Method for classifying projected offcuts in an industrial manufacturing process, and associated system

Abstract

The invention relates to a method for processing offcuts in an industrial manufacturing process, which comprises: ■ acquiring (ACQ1) a first schedule (PL1); ■ acquiring (ACQ2) a first nesting plan (PIMA); ■ characterising (CAR1) at least one projected offcut (CHk) defining at least one zone of the nesting plan (PIMA); ■ querying a first database of items (BD1) comprising a set of parts (Pn) to be produced; ■ establishing a first comparison (COMP1) between the dimensions (Kc) of the at least one projected offcut (CHk) and the dimensions of the parts to be produced (Pn) extracted from the first database of items (BD1); ■ determining a list (LIST1) of compatible parts to be produced; ■ classifying (CLASS1) each projected offcut (CHk); and ■ updating a database of offcuts (BD2).

Description

[0001] METHOD FOR CLASSIFYING PREDICTED FALLS OF MATERIAL IN AN INDUSTRIAL MANUFACTURING PROCESS, ASSOCIATED SYSTEM

[0002] Field of invention

[0003] The field of the invention relates to that of computer-implemented methods and systems for classifying material scraps produced during an industrial part manufacturing process. More particularly, the field of the invention relates to that of methods aimed at reducing the production of scraps in material cutting operations. The field of the invention relates more particularly to the cutting of sheet or plate material such as metallic materials, but may also find applications in the processing of glass, plastic such as polymers, wood, composite materials or even textiles.

[0004] State of the art

[0005] There are many solutions today aimed at planning and optimizing the production of a set of industrial parts cut from material plates. Optimizing this operation is generally achieved by producing a nesting plan, i.e. optimizing the arrangement of parts within a plate to optimize the reduction of material waste. Many algorithms exist to optimize this arrangement based on constraints dependent on the dimensions of the parts, their occurrence, the necessary margins, the cutting technique, etc.

[0006] However, during a planning operation for the production of industrial parts, significant material waste continues to be produced. The production of this material waste is sometimes unavoidable because a planning includes a final non-optimized material plate or because part orders can vary over time. In addition, the dimensions of the material plates can vary during a planning depending on the supply, and during the life cycle of an industrial production line there is a heterogeneity of the different products and parts to be produced which involves the production of material waste.

[0007] Summary of the invention

[0008] The invention makes it possible to overcome the aforementioned drawbacks of the prior art.

[0009] According to a first aspect, the invention relates to a computer-implemented method for classifying predicted material waste in an industrial manufacturing process comprising:

[0010] ■ Acquisition of an initial planning of a set of parts to be manufactured, said parts being intended to be cut from a set of material plates;

[0011] ■ Acquisition of at least one first nesting plan of parts to be cut for each sheet of material, each part to be cut comprising a two-dimensional profile and a thickness and the profile of which is inscribed within a first surface included in the surface of the sheet of material, each part to be manufactured represented within the first nesting plan being called a flank;

[0012] ■ Characterization of at least one predicted fall defining at least one area of ​​the nesting plane not occupied by flanks, said characterization comprising at least:

[0013] ■ an identifier for each expected fall;

[0014] ■ the dimensions of each expected fall;

[0015] ■ Querying a first database of articles comprising a set of parts to extract the geometric descriptors of said parts;

[0016] ■ First comparison between the dimensions of the at least one forecast drop and the dimensions of at least one part extracted from the first article database, said first comparison producing a correspondence indicator;

[0017] ■ Determination of a first list of compatible parts from the value of the correspondence indicator; ■ Selection of at least one part from the first list according to a given criterion;

[0018] ■ Classification of each forecast fall according to a plurality of labels based on a calculation of a score characteristic of said forecast fall, said score being calculated in particular based on at least the first criterion;

[0019] ■ Generation of a new first planning comprising the generation of at least one new nesting plan for at least one material plate comprising at least one new part selected from the first list within zones corresponding to a forecast fall having a reuse label;

[0020] ■ Updating a falls database in which at least one labeled predicted fall is recorded.

[0021] According to one embodiment, the computer-implemented method for classifying predicted material waste in an industrial manufacturing process is intended to be implemented for cutting plate(s) of material from at least one schedule of parts to be produced.

[0022] According to one embodiment, the acquisition of a first schedule forms a step of an industrial production method for a plurality of parts to be produced.

[0023] One advantage is that it allows for different uses of a forecasted fall and in particular allows this fall to be reused by re-entering a new part to be produced in the location of the forecasted fall.

[0024] According to one embodiment, the first planning comprises at least one milestone corresponding to a cutting forecast of at least one plate of material forming a step of an industrial production process of a plurality of parts to be produced. An advantage is to optimize a production line comprising several milestones within which different material cutting plans are planned.

[0025] According to one embodiment, the first schedule comprises at least one material plate identifier, at least one cutting date of each material plate of said first schedule and a quantity of parts to be produced.

[0026] According to one embodiment, at least one first schedule further comprises at least one product identifier to be produced.

[0027] According to one embodiment, an initial schedule comprises at least one product identifier and an association with a plurality of first schedules, each first schedule being associated with a material plate.

[0028] According to one embodiment, each nesting plan comprises a set of identifiers of parts to be produced, and for each identifier a profile of the part to be produced which is oriented and positioned within a surface representing the surface of a plate of material associated with said nesting plan. An advantage is to allow the data to be extracted from the nesting plan and not from an article database.

[0029] According to one embodiment, the first surface of the nesting plane is equal to the surface of at least one plate of material.

[0030] According to one embodiment, the dimensions of each fall include in particular a surface area and a thickness. An advantage is to take into account the thickness of the material plate when applying filters to a criterion for selecting the parts to be re-nested.

[0031] According to one embodiment, a set of offcuts is generated from a processing of all the areas of the nesting plane not occupied by flanks, said processing comprising a step of segmenting the surfaces of each predicted offcut from the cutting lines of the flanks of the nesting plane and the edges of the nesting plane. An advantage is to optimize the potential surface to be reused within a plate of material.

[0032] According to one embodiment, the step of segmenting the surfaces of each forecast fall also includes taking into account additional cutting line(s). One advantage is to take into account tracings that may indicate unused areas.

[0033] According to one embodiment, the step of segmenting the surfaces of each forecasted scrap comprises taking into account a set of exclusion criteria making it possible to assign an area of ​​the surface of the nesting plane not occupied by flanks to a scrap area which is not taken into account for the generation of a forecasted scrap. An advantage is to directly generate useful surfaces to define reusable forecasted scraps. The re-exploitation may correspond to the reassignment of the location to a new part to be produced or to a conservation of the scrap.

[0034] According to one embodiment, the step of segmenting the surfaces of each forecast fall comprises a first characterization of the fall taking into account the size of the forecast fall, the position of the forecast fall, a surface condition of the forecast fall and / or the material of the forecast fall. An advantage is to qualify the fall as much as possible for better reuse of the latter.

[0035] According to one embodiment, each forecast fall comprises a set of geometric descriptors including in particular:

[0036] ■ a minimal rectangle and / or;

[0037] ■ a polygon with a maximum number of edges and / or;

[0038] ■ an image of the predicted fall and / or;

[0039] ■ a two-dimensional outline of the profile of the predicted fall and / or;

[0040] ■ Data characterizing the exact surface area of ​​the predicted fall.

[0041] According to one embodiment, each forecast fall includes a set of complementary descriptors including in particular:

[0042] ■ A material plate identifier.

[0043] According to one embodiment, the first comparison comprises comparing the surface area of ​​a predicted fall with the surface area of ​​a part identified in the article database or in a list extracted from this database. An advantage is to allow the available location to be reallocated to optimize material production.

[0044] According to one embodiment, the comparison step comprises comparing the surface area of ​​a polygon inscribed in the outline of an area defining a predicted drop with the perimeter and / or the surface area of ​​an external polygon containing the surface area of ​​a part selected from the article database. The polygon modeling the drop is preferably convex. An advantage of using polygons is to simplify surface and layout calculations.

