Juan Lu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Juan Lu has a total of 55 co-authors. Here are the top co-authors by number of shared publications:
- Xiaoping Liao
School of Mechanical Engineering, Guangxi University, Nanning, China
5 shared publications Junyan Ma
Guangxi Key Laboratory of Manufacturing Systems and Advanced Manufacturing Technology, Guangxi University, Nanning, China
3 shared publicationsXiaoping Liao
Guangxi Key Laboratory of Manufacturing Systems and Advance Manufacturing Technology, Guangxi University, Nanning, China
3 shared publications- Changjian Wen
Guangxi Key Laboratory of Ocean Engineering Equipment and Technology, Beibu Gulf University, Qinzhou 535011, China
2 shared publications - Dan Chen
Beibu Gulf University, Qinzhou, China
2 shared publications - Haibin Ouyang
School of Mechanical and Electric Engineering, Guangzhou University, Guangzhou, China
2 shared publications
Latest Publications
- Open Access
- 19 November 2026
- Published by MDPI AG in Agriengineering
- Vol. 8  (11) , 500
A Boundary-Adaptive Model of Headland Turning Costs for Traversal Sequence Optimization of Rice-Seedling-Throwing Machines in Irregular Karst Paddy Fields
Path planning for rice-seedling-throwing machines (RSTMs) remains a challenging task in karst areas, where paddy fields are typically small, fragmented, and bounded by irregular, tortuous boundaries. This study integrates an adaptive model of headland turning costs with an improved pelican optimization algorithm (IPOA). Using the minimum turning radius and field boundaries, a turning cost function covering X- and U-type turns is established, with a dimensionless composite performance index defined as a weighted sum of operation time and fuel consumption. Two strategies are added: a Lévy flight disturbance to escape local optima and strengthen global exploration, and a nonlinear convergence factor that replaces the linear decay and supports early global exploration and later fine local exploitation. The model is coupled with the optimizer to convert boundary constraints into feasible turns and embed turning costs into row sequencing. Across ten fields and 30 independent runs, the improved POA, termed IPOA, attains the lowest mean path length, operation time, fuel consumption, and composite index C, reducing the composite index C by 4.46%, 2.44%, 1.72%, and 1.48% on average relative to the genetic algorithm (GA), ant colony optimization (ACO), particle swarm optimization (PSO), and POA. The lower mean values and the statistical evidence are kept distinct: Wilcoxon and Friedman tests confirm that the overall ranking advantage is statistically significant, offering a transferable route to energy-efficient precision agriculture in karst areas.
- 19 November 2026
- Published by MDPI AG in Agriengineering
- Vol. 8  (11) , 500
Open AccessA Boundary-Adaptive Model of Headland Turning Costs for Traversal Sequence Optimization of Rice-Seedling-Throwing Machines in Irregular Karst Paddy Fields
Path planning for rice-seedling-throwing machines (RSTMs) remains a challenging task in karst areas, where paddy fields are typically small, fragmented, and bounded by irregular, tortuous boundaries. This study integrates an adaptive model of headland turning costs with an improved pelican optimization algorithm (IPOA). Using the minimum turning radius and field boundaries, a turning cost function covering X- and U-type turns is established, with a dimensionless composite performance index defined as a weighted sum of operation time and fuel consumption. Two strategies are added: a Lévy flight disturbance to escape local optima and strengthen global exploration, and a nonlinear convergence factor that replaces the linear decay and supports early global exploration and later fine local exploitation. The model is coupled with the optimizer to convert boundary constraints into feasible turns and embed turning costs into row sequencing. Across ten fields and 30 independent runs, the improved POA, termed IPOA, attains the lowest mean path length, operation time, fuel consumption, and composite index C, reducing the composite index C by 4.46%, 2.44%, 1.72%, and 1.48% on average relative to the genetic algorithm (GA), ant colony optimization (ACO), particle swarm optimization (PSO), and POA. The lower mean values and the statistical evidence are kept distinct: Wilcoxon and Friedman tests confirm that the overall ranking advantage is statistically significant, offering a transferable route to energy-efficient precision agriculture in karst areas.
