AI Refrigerator Dual Diagnosis for Abnormality Cause Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional refrigerators fail to accurately diagnose abnormalities, leading to food and economic damage due to unrecognized issues and inefficient service technician visits.
Innovation Solution
An intelligent refrigerator system that uses a deep-learning-based first diagnosis engine to determine normal or abnormal operation states and a second diagnosis engine to identify the cause of abnormalities, providing corrective actions to customers and preemptive remote responses, and requesting material and technician dispatch as needed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional refrigerators operate without advanced diagnosis systems, then device complexity is reduced, but reliability deteriorates due to unrecognized abnormalities causing food damage
Solution Approach 1:
The diagnosis system is segmented into two distinct engines: a first diagnosis engine that performs initial abnormality detection using simple threshold comparisons, and a second diagnosis engine that performs detailed cause analysis only when abnormalities are detected. This segmentation allows the system to achieve high reliability without requiring complex diagnostic capabilities to run continuously, thus resolving the contradiction between reliability and device complexity.
Solution Approach 2:
The first diagnosis engine performs preliminary screening of operation information against predetermined reference values before triggering the more complex second diagnosis engine. This preliminary action filters out normal operations early, preventing unnecessary activation of complex diagnostic routines and maintaining system simplicity while ensuring abnormalities are caught for further analysis.
2Measurement precision
If a single diagnosis engine is used to identify all abnormality causes, then device complexity is reduced, but measurement precision deteriorates due to inability to accurately diagnose specific causes
Solution Approach 1:
The diagnostic function is divided into two specialized engines: the first engine specializes in detecting whether abnormalities exist by comparing operation data against reference thresholds, while the second engine specializes in analyzing the specific causes of detected abnormalities. This functional segmentation allows each engine to be optimized for its specific task, achieving high measurement precision without requiring a single overly complex diagnostic system.
Solution Approach 2:
The first diagnosis engine acts as an intermediary that filters and prepares abnormality data before passing it to the second diagnosis engine. This intermediary role ensures that the complex second engine only processes relevant abnormal cases, improving its diagnostic precision while keeping the overall system architecture manageable through clear separation of concerns.
3Loss of time
If service technicians are dispatched without accurate abnormality diagnosis, then response time is reduced, but loss of time increases due to repeated visits for re-diagnosis
Solution Approach 1:
The dual-engine diagnosis system provides detailed feedback about abnormality causes by analyzing operation information through both the initial detection engine and the detailed analysis engine. This feedback mechanism generates comprehensive diagnostic reports that include specific cause identification, enabling service technicians to prepare appropriate solutions before arrival and reducing the need for repeated visits, thus addressing both information accuracy and time efficiency.
Solution Approach 2:
The system performs preliminary detailed diagnosis through the second diagnosis engine before service technician dispatch, pre-identifying abnormality causes and preparing diagnostic information in advance. This preliminary action ensures that technicians receive accurate cause information ahead of time, allowing them to bring appropriate parts and solutions, thereby eliminating wasted time from repeated diagnostic visits.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Improves diagnosis accuracy, reduces food and economic losses by enabling timely corrective actions and efficient resource allocation for abnormality resolution.
Implementation Method 1
a compressor (53) connected to compress the refrigerant
Implementation Method 2
a condenser (54) connected to a discharge side of the compressor (53)
Implementation Method 3
a first evaporator (51) branched from the condenser (54) and connected to a suction side of the compressor (53)
Implementation Method 4
a refrigerant switching valve (56) installed at a point branched from an outlet of the condenser (54) to the first evaporator (51) and a second evaporator (52) to control a flow direction of the refrigerant
Data Source
AI summary
Disclosed is an artificial refrigerator. The artificial refrigerator according to the present disclosure includes at least one sensor for sensing an operation state of the refrigerator and obtaining operation information about the operation state of the refrigerator and a processor that determines whether the operation state of the refrigerator is normal or abnormal using a deep-learning-based first diagnosis engine based on the operation information obtained using the at least one sensor and diagnoses, upon determination of the abnormality, a cause of the abnormality using a deep-learning-based second diagnosis engine. In the artificial refrigerator of the present invention, at least one of a user terminal or a server may be associated with an artificial intelligence module, a drone (Unmanned Aerial Vehicle, UAV) robot, an augmented reality (AR) device, a virtual reality (VR) device, a device related to a 5G service, and the like.