Cognitive Test Advisor for Parallel Manufacturing Execution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manufacturing test plans often face delays due to individual test failures, leading to downstream bottlenecks and inefficiencies in the manufacturing process, as each test must be completed sequentially until all are resolved.
Innovation Solution
A cognitive test advisor system that analyzes structured and unstructured data using machine learning to identify potential test failure repair actions, prioritizes these actions based on historical data and user feedback, and dynamically adjusts the test plan to bypass impacted steps, allowing parallel execution of unaffected tests while resolving the failure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If tests are applied separately in series as part of a test failure plan, then each test can be individually executed and monitored, but the entire test plan is delayed until the test failure is resolved
Solution Approach 1:
The patent segments the test plan into independent test cases that can be executed in parallel. When a test failure occurs, only the failed test and its related dependencies are paused, while other independent tests continue to execute. This segmentation allows the system to maintain reliable failure detection for the failed test while minimizing the time loss for the overall test plan by allowing concurrent execution of unaffected tests.
Solution Approach 2:
The patent implements dynamic test plan execution by dynamically adjusting the test execution flow based on real-time test results. When a test failure is detected, the system dynamically identifies dependent tests and either executes them in parallel with modified expectations or skips them appropriately. This dynamic approach allows the test plan to adapt its execution strategy, maintaining reliability for critical tests while reducing overall completion time through parallel execution of independent tests.
2Reliability
If the entire test plan is delayed until a test failure is resolved, then comprehensive testing can be ensured, but downstream bottlenecks occur in the manufacturing process
Solution Approach 1:
The patent segments the manufacturing process into parallel testing streams. When a test failure occurs in one stream, only that specific test stream is paused for resolution, while other manufacturing streams continue to proceed with their testing. This segmentation ensures that testing completeness is maintained for the failed test while preventing downstream bottlenecks by allowing other manufacturing processes to continue uninterrupted.
Solution Approach 2:
The patent introduces an intermediary test management system that coordinates between different test streams and manufacturing processes. This intermediary system monitors test failures, identifies dependent tests, and manages the parallel execution strategy. It acts as a mediator that ensures testing completeness for critical tests while maintaining manufacturing throughput by coordinating which tests can proceed in parallel and which must wait for resolution.
3Measurement precision
If tests are executed sequentially to ensure proper dependency handling, then test accuracy is maintained, but test processing efficiency decreases
Solution Approach 1:
The patent implements dynamic test execution that adapts the sequencing strategy based on test dependencies and failure states. For tests with no dependencies or where dependencies have been resolved, the system dynamically enables parallel execution to improve efficiency. For tests with unresolved dependencies or critical accuracy requirements, the system maintains sequential execution to preserve measurement precision. This dynamic approach allows the system to optimize between efficiency and accuracy based on real-time conditions.
Solution Approach 2:
The patent applies different execution strategies to different parts of the test plan based on their specific requirements. Critical tests that require high measurement precision are executed sequentially with strict dependency handling, while less critical or independent tests are executed in parallel for improved efficiency. This local quality approach ensures that each test receives the appropriate execution treatment, maintaining accuracy where needed while improving overall processing efficiency through parallel execution of suitable tests.
Data Source
AI summary
A cognitive test advisor facility is provided to identify repair action recommendations. The facility receives a user input regarding a test failure, and generates an expanded search input by identifying additional, alternative words for the user input. A database(s) is searched for test failure records relevant to keywords of the expanded search input, and relevant test failure records are prioritized using a relationship strength score based, at least in part, on relationship of the test failure records to the expanded search input. The facility detects test failure records from the searching having a relationship strength score higher than a threshold value, and analyzes the detected test failure records to identify potential test repair actions. Based on the analyzing, the facility generates a solution priority list including one or more suggested test repair actions for the test failure, and provides the solution priority list to the user.