Laminate comprising tempered glass

Abstract

In some embodiments, the glass layer may be tempered in an oven that uses air to support and / or convey the glass therethrough. Thus, there may be uniform pressure on the major surface of the glass layer, and distortion may be reduced. In some embodiments, a method includes receiving parameters associated with a trained machine learning model configured to receive inputs indicative of parameters associated with sheet tempering and to output one or more recipe and / or bed load changes for a successive batch of sheets to be tempered; obtaining parameters associated with the first batch of sheets undergoing tempering; one or more modifications are determined by providing the obtained parameters to the trained machine learning model: a current recipe for processing the first batch of sheets; and / or a bed configuration of the second batch of sheets, wherein the one or more modifications are used to process the second batch of sheets.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] The PCT application form is filed concurrently with this specification as a part of this application. Each application identified in the concurrently filed PCT application form from which this application claims the benefit of or priority is incorporated herein by reference in its entirety and for all purposes. Background Art

[0003] Laminated glass structures are used in a variety of contexts. For example, they can be used in optically switchable windows, such as electrochromic windows. Laminated glass structures comprise at least two glass sheets bonded together at their respective major surfaces. One or more of the glass sheets may be tempered. An electrochromic device may be disposed on one or more major surfaces of the glass sheets. Unfortunately, glass sheets may have defects that can produce optically undesirable effects, which can be amplified when the glass sheets are laminated. Summary of the Invention

[0004] Aspects of the present disclosure relate to a laminated glass structure comprising: (a) a first, heat-treated glass layer having no peak-to-valley undulations of about 0.2 mm or greater; and (b) a second glass layer adhesively bonded to the heat-treated glass layer. The laminated glass structure does not exhibit a lens effect caused by the undulations. In some embodiments, the laminated glass structure further comprises an optically switchable device, such as an electrochromic device.

[0005] In certain embodiments, the laminated glass structure further includes an adhesive layer between the heat-treated glass layers, such as a resin (eg, polyvinyl butyral (PVB), ionoplast (SentryGlas, SBP), or a combination thereof).

[0006] In certain embodiments, the laminated glass structure further includes an electrochromic device disposed on a surface of the second glass layer opposite the heat-treated first glass layer. The second glass layer may be an annealed glass layer.

[0007] In certain embodiments, the laminated glass structure further includes: (i) an electrochromic device disposed on a surface of a second glass layer opposite the heat-treated first glass layer (the second glass layer may be an annealed glass layer); (ii) a heat-treated third glass layer; and (iii) a fourth glass layer adhesively bonded to the heat-treated third glass layer. In some cases, the electrochromic device is also disposed on a surface of the fourth glass layer.

[0008] In certain embodiments, the laminated glass structure further includes an electrochromic device disposed on a surface of a second glass layer opposite the heat-treated first glass layer. The second glass layer may include heat-treated glass. In certain embodiments, the heat-treated first glass layer is a tempered glass layer.

[0009] Other aspects of the present disclosure relate to an integrated glass unit comprising: any of the laminated glass structures described above; a mate lite; and a sealed interstitial region between the laminated glass structure and the mate lite.

[0010] Other aspects of the present disclosure relate to a laminated glass structure comprising (a) a first heat-treated glass layer having no curvature or a curvature of approximately 10 mm or less; and (b) a second glass layer adhesively bonded to the heat-treated glass layer. Such a laminated glass structure may further include an optically switchable device and / or an adhesive layer between the heat-treated glass layer and the glass layer. The heat-treated first glass layer may be a tempered glass layer.

[0011] In certain embodiments, the laminated glass structures described in these aspects further include an electrochromic device disposed on a surface of a second glass layer opposite the heat-treated first glass layer, wherein the second glass layer is an annealed glass layer.

[0012] In certain embodiments, the laminated glass structure described in these aspects further includes: (i) an electrochromic device disposed on a surface of the second glass layer opposite the heat-treated first glass layer (where the second glass layer is an annealed glass layer); (ii) a heat-treated third glass layer; and (iii) a fourth glass layer adhesively bonded to the heat-treated third glass layer. The electrochromic device may be disposed on a surface of the fourth glass layer.

[0013] In certain embodiments, the laminated glass structures described in these aspects further include an electrochromic device disposed on a surface of the second glass layer opposite the heat-treated first glass layer. The second glass layer may include heat-treated glass.

[0014] Other aspects of the present disclosure relate to laminated glass structures comprising: (a) a first heat-treated glass layer produced by heat-treating a preheat-treated glass layer in a furnace, wherein the preheat-treated glass layer is supported by a plurality of air jets; and (b) a second glass layer adhesively bonded to the heat-treated glass layer. In certain embodiments, these laminated glass structures further comprise an optically switchable device and / or an adhesive layer between the heat-treated glass layer and the glass layer. In various embodiments, the heat-treated first glass layer is produced by tempering the preheat-treated glass layer in a furnace.

[0015] The laminated glass structure of these aspects can further include an electrochromic device disposed on a surface of a second glass ply opposite the heat-treated first glass ply, wherein the second glass ply is an annealed glass ply.

[0016] The laminated glass structure of these aspects may further include: (i) an electrochromic device disposed on a surface of a second glass layer opposite the heat-treated first glass layer, wherein the second glass layer is an annealed glass layer; (ii) a heat-treated third glass layer; and (iii) a fourth glass layer adhesively bonded to the heat-treated third glass layer. In such a structure, the electrochromic device may be disposed on a surface of the fourth glass layer.

[0017] The laminated glass structure of these aspects can further include an electrochromic device disposed on a surface of the second glass layer opposite the heat-treated first glass layer. The second glass layer can include heat-treated glass.

[0018] Other aspects of the present disclosure relate to methods of making a laminated glass structure, which may be characterized by the following operations: (a) heat treating a preheat treated glass layer by supporting the preheat treated glass layer on a plurality of air jets while exposing the preheat treated glass layer to heat treating conditions to produce a heat treated first glass layer; and (b) adhesively bonding the heat treated first glass layer to a second glass layer.

[0019] In some embodiments, the preheat treated glass layer does not contact a solid surface during the thermal treatment. In some embodiments, the preheat treated glass layer does not contact a roller during the thermal treatment.

[0020] In certain embodiments, during heat treatment, the preheat treated glass layer floats substantially horizontally on the air generated using the plurality of air jets. In certain embodiments, during heat treatment, the preheat treated glass layer floats at an angle of inclination of no more than about 10 degrees from a horizontal plane on the air generated using the plurality of air jets. In certain embodiments, during heat treatment, the preheat treated glass layer floats substantially horizontally on the air generated using the plurality of air jets. The air jets can generate air flow at an angle, or within a range of angles, that generates a force to propel the preheat treated glass layer along a path in the heat treatment furnace where the heat treatment conditions are applied. The heat treatment furnace can include one or more guardrails that retain the preheat treated glass layer within the path of the heat treatment furnace.

[0021] In certain embodiments, exposing the preheat-treated glass layer to heat treatment conditions includes heating the preheat-treated glass with heat emitted by one or more heating plates while supporting the preheat-treated glass above a plurality of air jets. In some cases, the one or more heating plates include at least one heating plate positioned substantially below the preheat-treated glass.

[0022] In some embodiments, the method further includes fabricating an electrochromic device on the heat-treated first glass layer and / or on the second glass layer. In some embodiments, the method further includes forming the electrochromic device on a surface of the second glass layer opposite the heat-treated first glass layer, wherein the second glass layer is an annealed glass layer.

[0023] In certain embodiments, the method further includes: (a) forming a first portion of the electrochromic device on a surface of a second glass layer opposite the heat-treated first glass layer, wherein the second glass layer is an annealed glass layer; (b) forming a second portion of the electrochromic device on a surface of an annealed fourth glass layer opposite the heat-treated third glass layer; and (c) contacting the first portion of the electrochromic device to the second portion of the electrochromic device.

[0024] In certain embodiments, the method further includes forming an electrochromic device on a surface of a second glass layer opposite the heat-treated first glass layer, and wherein the second glass layer includes heat-treated glass.

[0025] In some embodiments, the heat treatment includes quenching the preheat-treated glass layer by exposing different portions of the preheat-treated glass layer to different cooling rates. In some embodiments, exposing different portions of the preheat-treated glass layer to different cooling rates is performed using one or more quenching air jets. In some embodiments, the heat treatment includes tempering the preheat-treated glass layer.

[0026] Other aspects of the present disclosure relate to any of the following methods of forming an integrated glass unit: assembling a laminated glass structure, a mating foil, and a spacer in a manner that forms a sealed interstitial region between the laminated glass structure and the mating foil produced as described above.

[0027] Certain aspects of the present disclosure relate to an apparatus that includes a furnace configured to accommodate a layer of glass and comprising: (a) a heater; (b) an air floatation surface; (c) a plurality of holes on the air floatation surface; and (d) a plenum or manifold configured to direct an air flow through the holes to generate air jets that can impinge on a first surface of the layer of glass and support the layer of glass above the air floatation surface.

[0028] In some embodiments, the apparatus further comprises a second plurality of holes configured to direct air onto a second surface of the glass layer opposite the first layer. In certain embodiments, the holes in the plurality of holes are configured to direct the air jet at a non-perpendicular angle relative to the first surface of the glass layer.

[0029] In certain embodiments, the furnace is configured so that as the glass layer moves through the tempering furnace, the edges of the glass sheet do not touch the surface of the furnace.

[0030] The apparatus may further include a quenching zone comprising a plurality of quenching holes configured to provide quenching air jets that can support the glass sheet while in the quenching zone. In some cases, at least one of the plurality of quenching holes includes a nozzle configured to adjust the pressure of the quenching air jet emitted by the nozzle. These and other features of the present disclosure will be presented in greater detail below with reference to the drawings.

[0031] In some embodiments, a method for determining thin film tempering process parameters and / or bedload layout is provided. In some embodiments, the method includes: receiving parameters associated with a trained machine learning model, the trained machine learning model configured to receive input indicating parameters associated with thin film tempering and output one or more recipes and / or bedload changes for a subsequent batch of thin films to be tempered; obtaining parameters associated with a first batch of thin films undergoing tempering; and determining, by providing the obtained parameters to the trained machine learning model, one or more modifications to: a current recipe for processing the first batch of thin films; and / or a bedload layout for a second batch of thin films, wherein the one or more modifications are used to process the second batch of thin films.

[0032] In some embodiments, a method includes: a) initializing a machine learning model configured to receive input indicating parameters associated with tempering a sheet and output one or more recipes and / or bed load changes for a subsequent batch of sheets to be tempered; b) utilizing the machine learning model to generate outputs including recipe changes and / or bed load layouts given the inputs indicating parameters associated with tempering a batch of sheets indicated in one or more training samples; c) updating weights of the machine learning model based at least in part on a difference between the generated outputs and a ground truth recipe and / or bed load layout for the changes indicated in the one or more training samples; and d) repeating operations (b) and (c) until it is determined that the machine learning model has completed training.

[0033] In some embodiments, a method includes: determining information associated with a residual heat load of a set of rollers of a furnace used to perform a tempering process on a first batch of thin sheets; and determining at least one of the following: 1) a modification to the tempering process, wherein the modified tempering process is to be used to process a second batch of thin sheets; or 2) a bed load layout for the second batch of thin sheets, wherein the modified tempering process and / or bed load layout accounts for the effects of the residual heat load of the set of rollers. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 Depicted are embodiments of laminated glass structures comprising a layer of tempered glass laminated to a second layer of glass.

[0035] Figure 2A is an exploded view of the components of a laminated glass structure.

[0036] Figure 2B It shows that Figure 2A Example of a final laminated glass structure manufactured from components.

[0037] Figure 3A and 3B Shown Figure 2A - Variation of the laminated glass embodiment of B.

[0038] Figure 4 is an exemplary flow chart illustrating certain processes for manufacturing a laminated glass structure.

[0039] Figure 5 A glass sheet is shown during a heat treatment process, wherein the glass sheet is supported against gravity by air jets providing pressure against the lower major surface of the glass sheet.

[0040] Figure 6 shows a glass sheet in a heat treatment process similar to Figure 5In the glass sheet, the direction of the pressure or air jet is not substantially perpendicular to the upper major surface and the lower major surface of the glass sheet.

[0041] Figure 7 Shown is an apparatus for carrying out a heat treatment, such as Figure 5 Heat treatment of the embodiment.

[0042] Figure 8A -B shows an example of a tempered environment that allows a glass sheet to be moved around within the environment while undergoing heat treatment.

[0043] Figure 8C -D schematically illustrates an exemplary quenching apparatus configured to achieve quenching in a manner that applies different degrees of quenching to different locations within the apparatus.

[0044] Figure 9 Presented are schematic illustrations of a cross-section of an electrochromic device according to some embodiments.

[0045] Figure 10 Depicted are insulated glass units (IGUs) having electrochromic flakes that can include the laminated glass structures disclosed herein.

[0046] Figure 11 is a flow chart of an exemplary process for using a trained machine learning model to determine modifications to a current recipe and / or bed load configuration, according to some embodiments.

[0047] Figure 12 is a flow chart of an exemplary process for training a machine learning model configured to determine modifications to a recipe and / or bed load configuration, according to some embodiments.

[0048] Figure 13 is a flow chart of an exemplary process for processing a second batch of sheets using a modified layout and / or recipe determined based on the heat loading of a set of rollers previously used to process a first batch of sheets, according to some embodiments.