[0045] According to one embodiment, the comparison step comprises comparing the perimeter and / or the surface area of ​​a plurality of polygons generated and inscribed in the outline of an area defining a predicted fall with the perimeter and / or the surface area of ​​an external polygon containing the surface area of ​​a part selected from the article database.

[0046] According to one embodiment, the comparison step comprises the implementation of an optimization algorithm aimed at determining the largest perimeter of an area of ​​the nesting plan defining at least one forecast fall or a set of forecast falls.

[0047] According to one embodiment, the first criterion comprises:

[0048] ■ taking into account a first occurrence of a part extracted from the article database and associated with a first planning or another planning and / or;

[0049] ■ taking into account a batch of identical parts extracted from the article database and associated with at least one material plate from the first planning and / or;

[0050] ■ at least a first time interval between two milestones of the same schedule in which the part extracted from the article database is associated with each of the two associated milestones, each milestone being associated with a different material plate and / or;

[0051] ■ at least one second time interval between two schedules in which the part extracted from the item database is associated with at least one milestone of each of the schedules.

[0052] According to one embodiment, the classification comprises:

[0053] ■ an allocation of a first label to the forecast falls for their reuse when the first criterion includes:

[0054] ■ an occurrence or lotting of parts selected in the first list in the first planning plan or another planning plan greater than a predefined threshold and; ■ a first or second time interval less than a predefined duration;

[0055] ■ an allocation of a second label to the forecast falls for their conservation when the first criterion includes:

[0056] ■ an occurrence or subdivision of parts selected in the first list in the first planning plan or another planning plan above a predefined threshold and

[0057] ■ a first or second time interval greater than a predefined duration and / or;

[0058] ■ an allocation of a third label to the forecasted falls for their conservation when the first criterion corresponds to structural, dimensional or quality properties of the forecasted fall corresponding to a predefined criterion and / or;

[0059] ■ an allocation of a fourth label to the forecast waste for disposal when the first criterion includes:

[0060] ■ an occurrence of selected parts less than a predefined threshold and;

[0061] ■ a first or second time interval greater than a predefined duration and;

[0062] ■ an assignment of the third label to the forecast fall.

[0063] According to one embodiment, the generation of the new nesting plan comprises the superposition of the first nesting plan and an intermediate nesting plan, said intermediate nesting plan comprising at least one new part to be produced selected from the first list and positioned and oriented within zones corresponding to a forecast fall having a reuse label.

[0064] According to one embodiment, the method comprises an update of the article database in which an occurrence of the new selected part is removed, added or postponed according to the modification made to the milestone. An advantage is to keep a database updated with the modifications of the schedule. Typically a part to be produced selected to be re-nested in a milestone is preferentially removed from the list of parts to be produced. According to one embodiment, the first article database comprises a set of parts pre-selected to be produced in at least one schedule. An advantage is to define a subset of parts to be produced that can be extracted according to a criterion of belonging to a product or a criterion of production time window.

[0065] According to one embodiment, the falls database comprises the falls having the second label and / or the third label so as to provide access to said falls thus labeled to a user via a communication interface accessible from a data network.

[0066] According to another aspect, the invention relates to a computer program product comprising instructions which, when the program is executed by a computer, cause the latter to implement the steps of the method of the invention.

[0067] According to another aspect, the invention relates to a system for generating a labeling of a predicted fall characterized in that it comprises:

[0068] ■ at least one communication interface for acquiring planning data and nesting plans and parts from the first database,

[0069] ■ a memory for recording said data, and

[0070] ■ a calculator for generating a labeling of said forecast falls according to the method of the invention, and in that it further comprises a communication interface for outputting the updated data of the labeled falls to computer equipment.

[0071] According to another aspect, the invention relates to a system which comprises a state sensor of a material plate in order to calculate a state criterion taken into account in the development of the first criterion, the state criterion being able to be linked in particular to the surface state of the material plate such as a quantification of a level of rust, impacts, a paint finish or an orientation criterion for example of a lamination or a fiber.

[0072] According to one embodiment, the method of the invention comprises calculating a scrap rate for a given category of material plate, the scrap rate being calculated on a set of nesting plans (PIMA) of one or more schedules (PLi), said scrap rate (Te) being expressed as a percentage of the residual quantity of material or the residual dimensions of material, said scrap rate being used to calculate the desired dimensions of a category of material plates.

[0073] According to one embodiment, the given material plate category comprises a set of material plates having

[0074] ■ differences in dimensions of less than 5% with respect to at least one average characteristic dimension of this set and;

[0075] ■ at least one characteristic dimension of the section of each material plate in the assembly is less than a predefined dimension.

[0076] Brief description of the figures

[0077] Other characteristics and advantages of the invention will emerge on reading the detailed description which follows, with reference to the appended figures, which illustrate:

[0078] ■ Figure 1: the different stages of the method of the invention according to one embodiment;

[0079] ■ Figure 2: An example representation of a parts database used to feed the production of nesting plans for different milestones of different industrial parts production schedules;

[0080] ■ Figure 3: a first example of a nesting plan in which a calculation of forecast waste is carried out from spaces not allocated to parts to be produced;

[0081] ■ Figure 4: an embodiment relating to the first example of nesting plan in which a calculation of forecast falls is carried out taking into account the identification of non-reusable zones;

[0082] ■ Figure 5: an embodiment relating to the first example of a nesting plan in which a calculation of forecasted scraps is carried out by taking into account a dimensional criterion of the scraps to be produced; ■ Figure 6: an embodiment relating to the first example of a nesting plan in which a calculation of forecasted scraps is carried out by taking into account a criterion of dimensions of the parts to be produced subsequently and identified in a database,

[0083] ■ Figure 7: a second example of a nesting plan used within a planning milestone that includes a forecast fall;

[0084] ■ Figure 8: A new nesting plan generated from the nesting plan of the second example which includes a set of parts reintegrated into the location of the predicted fall,

[0085] ■ Figure 9: an embodiment of a system of the invention.

[0086] Definitions

[0087] In the remainder of the description, a "nesting plane" is a surface whose dimensions are known and within which a plurality of part profiles along two dimensions {x, y} are arranged in an a priori optimized manner. The arrangement generally includes the positioning and orientation of each part within the surface and the definition of a margin between each part profile arranged according to the industrial tool used.

[0088] In the remainder of the description, the term "an anticipated fall" or "a fall forecast" is used to designate the estimated fall of material during a production stage of industrial parts within a sheet of material.

[0089] We call "a part" a part identified in a database or a file and which we have access to possibly extract its identifier and its dimensional characteristics, in particular to carry out surface comparison operations.

[0090] A part to be produced is a part selected or identified within a planning milestone or a part that is known to be manufactured and is in a list of parts ready to be selected within a planning and is not necessarily yet nested. A part to be produced can also refer to a part already selected and nested in a nesting plan and not yet produced. A flank is the designation of the profile of a part to be produced represented in a nesting plan.

[0091] In the remainder of the description, we refer to "a schedule" as an industrial schedule comprising a set of milestones associated with forecast dates, each milestone comprising the association of a material plate and a nesting plan for the production of a set of parts to be cut. A milestone can therefore be defined by a date and a quantity of parts to be produced present in a nesting plan and possibly in an available space defined by a forecast waste.

[0092] According to one exemplary embodiment, a milestone is associated with a nesting plan and a material plate. According to another exemplary embodiment, a milestone is defined solely by a part, a production quantity of said part and a manufacturing date.

[0093] In the remainder of the description, the term "final product" refers to the product made from a set of cut parts. The final product generally includes parts other than those cut from a sheet of material, however, generally a part cut from a sheet of material is manufactured to be included in a manufacturing process of a final product. There is therefore generally an association between the part present in a nesting plan and a final product to be produced.

[0094] Reception of planning

[0095] Figure 1 shows an embodiment of the method in which a set of steps are carried out.

[0096] A first step ACQi comprises the acquisition of a first planning PLi. The first planning is for example defined from a software component making it possible to plan milestones of an industrial parts production line. According to one example, the first planning comprises the choice of a material plate or a plurality of material plates and their dimensions. The planning may further comprise an association with a final product to be produced, such as an excavator, a car, a prefabricated item or other final device or system to be designed in particular thanks to an assembly of parts cut from the method of the invention. The method of the invention may comprise a step aimed at acquiring or receiving a plurality of planning. The first planning is called in the context of this description the planning used to illustrate an embodiment.In addition, the other PLi schedules are designated, the schedules likely to be taken into account in the method of the invention when a reuse of the offcuts is envisaged over a broader framework than the current schedule.

