WO2020176737A1

WO2020176737A1 - Prevention of black-listed parts from being 3d-printed

Info

Publication number: WO2020176737A1
Application number: PCT/US2020/020114
Authority: WO
Inventors: Christina Vasil; Arvind Rangarajan; Benjamin Edward Beckmann; Steven J. Duclos
Original assignee: General Electric Co
Current assignee: General Electric Co
Priority date: 2019-02-27
Filing date: 2020-02-27
Publication date: 2020-09-03
Anticipated expiration: 2021-08-27
Also published as: US20200269511A1; US11465359B2

Abstract

Methods for the identification of unapproved build files/parts based on similarity to previously tagged unapproved items are provided, without needing the unapproved build file/part to exactly match the previously tagged unapproved item. An authorization module may determine whether a part is authorized for fabrication via AM based on the part geometry's similarity to items in a pre-determined "blacklist" or items in a "whitelist". The blacklist may be a storage element containing geometric information on illicit geometries. Illicit geometries may include, but are not limited to firearms, missiles, export-controlled geometries and weapons of mass destruction. The whitelist may be a storage element containing geometric information on specifically-authorized geometries.

Description

PREVENTION OF BLACK-LISTED PARTS FROM BEING 3D-PRINTED

PRIORITY INFORMATION

[0001] The present application claims priority to U.S. Provisional Patent Application Serial Number 62/811,076 filed 27 Feb 2019 and to U.S. Patent Application Serial Number 16/436,240 filed on 10 June 2019.

BACKGROUND

[0002] An additive manufacturing system and process may be used to create a three- dimensional item. A user may want to obtain a three-dimensional item, such as a nozzle for a jet engine, a replacement part for a wind turbine, etc. In some cases, the user may have the part created by arranging to have a part file transmitted to an additive manufacturing platform. Currently, part files for a host of items may be publicly available. In some instances, the user may want to use the additive manufacturing platform to create items from these publicly available part files, where the items include illicit geometries, and without authorization.

[0003] It would be desirable to provide systems and methods to determine whether an item is authorized to be created via an additive manufacturing process.

BRIEF DESCRIPTION

[0004] A technical effect of some embodiments of the invention is an improved and/or computerized technique and system for authorizing fabrication of parts via additive manufacturing (AM). One or more embodiments provide for the identification of unapproved build files/parts based on similarity to previously tagged unapproved items, without needing the unapproved build file/part to exactly match the previously tagged unapproved item. There may be several ways in which a part would qualify as having an illicit geometry if not printed by a proper authority: 1. The part may be patented or copyrighted; 2. The design may be export controlled (EC), and 3. The type of part may require a license to manufacture/be a regulated item (e.g., missiles). One or more

embodiments provide an authorization module that may determine whether a part is authorized for fabrication via AM based on the part geometry’s similarity to items in a pre determined“blacklist” or items in a“whitelist”. The blacklist may be a storage element containing geometric information on illicit geometries. Illicit geometries may include, but are not limited to firearms, missiles, export-controlled geometries and weapons of mass destruction. The whitelist may be a storage element containing geometric information on specifically-authorized geometries. One or more embodiments may provide for the determination of a probability that a part geometry is on a whitelist or a blacklist. Further, a weight of the whitelist probability and the blacklist probability may be combined to determine whether the part geometry is authorized. Machine learning may be used, in one or more embodiments, to improve accuracy of the probability score of matching

whitelist/blacklist parts and a statistical significance. One or more embodiments may provide for the use of a secure, distributed ledger (block-chain) to uniquely store geometric signature data for the part securely, and for a publicly distributed blockchain or distribution within a given organization. Embodiments may provide for the application of a shrink-wrap function to a geometry before comparison to stored geometries to ensure a more accurate comparison for lattice- structured parts. Embodiments may provide for the identification of parts that are negatives of authorized/unauthorized geometries to identify builds of molds for

unauthorized/authorized geometries. Another technical effect of one or more embodiments is the identification of parts through partial matching to find assemblies that are printed in pieces (e.g., a barrel for a firearm and a handle for a firearm). In one or more embodiments, an active blockchain may be used to identify these different parts in an assembly being printed generally, and in some instances across multiple machines, possibly in multiple locations, where an assembly is composed of two or more parts.

[0005] Embodiments may allow for users/OEMs/manufacturers/government to carefully control which parts are allowed to be printed and are not allowed to be printed. Embodiments may not be dependent on a manufacturing modality.

