System and method for recommending goods to be recovered from recoverable material using machine learning

Abstract

A method for identifying and recovering target merchandise from a composite wind turbine blade in which a computing device receives quality level data indicative of quality levels of respective materials included within the turbine blade and merchandise data of a plurality of candidate merchandise that can be recovered from one or more materials of the turbine blade. The computing device determines an expected profitability for each of the plurality of respective candidate items, where the quality rating data for the respective material and the item data for the plurality of candidate items are provided as inputs to the data model such that the data model determines the expected profitability for each of the plurality of respective candidate items. The computing device determines, based on the expected profitability, a recommendation indicating, for a respective material of the turbine blade, one or more target merchandise items to be restored using the respective material. The device delivers the recommendation to another device or recipient such that a recovery of the target item can occur.

Description

Technical Field

[0001] This invention generally relates to a method of using machine learning to recommend (suggest) commodities to be recovered from the materials of composite components, such as the materials of rotor blades of wind turbines. Background Technology

[0002] Recycling is the act or process of converting recyclable materials into reusable materials. Typically, recycling processes involve manipulating or destroying recyclable materials (e.g., through melting processes) so that the resulting reusable materials can be used to create new products.

[0003] A wind turbine is a device that converts the kinetic energy of wind into electrical energy. For example, a wind turbine converts the kinetic energy of wind into electricity by using the aerodynamic force generated by the interaction between the wind and the rotor blades to rotate a generator.

[0004] Modern wind turbine blades are complex composite structures. These structures are made using a range of materials with different compositions, physical properties, and chemical properties. For example, wind turbine blades may include various sensors, lightning conductors and receivers for lightning protection, heating systems (e.g., electric or fluid-based) for anti-icing or de-icing, glass fiber reinforced composites and carbon fiber reinforced composites for supporting components, polymer foam or balsa wood for the stiffness of the sandwich structure, coatings for protection and aerodynamic performance, protective shells for erosion protection in areas such as the leading edge, roots for connecting the blade root to the hub, adhesives or fasteners for joining the various components together, and so on.

[0005] Due to the complexity of wind turbine blades, each component of a wind turbine blade can be recovered and recycled individually or in combination as various commodities. However, efforts to recycle wind turbine components or materials have largely ceased or become ineffective. One reason is that many wind turbine components are made of composite materials, where multiple materials are bonded together using epoxy resin. Much of the value of recycling composite materials lies in the actual removal or disposal of these “waste” materials, which would otherwise end up in landfills or require recycling in another (even more expensive) manner (e.g., where landfills are not permitted). Without efficient and / or effective ways to separate these materials, many wind turbine components and / or materials have been placed or buried in landfills without being recycled.

[0006] However, new methods for recycling components and / or materials of wind turbines have been discovered, involving separating each material of a composite material by exposing the composite to a swelling agent (e.g., formic acid, etc.) for a sustained period of time. This causes the epoxy resin to decompose, thereby allowing the separation of each material that was bound together using the epoxy resin.

[0007] In wind turbine blades and other structures, dismantling allows for the recovery (recycling) of various commodities with wide applications in different markets. However, the process of recovering commodities from materials varies from commodity to commodity and may involve materials from composite components that have already been separated using new recycling processes. For example, different types of fiber commodities can be recovered from fibrous materials, such as by using the fibrous material directly as a fiber mat, or by cutting, shredding, or crushing the fibrous material into small pieces for subsequent processes such as injection molding, cement, or remelting the fibrous material into new fibers or other products. Each of these commodities is recovered using different processes, involving different modifications to the material, etc. Therefore, the time, effort, and cost associated with recovering each commodity are different.

[0008] This can make it difficult for sellers to determine which (or which) goods to recover. For example, typical supply and demand for a commodity will fluctuate based on many different factors. The introduction of new methods for recycling composite materials may lead to an increase in the supply of goods that can be recovered from those materials. If there are multiple sellers in the market, the increase in supply may have the effect of causing a decrease in the price of the relevant goods. Other factors that may affect the market for raw material commodities include changes in laws or regulations in a geographic area, reductions in carbon dioxide emissions due to the replacement of non-recycled goods with recycled goods, changes in the transportation costs of these materials / goods (e.g., this may occur based on a significant increase in the supply of goods recovered from these materials), and so on. Each of these factors makes it difficult for sellers to choose the best goods to recover.

[0009] The object of this invention is to mitigate or overcome some or all of the problems described above. This invention is particularly advantageous when the composite component is a wind turbine blade comprising an amine-cured epoxy resin. Summary of the Invention

[0010] In one aspect of the invention, a method is disclosed for recommending one or more target commodities to be recovered (recycled) using materials within a composite component of a wind turbine.

[0011] To provide a specific example, this method can be applied to wind turbine blades that use epoxy resins and / or epoxy resin systems to bond materials in glass or carbon-reinforced composites. Epoxy resins and / or epoxy resin systems can include amine-cured epoxy resins such as Olin Airstone 760, Hexion RIMR035C infused epoxy resins, Aditya Birla recyclohexaneamine epoxy resin systems, etc. Such epoxy resins and / or epoxy resin systems allow for disassembly via swelling and / or dissolution in an acidic solution containing formic acid and / or acetic acid under relatively mild conditions. For formic acid, solutions of at least 50 wt% formic acid have been found to be effective at ambient temperature and pressure. However, increased temperature, pressure, and concentration increase the reaction rate.

[0012] To provide another example, this method can be applied to glass fiber reinforced composites that are recovered by separating the cured resin matrix from the fibers, allowing the fibers to be recovered as long single fibers, fiber pads of woven or sewn fibers, chopped fibers that allow for injection molding, and / or mass blocks of glass fibers for remelting. The cured resin matrix material can be recovered as a particulate resin matrix or can be chemically depolymerized into monomers or oligomers. Alternatively—but less ideal from a recycling perspective, as this constitutes downgraded recycling—the glass fiber reinforced composite can be crushed or ground into particles for use as filler, for example in concrete, or as a combination of fuel and filler in cement production.

[0013] The method includes receiving material data by a computing device, the material data including quality grade data indicating the quality grade of a corresponding material included in a composite component. The method also includes receiving commodity data by the computing device of a plurality of candidate goods retrievable from one or more materials in the composite component. The method further includes determining, by the computing device, the expected profitability of each of the plurality of corresponding candidate goods. The quality grade data of the corresponding materials and the commodity data of the plurality of candidate goods can be provided as input to a data model to enable the data model to determine the expected profitability of each of the plurality of corresponding candidate goods. The data model can be trained using machine learning based on historical quality grade data indicating the quality grade of materials included in the composite component and historical commodity data of candidate goods made from materials in the composite component. The method also includes determining, by the computing device and based on the expected profitability, a recommendation indicating one or more target goods to be retrieved using the corresponding materials in the composite component. The method further includes delivering the recommendation from the computing device to another device or recipient, enabling the retrievability of the target goods.

[0014] In embodiments of the invention, historical product data for candidate products may include sales price and sales volume data from an online marketplace, where one or more candidate products are sold. In this embodiment, the data model can be used to determine the expected profitability of candidate products among the candidate products, at least in part, based on the sales price and sales volume data from the online marketplace.

[0015] In another embodiment of the invention, the data model can be used to determine the expected profitability of a candidate product among a plurality of candidate products. For example, the data model can be used to determine the expected costs associated with resuming the candidate product (e.g., one of the materials used in the composite component). The data model can also be used to determine the expected selling price of the candidate product. The data model can then be used to determine the expected profitability of the candidate product based on the expected costs and the expected selling price.

[0016] In another embodiment of the invention, the expected sales price can be determined based on the historical sales price of the candidate product and the historical sales price of non-recycled products that share one or more characteristics with the candidate product.

