Global average ignition delay time of oil droplets with diameter of 0.4-0.7 mm. by Lei Bai (631944)

Subjects:

Relationship between fuel quantity and ignition delay time. by Lei Bai (631944)

Subjects:

Three classic combustion stages of the flame. by Lei Bai (631944)

Subjects:

Experimental Conditions of Fixed Spray hole diameter. by Lei Bai (631944)

Subjects:

Flame binarization image processing flow. by Lei Bai (631944)

Subjects:

Experimental condition of fixed oil drop volume. by Lei Bai (631944)

Subjects:

Relationship between Hot Surface Temperature and Ignition Event. by Lei Bai (631944)

Subjects:

Schematic diagram of experimental injector size. by Lei Bai (631944)

Subjects:

Droplet boiling modes at different temperatures. by Lei Bai (631944)

Subjects:

Risk Classification Diagram of Hot Surface. by Lei Bai (631944)

Subjects:

Physical parameters of engine lubricating oil. by Lei Bai (631944)

Subjects:

Average ignition delay time in each temperature range. by Lei Bai (631944)

Subjects:

Variation of heat flow with wall temperature. by Lei Bai (631944)

Subjects:

Fractal dimension evolution of oil droplet flame under different spray hole diameter. by Lei Bai (631944)

Subjects:

Evolution of flame fractal dimension of oil droplets with different volumes. by Lei Bai (631944)

Subjects:

Internal structure of an LSTM cell. by Xiangjuan Liu (618000)

“…Further integration of Spearman correlation analysis and PCA dimensionality reduction created multidimensional feature sets, revealing substantial accuracy improvements: The BiLSTM model achieved an 83.6% cumulative MAE reduction from 1.65 (raw data) to 0.27 (STL-PCA), while traditional models like Prophet showed an 82.2% MAE decrease after feature engineering optimization. Finally, the Beluga Whale Optimization (BWO)-tuned STL-PCA-BWO-BiLSTM hybrid model delivered optimal performance on test sets (RMSE = 0.22, MAE = 0.16, MAPE = 0.99%, ), exhibiting 40.7% higher accuracy than unoptimized BiLSTM (MAE = 0.27). …”

Prediction effect of each model after STL. by Xiangjuan Liu (618000)

“…Further integration of Spearman correlation analysis and PCA dimensionality reduction created multidimensional feature sets, revealing substantial accuracy improvements: The BiLSTM model achieved an 83.6% cumulative MAE reduction from 1.65 (raw data) to 0.27 (STL-PCA), while traditional models like Prophet showed an 82.2% MAE decrease after feature engineering optimization. Finally, the Beluga Whale Optimization (BWO)-tuned STL-PCA-BWO-BiLSTM hybrid model delivered optimal performance on test sets (RMSE = 0.22, MAE = 0.16, MAPE = 0.99%, ), exhibiting 40.7% higher accuracy than unoptimized BiLSTM (MAE = 0.27). …”

The kernel density plot for data of each feature. by Xiangjuan Liu (618000)

“…Further integration of Spearman correlation analysis and PCA dimensionality reduction created multidimensional feature sets, revealing substantial accuracy improvements: The BiLSTM model achieved an 83.6% cumulative MAE reduction from 1.65 (raw data) to 0.27 (STL-PCA), while traditional models like Prophet showed an 82.2% MAE decrease after feature engineering optimization. Finally, the Beluga Whale Optimization (BWO)-tuned STL-PCA-BWO-BiLSTM hybrid model delivered optimal performance on test sets (RMSE = 0.22, MAE = 0.16, MAPE = 0.99%, ), exhibiting 40.7% higher accuracy than unoptimized BiLSTM (MAE = 0.27). …”

Analysis of raw data prediction results. by Xiangjuan Liu (618000)

“…Further integration of Spearman correlation analysis and PCA dimensionality reduction created multidimensional feature sets, revealing substantial accuracy improvements: The BiLSTM model achieved an 83.6% cumulative MAE reduction from 1.65 (raw data) to 0.27 (STL-PCA), while traditional models like Prophet showed an 82.2% MAE decrease after feature engineering optimization. Finally, the Beluga Whale Optimization (BWO)-tuned STL-PCA-BWO-BiLSTM hybrid model delivered optimal performance on test sets (RMSE = 0.22, MAE = 0.16, MAPE = 0.99%, ), exhibiting 40.7% higher accuracy than unoptimized BiLSTM (MAE = 0.27). …”

Flowchart of the STL. by Xiangjuan Liu (618000)

“…Further integration of Spearman correlation analysis and PCA dimensionality reduction created multidimensional feature sets, revealing substantial accuracy improvements: The BiLSTM model achieved an 83.6% cumulative MAE reduction from 1.65 (raw data) to 0.27 (STL-PCA), while traditional models like Prophet showed an 82.2% MAE decrease after feature engineering optimization. Finally, the Beluga Whale Optimization (BWO)-tuned STL-PCA-BWO-BiLSTM hybrid model delivered optimal performance on test sets (RMSE = 0.22, MAE = 0.16, MAPE = 0.99%, ), exhibiting 40.7% higher accuracy than unoptimized BiLSTM (MAE = 0.27). …”