[0097] The method of the invention comprises receiving or acquiring a nesting plan denoted PIMA. This nesting plan P IMA corresponds to an arrangement of flanks, i.e. a representation of a profile of parts, within a surface. The surface of the nesting plan is preferably identical to that of a plate of material which will be used for cutting. However, the nesting plan may be defined in a lower surface or at least included in the surface of the plate of material which will be used to cut the parts arranged in the nesting plan. According to one example, a plurality of receptions of PIMA nesting plans are carried out according to the method of the invention, each nesting plan being associated for example with a milestone of the first planning PLi.

[0098] According to an exemplary embodiment, the steps of receiving the first PLi planning and a set of P IMA nesting plans can be implemented together.

[0099] Figure 2 represents an example of PLi planning comprising a plurality of milestones, each milestone being associated with a date ti, t2, ta, t4. Each of the dates ti, t2, ta, t4 is associated with a cutting operation of a plate of material TOLk aimed at producing a set of parts. Each milestone is associated with a PIMA nesting plan for guiding the machine tool for cutting the parts on the sheet metal TOLk.

[0100] Figure 2 represents a time scale representing the different milestones of the first PLi planning. According to one embodiment, the part profiles of each nesting plan are extracted from a BDi database of parts. According to another example, a digital file can contain all the data describing the parts to be produced. According to another embodiment, the geometry of the parts is directly deduced from a reading of the P IMA nesting plan, for example by means of a software component allowing the extraction of a contour of a part drawn within a P IMA nesting plan.

[0101] The method of the invention comprises a step of characterizing the free zones of the nesting plane P IMA. This step is noted CARi in figure 1. The free zones correspond to the zones not occupied by part profiles, that is to say flanks FLi on the surface of the material plate TOLk. The free zones correspond in a first approximation to all the predicted scraps. These predicted scraps can comprise several distinct zones or a single zone comprising portions of continuous surfaces.

[0102] Figure 3 represents an exemplary embodiment representing a PIMA nesting plan comprising a plurality of flanks FLi representing part profiles Pi arranged within a given surface. In this example, the predicted falls CHk correspond to the entire surface not occupied by flanks FLi.

[0103] Figure 4 represents an exemplary embodiment representing the same PIMA nesting plane as that of Figure 3 and therefore the same flanks FLi represented at the same locations as in the PIMA nesting plane of Figure 3. A drop CHk' is represented smaller than that represented in Figure 3.

[0104] An advantage of the invention is to treat the portions of each unused plate forming potential waste CHk, CHk' of material which can be reused in different ways.

[0105] One objective of the invention is to classify and label each forecast material waste so as to reuse these forecast waste or to keep any waste for other uses or for uses in the same use, but at a later date. However, there generally remains a waste which is difficult to envisage reusing. One of the possible labels for forecast waste is therefore "scrap" or "non-reusable waste".

[0106] In the example of Figure 4, the forecast waste CHk' corresponds to the entire surface area not occupied by FLi flanks from which have been subtracted non-exploitable ZR zones defined between the boundaries of the FLi flanks or between a boundary of an FLi flank and an edge of the PIMA nesting plan. In the latter case, it is considered that the ZR zones do not have dimensions large enough to allow these forecast wastes to be reassigned to a use other than their disposal or that it is necessary to consider a margin to ensure reuse of a useful zone.

[0107] A predicted fall may be an area arranged "next to" an edge of a sidewall FLi or an edge of the nesting plane P IMA, however, a predicted fall may also be included in the general shape of a sidewall FLi when the sidewall has an unrestrained interior area. This may be, for example, the inside of a window or door frame or the inside of a ring.

[0108] Generally speaking, we note a predicted fall CHk, the notation CHk' only allowing to illustrate the different ways of considering a fall in the processing of a nesting plan in the example of figure 4.

[0109] In this example, we understand that rules can be predefined to select a predicted waste that can be reused or not. For example, a spacing between two sides FLi that is less than a threshold distance can be defined in order to label a waste or not consider it for further processing. This threshold distance can be defined according to the material and thickness of the plate or according to the cutting tool. Other criteria can be taken into account such as the surface condition of the material plate or the type of part that we want to cut.

[0110] Thus in this step, the ZR zones are either removed from the forecasted reusable waste CHk and therefore are not treated as material waste, or labeled as forecasted waste which will be discarded. The method of the invention comprises two embodiments, consisting of labeling or not treating these wastes.

[0111] Figure 4 represents another type of predicted waste CHk' which is located at a certain minimum distance from the edge of the plate defining a non-useful zone ZR'. According to different embodiments, this zone ZR' can be considered as a predicted waste of the same label as the predicted waste CHk' or of another label. Identicaly a minimal space can be considered between a flank FLi and a waste CHk'. In Figure 4, an example of such a zone ZR' is represented. In this example, this zone is not taken into account in the calculation of the dimensions of the waste CHk'. According to another example, this margin is included in the dimensions of the waste CHk' in particular because it is the surface which will correspond to the actual waste after cutting the part.

[0112] According to one embodiment, the dimensions of the ZR margins between forecast offcuts or the dimensions of the margins between a flank or a forecast offcut may vary according to certain parameters, including for example: the profile of the part or the thickness of the material plate. Indeed, a curved profile may require movements of a cutting tool covering greater amplitudes than when cutting a straight profile.

[0113] Characterization of predicted falls

[0114] At a minimum, a CARi characterization of a forecast fall CHk includes a forecast fall identifier IDc which is generated when determining a forecast fall within the nesting plan.

[0115] According to one example, as soon as an area is sufficiently large, it is then characterized as a predicted fall. According to one embodiment, the “magnitude” threshold corresponds to a minimum of two dimensions in the plane along x and y. According to another embodiment, all the predicted falls identified are associated with an identifier independently of their dimension(s) including when they define a margin between two sides FLi.

[0116] Another characterization is a descriptor of the geometry K c of the predicted fall CHk. This descriptor of the geometry K c , also called geometric descriptor can include one or more of these characteristics:

[0117] - The position of each point of the contour of the predicted fall in the plane of the surface of the nesting plane;

[0118] - The maximum length;

[0119] - The maximum width;

[0120] - The diameter of a circle inscribed in a free zone of the nesting plane, that is to say an area not having a side, as well as the position of the center of the circle; - The diagonal of a rectangle inscribed in the free zone of the nesting plane, that is to say an area not having a side, as well as the position of this diagonal;

[0121] - The largest convex polygon inscribed in a free zone of the nesting plane, that is to say an area not having a side, as well as the position of each edge of the polygon in the plane;

[0122] - Etc.

[0123] The method of the invention comprises a step REQi aimed at querying a data resource which may be a database BDi or any other data file recorded in a memory in order to compare at least one descriptor of a CHk fall with dimensions of a PN part OR a descriptor of said PN part. The PN parts are preferably parts described in a nomenclature in which all the dimensional and structural characteristics of the parts are recorded. In the remainder of the description, a PN part is a part referenced in a data system such as a database in which said parts have a nomenclature. The characteristic data of the PN parts are accessible and possibly extracted from a complete database of parts, or possibly from a list of parts extracted from a complete database according to one or more selection criteria.

[0124] Other descriptors may be taken into account depending on the different embodiments, in particular the thickness of the material plate and the composition of the material. According to another example, the finish of the material plate, any surface treatment or even its condition may be taken into account.

[0125] Figure 2 represents such a database that can be queried to feed different planning with the integration of new parts into a PIMA nesting plan.

[0126] The invention makes it possible to benefit from the K characterization c of the CHK forecast fall in order to check to what extent a PN part from the BDi base can be selected to be produced in the free zone corresponding to the CHk forecast fall zone.

[0127] Comparison of extracted parts with scraps According to an example, data characterizing the thickness of the part, the type of material of the part or any other parameter characterizing the PN part can be taken into account in order to select a subset of PN parts that can be cut from the material plate. This or these characteristic data of a part can be compared to one or more homogeneous data of a material plate or a predicted scrap.