[0017] In another embodiment of the invention, determining the expected selling price may include processing quality grade data to identify the quality grade of the material, and determining the expected selling price based at least in part on the quality grade of the material.

[0018] In another embodiment of the invention, determining the expected selling price may include determining a pricing adjustment amount based on whether the candidate product is a recycled product, and determining the expected selling price based at least in part on the pricing adjustment amount.

[0019] In another embodiment of the invention, historical market data corresponding to the markets of a plurality of candidate products can be used to train the data model. In this embodiment, determining the expected profitability of a candidate product may include determining one or more change indicators of the market for the candidate product based on historical market data, and determining the expected profitability of the candidate product at least in part based on said one or more change indicators.

[0020] In another embodiment of the invention, one or more change indicators may include: indicators associated with changes in laws or regulations in the geographical area corresponding to the location of the composite component; indicators associated with a reduction in carbon dioxide emissions resulting from replacing non-recycled goods with candidate goods (wherein the non-recycled goods share one or more characteristics with the candidate goods); indicators associated with changes in the transportation costs of the candidate goods; indicators associated with the production location of the candidate goods; or indicators associated with the sales location of the candidate goods.

[0021] In another embodiment of the invention, historical market data corresponding to one or more markets for a given candidate product can be used to train the data model. In this embodiment, determining the profitability of a candidate product among the candidate products may include: processing historical market data to determine the maturity level of the market to which the candidate product belongs, selecting general machine learning features or specific machine learning features based on the market maturity level, and using the selected features to determine the profitability of the candidate product.

[0022] In another embodiment of the invention, determining a recommendation may include determining a set of instructions specifying changes to one or more materials of the composite component such that the target product is recovered from the material. In another embodiment of the invention, determining a recommendation may include determining a set of chemical treatment instructions specifying changes to one or more materials of the composite material such that the target product is recovered from the material.

[0023] In another embodiment of the invention, the material of the composite component may include a cured epoxy resin. In this embodiment, the target product may include one or more of the following: a particulate resin matrix, one or more chemically depolymerized monomers, and one or more chemically depolymerized oligomers. When a recommendation is determined, the method may include determining a recommendation to restore at least one of the following: a particulate resin matrix, one or more chemically depolymerized monomers, and one or more chemically depolymerized oligomers.

[0024] In another aspect of the invention, an apparatus for performing any of the methods described above is disclosed. The apparatus includes one or more memories and one or more processors communicatively coupled to the memories to receive material data including quality grade data indicating the quality grade of a corresponding material included in a composite component of a wind turbine; to receive commodity data of a plurality of candidate commodities retrievable from the composite component; to determine the expected profitability of each of the plurality of corresponding candidate commodities, wherein the quality grade data of the corresponding material and the commodity data of the plurality of candidate commodities are provided as input to a data model to determine the expected profitability of each of the plurality of corresponding candidate commodities. The data model is trained using machine learning based on historical quality grade data indicating the quality grade of the material included in the composite component and historical commodity data of candidate commodities made from the material in the composite component. Furthermore, the one or more memories and the one or more processors communicatively coupled to the memories determine recommendations based on the expected profitability, the recommendations indicating one or more target commodities to be retrievable using the corresponding material of the composite component; and deliver the recommendations to another device or recipient.

[0025] In another aspect of the invention, a computer-readable medium for performing any of the methods described above is disclosed. The non-transitory computer-readable medium stores instructions, and the instructions include one or more instructions that, when executed by one or more processors, cause the one or more processors to: receive material data, the material data including quality grade data indicating the quality grade of a corresponding material included in a composite component of a wind turbine; receive commodity data of a plurality of candidate commodities retrievable from the one or more materials of the composite component; determine the expected profitability of each of the plurality of corresponding candidate commodities, wherein the quality grade data of the corresponding material and the commodity data of the plurality of candidate commodities are provided as input to a data model to cause the data model to determine the expected profitability of each of the plurality of corresponding candidate commodities. The data model is trained using machine learning based on historical quality grade data indicating the quality grade of the material included in the composite component and historical commodity data of candidate commodities made from the material in the composite component. When executed by one or more processors, the instructions also cause the one or more processors to determine a recommendation based on the expected profitability, the recommendation indicating one or more target commodities to be retrievable using the corresponding material of the composite component; and deliver the recommendation to another device or recipient.

[0026] The foregoing summary presents a simplified overview of some embodiments of the invention to provide a basic understanding of certain aspects of the invention discussed herein. This summary is not intended to provide a broad overview of the invention, nor is it intended to identify any key or essential elements, or to define the scope of the invention. The sole purpose of the summary is merely to present some concepts in a simplified form as an introduction to the detailed description that follows. Attached Figure Description

[0027] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate various embodiments of the invention and, together with the general description of the invention given above and the detailed description of the embodiments given below, serve to explain the embodiments of the invention.

[0028] Figure 1 A wind turbine in which the product of the present invention can be advantageously used is shown.

[0029] Figure 2 A cross-sectional view of the rotor blades of a wind turbine is shown.

[0030] Figure 3A It is a diagram of a recycling management platform that receives historical data to be used to train data models.

[0031] Figure 3BIt is a chart that the recycling management platform uses to determine the features to be used to train the data model.

[0032] Figure 3C It is a chart of the training data model of the recycling management platform.

[0033] Figure 4A It is a graph showing the requests for recommendations received by the recycling management platform from user devices.

[0034] Figure 4B It is a chart that uses data models to determine the expected profitability of candidate commodities that can be recovered from materials in composite components, as presented by the recycling management platform.

[0035] Figure 4C It is a graph that the recycling management platform uses to determine recommendations based on the expected profitability of candidate products and then provides those recommendations to the user's device.

[0036] Figure 5 This is a diagram of example environments in which the systems and / or methods described in this article can be implemented.

[0037] Figure 6 yes Figure 5 A diagram of example components for one or more devices.

[0038] It should be understood that the accompanying drawings are not necessarily drawn to scale and may present slightly simplified representations of various features illustrating the basic principles of the invention. Specific design features of the operational sequences disclosed herein, including, for example, the specific dimensions, orientations, positions, and shapes of the various illustrated components, may be determined in part by the specific intended application and usage environment. Some features of the illustrated embodiments may have been enlarged or modified relative to other features for visualization and clarity. Detailed Implementation

[0039] The following detailed description of exemplary embodiments is taken with reference to the accompanying drawings, which illustrate by way of illustration specific details and embodiments in which the invention may be practiced. These embodiments have been described in sufficient detail to enable those skilled in the art to practice the invention. Other embodiments may be utilized and structural, logical, and electrical changes may be made without departing from the scope of the invention as defined in the appended claims.

[0040] Figure 1A wind turbine 100 in which the product of the present invention can be advantageously used is shown. The wind turbine 100 includes a tower 102, a nacelle 104 on which a rotor 106 is mounted, and a yaw bearing 108. The yaw bearing 108 rotatably connects the tower 102 to the nacelle 104. The rotor 106 includes a rotor hub to which three rotor blades (shown as rotor blades 110, 112, and 114, respectively) are attached. The yaw bearing 108 is configured such that the nacelle 104, together with the rotor 106 mounted thereon, is rotatable relative to the tower 102. Thus, the nacelle 104 can be arranged such that the rotor 106 is oriented towards the wind. When oriented towards the wind, the wind turbine 100 can operate to generate more electricity.

[0041] Despite Figure 1 The diagram illustrates a rotor 106, but it should be understood that multiple rotors can be supported by a tower 102. For example, a dual-rotor configuration can be seen in U.S. Publication No. 2022 / 0025866, and a configuration with two pairs of rotors can be seen in WO-A1-2018 / 157897. Therefore, aspects of the present invention are applicable to multi-rotor wind turbines or other types of wind turbines, and should not be limited to... Figure 1 Those shown.

