Chiller sensor fault diagnosis based on circle mapping and adaptive t-distribution Runge-Kutta algorithm optimized
Yuzhe Wang1,2,3, Jinglong Liu3, Feiyu Liu3
1SEAC Key Laboratory of Big Data Applied Technology, Dalian Minzu University, Dalian, 116000, China.
Scientific Reports
|January 6, 2026
Summary
A new optimizer, CTRUN, enhances Long Short-Term Memory networks for chiller sensor fault detection. This method improves accuracy and speed, reducing energy waste and equipment damage.
Area of Science:
- Engineering
- Computer Science
- Artificial Intelligence
Background:
- Faulty sensors increase energy consumption and risk equipment damage.
- Accurate sensor data is crucial for efficient control systems.
Purpose of the Study:
- To develop an advanced optimization algorithm for chiller sensor fault detection.
- To enhance the performance of Long Short-Term Memory (LSTM) networks in identifying sensor malfunctions.
Main Methods:
- Proposed the Circle Mapping and Adaptive t-Distribution Runge-Kutta optimizer (CTRUN).
- Utilized CTRUN to optimize LSTM hyperparameters for fault detection.
- Compared CTRUN with multiple optimization algorithms (RUN, PSO, SSA, SimuAPSO, ASFSSA, SBOA, HO).
- Employed Pearson correlation for feature selection to improve precision.
Main Results:
- CTRUN demonstrated superior convergence speed and optimization accuracy compared to other algorithms.
- The CTRUN-LSTM model achieved significant improvements in fault detection rates.
- Feature selection using Pearson correlation boosted diagnostic precision.
Conclusions:
- CTRUN is an effective optimizer for LSTM-based sensor fault detection.
- The proposed method enhances the reliability and efficiency of chiller systems.
- CTRUN offers a promising approach for improving industrial sensor monitoring.
Related Concept Videos
01:26Linear Approximation in Frequency Domain
344
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
344
01:19PID Controller
641
Proportional-Integral-Derivative (PID) controllers are widely used in various control systems to enhance stability and performance. In a thermostat, it adjusts heating or cooling based on the temperature difference between the actual and desired levels. They are often used in automotive speed systems, effectively managing sudden speed changes while maintaining a constant speed under varying conditions. On the other hand, PI controllers, commonly employed in voltage regulation, enhance stability...
641