Manufacturing a product using causal models
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for optimizing a process of manufacturing a product. In one aspect, the method comprises repeatedly performing the following: i) selecting a configuration of input settings for manufacturing a product, based on a causal model that measures causal relationships between input settings and a measure of a quality of the product; ii) determining the measure of the quality of the product manufactured using the configuration of input settings; and iii) adjusting, based on the measure of the quality of the product manufactured using the configuration of input settings, the causal model.
1. A method comprising:
repeatedly performing the following:
selecting a configuration of input settings for manufacturing a product, based on a causal model that measures causal relationships between input settings and a measure of a quality of the product, wherein control settings are assigned to different procedural instances that allow blocked groups to later be identified in order to compute impact measurements between blocked groups;
determining the measure of the quality of the product manufactured using the configuration of input settings;
adjusting, based on the measure of the quality of the product manufactured using the configuration of input settings, the causal model; and
re-computing the causal model by computing confidence intervals and d-scores that are based upon the computed impact measurements between the blocked groups.
2. The method of claim 1 , wherein:
selecting a configuration of input settings for manufacturing a product comprises selecting the configuration of input settings based on a set of internal control parameters, and
the method further comprises adjusting the internal control parameters based on the measure of the quality of the product manufactured using the configuration of input settings.
3. The method of claim 1 , wherein the measure of the quality of the product comprises one or more of the following:
one or more physical characteristics of the product;
a yield of the product;
an amount of raw materials used; or
a manufacturing time.
4. The method of claim 1 , wherein the input settings for manufacturing the product comprise one or more of the following:
a selection of raw materials;
one or more settings related to product design of the product; or
one or more settings related to a manufacturing process.
5. The method of claim 1 , wherein:
selecting the configuration of input settings comprises selecting the configuration based on the causal model and respective measures of a predetermined set of external variables; and
the method further comprises adjusting internal control parameters that parameterize an impact of the predetermined set of external variables on the selecting of the configuration.
6. The method of claim 5 , wherein the predetermined set of external variables comprises one or more of the following:
a measure of dust levels during manufacturing;
a measure of air flow during manufacturing;
a measure of lighting during manufacturing;
a temperature during manufacturing; or
a humidity during manufacturing.
7. The method of claim 1 , wherein the product is a batch of roofing granules.
8. The method of claim 1 , wherein the product is a batch of asphalt shingles.
9. The method of claim 1 , wherein selecting a configuration of input settings for manufacturing a product comprises selecting a configuration of input settings for dispensing adhesive material.
10. The method of claim 9 , wherein the measure of the quality of the product comprises one or more of the following:
one or more dimensions of a beads of the adhesive material relative to a set of respective desired dimensions;
a location of a bead of the adhesive material relative to a desired location;
a time duration of dispensing a given bead of the adhesive material;
a time between dispensing a first bead and dispensing a second bead of the adhesive material; or
a repeatability or CPK.
11. The method of claim 10 , wherein the dimensions of the beads of the adhesive material comprise one or more of:
a height of the beads;
a width of the beads; or
a cross-sectional area of the beads.
12. The method of claim 9 , wherein the input settings comprise one or more of the following:
one or more input settings related to a robot dispensing the adhesive material;
one or more input settings related to a valve from which the adhesive material is dispensed; or
one or more input settings related to an environment in which the adhesive material is dispensed.
13. The method of claim 12 , wherein the input settings related to the position of the robot dispensing the adhesive material comprise one or more of the following:
a distance of the robot from a substrate surface;
a location of the robot relative to a desired location;
a temperature of a dispense head of the robot; or
one or more motion parameters for the robot.
14. The method of claim 13 , wherein the motion parameters for the robot comprise one or more of the following:
an in-plane speed of the robot;
a normal speed of the robot;
a rotational speed of the robot;
an in-plane acceleration of the robot;
a normal acceleration of the robot; or
a rotational acceleration of the robot.
15. The method of claim 12 , wherein the input setting related to the valve from which the adhesive material is dispensed comprise one or more of the following:
a flow rate of the adhesive material;
a timing of opening and closing the valve; or
an applied back pressure of the valve.
16. The method of claim 12 , wherein the input settings related to the environment in which the adhesive material is dispensed comprise one or more of the following:
an ambient temperature of the environment; or
a humidity of the environment.
17. A system comprising one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to repeatedly perform the following operations:
select a configuration of input settings for manufacturing a product, based on a causal model that measures causal relationships between input settings and a measure of a quality of the product, wherein control settings are assigned to different procedural instances that allow blocked groups to later be identified in order to compute impact measurements between blocked groups;
determine the measure of the quality of the product manufactured using the configuration of input settings;
adjust, based on the measure of the quality of the product manufactured using the configuration of input settings, the causal model; and
re-compute the causal model by computing confidence intervals and d-scores that are based upon the computed impact measurements between the blocked groups.
18. One or more non-transitory computer-readable storage media storing instructions that when executed by one or more computers cause the one or more computers to repeatedly perform the following:
selecting a configuration of input settings for manufacturing a product, based on a causal model that measures causal relationships between input settings and a measure of a quality of the product, wherein control settings are assigned to different procedural instances that allow blocked groups to later be identified in order to compute impact measurements between blocked groups;
determining the measure of the quality of the product manufactured using the configuration of input settings;
adjusting, based on the measure of the quality of the product manufactured using the configuration of input settings, the causal model; and
re-computing the causal model by computing confidence intervals and d-scores that are based upon the computed impact measurements between the blocked groups.