Granted Patent B2

US 12,405,603 · App. 18/423,268 · Granted Sep 2, 2025

Inventors: Zehua Shao (Chengdu, CN); Haitang Xiang (Chengdu, CN); Bin Liu (Chengdu, CN); Yuefei Wu (Chengdu, CN); Lei Zhang (Chengdu, CN)

Assignee: CHENGDU QINCHUAN IOT TECHNOLOGY CO., LTD.

G05B19/41875G05B19/41835

Abstract

Claims (56)

1. An industrial Internet of Things (IoT) for determining repairability of a defective product, including: an obtaining module, a total correction cost determination module, and a defective product processing module, wherein

the obtaining module is configured to obtain defective product data;

the total correction cost determination module is configured to:

in response to a determination that a number of the defective product is larger than 1, perform a filtering operation on a defective product vector of the defective product to obtain a first defective product vector and a second defective product vector, the defective product vector being constructed based on the defective product data, wherein the first defective product vector is a filtered-out defective product vector, and the second defective product vector is a defective product vector left after filtering;

determine, based on the first defective product vector, a first total correction cost;

cluster the second defective product vector to determine at least one cluster center set;

for each of the at least one cluster center set, determine, based on one or more center set features, a number of raw material and manpower required by the cluster center set through a prediction model, the prediction model being a machine learning model; wherein the prediction model is obtained through training based on a plurality of labeled training samples, and a training process of the prediction model includes:

inputting the plurality of labeled training samples to an initial prediction model, constructing a loss function by the labels and an output result of the initial prediction model, and updating a parameter of the initial prediction model iteratively based on the loss function; wherein when the loss function of the initial prediction model satisfies a preset condition, the training process is completed, and a trained prediction model is obtained; and the training samples including sample center set features of a plurality of sample cluster center sets, and the labels indicating a number of raw material and manpower required for the sample cluster center sets;

determine, based on the number of raw material and the manpower required by the each of the at least one cluster center set, at least one second total correction cost; and

determine, based on the first total correction cost and the at least one second total correction cost, a total correction cost; and

the defective product processing module is configured to determine, based on the total correction cost and a preset cost, whether the defective product is repairable, and perform repair of the defective product based on the determination that the defective product is repairable.

2. The industrial IoT of claim 1 , wherein the one or more center set features include a target cluster center, a number of defective product vectors in the cluster center set, a variance of the defective product vectors in the cluster center set, at least one correction link of the cluster center set, and a device parameter, a type of raw material, and a labor participation of each of the at least one correction link.

3. The industrial IoT of claim 2 , wherein the prediction model is a long short term memory model, the at least one correction link of the cluster center set includes a first correction link and a second correction link, the first correction link is a correction link before the second correction link, the device parameter, the type of raw material, and the labor participation of the second correction link input by the long short term memory model are related to the device parameter, the type of raw material, and the labor participation of the first correction link.

4. The industrial IoT of claim 1 , wherein the total correction cost determination module is further configured to:

for each of the first defective product vector,

determine, based on the first defective product vector and a historical defective product vector library, a second reference vector;

determine, based on the second reference vector, a total correction cost corresponding to the each of the first defective product vector; and

determine, based on the total correction cost corresponding to the each of the first defective product vector, the first total correction cost.

5. The industrial IoT of claim 1 , comprising: a user platform, a service platform, a management platform, a sensing network platform, and an object platform that interact from top to bottom, wherein the obtaining module is performed by the object platform, the total correction cost determination module is performed by the sensing network platform and the management platform, and the defective product processing module is performed by the user platform, the service platform, the management platform, the sensing network platform, and the object platform;

the service platform, the management platform, and the sensing network platform are all arranged in a front-sub-platform layout; the front-sub-platform layout refers to that a corresponding platform is provided with a general platform and a plurality of sub-platforms, the plurality of sub-platforms respectively store and process data of different types and different receiving objects sent by a lower platform, the general platform stores and processes the data of the plurality of sub-platforms after summary, and transmits the data of the plurality of sub-platforms to an upper platform;

the object platform is configured as a product detection device of intelligent manufacture; when the product detection device detects the defective product, the product detection device packs defective product information and a defective product parameter as the defective product data, and sends the defective product data to the management platform;

the management platform is configured to determine the total correction cost based on the defective product data, compare the total correction cost with the preset cost of the general platform of the management platform, and perform the preset operation based on a comparison result, wherein the preset cost is a single-piece manufacturing cost of a product corresponding to the defective product.

6. The industrial IoT of claim 5 , wherein the preset operation includes:

in response to the comparison result that the total correction cost is lower than the preset cost, determining that the defective product is repairable, the general platform of the management platform issuing a correction instruction to the corresponding sub-platform of the management platform, the general platform of the sensing network platform, the sub-platform of the sensing network platform, and the product detection device based on a first description item, the product detection device receiving the correction instruction and assigning the corresponding product to a defective product correction assembly line based on the first description item.

7. The industrial IoT of claim 5 , wherein the defective product information at least includes a name, a number, and a type of the product corresponding to the defective product; and the defective product parameter at least includes a defective product parameter number and an error of the product corresponding to the defective product.

