DETECTION AND LOCATION OF POWDER SPREADING ANOMALIES USING ACOUSTIC EMISSION MEASUREMENTS

Abstract

Device for manufacturing a part using a method of selective fusion or selective sintering on a powder bed comprising a build plate having a working surface, parallel to a first direction and to a second direction, on which surface the part is intended to be manufactured, a wiper which is placed on the working surface and capable of moving and spreading the powder in the first direction on the working surface, characterized in that it further includes at least two acoustic sensors which are fixed and spaced in the second direction on the wiper and capable of detecting an acoustic signal; a laser range finder pointing in the first direction and capable of determining a position of the wiper in the first direction; and a control system capable of detecting an anomaly on the basis of said acoustic signal and of determining a position of the anomaly.

Claims

1. A device for manufacturing a part using a method of selective fusion or selective sintering on a powder bed comprising a build plate having a working surface, parallel to a first direction and to a second direction, on which surface the part is intended to be manufactured, a wiper which is placed on the working surface and capable of moving and spreading the powdery in the first direction on the working surface, characterized in that wherein it further comprises: at least two acoustic sensors which are fixed and spaced in the second direction on the wiper and capable of detecting an acoustic signal; a laser range finder pointing in the first direction and capable of determining a position of the wiper in the first direction; and a control system capable of detecting an anomaly on the basis of said acoustic signal and of determining a position of the anomaly along the first and second directions on the basis of the acoustic signal detected by said acoustic sensors and a position signal measured by said laser range finder and along a third direction by a number of layers of powder spread by the wiper.

2. The device according to claim 1, wherein the laser range finder is fixed on the wiper.

3. The device according to claim 1, wherein each acoustic sensor is fixed on the wiper by gluing or by a mechanical connection.

4. The device according to claim 1, wherein the control system is a machine learning system.

5. The device according to claim 4, wherein the machine learning system is a neural network.

6. The device according to claim 5, wherein the neural network is a convolutional neural network.

7. The device according to claim 4, wherein the machine learning system is a system of decision trees or a forest of decision trees.

8. A method for detecting an anomaly implemented by a device according to claim 1, comprising the following steps: detecting an acoustic signal by the at least two acoustic sensors; determining the position of the anomaly, the position of the anomaly being determined in the first direction by the position signal measured by the laser range finder, in the second direction by a time lag of the acoustic signal detected by the at least two acoustic sensors and in a third direction by a number of layers of powder spread by the wiper; and classifying the anomaly according to its severity.

9. The method for manufacturing a part by selective fusion or selective sintering on a powder bed comprising a step of detecting anomalies by the detection method according to claim 8.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Other features and advantages of the present invention will emerge from the description given below, with reference to the appended drawings which illustrate examples of embodiments without any limiting character.

[0036] FIG. 1 shows a device for manufacturing a part by selective fusion or selective sintering on a powder bed according to one embodiment of the invention.

[0037] FIG. 2 shows a wiper of the manufacturing device according to one embodiment of the invention.

DESCRIPTION OF EMBODIMENTS

[0038] FIG. 1 shows a device 100 for manufacturing a part by selective fusion or selective sintering on a powder bed comprising a build plate 101 having a working surface 102 on which the part is manufactured. The device 100 also comprises a wiper 110 which allows to spread the powder 103 in the direction X by moving on the working surface 102. The wiper 110 thus moves in a plane formed by the axes (X, Y) and the build plate 101 as well as the working surface 102 are parallel to this plane. The number of layers of powder deposited and spread defines the thickness of the final part along the axis Z.

[0039] After the spreading of the powder by the wiper 110, areas 160 of the working surface 102 are heated by an energy source, such as a laser beam or an electron beam, so as to sinter or fuse the powder in these areas 160.

[0040] In order to detect anomalies 150 resulting from contact or absence of contact between the powder and the wiper 110, the device 100 also comprises a laser range finder 130 and two acoustic sensors 121 and 122. The laser range finder 130 is fixed to one end 170 of the device 100 and is pointing towards the wiper 110 in the direction X. The range finder 130 allows to measure the position of the wiper 110 in the direction X, which allows to determine the position of any anomaly 150 in this same direction X.

[0041] The two acoustic sensors 121 and 122 are fixed on the wiper 110. They are spaced apart in the direction Y. When contact takes place between the wiper 110 and the powder 103 spread on the working surface 102, acoustic waves are emitted and propagate in the wiper 110. By propagating in the wiper, these acoustic waves are detected by the two acoustic sensors 121 and 122. Thanks to the data transmitted by the acoustic sensors 121 and 122, a control system 140 identifies or not an anomaly. These same data also allow to determine the position of the anomaly 150 in the direction Y. Indeed, thanks to the time lag between the detections of the acoustic wave by the two sensors 121 and 122, it is possible to go back to the position of the contact and therefore of the anomaly 150 in the direction Y.

[0042] The control system 140 determines the position of the anomaly 150 in the direction X, which is the position of the wiper 110 in this same direction X measured by the laser range finder 130.

[0043] The determination of the position of the anomaly 150 in the direction Z by the control system 140 is given by the number of layers of powder 103 deposited and spread on the build plate 101.

[0044] The laser range finder 130 and the acoustic sensors 121 and 122 can be fixed to the device 100 by gluing or by a mechanical connection.