[0042] Figure 2 This is a cross-sectional view of a rotor blade 200 of a wind turbine. In some embodiments, the rotor blade 200 may be a composite component as described herein. In some embodiments, the rotor blade 200 may correspond to rotor blade 110, rotor blade 112, and / or rotor blade 114. The rotor blade 200 has a plurality of spars caps 212, 214, 216, and 218. The rotor blade 200 has an outer shell 208 made of two half-shells 204, 206. The shells 204, 206 are molded from glass fiber reinforced plastic (GRP). Part of the outer shell 208 is a sandwich panel construction and includes a blade core in a lightweight form (e.g., polyurethane) sandwiched between inner and outer GRP layers or "skin".

[0043] The rotor blade 200 includes a first pair of spars and a second pair of spars 212, 214, 216, and 218 arranged between the sandwich panel regions of the outer casing 208. One spars in each pair is integrated with the windward casing, and the other spars in each pair is integrated with the leeward casing. The corresponding pairs of spars 212, 214, 216, and 218 are opposite to each other and extend longitudinally along the length of the rotor blade 200. A first longitudinally extending shear web 220 bridges the first pair of spars 212, 214, and a second longitudinally extending shear web 222 bridges the second pair of spars 216, 218. The shear webs 220 and 222, together with the spars 212, 214, 216, and 218, form a pair of I-beam structures that effectively transfer the load from the rotor blade 200 to the hub (not shown) of the wind turbine. The wing caps 212, 214, 216, and 218 specifically transmit tensile and compressive bending loads, while the shear webs 220 and 222 transmit shear stresses in the rotor blades 200.

[0044] In some embodiments, the spar caps (e.g., spar caps 212, 214, 216, 218) can be constructed using a stack of pultruded strips bonded together. The pultruded strips are bonded together by an adhesive such as a resin (e.g., epoxy resin). The pultruded strips are arranged in the stack with their respective bonded surfaces in an opposing relationship. The adhesive can be applied directly to the bonded surfaces of the pultruded strips or via another technique such as a resin infusion process. In the infusion process, liquid resin is supplied to the stack, and the resin is infused between the opposing bonded surfaces of the pultruded strips. The wind turbine blade 200 described above is exemplary, and wind turbine blades have a wide range of designs and constructions. Therefore, it should be understood that aspects of the invention are applicable to wind turbine arrangements other than those described above.

[0045] Figures 3A-3C This is a diagram of an example method 300 for using machine learning to train a data model to recommend materials for recovery from composite components. As used herein, recovering an item from a material can refer to any structural or physical alteration that, once made to the material, allows for the recovery of candidate items from that material.

[0046] The composite component described herein can be described as a rotor blade of a wind turbine. It should be understood that this is provided by way of example. In practice, example method 300 can be used to train a data model to recommend goods that are part of another type of composite component or assembly. For example, a composite component can refer to a specific component of a rotor blade, such as a sparsity cap, a specific component of the sparsity cap (such as a pultruded strip), etc. To provide another example, example method 300 can be used to train a data model to recommend goods when the composite component is another device, assembly, component, and / or sub-component. In these examples, a composite component can refer to a printed circuit board (PCB), a component or sub-component of a PCB, a vehicle (e.g., a boat, train, automobile, etc.), a vehicle assembly, a component or sub-component of a vehicle (e.g., the body of an automobile or the hull of a boat), etc.

[0047] like Figure 3A As shown, the recycling management platform 302 can receive historical data to be used for training the data model. For example, and as indicated by reference numeral 304, the recycling management platform 302 can receive historical material data of materials used in the rotor blades (i.e., composite components) of a wind turbine from a data storage device. Historical material data can be received via a network (e.g., the Internet) through a communication interface (such as an application programming interface (API) or a similar interface). The historical material data for the corresponding material may include material identifiers, type data, measurement data, quality grade data, component data, etc.

[0048] Material identifiers can be used to identify specific materials, such as via numeric codes, alphanumeric codes, etc. Type data can include data indicating material type (such as core components (e.g., foam, wood, etc.)), fiber type (e.g., synthetic fiber, semi-synthetic fiber, recycled fiber, carbon fiber, basalt fiber, glass fiber, metal fiber, etc.), adhesive type (e.g., epoxy resin, etc.), material type used within the lightning protection grid, coating type, etc.

[0049] Measurement data may include data that identifies (or can be used to identify) the boundaries of a corresponding material within the rotor blade (and / or within a given component of the rotor blade). For example, measurement data may include data identifying the length, height, width, area, and / or surface area of ​​the material. In some embodiments, the recycling management platform 302 may process the measurement data to add the material to a 3D part drawing (e.g., by defining the material boundaries when the material is used within the rotor blade, such as by using coordinates).

[0050] Additionally or alternatively, material data may include manufacturing data that provides information about the conditions under which the material was manufactured. For example, material manufacturing data may include data related to specific manufacturing actions. To provide a specific example, when a material is cured, the manufacturing data collected may include temperature data indicating the temperature at which the material is cured, time data indicating the duration of curing, pressure data indicating the pressure the material is exposed to during the curing process, data indicating the difference between measured properties of the material during the curing process and baseline properties (e.g., a standard / specification used to cure this type of material), etc. Similar types of data may be collected for other actions or processes associated with manufacturing. For instance, if these actions or processes associated with manufacturing apply to a specific component of the rotor blade, similar types of data may be collected for that specific component of the rotor blade.

[0051] Quality grade data may include data identifying the quality grade of a material. In some embodiments, quality grade data may include data identifying the quality grade of a specific portion or region within the material. For example, different portions of the material may experience varying amounts of wear and tear throughout its lifespan. In this case, the material's quality grade data could identify the quality grade of each portion of the material with a unique quality grade.

[0052] In some embodiments, the material data may also include information describing the properties and / or characteristics of the material. Additionally or alternatively, the material data may include information describing one or more components in which the material is used. For example, the material may be used in multiple components and / or sub-components of a rotor blade. In this case, the material data may include component data identifying one or more components and / or sub-components in which the material is used.

[0053] As indicated by reference numeral 306 in the attached figure, the recycling management platform 302 can receive historical commodity data of recycled goods recovered from materials used within rotor blades. For example, an online marketplace can provide records of transactions between buyers and sellers of goods. Historical commodity data can be obtained using data mining techniques, as further described herein. Historical commodity data can be stored using data storage devices and can be provided to the recycling management platform 302 when it is time to train a data model. Historical commodity data can be provided via a network (e.g., the Internet) through a communication interface (such as an API or a similar type of interface). Historical commodity data of recycled goods may include commodity identifiers, type data, descriptive data, image data, sales price data, sales volume data, status data, location data, etc.

[0054] Product identifiers can be used to identify a specific product, such as via numeric codes, alphanumeric codes, etc. Product type data may include data indicating the type of product. Product description may include data describing one or more characteristics and / or properties of the product, such as one or more materials used in the product, the way the product is modified or prepared (e.g., to restore the product from the materials), etc. Image data may include data representing images of the product and / or image metadata associated with images of the product.

[0055] Price data can include quoted prices or price ranges indicating the price of a product for sale, price acceptance data indicating the price of a product for sale, etc. Volume data can include data indicating the quantity or volume of goods sold. Status data can indicate the status related to the availability of a product for purchase. For example, if the entire supply of a product has been sold, the status of that product listed on the online marketplace can be updated to reflect that the product is out of stock. Location data can include data indicating one or more locations where the product is being sold. For example, location data can indicate the country, state, or province where the product is being sold, the geographic region where the product is being sold, etc.

[0056] In some embodiments, in addition to receiving historical commodity data of commodities recovered from rotor blade material, the recycling management platform 302 may also receive historical commodity data of non-recyclable commodities that share one or more characteristics with recycled commodities. For example, the market for a commodity may involve the sale of a recycled version of the commodity, but it may also involve the sale of non-recyclable and competing versions of the commodity. Thus, the recycling management platform 302 can receive historical commodity data of those non-recyclable commodities that compete with recycled commodities, share one or more characteristics or properties with recycled commodities, etc. Recycled commodities, as used below, may be referred to as commodities only or candidate commodities.