[0128] According to one embodiment, a tolerance or margin between the characteristic data of the part PN and that of the material plate TOLk can be defined according to a predefined criterion. For example, a thickness of a part PN not corresponding to the thickness of the plate TOLk while remaining less than a given difference can be selected. For example, if the plate has a thickness of 20 mm and a part has a thickness of 19.5 mm, according to a given tolerance criterion, the part PN can still be considered for selection in order to be produced within a space defined by a predicted waste. This tolerance can also be applied to a type of material of a part PN different from that of the material plate TOLk but whose desired characteristics are compatible with those of the material plate.Typically, a part that is supposed to be made of steel can also be made of titanium if only the mechanical strength characteristics must be respected.

[0129] According to one embodiment, the association between one or more parts and one or more predicted scraps is carried out from at least one table of correspondences or equivalence of characteristics defining the part(s) and respectively the predicted scrap(s).

[0130] A COMPi comparison step between the surface of one or more forecasted falls and one or more PN parts makes it possible to select a subset of forecast falls corresponding to a subset of PN parts.

[0131] The COMPi comparison step can be implemented in different ways. A surface comparison algorithm can be used to automate and optimize this calculation step on a large number of parts.

[0132] According to one embodiment, a first simple comparison step makes it possible to exclude or select a large number of parts and a second comparison step is carried out to refine the comparison from a preselection carried out during the first comparison step.

[0133] According to an exemplary embodiment, the first comparison step comprises comparing the largest dimension of a part PN with the largest dimension of the predicted fall CHk. When the largest dimension of a part is greater than the largest dimension of the fall, this part is not selected.

[0134] In one example, another dimension is tested between the dimensions of the PN part and the dimension of the CHk drop, for example a dimension perpendicular to the largest dimension of the PN part. An interest is to select PN parts quickly having at least two dimensions smaller respectively than the same two dimensions of the predicted CHk drop.

[0135] According to an exemplary embodiment, the comparison of certain dimensions of a scrap with those of a part takes into account an orientation constraint to be respected. The orientation constraint can be defined by data specific to the material plate. The orientation constraint can be imposed for example by a rolling direction, a fiber direction of a composite material. When an orientation constraint is imposed by the part or the plate, the dimensions compared between the part and the predicted scrap are chosen to respect this orientation constraint.

[0136] After this first comparison, a second comparison implementing a more complex algorithm makes it possible to process the selected PN parts.

[0137] However, according to one embodiment, the method of the invention comprises only one comparison step. The latter can be simple according to a technique previously described or complex, for example by implementing a surface comparison algorithm.

[0138] According to an example, the second comparison includes the comparison of the area of ​​each of the two-dimensional shapes on the one hand of each predicted fall CHk and on the other hand of each part PN.

[0139] The calculation of the area gives a first value making it possible to objectively deduce whether a part profile can be integrated within a geometric shape corresponding to that of a predicted fall CHk. According to one example, the database containing the identification of each part PN includes a geometric descriptor corresponding to the surface area of ​​the part PN. According to another example, the calculation of the area of ​​the part PN is carried out at each comparison carried out according to other characteristic values ​​of the geometric descriptors of each part PN making it possible to calculate an area.

[0140] According to an exemplary embodiment, the calculation of the circumference also makes it possible to provide an indicator making it possible to deduce whether or not a PN part profile is likely to fit into the shape of a predicted fall.

[0141] In another example, the comparison is carried out by positioning and orienting each profile relative to each other and iteratively changing the orientation of one of the shapes of the predicted fall CHk or the part PN.

[0142] According to another example, the fall is modeled CHk by a first polygon falling within the predicted fall surface CHk and a second polygon comprising the predicted fall surface CHk . An algorithm allows for example for a given maximum number of edges to calculate the largest first polygon and the smallest second polygon. One interest is to simplify the comparison operation by testing different orientations of the shape with respect to the profile of a PN part.

[0143] When a comparison operation results in a solution allowing the registration of a profile of a shape of a PN part within a surface of a predicted fall, a correspondence indicator INDi is generated.

[0144] Selected parts list

[0145] The comparison operation results in defining a first list LISTi of compatible PN parts of one or a plurality of forecast offcuts of a PIMA nesting plan. This step of determining a list of compatible PN products is noted DETi in figure 1. The list can be used in different ways.

[0146] A list LISTi can be generated for each milestone of a planning PLi , i.e. for each material plate TOLk. According to one embodiment, the list of parts PN is generated for a set of milestones of a planning PLi , i.e. a set of material plates TOLk. One interest is to obtain a better optimization of the reuse of the forecast scraps CHk by favoring a diversity of scenarios of integration or nesting of parts PN within a plurality of forecast scraps CHk.

[0147] According to a first embodiment, a first filtering on the parts to be produced in one or more schedules is carried out then a second filtering on the geometry of the profiles of the parts is carried out while taking into account criteria characterizing the parts such as their material, thickness, an orientation constraint, etc.

[0148] According to a second embodiment, the order of the filtering is reversed. First, a filtering is carried out on the geometry of a set of parts and then a filtering on the parts to be produced in one or more schedules is carried out from the parts having a filtered geometry. Other criteria characterizing the parts such as their material, thickness, an orientation constraint, etc. can be taken into account in one or the other filtering to select the parts to keep for re-nesting.

[0149] Selection criteria

[0150] The criterion for selecting a PN part from the base to be nested in a PIMA nesting plan at the location of at least one forecasted waste CHk is noted Ci. This criterion Ci can include one or more sub-criteria, also called criteria. The criteria Ci can include dimensional criteria inherited from the characteristics of the cutting of the forecasted waste CHk, structural criteria inherited from the material plate TOLk or even temporal criteria inherited from the characteristics of the existing or identified PLi, PLi schedules. According to another case, the criterion Ci responds to an optimization indicator of the PN parts to be produced, that is to say the factor which best optimizes the arrangement of PN parts within forecasted waste CHk. According to another case, a criterion Ci can correspond to the taking into account of a batching of PN parts which must be manufactured together or in the same milestone or the same schedule.

[0151] In the remainder of the description, the first criterion Ci is a criterion that is taken into account as a priority, i.e. before other criteria. However, taking into account a set of criteria is sometimes necessary in order to produce the PN part, for example a criterion relating to the type of material or to a dimension is often necessary to produce the PN part. It is therefore possible to dissociate the necessary criteria which correspond to the ranges of minimum or maximum values ​​chosen so that at least one PN part can be inscribed in a sufficient space, from the criteria for selecting a PN part among other parts.

[0152] According to a first example, the production planning of a PN part is taken into account as criterion Ci to select the said part(s).

[0153] A first operation aims to check whether one of the PN parts in the list is part of the first planning PLi. When this is the case, the number of occurrences of the PN part planned to be produced and the milestones in which this production is carried out are then checked. According to one embodiment, when the occurrence is less than a threshold value, for example two parts, the part is not selected to be reintegrated into a forecast drop location CHk. According to one embodiment, when the occurrence is greater than a threshold value, for example four parts, the PN part is not selected to be reintegrated into at least one forecast drop location CHk.

[0154] According to one embodiment, when the part is part of a batch of PN parts, that is to say that they are only manufactured in batches of a set of the same parts, then it is then verified that a certain number of forecasted drop surfaces are available or that the surface of a forecasted drop makes it possible to integrate a plurality of PN part profiles, depending on the number of parts in the batch.

[0155] In this case, an additional selection criterion is the availability of sufficient space among the forecasted CHk scraps to produce a subset of PN parts to be, for example, produced on the same day, in a given order and / or in the same schedule and / or in the same milestone. For this purpose, the set of forecasted CHk scraps of a milestone, a schedule or a set of schedules is considered for an optimization of a nesting of a subset of PN parts.

