System and methods for using machine learning to make intelligent recycling decisions
A device may receive historical operational data for a mechanical system, such as a rotor blade of a wind turbine. The device may determine one or more quality grades for each of one or more materials of the system, e.g., the rotor blade. The one or more quality grades may be determined by using a data model to process the historical operational data. The data model may be trained using machine learning based on one or both of historical operational data for similar systems, e.g., other rotor blades, and end-of-life (EOL) testing data for the same. The device may determine a recycling recommendation based on the one or more quality grades. The recycling recommendation may include instructions relating to recycling the one or more materials. The device may deliver the recycling recommendation to another device or recipient.
1. A method of making a recycling recommendation for a rotor blade of a wind turbine, comprising:
receiving, by a computing device, historical operational data for the rotor blade;
receiving, by the computing device, historical materials data identifying composite materials of the rotor blade;
determining, by the computing device, quality grades for materials included in respective composite materials of the rotor blade, wherein the quality grades are determined by using a data model to process the historical operational data and the historical materials data, and wherein the data model has been trained using machine learning based on one or more of historical operational data for other rotor blades, historical materials data for composite materials of the other rotor blades, and historical end-of-life (EOL) testing data for the other rotor blades, wherein the quality grades for a composite material, of the respective composite materials, include a first set of one or more quality grades for a first material of the composite material and a second set of one or more quality grades for a second material of the same composite material, the first set of one or more quality grades being different than the second set of one or more quality grades;
determining, by the computing device, the recycling recommendation based on the quality grades, wherein the recycling recommendation includes a set of cut instructions indicating to separate the first material from the second material using measurement data that identifies boundaries of the first material and boundaries of the second material;
delivering, from the computing device, the recycling recommendation to a controller that provides the set of cut instructions that include the measurement data to equipment configured to perform a cutting task; and
in response to receiving the set of cut instructions, cutting, by the equipment, the composite material of the rotor blade such that the first material with the first set of one or more quality grades is separated from the second material with the second set of one or more quality grades.
2. The method of claim 1 , wherein determining the first set of one or more quality grades for the first material and the second set of one or more quality grades for the second material, comprises:
providing the historical operational data and the historical materials data as input to the data model to cause the data model to output a first expected reusability score for the first material and a second expected reusability score for the second material,
determining a first quality grade for the first material based on the first expected reusability score, and
determining a second quality grade for the second material based on the second expected reusability score.
3. The method of claim 2 , wherein the first expected reusability score and the second expected reusability score are based on at least one of:
an expected residual strength of the material,
an expected structural integrity of the material, or
expected end-of-life (EOL) fiber lengths of fibers associated with the particular material.
4. The method of claim 1 , wherein the EOL testing data includes reusability scores for materials of the other rotor blades, and wherein respective reusability scores represent a degree to which a material or a portion of that material is reusable.
5. The method of claim 1 , wherein the historical materials data includes measurement data identifying boundaries of components of the other rotor blades and data identifying boundaries of the materials included in the respective composite materials, and wherein the data model is trained to associate each respective boundary and/or subset of a boundary with a reusability score.
6. The method of claim 1 , wherein the historical operational data for the rotor blade includes at least one of installation data, service data, or weather data, and wherein the historical operational data for the other rotor blades that is used to train the data model includes daily operations data and at least one of installation data, service data, or weather data.
7. The method of claim 1 , wherein determining the recycling recommendation comprises:
determining a set of bin placement instructions indicating to sort the first material and the second material into different recycling containers where each respective recycling container corresponds to a specific quality grade.
8. The method of claim 1 , wherein determining the first set of one or more quality grades comprises:
determining a first quality grade for a first portion of the first material, and
determining a second quality grade for a second portion of the same material, wherein the first quality grade of the first portion is different than the second quality grade of the second portion.
9. The method of claim 8 , wherein determining the recycling recommendation comprises:
determining a set of bin placement instructions indicating to place the first portion and the second portion of the same material into different recycling containers.