[0057] In some embodiments, the recycling management platform 302 may obtain historical product data from one or more online marketplaces. For example, the recycling management platform 302 may obtain historical product data from one or more online marketplaces by performing data mining techniques (commonly known as web crawling). After obtaining the historical product data, the recycling management platform 302 may store the data using a data storage device, enabling the recycling management platform 302 to access the historical product data when training a data model.

[0058] In some embodiments, historical product data obtained from online marketplaces may not have a format, file type, etc., that would be helpful in training a data model. In this case, the recycling management platform 302 can use one or more natural language processing techniques to analyze the historical product data. This allows the recycling management platform 302 to identify the corresponding type of historical product data and / or convert the historical product data into a uniform file type and / or file format that would be helpful in training a data model.

[0059] The historical product data provided above is for illustrative purposes only. In practice, other types of historical product data representing goods involved in previous business activities can be provided to the recycling management platform 302. For example:

[0060] - Product category or class

[0061] - The appearance / form of the product (e.g., powder, liquid, granules, white crystalline powder, spray, etc.).

[0062] -Product applications (electronic chemicals, plastic additives, coating additives, rubber additives, water treatment chemicals, etc.).

[0063] -Business between sellers and buyers (exporters, manufacturers, wholesalers, importers, agents)

[0064] - Applicable product certificates or regulatory authorizations

[0065] - Applicable seller or buyer certificates or authorizations

[0066] - Supplier location, categorized by country and / or city or region

[0067] - Supplier ranking or feedback score, and experience

[0068] - Supplier delivery time

[0069] As indicated by reference numeral 308 in the attached figure, the recycling management platform 302 can receive historical market data of one or more markets in which recycled goods are exchanged. For example, each corresponding recycled good may be part of a market. Markets may experience fluctuations in supply and demand due to any number of different reasons. For example, an increase in the supply of recyclable materials may lead to an increase in the supply of recycled goods. This may have the effect of causing a decrease in the price of those recycled materials in the market. Those skilled in the art will understand that changes in the market can occur due to any number of different reasons. In order to accurately predict whether it is more profitable (e.g., profitable) for a seller to recover a first good from materials or a second good from the same materials, the recycling management platform 302 can receive historical market data (e.g., markets for the first and second goods respectively) to enable recommendations based on recent changes in one or more of the market conditions and / or based on predicted changes in one or more of the market conditions.

[0070] Historical market data for the relevant market may include market identifiers, type data, descriptive data, regulatory data, market maturity data, supply and demand data of customers and / or suppliers, distribution channel data, supply chain data, market segmentation data, transportation data, environmental data, etc.

[0071] A market ID can be used to identify a specific market, such as via a numeric code, alphanumeric code, etc. Market type data can include data indicating the type of market. For example, if recycled fibers are recovered in some way (e.g., cutting, shredding, crushing, etc.), the recovered goods (fiber-based goods) can be part of a market for recovered fiber-based goods. Market description data can include data describing the type of market, the types of goods bought and sold in the market, etc.

[0072] Regulatory data may include data describing one or more aspects of laws or regulations that affect the market. Specifically, historical market data may include data identifying laws or regulations that affect the market, data indicating the geographic area to which the laws or regulations apply, data describing the laws or regulations, etc. Data describing laws or regulations may include, for example, information describing laws or regulations concerning imports and / or exports to that geographic area, information describing changes to those laws or regulations, and / or any other type of information that could affect the market.

[0073] Market maturity data can include maturity identifiers that identify the maturity level of the market to which a product belongs, as well as data describing the maturity level of the market. For example, if a product is part of a relatively new market, the data describing the market maturity level could specify that it is a new market and that the product has only recently become available for sale.

[0074] Supply and demand data can include supply data indicating the supply and demand of goods. For example, supply and demand data can include sales data and / or product data for selling goods within a given time period, purchase data and / or product data for buying goods within a given time period, etc. Market segmentation data can include data used to divide the market into segments based on things such as preferences, habits, trends, etc. For example, market segmentation data can include data indicating the preferences of sellers of goods, data indicating the preferences of buyers of goods, data indicating habits or trends specific to a subset of the market (e.g., specific to sellers, buyers, geographic locations, or regions, etc.), etc.

[0075] Distribution channel data may include data indicating the number of distribution channels available in the market, data identifying each corresponding distribution channel, and data describing each corresponding distribution channel. Transportation data may include data identifying transportation costs in geographical locations or regions. For example, regional transportation data may include data indicating one or more modes of transportation, data indicating the costs associated with each mode of transportation, and data indicating the average cost associated with a mode of transportation over a given time period. Environmental data may include data indicating environmental changes that may be associated with recycled goods. For example, an increase in the supply of recycled goods, due to the replacement of non-recycled goods with recycled goods, can lead to a reduction in carbon dioxide emissions.

[0076] In some embodiments, historical market data can be collected from multiple auctions of various recycled goods in various markets. Alternatively or additionally, historical market data can be provided by domain experts. Alternatively or additionally, data mining techniques can be used to obtain historical market data. Alternatively or additionally, third-party APIs that allow querying market data can be used to obtain historical market data.

[0077] In some embodiments (not shown), before using historical data to train a data model, the recycling management platform 302 may perform one or more preprocessing operations to standardize the historical data into a uniform data type, data format, etc. For example, historical data may be received in different file types and / or formats, and the recycling management platform 302 may apply appropriate standardization techniques to the different data types or data formats, so that the historical data is transformed into a uniform data type, data format, etc.

[0078] In some embodiments (not shown), the recycling management platform 302 may receive historical cost data. Historical cost data may be information indicating one or more costs associated with recovering goods from materials in composite components.

[0079] In this way, the recycling management platform 302 receives historical data used to train the data model.

[0080] like Figure 3B As shown by reference numeral 310 in the accompanying drawings, the recycling management platform 302 can select features for training the data model. For example, the recycling management platform 302 can identify a feature set that includes features that can be used to train the data model, and can select a subset of the identified features.

[0081] Features can be measurable properties or characteristics that can be used to train data models using machine learning. Feature sets can include features of historical data values, features that aggregate historical data values, features of combinations of historical data values, features of a benchmark of one or more of these values, features of relationships between two or more of these values, etc. Specific example features are provided below.

[0082] The characteristics of material data may include, for example, characteristics that identify the material type, characteristics that identify the material properties or characteristics, characteristics that identify the material's measured values, and characteristics that identify the material's quality grade.

[0083] Similar characteristics can be identified for each of other types of historical data. For example, the feature set could include features related to historical commodity data of goods recovered from materials used within rotor blades. This could include features related to commodity type data, descriptive data, image data, sales price data, sales volume data, status data, location data, and so on.

[0084] Additionally, the feature set may include features related to historical market data, which may include features related to the markets in which goods are exchanged. This may include features related to market type data, market description data, regulatory data, market maturity data, supply and demand data, distribution channel data, market segmentation data, transportation data, environmental data, and so on.

[0085] As described above, a feature set can include features of aggregated historical data values, features of combinations of historical data values, features of a benchmark, and / or features of relationships between two or more of these values. For example, features of aggregated data values ​​can include features related to totals, averages, mean, mode, etc. Features of different combinations of historical data values ​​can include features of all (or some) combinations of two or more different historical data values. Features of a benchmark can include benchmark values ​​of different types of historical data. For example, a benchmark value for sales price data could be a value indicating a preferred sales price.