- Open Access
A Method for Predicting Tool Wear Under Different Milling Conditions by Integrating Adaptive VMD with a Two-Stage Attention Mechanism
Reliable tool condition monitoring under high-noise and different milling conditions requires robust signal preprocessing and adaptive feature extraction. This study proposes a tool wear prediction framework that integrates Adaptive Variational Mode Decomposition (AVMD) with a two-stage Convolutional Block Attention Module (CBAM). AVMD uses signal spectral features to guide a directed search for decomposition parameters, reducing reliance on manually specified settings. The reference architecture processes reconstructed multi-sensor signals through multiscale convolution and a DenseNet–BiLSTM network, with two CBAM stages for feature recalibration. The first CBAM follows multiscale convolution and precedes DenseNet, while the second follows BiLSTM. Using the selected configurations, within-tool evaluations achieve R2 values of 0.9399–0.9573 on TC18 titanium-alloy milling data and 0.9907–0.9929 on the public PHM 2010 dataset. Exploratory cross-tool evaluations on PHM 2010 yield R2 values of 0.8954–0.9599 under fixed cutting conditions. t-distributed stochastic neighbor embedding and Shapley additive explanations are used to visualize feature representations and assess feature contributions to model predictions. The results demonstrate the potential of the framework for multi-sensor tool wear estimation in the evaluated machining scenarios.
Open AccessA Method for Predicting Tool Wear Under Different Milling Conditions by Integrating Adaptive VMD with a Two-Stage Attention Mechanism
Reliable tool condition monitoring under high-noise and different milling conditions requires robust signal preprocessing and adaptive feature extraction. This study proposes a tool wear prediction framework that integrates Adaptive Variational Mode Decomposition (AVMD) with a two-stage Convolutional Block Attention Module (CBAM). AVMD uses signal spectral features to guide a directed search for decomposition parameters, reducing reliance on manually specified settings. The reference architecture processes reconstructed multi-sensor signals through multiscale convolution and a DenseNet–BiLSTM network, with two CBAM stages for feature recalibration. The first CBAM follows multiscale convolution and precedes DenseNet, while the second follows BiLSTM. Using the selected configurations, within-tool evaluations achieve R2 values of 0.9399–0.9573 on TC18 titanium-alloy milling data and 0.9907–0.9929 on the public PHM 2010 dataset. Exploratory cross-tool evaluations on PHM 2010 yield R2 values of 0.8954–0.9599 under fixed cutting conditions. t-distributed stochastic neighbor embedding and Shapley additive explanations are used to visualize feature representations and assess feature contributions to model predictions. The results demonstrate the potential of the framework for multi-sensor tool wear estimation in the evaluated machining scenarios.
- Open Access
- 17 May 2026
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 14  (10) , 924
A Study on the MSC-BiLSTM Ship Track Prediction Model Incorporating an Adaptive Attention Mechanism
Accurate ship trajectory prediction is vital for intelligent maritime traffic management, yet conventional hybrid models often fail to balance local feature extraction, long-term dependency capture, and flexible feature weighting when processing AIS data. This paper proposes an MSC-BiLSTM-ATTENTION model that integrates trajectory clustering and an adaptive attention mechanism into a unified framework. Its fundamental advance over existing incremental hybrid architectures is twofold. First, a K-means clustering step groups trajectories with similar motion patterns before model training, effectively reducing the impact of data heterogeneity on prediction accuracy. Second, the deep learning backbone synergizes multi-scale convolution (MSC)—which captures local features at multiple temporal granularities via parallel kernels—with a bidirectional LSTM (BiLSTM) for forward–backward dependency learning, and an adaptive self-attention mechanism that dynamically optimizes feature weights to amplify critical navigation information. Extensive experiments on AIS data from the Gulf of Mexico and the U.S. Atlantic Coast, covering four seasons, benchmark the model against attention-enhanced architectures including Transformer, CNN-BiLSTM-ATTENTION, and DenseNet-BiGRU-ATTENTION across two distinct regions. The proposed model achieves significant improvements in predicting longitude, latitude, speed over ground, and course over ground, reducing MAE by over 76.9% and RMSE by over 65.3% compared with the strongest baseline. Ablation studies confirm that the synergy of all three modules is essential. The results demonstrate the model’s effectiveness and its practical value for intelligent maritime supervision, navigation risk warning, and waterborne traffic management.
- 17 May 2026
- Published by MDPI AG in Journal of Marine Science and Engineering
- Vol. 14  (10) , 924
Open AccessA Study on the MSC-BiLSTM Ship Track Prediction Model Incorporating an Adaptive Attention Mechanism
Accurate ship trajectory prediction is vital for intelligent maritime traffic management, yet conventional hybrid models often fail to balance local feature extraction, long-term dependency capture, and flexible feature weighting when processing AIS data. This paper proposes an MSC-BiLSTM-ATTENTION model that integrates trajectory clustering and an adaptive attention mechanism into a unified framework. Its fundamental advance over existing incremental hybrid architectures is twofold. First, a K-means clustering step groups trajectories with similar motion patterns before model training, effectively reducing the impact of data heterogeneity on prediction accuracy. Second, the deep learning backbone synergizes multi-scale convolution (MSC)—which captures local features at multiple temporal granularities via parallel kernels—with a bidirectional LSTM (BiLSTM) for forward–backward dependency learning, and an adaptive self-attention mechanism that dynamically optimizes feature weights to amplify critical navigation information. Extensive experiments on AIS data from the Gulf of Mexico and the U.S. Atlantic Coast, covering four seasons, benchmark the model against attention-enhanced architectures including Transformer, CNN-BiLSTM-ATTENTION, and DenseNet-BiGRU-ATTENTION across two distinct regions. The proposed model achieves significant improvements in predicting longitude, latitude, speed over ground, and course over ground, reducing MAE by over 76.9% and RMSE by over 65.3% compared with the strongest baseline. Ablation studies confirm that the synergy of all three modules is essential. The results demonstrate the model’s effectiveness and its practical value for intelligent maritime supervision, navigation risk warning, and waterborne traffic management.
