In order to demonstrate whether the sparrow search algorithm can show good performance in optimization, this paper improves the prediction model by this algorithm and predicts the change data of wood mechanical properties under different conditions, which better reflects the connection between the process parameters of wood heat treatment and the change of wood mechanical properties. The article takes the five main mechanical property parameters of thermally modified wood: compressive strength along the grain, flexural strength, flexural elastic modulus, radial hardness, and tangential hardness, respectively, as the objects of study and improves the sparrow search algorithm by Tenting chaotic mapping and then optimizes the Back Propagation (BP) network model by this algorithm. The results show that the number of iterations of the optimized Tent-Sparrow search algorithm-Back Propagation network model (TSSA-BP) is only one-eighth that of the original BP network model, and the convergence speed is greatly improved, the root mean square error of the TSSA-BP model is at least one-half times that of the original BP model, and the optimized model fits the original data better in terms of predicted values; thus, this article provided a feasible prediction algorithm for the field related to the mechanical property changes of wood after heat treatment.

Recently, Japan’s discharge of wastewater from the Fukushima nuclear disaster into the ocean has attracted widespread attention. To effectively address the challenge of separating uranium, the focus is on finding a healthy and environmentally friendly way to adsorb uranium using biochar. In this paper, a BP neural network is combined with each of the four meta-heuristic algorithms, namely Particle Swarm Optimization (PSO), Differential Evolution (DE), Cheetah Optimization (CO) and Fick’s Law Algorithm (FLA), to construct four prediction models for the uranium adsorption capacity in the treatment of radioactive wastewater with biochar: PSO-BP, DE-BP, CO-BP, FLA-BP. The coefficient of certainty (R²), error rate and CEC test set are used to judge the accuracy of the model based on the BP neural network. The results show that the Fick’s Law Algorithm (FLA) has a better search ability and convergence speed than the other algorithms. The importance of the input parameters is quantitatively assessed and ranked using XGBoost in order to analyze which parameters have a greater impact on the predictions of the model, which indicates that the parameters with the greatest impact are the initial concentration of uranium (C₀, mg/L) and the mass percentage of total carbon (C, %). To sum up, four prediction models can be applied to study the adsorption of uranium by biochar materials during actual experiments, and the advantage of Fick’s Law Algorithm (FLA) is more obvious. The method of model prediction can significantly reduce the radiation risk caused by uranium to human health during the actual experiment and provide some reference for the efficient treatment of uranium wastewater by biochar.

In this study, the CPA algorithm was used to optimize a BP neural network model to predict the bond strength and surface roughness of heat-treated wood. The neural network model was trained and optimized using MATLAB software. The results of the BP neural network, random forest algorithm, and optimized CPA-BP model were compared. The results show that the CPA-optimized BP neural network model has a better R² compared to the conventional BP neural network model. After using the CPA-optimized BP neural network model, the R² value increased by 8.1%, the MAPE value decreased by 3.74%, and the MAE value decreased by 33.91% in the prediction of the surface bond strength. The R² values increased by 3.02% and 20.47%, respectively, in predicting the mean and maximum values of surface roughness. The results indicate that the model is reliable in predicting wood bond strength and wood surface roughness. Using this model to predict wood bond strength and surface roughness can also reduce the required experimental cost.

Six hybrid models of cellulose amorphous region and water molecules were established by using a molecular dynamics software to simulate changes of cellulose and water molecules during bamboo hydrothermal treatment. The results indicated that in the range of hydrothermal treatment temperature of bamboo from 150 to 240 °C, the diffusion coefficient of water molecules increased with the increase of temperature, conducive to the processing efficiency of hydrothermal treatment. The mean square displacement (MSD) of the bamboo cellulose chain increased with the increase of temperature, not conducive to the thermal stability of cellulose. The energy change of the system predicts that a higher hydrothermal treatment temperature will result in faster material aging degradation. The comprehensive analysis of mechanical parameters showed that when the hydrothermal treatment temperature did not exceed 180 °C, bamboo cellulose had better plasticity and toughness.

Based on molecular dynamics, a water and cellulose model was constructed to provide more theoretical support for the behavior characteristics of cellulose properties in thermo-hydro-mechanical treatment. In this paper, dynamic simulations were carried out under the NPT ensemble at 4, 5.5, 8, and 12 MPa, respectively. Moreover, we analyze the effects on the mechanical properties of wood cellulose in terms of the hydrogen bond numbers, small molecule diffusion coefficients, end-to-end distances, and mechanical parameters of the water–cellulose model. The results indicate that the densification of the water–cellulose model gradually increases with increasing pressure. The effect of pressures on mechanical properties is mainly due to the formation of massive hydrogen bonds within the cellulose chain and between water and cellulose. This is reflected in the fact that water molecules are more difficult to diffuse in the cellulose, which therefore weakens the negative effect of large amounts of water on the cellulose. The increase in end-to-end distance represents the stiffness of the cellulose chains being strengthened. The mechanical parameters indicate an increase in wood stiffness to resist deformation better, while reducing tensile properties at the same time. The dynamic simulation results in this paper can well correspond to macroscopic experiments.

The existing original BP neural network models for wood performance prediction have low fitting accuracy and imprecise prediction results. We propose a nonlinear, adaptive grouping gray wolf optimization (NAGGWO)-BP neural network model for wood performance prediction. Firstly, the original gray wolf optimization (GWO) algorithm is optimized. We propose CPM mapping (the Chebyshev mapping method combined with piecewise mapping followed by mod operation) to generate the initial populations and improve population diversity, and an ‘S’-type nonlinear control parameter is proposed to balance the exploitation and exploration capabilities of the algorithm; an adaptive grouping strategy is also proposed, based on which the wolves are divided into the predator, wanderer, and searcher groups. The improved differential evolution strategy, the stochastic opposition-based learning strategy, and the oscillation perturbation operator are used to update the positions of the wolves in the different groups to improve the convergence speed and accuracy of the GWO. Then, the BP neural network weights and thresholds are optimized using the NAGGWO algorithm. Finally, we separately predicted heat-treated wood’s five main mechanical property parameters using different models. The experimental results show that the proposed NAGGWO-BP model significantly improved the mean absolute error (MAE), the mean square error (MSE), and the mean absolute percentage error (MAPE) of the specimens, compared with the BP, GWO-BP, and TSSA-BP algorithms. Therefore, this model has strong generalization ability and good prediction accuracy and reliability, which can fully meet practical engineering needs.