To address the complex layouts and dense inspection points of oilfield metering and water⁃injection facilities, where the conventional A* algorithm exhibits low search efficiency, this study proposes a path⁃planning method for oilfield inspection robots based on an improved weighted A* algorithm. First, metering rooms, water⁃injection rooms, stairways, doors, and various outdoor obstacles were modeled using the actual layout of the Shenyang Oil Production Plant of Liaohe Oilfield Company, and a regular 60×60 grid map was constructed. Multiple inspection targets were then defined according to the actual locations of on⁃site valves. A goal⁃distance⁃dependent dynamic weight function was introduced into the weighted A* framework to strengthen directional guidance during long⁃range planning while yielding smoother and more stable local paths near the target. An adaptive node projection mechanism and eight⁃neighborhood constraints were also incorporated to improve path feasibility and robustness in complex environments. In addition, a lightweight traveling salesman problem (TSP) heuristic based on the nearest⁃neighbor strategy was used to optimize the inspection sequence for indoor valves. Turning⁃point extraction was subsequently applied to simplify the planned paths and eliminate redundant nodes. The proposed method was validated in a three⁃dimensional simulation environment built using ROS2 and RViz. The results show that the improved weighted A* algorithm outperforms the conventional A* algorithm significantly in terms of path length, number of turning points, and trajectory smoothness, thereby enhancing the path⁃planning performance of oilfield inspection robots.

In the research on the thermal efficiency of atmospheric tube heating furnaces, it is necessary to conduct effective online measurement of thermal efficiency and select relatively reliable advanced control methods. On the basis of the research on the combustion mechanism of the heating furnace, the online measurement method based on the principle and data processing is used to process the thermal efficiency, and the "dynamic matrix control" is introduced in the process of optimizing the control of the heating furnace efficiency, which is compared with the traditional control method. The introduction of dynamic matrix control makes the system have a better control effect. At the same time, the "particle swarm algorithm" was selected to optimize the parameters of dynamic matrix control. In the optimization process of dynamic matrix parameters, the particle swarm algorithm relatively shortens the optimization time and improves the control quality, so as to achieve a more satisfactory control effect. Finally, compare with internal model control, it shows that dynamic matrix control can achieve relatively better control effect.

Aiming at the problem of temperature tracking and balance control of each branch pipe of the heating furnace, an improved genetic algorithm was proposed to optimize the multi?deviation control of the temperature tracking and balance of the branch pipe temperature of the heating furnace. The scheme used the temperature deviation of the raw materials of each branch pipe after mixing and the temperature deviation of each branch pipe. By adjusting the feed flow rate and fuel flow rate, it not only ensured that the flow rate of the main pipe is constant during the regulation process, but also realized the dual goal of temperature tracking and balance of each pass. Multi?passes are analyzed as a whole, so the temperature comparison of adjacent branch pipes was avoided repeatedly. At the same time, the improved genetic algorithm was used to optimize the controller parameters of the differences control technique, which overcomes the difficulty of controller parameter tuning. The simulation results show the feasibility and effectiveness of the improved genetic algorithm to optimize the differences control scheme.

In order to improve the balance between invisibility and robustness of image watermarking, a color image watermarking algorithm is studied by using wavelet transform and Heisenberg array decomposition （HAD） singular value decomposition （SVD）. Firstly, the host image and watermark image are transformed through color space color space, then the host image is transformed by wavelet transform, then the low frequency coefficients are decomposed by HAD and SVD, and the watermark is embedded after SVD in the low frequency. The experimental results show that the proposed watermarking method has strong robustness against multiple watermarking attacks, which is reflected by the normalized correlation NC of the objective evaluation criteria of extracted watermarks. The host image has good invisibility after embedded watermark, which is reflected by objective evaluation standard peak signal?to?noise ratio （PSNR） and structural similarity of images （SSIM）. It can embed grayscale or color large watermark with strong ability of embedding information. It is concluded that that the watermarking method has a certain application value.

The dry point of gasoline on the top of atmospheric tower is closely related to product quality, but it is difficult to measure the gasoline dry point online, and the soft sensor is a technical way to solve the estimation and control prediction of such variables. Due to the complexity of atmospheric and vacuum distillation process, the correlation between the variables increases. In this paper, sparse principal component analysis (SPCA) was introduced into kernel principal component analysis（KPCA） algorithm, and the input variables of the model were selected by sparse kernel principal component analysis（SKPCA） algorithm. The nonlinear dimensionality reduction between data was realized, the principal component structure was simplified, and the sparsity of principal component variables was increased. The selected sparse principal components were used as the input of the least squares support vector machine (LSSVM), and the soft sensor prediction model for the top dry point of atmospheric tower was established. The simulation results show that the SKPCA?LSSVM model has higher prediction accuracy and superior model performance compared with the traditional PCA?LSSVM and KPCA?LSSVM methods.