10. The method of claim 8 , wherein determining the recycling recommendation comprises:
determining another set of cut instructions indicating to separate the first portion of the first material from the second portion of the first material;
wherein delivering the recycling recommendation comprises:
delivering said recommendation to the controller or to another controller such that the controller or the other controller provides the set of cut instructions to equipment configured to perform the cutting task; and
in response to receiving the set of cut instructions, cutting, by the equipment configured to perform the cutting task, the first material such that the first portion with the first quality grade is separated from the second portion with the second quality grade.
11. A non-transitory computer-readable medium storing instructions, the instructions comprising:
one or more instructions that, when executed by one or more processors, cause the one or more processors to:
receive historical operational data for a rotor blade of a wind turbine;
receive historical materials data identifying composite materials of the rotor blade;
train a data model in said memory using machine learning based on at least one of historical operational data for other rotor blades, historical materials data for composite materials of the other rotor blades, and end-of-life (EOL) testing data for the other rotor blades,
determine quality grades for materials included in respective composite materials of the rotor blade, wherein the quality grades are determined by using said data model to process the historical operational data and the historical materials data, wherein the quality grades include at least one of:
a first quality grade for a first material of a composite material, of the respective composite materials, and a second quality grade for a second material of the same composite material, the first quality grade being different than the second quality grade, and
a third quality grade for a first portion of the first material and a fourth quality grade for a second portion of the first material;
determine a recycling recommendation based on the quality grades, wherein the recycling recommendation includes at least one of:
a first set of cut instructions indicating to separate first material from the second material using first measurement data that identifies boundaries of the first material and boundaries of the second material, and
a second cut instructions indicating to separate the first portion of the first material from the second portion of the first material using second measurement data that identifies boundaries of the first portion and boundaries of the second portion; and
deliver the recycling recommendation to a controller that provides the first set of cut instructions that include the first measurement data and/or the second set of cut instructions that include the second measurement data to equipment configured to perform a cutting task,
wherein the equipment, in response to receiving the first set of cut instructions, cuts the composite material of the rotor blade such that the first material with the first quality grade is separated from the second material with the second quality grade, and
wherein the equipment, in response to receiving the second set of cut instructions, cuts the first material, which is part of the composite material of the rotor blade, such that the first portion with the third quality grade is separated from the second portion with the fourth quality grade.
12. A device, comprising:
one or more memories; and
one or more processors, communicatively coupled to the one or more memories, to:
receive historical operational data for a rotor blade of a wind turbine;
receive historical materials data identifying composite materials of the rotor blade;
determine one or more quality grades for materials included in respective composite materials of the rotor blade, wherein the quality grades are determined by using a data model to process the historical operational data and the historical operational data, and wherein the data model has been trained using machine learning based on at least one of historical operational data for other rotor blades, historical materials data for composite materials of the other rotor blades, and end-of-life (EOL) testing data for the other rotor blades, wherein the quality grades for a composite material, of the respective composite materials, include sets of one or more quality grades for each material of the composite material, wherein a set of quality grades for a first material include a first quality grade for a first portion of the first material and a second quality grade for a second portion of the first material;
determine a recycling recommendation based on the one or more quality grades, wherein the recycling recommendation includes a set of cut instructions indicating to separate the first portion of the first material from the second portion of the first material using measurement data that identifies boundaries of the first portion and boundaries of the second portion; and
deliver the recycling recommendation to a controller that provides the set of cut instructions that include the measurement data to equipment configured to perform a cutting task, wherein the equipment, in response to receiving the set of cut instructions, cuts the first material, which is part of the composite material of the rotor blade, such that the first portion with the first quality grade is separated from the second portion with the second quality grade.
13. The device of claim 12 , wherein the recycling recommendation further includes a set of bin placement instructions indicating to place the first portion of the first material, the second portion of the first material, and the second material into different recycling containers;
wherein delivering the recycling recommendation comprises:
delivering the set of bin placement instructions to the controller or to another controller such that the controller or other controller provides the set of bin placement instructions to equipment configured to perform a bin placement task; and
in response to receiving the set of bin placement instructions, placing, by the equipment configured to perform the bin placement task, the first portion of the first material, the second portion of the first material, and the second material into different recycling containers.