[0049] Figure 14 is a diagram of an exemplary system for determining recipe and / or layout modifications, according to some embodiments. DETAILED DESCRIPTION

[0050] Introduction and Context

[0051] Existing processes for producing laminated glass structures often encounter distortion issues, particularly when one or more of the glass layers in the laminate undergoes tempering or other heat treatments. Distortion can be caused by the following reasons. Tempered glass is typically tempered in a furnace that uses rollers to convey the glass. Because the glass softens at these high temperatures, it produces "roller waves" during the tempering process. This is caused by the speed at which the glass moves through the tempering furnace and the spacing of the rollers. There is a certain sag in the glass between the rollers. The distortion is usually only slight, about 1 mm or less, but the pattern is regular. When the tempered glass is laminated to another piece of glass, these uneven surfaces (recesses) are filled by the laminating adhesive, even if the other piece of glass is completely flat. This creates an optical effect known as a "lensing effect," where the light passing through is magnified and distorted.

[0052] In some embodiments, this problem is solved by tempering the glass layers in a furnace that uses air to support and / or convey the glass through. Thus, there can be uniform pressure across the major surfaces of the glass, and thus no roller waves or other distortions.

[0053] In some embodiments, laminated glass structures containing tempered glass sheets have little or no lensing effect or curvature of the glass surface.

[0054] the term

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art. A more complete understanding of the terms presented immediately below can be obtained by reference to the remainder of the specification. The following description is presented to provide context and an introduction to the complex concepts described herein. These descriptions are not intended to limit the full scope of this disclosure.

[0056] Glass ply - A glass ply is a section or piece of generally flat glass, typically having two major surfaces that are significantly larger than all other surfaces. In various embodiments, the two major surfaces are parallel or substantially parallel. In the embodiments disclosed herein, at least one generally flat surface of some glass plies is susceptible to roller waves. A glass ply is sometimes referred to as a glass sheet. It can take the form of a thin sheet of glass, such as used in windows such as integrated glass units (IGUs). In various embodiments, the glass ply is provided as a layer of a laminated glass structure.

[0057] Roller waves are repetitive, periodic waves observed in tempered glass. They can distort reflected images in the glass. Roller waves are generated when heated and softened glass moves along rollers during the tempering process. Roller waves can be characterized by peak-to-valley distance and / or wavelength.

[0058] Roller wave measurements can be performed according to ASTM C1651:

[0059] This test method is a procedure for determining the peak-to-valley depth and wavelength of roller waves in flat glass and then calculating the optical distortion caused by the roller waves. Peak-to-valley measurements provide a means of monitoring roller wave distortion in heat-treated glass products. Roller waves are inherent in flat glass heat-treated in furnaces that use rollers to convey the glass. For additional glass property and quality information, refer to ASTM specifications C1036 and C1048, which are incorporated herein by reference in their entirety.

[0060] Exemplary instruments for measuring roller waves include the following available from Strainoptics, Inc. (North Wales, Pennsylvania):

[0061] The RWG-DF Digital Flat Roller Wave Gauges feature a 16-inch long, flat, Delrin-coated bottom surface. The RWG-DF is equipped with a digital indicator for easy readout of peak and valley measurements (W). The instrument is used with a tape measure to determine the roller wavelength (L), or the distance between two consecutive peaks or valleys (see figure on next page). The digital instrument can be set for English or metric readings and has a sensitivity of 0.01 mm (0.0005 inches).

[0062] The RWG-D digital roller wave gauge features a wear-resistant three-point contact bottom surface and a digital indicator readout with a metric resolution of 0.01 mm or an imperial resolution of 0.0005 inches. The contact point spacing can be adjusted based on the length of the peak-to-peak roller wave distance for more accurate and repeatable results. A high-sensitivity model (RWG-D-HS) is available for applications requiring high distortion sensitivity (1 mdpt).

[0063] Roller Wave Distortion - This is an optical effect caused by undulations (usually roller waves) on a window or other transparent structure. The optical effect may appear as a lens effect, which is a localized variation in the refraction of the transparent structure and gives the observer the impression of magnification at periodic intervals on the surface of the structure. The period of the lens effect corresponds to the period of the responsible roller waves. The lens effect may be at least partially due to the resin or other medium at the interface of the surface of the first transparent structure having the roller waves and the second transparent structure bonded to the surface of the first transparent structure. In various embodiments, roller wave distortion occurs when the first transparent structure is a tempered glass sheet and the second transparent structure is a second glass sheet laminated to the tempered glass sheet. However, the second transparent structure may or may not have roller waves, in which case the roller waves may exacerbate the lens effect.

[0064] Undulation (the distance between peaks and valleys at a given wavelength) - This term describes roller waves and other types of periodic variations in the face of a flat surface, such as a sheet of glass. Roller waves are caused by rollers that rest or transport a flat workpiece during heat treatments such as tempering, while undulation can be caused by any process.

[0065] Bow - Bow refers to the deviation from flatness across the entire face of a glass sheet. In some cases, bow is measured at or near the center of the glass sheet. In some cases, bow is measured from a three-point reference plane around the edge of the window. The bow value is then calculated by measuring the position of the mid-surface at the center of the window and determining its distance from the reference plane.

[0066] In some embodiments, bow (or warpage) is calculated using ASTM C1048 (Section 11.6):

[0067] 11.6 Local Warp and Overall Bow and Warp—Place the sample glass in a free-standing vertical position, resting on a spacer at the quarter point. With the glass in this position, place a ruler across the concave surface, parallel to and within 25.4 mm (1 inch) of the edge, and measure the maximum deviation using a taper or feeler gauge, dial indicator, or fine scale ruler. When the above procedure is not applicable to the larger size of 3 mm (1 / 8 inch) thickness, place the glass on a flat surface, concave side down, and use a taper gauge, feeler gauge, dial indicator, or fine scale ruler, reading in 0.02 mm (0.001 inch) increments, to determine the overall bow and warp. When the alternative (horizontal) procedure is used, the overall bow and warp values ​​shown in the second row of Table 2 [reproduced below] apply to 3 mm (1 / 8 inch).

[0068] Table 2 Overall curvature and warpage, maximum value

[0069]

[0070] A Values ​​apply to 3 mm only when the alternative inspection procedure in 11.6 is used. 1 / 8 inches) thickness.

[0071] Although this specification generally describes "tempered" glass and methods and apparatus for producing tempered glass, the glass, methods, and apparatus described herein should be understood to refer to both heat-strengthened glass and tempered glass, unless the context clearly indicates otherwise. The term "heat-treated" glass should be understood to include tempered glass, heat-strengthened glass, and other forms of glass that have been heat-treated to achieve mechanical improvements.

[0072] laminated

[0073] The laminated glass structures disclosed herein include at least two component glass layers, at least one of which can be a glass sheet. In some cases, at least one of the component glass layers is a tempered glass layer bonded to a different glass layer (sometimes referred to as a "second glass layer"). The second glass layer can be another tempered glass layer, or it can be an untempered glass layer. Examples of untempered glass layers include annealed glass layers, heat-strengthened glass (i.e., semi-tempered or semi-strengthened glass), and the like.

[0074] The second glass layer can be bonded to the tempered glass layer using any of a variety of bonding methods. In some examples, the bonding is an adhesive bond. For example, the laminated glass structure can include a bonding layer between the tempered glass layer and the glass layer. The bonding layer can include a resin. Examples of such resins include polyvinyl butyral (PVB) resin, polyurethane, ethylene vinyl acetate (EVA), ionoplast interlayers (e.g., available from SentryGlas, SBP), and combinations thereof.

[0075] Lamination utilizes various techniques, including inserting solid resin sheets between glass layers and heat pressing, using liquid resins, and other techniques known in the art. The adhesive layer can be appropriately selected based on its function; for example, various structural and aesthetic properties can be achieved depending on how the laminated structure will be deployed in the structure.

[0076] Optical properties

[0077] As explained, laminated glass structures comprising at least one tempered glass sheet may exhibit a lens effect. In certain embodiments described herein, the laminated glass structure does not exhibit a lens effect caused by undulations on at least one surface of the glass sheets in the structure. This is because the bonded glass sheets do not contain significant roller waves or other undulations. Other optical properties and functionalities of the laminating adhesive may include, for example, tint (static or dynamic electrochromic, UV blocking, anti-reflection, anti-iridescence, etc.). In some embodiments, the laminated glass structure includes an electrochromic device or other optically switchable device comprising one or more organic (e.g., polymer) components (e.g., ion-conducting layers, suspended particle layers, liquid crystals, etc.). In such embodiments, one or more such organic components may be included along with the adhesive bonding the at least one tempered glass sheet. In this manner, when the two glass sheets are laminated together, an optically switchable device is formed. Such glass sheets may include a transparent conductive layer, such as a transparent conductive oxide (e.g., indium tin oxide, fluorinated tin oxide, etc.).

[0078] Undulations on the glass surface

[0079] In certain embodiments, a laminated glass structure includes a glass sheet having at least one surface that has no undulation of about 0.5 mm or greater in peak-to-valley distance, or no undulation of about 0.2 mm or greater. This peak-to-valley distance can be determined, for example, as described in discussion forums regarding ASTM C1048. In certain laminated glass structures, such a surface can be bonded to a mating surface of an adjacent glass sheet in the laminated glass structure. In various embodiments, the glass sheet that has no undulation of about 0.5 mm or greater in peak-to-valley distance (or no undulation of about 0.2 mm or greater) is a tempered glass layer.

[0080] Curvature of the glass surface

[0081] In certain embodiments, a laminated glass structure includes a glass sheet having at least one surface with no curvature, a curvature of approximately 10 mm or less, or a curvature of approximately 5 mm or less. This curvature can be determined, for example, as described in ASTM C1048. In certain laminated glass structures, such a surface can be bonded to a mating surface of an adjacent glass sheet in the laminated glass structure. In various embodiments, the glass sheet with no curvature (or with a curvature of approximately 10 mm or less, or approximately 5 mm or less) is a tempered glass layer.

[0082] Laminated glass configuration

[0083] As mentioned, the laminated glass structure comprises at least two component glass layers. In various embodiments, one or more of these component glass layers has an optically switchable glass layer disposed on a surface. The optically switchable device can be an electrochromic device. Several exemplary configurations of the laminated glass structure are presented herein.

[0084] Figure 1 An embodiment of a laminated glass structure 101 is depicted, comprising a tempered glass layer 105 laminated to a second glass layer 109. Second glass layer 109 can be an annealed glass sheet, a tempered glass sheet, or any other substrate. If tempered, glass layer 109 typically has the same dimensional tolerances as tempered glass layer 105, i.e., at least with respect to roll, undulation, and curvature. Tempered glass layer 105 is bonded to second glass layer 109 via an interlayer adhesive 107, such as a resin (e.g., PVB or an ionomer interlayer). Second glass layer 109 can be inset around its perimeter from glass layer 105 to protect its edges and / or the optically switchable device thereon; however, if glass layer 109 is tempered, inset may not be required. Glass layers 105 and 109 can have the same or different thicknesses, each typically being about 2 mm to about 12 mm thick.

[0085] Laminated glass structure 101 includes an electrochromic device 111 disposed on a surface of second glass layer 109 opposite the surface bonded to tempered glass layer 105. Optionally, laminated glass structure 101 includes an anti-reflective layer, which may be disposed on a surface of tempered glass layer 105 or a surface of second glass layer 109. In some cases, the anti-reflective layer is disposed on a surface of tempered glass layer 105 opposite adhesive 107.

[0086] If the tempered glass layer 105 exhibits undulations, such as roller waves, the laminated glass structure 101 may exhibit a lens effect because the adhesive 107 fills the interstitial areas formed in the valleys of the undulations. In certain embodiments, the tempered glass layer 105 is formed to have no roller waves or to have roller waves with a peak-to-valley spacing of no greater than approximately 0.5 mm. In certain embodiments, the tempered glass layer 105 has no bow or warp. In certain embodiments, the tempered glass layer 105 has no bow greater than approximately 10 mm.

[0087] Although Figure 1 Not shown in FIG, but a laminated structure having elements of structure 101 may include one or more additional elements, such as one or more additional glass layers (not shown). Structure 101 may be the outer sheet of an insulating glass unit.

[0088] In some embodiments, the laminated glass structure comprises two or more layers of tempered glass. In some cases, none of the layers of tempered glass have curvature that would cause optical distortion (e.g., any curvature is about 10 mm or less). In some cases, none of the layers of tempered glass have undulation that would cause optical distortion (e.g., any undulation has a peak-to-valley distance of about 0.5 mm or less). Figure 2A and 2B Examples that meet these requirements are presented.

[0089] Figure 2A An exploded view of the assembly 201 of the laminated glass structure is shown. In some embodiments, the laminated glass structure (e.g. Figure 2B The components are manufactured separately in a process to form a laminated glass structure 231. The component 201 includes a first laminated glass component 202 and a second laminated glass component 204. These components can be manufactured separately and then joined to form the final laminated glass structure.

[0090] Assembly 202 comprises a tempered first glass layer 205 bonded to a second glass layer 209. The bonding of layers 205 and 209 is achieved by an adhesive interlayer 207. Interlayer 207 may comprise a resin such as PVB or an ionomer interlayer.

[0091] The partial electrochromic device 211 is disposed on the surface of the second glass layer 209 opposite the surface bonded to the tempered glass layer 205. The partial electrochromic device 211 may include one or more layers of an electrochromic device.

[0092] Component 204 can be a reflection of component 202, but has different components of the electrochromic device. In the depicted embodiment, component 204 includes a tempered third glass layer 215 bonded to a fourth glass layer 219. The bonding of layers 215 and 219 is achieved via an adhesive interlayer 217. Interlayer 117 can include a resin such as PVB or an ionomer interlayer.

[0093] The second partial electrochromic device 221 is disposed on the surface of the fourth glass layer 219 opposite the surface bonded to the third tempered glass layer 215. The partial electrochromic device 221 may include one or more layers of an electrochromic device.

