Monitoring method of cooling system and monitoring device thereof
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional cooling system monitoring methods fail to detect abnormalities or impending failures in advance, leading to unexpected shutdowns and inefficient maintenance processes.
Innovation Solution
A monitoring method and device utilizing deep learning to establish an abnormality determination model, analyzing temperature data from multiple sensors to predict potential equipment failures and provide early warnings, allowing for proactive maintenance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional pressure switch monitoring is used, then high-low pressure protection is achieved, but abnormality detection capability is insufficient
Solution Approach 1:
The patent replaces the traditional mechanical pressure switch monitoring system with a temperature-based monitoring system using temperature sensors and deep learning algorithms. Temperature sensors are installed at key locations (compressor, evaporator, condenser) to collect thermal data, which is then processed by a deep learning model to detect abnormalities and predict failures, thereby improving detection capability while maintaining protection reliability.
Solution Approach 2:
The patent changes the monitoring parameter from pressure to temperature. By installing temperature sensors at critical components and using deep learning to analyze temperature patterns, the system can detect abnormalities earlier and more accurately than pressure-based systems, resolving the contradiction between protection reliability and abnormality detection difficulty.
2Ease of repair
If copper tube evacuation is performed for pressure switch repair, then compressor maintenance is enabled, but system downtime increases
Solution Approach 1:
The deep learning monitoring system performs preliminary detection of abnormalities and predicts potential failures before they occur. By identifying issues early through temperature pattern analysis, the system enables proactive maintenance scheduling, allowing repairs to be performed during planned downtime rather than causing unexpected system shutdowns and extended evacuation procedures.
Solution Approach 2:
The monitoring system provides self-diagnostic capabilities by automatically detecting abnormalities and generating maintenance alerts. This reduces the need for manual pressure switch inspections and repairs, enabling the system to indicate its own health status and reducing overall maintenance downtime through targeted, data-driven maintenance scheduling.
3Device complexity
If traditional monitoring systems are used, then simple pressure detection is achieved, but predictive maintenance capability is lost
Solution Approach 1:
The monitoring system is segmented into distinct functional modules: temperature sensors positioned at the compressor, evaporator, and condenser; data transmission components; and a deep learning analysis module. This segmentation allows the complex predictive maintenance functionality to be achieved through coordinated simple components, managing overall system complexity while enabling advanced reliability monitoring.
Solution Approach 2:
The deep learning algorithm serves as an intermediary between the simple temperature sensor data and the complex predictive maintenance decisions. The algorithm processes raw temperature readings, identifies patterns indicating potential failures, and generates maintenance recommendations, thereby bridging the gap between simple data collection and complex predictive capabilities without requiring direct complex hardware interactions.
Data Source
AI summary
A monitoring method of a cooling system and a monitoring device thereof are provided. The monitoring method includes the steps: establishing an abnormality determination model according to predetermined abnormal data and predetermined abnormal types using deep learning by a monitoring module; generating groups of temperature data respectively by a plurality of temperature sensors; and determining one or more abnormal types and an abnormal prediction of the cooling system according to the groups of temperature data and the plurality of temperature sensors using the abnormality determination model by the monitoring module.