[0156] According to one embodiment, the method of the invention makes it possible to take into account planning data associated with the part PN. This planning data makes it possible to automatically check whether the part PN selected from the first list LISTi is included in another planning PLi than the first planning PLi. Figure 2 represents this verification step in which the part PN extracted from the database BDi is included in another planning PLi. This other planning may correspond to a planning of another final product or a manufacturing of a variant of the final product. When this planning data is associated with a part PN in the database BDi, it can be used so as to predict a reintegration of at least one occurrence of this part PN in an available location of a forecast fall CHk.

[0157] An interest is to select each part according to a given criterion Ci in order to label each forecast fall CHk. This selection step is noted SELi.

[0158] According to an exemplary embodiment, the correspondence indicator IN Di makes it possible to associate a part PN with a forecasted fall CHk. In this example, the method of the invention makes it possible to search for which parts can be selected to be re-registered or re-nested in a given fall CHk. In this embodiment, the method of the invention makes it possible to determine which set of parts best fills the forecasted fall CHk. An algorithm for optimizing the space defined by the forecasted fall is then implemented.

[0159] According to a first embodiment, each part in the list LISTi is associated with one or a plurality of forecast waste CHk when a correspondence indicator INDi has been generated. It is understood that the invention also makes it possible to draw up a list of forecast waste CHk for each part to be produced identified according to the correspondence indicator INDi.

[0160] The method of the invention comprises the SELi selection of a PN part to be produced associated with a reusable forecast fall to be reassigned to a milestone of a PLi, PL planning in order to complete or regenerate a P IMA nesting plan.

[0161] In another example, the INDi matching indicator allows at least one forecasted waste to be associated with a PN part. In this example, we are looking for which forecasted waste corresponds best for a given part. We can consider a list of forecasted waste LIST2 that is identified within at least one milestone of at least one schedule. This LIST2 list can then be compared with the dimensions of each part to be produced.

[0162] According to this second embodiment compatible with the first embodiment, each forecast fall CHk identified in a milestone of a schedule or in a schedule is associated with a plurality of parts of the first list LIST1 when a correspondence indicator has been generated.

[0163] Thus, this indicator makes it possible to maintain a list of parts from list LIST1 and a list of forecasted scraps LIST2 from a schedule which allow correspondences to be drawn up. These correspondences then make it possible to optimize the reuse of PN parts within a PL1 schedule or to optimize the forecasted scraps identified for their reuse.

[0164] One interest is to draw up a set of possibilities for reintegrating PN parts within a plurality of forecasted scraps before implementing an algorithm aimed at optimizing this reintegration according to optimization criteria. Indeed, when several solutions exist to associate several forecasted scraps with a part to be produced or to associate several parts to be produced with a scrap, it is necessary to choose which forecasted scrap is associated with a given part to be produced or conversely to choose which part to be produced is associated with a forecasted scrap.

[0165] Consideration of additional criteria

[0166] The optimization criteria may include the occurrence of a PN part, the dimensions of a PN part, etc. Indeed, the method of the invention makes it possible, for example, to prioritize the reintegration of large-sized parts to be produced. According to another example, a predicted drop location CHk making it possible to integrate a batch of identical parts may be prioritized with respect to another part to be integrated or a plurality of different parts.

[0167] The selection step SEL1 also allows to take into account an additional criterion Ci associated with the part PN. The criterion Ci can include different types of characterization of the part PN from the list LISTi or from a characterization of the product of which the part is part or from a planning in which the part is planned. For example, a criterion Ci includes the consideration of a first occurrence of a part extracted from the article database BDi within the first planning PLi or from another planning PLi. In this case, it is a characterization of the product or of the planning that is taken into account. According to another example, the characterization can be linked to an intrinsic characterization of the part, such as its surface finish or an orientation or thickness constraint.

[0168] According to another example which can be combined with the previous one, a criterion Ci includes taking into account a batching of identical PN parts from the article database BDi of parts to be produced.

[0169] According to another example which can be combined with the previous one, a criterion Ci comprises the consideration of at least a first time interval between two milestones of the same planning PLi in which the part extracted from the article database BDi is associated with each of the two associated milestones, each milestone being associated with a different material plate (TOLk). One advantage is to take into account a notion of temporality. Indeed, the method of the invention makes it possible to take into account a time horizon criterion beyond which one no longer seeks to reintegrate a part PN. Another advantage is to prioritize the reintegration according to the date on which the manufacturing need is expected.

[0170] According to another example which can be combined with the previous one, a criterion Ci includes taking into account at least a second time interval between two schedules PLi, PLi in which the part extracted from the article database BDi is associated with at least one milestone of each of the schedules.

[0171] According to another example that can be combined with the previous ones, a criterion of heterogeneity of the scraps produced is a criterion to be optimized. The objective of this optimization is to identify the redundant nature of the scraps produced. According to one embodiment, it is sought to minimize the heterogeneity of the scraps produced so as to favor identical scraps produced. The scraps produced can come from forecast scraps that are not associated with PN parts to be re-nested or from new scraps resulting from a nesting of a PN part producing a new scrap.

[0172] In another example that can be combined with the previous ones, the selection criterion favors the optimization of the dimensions of a set of forecast drops of a set of nesting plans with respect to the dimensions of a particular forecast drop or forecast drops of a nesting plan. In this case, an entire schedule comprising several milestones is replanned with the generation of new PIMA nesting plans.

[0173] Classification

[0174] At the end of this SELi selection step, a classification of the CHK forecast fall is carried out. This step is noted CLASSi in Figure 1. The classification makes it possible to label the forecast falls according to different labels.

[0175] The classification can be performed by a machine learning algorithm such as a convolutional neural network. Any other learning function that can calculate a class membership prediction score from values ​​forming attributes of the predicted fall CHk can be used. A cost function can then be implemented to train the learning function, in other words the machine learning model. Such a learning function can be learned with a labeled data set whose class is known.

[0176] Other algorithms can be used such as any expert system based on a knowledge base, rules and an inference engine for example.

[0177] The score can also be calculated from rules allowing the comparison of values ​​attributed to characteristics of at least one predicted fall from a set of measured, evaluated, calculated or predicted criteria with predefined threshold values ​​or values ​​from characteristics extracted from PN parts in the BDi article database.

[0178] According to an example, if a material criterion of the material plate within which a predicted fall CHk identified, for example the material is aluminum, a first characteristic value of the material can be assigned to the predicted fall Vi = 1 if PN parts of the article database BDi are made of aluminum.

[0179] If at least one PN part of an article base has compatible dimensions of a dimensional drop of the material plate then a second value V2 = 1 can also be associated. Then if V1 = V2 = 1, the forecast drop CHk can have a first label LB1, corresponding to an availability of a part that can be re-nested.

[0180] According to the same example, if the material is titanium and there are no corresponding parts, the first value assigned can be V1 = 2. If at least one PN part of an article base has compatible dimensions of the dimensional fall CHk then the second value is always V2 = 1. Then, the forecast fall CHk can have a first label LB3, that is to say that we wish to keep the fall for a later valuation, in particular because of the material which can be valued.

[0181] Other rule possibilities can allow combining criteria values ​​in order to associate labels with the predicted CHk falls.

[0182] A first label LB1 corresponds to the forecasted scraps that can be reused in order to nest a PN part from the database in the expected location of the forecasted scrap. Different re-nesting possibilities can be implemented in the method of the invention.

[0183] When a part is selected to be integrated into a nesting plan, different scenarios are possible. Figures 5 and 6 represent two different scenarios in which different parts are integrated into CHk scraps of different sizes. Figure 5 represents a scenario in which the larger parts have been reintegrated into the forecast scraps. The forecast scrap CHk' in Figure 4 has been divided into two portions defining two CHk scraps that can be used by reintegrating two different parts.

[0184] Figure 6 shows an embodiment in which smaller size forecast scraps have been used to reintegrate smaller parts because they are included in a lot of parts.

[0185] The invention makes it possible to treat the forecast fall of Figure 4 as a single forecast fall to which several PN parts are assigned. Figure 6 represents an embodiment in which the forecast fall is associated with a single PN part.

[0186] In both cases, the part label is noted LBi and this label corresponds to a reuse of the forecast fall in a current or future planning.

