printing point based on the aligned height sequence; Among them, the second laser probe and the first laser probe are arranged in front and behind each other in the direction of the additive gun's travel, and move with the additive gun. The measurement points corresponding to the second laser probe and the first laser probe are respectively located in front and behind the additive melt pool, and are at a certain distance from the melt pool.

Images