[0006] With this and other advantages and features that will become hereinafter apparent, a more complete understanding of the nature of the invention can be obtained by referring to the following detailed description and to the drawings appended hereto.

[0007] Other embodiments are associated with systems and/or computer-readable medium storing instructions to perform any of the methods described herein.

DRAWINGS

[0008] FIG. 1 illustrates a system according to some embodiments

[0009] FIG. 2 illustrates a flow diagram according to some embodiments.

[0010] FIG. 3 illustrates a flow diagram according to some embodiments.

[0011] FIG. 4 illustrates a non-exhaustive example of a blacklist database according to some embodiments. [0012] FIG. 5 illustrates a non-exhaustive example of a shape signature according to some embodiments.

[0013] FIG. 6 illustrates an example of a blockchain flow diagram according to some embodiments.

[0014] FIG. 7 illustrates a system according to some embodiments.

DETAILED DESCRIPTION

[0015] As 3D printing (additive manufacturing) becomes more accessible to individuals around the world, so does the potential to print contraband, including weapons and explosive components. Currently, given an additive build file, a machine user may print virtually any geometry with no safety checks - a problem inherent to AM. Today, with access to the internet, users may download sensitive files of these illicit parts and load them in an additive manufacturing machine to be printed. An example geometry is“The

Liberator,” a plastic, additively— manufacturable firearm that was released to the public via the internet.

[0016] Current efforts to address this include a process to download a geometry file containing firearms, slightly modify the geometry such that it renders the firearm ineffective, and re-upload the altered geometry file back to the internet to intentionally proliferate faulty firearm files. However, this approach is rendered ineffective for those capable of 3D design, as they may re-alter a faulty geometry, and, or, create a new geometry from scratch, or for those who have other sources for acquiring such files.

[0017] One or more embodiments provide for an authorization module to limit the capability of additive machines to print unauthorized parts. The authorization module may use shape recognition processes, blockchain technology, and artificial intelligence to identify and prohibit the production of unauthorized parts. The authorization module may allow part geometries to be reduced to shape signatures for purposes of fast, simple, and accurate comparison, enabling same or similar - non-exact - geometries to be detected as matches.

[0018] The authorization module may include a processor and a communication interface. Initially, at S210, the authorization module may receive, via the communication interface, a part file with instructions to manufacture one or more parts with an additive manufacturing machine. The part file may be one of a geometry file or a build file. It is noted that a geometry file may include the geometry for the part, and may need to be converted to a build file prior to receipt by the additive manufacturing. A build file may include the outline of the shape, layer-by-layer, in a machine-readable instruction. The part file may be in the form of a CLS file, or any other suitable format.

[0019] Then a geometric analysis module may generate a shape signature for the part based on the part file at S212. The shape signature may be a compact representation for some essence of a shape. The shape signature may capture some global geometric properties which are scale, translation, and rotation invariant. As a first step in the generation of the shape signature, the geometric analysis module may reconstruct a stereolithography (STL) file from the part file, or any other suitable file format. The STL file may be pose- normalized, assuring that the geometry is rotated, translated, and scaled appropriately. The distributions of the maps of distance, angle or curvature may be used to calculate a unique shape signature. Some non-exhaustive examples of shape signature processes include spherical harmonic decomposition and Zerinke polynomials. The shape signature may include one or more dimensions for the part. For example, a handle for a firearm may include two dimensions: a cylinder and a notch. Each of the one or more dimensions may include a weight. In one or more embodiments the weight may be related to the uniqueness of the dimension. For example, with the firearm handle, the notch may be a more unique feature or dimension than the cylinder. The shape signature may be output or represented as an array of data, which may include representation as a histogram, or otherwise suitably represented. For geometries that include large internal holes, the negative geometry may be computed and also checked against the database (to account for potential mold prints).

[0020] The generated shape signature for the part is then analyzed with respect to one or more stored shape signatures, stored in a signature storage entity. In one or more embodiments, the signature storage entity may be at least one database, or other suitable storage entity. The signature storage entity may include stored shape signatures that are categorized as“blacklist” or“whitelist”. In one or more embodiments, the signature storage entity may include separate databases for blacklist and whitelist items, or may include both items in a single database. The whitelist items may be items of approved geometries from enterprise databases, while the blacklist items may be items published by - for example - firearms manufacturers/suppliers, government entities, the Department of Justice, etc., or any other suitable party.