[0187] This first LBi label can be addressed when an occurrence or batching of parts selected in the first LISTi list in the first PLi planning plan or another PL planning plan exceeds a predefined threshold. This condition can be combined with a duration criterion. The CHK forecast waste is for example labeled with the LBi label if the selected part PN is planned in production in a limited time horizon, i.e. within a PLi or PLi planning plan.

[0188] A second label LB2 corresponds to forecasted waste CHk that is not used to reintegrate a PN part to be produced during the production of a next schedule or a next milestone of a schedule. This label corresponds to a label for conserving the forecasted waste. This case can occur when no part is selected that is compatible with the forecasted waste CHk or when the first criterion Ci does not meet certain conditions even though a part corresponds to the location of the forecasted waste. This can be the case if no occurrence of the part is present in a milestone of a future schedule. This can also occur when a part is only produced within a batch and there is not enough forecasted waste surface to reintegrate all the parts of the batch.

[0189] A third label LB3 corresponds to forecasted scraps that we wish to keep for their structural or dimensional property(ies) independently of the availability of a compatible surface of a PN part to be produced. In this case, a PN part from the first list LISTi and whose criterion Ci is compatible with a forecasted scrap is not sufficient to label the forecasted scrap as a source of material to be reused within the material plate. In this case, the method of the invention makes it possible to value the forecasted scrap CHk according to a criterion linked to the quality of the material, its surface condition, the material used for example.

[0190] In the case of labeling by a third LB3 label, of an identified forecasted fall, the conservation decision can be made according to a criterion independent of the step of querying the first article database making it possible to extract a geometric descriptor of a part. Indeed, according to an exemplary embodiment, only the dimensions of the fall can be considered to label the fall according to the third LB3 label. The invention therefore relates to a method of the invention in which the step of querying the article database is an optional step.

[0191] A fourth label LB4 corresponds to scrap forecasted for scrapping. This label LB4 is for example assigned when the first criterion Ci includes an occurrence of selected parts lower than a predefined threshold. In a borderline case, the threshold value is zero. It is understood that if there is no part to be produced that can be produced within a forecasted scrap CHk, there is no point in reusing the scrap that will be produced in a nesting plan. Finally, if this forecasted scrap CHk is not of interest for conservation for another use, scrapping it may be the most appropriate solution. The scrap produced can therefore be scrapped.

[0192] According to one embodiment, a fifth LBs label is assigned to a forecast fall CHk. This fifth LBs label makes it possible to annotate a forecast fall CHk to be re-cut for later use. In the latter case, the LBs label is a temporary label assigned to a forecast fall CHk which will have a new LB2 label once cut.

[0193] One advantage is to keep the waste actually produced near a cutting machine so that the waste produced can be re-cut first and then archived in a dedicated room for conservation later.

[0194] According to one embodiment, a sixth label LBs is associated with a forecast waste CHk restoring a surface condition of the latter. One advantage is to allow a surface treatment to be carried out on the waste produced for its reuse according to one of the labels LB1, LB2, LB3. The label LBs can therefore be assigned cumulatively with another label assigned to a forecast waste CHk. The label of a forecast waste LB1, LB2, LB3 can be modified after the surface treatment has been carried out. According to one embodiment, other labels can be used to classify the forecast waste CHk. According to one embodiment, the first label LBi comprises sub-labels making it possible to prioritize the use of the forecast waste CHk in a future PL planning.According to an example, a first sub-label LBu is assigned when the forecasted CHk drop must be reused for a part to be produced quickly, i.e. in a short time horizon, and therefore within a time limit below a given threshold. In the latter case, the association of a PN part with a schedule can be analyzed when such an association is created.

[0195] In another example, a second sub-label LB12 is used to annotate a predicted waste CHk according to a preference criterion for cutting one or more parts to be reintegrated. This may correspond to the case of Figure 5 and Figure 6. In both cases, the predicted waste CHk is labeled with a label LB1. However, in Figure 5, the reassignment of the predicted waste CHk is governed by the reintegration of large PN parts. In this case, the predicted waste CHk may have a first label LB12. In the case of Figure 6, the subdivision criterion is more important and the predicted waste CHk may have another sub-label LB13. However, this last sub-labeling is not critical since the predicted waste is reused in both cases.

[0196] According to one embodiment, the classification step comprises taking into account a storage indicator of the scraps already produced, for example having a label LB2, LB3. To this end, querying a scrap database BD2 makes it possible to obtain this indicator. One advantage is to assign a label to a scrap taking into account a quantity of scraps already produced and referenced in the database BD2.

[0197] According to one embodiment, the assignment of a conservation label LB2, LB3 comprises the association of a conservation duration with a forecast or actual drop, the data characterizing said drop and duration being recorded in the database BD2. An advantage is to trigger an automatic action at the end of the elapsed conservation duration. The action can be the assignment of a new label or the search for a schedule comprising a part to be produced corresponding to the data characterizing the recorded drop, or even the association with a new conservation duration to keep or not the drop. New schedule

[0198] When a PN part is selected from the LISTi list to be assigned to a location of a forecasted scrap of a PIMA nesting plan of a milestone of a first PLi planning, the first PLi planning is modified. This modification leads to generating a new PLi planning. The new PLi planning may include a modification of a single milestone or of a plurality of milestones depending on the number of PIMA nesting plans that have been impacted by the reassignment of a PN part to be produced. The modification of a milestone may include a new quantity of parts to be produced within a TOLk material plate from a new generated nesting plan reusing the spaces defined by the forecasted scraps.

[0199] If a re-nesting of a PN part within a given milestone impacts a subsequent milestone with another PIMA nesting plan, then the new PLi' planning includes the update of all milestones.

[0200] Figure 7 represents a PIMA nesting plan comprising a set of flanks FLi, only one of which has been represented in Figure 7. The PIMA nesting plan comprises a provisional fall CHk on the right-hand side of rectangular shape and large enough to accommodate a plurality of parts PN. The label of this provisional fall is LBi.

[0201] Figure 8 shows an example of the arrangement of a set of PN parts distributed within the location of the predicted fall CHk.

[0202] Intermediate nesting plan

[0203] According to one embodiment, an intermediate nesting plan PIMi is generated whose surface corresponds to the surface of the forecast fall CHk. This intermediate nesting plan PIMi comprises a plurality of parts PN whose profiles are integrated so as not to overlap and so as to be included in the available surface of the forecast fall CHk.

[0204] In a second step, a new PIMB nesting plan is generated comprising the superposition of the first PIMA nesting plan and the PIMi nesting plan. An advantage of this solution is that it does not modify the nesting plan(s) already optimized according to certain constraints. An advantage is that it allows the implementation of the method of the invention without modifying the existing nesting plan optimization software. The new PIMB nesting plan replaces the old nesting plan of a planning milestone.

[0205] According to one embodiment, a new PIMB nesting plan is generated. The new PIMB nesting plan comprises the re-nesting of all the parts initially nested in the PIMA nesting plan and the new identified parts that can be re-nested in the corresponding forecast scraps. In order to carry out this re-nesting, a re-nesting software component can be implemented to regenerate a nesting plan from all the identified parts.

[0206] Parts Base - BD1

[0207] Advantageously, the method of the invention comprises a step aimed at updating MAJ2 the database BD1. This update comprises the removal of the occurrences of the PN parts which have been selected to be integrated into a new nesting plan PIMB of a milestone of a given planning.

[0208] Falls Base - BD2

[0209] Furthermore, the method of the invention comprises an update MAJ1 of a fall database BD2 in which at least one labeled predicted fall CHk is recorded.

[0210] The BD2 fall database contains the falls identified by their identifier during their CAR1 characterization. One advantage is to store forecast falls that can change status from "forecast fall" to "actual fall" because they have been produced, for example when they have an LB2 label or an LB3 label. According to one embodiment, the actual falls of an LB2 or LB3 label are made available via a third-party service accessible to at least one user.

[0211] A user interface can then allow a user to access a plurality of actual scraps. The scraps are potentially stored or reused in planning. To this end, the user interface makes it possible to sort, choose and select a scrap that interests a user and that possibly meets certain constraints. The user interface therefore allows access to sorting functions or allows selection criteria to be displayed. When the data relating to the scraps are recorded on a server, the service can be accessible, for example, via a communication interface accessible from a data network such as the Internet or an intranet.