[0094] Partial electrochromic devices 211 and 221 include layers that form different and complementary parts of a complete electrochromic device. For example, partial device 211 can be an electrochromic layer (sometimes implemented using a cathodically coloring electrochromic material), and partial device 221 can be a counter electrode (optionally implemented using an anodically coloring electrochromic material). The partial device may additionally contain layers used in electrochromic devices, such as transparent conductive layers, ion conductive layers, etc.

[0095] Figure 2B A laminated glass structure 231 is shown, which has a fully fabricated electrochromic device 230 formed from partial electrochromic devices 211 and 221. Lamination adhesive 232 is used to bond 211 and 221 together; it acts as an adhesive and ion conductor (electrolyte) for device 230. Adhesive 232 can be applied between the partial devices as a polymer sheet, laminated as a liquid resin, etc. Adhesive 232 can have optical properties to complement the optical properties of the optical device.

[0096] Second glass layer 209 can be an annealed glass layer, a tempered glass layer, or any other type of glass layer. Separately, fourth glass layer 219 can be an annealed glass layer, a tempered glass layer, or any other type of glass layer. In some embodiments, the fully fabricated electrochromic device 230, combined with second and fourth glass layers 209 and 219, is relatively thin, for example, approximately 1 to 5 mm.

[0097] In some examples, partial electrochromic device 211 includes an electrochromic cathode layer (e.g., tungsten oxide on annealed glass) on glass layer 209. In some embodiments, partial electrochromic device 221 includes an electrochromic anode layer (e.g., nickel tungsten oxide on annealed glass) on fourth glass layer 219. In some embodiments, fully fabricated electrochromic device 230 includes an organic ion-conducting layer between the cathodically coloring electrochromic layer and the anodically coloring electrochromic layer.

[0098] It should be noted that Figure 2B The laminated glass structure 231 shown may be formed by, for example, Figure 2A For example, the electrochromic device laminate 234 may be fabricated prior to laminating the device laminate 234 to form the laminated glass structure 231. Figure 2B Not shown, but a laminated glass structure having elements of structure 231 may include one or more additional elements, such as one or more additional glass layers (not shown).

[0099] Figure 3A and 3B Shown Figure 2A -B changes in laminated glass structure and manufacturing technology. Figure 3A An exploded view of the assembly 301 of a laminated glass structure is shown. In some embodiments, the laminated glass structure (e.g., Figure 3B The components are manufactured separately in the process of the structure 331). The component 301 includes a first laminated glass component 302 and a second laminated component 304. Figure 2A As with components 202 and 204 , these components may be manufactured separately and then joined to form the final laminated glass structure.

[0100] Assembly 302 includes a tempered first glass layer 305 and a partial electrochromic device 311 disposed on a surface of tempered glass layer 305. Partial electrochromic device 311 may include one or more layers of an electrochromic device.

[0101] Component 304 may be a reflection of component 302, but has different components of the electrochromic device. In the depicted embodiment, component 304 includes a tempered second glass layer 315 and a partial electrochromic device 321, which may include one or more layers of the electrochromic device.

[0102] Partial electrochromic devices 311 and 321 include layers that form different and complementary parts of a complete electrochromic device. For example, partial device 311 can be an electrochromic layer (sometimes implemented using a cathodically coloring electrochromic material), and partial device 321 can be a counter electrode (optionally implemented using an anodically coloring electrochromic material). The partial device may additionally contain layers used in electrochromic devices, such as transparent conductive layers, ion conductive layers, etc.

[0103] Figure 3B A laminated glass structure 331 is shown having a fully fabricated electrochromic device 330 formed from partial electrochromic devices 311 and 321. A laminating adhesive 332 is used to bond partial devices 311 and 321 together. Adhesive 332 can act as both a binder and an ion conductor (electrolyte) for device 330. Adhesive 332 can be applied between partial devices as a polymer sheet, laminated as a liquid resin, etc. Adhesive 332 can have optical properties to complement the optical properties of the optical device.

[0104] In some examples, partial electrochromic device 311 includes an electrochromic cathode layer (e.g., tungsten oxide) on a tempered first glass layer 305. In some embodiments, partial electrochromic device 321 includes an electrochromic anode layer (e.g., nickel tungsten oxide) on a tempered second glass layer 315. In some embodiments, fully fabricated electrochromic device 330 includes an organic ion-conducting layer between a cathodically coloring electrochromic layer and an anodically coloring electrochromic layer.

[0105] It should be noted that Figure 3B The laminated glass structure 331 shown may be formed by, for example, Figure 3A In addition, although Figure 3B Although not shown, the laminated glass structure having the elements of structure 331 may include one or more additional elements, such as one or more additional glass layers (not shown). Furthermore, in some embodiments, only one of the glass layers 305 and 315 is tempered glass. The other may be, for example, annealed glass.

[0106] Manufacturing method

[0107] Laminated glass structures of the type disclosed herein can be manufactured using any of a variety of methods. In some cases, the methods employ tempering a glass layer while the glass layer is at least partially supported on a cushion of air, such as an air stream. In some embodiments, tempering occurs without the glass layer contacting a solid surface (or with minimal contact). While supported, the glass layer is exposed to tempering conditions, such as heat treatment.

[0108] In some embodiments, a laminated glass structure is produced by tempering a pre-tempered glass layer while supporting the pre-tempered glass layer with a gas, such as air, for example, via multiple air jets. A pre-tempered glass layer is a glass layer that has not yet been fully tempered but can be subjected to a tempering process and converted into a tempered glass layer. Tempering involves exposing the pre-tempered glass layer to tempering conditions that convert the pre-tempered glass layer into a tempered glass layer. The resulting tempered glass layer may have no or minimal surface undulations, as described herein. The resulting tempered glass layer may have no or minimal surface curvature, as described herein.

[0109] To produce a laminated glass structure, the resulting tempered glass layer can be bonded to a second glass layer using the bonding processes described elsewhere herein.

[0110] In some embodiments, the pre-tempered glass layer does not contact a solid surface during tempering and while supported on the plurality of air jets. In some embodiments, the pre-tempered glass layer does not contact a roller during tempering and while supported on the plurality of air jets.

[0111] Typically, the glass layers are supported by gas, such that the gas pressure below the glass is higher than the gas pressure above the glass. In some embodiments, this is achieved by applying gas pressure while the glass is in a horizontal or substantially horizontal orientation, i.e., the applied pressure pushes against the major surfaces of the glass to lift the glass. Gas pressure can also be used to guide the glass through the tempering environment, i.e., a net force is applied to create a flow (e.g., laminar flow) through the glass. Gas pressure can also be used to guide the glass through the tempering environment, or rather, rather than do so, e.g., a force having an associated direction can be applied to the glass before it is fully introduced into the tempering environment, the force being sufficient to carry the glass through the tempering environment.

[0112] The temperature within the tempering environment is consistent with conventional tempering conditions (i.e., heating and quenching protocols), for example, the support gas and gas envelope surrounding the glass may or may not be heated. For example, in one or more heating zones of the furnace, the support gas may be heated by heating elements in said zones and / or independently heated to facilitate thermal uniformity of the heating protocol. In conventional tempering furnaces, the bottom surface of a glass sheet receives a greater heat flux than the top surface. This is because the bottom surface receives additional heat from the rollers. The resulting temperature non-uniformity can cause distortion within the tempered glass. This problem is eliminated or mitigated when a glass sheet is tempered while floating on air jets, as disclosed herein, in various embodiments.

[0113] In a quenching protocol, the supporting gas and gas envelope surrounding the glass may be at ambient temperature, such as room temperature, and / or may be cooled to help quench the hot glass, thereby forming tensile and compressive regions of the tempered glass.

[0114] Because the hot and cold gases have different densities, the pressure of the incoming gas used to form the support gas and gas envelope (i.e., to support and / or transport the glass through the tempering environment) can be varied to accommodate the density variations and uniformly support the glass through the tempering environment. This may require different manifolds and / or injection, but this is well within the skill of the skilled artisan.

[0115] In some cases, during tempering, the pre-tempered glass layer floats substantially horizontally on the air generated using the plurality of air jets. In some embodiments, during tempering, the pre-tempered glass layer floats on the air generated using the plurality of air jets at an angle of inclination of no greater than about 60 degrees (or no greater than about 20 degrees) from a horizontal plane. In some embodiments, the pre-tempered glass layer floats at an angle of inclination of no greater than about 10 degrees, or no greater than about 5 degrees, or no greater than about 2 degrees.

[0116] In some embodiments, the air jet generates an air flow at an angle or within a range of angles that generates a force that pushes the pre-tempered glass layer along a path in the tempering furnace where tempering conditions are applied.

[0117] In some embodiments, the tempering furnace includes one or more guardrails that keep the pre-tempered glass layer within the path of the tempering furnace. As examples, such guardrails may include rollers or immovable rods or tracks, where the guardrails only touch the edges of the glass as it passes through the tempering environment.

[0118] In certain embodiments, exposing the pre-tempered glass layer to tempering conditions comprises heating the pre-tempered glass with heat emitted by one or more heating plates while supporting the pre-tempered glass above the plurality of air jets. In some embodiments, the one or more heating plates include at least one heating plate positioned substantially below the pre-tempered glass.

[0119] The manufacturing methods disclosed herein can include bonding a tempered glass layer having no or very little undulation or curvature to a second glass layer. Bonding can be performed by applying an adhesive material between the two glass layers and pressing those layers together.

[0120] The manufacturing methods disclosed herein can include manufacturing an electrochromic device on at least one glass surface, such as one of the surfaces of the tempered first glass layer and / or one of the surfaces of the second glass layer.

[0121] In some examples, such manufacturing methods include forming an electrochromic device on a surface of a second glass layer opposite the tempered first glass layer. The second glass layer can be tempered or untempered. For example, the second glass layer can be an annealed glass layer.

[0122] In some examples, such a manufacturing method includes forming a first portion of an electrochromic device on a surface of a second glass layer opposite the tempered first glass layer; forming a second portion of the electrochromic device on a surface of a fourth glass layer opposite the tempered third glass layer; and contacting the first portion of the electrochromic device with the second portion of the electrochromic device. Contacting the first and second portions of the electrochromic device provides a complete electrochromic stack, including an electrochromic layer and a counter electrode layer. In some embodiments, the second glass layer is an annealed glass layer, the fourth glass layer is an annealed glass layer, or both the second and fourth glass layers are annealed glass layers.

[0123] The laminated glass structures disclosed herein can be provided as part of an insulating glass unit (IGU). In some embodiments, a manufacturing method includes assembling the laminated glass structures disclosed herein, a mating sheet, and a spacer in a manner that forms a sealed volume between the laminated glass structure and the mating sheet. The sealed volume is typically filled with an inert gas to impart insulating properties.

[0124] Figure 4 is an exemplary flow chart illustrating certain processes 401 for manufacturing a laminated glass structure. As shown, the process begins at operation 403, in which a pre-tempered glass sheet is provided to a tempering apparatus. Next, at operation 405, the pre-tempered glass sheet is tempered in the tempering apparatus. Thereafter, at operation 407, the resulting tempered glass sheet is optionally processed to apply one or more optical effects or features, such as all or part of an optically switchable device, an anti-reflective layer, an anti-iridescence layer, a diffusion barrier, a passive tinting or coloring device, or the like. Next, at operation 409, the tempered glass sheet is assembled with another glass sheet to form a laminated glass structure. In some embodiments, the resulting laminated glass structure is assembled into an insulating glass unit, a framed window, or other window structure. See operation 411.

[0125] In some embodiments, before providing the pre-tempered glass sheet to the tempering furnace, the sheet is cleaned to remove any particles that may be present on the sheet surface. Particles present before tempering will be baked into the sheet; these particles cannot be removed by post-tempering washing. Pre-tempering cleaning can be performed using any of a variety of techniques, such as washing with a liquid including hot water, a surfactant (e.g., a detergent), and / or an alkaline solution (e.g., potassium hydroxide). Other examples of cleaning techniques include mechanical dry brush cleaning, plasma etching, high-pressure air nozzle cleaning, and CO2 cleaning.

[0126] In some embodiments, the tempering process is performed in an environment that uses filtered air. An example of such an environment is a clean room. The air reaching the glass sheet can be filtered regardless of its source, for example, whether or not it is recirculated from a location within the tempering environment.

[0127] Manufacturing equipment

[0128] Equipment for producing tempered glass sheets without significant roller wave and / or bow can take various forms. To reduce roller wave, the equipment can include a furnace that exposes the pre-tempered glass sheet to tempering conditions without causing the glass sheet to contact rollers. In some embodiments, the furnace uses air to support and / or convey the pre-tempered glass sheet during tempering. As a result, uniform pressure can be applied across the major surfaces of the glass sheet, and roller wave, bow, or other distortions can be minimal or absent.

[0129] Tempered glass is conventionally manufactured by heating a pre-tempered glass sheet to a temperature well above its transition temperature, approximately 564°C (1,047°F), to approximately 620°C (1,148°F), but typically not below approximately 600°C. The same is true for heat-strengthened glass, but the cooling cycles for tempering and strengthening are different. Heat-strengthened glass is typically 2 to 4 times stronger than annealed glass of the same thickness and configuration, while tempered glass is typically 2 to 3 times stronger than heat-strengthened glass. As an example, according to ASTM C1048, heat-strengthened glass typically achieves a residual surface compressive stress of approximately 3,500 to 7,500 psi for 6 mm glass. 6 mm thick tempered glass must have a minimum surface compressive stress of 10,000 psi or an edge compressive stress of not less than 9,700 psi, but to be considered safety glass, the surface compressive stress should exceed 15,000 psi.

[0130] In certain embodiments, the "working temperature" for thermal strengthening or tempering is about 600 to 640°C, or about 610 to 630°C, or about 615 to 625°C, or about 619 to 621°C, as exemplary working temperatures.

