Data-Driven Fault Detection and Diagnosis in Cooling Units Using Sensor-Based Machine Learning Classification
Amilcar Quispe-Astorga1, Roger Jesus Coaquira-Castillo1, L Walter Utrilla Mego2
1LIECAR Laboratory, Universidad Nacional de San Antonio Abad del Cusco (UNSAAC), Cusco 08003, Peru.
Sensors (Basel, Switzerland)
|June 27, 2025
Summary
This study introduces an automated system for real-time fault detection in Precision Air Conditioning (PAC) systems. The Random Forest model achieved high accuracy, improving system efficiency and reducing energy consumption.
Area of Science:
- Engineering
- Computer Science
Background:
- Precision Air Conditioning (PAC) systems are critical for sensitive environments but susceptible to failures.
- System failures lead to inefficiencies, increased energy use, and reduced equipment performance.
Purpose of the Study:
- To develop an automatic, real-time fault detection and diagnosis system for PAC units.
- To classify system events as normal or faulty using sensor data analysis.
Main Methods:
- Utilized data-driven machine learning models on sensor data (pressure, temperature, current, voltage).
- Implemented and compared multiple models including SVM, DT, GB, KNN, NB, and RF.
- Collected and preprocessed a dataset of 20,000 PAC operational samples.
Main Results:
- The Random Forest (RF) model demonstrated superior performance with 96% accuracy in offline tests and 95.28% in real-time.
- Other models showed varying accuracies: SVM (93%), DT (93%), GB (91%), KNN (83%), NB (77%).
- A real-time validation test of the RF model achieved 93.49% accuracy.
Conclusions:
- The proposed data-driven system effectively detects and diagnoses faults in PAC systems in real-time.
- The Random Forest model is highly effective for this application, enhancing system reliability and efficiency.
Related Concept Videos
01:07Refrigerators and Heat Pumps
2.5K
Refrigerators or heat pumps are heat engines operating in a reverse direction. For a refrigerator, the focus is on removing heat from a specific area, whereas, for a heat pump, the focus is on dumping heat into one particular area. A refrigerator (or heat pump) absorbs heat Qc from the cold reservoir at Kelvin temperature Tc and discards heat Qh to the hot reservoir at Kelvin temperature Th, while work W is done on the engine’s working substance.
A household refrigerator removes heat from...
A household refrigerator removes heat from...
2.5K
02:44Heating and Cooling Curves
24.1K
When a substance—isolated from its environment—is subjected to heat changes, corresponding changes in temperature and phase of the substance is observed; this is graphically represented by heating and cooling curves.
For instance, the addition of heat raises the temperature of a solid; the amount of heat absorbed depends on the heat capacity of the solid (q = mcsolidΔT). According to thermochemistry, the relation between the amount of heat absorbed or released by a substance, q, and its...
For instance, the addition of heat raises the temperature of a solid; the amount of heat absorbed depends on the heat capacity of the solid (q = mcsolidΔT). According to thermochemistry, the relation between the amount of heat absorbed or released by a substance, q, and its...
24.1K
01:26Classification of Systems-I
319
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
319
01:18Steps in Outbreak Investigation
213
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
213
01:31Classification of Systems-II
242
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
242
01:25Distribution Reliability and Automation
167
Distribution reliability in electrical power systems is critical for ensuring an uninterrupted power supply to consumers at minimal cost. According to IEEE Standard Terms, reliability is the probability that a device will function without failure over a specified time period or amount of usage. For electric power distribution, this translates to maintaining continuous power supply and addressing customer concerns over power outages. Several indices, as defined by IEEE Standard 1366-2012, are...
167