Offset Vector Research Articles

Application of OVT Domain Processing Technology in 3D Seismic Exploration of Coalbed Methane in Heshun Hengling Block

This study introduces the OVT (Offset Vector Tile) domain processing technology to improve the accuracy of small structure detection in 3D seismic exploration of coalbed methane in the Heshun-Hengling block in China. The OVT technology optimizes wide azimuth seismic data processing through steps such as facet division, five-dimensional regularization, pre-stack time migration, and azimuthal anisotropy correction. The results show that OVT processing retains azimuth information, enhancing the ability to reflect stratum changes with azimuth; azimuthal anisotropy correction improves the resolution of the profile. The profile after OVT processing has a natural waveform, good continuity of the phase axis, and a wide frequency band, meeting the requirements of the “Coalbed Methane Seismic Exploration Specification”. It demonstrates the advantages of OVT technology in imaging complex geological structures, providing a new perspective for seismic exploration.

An attention-based bilateral feature fusion network for 3D point cloud.

The widespread use of deep learning in processing point cloud data promotes the development of neural networks designed for point clouds. Point-based methods are increasingly becoming the mainstream in point cloud neural networks due to their high efficiency and performance. However, most of these methods struggle to balance both the geometric and semantic space of the point cloud, which usually leads to unclear local feature aggregation in geometric space and poor global feature extraction in semantic space. To address these two defects, we propose a bilateral feature fusion module capable of combining geometric and semantic data from the point cloud to enhance local feature extraction. In addition, we propose an offset vector attention module for better extraction of global features from point clouds. We provide specific ablation studies and visualizations in the article to validate our key modules. Experimental results show that the proposed method performs superior in both point cloud classification and segmentation tasks.

Pre-Stack Fracture Prediction in an Unconventional Carbonate Reservoir: A Case Study of the M Oilfield in Tarim Basin, NW China

The reservoir of the M oilfield in Tarim Basin is an unconventional fracture-cave carbonate rock, encompassing various reservoir types like fractured, fracture-cave, and cave, exhibiting significant spatial heterogeneity. Despite the limited pore space in fractures, they can serve as seepage pathways, complicating the connectivity between reservoirs. High-precision fracture prediction is critical for the effective development of these reservoirs. The conventional post-stack seismic attribute-based approach, however, is limited in its ability to detect small-scale fractures. To address this limitation, a novel pre-stack fracture prediction method based on azimuthal Young’s modulus ellipse fitting is introduced. Offset Vector Tile (OVT) gather is utilized, providing comprehensive information on azimuth and offset. Through analyzing azimuthal anisotropies, such as travel time, amplitude, and elastic parameters, smaller-scale fractures can be detected. First, the original OVT gather data are preprocessed to enhance the signal-to-noise ratio. Subsequently, these data are partially stacked based on different azimuths and offsets. On this basis, pre-stack inversion is carried out for each azimuth to obtain the Young’s modulus in each direction, and, finally, the ellipse fitting algorithm is used to obtain the orientation of the long axis of the ellipse and the ellipticity, indicating the fracture orientation and density, respectively. The fracture prediction results are consistent with the geological structural features and fault development patterns of the block, demonstrating good agreement with the imaging logging interpretations. Furthermore, the results align with the production dynamics observed in the production wells within the block. This alignment confirms the high accuracy of the method and underscores its significance in providing a robust foundation for reservoir connectivity studies and well deployment decisions in this region.

Rethinking Mesh Watermark: Towards Highly Robust and Adaptable Deep 3D Mesh Watermarking

The goal of 3D mesh watermarking is to embed the message in 3D meshes that can withstand various attacks imperceptibly and reconstruct the message accurately from watermarked meshes. The watermarking algorithm is supposed to withstand multiple attacks, and the complexity should not grow significantly with the mesh size. Unfortunately, previous methods are less robust against attacks and lack of adaptability. In this paper, we propose a robust and adaptable deep 3D mesh watermarking Deep3DMark that leverages attention-based convolutions in watermarking tasks to embed binary messages in vertex distributions without texture assistance. Furthermore, our Deep3DMark exploits the property that simplified meshes inherit similar relations from the original ones, where the relation is the offset vector directed from one vertex to its neighbor. By doing so, our method can be trained on simplified meshes but remains effective on large size meshes (size adaptable) and unseen categories of meshes (geometry adaptable). Extensive experiments demonstrate our method remains efficient and effective even if the mesh size is 190× increased. Under mesh attacks, Deep3DMark achieves 10%∼50% higher accuracy than traditional methods, and 2× higher SNR and 8% higher accuracy than previous DNN-based methods.