[0131] In some embodiments, the furnace utilizes an air flotation surface, which may take the form of or be constructed similarly to an air flotation table that uses a plenum or manifold to deliver air or other gas, such as an inert gas, through holes to create air "jets" that support the glass substrate above a surface, such as the table surface. Thus, "air jet" or "air stream" may refer to a flow of air or other gas generated by a physical structure, such as holes, through which air or other gas passes. Thus, "a plurality of air jets" may refer to one or more such holes, typically but not necessarily, through a surface, such as a table, through which air or other gas passes to support the substrate, or to a corresponding air stream ejected from a physical device.

[0132] In the case of the tempering furnaces described herein, the major working surfaces of the glass sheet (typically the two largest parallel planes of the glass sheet) are exposed to such air jets as the glass substrate is heated and quenched during the tempering process. In certain embodiments, the jets simply support the glass sheet, preventing it from contacting underlying surfaces or potentially anything other than the gas while passing through the furnace. For example, a roller system supporting the glass sheet at the entrance to the furnace may also transport the glass sheet into the furnace. The roller system imparts momentum to the glass sheet sufficient to carry it through the furnace while it is supported by the air jets. In some embodiments, the air jets are angled to generate an airflow sufficient to move the glass sheet through the furnace. This may include air jets on one or both of the major working surfaces of the glass sheet. In some embodiments, the glass sheet is moved through the furnace using a combination of the momentum of the glass sheet entering the furnace and the angled air jets.

[0133] In some embodiments, the tempering furnace is tilted from the horizontal, from the end where the glass enters the furnace to the end where the glass sheet exits the furnace, so that gravity can carry the glass sheet through the furnace. A combination of the aforementioned moving components can be used to move the glass sheet through the furnace.

[0134] As the glass moves through the tempering furnace, the edges of the glass sheet are not touched. In one embodiment, the glass sheet is introduced into the furnace with appropriate momentum and alignment so that it passes through the furnace supported only by the multiple air jets. In one embodiment, the glass sheet is introduced into the furnace, gravity pulls it through the furnace, and the glass sheet is supported and aligned only by the multiple air jets so that the glass sheet does not contact any solid surfaces. In certain embodiments, the air jets are used to provide a force on the edges of the glass sheet to push or guide the glass sheet through the furnace without causing it to contact any solid surfaces. In certain embodiments, the air jets that strike the edges of the glass sheet can be angled to provide not only guidance but also to apply lateral force to move the glass through the furnace.

[0135] Figure 5-8B Several examples of how glass sheets can be supported and / or conveyed in a tempering environment, such as a tempering furnace, are shown.A tempering environment can include heating and cooling zones.

[0136] Figure 5A glass sheet 503 is shown supported against gravity by air jets, which provide a first pressure 505 acting on the lower major surface of the glass sheet. Through environmental conditions or other means, the upper major surface of the glass sheet 503 is subjected to a second pressure 511. During tempering, the first pressure 505 is greater than the second pressure 511. In this way, the glass sheet 503 is supported against the gas as it passes through the tempering environment. It should be noted that the pressures 505 and 511 are oriented generally perpendicular to the upper and lower major surfaces of the glass sheet 503. The glass sheet 503 passes through the tempering environment using momentum applied before and / or during entry into the tempering environment. The glass sheet does not need to contact anything other than the gas as it passes through. However, in some embodiments, "guardrails" or "bumpers" may be present. These devices require only light contact with the edges to guide the glass sheet through.

[0137] Figure 6 A glass sheet 603 is shown, which is similar to Figure 5 The sheet is supported against gravity by air jets that provide a first pressure 605 acting on the lower major surface of the glass sheet. And the upper major surface of the glass sheet 603 is subjected to a second pressure 611. Figure 5 As in the case of , during tempering, the first pressure 605 is greater than the second pressure 611, and therefore, the glass sheet 603 is supported on the gas while passing through the tempering environment. Figure 5 Unlike the situation in FIG, the direction of pressure 605 is not substantially perpendicular to the upper and lower major surfaces of glass sheet 603. In fact, the airflow on the upper major surface of glass sheet 603 has a direction that can push the glass through its force vector. In this example, the airflow on the top of the glass pushes the glass through the tempering environment. Such an embodiment can establish laminar flow across the working surface of the glass. In some embodiments, pressure 611 can also have a non-vertical direction, and therefore, it can also help to transport the glass sheet through the tempering environment. Figure 5 As in the case of a tempered environment, the glass piece 603 may pass through the tempered environment without touching anything other than the gas as it passes through, or it may only touch the "guardrail" or "bumper".

[0138] Figure 7 Shown Figure 5Implementation of an embodiment of an embodiment of the present invention. As shown, the tempering system includes gas manifolds 713 and 715, which provide uniform gas pressure through appropriately spaced and sized holes. Manifolds 713 and 715 can also provide uniform heating. These manifolds can be made of metal, ceramic, or other materials that can be heated uniformly from behind (for example, the manifold is between the glass sheet and the heater). The manifold and gas temperatures can be the same or substantially the same. The manifolds have sufficient thermal mass so that they are not cooled to any significant extent by the incoming glass (in this example, glass sheet 703) (thus being a stable heat source) and can handle high production volumes of glass. The air jet from manifold 713 provides pressure 705 on the upper surface of sheet 703, and the air jet from manifold 715 provides pressure 711 on the lower surface of sheet 703.

[0139] In some embodiments, a glass sheet is tempered by passing through the heating and quenching zones of a tempering furnace in a single pass. For example, a pre-tempered glass sheet may enter the tempering furnace while being imparted with momentum prior to entering the furnace. The furnace's heating zone is sufficiently long to allow the glass sheet to reach a uniform temperature before entering the quenching zone. In some cases, the heating zones have different temperatures along the path followed by the glass sheet. For example, the furnace may include a relatively hot upstream zone configured to quickly bring the glass sheet to the desired temperature, and a relatively cool downstream zone configured to stabilize the glass sheet to a uniform final temperature suitable for tempering. Regardless of the number of heating zones used, the glass sheet may be supported by an airbed that maintains uniform pressure on the glass sheet. In many embodiments, the heated glass sheet enters the quenching zone on airbed supports. The quenching zone may also be gas-supported.

[0140] In some embodiments, the tempering environment uses, for example Figure 8A - A rastering mechanism as depicted in FIG. Such a mechanism can be configured to push a floating glass sheet back and forth within a single, relatively short heating zone until the sheet reaches the desired temperature. After reaching the desired temperature, a mechanism (e.g., one of the rastering mechanisms) provides a final push to float the glass downstream into one or more quenching zones, which also support the glass sheet via gas.

[0141] Figure 8A -B shows an example of a tempering environment 801 that allows a glass sheet 803 to be moved back and forth within the environment. This back and forth movement is sometimes called rastering and is commonly used in glass tempering furnaces. The rastering mechanism may include a rotating assembly that pushes the glass upstream or downstream to help distribute the heat of the glass sheet in the heating zone. Figure 8AIn the example depicted in FIG-B, the mechanism may include arms or prongs 821 and 823 that engage the leading or trailing edge of a glass sheet to push it. The rotation may be timed to gently grasp the glass, slowing and stopping its momentum, and then changing its direction without applying deforming forces to the glass sheet. The arms or prongs may rotate about an axis to enter and exit the plane of the glass, thereby engaging the glass sheet. When not engaging the glass sheet, slots or channels in a heating manifold (e.g., heating manifold 815) may accommodate the arms or prongs 821 and 823. Thus, the arms or prongs 821 and 823 can be maintained at the same temperature as the heating environment by nesting in the channels or slots of heating manifold 815. The arms or prongs 821 and 823 may be made of metal for good heat transfer and may be very thin to minimize the physical footprint when touching the glass sheet. Because the glass sheet floats on an airbed, minimal force may be required to move the glass sheet or change its direction. There may be two or more arms or forks to guide the glass sheet in each direction so that the collective force required to stop or start the glass movement is distributed among the multiple arms or forks. The arms or forks may be spring-loaded or spring-loaded to allow for gradual and / or less forceful stopping and starting of the glass sheet.

[0142] The arms or forks may incorporate a mechanism to gradually engage the glass piece in a manner that gradually reduces its momentum, and then change direction to push the glass in the opposite direction, in either case without generating sufficient force to warp or distort the glass.

[0143] Similar to other embodiments disclosed herein, the tempering environment can include manifolds 813 and 815 configured to generate gas jets that apply pressure 811 on the lower major surface of glass sheet 803 and pressure 805 on the upper major surface of glass sheet 803 .

[0144] It should be noted that Figure 5-8B The tempering environment presented in FIG can be used for the heating and / or quenching stages of tempering. One or both of the heating and quenching zones can be used, for example Figure 8A -The rasterization mechanism shown in B.

[0145] In certain embodiments, the tempering environment is configured to achieve quenching by applying different degrees of quenching to different locations within the quenching zone (e.g., the zone near the exit of the tempering furnace). This can be useful when the tempering process simultaneously heats glass sheets of different sizes and / or shapes (e.g., different aspect ratios). Such a collection of glass sheets is sometimes referred to as a mixed-size load. When processing a mixed-size load, larger glass sheets tend to have lower temperatures than smaller glass sheets at the same load. Therefore, with a mixed load, it may be necessary to cool the smaller glass sheets more aggressively.

[0146] When the load contains relatively large glass sheets (e.g., glass sheets having a surface area of ​​at least about 5,000 square inches), it may also be useful to apply different degrees of quenching to different locations within the quenching zone. Large glass sheets sometimes suffer from temperature non-uniformity, with the center of these sheets being cooler than their edges. This is because the edges of the sheet can become overheated due to radiative heat transfer. Selectively cooling the outer regions of large glass sheets can offset this uneven temperature variation from the center to the edge.

[0147] Selective cooling or bed load-dependent recipes can be employed to promote consistent and uniform cooling of the glass undergoing quenching. In some embodiments, the quench zone is configured to generate one or more adjustable air jets that can be ejected through one or more quench nozzles near the exit of the tempering furnace. In some embodiments, the quench nozzles or other air jet sources can be translated within a two-dimensional region within the quench zone. This allows for selectively directing or activating one or more air jets in areas where preferential cooling is desired, such as smaller glass sheets or edge regions of glass sheets under mixed loads, regardless of load type.

[0148] In some embodiments, the quenching zone utilizes multiple adjustable air jets, which may be ejected through multiple quench nozzles. Each adjustable air jet may have its air velocity, flow rate, pressure, and / or temperature controlled to permit varying degrees of quenching at different locations. In some cases, the adjustment may simply involve turning an air jet on or off.

[0149] Because adjustable cooling may need to be adjusted quickly to account for moment-to-moment process variations, the quenching system can employ feedback, such as closed-loop control. In some embodiments, closed-loop control is implemented by imaging (mixed-size loads) and / or pyrometers (temperature non-uniformity).

[0150] Figure 8C An exemplary quenching apparatus 841 is schematically shown, which is configured to achieve quenching in a manner that applies different degrees of quenching to different locations within the apparatus. The apparatus 841 includes a plurality of adjustable quenching nozzles 843 from which air is blown onto the quenching section of the glass. Figure 8C , apparatus 841 is operated in a first mode in which the air jets of each of a plurality of quench nozzles 843 are adjusted to tailor quenching conditions for different sized glass sheets simultaneously undergoing quenching.

[0151] Figure 8CA quench section is shown with two mixed-size sheets in a bed load. These two mixed-size sheets can have different temperatures because, when processing mixed-size loads, the larger glass sheets tend to be cooler than the smaller glass sheets at the same load. Therefore, with mixed loads, the smaller glass sheets may need to be cooled more quickly. In the figure, sheet 845 is a relatively large glass sheet, and sheet 847 is a relatively small glass sheet.

[0152] exist Figure 8C In the quench pattern depicted in FIG, P1 and P2 represent the air pressure intensities from the respective nozzles, with P1 providing higher pressure, and therefore more rapid cooling, to the large glass flakes 845, and P2 providing lower pressure, and therefore less rapid cooling, to the small glass flakes 847. Larger glass flakes typically have lower exit temperatures entering the quench, and therefore will need to be cooled more rapidly to establish a compressive layer on the outer surface of the flakes and tension within them before the glass temperature drops below the temperature at which it transitions to a solid. Therefore, in the depicted embodiment, higher pressure is used for the large glass flakes, while lower pressure is used for the small glass flakes.

[0153] Figure 8D A quenching apparatus 841 is schematically shown operating in different modes, which may be suitable for quenching a large glass sheet (such as the large sheet 849 shown in the figure) that has a non-uniform temperature, with the center being cooler than the edges. Selectively cooling the outer regions of the large glass sheet can offset the non-uniform temperature variation from the center to the edge. Figure 8D In FIG. 8 , some adjustable quench nozzles 843 generate air jets at a higher pressure, P1, while other adjustable quench nozzles 843 generate air jets at a lower pressure, P2. This variation in the pressure of the air jets impacting glass sheet 849 counteracts the uneven temperature of the glass sheet upon entering quench apparatus 841. It should be noted that upon entering the quench apparatus, the center of a large glass sheet is typically at a lower temperature than its edges. Therefore, the central region of the sheet must be cooled rapidly to establish a compressive layer on the sheet's outer surface and tension within it before the central region reaches its temperature at which it transitions to a solid. In contrast, a lower pressure can be used to cool the higher-temperature edges of the sheet.