[0021] With respect to FIGS. 4 and 5, FIG. 4 is a non-exhaustive example of what a blacklist may look like/contain. The shape signature data may be stored in some form that is easy to compare with other signatures. The non-exhaustive example herein is the height of the bins in a histogram, where the histogram is shown in FIG. 5. Taking a closer look, the shape signature data for the hand gun designs 1 through N may be very dimensionally similar, with only a few numbers in the array being slightly different from one another between designs. However, when looking at the gun silencer designs, while similar to each other, they differ from the hand gun design signature data.

[0022] In one or more embodiments, the analysis may determine the probability and statistical significance of the generated shape signature corresponding to at least one of a stored shape signature in the whitelist or the blacklist in S214. As used herein, a blacklist item may be referred to as an“unauthorized-to-print” item and a whitelist item may be referred to as an“authorized-to-print” item. The determination that the generated shape signature corresponds to a stored shape signature may be based on: a determination of a probability that each of the dimensions of the generated shape signature matches at least one of the dimensions of the stored shape signatures; a determination whether the probability is statistically significant based on a statistical significance process; and the output of a weighting process that receives the determined probability and determined statistical significance. It is further noted that exact matches between the generated shape signature and stored shape signature may not be necessary - using geometric analytical techniques, parts may be considered a match against the blacklist if they are within a defined degree of shape similarity, or if the geometry only matches a portion of a blacklist geometry (i.e., it is a partial match). The authorization module may also be able to work around other various loop holes, such as lattice structures and mold geometries (i.e., where the to-be-printed part is a negative shape of a blacklisted part).

[0023] In one or more embodiments, the analysis may be done using a level-of-detail approach, or progressive matching, where large landmarks are checked first, and more detailed matching is checked progressively. This approach may dispel likely-approved parts quickly.

[0024] In one or more embodiments, after calculating whitelist and blacklist probability scores, the scores may be passed through a weighting function to determine the final probability of the geometry being authorized, and a statistical significance will be determined. The final decision will be made (approved/authorized vs not

approved/unauthorized), and the shape signature data and the decision may be hashed and added to the blockchain. For transactions containing unauthorized parts, the shape signatures may be added to the blacklist database. This inclusion therein may create a decentralized system which is less likely to be hacked/overridden, and may enable detection of multiple printers working in tandem to print a single assembly. [0025] The blacklist/whitelist determination may then be received at a printing decision module at S216, which may make an ultimate decision on whether to print. In one or more embodiments, these decisions, along with shape signatures may be hashed and sent to a blockchain to serve as a record. In one or more embodiments, if the part is identified as a likely-blacklisted part, a number of options for recourse may be offered per the printing decision module, such as flagging for later investigation, stopping the build, the machine being locked/powered down and, reporting to the relevant authorities.

[0026] In one or more embodiments, the authorization module may check for partial matching, as the user may not be printing a full assembly.

[0027] It is noted that the authorization module may be deployed at at least two points in the additive design-to-manufacture thread: 1) when a build file is generated from a CAD geometry (e.g., a CLS file) and 2) when a build file is loaded to be printed on a machine, further securing the supply chain. The authorization module may be independent of machine architecture and additive manufacturing modality, allowing for a more universal and sustainable solution.

[0028] The authorization module may utilize computational geometric techniques to identify potentially unauthorized parts intended for printing, with the potential of learning and improving capability for detection over time through the use of machine learning. After geometric analysis, the authorization module may store each part geometry (e.g., shape signature) as a transaction with metadata (how likely it is to be a blacklisted part and metrics about geometrical features) via blockchain, which may enable auditability, if required. This may allow printers of unauthorized parts to be traced. Additionally, the authorization module may 1. For networked or non-networked machines, identify subversive techniques that may help identify parts that have geometrically“drifted” from the blacklisted geometry, 2. For networked or non-networked machines, find more patterns across blacklisted parts and search for such characteristics in new geometries, and 3. For networked machines, identify coordinated additive machines that are working together to build an assembly of parts that is unauthorized. This may allow the authorization module to stay relevant over time through self-maintenance. It should also be noted this authorization module may be coupled with a “whitelisting” technology, where machines are only permitted to print a given set of parts (i.e., the whitelist), further preventing unwanted builds.