Adaptive fault enhancement in OVT domain based on anisotropy theory

As a result of the combined influence of multi-stage and multi-directional tectonic activities, the subsurface medium in complex structural areas can easily develop intricate fault systems with varying scales and directions. Post-stack seismic and azimuth-stack attributes have limited precision in recognizing such complex fault systems. In this paper, we propose an adaptive fault enhancement workflow in offset vector tile (OVT) domain based on anisotropy theory to improve the recognition ability of seismic data for multi-directional faults and minor faults. The vertical directions of fault strikes and tectonic strikes estimated by the gradient structure tensor (GST) can be used as sensitive observation azimuths of faults. At the same time, according to the anisotropic forward modeling and real data amplitude variation with offset (AVO) analysis of minor faults in marine shale of Wufeng-Longmaxi formations in Sichuan Basin, China, the incident angles with the largest difference between isotropic and anisotropic reflection coefficients can be used as sensitive incident angles of faults. A new fault enhancement seismic data can be reconstructed from the OVT gathers by traversing the sensitive azimuths and incident angles adaptively. The 3D model and real data indicate that the faults enhanced by the workflow we proposed are clearer in shape, smaller in scale, and richer in details, which is consistent with geology and well.

Horizontal transverse isotropy anisotropic parameter inversion via azimuthal seismic velocity anisotropy and its application to anisotropic 3D in-situ stress estimation

Anisotropic parameter inversion in horizontal transverse isotropy (HTI) media plays an important role in predicting the fracture density and the anisotropic in-situ stress for unconventional reservoirs. The current industry practice is to use the azimuthal PP-wave reflection coefficient to estimate the HTI anisotropic parameters. Based on the linear slip theory, we develop an innovative approach that uses azimuthal P-wave phase velocity to calculate HTI anisotropic parameters, which presents superiority over the conventional azimuthal PP-wave reflection coefficient inversion. Specifically, we first verify that the azimuthal P-wave phase velocity is for the HTI elliptical fitting than the azimuthal PP-wave reflection coefficient using the analytical formulations. Second, we sort the prestack wide-azimuth data into offset vector tile sectors and perform amplitude-variation-with-offset inversion at each azimuth. Third, we apply an elliptical fitting to the obtained azimuthal P-wave phase velocities to estimate the HTI anisotropic parameters, fracture density, and fracture direction. Fourth, based on the HTI mechanical earth model, we formulate a cost-effective 3D in-situ stress estimation method using the obtained elastic parameters and fracture compliance. Finally, field examples from the Zhaotong area, China, demonstrate that the estimated fracture density and anisotropic in-situ stress are more accurate and have higher resolution compared with conventional methods. The dominant stress regime in the study area is a strike-slip faulting regime with a governing orientation of northeast–southwest and presents good alignments with well logs, which demonstrates the reliability and accuracy of our method for predicting fracture density and anisotropic in-situ stress.

Cooperative Standoff Target Tracking using Multiple Fixed-Wing UAVs with Input Constraints in Unknown Wind

This paper investigates the problem of cooperative standoff tracking using multiple fixed-wing unmanned aerial vehicles (UAVs) with control input constraints. In order to achieve accurate moving target tracking in the presence of unknown background wind, a coordinated standoff target tracking algorithm is proposed. The objective of the research is to steer multiple UAVs to fly a circular orbit around a moving target with prescribed intervehicle angular spacing. To achieve this goal, two control laws are proposed, including relative range regulation and space phase separation. On one hand, a heading rate control law based on a Lyapunov guidance vector field is proposed. The convergence analysis shows that the UAVs can asymptotically converge to a desired circular orbit around the target, regardless of their initial position and heading. Through a rigorous theoretical proof, it is concluded that the command signal of the proposed heading rate controller will not violate the boundary constraint on the heading rate. On the other hand, a temporal phase is introduced to represent the phase separation and avoid discontinuity of the wrapped space phase angle. On this basis, a speed controller is developed to achieve equal phase separation. The proposed airspeed controller meets the requirements of the airspeed constraint. Furthermore, to improve the robustness of the aircraft during target tracking, an estimator is developed to estimate the composition velocity of the unknown wind and target motion. The proposed estimator uses the offset vector between the UAV’s actual flight path and the desired orbit, which is defined by the Lyapunov guidance vector field, to estimate the composition velocity. The stability of the estimator is proved. Simulations are conducted under different scenarios to demonstrate the effectiveness of the proposed cooperative standoff target tracking algorithm. The simulation results indicate that the temporal-phase-based speed controller can achieve a fast convergence speed and small phase separation error. Additionally, the composition velocity estimator exhibits a fast response speed and high estimation accuracy.