[0154] EC units and IGUs

[0155] Figure 9, a schematic cross-section of an electrochromic device 900 according to some embodiments is shown. This device can be formed on one or more glass sheets used to form the laminated glass structures described herein. The electrochromic device includes a substrate 902, a conductive layer (CL) 904, an electrochromic layer (EC) 906, an ion-conducting layer (IC) 908, a counter electrode layer (CE) 910, and a conductive layer (CL) 914. Elements 904, 906, 908, 910, and 914 can be collectively referred to as an electrochromic stack 920. In some cases, the ion-conducting layer 908 can be omitted. A voltage source 916 operable to apply an electric potential across the electrochromic stack 920 causes the electrochromic device to transition from, for example, a clear state to a tinted state. In other embodiments, the order of the layers is reversed relative to the substrate. That is, the order of the layers is as follows: substrate, conductive layer, counter electrode layer, ion-conducting layer, electrochromic material layer, conductive layer.

[0156] Electrochromic layer 906 is cathodically toned, while counter electrode layer 910 can be anodically toned or optically passive (sometimes referred to as an "ion storage layer" because ions reside there when the device is not toned). In some embodiments, electrochromic layer 906 comprises tungsten oxide. In some embodiments, counter electrode layer 910 comprises nickel tungsten oxide.

[0157] It should be understood that the reference to the transition between the clear state and the toned state is non-limiting and is merely provided to suggest one example of many examples of electrochromic transitions that may be implemented. Unless otherwise specified herein, whenever a clear-to-toned transition is mentioned, the corresponding apparatus or process encompasses other optical state transitions, such as non-reflective-reflective, transparent-opaque, tinted-colorless, etc. In addition, the term "clear" refers to an optically neutral state, such as colorless, transparent, or translucent. Still further, unless otherwise specified herein, the "hue" or "color" of the electrochromic transition is not limited to any particular wavelength or wavelength range. As will be appreciated by those skilled in the art, the selection of appropriate electrochromic and counter electrode materials determines the associated optical transition.

[0158] In certain embodiments, the electrochromic device reversibly cycles between a clear state and a toned state. In the clear state, an electric potential is applied to electrochromic stack 920 such that available ions in the stack that can place electrochromic material 906 in the toned state remain primarily in counter electrode 910. When the electric potential across the electrochromic stack is reversed, ions are transported across ion-conducting layer 908 to electrochromic material 906 and cause the material to enter the toned state.

[0159] In certain embodiments, all materials making up the electrochromic stack 920 are inorganic, solid (i.e., in the solid state), or both inorganic and solid. Since organic materials tend to degrade over time, inorganic materials provide the advantage of a reliable electrochromic stack that works for a long time. Solid-state materials also provide the advantage of not having sealing and leakage problems, which are typically present with liquid materials. It will be understood that any one or more of the layers in the stack may contain a certain amount of organic material, but in many embodiments, one or more of these layers contain little or no organic matter. The same is true for liquids that may be present in small amounts in one or more layers. It will also be understood that solid-state materials can be deposited or otherwise formed by a process that employs a liquid component (e.g., certain processes employing sol-gel or chemical vapor deposition).

[0160] Reference again Figure 9 Voltage source 916 is typically a low voltage power source (between about 1V and about 20V, depending on the electrochromic device used) and can be configured to operate in conjunction with radiation sensors and other environmental sensors. Voltage source 916 can also be configured to interface with an energy management system, such as a computer system that controls the electrochromic device based on factors such as the time of year, the time of day, and measured environmental conditions. Such an energy management system, combined with large-area electrochromic devices (i.e., electrochromic windows), can significantly reduce energy consumption in buildings.

[0161] Figure 10 An insulating glass unit (IGU) 1020 is depicted having an EC sheet 1000 that may include the laminated glass structures disclosed herein. The EC sheet 1000 comprises an EC device and an associated pair of bus bars 1005 that each energize the device via a transparent conductor. The pair of transparent conductors sandwich the EC material between them so that an electric potential can be applied across the device material. The IGU is manufactured by combining the EC sheet 1000 with spacers 1010 and mating sheets 1015 and appropriate sealants and wiring (not shown) to the bus bars. In some applications, a second set of spacers and mating sheets may be added (e.g., a triple pane IGU). The two mating sheets may be of different types. As Figure 10 As depicted in the lower half of , the IGU can be transparent (left), toned to an intermediate state (center), or fully toned (right).

[0162] Various aspects of the present disclosure relate to integrated glass units comprising at least two lamellae and a hermetically sealed interstitial region between the lamellae. At least one of the lamellae is a laminated glass structure having a tempered glass layer with minimal or no undulation or curvature, as described elsewhere herein. Aside from having such a tempered glass layer, the laminated glass structure can have any configuration.

[0163] Identify modifications to tempering recipes and / or bed load layout configurations

[0164] Many of the techniques described above relate to tools and hardware for tempering thin sheets, such as where the tempered sheet does not touch rollers but is instead moved through various zones of a furnace using a set of air jets. Additionally, techniques are disclosed herein for determining tempering recipe parameters and / or bed load configurations that improve thin sheet tempering (e.g., to minimize sheet bending, minimize distortion, or meet other thin sheet tempering specifications) using existing tools and / or hardware (e.g., tools and / or hardware that include rollers for moving the sheet). For example, techniques are disclosed herein for determining tempering recipe parameters and / or bed load configurations for a batch of thin sheets undergoing tempering based on parameters associated with a previously tempered batch of thin sheets using a machine learning model. However, it should be understood that, in some embodiments, the techniques disclosed below for determining tempering process parameters using a machine learning model can be applied to tools that use air jets to move the sheet through various zones of a furnace, such as by determining changes in air temperature or pressure, the timing of when the air jets are turned on or off, and the like.

[0165] Conventionally, a batch of sheets may be tempered, which may involve heating the sheets to a high temperature (e.g., 600 or 700 degrees Celsius, or similarly high temperatures) and then quenching or rapidly cooling the sheets. The sheets may be heated by moving the sheets through a furnace (as described above) using rollers or air jets (as described above). The sheets may have sheet specifications that are to be achieved after the tempering process. As used herein, sheet specifications may include bow below a target threshold, break weight within target break weight criteria, glass surface stress (gasp) or compression within a target range, and / or visual distortion below a target threshold. Performing the tempering process so that the sheets achieve the target sheet specifications, as described above, can be difficult. Furthermore, in some cases, tempering a first batch of sheets may cause changes in various aspects of the furnace, making it impossible to achieve the target sheet specifications when processing a second batch of sheets using the same tempering process parameters, for example due to residual heat loads on the furnace rollers from processing the previous batch of sheets. The described techniques allow modification of tempering process parameters and / or tempering recipes and / or determination of bed load configurations or layouts that improve the likelihood that the wafer will achieve target wafer specifications.

[0166] In some embodiments, modifications to tempering recipe parameters may be determined and / or a bed load layout configuration may be determined. The tempering recipe parameters and / or bed load layout configuration may be determined based on parameters associated with a first batch of sheets undergoing tempering. For example, the modifications to the recipe parameters and / or bed load layout configuration may be determined by providing parameters associated with the first batch of sheets undergoing tempering to a trained machine learning model, wherein the trained machine learning model is configured to provide as output information indicative of a change in the tempering recipe and / or bed load layout for a subsequent batch of sheets undergoing processing. For example, the parameters associated with the first batch of sheets may include a layout of the first batch of sheets (e.g., the spacing of the sheets relative to each other within the bed load), size and / or dimensional information associated with each sheet in the first batch of sheets, bend information associated with the bend of the sheets in the first batch of sheets after undergoing tempering, distortion data, break weight, surface compression force, or any combination thereof. The trained machine learning model may then generate an output indicating modifications to the tempering recipe and / or bed load layout such that a subsequent batch of sheets processed using the modified recipe and / or determined bed load layout conforms to one or more sheet specifications. Sheet specifications may include criteria related to maximum bending, break weight, distortion, glass surface stress or compression, etc. Modifications to the tempering recipe may include changing the heating profile and / or cooling profile used to perform tempering. In some embodiments, the bed load layout may indicate the relative placement of sheets. For example, the bed load layout may indicate where sheets of a particular size are to be placed relative to sheets of other sizes, e.g., sheet A of a first size is to be placed next to sheet B of a second size, and so on.

[0167] Figure 11 is a flow chart of an exemplary process 1100 for determining tempering recipe parameters and / or bed load layout configuration according to some embodiments. In some embodiments, the blocks of process 1100 may be executed by one or more processors of one or more computing devices. For example, the computing device may be a desktop computer, a tablet computer, a laptop computer, etc. The computing device may be associated with the thin sheet tempering equipment. In some embodiments, the computing device may be local to the thin sheet tempering equipment, or may be remote from the tempering equipment. For example, in some embodiments, one or more computing devices may be cloud devices. In some embodiments, the blocks of process 1100 may be executed as described above. Figure 11 In some embodiments, two or more blocks of process 1100 may be executed substantially in parallel. In some embodiments, one or more blocks of process 1100 may be omitted.

[0168] At 1102, process 1100 may obtain parameters associated with a trained machine learning model, the trained machine learning model being configured to receive input indicating parameters associated with sheet tempering and to output one or more recipes and / or bed load changes for a subsequent batch of sheets to be tempered. The parameters associated with the trained machine learning model may include: weights associated with nodes of the machine learning model, wherein the weights are determined as a result of the training process; and / or the architecture of the machine learning model.

[0169] At 1104, process 100 may obtain parameters associated with a first batch of sheets undergoing tempering. In some embodiments, the parameters associated with the first batch of sheets may include a heating and / or cooling curve specifying temperature and timing information (e.g., the sheets are to be heated in a furnace zone having a specified temperature for a specified duration, the sheets are to be cooled to a specific temperature within a specified duration, etc.). Parameters associated with sheet tempering may include characteristics of the first batch of sheets after the tempering process is performed. For example, the parameters may include sheet bow information (which may be destructively measured on a subset of sheets in the first batch), distortion information indicating the magnitude of roller waves on the sheets (e.g., measured in millidiopters), glass surface stress measurements indicating surface compressive forces, break weight, or any combination thereof. Parameters associated with the first batch of sheets may include the layout of the first batch of sheets, such as within the furnace or within a specific furnace zone and / or relative to the furnace rollers. For example, the layout may indicate the relative placement of the sheets relative to one another, such as sheet A having a specific size being in a specific position relative to sheet B having a specific size. In some embodiments, the parameters associated with the first batch of lamellae may include pyrometer data and / or data derived from the pyrometer data. For example, various image processing algorithms (e.g., edge detection, object detection, etc.) may be applied to the pyrometer data to determine lamellae layout, the average and / or standard deviation of temperatures across the lamellae, and the like.

[0170] Process 1100 can use a trained machine learning model to determine one or more modifications to: a current recipe for processing a first batch of slices; and / or a bed load configuration for processing a second batch of slices, wherein the one or more modifications are used to process the second batch of slices. The one or more modifications to the current recipe can include changing a heating profile and / or cooling profile associated with the tempering recipe. For example, the one or more modifications can include changing the temperature of one or more heating and / or cooling zones. As another example, the one or more modifications can include changing the duration that the slices remain in each heating and / or cooling zone.

[0171] In some embodiments, the bed loading configuration for the second batch of sheets may take into account deficiencies in the first batch of sheets with respect to the characteristics of the first batch of sheets after the tempering process, such as deficiencies in bowing, glass surface stress, visual distortion, break weight, etc. For example, the bed loading configuration for the second batch of sheets may be a bed loading configuration determined by a trained machine learning model that is more likely to enable the second batch of sheets to achieve the sheet tempering specifications. In some embodiments, the bed loading configuration for the second batch of sheets may take into account the thermal load or thermal signature characteristics of the furnace rollers resulting from processing the first batch of sheets. For example, where the first batch of sheets includes large sheets, there may be cold spots on the rollers due to the processing of the large sheets in the first batch of sheets. Therefore, the bed loading configuration for the second batch of sheets may indicate that sheets of a certain size, such as sheets having an area less than a predetermined threshold, should be placed in a cold zone.

[0172] A second batch of sheets can then be processed using a modified tempering recipe and / or bed load configuration determined using the output of the trained machine learning model. Due to the modified tempering recipe and / or bed load configuration, the second batch of sheets can be tempered in a manner such that sheets in the second batch are likely to meet tempering specifications, such as a sheet bow metric below a predetermined threshold, a visual distortion metric below a predetermined threshold, a glass surface stress metric meeting a predetermined criterion, and / or a break weight meeting a predetermined criterion.

[0173] It should be noted that in the case of a furnace without rollers, the machine learning model can determine tempering process modifications that include modifications to the air flow of the multiple air jets used to move a batch of sheets through various zones of the furnace. For example, the modifications can include modifications to the temperature of the air from one or more air jets, modifications to the pressure of the air from one or more air jets, and / or whether to disable or turn off one or more air jets.

[0174] As described above, in some embodiments, a trained machine learning model may be used to determine tempering recipe parameters and / or bed load layout configurations. The machine learning model may be any suitable type of model. For example, the machine learning model may be a supervised machine learning model, such as a regression model (e.g., a linear regression model), a random forest model, a neural network, etc. For some types of models, feature selection may be performed before initializing and / or training the machine learning model to determine which parameters (e.g., sheet bending metrics, temperature measurements, glass surface stress measurements, compression force measurements, etc.) to use to train the model. Feature selection may be performed using principal component analysis (PCA), linear discriminant analysis (LDA), etc. For some types of models, feature selection may not be performed explicitly. For example, using a random forest model ensemble, each model may utilize a different combination of parameters, with each model providing an output prediction. Continuing with this example, the aggregated output of the different random forest models in the random forest model ensemble may be used to determine which parameter or parameter combination to use for the trained machine learning model.

[0175] In some embodiments, a reinforcement model may be used in addition to or as an alternative to using a supervised machine learning model. When a reinforcement model is used, the model may provide outputs, such as recipe changes or bed load configuration layouts. A training data set may be used to determine the consequences of utilizing the outputs to determine whether to reward or penalize the model based on the outputs (e.g., whether the target sheet tempering specification can be achieved using the output recipe parameters and / or bed load layout, the extent to which the output recipe parameters and / or bed load layout result in deviation from the sheet tempering specification), and the extent to which the model should be rewarded or penalized. In this way, the reinforcement model may be trained to generate output tempering recipe parameters and / or bed load layouts that are generally rewarded and are therefore more likely to achieve tempered sheets that meet the specifications. By training the reinforcement learning model, an optimal (or near-optimal) solution may be determined based on the version of the model that receives the maximum reward.