[0212] The method of the invention makes it possible to record data specific to the offcuts even when they have been reused by a rearrangement of the nesting plan by the integration of new parts. One advantage of recording this data relating to a offcut that no longer exists is to account for the savings made thanks to the method of the invention. The savings can be financial, but also environmental by measuring the reduction in the carbon footprint or the reduction in energy consumption.

[0213] In fact, a predicted fall that is avoided makes it possible to reduce the subsequent management of residual material.

[0214] Fall rate

[0215] According to one embodiment, the method of the invention comprises a calculation of a waste rate Te for a given category of material plate TOLk. The waste rate Te is for example calculated on a set of PIMA nesting plans of one or more plannings PLi, PLi.

[0216] The drop rate Te corresponds, in one example, to the percentage of unretained material of a given material plate TOLk. In another example, the drop rate Te is expressed as a percentage of the residual quantity of material or the residual surface area of ​​the material plate.

[0217] According to one embodiment, the scrap rate is used to calculate desired dimensions of a category of TOLk material plates.

[0218] An advantage of this embodiment is to optimize on the one hand the reuse of CHk scraps and on the other hand the dimensions of the TOLk material plates to be considered at the input of a PLi, PLi planning.

[0219] According to one embodiment, the method of the invention implements, for a given schedule, an optimization algorithm making it possible to minimize the CHk scrap rate of the fourth label LB4 for a set of TOLk material plates having different lengths. According to one embodiment, the optimization algorithm comprises an inference or regression operation in order to calculate a minimum CHk scrap surface having the fourth LB4 label. This embodiment can also be applied to other labels or sub-labels of forecast scraps or to a group of labels. According to one embodiment, the optimization algorithm is applied to a given number of predefined dimensions of TOLk material plates. This case is interesting when it is known that a reduced number of at least one dimension of TOLk material plates are available, for example, from a catalog.According to another embodiment, the optimization algorithm is carried out on a continuous range of values ​​of material plate dimensions. This case is interesting when it is possible to define at least one input dimension of a material plate TOLk as soon as it is machined.

[0220] According to one embodiment, a yield rate is calculated instead of a drop rate Te. In this case, the aim is to optimize the value of the yield rate. It is possible to apply an algorithm aimed at optimizing all of the labels LBi, LB2, LB3 or to apply an algorithm favoring the optimization of a single label such as the label LB1.

[0221] According to one embodiment, the optimization of the scrap rate Te or the yield rate can take into account an optimization criterion which is for example the surface condition or the material of the material plate TOLk. That is to say that we seek to optimize in a certain way a plate of such type or such type. We will seek for example to optimize the scrap rate Te according to the label LB3 for a material plate having a surface treatment of a first type and we will seek to optimize the scrap rate Te according to the label LB1 for a material plate having a surface treatment of a second type.

[0222] When a drop rate Te is calculated for a given category of plates, this drop rate Te can be optimized for a family of plates. In this case, a category or family of material plates is called a material plate having, for example, at least one physical property in common such as a surface condition, a density or an identical material.

[0223] A surface condition may include a characterization of a coating, paint, or machine surface treatment such as a direction or orientation of rolling or other surface treatment performed by a tool. A "category of material plates" may also alternatively or in combination mean a plate having length differences of at least one dimension less than a given threshold, such as a threshold of 5%, relative to an average length of that dimension of the set of plates considered.

[0224] Another alternative or cumulative condition for defining material plates of the same category may be the consideration of at least one characteristic dimension of the section of each plate of the set of material plates lower or higher than a given threshold with respect to a reference characteristic dimension.

[0225] The reference value can be obtained by calculating an average of the material plates in this set.

[0226] According to one embodiment, the method of the invention comprises a step of simulating at least one schedule according to a set of categories of material plates TOLk. In this case, the simulation comprises an optimization of the determination of a category of material plates TOLk so as to minimize the waste rate Te of said simulated schedule.

[0227] According to one embodiment, the simulation makes it possible to carry out different optimizations by taking into account different criteria to infer and determine an optimized solution. For example, the optimization can take into account a given number of parts of a simulated schedule, a number of identical parts of a simulated schedule, a heterogeneity or homogeneity factor of a set of parts arranged within a PIMA nesting plan, OR a statistical distribution of parts according to a given characteristic such as the length of one of its dimensions.

[0228] According to one embodiment, the method of the invention comprises the calculation of a statistical indicator corresponding to a quantification of a type of forecast or actual waste produced on a set of schedules. According to one example, this statistical indicator makes it possible to generate a criterion taken into account when labeling a waste to be produced. One advantage is to take into account the actual waste already produced and to redirect the production of other waste that can be kept.

[0229] System Finally, the invention relates to an STi system represented in Figure 9 comprising at least one computer for executing the steps of the method. According to one embodiment, the computer is a server accessible from a data network. According to another embodiment, the server is a local server accessible from the industrial site from which the user interface is located.

[0230] According to one embodiment, the various databases, including BDi and BD2, are hosted within a remote data server. Other remote servers may be used within the framework of the invention, in particular servers allowing access to the service offered by the implementation of the method of the invention. For example, a user authentication server may be implemented within the framework of the invention.

[0231] The computer or the plurality of calculation units executing the method of the invention comprises at least one calculator K1 making it possible in particular to carry out the operations of comparison and labeling of the forecasted scraps. The computer comprises at least one communication interface INT1 making it possible to receive data such as nesting plans, schedules, and part identifiers. According to one example, different input interfaces INT1 make it possible to receive the different data processed in the method of the invention.

[0232] The system of the invention also comprises a computer having an INT2 output making it possible to transmit the data produced by the calculator K1, such as the data characterizing the predicted falls and the labels.

[0233] In one example, the computer K1 also performs the operations to produce a new nesting plan. However, in another example, this operation is performed by another remote server (not shown) capable of producing a new nesting plan incorporating the new designated and characterized parts that have been selected from the list LIST1.

[0234] The computer advantageously comprises a memory M1 for storing data received or produced by the computer such as the list LIST1 or data for labeling or characterizing scraps or parts. According to one embodiment, the method of the invention comprises a step of producing a cut of a set of parts from a plate of material TOLk. This step also comprises the production, where appropriate, of a production of scraps of material. This step is preferably carried out after the classification in order to take full advantage of the new planning and labeling of the forecast scraps and in particular of the scraps of material actually produced.

[0235] In other words, the method of the invention is implemented by computer for the classification of predicted material waste in an industrial manufacturing process. The method of the invention is intended to be implemented for the cutting of material plate(s) from a new schedule comprising a set of milestones, each milestone being associated with a cutting of at least one material plate according to a nesting plan. The technical effect obtained is to generate a new schedule allowing better optimization of the cutting space by reallocating material spaces that would have been lost and by allowing a reduction in the unusable waste actually produced.

[0236] The invention can also be implemented directly during the industrial planning of an industrial manufacturing process aimed at cutting plates of material to obtain mechanical parts. The method of the invention then corresponds to a step prior to the cutting of material and the manufacturing process.

[0237] Thus, the invention covers a method of cutting material comprising a prior step of classifying predicted material offcuts and a cutting method implementing the new planning obtained with the classification method to produce cut parts.