A Novel Approach to Match Individual Trees between Aerial Photographs and Airborne LiDAR Data

Integrating multimodal remote sensing data can optimize the mapping accuracy of individual trees. Yet, one issue that is not trivial but generally overlooked in previous studies is the spatial mismatch of individual trees between remote sensing datasets, especially in different imaging modalities. These offset errors between the same tree on different data that have been geometrically corrected can lead to substantial inaccuracies in applications. In this study, we propose a novel approach to match individual trees between aerial photographs and airborne LiDAR data. To achieve this, we first leveraged the maximum overlap of the tree crowns in a local area to determine the correct and the optimal offset vector, and then used the offset vector to rectify the mismatch on individual tree positions. Finally, we compared our proposed approach with a commonly used automatic image registration method. We used pairing rate (the percentage of correctly paired trees) and matching accuracy (the degree of overlap between the correctly paired trees) to measure the effectiveness of results. We evaluated the performance of our approach across six typical landscapes, including broadleaved forest, coniferous forest, mixed forest, roadside trees, garden trees, and parkland trees. Compared to the conventional method, the average pairing rate of individual trees for all six landscapes increased from 91.13% to 100.00% (p = 0.045, t-test), and the average matching accuracy increased from 0.692 ± 0.175 (standard deviation) to 0.861 ± 0.152 (p = 0.017, t-test). Our study demonstrates that the proposed tree-oriented matching approach significantly improves the registration accuracy of individual trees between aerial photographs and airborne LiDAR data.

Prediction and optimization of employee turnover intentions in enterprises based on unbalanced data.

The sudden resignation of core employees often brings losses to companies in various aspects. Traditional employee turnover theory cannot analyze the unbalanced data of employees comprehensively, which leads the company to make wrong decisions. In the face the classification of unbalanced data, the traditional Support Vector Machine (SVM) suffers from insufficient decision plane offset and unbalanced support vector distribution, for which the Synthetic Minority Oversampling Technique (SMOTE) is introduced to improve the balance of generated data. Further, the Fuzzy C-mean (FCM) clustering is improved and combined with the SMOTE (IFCM-SMOTE-SVM) to new synthesized samples with higher accuracy, solving the drawback that the separation data synthesized by SMOTE is too random and easy to generate noisy data. The kernel function is combined with IFCM-SMOTE-SVM and transformed to a high-dimensional space for clustering sampling and classification, and the kernel space-based classification algorithm (KS-IFCM-SMOTE-SVM) is proposed, which improves the effectiveness of the generated data on SVM classification results. Finally, the generalization ability of KS-IFCM-SMOTE-SVM for different types of enterprise data is experimentally demonstrated, and it is verified that the proposed algorithm has stable and accurate performance. This study introduces the SMOTE and FCM clustering, and improves the SVM by combining the data transformation in the kernel space to achieve accurate classification of unbalanced data of employees, which helps enterprises to predict whether employees have the tendency to leave in advance.

A Flexible and Decoupled Space Vector Modulation Scheme With Carrier-Based Implementation for Multilevel Converters

This article proposes a novel space vector pulse width modulation (SVPWM) scheme for multilevel converters in <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">abc</i> coordinate system, in which the reference vector is decomposed into an offset vector and a remainder vector that can be synthesized using two-level SVPWM. The switching state satisfying a specific relationship is first selected as the offset vector such that the common-mode components are eliminated and therefore the phase voltages are decoupled. A dynamic reference point mechanism establishes a one-to-one correspondence between all available vector combinations and one unique variable, i.e., the number of level shifts. This feature further facilitates a general approach to determining the optimum switching states to satisfy different control objectives, such as common-mode voltage rejection. Besides, phase decoupling enables the introduction of carrier-based modulation to simplify implementation, where the duty cycle of the zero vector can be flexibly adjusted while the non-zero vectors remain the same to generate an equivalent output. Consequently, two-level SVPWM-based method and carrier-based PWM are combined to exploit their respective strengths. The proposed scheme achieves overmodulation operation, and provides more flexibility, i.e., redundant switching states and adjustable duty cycles, to optimize switching patterns. Simulation and experimental results validate the proposed algorithm.

