Research on fault diagnosis of coal mill system based on the simulated typical fault samples

Hu, Yong; Boyu, Ping; Zeng, Deliang; Niu, Yuguang; Gao, Yaokui; Zhang, Dongming

doi:10.1016/j.measurement.2020.107864

Cited by 21 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…frontiersin.org actual value and the reconstructed value. The second term is the weight attenuation, which is used to indicate the strength of the weight decay and prevent over-fitting (Hu et al, 2020).…”

Section: Frontiers In Energy Researchmentioning

confidence: 99%

Condition monitoring and early fault warning of power plant auxiliary equipment using LSTM-SDAE model with an adaptive threshold

Hong

Liang

et al. 2023

Front. Energy Res.

View full text Add to dashboard Cite

With the increasing penetration of renewable energy in the power grid, which makes power plant equipment is always in changing operating conditions. The correlation between the main and auxiliary equipment of the unit is easy to lead a potential fault, therefore, the safety and reliability of the auxiliary equipment of thermal power units have become a more challenging issue in the case of large-scale renewable energy. Adaptive condition monitoring of the auxiliary equipment can reduce maintenance costs and improve reliability in the thermal power units. Most existing studies perform poorly at extracting features from distributed control systems data and make less use of time series data. A novel adaptive condition monitoring framework and early fault warning method based on long short-term memory and stack denoising auto-encoder network has been proposed for auxiliary equipment of power plant unit. The proposed framework has two main parts, which contain condition monitoring and adaptive early fault warning. The Mahalanobis distance of a reconstruction error is defined as the monitoring indicator to reflect the condition of the equipment. The Chebyshev inequality determines an adaptive threshold for early anomaly detection that applies to changeable working conditions. The effectiveness of the proposed method was verified by the actual case of the coal mill. The adaptive threshold method can obtain the advance time of 42s and 108s, respectively.

show abstract

Section: Frontiers In Energy Researchmentioning

confidence: 99%

Condition monitoring and early fault warning of power plant auxiliary equipment using LSTM-SDAE model with an adaptive threshold

Hong

Liang

et al. 2023

Front. Energy Res.

View full text Add to dashboard Cite

show abstract

“…The finer particles are introduced into the boiler, whereas the coarser particles fall back to the grinding disc for further grinding. Stone coal and sundries mixed with the raw coal are passed to the air ring, after which they fall into the glove box [28]. When the load increases, the output of the mixed coal cannot adapt to the change in load, which leads to a blockage in the coal mill.…”

Section: Characteristics Of Coal Millmentioning

confidence: 99%

“…Where the first term is the reconstruction loss of data samples, m represents the sample numbers, the second term is the weight attenuation, and λ is the weight attenuation coefficient, which is used to express the intensity of weight attenuation and prevent over fitting [28]. The L2 regularization term is selected here.…”

Section: A Basic Principle Of Sdaementioning

confidence: 99%

“…Simultaneously, the reconstructed data must be significantly similar to the original data. However, in practice, the probability of introducing random noise should be appropriate; otherwise, the original data will be corrupted by noise, rendering it unusable [28]. The hidden layer output y is obtained after the weighting and mapping operation f e .…”

Section: A Basic Principle Of Sdaementioning

confidence: 99%

See 1 more Smart Citation

Early Warning of Critical Blockage in Coal Mills Based on Stacked Denoising Autoencoders

Hong

Liang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Coal mills have a significant influence on the reliability, efficiency, and safe operation of a coal-fired power plant. Coal blockage is one of the main reasons for coal mill malfunction. It is highly essential to accurately detect the critical blockage in coal mills to ensure a safe and stable operation of the unit. Taking advantage of unsupervised learning methods and historical process data from distributed control systems (DCS), a stacked denoising autoencoder (SDAE) network-based approach for monitoring critical blockage in a coal mill is proposed in this work. The SDAE model with optimized parameters is applied to reconstruct the operating data during normal operating conditions. The intrinsic relationship between all input variables was captured by training a multilayer network model. The monitoring indicator was obtained from the reconstruction errors, and the threshold for monitoring indicators was obtained using kernel density estimation (KDE) during normal operation. The proposed network is independent of fault data, requires a reduced on-line calculation, and demonstrates a better real-time performance compared to conventional methods. The abnormal variables analysis may provide a theoretical evidence for critical blockage. The effectiveness of the proposed method is validated using operating data collected from an actual coal-fired power plant in China. The results demonstrated that the proposed method can effectively detect critical blockage in a coal mill and issue a timely warning, which allows operators to detect potential faults.

show abstract

“…Therefore, intelligent fault diagnosis methods based on state parameters for coal mining machinery may face many challenges, such as insufficient detection approaches, more data interference factors, difficult data collections, etc. Nowadays, the fault diagnosis of coal mining machinery still relies on information threshold discrimination [6][7][8]. Recently, some scholars begin to use data mining-based methods to seek fault types for mining machinery such as artificial intelligence approaches including genetic algorithms and artificial neural networks, which allow employing the non-iterative methods, where one only needs to enter input parameters as the considered parameters of the process are generated as an answer to the input data set.…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis of Coal Mining Machinery Based on State Parameters

Song¹

2020

Fuzzy Systems and Data Mining VI

View full text Add to dashboard Cite

The reliable operation of coal mining machinery acts as an important guarantee for safe productions in underground coal mines. The status monitoring and fault diagnosis of traditional coal mining machinery mainly rely on threshold judgments. However, a single judgment condition and a long fault propagation chain can be found in the method of threshold judgments, which make it difficult to accurately seek the fault type. By using the data analysis of state parameters for coal mining machinery, fault parameters and propagation paths can be analyzed effectively. This paper takes the cutting unit of a certain type of bolter miners as an example, a static and dynamic numerical analysis method of the cutting unit of bolter miners are established by virtue of FTA-Petri net models and BP-Firefly neural networks, which can provide a new perspective for fault diagnosis of coal mining machinery.

show abstract

Research on fault diagnosis of coal mill system based on the simulated typical fault samples

Cited by 21 publications

References 16 publications

Condition monitoring and early fault warning of power plant auxiliary equipment using LSTM-SDAE model with an adaptive threshold

Condition monitoring and early fault warning of power plant auxiliary equipment using LSTM-SDAE model with an adaptive threshold

Early Warning of Critical Blockage in Coal Mills Based on Stacked Denoising Autoencoders

Fault Diagnosis of Coal Mining Machinery Based on State Parameters

Contact Info

Product

Resources

About