[0176] Whether supervised training or reinforcement learning is used, a training set can be used to train the model. For supervised training, the training set can include sheet parameters paired with ground truth decisions that the model is to be trained to generate. For example, the sheet parameters can include any combination of: bed load layout or position of a particular sheet, sheet dimensions (e.g., length, width, area, thickness, etc.), temperature information, sheet bending information indicating a sheet bending metric after tempering, a sheet distortion metric indicating visual distortion after tempering, a glass surface stress metric indicating glass surface stress after tempering, and / or a break weight metric indicating break weight after tempering. The ground truth paired with a given training sample can include one or more modifications to the tempering process and / or bed load layout that are to be implemented for tempering a subsequent batch of sheets in response to tempering a first batch of sheets associated with the sheet parameters of the training sample. In other words, each training sample may include parameters associated with a first batch of processed wafers (which may include information indicating the results of the tempering process) and a paired ground truth decision indicating how to modify the tempering process or bed load layout for a subsequent batch of wafers. The ground truth decision may include changing the heating and / or cooling curves, and / or the bed load layout for the second batch of wafers.

[0177] In the case of reinforcement learning, the dataset may indicate the tempering process parameters and / or bed layout used to process a given batch of sheets, as well as the sheet tempering parameters resulting from tempering the batch of sheets using the tempering process parameters and / or bed layout. The tempering parameters may include bending information, glass surface stress information, break weight information, visual distortion information, or any combination thereof. By updating the reinforcement model using metrics indicative of the results of the tempering process, the model can be trained to generate more optimized tempering process parameters and bed layouts that are more likely to produce sheets within tempering specifications.

[0178] In some embodiments, the machine learning model may additionally or alternatively take as input temperature information indicating, for example, the temperature across a sheet or at different portions of a sheet. For example, the temperature information may indicate the average temperature of the sheet, the deviation across the sheet (e.g., the standard deviation of the temperature across the sheet and / or the variance of the temperature across the sheet), etc. In some embodiments, the temperature information may be derived from pyrometer data. The pyrometer data may be represented as image data. In some embodiments, image processing techniques may be applied to the pyrometer image data to derive the temperature data. For example, the image processing techniques may include performing edge detection to identify sheet edges, thereby determining pixels associated with a given sheet. Based on the pyrometer heat map values ​​and the determined pixel locations, temperature information associated with each sheet may be determined.

[0179] Figure 12is a flow chart of an exemplary process 1200 for training a machine learning model in accordance with some embodiments. The machine learning model may be a supervised machine learning model that is trained to take as input parameters associated with a first batch of slices undergoing tempering and to generate as output modifications to the tempering recipe and / or bed load configuration for a subsequent batch of slices. In some embodiments, the blocks of process 1200 may be executed by one or more processors of one or more computing devices, such as a server device, a desktop computer, a laptop computer, etc. In some embodiments, the computing device may be a cloud device. In some embodiments, the blocks of process 1200 may be executed as described in the accompanying Figure 12 In some embodiments, two or more blocks of process 1200 may be executed substantially in parallel. In some embodiments, one or more blocks of process 1200 may be omitted.

[0180] Process 1200 may begin at 1202 by initializing a machine learning model configured to receive input indicating parameters associated with tempering a thin sheet and output one or more recipes and / or bed load changes for a subsequent batch of thin sheets to be tempered. For example, initializing the machine learning model may include setting weights of the machine learning model to initial values. The machine learning model may be a linear regression model, a neural network model, a random forest model, a decision tree, or the like.

[0181] It should be noted that various pre-training steps may be taken before initializing the machine learning model. For example, in some embodiments, the data to be used as part of the training set may be cleaned, for example, to remove outlier data. As another example, in some embodiments, PCA, LDA, etc. may be used to perform feature selection, for example, to select parameters to be used as input to the machine learning model.

[0182] At 1204, process 1200 may utilize a machine learning model to generate outputs including recipe changes and / or bed load layouts, given inputs of parameters associated with tempering a batch of sheets. In other words, the machine learning model may utilize parameters associated with tempering a batch of sheets as inputs and generate one or more recipe changes and / or bed load layouts as outputs for use in conjunction with tempering a subsequent second batch of sheets. As described above, the input parameters may include information regarding the dimensions of the first batch layout, the layout of the sheets within the first batch (e.g., the relative placement of the sheets relative to one another), metrics indicating the results of the tempering process for the first batch of sheets (e.g., a bow metric, a visual distortion metric, a break weight metric, a glass surface stress metric, a compression metric, etc.), temperature information indicating the temperature at various locations on or across the sheets at different points in the tempering process, or any combination thereof. The outputs may include one or more recipe changes, such as modifying a heating zone or cooling zone to have a different temperature than that used to process the first batch of sheets, maintaining the sheets in a particular heating zone or cooling zone for a different duration than that used for the first batch of sheets, etc. As another example, the output may include a bed load layout for a subsequent second batch of sheets, such as sheets of a certain size to be placed in a certain area of ​​a set of rollers used to move the sheets through the furnace, two sheets of certain relative sizes (e.g., a large sheet and a small sheet) to be placed adjacent to each other, or any other placement information.

[0183] At 1206, process 1200 may update the weights of the machine learning model based on the difference between the predicted recipe and / or bed load change and the ground truth recipe and / or bed load change indicated in the training data. For example, if the ground truth data indicates that the temperature of a heated zone will be increased by 100 degrees and the model output indicates that the heated zone will be increased by 50 degrees, the weights may be updated based on the error between the model output and the ground truth output, e.g., a difference of 50 degrees. The error in the bed load layout may be determined based on the proximity of different sized sheets relative to the ground truth layout, the distance between the center of a given sheet in the predicted layout and the center of the sheet in the ground truth layout, etc. In some embodiments, the error may be provided to a cost function, and the model weights may be updated based on the cost function. For example, the weights may be updated based on the minimum of the cost function (e.g., the location where the error is minimized). The weight update may be based on moving toward the minimum in the direction of steepest descent, e.g., using gradient descent. In some cases, backpropagation may be used to calculate the gradient used to update the weights in the direction of steepest descent. Any suitable learning rate can be utilized when updating the weights, and the learning rate can be tuned using hyperparameter tuning.

[0184] At 1208, process 1200 can determine whether to continue training the model. For example, process 1200 can determine whether more than a predetermined number of training iterations have been performed, or whether the update of the weights relative to the previous weight values ​​is less than a predetermined threshold, and in response, can determine that training is complete.

[0185] If at 1208, process 1200 determines that model training should continue ("yes" at 1208), process 1200 can loop back to block 1204 and can continue training the model. Conversely, if at 1208, process 1200 determines that training is complete ("no" at 1208), process 1200 can end.

[0186] The parameters (e.g., weights) of the trained model can then be used to determine recipe changes and / or bed load layouts, e.g. Figure 11 Shown and combined with the above Figure 11 Depicted.

[0187] It should be noted that although Figure 12 While depicted, a machine learning model is trained based on ground truth data indicating the target tempering process changes and / or target bed load layouts that the model is trained to predict, in some embodiments, the model may alternatively be trained to predict sheet properties for a tempered sheet subjected to a tempering process with specific process parameters and / or a specific bed load layout. For example, the model may be trained to predict that a sheet tempered using a specific tempering process may have a predicted curvature, a predicted break weight, a predicted glass surface stress or compression force, and / or a predicted distortion. Continuing with this example, modifications to the tempering process and / or bed load layout may be determined based on the predicted sheet properties, for example, to determine modifications and / or bed load layouts that are more likely to bring the predicted sheet properties within target specifications. As a more specific example, if the model predicts that the curvature of the sheet will exceed a curvature threshold, modifications to the tempering process and / or bed load layout that are likely to bring the sheet curvature below the threshold may be determined. In some embodiments, modifications to the tempering process and / or bed load layout may be determined in an iterative process. For example, a machine learning model can predict, for tempering process parameter A (e.g., for a specific layout and / or heating / cooling profile), a sheet property B (e.g., predicted bow, predicted break weight, predicted distortion, predicted glass surface stress or compression, etc.) caused by process parameter A. Continuing with this example, in response to determining that sheet property B causes the sheet to be out of specification, process parameter A' can be determined, and the model can be used to determine sheet property B' resulting from process parameter A'. Sheet property B' may be closer to the target specification than sheet property B; however, in response to determining that sheet property B' also exceeds the target specification, process parameter A' can be determined. This process can be iteratively repeated until the predicted sheet property is determined to be within specification.

[0188] In some embodiments, information associated with the thermal loading of a set of rollers used to temper a first batch of sheets can be used to determine a change in the tempering recipe and / or bed load layout to be used for processing a subsequent second batch of sheets. For example, in some embodiments, information associated with the thermal loading of a set of rollers used to temper a first batch of sheets can indicate that during the tempering process, specific areas of the rollers were cooler due to placement of relatively larger sheets from the first batch of sheets, or conversely, different areas of the rollers were hotter due to placement of relatively smaller sheets from the first batch of sheets. Continuing with this example, in some embodiments, the bed load layout for the subsequent second batch of sheets can include placing relatively smaller sheets in a cooler area of ​​the rollers that previously held larger sheets from the first batch of sheets, and / or can include placing relatively larger sheets in a hotter area of ​​the rollers that previously held smaller sheets from the first batch of sheets. Additionally or alternatively, in some embodiments, the recipe change can include altering a heating profile or a cooling profile, such as described above.

[0189] Figure 13 is a flow chart of an exemplary process 1300 for modifying a tempering process and / or bed load layout based on the thermal load of a furnace roller, according to some embodiments. In some embodiments, the blocks of process 1300 may be executed by one or more processors of one or more computing devices. The one or more computing devices may be located locally at the furnace or remotely (e.g., in the cloud). In some embodiments, the blocks of process 1300 may be executed as described in the accompanying Figure 13 In some embodiments, two or more blocks of process 1300 may be executed substantially in parallel. In some embodiments, one or more blocks of process 1300 may be omitted.

[0190] Process 1300 may begin at 1302 by obtaining information associated with the thermal load of a set of rollers used to process a first batch of sheets. The thermal load information may include heating information and / or temperature information associated with rollers in the set of rollers. The thermal load information may be derived based on thermocouple data. For example, the thermocouple data may be used to determine whether a given region of the set of rollers is cooler or hotter than another region of the set of rollers.

[0191] At 1304, process 1300 may determine one or more of the following based on the thermal load: a layout for a second batch of sheets to be processed using the set of rollers, or a modification to the recipe for processing the second batch of sheets. As described above, the layout may indicate that sheets of a given size will be positioned in a specific area due to the thermal load. For example, smaller sheets may be placed in a cooler area of ​​the set of rollers, and larger sheets may be placed in a hotter area of ​​the set of rollers. In some embodiments, the layout may indicate the relative positions of the sheets in the second batch relative to each other. In some embodiments, the layout may indicate the spacing between two sheets in the batch, for example, whether the two sheets are to be spaced a given distance apart from each other. The layout information may be determined based on known dimensional information for the sheets in the second batch, such as a known length and / or width of the sheets, a known aspect ratio, etc. In some embodiments, the modification to the recipe may include changing the heating curve and / or cooling curve, as described above.

[0192] At 1306 , process 1300 can process a second batch of sheets using the determined layout and / or modified recipe.

[0193] Figure 14 A schematic diagram of an exemplary system for modifying a tempering process and / or determining a bed load layout according to some embodiments is depicted. As shown, a sheet tempering control system 1402 can be configured to determine a recipe modification and / or bed load layout. For example, the sheet tempering control system 1402 can be configured to utilize data associated with the tempering of a first batch of sheets to determine a recipe modification and / or bed load layout configuration to be used for a second batch of sheets, e.g., to increase the likelihood that the second batch of sheets will meet certain sheet specifications (e.g., with respect to bow, visual distortion, break weight, glass surface stress, etc.) after tempering. As described above in conjunction with Figure 11 and 12 As described, in some embodiments, the sheet tempering control system 1402 may use a trained machine learning model to determine recipe modifications and / or bed load layouts. Additionally or alternatively, as Figure 13 Shown and combined with the above Figure 13 As depicted, in some embodiments, a sheet tempering control system may determine recipe modifications and / or bed load placement based on the residual heat load on the furnace rollers resulting from processing the first batch of sheets.

[0194] like Figure 14 As shown, the sheet tempering control system 1402 can receive various data. For example, the sheet tempering control system 1402 can receive furnace load data 1404. The furnace load data 1404 can indicate characteristics of sheets in a first batch of sheets undergoing the tempering process, such as size or dimension information of the first batch of sheets, thickness information, and the layout of the sheets in the first batch of sheets within the furnace and / or on the rollers.

[0195] The sheet tempering control system 1402 may receive heating and / or temperature data 1406. In some embodiments, the heating and / or temperature data 1406 may include pyrometer data, which may be image data. The pyrometer data may be used to determine temperature information at various locations on a sheet in a first batch of sheets in the furnace, the average temperature of a given sheet, the standard deviation or variance of the temperature across the sheet, and the like. In some embodiments, the heating and / or temperature data 1406 may include thermocouple data, which indicates temperature information at various locations within the furnace or associated with a region of a set of rollers.