Converted PS-wave imaging based on offset vector tiles

Stacking using offset vector tiles (OVTs) is a technique used to simultaneously retain the offset and azimuth information in a wide-azimuth seismic survey by building minimal data sets of underground homogeneous illumination. Currently, derived from the assumption that reflection points and common midpoints are in the same lateral location because the raypath is symmetric, PP-wave OVT processing has been widely applied to seismic imaging and offset and/or azimuth analysis. However, it is difficult to directly apply the PP-wave OVT gathering method to the PS wave because the PS-wave raypath is asymmetric and the conversion point varies with depth. To solve this problem, we have developed an improved PS-wave OVT imaging technique based on the precise conversion point calculation and the equivalent converted-wave hypothesis, in which the PS-wave OVT gather with homogeneous illumination can be obtained in a manner similar to the PP wave. Moreover, to further improve the imaging quality, an azimuthal anisotropic normal moveout is applied to correct the traveltime difference. With tests of synthetic and field data, it can be concluded that our method represents a new and feasible solution for PS-wave OVT gathering.

Towards Enhanced Eddy Current Testing Array Probes Scalability for Powder Bed Fusion Layer-Wise Imaging

This work presents a new eddy current testing array probe and readout electronics that target the layer-wise quality control in powder bed fusion metal additive manufacturing. The proposed design approach brings important benefits to the sensors' number scalability, exploring alternative sensor elements and minimalist signal generation and demodulation. Small-sized, commercially available surface-mounted technology coils were evaluated as an alternative to usually employed magneto-resistive sensors, demonstrating low cost, design flexibility, and easy integration with the readout electronics. Strategies to minimize the readout electronics were proposed, considering the specific characteristics of the sensors' signals. An adjustable single phase coherent demodulation scheme is proposed as an alternative to traditional in-phase and quadrature demodulation provided that the signals under measurement showed minimal phase variations. A simplified amplification and demodulation frontend using discrete components was employed together with offset removal, vector amplification, and digitalization implemented within the microcontrollers' advanced mixed signal peripherals. An array probe with 16 sensor coils and a 5 mm pitch was materialized together with non-multiplexed digital readout electronics, allowing for a sensor frequency of up to 1.5 MHz and digitalization with 12 bits resolution, as well as a 10 kHz sampling rate.

One-Winged Momentum-Biased Solar Sail: A New Methodology for Propellantless Attitude Control

This paper proposes a new methodology for solar-sail attitude control that uses only momentum wheels. Different from conventional solar sails packaged in a central hub, the sailcraft is deployed in the direction of one side of the storage. In this single-wing configuration, the offset between the center of mass (c.m.) and center of pressure (c.p.) is large and lies in the sail plane. When specular reflection is dominant, solar-radiation-pressure (SRP) force vector points in the out-of-plane direction, thus causing an in-plane SRP torque orthogonal to the c.m./c.p. offset vector. Therefore, by placing a bias momentum in the c.m./c.p. direction, the sailcraft keeps rotating in the same plane while maintaining its orientation relative to the sun. Analysis reveals that the attitude motion of the one-winged momentum-biased solar sail is basically unstable, but the system can be stabilized in a neutral manner through minor control of the bias momentum. Furthermore, adding another control moment in the out-of-plane direction enables asymptotic stability. Control in the remaining in-plane direction makes it possible to avoid wheel saturation. Numerical simulations demonstrate that both attitude maintenance and maneuver can be performed and that the controller is robust to parameter errors.

Learning to Extract Building Footprints From Off-Nadir Aerial Images.