[0045] According to a particular feature of the invention, the acoustic sensors 121 and 122 are placed respectively at ⅓ and at ⅔ of the length of the wiper 110 in the direction Y.

[0046] If no wave is detected by the two acoustic sensors 121 and 122, this means either that there is no more powder to spread or that the wiper 110 has reached the end of its travel, or that there is a hole in the powder bed 103 which may be an anomaly. It will be the control system 140 which will determine whether or not the absence of acoustic signals constitutes an anomaly. In the same way, the position of this hole in the powder 103 can be determined thanks to the time lag between the two acoustic sensors 121 and 122.

[0047] The control system 140 may be a machine learning system. The system 140 can thus learn to classify the acoustic waveforms detected by the acoustic sensors 121 and 122 contacts, to determine whether the contact, or the absence of contact, is an anomaly 150 and then classify this anomaly 150 according to its severity. Indeed, an anomaly 150 can be the result of a gas bubble, a hole in the spread powder, an elevation of the powder, an incomplete spread of the powder, traces in the spread or else of uneven spreading. These anomalies do not have the same level of severity. Generally, the most severe anomalies result from the elevation of powder, traces in the spread, and uneven spreading in the plane (X, Y) of the working surface 102. The classification according to the severity of the anomalies allows the control system 140 to give or predict the risk of damage to the wiper, to the final part and to decide whether or not production should be interrupted.

[0048] The classification of detected anomalies 150 can be done according to the features of the detected waves: waveform, amplitude, duration, etc.

[0049] According to a particular feature of the invention, the machine learning system is selected from a convolutional neural network, a system based on probabilistic modeling, a system based on a kernel algorithm, decision trees, a forest of decision trees or a gradient implementation system. A convolutional neural network will, for example, allow automatic extraction and prioritization of contacts and non-contacts detected in order to classify anomalies according to their severity.

[0050] FIG. 2 shows a wiper 210, and more particularly the arrangement of the acoustic sensors 221 and 222 and of the laser range finder 230 according to another embodiment of the invention. The two acoustic sensors 221 and 222 are still fixed on the wiper 210 and spaced in the direction Y. In order to obtain a significant time lag to determine the position of the anomaly 250 in the direction Y, the acoustic sensors 221 and 222 are each placed on one end of the wiper 210.

[0051] The laser range finder 230 is fixed on the wiper 210 and is always pointing in the direction X to determine the position of the wiper 210 and of the anomaly 250 in this same direction X.

[0052] According to a particular feature of the invention, the laser range finder 230 is placed in the middle of the wiper 210 between the two acoustic sensors 221 and

[0053] As before, the two acoustic sensors 221 and 222, as well as the laser range finder 230 can be fixed on the wiper 210 by gluing or by a mechanical connection.

[0054] In the event of contact between the wiper 210 and the powder at the instant t.sub.0, acoustic waves propagate in the wiper 210. The acoustic sensor 221 detects these waves at the instant t.sub.0+a, while the acoustic sensor 222 detects these same waves at the instant t.sub.0+a+b. It is the time difference between the two instants of detection b which allows to determine the position of the contact (and of the possible anomaly 250) in the direction Y, the positions of the two acoustic sensors 221 and 222 being known.

[0055] As indicated previously, the stoppage of the propagation of acoustic waves in the wiper can also be detected and the possible anomaly at the origin of this stoppage will also be located thanks to the time lag between the acoustic sensors.

[0056] In order to achieve a more precise location of the anomaly in the direction Y, the manufacturing device can also comprise more than three acoustic sensors. Indeed, if the acoustic sensors are too far apart, one of the sensors could not perceive the acoustic wave propagating in the wiper, or could perceive a wave already disturbed by the arrival of a new wave. The use of three or four sensors allows to overcome this, because it is thus possible to place the sensors at closer intervals, while maintaining sufficient spacing between at least two sensors to detect a significant time difference for the determination of the position of the anomaly.

[0057] According to a particular feature of the invention, the device comprises three acoustic sensors placed respectively at ¼, 2/4 and ¾ of the length of the wiper in the direction Y.

[0058] Another object of the invention is a method for detecting an anomaly during the spreading of the powder by the wiper, the method being implemented by one of the devices presented previously.

[0059] The method first comprises the detection of an acoustic signal by the acoustic sensors, then the determination of the position of the anomaly, and finally the classification of the anomaly according to its severity.

[0060] The position of the anomaly is determined: [0061] in the first direction X by the position signal measured by the laser range finder, [0062] in the second direction Y by a time lag of the acoustic signal detected by the acoustic sensors, and [0063] in the third direction Z by the number of layers of powder spread by the wiper.

[0064] It is the control system which determines whether the detected acoustic wave or the absence of a wave is indeed the result of an anomaly, then which determines the position of this anomaly and finally which classifies this anomaly according to its severity.

[0065] Another object of the invention is a method for manufacturing a part by selective fusion or selective sintering on a powder bed comprising a step of detecting anomalies by the detection method described previously.

[0066] The detection of an anomaly, the determination of its position in space and its classification allows to know if this anomaly must be corrected, and if so, it can be done quickly by knowing its precise position; or if the manufacturing should be stopped. This also allows to predict any defects in the final part.