[0086] The characteristics of a relationship can include values ​​indicating a relationship or association between two or more other values ​​(i.e., two or more historical data values, combinations of values, aggregations of values, etc.), values ​​indicating trends found within the data, etc. For example, these characteristics could include values ​​indicating a relationship between the selling price and quality grade of a material. Specifically, if a material has a low quality grade, the selling price of that material may be lower relative to a material with an average quality grade. Similarly, if a material has a high quality grade, the selling price of that material may be higher relative to a material with an average quality grade. Those skilled in the art will understand that many different relationships can be identified between historical data values. For example, characteristics can be identified for the relationship between product sales volume / product size and each corresponding type of market data.

[0087] In some embodiments, the recycling management platform 302 can identify feature sets by processing historical data using one or more feature identification techniques. These one or more feature identification techniques may include text mining and latent semantic analysis (LSA), trend variable analysis, interest diversity analysis, neural network technology, composite index analysis, cluster analysis, etc.

[0088] In some embodiments, the recycling management platform 302 can select a subset of identified features by processing the feature set and / or historical data using one or more feature selection techniques. The one or more feature selection techniques may include one or more filtering techniques, one or more wrapper techniques, one or more embedded techniques, etc. One or more filtering techniques can be used to remove duplicate or redundant features. These techniques may include chi-square tests, correlation coefficients, variance thresholds, etc. One or more wrapper techniques may involve iterative methods for feature selection (and / or reduction) and may include forward selection techniques, backward elimination techniques, bidirectional elimination techniques, exhaustive selection techniques, recursive elimination techniques, etc. One or more embedded techniques may include regularization techniques, tree-based selection techniques, etc.

[0089] Additionally or alternatively, the recycling management platform 302 may receive features used to train the data model. For example, the feature set or a subset of the feature set may be determined by a domain expert and provided to (or made accessible to) the recycling management platform 302.

[0090] In this way, the recycling management platform 302 determines the features used to train the data model.

[0091] like Figure 3CAs shown by reference numeral 312 in the accompanying drawings, the recycling management platform 302 can train a data model to determine the expected profitability of goods recovered from materials in composite components. For example, the recycling management platform 302 can train the data model using one or more machine learning techniques to analyze historical data and / or identified features. These machine learning techniques may include classification-driven training techniques, logistic regression-based training techniques, Naive Bayes classifier techniques, support vector machine (SVM) techniques, neural networks, etc.

[0092] In some embodiments, the recycling management platform 302 may use an iterative method to train a data model. For example, the recycling management platform 302 may use the data model to process historical training data on composite components such as rotor blades, so that the data model determines the expected profitability score of the commodity. Historical training data can exclude known outputs, allowing the data model to effectively predict the expected profitability of candidate commodities.

[0093] In some embodiments, the recycling management platform 302 may use a data model to determine expected profitability using the following equation: Expected Profitability = Expected Selling Price - Expected Costs + / - Adjustment. The expected selling price may be determined based on historical price data and any features found in historical training data that indicate changes in the selling price. The expected costs may be determined based on historical cost data and any features found in historical training data that indicate changes in the expected costs.

[0094] Next, the recycling management platform 302 may consider further ensuring modifications to the expected profitability value by one or more adjustments. For example, when recycled goods are sold on the market, they can command a sales premium because they are recycled (i.e., green) products. The sales premium can vary depending on the geographic region of the goods being sold. The sales premium can also vary based on other factors, such as the laws or regulations of the region, as these relate to the exchange of raw materials. In one embodiment, the recycling management platform 302 may add the sales premium as a positive adjustment value for updating the current total profitability value. Continuing this example, the recycling management platform 302 may also adjust the total profitability value based on the quality grade of the materials. For example, recycled materials may have a lower quality grade than virgin materials and may be discounted when sold on the market. With this in mind, the recycling management platform 302 may adjust the total profitability value based on the quality grade of the materials. In some embodiments, when the data model is trained, the recycling management platform 302 may update the weights of the data model based on the accuracy of the predictions. For example, if the recycling management platform 302 cannot properly estimate the profitability of composite materials, the platform can adjust the weights within the data model so that the weights of certain values ​​are less or greater than the weights during the previous profitability forecast period.

[0095] In this way, the recycling management platform 302 trains a data model to determine the quality grade of materials based on their expected reusability.

[0096] As mentioned above, Figures 3A-3C This is provided as an example only. Other examples may differ from the reference. Figures 3A-3C The described example. For example, with Figures 3A-3C Compared to what is shown, there may be additional equipment and / or networks, fewer equipment and / or networks, different equipment and / or networks, or equipment and / or networks with different arrangements. Furthermore, Figures 3A-3C The two or more devices shown can be implemented within a single device, or Figures 3A-3C The single device shown can be implemented as multiple and / or distributed devices. Additionally or alternatively, a group of devices (e.g., one or more devices) of Example Embodiment 300 can perform one or more functions described as being performed by another group of devices of Example Method 300.

[0097] Figures 4A-4C This is a diagram of an example method 400 for using machine learning to determine the expected profit of candidate goods that can be recovered from a composite component. As used herein, recovering candidate goods components can refer to any process implemented on a composite component that allows for the recovery of candidate goods from the component.

[0098] In one or more embodiments described herein, the composite component may be a rotor blade of a wind turbine. It should be understood that this is provided by way of example. In practice, example method 400 may be used to determine the expected profit of candidate goods that can be recovered from other components of a wind turbine. Additionally or alternatively, example method 400 may be used to determine the expected profit of candidate goods that can be recovered from other objects / equipment / machines (such as printed circuit boards (PCBs), vehicles (e.g., ships, trains, automobiles, etc.), other composite materials, etc.).

[0099] like Figure 4A As shown, example method 400 involves data communication between user equipment 402, recycling management platform 404, and data storage device 406. As indicated by reference numeral 408, a user can input a request for recommendations regarding which candidate goods to recover from the rotor blades. For example, a user can interact with the user interface of user equipment 402 to input a request for recommendations. In some embodiments, the user interface may be part of an application and / or API that allows the user to submit requests to recycling management platform 404. When a user submits a request, request data can be provided to recycling management platform 404. The request data may include rotor blade identifiers and / or identifiers for each corresponding material in the rotor blades.

[0100] As indicated by reference numeral 410 in the attached figure, the recycling management platform 404 can obtain data on the corresponding materials of the rotor blades and commodity data on candidate commodities that can be recovered from the blades. For example, the recycling management platform 404 can provide a request for material data and / or commodity data to the data storage device 406 based on received request data. The data storage device 406 can use data structures to store material data and / or commodity data associated with rotor blade identifiers and / or material identifiers of the corresponding materials. In this way, the data storage device 406 can use the received identifiers to identify the material data and / or commodity data and provide it to the recycling management platform 404.

[0101] In some embodiments, the recycling management platform 404 may acquire other types of historical data from the data storage device 406. For example, the recycling management platform 404 may obtain historical market data that provides market information related to the candidate product's market. One or more types of data described herein can have predictive values ​​only if the collected data is current. This allows for the periodic collection of different types of data (e.g., and for retraining data models), enabling the recycling management platform 404 to utilize current data related to the product and its corresponding market.

[0102] like Figure 4B As shown by reference numeral 412 in the attached figure, the recycling management platform 404 can use a data model to determine the expected profitability of corresponding candidate commodities. For example, the recycling management platform 404 can provide material data, commodity data, and / or any other collected data as input data to the data model. Figures 3A-3C Describe the training of the data model. This data model can use machine learning to process the input data to determine, for each candidate commodity, the seller's expected profitability if the candidate commodity is restored using one or more materials of the rotor blades.

[0103] In some embodiments, the recycling management platform 404 may use a data model to determine the expected profitability score of a candidate commodity. The expected profitability score can represent the profitability a seller could obtain if that candidate commodity score were recovered from the material. By processing input data using a data model, the recycling management platform 404 can determine historical material data, including quality grade data indicating whether the material is of high or low quality, and commodity data specifying the most recent price at which the candidate commodity was sold in the market. Furthermore, the recycling management platform 404 can determine whether the market is new (e.g., based on receiving a small amount of commodity data, based on receiving market maturity data indicating that the market is new, etc.). Each of these considerations can influence how the recycling management platform 404 calculates the expected profitability score, how the recycling management platform 404 weights certain variables in the equation to determine the expected profitability score, etc.