[0029] Based on the geometry’s similarity to parts in the database, it may be assigned a blacklist probability score, or the likelihood of the part being a blacklisted part, and the statistical significance of said probability. This result along with analytical details on the part geometry may be added to the blockchain as a record. Blockchain may also be used to store, as a non-exhaustive example, the blacklist database, adding the benefit of distributed authority and mitigating the ability of users to alter the database. For active / networked machines, the blockchain-enabled blacklist database may be actively modified to include newly-found unauthorized geometries available on the internet, further improving control of the additive supply chain. Moreover, for active machines, the blockchain records may be used to determine if close-by machines are printing parts of an assembly in tandem, which may not individually trigger blacklist flags, but together form a blacklisted part. This may be determined based on things including, but not limited to similarity of parts (i.e., whether they appear to fit together or look like subcomponents of a blacklisted assembly), proximity of machines, and time stamps of build data sent to the blockchain.

[0030] Note the embodiments described herein may be implemented using any number of different hardware configurations. For example, FIG.7 illustrates an authorization platform 700 that may be, for example, associated with the system 100 of FIG. 1. The authorization platform 700 comprises an authorization processor 710 (“processor”), such as one or more commercially available Central Processing Units (CPUs) in the form of one-chip microprocessors, coupled to a communication device 720 configured to communicate via a communication network (not shown in FIG. 7). The communication device 720 may be used to communicate, for example, with one or more users. The authorization platform 700 further includes an input device 740 (e.g., a mouse and/or keyboard to enter information) and an output device 750 (e.g., to output the outcome of module execution).

[0031] The processor 710 also communicates with a memory/storage device 730.

The storage device 730 may comprise any appropriate information storage device, including combinations of magnetic storage devices (e.g., a hard disk drive), optical storage devices, mobile telephones, and/or semiconductor memory devices. The storage device 730 may store a program 712 and/or authorization processing logic 714 for controlling the processor 710. The processor 710 performs instructions of the programs 712, 714, and thereby operates in accordance with any of the embodiments described herein. For example, the processor 710 may receive data and then may apply the instructions of the programs 712, 714 to determine whether a received part geometry is authorized for printing via an additive manufacturing machine.

[0032] The programs 712, 714 may be stored in a compressed, uncompiled and/or encrypted format. The programs 712, 714 may furthermore include other program elements, such as an operating system, a database management system, and/or device drivers used by the processor 710 to interface with peripheral devices.

[0033] As used herein, information may be“received” by or“transmitted” to, for example: (i) the platform 700 from another device; or (ii) a software application or module within the platform 700 from another software application, module, or any other source.

[0034] As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a system, method or computer program product. Accordingly, aspects of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, micro-code, etc.) or an embodiment combining software and hardware aspects that may all generally be referred to herein as a“circuit,”“module” or“system.” Furthermore, aspects of the present invention may take the form of a computer program product embodied in one or more computer readable medium(s) having computer readable program code embodied thereon.

[0035] The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.

It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be

implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

[0036] It should be noted that any of the methods described herein can include an additional step of providing a system comprising distinct software modules embodied on a computer readable storage medium; the modules can include, for example, any or all of the elements depicted in the block diagrams and/or described herein. The method steps can then be carried out using the distinct software modules and/or sub-modules of the system, as described above, executing on one or more hardware processors 710 (FIG. 7). Further, a computer program product can include a computer-readable storage medium with code adapted to be implemented to carry out one or more method steps described herein, including the provision of the system with the distinct software modules.

[0037] Further aspects of the invention are provided by the subject matter of the following clauses:

[0038] 1. A method comprising: receiving, via a communication interface of an authorization module comprising a processor, a part file with instructions to manufacture one or more parts with an additive manufacturing machine; generating a shape signature for the part based on the part file; providing a signature storage entity storing one or more stored shape signatures, wherein the one or more stored shape signatures are one of an authorized- to-print stored shape signature and an unauthorized-to-print stored shape signature;

determining the generated shape signature of the part corresponds to at least one of the authorized-to-print stored shape signatures or at least one of the unauthorized-to-print stored shape signatures; and receiving, at a printing decision module, the determination of whether the generated shape signature of the part corresponds to at least one authorized-to-print stored shape signature or at least one unauthorized-to-print stored shape signature.

[0039] 2. The method of any preceding clause, further comprising: recording the generated shape signature for the part in a secure, ledger.

[0040] 3. The method of any preceding clause, wherein the part file is one of a geometry file or a build file.

[0041] 4. The method of any preceding clause, wherein determining the shape signature of the part corresponds to the one or more stored shape signatures further comprises: determining a probability the generated shape signature matches at least one stored shape signatures; and determining whether the probability is statistically significant based on a statistical significance process.

[0042] 5. The method of any preceding clause, wherein matching is one of exact or non-exact.

[0043] 6. The method of any preceding clause, wherein generating the shape signature further comprises: receiving the part file at a geometric analysis module of the authorization module; and executing a shape characterization process.