[0196] The sheet tempering control system 1402 may receive quench data 1408. Quench data 1408 may be obtained after the first batch of sheets moves to the quenching zone, where the sheets undergo rapid cooling after being heated in one or more zones of the furnace. In some embodiments, quench data 1408 may include data obtained after the quenching process is complete. For example, quench data 1408 may include visual distortion measurements, such as peak-to-valley measurements indicating waves or undulations in the glass layer. The visual distortion measurements may be Osprey measurements.

[0197] The sheet tempering control system 1402 may receive furnace unload data 1410. The furnace unload data 1410 may include various measurements, such as break weight, glass surface stress, and / or sheet bow metrics. Note that in some embodiments, some of the furnace unload data 1410 may be destructive and therefore may only be measured for a subset of the first batch of sheets.

[0198] During and after processing the first batch of sheets, data 1404 to 1410 can be provided to the sheet tempering control system 1402. Based on the data 1404 to 1410, the sheet tempering control system 1402 can determine how to adjust the tempering process when performing the tempering process with the subsequent second batch of sheets. The adjustments can take into account defects observed in the first batch of sheets that were caused by the tempering process used for the first batch of sheets (e.g., defects such as excessive bow, defects in break weight and / or glass surface stress, visual distortion exceeding a certain distortion threshold, etc.), and / or compensate for the thermal load caused by the sheets in the first batch of sheets.

[0199] It should be noted that in the case of a furnace without rollers, the sheet tempering control system 1402 can determine tempering process modifications that include modifications to the air flow of the multiple air jets used to move a batch of sheets through various zones of the furnace. For example, the modifications can include modifications to the temperature of the air from one or more air jets, modifications to the pressure of the air from one or more air jets, and / or whether to disable or turn off one or more air jets.

[0200] Other Examples and Conclusions

[0201] Although omitted for brevity, embodiments of the systems and / or methods may include every combination and permutation of the various system components and the various method processes, wherein one or more instances of the methods and / or processes described herein may be performed asynchronously (e.g., sequentially), simultaneously (e.g., in parallel), or in any other suitable order by and / or using one or more instances of the systems, elements, and / or entities described herein.

[0202] Those skilled in the art will recognize from the foregoing detailed description, the drawings and the claims that modifications and changes may be made to the preferred embodiments of the present invention without departing from the scope of the invention as defined in the appended claims.

[0203] Example embodiment:

[0204] Embodiment 1. A laminated glass structure comprising: a first heat-treated glass layer having no undulation with a peak-to-valley distance of about 0.2 mm or greater; and a second glass layer adhesively bonded to the heat-treated glass layer, wherein the laminated glass structure does not exhibit a lens effect caused by the undulation.

[0205] Embodiment 2. The laminated glass structure of embodiment 1, further comprising an optically switchable device.

[0206] Embodiment 3. The laminated glass structure of Embodiment 2, wherein the optically switchable device is an electrochromic device.

[0207] Embodiment 4. The laminated glass structure of any preceding embodiment, further comprising an adhesive layer between the heat-treated glass layer and the glass layer.

[0208] Embodiment 5. The laminated glass structure of embodiment 4, wherein the adhesive layer comprises a resin.

[0209] Embodiment 6. The laminated glass structure according to embodiment 5, wherein the resin comprises polyvinyl butyral (PVB), ionoplast interlayer (SentryGlas, SBP), or a combination thereof.

[0210] Embodiment 7. The laminated glass structure of any preceding embodiment, further comprising an electrochromic device disposed on a surface of the second glass layer opposite the heat-treated first glass layer, and wherein the second glass layer is an annealed glass layer.

[0211] Embodiment 8. The laminated glass structure of any of Embodiments 1 to 6, further comprising: an electrochromic device disposed on a surface of the second glass layer opposite the heat-treated first glass layer, wherein the second glass layer is an annealed glass layer; a heat-treated third glass layer; and a fourth glass layer adhesively bonded to the heat-treated third glass layer.

[0212] Embodiment 9. The laminated glass structure of embodiment 8, wherein the electrochromic device is further disposed on a surface of the fourth glass layer.

[0213] Embodiment 10. The laminated glass structure of any of Embodiments 1 to 6, further comprising an electrochromic device disposed on a surface of the second glass layer opposite the heat-treated first glass layer, and wherein the second glass layer comprises heat-treated glass.

[0214] Embodiment 11. The laminated glass structure of any preceding embodiment, wherein the heat-treated first glass layer is a tempered glass layer.

[0215] Embodiment 12. An integrated glass unit comprising: the laminated glass structure of any one of embodiments 1 to 11; a mating sheet; and a sealed interstitial region between the laminated glass structure and the mating sheet.

[0216] Embodiment 13. A laminated glass structure comprising: a first heat-treated glass layer having no curvature or a curvature of about 10 mm or less; and a second glass layer adhesively bonded to the heat-treated glass layer.

[0217] Embodiment 14. The laminated glass structure of Embodiment 13, further comprising an optically switchable device.

[0218] Embodiment 15. The laminated glass structure of embodiment 13 or 14, further comprising an adhesive layer between the heat-treated glass layer and the glass layer.

[0219] Embodiment 16. The laminated glass structure of any of Embodiments 13 to 15, further comprising an electrochromic device disposed on a surface of the second glass layer opposite the heat-treated first glass layer, and wherein the second glass layer is an annealed glass layer.

[0220] Embodiment 17. The laminated glass structure of any of Embodiments 13 to 15, further comprising: an electrochromic device disposed on a surface of the second glass layer opposite the heat-treated first glass layer, wherein the second glass layer is an annealed glass layer; a heat-treated third glass layer; and a fourth glass layer adhesively bonded to the heat-treated third glass layer.

[0221] Embodiment 18. The laminated glass structure of Embodiment 17, wherein the electrochromic device is further disposed on a surface of the fourth glass layer.

[0222] Embodiment 19. The laminated glass structure of any of Embodiments 13 to 15, further comprising an electrochromic device disposed on a surface of the second glass layer opposite the heat-treated first glass layer, and wherein the second glass layer comprises heat-treated glass.

[0223] Embodiment 20. The laminated glass structure of any of Embodiments 13 to 19, wherein the heat-treated first glass layer is a tempered glass layer.

[0224] Embodiment 21. A laminated glass structure comprising: a first heat-treated glass layer produced by heat-treating a preheat-treated glass layer in a furnace wherein the preheat-treated glass layer is supported by a plurality of air jets; and a second glass layer adhesively bonded to the heat-treated glass layer.

[0225] Embodiment 22. The laminated glass structure of Embodiment 21, further comprising an optically switchable device.

[0226] Embodiment 23. The laminated glass structure of Embodiment 21 or 22, further comprising an adhesive layer between the heat-treated glass layer and the glass layer.

[0227] Embodiment 24. The laminated glass structure of any of Embodiments 21 to 23, further comprising an electrochromic device disposed on a surface of the second glass layer opposite the heat-treated first glass layer, and wherein the second glass layer is an annealed glass layer.

[0228] Embodiment 25. The laminated glass structure of any of Embodiments 21 to 23, further comprising: an electrochromic device disposed on a surface of the second glass layer opposite the heat-treated first glass layer, wherein the second glass layer is an annealed glass layer; a heat-treated third glass layer; and a fourth glass layer adhesively bonded to the heat-treated third glass layer.

[0229] Embodiment 26. The laminated glass structure of Embodiment 25, wherein the electrochromic device is further disposed on a surface of the fourth glass layer.

[0230] Embodiment 27. The laminated glass structure of any of Embodiments 21 to 23, further comprising an electrochromic device disposed on a surface of the second glass layer opposite the heat-treated first glass layer, and wherein the second glass layer comprises heat-treated glass.

[0231] Embodiment 28. The laminated glass structure of any one of Embodiments 21 to 27, wherein the heat-treated first glass layer is produced by tempering the preheat-treated glass layer in the furnace.

[0232] Embodiment 29. A method of manufacturing a laminated glass structure, the method comprising: heat treating a preheat treated glass layer by supporting the preheat treated glass layer on a plurality of air jets while exposing the preheat treated glass layer to heat treating conditions, wherein heat treating the preheat treated glass layer produces a heat treated first glass layer; and adhesively bonding the heat treated first glass layer to a second glass layer.

[0233] Embodiment 30. The method of embodiment 29, wherein the preheat-treated glass layer does not contact a solid surface during the thermal treatment.

[0234] Embodiment 31. The method of embodiment 29, wherein the preheat treated glass layer does not contact a roller during the heat treatment.

[0235] Embodiment 32. The method of embodiment 29, 30, or 31, wherein during the heat treatment, the preheat treated glass layer floats substantially horizontally on air generated using the plurality of air jets.

[0236] Embodiment 33. The method of embodiment 29, 30, or 31, wherein during the heat treatment, the preheat treated glass layer floats on air generated using the plurality of air jets at an angle of inclination of no more than about 10 degrees from a horizontal plane.

[0237] Embodiment 34. The method of embodiment 33, wherein during the heat treatment, the preheat treated glass layer floats substantially horizontally on air generated using the plurality of air jets.

[0238] Embodiment 35. A method according to any one of embodiments 32, 33 or 34, wherein the air jet generates an air flow at a certain angle or within a certain range of angles, and the air flow generates a force to push the preheat treated glass layer along a path in the heat treatment furnace where the heat treatment conditions are applied.

[0239] Embodiment 36. The method of embodiment 35, wherein the heat treatment furnace comprises one or more guardrails that retain the preheat treated glass layer within the path of the heat treatment furnace.

[0240] Embodiment 37. The method of any one of Embodiments 29 to 36, wherein exposing the preheat treated glass layer to heat treatment conditions comprises heating the preheat treated glass with heat emitted by one or more heating plates while supporting the preheat treated glass on the plurality of air jets.

[0241] Embodiment 38. The method of Embodiment 37, wherein the one or more heating plates include at least one heating plate positioned substantially below the preheat treated glass.

[0242] Embodiment 39. The method of any one of Embodiments 29 to 38, further comprising fabricating an electrochromic device on the heat-treated first glass layer and / or on the second glass layer.

[0243] Embodiment 40. The method of any one of Embodiments 29 to 39, further comprising forming an electrochromic device on a surface of the second glass layer opposite the heat-treated first glass layer, and wherein the second glass layer is an annealed glass layer.

[0244] Embodiment 41. The method of any one of Embodiments 29 to 38, further comprising: forming a first portion of the electrochromic device on a surface of the second glass layer opposite the heat-treated first glass layer, wherein the second glass layer is an annealed glass layer; forming a second portion of the electrochromic device on a surface of an annealed fourth glass layer opposite the heat-treated third glass layer; and contacting the first portion of the electrochromic device to the second portion of the electrochromic device.

[0245] Embodiment 42. The method of any one of Embodiments 29 to 38, further comprising forming an electrochromic device on a surface of the second glass layer opposite the heat-treated first glass layer, and wherein the second glass layer comprises heat-treated glass.

[0246] Embodiment 43. The method of any one of Embodiments 29 to 42, wherein the heat treating comprises quenching the preheat treated glass layer by exposing different portions of the preheat treated glass layer to different cooling rates.

[0247] Embodiment 44. The method of any one of Embodiment 43, wherein exposing different portions of the preheat-treated glass layer to different cooling rates is performed with one or more quenching air jets.

[0248] Embodiment 45. The method of any one of Embodiments 29 to 44, wherein the heat treatment comprises tempering the preheat-treated glass layer.

[0249] Embodiment 46. A method of forming an integrated glass unit, the method comprising assembling a laminated glass structure, a mating sheet, and a spacer together in a manner that forms a sealed interstitial region between the laminated glass structure produced by the method of any one of Embodiments 29 to 45 and the mating sheet.

[0250] Embodiment 47. An apparatus comprising: a furnace configured to accommodate a glass layer and comprising: a heater; an air floatation surface; a plurality of holes located on the air floatation surface; and a plenum or manifold configured to direct an air flow through the holes to generate air jets that can impact a first surface of the glass layer and support the glass layer above the air floatation surface.

[0251] Embodiment 48. The apparatus of Embodiment 47, further comprising a second plurality of holes configured to direct air onto a second surface of the glass layer opposite the first layer.

[0252] Embodiment 49. The apparatus of Embodiment 47 or 48, wherein the holes in the plurality of holes are configured to direct the air jet at a non-perpendicular angle relative to the first surface of the glass layer.

[0253] Embodiment 50. The apparatus of any one of Embodiments 47 to 49, wherein the furnace is configured such that edges of the glass sheet do not contact surfaces of the furnace as the glass layer moves through the tempering furnace.

[0254] Embodiment 51. The apparatus of any one of embodiments 47 to 50, further comprising a quenching zone comprising a plurality of quenching holes configured to provide quenching air jets that can support the glass sheet while the glass sheet is in the quenching zone.

[0255] Embodiment 52. The apparatus of Embodiment 51, wherein at least one of the plurality of quench holes comprises a nozzle configured to adjust a pressure of a quench air jet emitted by the nozzle.

[0256] Embodiment 53. A method comprising: receiving parameters associated with a trained machine learning model, the trained machine learning model being configured to receive input indicating parameters associated with tempering of a sheet and output one or more recipes and / or bed load changes for a subsequent batch of sheets to be tempered; obtaining parameters associated with a first batch of sheets undergoing tempering; determining one or more modifications to: a current recipe for processing the first batch of sheets; and / or a bed load configuration for a second batch of sheets by providing the obtained parameters to the trained machine learning model, wherein the one or more modifications are used to process the second batch of sheets.

[0257] Embodiment 54. The method of embodiment 53, wherein the parameters associated with the first batch of sheets include a layout of a plurality of sheets in the first batch of sheets within a furnace used to perform the tempering.

[0258] Embodiment 55. The method of Embodiment 54, wherein the layout is determined based at least on pyrometer data.

[0259] Embodiment 56. The method of Embodiment 55, wherein the layout is determined by applying image processing techniques to the pyrometer data.

