METHOD AND SYSTEM FOR EARLY DETECTION OF VEHICLE PARTS FAILURE

• US 20180237029A1
• Filed: 02/22/2018
• Published: 08/23/2018
• Est. Priority Date: 02/23/2017
• Status: Active Grant

• Current Assignee: TATA Consultancy Services Limited (Tata Sons Pvt Ltd.)
• Original Assignee: TATA Consultancy Services Limited (Tata Sons Pvt Ltd.)
• Inventors: BANSAL, Vandita, GADWALA, Surendra Babu, JAYARAMAN, Malini, SHARIF, Omar, KALIRAJ, Senthil Kumar
• Granted Patent: US 10,589,749 B2
• Time in Patent Office: Days
• CPC Class Codes: B60W 2050/021 Means for detecting failure or malfunction
• CPC Class Codes: B60W 50/0205 Diagnosing or detecting failures; Failure detection models
• CPC Class Codes: G06Q 10/06375 Prediction of business process outcome or impact based on a proposed change
• CPC Class Codes: G07C 5/0808 Diagnosing performance data testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005

Abstract

System and method for early detection of vehicle parts failure are disclosed. The method includes identifying discriminative rules from unstructured and structured data corresponding to subsystems of a vehicle. Causal parts categories are mapped to the subsystems based on the discriminative rules to obtain a plurality of causal part-subsystem pairs. The causal part categories are representative of vehicle parts responsible for failure of corresponding subsystems. Scores are assigned to the causal part-subsystem pairs based on an occurrence of causal part categories to a corresponding subsystem within a source. An emerging issue score is computed based on the scores, a corresponding weightage associated with the sources of the causal part category, and an extent of coverage of the each causal part in each of the plurality of causal part-subsystem pairs. The emerging issue score is compared with the threshold vehicle part failure score to identify causal part categories associated with vehicle parts failure.

Claims

1. A computer-implemented method for early detection of vehicle parts failure for a vehicle having a plurality of subsystems, the method comprising:

identifying, via one or more hardware processors, a plurality of discriminative rules from an unstructured data and a structured data corresponding to the plurality of subsystems, the unstructured data and a structured data derived from a plurality of sources;

mapping, via the one or more hardware processors, and based on the plurality of discriminative rules, a plurality of causal part categories associated with the structured data and the unstructured data with the plurality of subsystems to obtain a plurality of causal part-subsystem pairs, a causal part-subsystem pair comprising mapping of a causal part category with a corresponding subsystem, and wherein the plurality of causal part categories are representative of vehicle parts responsible for failure of a corresponding subsystem of the plurality of subsystems;

assigning, via the one or more hardware processors, a score to each of the plurality of causal part-subsystem pairs based on the pattern of occurrence of causal part categories corresponding to a subsystem of the plurality of subsystems within a source of the plurality of sources;

computing, via the one or more hardware processors, and corresponding to each causal part category of the plurality of causal part categories, an emerging issue score based on the score assigned to each of the plurality of causal part-subsystem pairs and a corresponding weightage associated with a source of the plurality of sources of the causal part category, and an extent of coverage of the each causal part in each of the plurality of causal part-subsystem pairs; and

identifying, via the one or more hardware processors, one or more causal part categories associated with vehicle parts failure based on a comparison of the emerging issue score with a threshold vehicle part failure score.

2. The method of claim 1, wherein the structured data comprises telematics data.

3. The method of claim 2, further comprising receiving the structured data from a first set of sources of the plurality of sources, the first set of sources comprise a plurality of sensors

4. The method of claim 1, wherein the unstructured data comprises one or more of complaint logs, appointment logs, surveys, opinion expressed by customers on web, and warranty data.

5. The method of claim 1, further comprising updating the plurality of rules based on one or more machine learning models.

6. The method of claim 1, wherein, identifying the one or more causal part categories associated with vehicle parts failure comprises determining the emerging issue score associated with the one or more causal part categories to be greater than or equal to the threshold vehicle part failure score.

7. A system for early detection for vehicle parts failure of a vehicle having a plurality of subsystems, the system comprising:

one or more memories storing instructions; and

one or more hardware processors coupled to said one or more memories, wherein said one or more hardware processors are configured by said instructions to;

identify a plurality of discriminative rules from an unstructured data and a structured data corresponding to the plurality of subsystems, the unstructured data and a structured data derived from a plurality of sources;

map based on the plurality of discriminative rules, a plurality of causal part categories associated with the structured data and the unstructured data with the plurality of subsystems to obtain a plurality of causal part-subsystem pairs, a causal part-subsystem pair comprising mapping of a causal part category with a corresponding subsystem, and wherein the plurality of causal part categories are representative of vehicle parts responsible for failure of a corresponding subsystem of the plurality of subsystems;

assign a score to each of the plurality of causal part-subsystem pairs based on the pattern of occurrence of causal part categories corresponding to a subsystem of the plurality of subsystems within a source of the plurality of sources;

compute, corresponding to each causal part category of the plurality of causal part categories, an emerging issue score based on the score assigned to each of the plurality of causal part-subsystem pairs and a corresponding weightage associated with a source of the plurality of sources of the causal part category, and an extent of coverage of the each causal part in each of the plurality of causal part-subsystem pairs; and

identify one or more causal part categories associated with vehicle parts failure based on a comparison of the emerging issue score with a threshold vehicle part failure score.

8. The system of claim 7, wherein the structured data comprising telematics data.

9. The system of claim 7, one or more hardware processors are further configured by said instructions to receive the structured data from a first set of sources of the plurality of sources, the first set of sources comprise a plurality of sensors.

10. The system of claim 7, wherein the unstructured data comprises one or more of complaint logs, appointment logs, surveys, opinion expressed by customers on web, and warranty data.

11. The system of claim 7, wherein the one or more hardware processors are further configured by said instructions to update the plurality of rules based on one or more machine learning models.

12. The system of claim 7, wherein to identify the one or more causal part categories associated with vehicle parts failure, the one or more hardware processors are configured by said instructions to determine the emerging issue score associated with the one or more causal part categories to be greater than or equal to the threshold vehicle part failure score.

13. The non-transitory computer-readable medium having embodied thereon a computer program for executing, a computer-implemented method for early detection of vehicle parts failure for a vehicle having a plurality of subsystems comprising:

identifying, via one or more hardware processors, a plurality of discriminative rules from an unstructured data and a structured data corresponding to the plurality of subsystems, the unstructured data and a structured data derived from a plurality of sources;

mapping, via the one or more hardware processors, and based on the plurality of discriminative rules, a plurality of causal part categories associated with the structured data and the unstructured data with the plurality of subsystems to obtain a plurality of causal part-subsystem pairs, a causal part-subsystem pair comprising mapping of a causal part category with a corresponding subsystem, and wherein the plurality of causal part categories are representative of vehicle parts responsible for failure of a corresponding subsystem of the plurality of subsystems;

assigning, via the one or more hardware processors, a score to each of the plurality of causal part-subsystem pairs based on the pattern of occurrence of causal part categories corresponding to a subsystem of the plurality of subsystems within a source of the plurality of sources;

computing, via the one or more hardware processors, and corresponding to each causal part category of the plurality of causal part categories, an emerging issue score based on the score assigned to each of the plurality of causal part-subsystem pairs and a corresponding weightage associated with a source of the plurality of sources of the causal part category, and an extent of coverage of the each causal part in each of the plurality of causal part-subsystem pairs; and

identifying, via the one or more hardware processors, one or more causal part categories associated with vehicle parts failure based on a comparison of the emerging issue score with a threshold vehicle part failure score.