[0104] In this way, the recycling management platform 404 determines the expected profitability of the corresponding candidate products.

[0105] like Figure 4C As shown by reference numeral 414 in the accompanying drawings, the recycling management platform 404 can determine recommendations for target commodities to be recovered from the rotor blades based on the output of the data model. In addition to recommending target commodities to be recovered, the recommendations may also include one or more sets of instructions on how to recover the corresponding commodities.

[0106] In some embodiments, the recommendation may include a set of instructions specifying how the material from the rotor blades is processed to allow for the recovery of a candidate product from the rotor blades. The instructions may specify the amount of material to be changed and / or the manner in which the material is changed. For example, if the material is fiber, depending on the fiber's use in a given product, the fiber may need to be cut into larger portions for use in fiber mats, may need to be cut, shredded, or crushed into smaller portions for use in injection molding, cement, or may require particularly good cleaning to remove metal components, thereby allowing for better remelting to create new fibers, etc. Additionally or alternatively, the recommendation may include a set of chemical processing instructions specifying how the material of the rotor blades is changed to allow for the recovery of a candidate product from that material.

[0107] In some embodiments, the recycling management platform 404 may recommend one item to be recovered from a given material. In some embodiments, the recycling management platform 404 may recommend multiple items or combinations of items to be recovered from a given material.

[0108] In some embodiments, the recycling management platform 404 may determine recommendations by referring to a data structure. For example, the recycling management platform 404 may access a data structure that associates data identifying expected profitability scores with product identifiers of corresponding candidate products and instructions such as those described above. The recycling management platform 404 may refer to the data structure to identify target products to recommend and to determine which instructions to include in the recommendations.

[0109] As indicated by reference numeral 416, the recycling management platform 404 can deliver recommendations to user equipment 402. In some embodiments, recycling recommendations can be delivered to another recipient, such as an email account or related account. As indicated by reference numeral 418, user equipment 402 can display the recommendation. This allows users to use the recommendation to implement the process of recovering recommended goods, enabling the recommended goods to be made available for sale in the marketplace.

[0110] In some embodiments, recommendations may be provided to a controller (e.g., a computing device with a processor) that is part of an automated or semi-automated recycling facility. The automated or semi-automated recycling facility may have one or more pieces of equipment configured to automatically perform certain recycling tasks. The controller may be configured to send instructions to each piece of equipment to allow the equipment to autonomously perform recycling tasks. In this case, the controller may use recommendations to generate instructions that allow or cause the pieces of equipment to perform recycling tasks, such as cutting material in a certain way, placing material into a recycling container, etc.

[0111] In some embodiments, recommendations may be provided to the user equipment of the recycling equipment operator. For example, the recommendations may be provided to and displayed on the user equipment's user interface. The user interface may display instructions that the operator can use to perform recycling tasks, such as cutting instructions and / or container recycling instructions described herein.

[0112] As mentioned above, Figures 4A-4C This is provided as an example only. Other examples may differ from the reference. Figures 4A-4C The described example. For example, with Figures 4A-4C Compared to those shown, there may be additional equipment and / or networks, fewer equipment and / or networks, different equipment and / or networks, or equipment and / or networks with different arrangements. Furthermore, Figures 4A-4C The two or more devices shown can be implemented within a single device, or Figures 4A-4C The single device shown can be implemented as multiple and / or distributed devices. Additionally or alternatively, a group of devices (e.g., one or more devices) of Example Method 400 can perform one or more functions described as being performed by another group of devices of Example Embodiment 400.

[0113] Figure 5 This is a diagram of 500 example environments from which the systems and / or methods described in this paper can be implemented. (Example...) Figure 5 As shown, environment 500 may include user equipment 502, data storage device 504, a recycling management platform 506 supported within a cloud computing environment 508, and / or network 512. The devices in environment 500 may be interconnected via wired connections, wireless connections, or a combination of wired and wireless connections. User equipment 502 may correspond to user equipment 402. Data storage device 504 may correspond to data storage device 406. Recycling management platform 506 may correspond to recycling management platform 302 and / or recycling management platform 404.

[0114] User equipment 502 includes one or more devices capable of receiving, generating, storing, processing, and / or providing information associated with recommendations. User equipment 502 may include devices such as tablet computers (e.g., iPads), mobile phones (e.g., smartphones, cordless phones, etc.), laptop computers, handheld computers, server computers, gaming devices, wearable communication devices (e.g., smartwatches, smart glasses, etc.), or similar types of devices. In some embodiments, user equipment 502 may submit a request for recommendations to recycling management platform 506. In some embodiments, user equipment 502 may receive recommendations from recycling management platform 506.

[0115] Data storage device 504 includes one or more devices capable of receiving, storing, processing, and / or providing historical data. Data storage device 504 may include a server device or a group of server devices. In some embodiments, data storage device 504 may support data structures that associate different types of historical data. In some embodiments, data storage device 504 may receive requests (e.g., queries) for historical data from recycling management platform 506. This allows data storage device 504 to provide historical data to recycling management platform 506.

[0116] The recycling management platform 506 includes one or more devices capable of receiving, storing, processing, and / or providing information associated with the composite components. The recycling management platform 506 may include server equipment (e.g., a host server, web server, application server, etc.), data center equipment, or similar equipment.

[0117] In some embodiments, the recycling management platform 506 may receive a request for recommendations from the user equipment 502. In some embodiments, the recycling management platform 506 may obtain historical data associated with one or more rotor blades of a wind turbine from the data storage device 504. For example, the recycling management platform 506 may make a request for historical data to the data storage device 504. This may cause the data storage device 504 to provide historical data to the recycling management platform 506.

[0118] In some embodiments, the recycling management platform 506 stores or has access to a data model that has been trained using machine learning. In some embodiments, the recycling management platform 506 may train the data model using historical data of composite components, such as a set of wind turbines. In some embodiments, the recycling management platform 506 may receive the trained data model from another device. In some embodiments, the recycling management platform 506 may provide recommendations to user equipment 502.

[0119] In some embodiments, as shown in the figures, the recycling management platform 506 may be hosted in a cloud computing environment 508. It is worth noting that while the embodiments described herein depict the recycling management platform 506 as hosted in a cloud computing environment 508, in some embodiments, the recycling management platform 506 may not be cloud-based (i.e., may be implemented outside of a cloud computing environment) or may be partially cloud-based.

[0120] The cloud computing environment 508 includes the environment of the managed recycling management platform 506. The cloud computing environment 508 can provide services such as computing, software, data access, and storage, without requiring end users to know the physical location and configuration of the systems and / or devices of the managed recycling management platform 506. As shown in the figure, the cloud computing environment 508 may include a set of computing resources 510 (collectively referred to as "computing resources 510" and individually as "computing resources 510").

[0121] Computing resource 510 includes one or more personal computers, workstation computers, server devices, or other types of computing and / or communication devices. In some embodiments, computing resource 510 may host a recycling management platform 506. Cloud resources may include computing instances performed in computing resource 510, storage devices provided in computing resource 510, data transmission devices provided by computing resource 510, etc. In some embodiments, computing resource 510 may communicate with other computing resources 510 via wired connections, wireless connections, or a combination of wired and wireless connections.

[0122] like Figure 5 As further shown, computing resources 510 may include a set of cloud resources, such as one or more applications (APP) 510a, one or more virtual machines (VM) 510b, virtualized storage (VS) 510c, one or more hypervisors (HYP) 510d, etc.