Claims

CLAIMS 1. Computer-implemented method for classifying predicted material waste in an industrial manufacturing process intended to be implemented for cutting material plate(s) from a plan (PLT), said method comprising: ■ Acquisition (ACQi) of a first planning (PLi) of a set of parts (Pi) to be manufactured, forming a step of an industrial production process of a plurality of parts to be produced, said parts (Pi) being intended to be cut from a set of material plates (TOLk); ■ Acquisition (ACQ2) of at least one first nesting plan (PIMA) of parts (Pi) to be cut for each plate of material (TOLk), each part to be cut (Pi) comprising a two-dimensional profile and a thickness and the profile of which is inscribed within a first surface included in the surface of the plate of material (TOLk), each part to be manufactured represented within the first nesting plan (PIMA) being called a flank (FL); ■ Characterization (CAR1) of at least one predicted fall (CHk) defining at least one area of ​​the nesting plane (PIMA) not occupied by flanks (FL1), said characterization (CAR1) comprising at least: ■ an identifier (ID C ) of each forecast fall (CHk); ■ dimensions (K c ) of each forecast fall (CHk); ■ Query (REQ1) of a first article database (BD1) comprising a set of parts (P n) to extract the geometric descriptors of said parts (P n ) ; ■ First comparison (COMP1) between the dimensions (K c ) of at least one predicted fall (CHk) and the dimensions of at least one part (P n ) extracted from the first article database (BD1), said first comparison (COMP1) producing a correspondence indicator (IND1); ■ Determination of a first list (LISTi) of compatible parts (Pn') from the value of the correspondence indicator (INDi); ■ Selection (SELi) of at least one part (Pn) from the first list (LISTi) to be produced according to a given criterion (Ci) to be reassigned to a milestone of a planning (PLi, PLi); ■ Classification (CLASSi) of each forecast fall (CHk) according to a plurality of labels (LBi, LB2, LB3) from a calculation of a characteristic score of said forecast fall (CHk), said score being calculated in particular from at least the first criterion (Ci); ■ Generation (GEN1) of a new first planning (PLi') comprising the generation of at least one new nesting plan (PIMB) for at least one material plate (TOLk) comprising at least one new part selected from the first list (LISTi) within zones corresponding to a forecast fall (CHk) having a reuse label (LB1); ■ Update (MAJ1) of a falls database (BD2) in which at least one labeled predicted fall (CHk) is recorded.

2. Method according to claim 1 characterized in that the first planning (PLi) comprises at least one milestone corresponding to a cutting forecast of at least one plate of material (TOLk) forming a step of an industrial production process of a plurality of parts to be produced.

3. Method according to any one of claims 1 to 2, characterized in that an initial planning (PLo) comprises at least one product identifier and an association with a plurality of first plannings (PLi), each first planning (PLi) being associated with a material plate (TOLk).

4. Method according to any one of claims 1 to 3 characterized in that the nesting plan (PIMA) comprises a set cl' identifiers of parts to be produced, and for each identifier a profile of the part to be produced which is oriented and positioned within a surface representing the surface of a material plate (TOLk) associated with said nesting plane (PIMA).

5. Method according to any one of claims 1 to 4, characterized in that the first surface of the nesting plane (PIMA) is equal to the surface of at least one plate of material (TOLk).

6. Method according to any one of claims 1 to 5, characterized in that the dimensions (K c ) of each fall (CHi) include in particular a surface area and a thickness.

7. Method according to any one of claims 1 to 6, characterized in that a set of offcuts (CHk) is generated from a processing of all the zones of the nesting plane not occupied by flanks (FLi), said processing comprising a step of segmentation (SEGi) of the surfaces of each predicted offcut from the cutting lines of the flanks of the nesting plane (PIMA) and the edges of the nesting plane.

8. Method according to claim 7 characterized in that the step of segmenting (SEGi) the surfaces of each forecast fall (CHk) comprises taking into account a set of exclusion criteria making it possible to assign an area of ​​the surface of the nesting plane (P IMA) not occupied by flanks (FLi) to a waste area which is not taken into account for the generation of a forecast fall.

9. Method according to any one of claims 7 to 8 characterized in that the step of segmentation (SEGi) of the surfaces of each predicted fall (CHk) comprises a first characterization (CAR10) of the fall taking into account the size of the predicted fall (CHk), the position of the predicted fall (CHk), a surface state of the predicted fall (CHk) and / or the material of the predicted fall (CHk).

10. Method according to any one of claims 1 to 9, characterized in that each forecast fall (CHk) comprises a set of geometric descriptors including in particular: ■ a minimal rectangle and / or; ■ a polygon with a maximum number of edges and / or; ■ an image of the predicted fall and / or; ■ a two-dimensional outline of the profile of the predicted fall and / or; ■ data characterizing the exact surface area of ​​the predicted fall.

11. Method according to any one of claims 1 to 10 characterized in that the first comparison (COMPi) comprises the comparison of the surface of a predicted fall (CHk) with the surface of a part identified in the article database (BDi).

12. Method according to any one of claims 1 to 11, characterized in that the comparison step (COMP1) comprises comparing the surface area of ​​a polygon inscribed in the outline of a zone defining a predicted fall (CHk) with the perimeter and / or the surface area of ​​an external polygon containing the surface area of ​​a part selected from the article database (BDi).

13. Method according to any one of claims 1 to 12, characterized in that the comparison step (COMPi) comprises comparing the perimeter and / or the surface area of ​​a plurality of polygons generated and inscribed in the outline of an area defining a predicted fall (CHk) with the perimeter and / or the surface area of ​​an external polygon containing the surface area of ​​a part selected in the article database (BDi).

14. Method according to any one of claims 1 to 13 characterized in that the first criterion (Ci) comprises: taking into account a first occurrence of a part extracted from the article database (BDi) and associated with a first planning (PLi) or another planning (Pi) and / or ■ taking into account a batching of identical parts extracted from the article database (BDi) and associated with at least one material plate (TOLk) from the first planning (PLi) and / or; ■ at least a first time interval between two milestones of the same planning (PLi) in which the part extracted from the article database (BDi) is associated with each of the two associated milestones, each milestone being associated with a different material plate (TOLk) and / or; ■ at least one second time interval between two schedules (PLi, PLi) in which the part extracted from the article database (BDi) is associated with at least one milestone of each of the schedules.

15. Method according to any one of claims 1 to 14 characterized in that the classification (CLASSi) comprises: ■ an allocation of a first label (LBi) to the forecast falls (CHk) for their reuse when the first criterion (Ci) includes: ■ an occurrence or a subdivision of parts selected in the first list (LISTi) in the first planning plan (PLi) or another planning plan (PLi) greater than a predefined threshold and; ■ a first or second time interval less than a predefined duration; ■ an allocation of a second label (LB2) to the forecast falls (CHk) for their conservation when the first criterion (Ci) includes: ■ an occurrence or a subdivision of parts selected in the first list (LISTi) in the first plan of planning (PLi) or another planning plan (PLi) above a predefined threshold and ■ a first or second time interval greater than a predefined duration and / or; ■ an allocation of a third label (LB3) to the forecast falls (CHk) for their conservation when the first criterion (Ci) corresponds to structural, dimensional or quality properties of the forecast fall corresponding to a predefined criterion and / or; ■ an allocation of a fourth label (LB4) to the forecast waste (CHk) for their disposal when the first criterion (Ci) includes: ■ an occurrence of selected parts less than a predefined threshold and; ■ a first or second time interval greater than a predefined duration and; ■ an assignment of the third label (LB3) to the forecast fall.

16. Method according to any one of claims 1 to 15, characterized in that the generation of the new nesting plan (PIMB) comprises the superposition of the first nesting plan (PIMA) and an intermediate nesting plan (PIMi), said intermediate nesting plan (PIMi) comprising at least one new part to be produced selected from the first list (LIST1) and positioned and oriented within zones corresponding to a forecast fall having a reuse label (LB1).

17. Method according to any one of claims 1 to 16, characterized in that the database of falls (BD2') comprises the falls having the second label (LB2) and / or the third label (LB3) so as to provide access to said falls thus labeled to a user via a communication interface accessible from a data network.

18. Computer program product comprising instructions which, when the program is executed by a computer, cause the latter to implement the steps of the method according to any one of claims 1 to 17.

19. System (STi) for generating a labeling of a forecast fall characterized in that it comprises: ■ at least one communication interface (INTi) to acquire planning data and nesting plans and parts from the first database, ■ a memory (MEMi) for recording said data and ■ a calculator (Ki) for generating a labeling of said forecast falls according to the method of any one of claims 1 to 17, and in that it further comprises an output communication interface (INT2) for the updated data of the labeled falls to computer equipment.

20. System (ST1) according to claim 19 characterized in that it comprises a state sensor of a material plate in order to calculate a state criterion taken into account in the development of the first criterion (Ci), the state criterion being able to be linked in particular to the surface state of the material plate such as a quantification of a level of rust, impacts, a paint finish or an orientation criterion for example of a lamination or a fiber.

Images