[0260] Embodiment 57. The method of embodiment 56, wherein the image processing technique is used to determine the mean and standard deviation of the temperature across the first batch of slices.

[0261] Embodiment 58. The method of any one of Embodiments 53 to 57, wherein the parameters associated with the first batch of lamellae include curvature information associated with curvature of lamellae in the first batch of lamellae.

[0262] Embodiment 59. The method of any one of Embodiments 53 to 58, wherein the parameters associated with the first batch of slices include distortion data.

[0263] Embodiment 60. The method of any one of Embodiments 53 to 59, wherein the parameter associated with the first batch of flakes comprises a break weight of the first batch of flakes.

[0264] Embodiment 61. The method of any one of Embodiments 53 to 60, wherein the parameter associated with the first batch of flakes comprises a surface compressive force of the first batch of flakes.

[0265] Example 62. A method according to any one of Examples 53 to 61, wherein the machine learning model is trained by updating weights associated with the machine learning model based at least in part on a comparison of a baseline true recipe modification and / or predicted bed load configuration of a training sample with a predicted recipe modification and / or predicted bed load configuration of the training sample.

[0266] Embodiment 63. A method according to any one of embodiments 53 to 62, wherein the one or more modifications cause the second batch of sheets to meet sheet specifications, wherein the sheet specifications include at least one of the following: a target sheet bend metric, a target breaking weight, a target distortion metric, or a target compression metric.

[0267] Embodiment 64. The method of any one of Embodiments 53 to 63, wherein the one or more modifications comprise one or more modifications to the current recipe, and wherein the one or more modifications to the current recipe comprise modifications to a heating profile and / or cooling profile used to perform the tempering.

[0268] Embodiment 65. The method of any one of Embodiments 53 to 64, wherein the one or more modifications are modifications to the bed load configuration for the second batch of sheets, and wherein the modification to the bed load configuration includes placing sheets in the second batch of sheets based on size.

[0269] Embodiment 66. The method of embodiment 65, wherein the positioning of the sheets comprises relative positioning of the sheets in the second batch of sheets relative to each other.

[0270] Embodiment 67. The method of any one of Embodiments 53 to 66, wherein the one or more modifications include modifications to the air flow provided by one or more jets within the furnace.

[0271] Embodiment 68. The method of embodiment 67, wherein the modification of the air flow comprises modification of the pressure provided by the jet.

[0272] Example 69. A method comprising: a) initializing a machine learning model configured to receive input indicating parameters associated with tempering a thin film and output one or more recipes and / or bed load changes for a subsequent batch of thin films to be tempered; b) utilizing the machine learning model to generate outputs including recipe changes and / or bed load layouts given the inputs indicating parameters associated with tempering a batch of thin films indicated in one or more training samples; c) updating weights of the machine learning model based at least in part on a difference between the generated outputs and a ground truth recipe and / or bed load layout of the changes indicated in the one or more training samples; d) repeating operations (b) and (c) until it is determined that the machine learning model has completed training.

[0273] Embodiment 70. The method of embodiment 69, wherein the parameters associated with the batch of sheets include a layout of a plurality of sheets in the first batch within a furnace used to perform the tempering.

[0274] Embodiment 71. The method of Embodiment 70, wherein the layout is determined based at least on pyrometer data.

[0275] Embodiment 72. The method of Embodiment 71, wherein the layout is determined by applying image processing techniques to the pyrometer data.

[0276] Embodiment 73. The method of any one of Embodiments 69 to 72, wherein the parameters associated with the tempering of the batch of sheets include at least one of: distortion data, bending information, breaking weight, and / or surface compression force.

[0277] Embodiment 74. A method according to any one of embodiments 69 to 73, wherein the machine learning model comprises a regression model.

[0278] Embodiment 75. A method according to any one of embodiments 69 to 74, further comprising performing feature selection before initializing the machine learning model in operation (a).

[0279] Embodiment 76. The method of embodiment 75, wherein the feature selection comprises using principal component analysis (PCA) or linear discriminant analysis (LDA).

[0280] Embodiment 77. The method of embodiment 75 or 76, further comprising performing data cleansing to delete a subset of data associated with the first batch of slices before initializing the machine learning model in operation (a).

[0281] Embodiment 78. A method according to any one of embodiments 69 to 77, wherein the machine learning model comprises a random forest architecture.

[0282] Embodiment 79. The method of any one of Embodiments 69 to 77, wherein the machine learning model utilizes a reinforcement learning architecture.

[0283] Example 80. A method comprising: determining information associated with a residual heat load of a set of rollers of a furnace used to perform a tempering process on a first batch of thin sheets; and determining at least one of: 1) a modification to the tempering process, wherein the modified tempering process is to be used to process a second batch of thin sheets; or 2) a bed load layout for the second batch of thin sheets, wherein the modified tempering process and / or the bed load layout accounts for the effects of the residual heat load of the set of rollers.

[0284] Embodiment 81. The method of embodiment 80, wherein the modified tempering process includes a modification of the heating profile and / or cooling profile to be applied.

[0285] Embodiment 82. The method of any one of Embodiments 80 or 81, wherein the bed load layout of the second batch of lamellae comprises positions of lamellae in the second batch of lamellae based at least in part on lamella size.

[0286] Embodiment 83. A system comprising: one or more processors; and a non-transitory computer-readable medium storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations according to any one of embodiments 53 to 82.

[0287] Embodiment 84. A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform the operations of any one of Embodiments 53 to 82.

Claims

1. A laminated glass structure, characterized in that: include: The heat-treated first glass layer has no peak-to-valley distance of about 0.2 mm or greater; as well as A second glass layer is adhesively bonded to the heat-treated glass layer, wherein the laminated glass structure does not exhibit a lens effect caused by relief.

2. The laminated glass structure according to claim 1, wherein: Further included is an optically switchable device.

3. The laminated glass structure according to claim 2, wherein: The optically switchable device is an electrochromic device.

4. Laminated glass structure according to any one of the preceding claims, characterized in that: The invention further includes an adhesive layer between the heat-treated glass layer and the glass layer.

5. The laminated glass structure according to claim 4, characterized in that: The adhesive layer includes a resin.

6. The laminated glass structure according to claim 5, characterized in that: The resin includes polyvinyl butyral (PVB), ionomer intermediate film (SentryGlas, SBP) or a combination thereof.

7. Laminated glass structure according to any one of the preceding claims, characterized in that: Further included is an electrochromic device disposed on a surface of the second glass layer opposite the heat-treated first glass layer, and wherein the second glass layer is an annealed glass layer.

8. The laminated glass structure according to any one of claims 1 to 6, characterized in that: Further including: an electrochromic device disposed on a surface of the second glass layer opposite the heat-treated first glass layer, wherein the second glass layer is an annealed glass layer; a heat-treated third glass layer; as well as A fourth glass layer is adhesively bonded to the heat-treated third glass layer.

9. The laminated glass structure according to claim 8, wherein: The electrochromic device is also disposed on the surface of the fourth glass layer.

10. The laminated glass structure according to any one of claims 1 to 6, characterized in that: Further included is an electrochromic device disposed on a surface of the second glass layer opposite the heat-treated first glass layer, and wherein the second glass layer comprises heat-treated glass.

11. Laminated glass structure according to any one of the preceding claims, characterized in that: The heat-treated first glass layer is a tempered glass layer.

12. An integrated glass unit, characterized in that: include: The laminated glass structure according to any one of claims 1 to 11; Matching flakes; as well as A void area is sealed between the laminated glass structure and the mating sheet.

13. A laminated glass structure, characterized in that: include: a heat-treated first glass layer having no curvature or a curvature of about 10 mm or less; as well as A second glass layer is adhesively bonded to the heat-treated glass layer.

14. A laminated glass structure, characterized in that: include: a first heat-treated glass layer produced by heat-treating a preheat-treated glass layer in a furnace wherein the preheat-treated glass layer is supported by a plurality of air jets; as well as A second glass layer is adhesively bonded to the heat-treated glass layer.

15. The laminated glass structure according to claim 14, wherein: Further included is an optically switchable device.

16. A method of manufacturing a laminated glass structure, characterized in that: The method comprises: heat treating the preheat-treated glass layer by supporting the preheat-treated glass layer on a plurality of air jets while exposing the preheat-treated glass layer to heat-treating conditions, wherein heat-treating the preheat-treated glass layer produces a heat-treated first glass layer; and The heat-treated first glass layer is adhesively bonded to a second glass layer.

17. The method according to claim 16, wherein: During the heat treatment, the preheat-treated glass layer does not contact a solid surface.

18. The method according to claim 16, wherein: During the heat treatment, the preheat-treated glass layer does not contact the rollers.

19. The method according to claim 16, wherein: During the heat treatment, the preheat-treated glass layer floats substantially horizontally on air generated using the plurality of air jets.

20. A device, characterized in that: include: A furnace configured to accommodate a layer of glass and comprising: heater; air floating surface; a plurality of holes on the air floating surface; and A plenum or manifold is configured to direct airflow through the apertures to generate air jets capable of impinging upon the first surface of the glass layer and supporting the glass layer above the air float surface.

21. The device according to claim 20, characterized in that: Further included is a second plurality of holes configured to direct air onto a second surface of the glass layer opposite the first layer.

22. A method comprising: include: receiving parameters associated with a trained machine learning model, the trained machine learning model configured to receive input indicative of parameters associated with tempering of a sheet and output one or more recipes and / or bed load changes for a subsequent batch of sheets to be tempered; obtaining parameters associated with a first batch of thin sheets undergoing tempering; as well as One or more modifications to: a current recipe for processing the first batch of sheets; and / or a bed load configuration for processing the second batch of sheets are determined by providing the obtained parameters to the trained machine learning model, wherein the one or more modifications are used to process the second batch of sheets.

23. The method according to claim 22, wherein: The parameters associated with the first batch of sheets include a layout of a plurality of sheets of the first batch of sheets within a furnace used to perform the tempering.

24. The method according to claim 23, wherein: The layout is determined based at least on pyrometer data.

25. The method according to claim 24, wherein: The layout is determined by applying image processing techniques to the pyrometer data.

26. The method according to claim 25, characterized in that: The image processing techniques are used to determine the mean and standard deviation of the temperature across the first batch of slices.

27. The method according to any one of claims 22 to 26, characterized in that: The parameters associated with the first batch of lamellae include curvature information associated with curvature of lamellae in the first batch of lamellae.

28. The method according to any one of claims 22 to 26, characterized in that: The parameters associated with the first batch of flakes include distortion data.

29. The method according to any one of claims 22 to 26, characterized in that: The parameters associated with the first batch of sheets include a break weight of the first batch of sheets.

30. The method according to any one of claims 22 to 26, characterized in that: The parameters associated with the first batch of flakes include surface compression of the first batch of flakes.

31. The method according to any one of claims 22 to 26, characterized in that: The machine learning model is trained by updating weights associated with the machine learning model based at least in part on a comparison of ground truth recipe modifications and / or predicted bed loading configurations for training samples with predicted recipe modifications and / or predicted bed loading configurations for the training samples.

32. The method according to any one of claims 22 to 26, characterized in that: The one or more modifications cause the second batch of sheets to meet sheet specifications, wherein the sheet specifications include at least one of: a target sheet bow metric, a target break weight, a target distortion metric, or a target compression metric.

33. The method according to any one of claims 22 to 26, characterized in that: The one or more modifications include one or more modifications to the current recipe, and wherein the one or more modifications to the current recipe include modifications to a heating profile and / or a cooling profile used to perform the tempering.

34. The method according to any one of claims 22 to 26, characterized in that: The one or more modifications are modifications to the bed load configuration for the second batch of lamellae, and wherein the modification to the bed load configuration includes positioning lamellae in the second batch of lamellae based on size.

35. The method according to claim 34, wherein: Said positioning of the sheets comprises relative positioning of the sheets in said second batch of sheets with respect to each other.

36. The method according to any one of claims 22 to 26, characterized in that: The one or more modifications include modifications to the air flow provided by one or more jets within the furnace.

37. The method according to claim 36, wherein: The modification of the air flow comprises a modification of the pressure provided by the jet.

38. A method comprising: include: a) initializing a machine learning model configured to receive input indicative of parameters associated with tempering of a sheet and output one or more recipes and / or bed load changes for a subsequent batch of sheets to be tempered; b) utilizing the machine learning model to generate outputs comprising recipe changes and / or bed load layouts given input of parameters associated with tempering of a batch of sheets indicated in one or more training samples; c) updating weights of the machine learning model based at least in part on differences between the generated output and a changed ground truth recipe and / or bed load configuration indicated in the one or more training samples; as well as d) Repeat operations (b) and (c) until it is determined that the machine learning model has completed training.

39. The method according to claim 38, wherein: The machine learning model includes a regression model.

40. The method according to any one of claims 38 or 39, characterized in that: Further including performing feature selection before initializing the machine learning model in operation (a).

41. The method according to claim 40, wherein: The feature selection includes using principal component analysis (PCA) or linear discriminant analysis (LDA).

42. The method according to claim 40, wherein: Further including performing data cleaning to delete a subset of data associated with the first batch of slices before initializing the machine learning model in operation (a).

43. The method according to any one of claims 38 or 39, characterized in that: The machine learning model includes a random forest architecture.

44. The method according to any one of claims 38 or 39, characterized in that: The machine learning model utilizes a reinforcement learning architecture.

45. A method comprising: include: determining information associated with a residual heat load of a set of rollers of a furnace used to perform a tempering process on a first batch of sheets; as well as Determining at least one of: 1) a modification to the tempering process, wherein the modified tempering process is to be used to process a second batch of sheets; or 2) a bed load layout for the second batch of sheets, wherein the modified tempering process and / or the bed load layout accounts for the effects of the residual heat load of the set of rollers.

Images