[0123] Application 510a may include one or more software applications that can be provided to or accessed by user device 502 and / or recycling management platform 506. Application 510a may eliminate the need to install and execute software applications on these devices. In some embodiments, an application 510a may send / receive information to / from one or more other applications 510a via virtual machine 510b. In some embodiments, application 510a may be a recycling management application and / or an application that recommends goods to be recycled for materials using composite components. The recycling management application may include one or more user interfaces that, when displayed on user device 502, allow a user to submit a request for recycling recommendations.

[0124] Virtual machine 510b may include a software implementation of a machine (e.g., a computer) that executes programs like a physical machine. Virtual machine 510b may be a system virtual machine or a process virtual machine, depending on the extent to which virtual machine 510b uses and corresponds to any real machine. A system virtual machine may be a complete system platform that supports the execution of a complete operating system (“OS”). A process virtual machine may execute a single program and may support a single process. In some embodiments, virtual machine 510b may execute on behalf of another device (e.g., user device 502) and may manage the infrastructure of cloud computing environment 508, such as data management, synchronization, or long-duration data transfer.

[0125] Virtualized storage 510c may include one or more storage systems and / or one or more devices that utilize virtualization technology within the storage system or device of computing resource 510. In some embodiments, within the context of the storage system, the type of virtualization may include block virtualization and file virtualization. Block virtualization may refer to the abstraction (or separation) of logical storage from physical storage, enabling access to the storage system regardless of physical storage or heterogeneous architecture. Separation allows storage system administrators flexibility in how they manage end-user storage. File virtualization eliminates the dependency between data accessed at the file level and the location of the physical storage file. This enables performance optimization for storage usage, server consolidation, and / or non-disruptive file migration.

[0126] Hypervisor 510d can provide hardware virtualization technology that allows multiple operating systems (e.g., "guest operating systems") to run simultaneously on a host computer such as computing resource 510. Hypervisor 510d can present a virtual operating platform to the guest operating system and can manage the execution of the guest operating system.

[0127] Network 512 may include one or more wired and / or wireless networks. For example, network 512 may include cellular networks (e.g., fifth-generation (5G) networks, fourth-generation (4G) networks, such as Long Term Evolution (LTE) networks, third-generation (3G) networks and / or Code Division Multiple Access (CDMA) networks), Public Land Mobile Networks (PLMNs), Local Area Networks (LANs), Wide Area Networks (WANs), Metropolitan Area Networks (MANs), Telephone Networks (e.g., Public Switched Telephone Networks (PSTN)), Private Networks, Self-organizing Networks, Intranets, the Internet, Fiber-based Networks, Cloud Computing Networks, etc., and / or combinations of these or other types of networks.

[0128] Figure 5 The number and arrangement of devices and networks shown are provided as an example. In reality, with... Figure 5Compared to what is shown, there may be additional equipment and / or networks, fewer equipment and / or networks, different equipment and / or networks, or equipment and / or networks with different arrangements. Furthermore, Figure 5 The two or more devices shown can be implemented within a single device, or Figure 5 The single device shown can be implemented as multiple distributed devices. Additionally or alternatively, a group of devices in environment 500 (e.g., one or more devices) can perform one or more functions described as being performed by another group of devices in environment 500.

[0129] Figure 6 This is a diagram of example components of device 600. Device 600 may correspond to user device 502, data storage device 504, and / or recycling management platform 506. In some embodiments, user device 502, data storage device 504, and / or recycling management platform 506 may include one or more devices 600 and / or one or more components of device 600. Figure 6 As shown, device 600 may include bus 602, processor 604, memory 606, storage component 608, input component 610, output component 612 and / or communication interface 614.

[0130] Bus 602 includes components that allow communication between multiple components of device 600. Processor 604 is implemented in hardware, firmware, and / or a combination of hardware and software. Processor 604 includes a central processing unit (CPU), graphics processing unit (GPU), accelerated processing unit (APU), microprocessor, microcontroller, digital signal processor (DSP), field-programmable gate array (FPGA), application-specific integrated circuit (ASIC), and / or another type of processing component. In some embodiments, processor 604 includes one or more processors capable of being programmed to perform functions. Memory 606 includes random access memory (RAM), read-only memory (ROM), and / or another type of dynamic or static storage device (e.g., flash memory, magnetic storage, and / or optical storage) storing information and / or instructions used by processor 604.

[0131] Storage component 608 stores information and / or software related to the operation and use of device 600. For example, storage component 608 may include hard disks (e.g., magnetic disks, optical disks, magneto-optical disks, and / or solid-state disks), compact discs (CDs), digital versatile discs (DVDs), floppy disks, cassette tapes, magnetic tapes, and / or other types of non-transitory computer-readable media, and corresponding drives.

[0132] Input component 610 includes components that allow device 600 to receive information, such as via user input (e.g., a touchscreen display, keyboard, keypad, mouse, buttons, switches, and / or microphone). Additionally or alternatively, input component 610 may include sensors for sensing information (e.g., a Global Positioning System (GPS) component, accelerometer, gyroscope, and / or actuator). Output component 612 includes components that provide output information from device 600 (e.g., a display, speaker, and / or one or more light-emitting diodes (LEDs)).

[0133] Communication interface 614 includes transceiver-like components (e.g., a transceiver and / or separate receiver and transmitter) that enable device 600 to communicate with other devices, such as via a wired connection, a wireless connection, or a combination of wired and wireless connections. Communication interface 614 can allow device 600 to receive information from and / or provide information to another device. For example, communication interface 614 may include an Ethernet interface, an optical interface, a coaxial interface, an infrared interface, a radio frequency (RF) interface, a universal serial bus (USB) interface, a Wi-Fi interface, a cellular network interface, etc.

[0134] Device 600 can perform one or more processes described herein. Device 600 can perform these processes based on software instructions stored in a non-transitory computer-readable medium (such as memory 606 and / or storage component 608) executed by processor 604. Computer-readable media are defined herein as non-transitory memory devices. Memory devices include memory space within a single physical storage device or memory space distributed across multiple physical storage devices.

[0135] Software instructions may be read into memory 606 and / or storage component 608 via communication interface 614 from another computer-readable medium or from another device. When executed, the software instructions stored in memory 606 and / or storage component 608 may cause processor 604 to perform one or more processes described herein. Additionally or alternatively, hard-wired circuitry may be used in place of or in combination with software instructions to perform one or more processes described herein. Therefore, the embodiments described herein are not limited to any particular combination of hardware circuitry and software.

[0136] Figure 6 The number and arrangement of components shown are provided as an example. In reality, with... Figure 6 Compared to those shown, device 600 may include additional components, fewer components, different components, or components arranged differently. Additionally or alternatively, a set of components of device 600 (e.g., one or more components) may perform one or more functions described as being performed by another set of components of device 600.

[0137] The foregoing disclosure provides illustrations and descriptions, but is not intended to be exhaustive or to limit the embodiments to the precise forms disclosed. Modifications and variations can be made based on the foregoing disclosure, or modifications and variations can be obtained from the practice of the embodiments.

[0138] This document describes several embodiments in conjunction with thresholds. As used herein, depending on the context, satisfying a threshold can mean a value greater than the threshold, more than the threshold, higher than the threshold, greater than or equal to the threshold, less than the threshold, less than the threshold, lower than the threshold, less than or equal to the threshold, equal to the threshold, etc.

[0139] Some user interfaces have been described herein and / or illustrated in the accompanying drawings. User interfaces may include graphical user interfaces, non-graphical user interfaces, text-based user interfaces, etc. A user interface can provide information for display. In some embodiments, a user can interact with the information, such as by providing input via input components of a device that provides the user interface for display. In some embodiments, the user interface may be configured by the device and / or the user (e.g., a user can change the size of the user interface, the information provided via the user interface, the position of the information provided via the user interface, etc.). Additionally or alternatively, the user interface may be pre-configured as a standard configuration, a specific configuration based on the type of device on which the user interface is displayed, and / or a set of configurations based on the capabilities and / or specifications associated with the device on which the user interface is displayed.