Extracting building footprints from aerial images is essential for precise urban mapping with photogrammetric computer vision technologies. Existing approaches mainly assume that the roof and footprint of a building are well overlapped, which may not hold in off-nadir aerial images as there is often a big offset between them. In this paper, we propose an offset vector learning scheme, which turns the building footprint extraction problem in off-nadir images into an instance-level joint prediction problem of the building roof and its corresponding "roof to footprint" offset vector. Thus the footprint can be estimated by translating the predicted roof mask according to the predicted offset vector. We further propose a simple but effective feature-level offset augmentation module, which can significantly refine the offset vector prediction by introducing little extra cost. Moreover, a new dataset, Buildings in Off-Nadir Aerial Images (BONAI), is created and released in this paper. It contains 268,958 building instances across 3,300 aerial images with fully annotated instance-level roof, footprint, and corresponding offset vector for each building. Experiments on the BONAI dataset demonstrate that our method achieves the state-of-the-art, outperforming other competitors by 3.37 to 7.39 points in F1-score. The codes, datasets, and trained models are available at https://github.com/jwwangchn/BONAI.git.

Fall Detection for Shipboard Seafarers Based on Optimized BlazePose and LSTM.

Aiming to avoid personal injury caused by the failure of timely medical assistance following a fall by seafarer members working on ships, research on the detection of seafarer’s falls and timely warnings to safety officers can reduce the loss and severe consequences of falls to seafarers. To improve the detection accuracy and real-time performance of the seafarer fall detection algorithm, a seafarer fall detection algorithm based on BlazePose–LSTM is proposed. This algorithm can automatically extract the human body key point information from the video image obtained by the vision sensor, analyze its internal data correlation characteristics, and realize the process from RGB camera image processing to seafarer fall detection. This fall detection algorithm extracts the human body key point information through the optimized BlazePose human body key point information extraction network. In this section, a new method for human bounding-box acquisition is proposed. In this study, a head detector based on the Vitruvian theory was used to replace the pre-trained SSD body detector in the BlazePose preheating module. Simultaneously, an offset vector is proposed to update the bounding box obtained. This method can reduce the frequency of repeated use of the head detection module. The algorithm then uses the long short-term memory neural network to detect seafarer falls. After extracting fall and related behavior data from the URFall public data set and FDD public data set to enrich the self-made data set, the experimental results show that the algorithm can achieve 100% accuracy and 98.5% specificity for the seafarer’s falling behavior, indicating that the algorithm has reasonable practicability and strong generalization ability. The detection frame rate can reach 29 fps on a CPU, which can meet the effect of real-time detection. The proposed method can be deployed on common vision sensors.

Supine Infant Pose Estimation via Single Depth Image

objective: The infant pose estimation is very important for the evaluation of infants&#x2019; brain development and motor quality. Here, we propose a new method to quickly build a large-scale depth image pose dataset, and on this basis, establish the XJTU-IDP dataset, then we also propose a new method based on joint feature coding to estimate the infants&#x2019; posture from depth image. Methods: First, we use Kinect V2 to collect depth and color images synchronously, and use the proposed framework to build a large dataset. Then we encode the offset vector in the confidence region of each joint of the infant, and export the joint positioning and connection encoding through our convolutional neural network (CNN) model. The proposed method is tested from two datasets (including 16 and 27 clinical actual infants, respectively). Results: When applied to pose estimation, the median root mean square distance (RMSD) calculated among all limbs is 4.12 pixels, which is much lower than the baseline (9.06 pixels) on babyPose dataset and RMSD in XJTU-IDP dataset is 3.93 pixels, which achieves the best in comparison with the state-of-the-arts. Conclusion: The proposed framework of the building dataset in our work is effective, and the joint feature coding can enrich the network information. Significance: Our work not only provides a larger infant pose dataset to make up for the deficiencies of babyPose, but also proposes a new framework for quickly establishing high-quality dataset. The proposed pose estimation method significantly improves the state of art in automatic measurement of infants&#x2019; health status.

ONSHORE SEISMIC IMAGING USING DIFFERENT DATA DOMAIN IN NORTHERN NIGER DELTA, NIGERIA

Wide azimuth land acquisition, 3D data is spatially well sampled with a wide range of azimuth and the offsets distributed around those azimuths. This work examined how advance seismic processing technique has come onshore, using offset vector tile methods, high-fidelity, high-resolution is available for use on onshore data. Data were split into one hundred and twenty four vector tiles as a function of source-to-detector distance and azimuth relationship individual pre-trace is assigned an offset vector tiles number that is stored in the trace headers the number is based on the relative shot and receiver location for the trace. Data is regularized to maintain the necessary number of traces and the range of offset in each bin and allow to be filled then migration of the target lines and stacking. After regularization for both the common offset binning and the offset vector tiles (OVTs), it was observed that there is improved signal to noise ratio in the offset vector tiles as compare to the common offset binning, and there is overall improvement in event continuity on the OVTs result. Because onshore (land) data exhibit poor signal-to-noise ratios arising from irregular geometries and noise contamination a fundamental change in processing methods is required. The offset vector tiles (OVTs) have proven to be an effective and efficient tool for 3D wide azimuth acquisitions, the OVTs domain pre-processing, will yield a better imaging when compared to the common offset binning (COB) domain pre-processing.