- 20 April 2026
- Published by Elsevier in Measurement
- Vol. 277
An adaptive recognition model for tool wear state across multiple datasets
- 20 April 2026
- Published by Elsevier in Measurement
- Vol. 277
An adaptive recognition model for tool wear state across multiple datasets
- 19 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25  (13) , 24907-24919
Optimal Clustering on Spectral Line in Inertial Parameter Identification From Experimental Data
The accurate identification of inertial parameters is essential for studying dynamic system behaviors, where frequency-domain inertia restraint methods are widely recognized for their computational efficiency and precision. However, these conventional approaches remain insufficient in resolving uncertainties associated with mass-line frequency band selection, which may compromise inertial parameter identification accuracy. To address this limitation, the paper analyses the relationship between the frequency response function and the inertia parameters, replaces the traditional idea of determining all inertia parameters by the spectral line optimization of a single inertia parameter, establishes the optimization criterion of the inertia parameter, and improves the efficiency and accuracy of the inertia parameter by combining the method of cluster analysis. The acceleration sensor and force sensors were employed to acquire the experimental data of the modal test, enabling the frequency response function analysis and modal parameters extraction. Comparative validation against traditional methods demonstrates that the proposed approach significantly enhances the accuracy and efficiency of rigid-body inertial parameter identification. The results validate the efficacy of parameter refinement and cluster-based optimization in inertia restraint methods for rigid-body inertial parameter determination, providing an optimal clustering framework for dynamic system parameter identification.
- 19 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25  (13) , 24907-24919
Optimal Clustering on Spectral Line in Inertial Parameter Identification From Experimental Data
The accurate identification of inertial parameters is essential for studying dynamic system behaviors, where frequency-domain inertia restraint methods are widely recognized for their computational efficiency and precision. However, these conventional approaches remain insufficient in resolving uncertainties associated with mass-line frequency band selection, which may compromise inertial parameter identification accuracy. To address this limitation, the paper analyses the relationship between the frequency response function and the inertia parameters, replaces the traditional idea of determining all inertia parameters by the spectral line optimization of a single inertia parameter, establishes the optimization criterion of the inertia parameter, and improves the efficiency and accuracy of the inertia parameter by combining the method of cluster analysis. The acceleration sensor and force sensors were employed to acquire the experimental data of the modal test, enabling the frequency response function analysis and modal parameters extraction. Comparative validation against traditional methods demonstrates that the proposed approach significantly enhances the accuracy and efficiency of rigid-body inertial parameter identification. The results validate the efficacy of parameter refinement and cluster-based optimization in inertia restraint methods for rigid-body inertial parameter determination, providing an optimal clustering framework for dynamic system parameter identification.
