Fault diagnosis for temperature, flow rate and pressure sensors in VAV systems using wavelet neural network

Du, Zhimin; Jin, Xinqiao; Yang, Yunyu

doi:10.1016/j.apenergy.2009.01.015

Cited by 132 publications

(46 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Failing sensors can force a plant or plant component into non-optimal operation, and can disrupt plant operation. In the worst-case scenario, sensor failure can lead to damage to components (Du et al, 2009). Therefore, an effective approach for validating sensors in NGCC power plants is highly desirable.…”

Section: Introductionmentioning

confidence: 99%

Multiple Sensor Validation for Natural Gas Combined Cycle Power Plants Based on Robust Input Training Neural Networks

Ren

2017

J. Chem. Eng. Japan / JCEJ

View full text Add to dashboard Cite

Modern industrial power plants require continuous monitoring to ensure their safe and reliable operation. This monitoring depends heavily on accurate sensor readings from a large number of sensors, making sensors an important part of any plant. The possibility of more than a single sensor being simultaneously faulty should not be overlooked. In this paper, a nonlinear system data validation approach based on a robust input-training neural network is proposed for detecting, isolating, and reconstructing multiple sensor faults in a power plant. An in uence factor function and reliability coe cients were introduced into an objective function for the purpose of inhibiting the in uence of numerous failure data with signi cant errors. The proposed method was evaluated on a single-shaft gas turbine from a natural gas combined cycle power plant. The result shows that the proposed model has a high degree of accuracy in multiple sensor failure cases.

show abstract

Section: Introductionmentioning

confidence: 99%

Multiple Sensor Validation for Natural Gas Combined Cycle Power Plants Based on Robust Input Training Neural Networks

Ren

2017

J. Chem. Eng. Japan / JCEJ

View full text Add to dashboard Cite

show abstract

“…ANN coupled with CFD and genetic algorithm (GA) has been used for HVAC design and optimization [63]- [66]. ANN is usually coupled with GA for optimization purpose.…”

Section: Figure 210 Average Temperature Rate Around the Person With mentioning

confidence: 99%

A virtual thermostat for local temperature control

Alhashme

2016

Energy and Buildings

View full text Add to dashboard Cite

This thesis presents design and operation of a newly developed virtual thermostat to control any desired local temperature in an HVAC controlled space. Conventional HVAC thermostats use a single point temperature sensor at one fixed location in a controlled space to control the temperature of the whole space. The single point temperature sensor does not represent the entire controlled domain. In addition, in most applications only a small zone in the controlled space needs to be controlled (for example where the people are located). Heating and cooling of the unnecessary zones lead to extra energy consumption that can be saved if only the required zones are controlled. Such a control system requires knowledge of the temperature distribution in the whole zone at all times. In this work, we have used computational fluid dynamics (CFD) to determine the distributive temperature inside the controlled space at all times and turn the HVAC system ON and OFF based on the temperature of the desired zone in the space. In this study, we have determined the energy savings by comparing the energy consumption of a conventional thermostat controlled system with a locally controlled one. Several cases with different heat losses, and different inlet air velocities and directions are studied. Energy savings of up to 22% is realized for the cases studied here. In addition, the study showed the effect of person's location on the energy saving using the local control. One of the main problems with such a control system is that the CFD calculations may take a long time (10-24 hours depending on the complexity of the iii problem), which is not practical for real-time temperature control. In order to reduce the computational times and simulate various operating conditions quickly, an artificial neural network (ANN) model is used to train the temperature control system. This resulted in reduction of the computational times to few seconds, making this system practical. This thesis, presents various elements of the newly developed virtual thermostat and its operating principals.iv

show abstract

“…Since the wavelet neural network [16][17][18] has good nonlinear quality, fully distributed storage structure, and fault-tolerance, especially the local time-frequency characteristics and zoom capability, it is suitable for solving the problem about nonlinear fitting, hysteresis effect and temperature compensation of the pressure sensor. Wavelet neural network is the feedforward neural network that is based on the wavelet function as the activation function of the neurons.…”

Section: Ga-wnn Compensation Algorithmmentioning

confidence: 99%

Research on High-Precision, Low Cost Piezoresistive MEMS-Array Pressure Transmitters Based on Genetic Wavelet Neural Networks for Meteorological Measurements

Zhang

Liu

et al. 2015

Micromachines

View full text Add to dashboard Cite

This paper provides a novel and effective compensation method by improving the hardware design and software algorithm to achieve optimization of piezoresistive pressure sensors and corresponding measurement systems in order to measure pressure more accurately and stably, as well as to meet the application requirements of the meteorological industry. Specifically, GE NovaSensor MEMS piezoresistive pressure sensors within a thousandth of accuracy are selected to constitute an array. In the versatile compensation method, the hardware utilizes the array of MEMS pressure sensors to reduce random error caused by sensor creep, and the software adopts the data fusion technique based on the wavelet neural network (WNN) which is improved by genetic algorithm (GA) to analyze the data of sensors for the sake of obtaining accurate and complete information over the wide temperature and pressure ranges. The GA-WNN model is implemented in OPEN ACCESSMicromachines 2015, 6 555 hardware by using the 32-bit STMicroelectronics (STM32) microcontroller combined with an embedded real-time operating system µC/OS-II to make the output of the array of MEMS sensors be a direct digital readout. The results of calibration and test experiments clearly show that the GA-WNN technique can be effectively applied to minimize the sensor errors due to the temperature drift, the hysteresis effect and the long-term drift because of aging and environmental changes. The maximum error of the low cost piezoresistive MEMS-array pressure transmitter proposed by us is within 0.04% of its full-scale value, and it can satisfy the meteorological pressure measurement.

show abstract

Fault diagnosis for temperature, flow rate and pressure sensors in VAV systems using wavelet neural network

Cited by 132 publications

References 28 publications

Multiple Sensor Validation for Natural Gas Combined Cycle Power Plants Based on Robust Input Training Neural Networks

Multiple Sensor Validation for Natural Gas Combined Cycle Power Plants Based on Robust Input Training Neural Networks

A virtual thermostat for local temperature control

Research on High-Precision, Low Cost Piezoresistive MEMS-Array Pressure Transmitters Based on Genetic Wavelet Neural Networks for Meteorological Measurements

Contact Info

Product

Resources

About