POI Detection of High-Rise Buildings Using Remote Sensing Images: A Semantic Segmentation Method Based on Multitask Attention Res-U-Net

A Point-Of-Interest (POI) represents a specific point location that may be useful or interesting for people, and therefore each and every building footprint in a topographic map can be recognized as a POI. Automatic extraction of building footprints using remote sensing images has become a challenging and important research topic which is in demand for urban planning and development. Extensive studies have explored a variety of semantic segmentation methods using deep learning algorithms to achieve better performance in building footprint extraction, however the existing algorithms were shown to have some limitations which lead to poor segmentation results. Building roofs were recognized as building footprints in the previous studies. This is prone to error especially for high-rise buildings due to different sensor view angles. In this paper, we propose a multi-task Res-U-Net model with attention mechanism for the extraction of the building roofs and the whole building shapes from remote sensing images, then use an offset vector method to detect the footprints of the high-rise buildings based on the boundaries of the corresponding building roofs and shapes. We also apply the online food delivery (OFD) data to parse the POI name of every building footprint. Several strategies are also developed in combination with the proposed model, including data augmentation and post-processing. We conduct numerical experiments using real data of remote sensing images and OFD historical order data. Results demonstrate that our proposed model achieves a total F1-score of 77.05% and intersection over union (IoU) of 63.55% in terms of the building roof segmentation, and an overall F1-score of 79.02% and IoU of 66.05% for the whole building shape segmentation, which both achieve the best performance among all baseline models.

Predicting the azimuth of natural fractures and in situ horizontal stress: A case study from the Sichuan Basin, China

The azimuth of fractures and in situ horizontal stress are important factors in planning horizontal wells and hydraulic fracturing for unconventional resource plays. The azimuth of natural fractures can be directly obtained by analyzing image logs. The azimuth of the maximum horizontal stress [Formula: see text] can be predicted by analyzing the induced fractures on image logs. The clustering of microseismic events also can be used to predict the azimuth of in situ maximum horizontal stress. However, the azimuth of natural fractures and the in situ maximum horizontal stress obtained from image logs and microseismic events are limited to the wellbore locations. Wide-azimuth seismic data provide an alternative way to predict the azimuth of natural fractures and maximum in situ horizontal stress if the seismic attributes are properly calibrated with interpretations from well logs and microseismic data. To predict the azimuth of natural fractures and in situ maximum horizontal stress, we have focused our analysis on correlating the seismic attributes computed from pre- and poststack seismic data with the interpreted azimuth obtained from image logs and microseismic data. The application indicates that the strike of the most-positive principal curvature [Formula: see text] can be used as an indicator for the azimuth of natural fractures within our study area. The azimuthal anisotropy of the dominant frequency component of offset vector title seismic data can be used to predict the azimuth of maximum in situ horizontal stress within our study area that is located in the southern region of the Sichuan Basin, China. The predicted azimuths provide important information for the subsequent well planning and hydraulic fracturing.

Simultaneous outline shape and size optimization for stiffeners in practical engineering structures

This article presents an engineering method to optimize the stiffener outline shape and cross-sectional sizes simultaneously for stiffened plate structures. A new optimization model for stiffened plate is established, and a hierarchical algorithm including external and internal optimization module is proposed to tackle the shape and size variables respectively. In external optimization, genetic algorithm (GA) is utilized to optimize binary-coded shape variables, and when calculating individual fitness values in GA, an internal optimization only involving size variables is carried out. For each individual, the stiffener outline shape is determined by a given shape variable vector and a reasonable finite element model could be automatically built with a parametric modeling method. The solution of internal optimization problem can be obtained by size optimization method, and an offset vector which updates during each cycle is created to modify the relative position of plate and stiffeners, ensuring the practicality of the optimal results in engineering. The presented approach is firstly verified through a typical example and then it is applied to the structural design of a micro-satellite. The results show that the method is effective in dealing with the simultaneous outline shape and size optimization problem of stiffeners, and the optimal results could be directly applied in practical engineering structures.