- Open Access
- 11 April 2025
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 58  (7) , 1-31
Modeling and effect analysis of machining parameters for surface roughness and specific energy consumption during TC18 machining using deep reinforcement learning and neural networks
- 11 April 2025
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 58  (7) , 1-31
Open AccessModeling and effect analysis of machining parameters for surface roughness and specific energy consumption during TC18 machining using deep reinforcement learning and neural networks
- 25 November 2024
- Published by Springer Nature in JOM
- Vol. 77  (4) , 1727-1745
Multiobjective Optimization of the Difficult-to-Machine Material TC18 Based on AVOA-SVR and MOAVOA
- 25 November 2024
- Published by Springer Nature in JOM
- Vol. 77  (4) , 1727-1745
Multiobjective Optimization of the Difficult-to-Machine Material TC18 Based on AVOA-SVR and MOAVOA
- 22 October 2024
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 135  (5-6) , 2755-2776
Optimization of machining efficiency and side quality in irregular sheet metal parts milling based on improved multi-objective seagull optimization algorithm
- 22 October 2024
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 135  (5-6) , 2755-2776
Optimization of machining efficiency and side quality in irregular sheet metal parts milling based on improved multi-objective seagull optimization algorithm
- Open Access
- 15 April 2024
- Published by MDPI AG in Mathematics
- Vol. 12  (8) , 1187
Combining Autoregressive Integrated Moving Average Model and Gaussian Process Regression to Improve Stock Price Forecast
Stock market performance is one key indicator of the economic condition of a country, and stock price forecasting is important for investments and financial risk management. However, the inherent nonlinearity and complexity in stock price movements imply that simple conventional modeling techniques are not adequate for stock price forecasting. In this paper, we present a hybrid model (ARIMA + GPRC) which combines the autoregressive integrated moving average (ARIMA) model and Gaussian process regression (GPR) with a combined covariance function (GPRC). The proposed hybrid model can account for both the linearity and nonlinearity in stock price movements. Based on daily data on three stocks listed on the Shanghai Stock Exchange (SSE), it is found that GPRC outperforms GPR with a single covariance function. Further, the proposed hybrid model is compared with the ARIMA model, artificial neural network (ANN), and GPRC model. Based on the forecasting trend and the statistical performance of the four models, the ARIMA + GPRC model is found to be the dominant model for stock price forecasting and can significantly improve forecasting performance.
- 15 April 2024
- Published by MDPI AG in Mathematics
- Vol. 12  (8) , 1187
Open AccessCombining Autoregressive Integrated Moving Average Model and Gaussian Process Regression to Improve Stock Price Forecast
Stock market performance is one key indicator of the economic condition of a country, and stock price forecasting is important for investments and financial risk management. However, the inherent nonlinearity and complexity in stock price movements imply that simple conventional modeling techniques are not adequate for stock price forecasting. In this paper, we present a hybrid model (ARIMA + GPRC) which combines the autoregressive integrated moving average (ARIMA) model and Gaussian process regression (GPR) with a combined covariance function (GPRC). The proposed hybrid model can account for both the linearity and nonlinearity in stock price movements. Based on daily data on three stocks listed on the Shanghai Stock Exchange (SSE), it is found that GPRC outperforms GPR with a single covariance function. Further, the proposed hybrid model is compared with the ARIMA model, artificial neural network (ANN), and GPRC model. Based on the forecasting trend and the statistical performance of the four models, the ARIMA + GPRC model is found to be the dominant model for stock price forecasting and can significantly improve forecasting performance.
- Open Access
Optimization Method of Sheet Metal Laser Cutting Process Parameters under Heat Influence
To address the issues of workpiece distortion and excessive material melting caused by heat accumulation during laser cutting of thin-walled sheet metal components, this paper proposes a segmented optimization method for process parameters in sheet metal laser cutting considering thermal effects. The method focuses on predetermined perforation points and machining paths. Firstly, an innovative temperature prediction model is established for the nth perforation point during the cutting process, with a prediction error of less than 10%. Secondly, using the PSO-BP-constructed prediction model for laser cutting quality features and an empirical model for processing efficiency features, a multi-objective model for quality and efficiency is generated. The NSGA II algorithm is employed to solve the objective optimization model and obtain the Pareto front. Next, based on the predicted temperature at the perforation point using the model , the TOPSIS decision-making method is applied. Different weights for quality and efficiency are set during the cutting stages where the temperature is below the lower threshold and above the upper threshold. Various combinations of machining parameters are selected, and by switching the parameters during the cutting process, the thermal accumulation (i.e., temperature) during processing is controlled within a given range. Finally, the effectiveness of the proposed approach is verified through actual machining experiments.Open AccessOptimization Method of Sheet Metal Laser Cutting Process Parameters under Heat Influence
To address the issues of workpiece distortion and excessive material melting caused by heat accumulation during laser cutting of thin-walled sheet metal components, this paper proposes a segmented optimization method for process parameters in sheet metal laser cutting considering thermal effects. The method focuses on predetermined perforation points and machining paths. Firstly, an innovative temperature prediction model is established for the nth perforation point during the cutting process, with a prediction error of less than 10%. Secondly, using the PSO-BP-constructed prediction model for laser cutting quality features and an empirical model for processing efficiency features, a multi-objective model for quality and efficiency is generated. The NSGA II algorithm is employed to solve the objective optimization model and obtain the Pareto front. Next, based on the predicted temperature at the perforation point using the model , the TOPSIS decision-making method is applied. Different weights for quality and efficiency are set during the cutting stages where the temperature is below the lower threshold and above the upper threshold. Various combinations of machining parameters are selected, and by switching the parameters during the cutting process, the thermal accumulation (i.e., temperature) during processing is controlled within a given range. Finally, the effectiveness of the proposed approach is verified through actual machining experiments.