Least Mean Square-Based Fuzzy c-Means Clustering for Load Recognition of Induction Heating

Qais, Mohammed H.; Loo, K. H.; Liu, Junwei; Lai, Cheung-Ming

doi:10.1109/tim.2022.3196702

Cited by 10 publications

(5 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the same time, the input gate will decide which parts of g t will be forgotten by generating an input state, i t , as in (15). Then, the new memory cell state, c t , is achieved as in (16).…”

Section: Autoencoder Structurementioning

confidence: 99%

“…In [15], a model predictive control based on a deep neural network is applied for the resonant inverter of the IH system. In [16], unsupervised learning was applied to recognize the material and size of the cookware. In [17], a high-efficiency multi-output resonant inverter topology with zero voltage switching and front-end power factor correction is proposed for domestic IH systems [18].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

LSTM-Based Stacked Autoencoders for Early Anomaly Detection in Induction Heating Systems

Qais,

Kewat,

Loo

et al. 2023

Mathematics

Self Cite

View full text Add to dashboard Cite

Due to the contactless operation of cookware on induction heating systems, the temperature of the cookware is measured remotely using thermal sensors placed on the center of the coil. Hence, the measurement error of these sensors increases if the cookware placement is not centered on the top of the coil. Therefore, this study presents a new data-driven anomaly detection method to detect overheated cookware using the thermal sensor of the case temperature of the inverter module. This method utilizes the long short-term memory (LSTM)-based autoencoder (AE) to learn from large training data of temperatures of cookware and the inverter. The learning of the LSTM-AE model is achieved by minimizing the residual error between the input and reconstructed input data. Then, the maximum residual error can be set to be a threshold value between the normal and abnormal operation. Finally, the learned LSTM-AE model is tested using new testing data that include both normal and abnormal cases. The testing results revealed that the LSTM-AE model can detect cookware overheating by using the inverter temperature only. In addition, the LSTM-AE model can detect the faults in the inverter side, such as poor air ventilation and a faulted cooling fan. Furthermore, we utilized different deep learning algorithms, such as the recurrent neural network (RNN) and the fully connected layers, in the internal layers of the AE. The results demonstrated that the LSTM-AE could detect anomalies earlier than the other models.

show abstract

Section: Autoencoder Structurementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

LSTM-Based Stacked Autoencoders for Early Anomaly Detection in Induction Heating Systems

Qais,

Kewat,

Loo

et al. 2023

Mathematics

Self Cite

View full text Add to dashboard Cite

show abstract

“…The method presented for determining the loaded material is carried out by using circuit analysis and quasi‐resonance in [20]. In [21], least mean squares based on fuzzy c‐means clustering were used for load identification. To reduce the noise of the induction cooker and meet the electromagnetic compatibility (EMC), literature [22] uses conductance control to reduce the harmonic distortion of the grid current.…”

Section: Introductionmentioning

confidence: 99%

“…However, in terms of power estimation and stability, there are very few research and discussions about the familiar half-bridge cooking utensils. Even the latest studies, such as [20,21], the analysis is still based on driving with a near constant DC source. Ref.…”

Section: Introductionmentioning

confidence: 99%

Study of half‐bridge series‐resonant induction cooker powered by line rectified DC with less filtering

Hsieh

Kuo

Chang³

2023

IET Power Electronics

View full text Add to dashboard Cite

This paper presents an analysis and design strategy for a half‐bridge series resonant induction heating (HB SR‐IH) cooker powered by a rectified sinusoidal DC. The simplified equivalent circuit of an induction cooker is modelled by a train of rectified sinusoidal DC pulses chopped at the switching frequency. An average root‐mean‐square (RMS) method is proposed to calculate the RMS resonant voltage and current extrapolated to the power line frequency period. The stability of the cooker is achieved by properly setting the damping ratio in the root‐locus plane to keep the system running quasi‐resonantly at the required power. The power control of the SR HB‐IH cooktop is performed by forced commutation above the resonance frequency. A prototype of a 3 kW HB SR‐IH cooker was designed and implemented to validate the estimated results. Various waveforms from low power to high power are discussed and verified by damping ratio control. The SR HB‐IH cooktop achieves a high‐power factor of 0.95 to 0.995 when generating 300W to 3kW due to less filtered DC power. The power quality assessment showed that the total harmonic distortion (THD) of the line current and voltage measured at 3 kW was 4.1% and 3.5%, respectively.

show abstract

“…Induction heating procedures (IHPs) have several characteristics that are superior to electric burners and gas cooking burners, including quicker warming rates, lower energy usage and expenses, no harmful greenhouse gases emissions, touchless scorching that is secure, and compact sizes [5]. The primary components of a household IHP system are the power circuit design, the process control, the coil, and the cooking utensils [6].…”

Section: Introductionmentioning

confidence: 99%

Performance of an Adaptive Optimization Paradigm for Optimal Operation of a Mono-Switch Class E Induction Heating Application

Aziz¹,

Lai²,

Loo

2023

Mathematics

Self Cite

View full text Add to dashboard Cite

The progress of technology involves the continuous improvement of current machines to attain higher levels of energy efficiency, operational dependability, and effectiveness. Induction heating is a thermal process that involves the heating of materials that possess electrical conductivity, such as metals. This technique finds diverse applications, including induction welding and induction cooking pots. The optimization of the operating point of the inverter discussed in this study necessitated the resolution of a pair of non-convex mathematical models to enhance the energy efficiency of the inverters and mitigate switching losses. In order to determine the most advantageous operational location, a sophisticated surface optimization was conducted, requiring the implementation of a sophisticated optimization methodology, such as the adaptive black widow optimization algorithm. The methodology draws inspiration from the resourceful behavior of female black widow spiders in their quest for nourishment. Its straightforward control variable design and limited computational complexity make it a feasible option for addressing multi-dimensional engineering problems within confined constraints. The primary objective of utilizing the adaptive black widow optimization algorithm in the context of induction heating is to optimize the pertinent process parameters, including power level, frequency, coil design, and material properties, with the ultimate goal of efficiently achieving the desired heating outcomes. The utilization of the adaptive black widow optimization algorithm presents a versatile and robust methodology for addressing optimization problems in the field of induction heating. This is due to its capacity to effectively manage intricate, non-linear, and multi-faceted optimization predicaments. The adaptive black widow optimization algorithm has been modified in order to enhance the optimization process and guarantee the identification of the global optimum. The empirical findings derived from an authentic inverter setup were compared with the hypothetical results.

show abstract

Least Mean Square-Based Fuzzy c-Means Clustering for Load Recognition of Induction Heating

Cited by 10 publications

References 33 publications

LSTM-Based Stacked Autoencoders for Early Anomaly Detection in Induction Heating Systems

LSTM-Based Stacked Autoencoders for Early Anomaly Detection in Induction Heating Systems

Study of half‐bridge series‐resonant induction cooker powered by line rectified DC with less filtering

Performance of an Adaptive Optimization Paradigm for Optimal Operation of a Mono-Switch Class E Induction Heating Application

Contact Info

Product

Resources

About