A Spark Streaming-Based Early Warning Model for Gas Concentration Prediction

Huang, Yuxin; Li, Shugang; Fan, Jingdao; Yan, Zhenguo; Li, Chuan

doi:10.3390/pr11010220

Cited by 3 publications

(1 citation statement)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They used a deep local adaptive network, two-stage qualitative trend analysis, and a five-state Bayesian network to gradually implement fault detection, identification, and diagnosis. Huang et al [25] proposed a gas concentration early warning model involving the spark streaming framework. This model combines the particle swarm optimization algorithm and the gated recurrent unit model in the spark streaming framework.…”

Section: Literature Reviewmentioning

confidence: 99%

Enhancing LightGBM for Industrial Fault Warning: An Innovative Hybrid Algorithm

Li,

Jin,

Dogani

et al. 2024

Processes

View full text Add to dashboard Cite

The reliable operation of industrial equipment is imperative for ensuring both safety and enhanced production efficiency. Machine learning technology, particularly the Light Gradient Boosting Machine (LightGBM), has emerged as a valuable tool for achieving effective fault warning in industrial settings. Despite its success, the practical application of LightGBM encounters challenges in diverse scenarios, primarily stemming from the multitude of parameters that are intricate and challenging to ascertain, thus constraining computational efficiency and accuracy. In response to these challenges, we propose a novel innovative hybrid algorithm that integrates an Arithmetic Optimization Algorithm (AOA), Simulated Annealing (SA), and new search strategies. This amalgamation is designed to optimize LightGBM hyperparameters more effectively. Subsequently, we seamlessly integrate this hybrid algorithm with LightGBM to formulate a sophisticated fault warning system. Validation through industrial case studies demonstrates that our proposed algorithm consistently outperforms advanced methods in both prediction accuracy and generalization ability. In a real-world water pump application, the algorithm we proposed achieved a fault warning accuracy rate of 90%. Compared to three advanced algorithms, namely, Improved Social Engineering Optimizer-Backpropagation Network (ISEO-BP), Long Short-Term Memory-Convolutional Neural Network (LSTM-CNN), and Grey Wolf Optimizer-Light Gradient Boosting Machine (GWO-LightGBM), its Root Mean Square Error (RMSE) decreased by 7.14%, 17.84%, and 13.16%, respectively. At the same time, its R-Squared value increased by 2.15%, 7.02%, and 3.73%, respectively. Lastly, the method we proposed also holds a leading position in the success rate of a water pump fault warning. This accomplishment provides robust support for the timely detection of issues, thereby mitigating the risk of production interruptions.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Enhancing LightGBM for Industrial Fault Warning: An Innovative Hybrid Algorithm

Li,

Jin,

Dogani

et al. 2024

Processes

View full text Add to dashboard Cite

show abstract

A Storm Frame Optimization Method for Predicting and Warning the Safety Status of a Shearer

Zhang,

He,

et al. 2024

Energy Science & Engineering

View full text Add to dashboard Cite

Real‐time monitoring, prediction, and early warning of operating status during intelligent mining are the key to ensuring stable production. To solve the problem of lag in determining the operating status of a shearer, this study proposes a new method for predicting and warning the real‐time operating status of the shearer involving the Storm framework, based on parallel optimization of data processing and the gated recurrent unit (GRU) model based on hyperparameter optimization. First, the GRU model is optimized through hyperparameter optimization to achieve adaptive and accurate prediction and early warning of multidimensional state parameters of the shearer. Second, a virtual machine is constructed to host the Storm framework, parallel optimized real‐time processing of data is performed on the Storm framework, and real‐time data flow patterns are constructed to speed up data processing and retrieval, ensuring each tuple is fully processed through the topology structure. Finally, the optimized GRU model is embedded into the optimized Storm framework to achieve real‐time prediction and early warning of different dimensional data of the shearer. The prediction accuracy, early warning accuracy, and processing efficiency of the Storm platform are used as evaluation indicators to analyze and evaluate the model, verifying the efficiency and applicability of the proposed model. Experimental results show that the model has a prediction accuracy of 93%, an early warning accuracy of 93.05%, and consumes 10 s. It can achieve high performance, low latency, and high precision in predicting and providing early warnings for the shearer's state parameters, greatly improving the efficiency of predicting and early warning the operating status parameters of the shearer. This model realizes real‐time prediction and early warning of the shearer's operating status, providing technical support for intelligent mining in coal mines.

show abstract

A new canary in the coal mine?

Ramsauer

2023

KI-Kritik / AI Critique

View full text Add to dashboard Cite

A Spark Streaming-Based Early Warning Model for Gas Concentration Prediction

Cited by 3 publications

References 31 publications

Enhancing LightGBM for Industrial Fault Warning: An Innovative Hybrid Algorithm

Enhancing LightGBM for Industrial Fault Warning: An Innovative Hybrid Algorithm

A Storm Frame Optimization Method for Predicting and Warning the Safety Status of a Shearer

A new canary in the coal mine?

Contact Info

Product

Resources

About