[0140] Clearly, the systems and / or methods described herein can be implemented in various forms of hardware, firmware, and / or combinations of hardware and software. The actual dedicated control hardware or software code used to implement these systems and / or methods does not limit the embodiments. Therefore, this document describes the operation and behavior of the systems and / or methods without reference to specific software code—it should be understood that software and hardware can be used to implement the system and / or method based on the description herein.

[0141] Unless explicitly stated otherwise, the elements, actions, or instructions used herein should not be construed as critical or necessary. Furthermore, as used herein, the articles “a” and “one” are intended to include one or more items and may be used interchangeably with “one or more.” Additionally, as used herein, the term “set (group)” is intended to include one or more items (e.g., related items, unrelated items, a combination of related and unrelated items, etc.) and may be used interchangeably with “one or more.” Where only one item is referred to, the phrase “only one” or similar language is used. Furthermore, as used herein, the terms “having” and the like are intended to be open-ended terms. Additionally, unless explicitly stated otherwise, the phrase “based on” is intended to mean “at least partially based on.”

[0142] While all inventions have been described by way of various embodiments, and while these embodiments have been described in considerable detail, the applicant does not intend to limit the scope of the appended claims or restrict them in any way to such details. Other advantages and modifications will be apparent to those skilled in the art. Therefore, the invention is not, in its broader aspects, limited to the specific details, representative devices and methods, and illustrative examples shown and described. Thus, deviations from these details may be made without departing from the spirit or scope of the applicant's overall inventive concept.

Claims

1. A method for recovering one or more target commodities from a material included in a composite component of a wind turbine, the method comprising: Material data is received by a computing device, the material data including quality grade data indicating the quality grade of the corresponding material included in the composite component; The computing device receives product data associated with a plurality of candidate products that can be recovered from one or more materials of the composite component; The computing device determines the expected profitability of each of the plurality of corresponding candidate goods, wherein quality grade data of the corresponding materials and commodity data of the plurality of candidate goods are provided as input to a data model to enable the data model to determine the expected profitability of each of the plurality of corresponding candidate goods, and wherein the data model has been trained using machine learning based on the following: Historical quality grade data indicating the quality grade of materials included in composite components, and Historical product data for candidate products made from the materials in those composite components; The computing device determines recommendations based on the expected profitability, the recommendations indicating the one or more target commodities to be restored using the corresponding materials for the composite component; The recommendation is delivered from the computing device to another device or recipient; and The target product is recovered from the material within the wind turbine composite component in a manner consistent with the recommendations.

2. The method according to claim 1, wherein, The historical product data for the candidate products includes sales price and sales volume data from online marketplaces, one or more of the candidate products being sold in the online marketplaces, and wherein determining the expected profitability includes: Using the data model, the expected profitability of candidate products among the plurality of candidate products is determined, based at least in part on sales price and sales volume data from the online marketplace.

3. The method according to claim 1 or 2, wherein, Determining the expected profitability of a candidate product among the plurality of candidate products includes: The data model is used to determine the expected costs associated with restoring the candidate commodity using one or more materials from the composite component. The data model is used to determine the expected selling price of the candidate products, and The expected profitability of the candidate product is determined based on the expected cost and the expected selling price.

4. The method according to claim 3, wherein, Determining the expected selling price includes: The expected sales price is determined based on the historical sales prices of the candidate products and the historical sales prices of non-recycled products that share one or more characteristics with the candidate products.

5. The method according to claim 3 or 4, wherein, Determining the expected selling price includes: Process the quality grade data to identify the quality grade of the material, and The expected selling price is determined at least in part based on the quality grade of the material.

6. The method according to claim 3 or 4, wherein, Determining the expected selling price includes: The pricing adjustment amount is determined based on the fact that the candidate product is a recycled product, and The expected selling price is determined at least in part based on the pricing adjustment amount.

7. The method according to any one of the preceding claims, wherein, The data model has been trained using historical market data corresponding to the markets of the candidate products among the plurality of candidate products, and wherein determining the expected profitability of the candidate products includes: Based on the historical market data, determine one or more indicators of market change for the candidate products, and The expected profitability of the candidate product is determined at least in part based on one or more of the change indicators.

8. The method according to claim 7, wherein, The one or more change indicators include at least one of the following: Indicators associated with changes in laws or regulations in the geographical region corresponding to the location of the composite component. An indicator associated with the reduction in carbon dioxide emissions resulting from replacing non-recyclable goods with the candidate goods, wherein the non-recyclable goods share one or more characteristics with the candidate goods. Indicators associated with changes in the transportation costs of the candidate goods. Indicators associated with the production location of the candidate product, or Indicators associated with the sales position of the candidate products.

9. The method according to any one of the preceding claims, wherein, The data model has been trained using historical market data from one or more markets corresponding to the respective candidate products, and wherein determining the profitability of the candidate products includes: The historical market data is processed to determine the maturity level of the market to which the candidate products belong. The selection of general or specific machine learning features is based on the market's maturity level. The profitability of the candidate product is determined using the selected features.

10. The method according to any one of the preceding claims, wherein, Determining the recommendations includes: A set of instructions is defined, which specifies the alteration of one or more materials in the composite component such that the target product is recovered from the materials.

11. The method according to any one of the preceding claims, wherein, The composite component is made of cured epoxy resin, and the target product includes one or more of the following: Particulate resin matrix, One or more chemically depolymerized monomers, and One or more chemically depolymerized oligomers; and The determination of the recommendation includes: It is recommended to restore at least one of the following: the particulate resin matrix, the one or more chemically depolymerized monomers, and the one or more chemically depolymerized oligomers.

12. The method according to any one of the preceding claims, wherein, Determining the recommendations includes: A set of chemical processing instructions is determined, the set of chemical processing instructions specifying the alteration of one or more materials in the composite component in a manner that restores the target product from the materials.

13. An apparatus comprising: One or more memory units; as well as One or more processors, the one or more processors being communicatively coupled to the one or more memories to: Receive material data, said material data including quality grade data indicating the quality grade of the corresponding materials included in the composite components of the wind turbine; Receive commodity data of multiple candidate commodities that can be recovered from one or more materials of the composite component; Determine the expected profitability of each of the plurality of corresponding candidate products, wherein quality grade data of the corresponding materials and product data of the plurality of candidate products are provided as input to a data model, so that the data model determines the expected profitability of each of the plurality of corresponding candidate products, and wherein the data model has been trained using machine learning based on the following: Historical quality grade data indicating the quality grade of materials included in composite components, and Historical product data of candidate products made from the materials in the composite component; Recommendations are determined based on the expected profitability, and the recommendations indicate one or more target commodities to be restored using the corresponding materials for the composite component; and The recommendation is delivered to another device or recipient.

14. A non-transitory computer-readable medium storing instructions, the instructions comprising: One or more instructions, which, when executed by one or more processors, cause the one or more processors to: Receive material data, said material data including quality grade data indicating the quality grade of the corresponding materials included in the composite components of the wind turbine; Receive commodity data of multiple candidate commodities that can be recovered from one or more materials of the composite component; Determine the expected profitability of each of the plurality of corresponding candidate products, wherein quality grade data of the corresponding materials and product data of the plurality of candidate products are provided as input to a data model, so that the data model determines the expected profitability of each of the plurality of corresponding candidate products, and wherein the data model has been trained using machine learning based on the following: Historical quality grade data indicating the quality grade of materials included in composite components, and Historical product data of candidate products made from the materials in the composite component; Recommendations are determined based on the expected profitability, and the recommendations indicate one or more target commodities to be restored using the corresponding materials for the composite component; and The recommendation is delivered to another device or recipient.

Images