[0044] 7. The method of any preceding clause, wherein the shape signature is output as an array of data histogram.

[0045] 8. The method of any preceding clause, wherein the shape signature includes one or more dimensions for the part. [0046] 9. The method of any preceding clause, wherein each of the one or more dimensions include a weight.

[0047] 10. The method of any preceding clause, wherein determining the generated shape signature corresponds to at least one stored shape signatures further comprises:

determining a probability that each of the dimensions of the generated shape signature matches at least one of the dimensions of the stored shape signatures; determining whether the probability is statistically significant based on a statistical significance process; and receiving the determined probability and determined statistical significance at a weighting process.

[0048] 11. The method of any preceding clause, wherein the shape signature corresponds to at least one stored shape signature when a threshold is reached.

[0049] 12. The method of any preceding clause, further comprising: printing the part with the additive manufacturing machine when the printing decision module receives the determination that the generated shape signature of the part corresponds to the authorized-to- print list.

[0050] 13. The method of any preceding clause, further comprising: preventing the generated shape signature from being used to print the part with the additive manufacturing machine when the printing decision module receives the determination that the generates shape signature of the part corresponds to the unauthorized-to-print list.

[0051] This written description uses examples to disclose the invention, including the preferred embodiments, and also to enable any person skilled in the art to practice the invention, including making and using any devices or systems and performing any incorporated methods. The patentable scope of the invention is defined by the claims, and may include other examples that occur to those skilled in the art. Such other examples are intended to be within the scope of the claims if they have structural elements that do not differ from the literal language of the claims, or if they include equivalent structural elements with insubstantial differences from the literal languages of the claims. Aspects from the various embodiments described, as well as other known equivalents for each such aspects, can be mixed and matched by one of ordinary skill in the art to construct additional embodiments and techniques in accordance with principles of this application.

[0052] Those in the art will appreciate that various adaptations and modifications of the above-described embodiments can be configured without departing from the scope and spirit of the claims. Therefore, it is to be understood that the claims may be practiced other than as specifically described herein.

Claims

1. A method comprising:

receiving, via a communication interface of an authorization module comprising a processor, a part file with instructions to manufacture one or more parts with an additive manufacturing machine;

generating a shape signature for the part based on the part file;

providing a signature storage entity storing one or more stored shape signatures, wherein the one or more stored shape signatures are one of an authorized-to-print stored shape signature and an unauthorized-to-print stored shape signature;

determining the generated shape signature of the part corresponds to at least one of the authorized-to-print stored shape signatures or at least one of the unauthorized-to-print stored shape signatures; and

receiving, at a printing decision module, the determination of whether the generated shape signature of the part corresponds to at least one authorized-to-print stored shape signature or at least one unauthorized-to-print stored shape signature.

2. The method of claim 1, further comprising:

recording the generated shape signature for the part in a secure, ledger.

3. The method of claim 1, wherein the part file is one of a geometry file or a build file.

4. The method of claim 1, wherein determining the shape signature of the part

corresponds to the one or more stored shape signatures further comprises:

determining a probability the generated shape signature matches at least one stored shape signatures; and

determining whether the probability is statistically significant based on a statistical significance process.

5. The method of claim 4, wherein matching is one of exact or non-exact.

6. The method of claim 1, wherein generating the shape signature further comprises:

receiving the part file at a geometric analysis module of the authorization module; and

executing a shape characterization process.

7. The method of claim 1, wherein the shape signature is output as an array of data histogram.

8. The method of claim 1, wherein the shape signature includes one or more dimensions for the part.

9. The method of claim 8, wherein each of the one or more dimensions include a weight.

10. The method of claim 9, wherein determining the generated shape signature

corresponds to at least one stored shape signatures further comprises:

determining a probability that each of the dimensions of the generated shape signature matches at least one of the dimensions of the stored shape signatures;

determining whether the probability is statistically significant based on a statistical significance process; and

receiving the determined probability and determined statistical significance at a weighting process.

11. The method of claim 1, wherein the shape signature corresponds to at least one stored shape signature when a threshold is reached.

12. The method of claim 1, further comprising:

printing the part with the additive manufacturing machine when the printing decision module receives the determination that the generated shape signature of the part corresponds to the authorized-to-print list.

13. The method of claim 1, further comprising:

preventing the generated shape signature from being used to print the part with the additive manufacturing machine when the printing decision module receives the

determination that the generates shape signature of the part corresponds to the unauthorized- to-print list.