8. The industrial IoT of claim 5 , wherein when the total correction cost is greater than the preset cost, the general platform of the management platform is further configured to:

issue a processing instruction to the corresponding sub-platform of the management platform, the general platform of the sensing network platform, the sub-platform of the sensing network platform, and the product detection device, and the product detection device perform a defective product processing on the corresponding defective product based on the processing instruction.

9. A control method of an industrial Internet of Things (IoT) for determining repairability of a defective product, comprising:

obtaining defective production data;

determining that a number of the defect product is larger than 1, in response to determining that a number of the defective product is larger than 1, performing a filtering operation on a defective product vector of the defective product to obtain a first defective product vector and a second defective product vector, the defective product vector being constructed based on the defective product data, wherein the first defective product vector is a filtered-out defective product vector, and the second defective product vector is a defective product vector left after filtering;

determining, based on the first defective product vector, a first total correction cost;

clustering the second defective product vector to determine at least one cluster center set;

for each of the at least one cluster center set, determining, based on one or more center set features, a number of raw material and manpower required by the cluster center set through a prediction model, the prediction model being a machine learning model; wherein the prediction model is obtained through training based on a plurality of labeled training samples, and a training process of the prediction model includes:

inputting the plurality of labeled training samples to an initial prediction model, constructing a loss function by the labels and an output result of the initial prediction model, and updating a parameter of the initial prediction model iteratively based on the loss function;

wherein when the loss function of the initial prediction model satisfies a preset condition, the training process is completed, and a trained prediction model is obtained; and

the training samples including sample center set features of a plurality of sample cluster center sets, and the labels indicating a number of raw material and manpower required for the sample cluster center sets;

determining, based on the number of raw material and the manpower required by the each of the at least one cluster center set, at least one second total correction cost; and

determining, based on the first total correction cost and the at least one second total correction cost, a total correction cost; and

determining, based on the total correction cost and a preset cost, that the defective product is repairable, and performing repair of the defective product based on the determination that the defective product is repairable.

10. The control method of the industrial IoT of claim 9 , wherein the one or more center set features include a target cluster center, a number of defective product vectors in the cluster center set, a variance of the defective product vectors in the cluster center set, at least one correction link of the cluster center set, and a device parameter, a type of raw material, and a labor participation of each of the at least one correction link.

11. The control method of the industrial IoT of claim 10 , wherein the prediction model is a long short term memory model, the at least one correction link of the cluster center set includes a first correction link and a second correction link, the first correction link is a correction link before the second correction link, the device parameter, the type of raw material, and the labor participation of the second correction link input by the long short term memory model are related to the device parameter, the type of raw material, and the labor participation of the first correction link.

12. The control method of the industrial IoT of claim 9 , wherein the determining, based on the first defective product vector, a first total correction cost includes:

for each of the first defective product vector,

determining, based on the first defective product vector and a historical defective product vector library, a second reference vector;

determining, based on the second reference vector, a total correction cost corresponding to the each of the first defective product vector; and

determining, based on the total correction cost corresponding to the each of the first defective product vector, the first total correction cost.

13. The control method of the industrial IoT of claim 9 , wherein the industrial IoT includes: a user platform, a service platform, a management platform, a sensing network platform, and an object platform that interact from top to bottom;

the service platform, the management platform, and the sensing network platform are all arranged in a front-sub-platform layout; the front-sub-platform layout refers to that a corresponding platform is provided with a general platform and a plurality of sub-platforms, the plurality of sub-platforms respectively store and process data of different types and different receiving objects sent by a lower platform, the general platform stores and processes the data of the plurality of sub-platforms after summary, and transmits the data of the plurality of sub-platforms to an upper platform;

the object platform is configured as a product detection device of intelligent manufacture; when the product detection device detects the defective product, the product detection device packs defective product information and a defective product parameter as the defective product data, and sends the defective product data to the management platform;

the management platform is configured to determine the total correction cost based on the defective product data, compare the total correction cost with the preset cost of the general platform of the management platform, and perform the preset operation based on a comparison result, wherein the preset cost is a single-piece manufacturing cost of a product corresponding to the defective product.

14. The control method of the industrial IoT of claim 13 , wherein the preset operation includes:

in response to the comparison result that the total correction cost is lower than the preset cost, determining that the defective product is repairable, the general platform of the management platform issuing a correction instruction to the corresponding sub-platform of the management platform, the general platform of the sensing network platform, the sub-platform of the sensing network platform, and the product detection device based on a first description item, the product detection device receiving the correction instruction and assigning the corresponding product to a defective product correction assembly line based on the first description item.

15. The control method of the industrial IoT of claim 13 , wherein the defective product information at least includes a name, a number, and a type of the product corresponding to the defective product; and the defective product parameter at least includes a defective product parameter number and an error of the product corresponding to the defective product.

16. The control method of the industrial IoT of claim 13 , wherein the preset operation includes:

the general platform of the management platform issuing a processing instruction to the corresponding sub-platform of the management platform, the general platform of the sensing network platform, the sub-platform of the sensing network platform, and the product detection device, and the product detection device performing a defective product processing on the corresponding defective product based on the processing instruction.

17. A non-transitory computer-readable storage medium storing computer instructions, wherein when reading the computer instructions in the storage medium, a computer implements the method of claim 9 .

Assignments (1)

Priority Claims (1)

Continuity (2)

References Cited (22)