Wall crack detection is one of the primary tasks in determining the structural integrity of a building for both restorative and preventive attempts. Machine learning techniques, such as deep learning (DL) with computer vision capabilities, have gradually become more prevalent as they can provide expert assessments with an acceptable performance when the crack detection involves a considerable number of structures. Despite such a prospective application, classification on different types of wall cracks is relatively less common, possibly due to the absence of the professional-standard-to-dataset translation. In this work, we utilised a complete pipeline, starting from novel dataset construction, ground truth formulation based on civil engineering standards, and training and testing steps. Our work focused on multi-class classification with regard to the binary classification (i.e., determining only two categories) used in previous studies. We implemented transfer learning based on VGG16 and RestNET50 for feature extraction, combined them with an ANN and kNN for the classifier, and compared their prediction performances. Our results indicate that the developed models can distinguish images that contain wall cracks into three categories of features based on the degree of damage: light, medium, and severe. Furthermore, since greyscale images offer more precise readings and predictions, the use of augmentation in dataset generation is critical. Although ResNet50 is the most stable network in terms of accuracy, it performs better when paired with kNN.

Purpose: Structural health monitoring (SHM) has gained significant attention due to its capability in providing support for efficient and optimal bridge maintenance activities. However, despite the promising potential, the effectiveness of SHM system might be hindered by unprecedented factors that impact the continuity of data collection. This research presents a framework utilising convolutional neural network (CNN) for estimating structural response using environmental variations.Design/methodology/approach: The CNN framework is validated using monitoring data from the Suramadu bridge monitoring system. Pre-processing is performed to transform the data into data frames, each containing a sequence of data. The data frames are divided into training, validation and testing sets. Both the training and validation sets are employed to train the CNN models while the testing set is utilised for evaluation by calculating error metrics such as mean absolute error (MAE), mean absolute percentage error (MAPE) and root mean square error (RMSE). Comparison with other machine learning approaches is performed to investigate the effectiveness of the CNN framework.Findings: The CNN models are able to learn the trend of cable force sensor measurements with the ranges of MAE between 10.23 kN and 19.82 kN, MAPE between 0.434% and 0.536% and RMSE between 13.38 kN and 25.32 kN. In addition, the investigation discovers that the CNN-based model manages to outperform other machine learning models.Originality/value: This work investigates, for the first time, how cable stress can be estimated using temperature variations. The study presents the first application of 1-D CNN regressor on data collected from a full-scale bridge. This work also evaluates the comparison between CNN regressor and other techniques, such as artificial neutral network (ANN) and linear regression, in estimating bridge cable stress, which has not been performed previously.

Despite extensive study, performing Rapid visual screening is still a challenging task for many countries. The challenges include the lack of trained engineers, limited resources, and a large building inventory to detect. One of the most important aspect in rapid visual screening is to establish the building classification based on the guidelines’ specific criteria. This study proposes a general framework based on Convolutional Neural Network to perform automated building classification for the rapid visual screening procedure. The method classifies buildings based on the Federal Emergency Management Agency (FEMA)-154 guidelines and uses transfer learning techniques from a pre-trained network. The Indonesian building portfolio is used as a case study and a dataset of building images generated through web-scraping on Google Search™ engines and Google StreetView™ website is used for the method validation. Results show that the proposed framework has promising potential to automate the building classification based on FEMA-154 guidelines.

Shell structure has been popular for various application in building, aerospace, oil and gas, ship and automobile industry. This type of element is light weight and can be provide great stiffness for large structure. Furthermore, it is very useful for building architecture and appearance. However, currently, construction is not only concerning structural strength but also focusing on building cost and its impact to environment. Finding the balance between structural strength, cost and aesthetic appearance is essentials this nowadays. Hence, construction framework to find the leeway between those parameters is greatly important. This paper will discuss the framework for shape optimization of shell element by using Genetic Algorithm (GA) method. The shape of structure will be developed from Non-Uniform Rationale Bi-Spline (NURBS). Finite element analysis based on Reissner-Mindlin plate theory is utilized to find the element stress within the structure. Genetic algorithm method will evaluate and perform search operation inside the result domain with constraints of structural weight and element stress. The framework then was implemented in numerical example to find its effectiveness on obtaining the most optimum shape of shell structure. Based on the numerical result, it is clear that the proposed frame work is able to reach the convergence to the optimum structure without violating the given constraints.

[IN] Untuk mengurangi pengaruh defleksi yang berlebihan pada gedung akibat beban gempa, dibutuhkan struktur yang dapat mereduksi pengaruh dari beban gempa yaitu struktur dinding geser. Corewall merupakan modifikasi dari struktur dinding geser yang dapat menahan pengaruh beban lateral dan efek torsi dari adanya eksentrisitas serta juga dapat difungsikan sebagai ruang lift. Dalam perencanaannya, corewall diberi bukaan yang difungsikan sebagai pintu untuk lift. Dengan adanya bukaan dapat memberikan pengaruh terhadap kekakuan pada corewall. Tujuan dari penelitian ini yaitu melakukan analisis terhadap kinerja sistem struktur frame dan corewall dengan bukaan dalam menahan beban lateral pada gedung tidak beraturan. Metode yang digunakan adalah analisis dinamik respon spektrum berdasarkan peraturan SNI 1726-2012. Tahapan awal dalam penelitian ini adalah menentukan posisi letak corewall yang yang terbaik. Setelah didapat posisi corewall yang optimal, selanjutnya dilakukan investigasi terhadap 12 tipe bukaan pada corewall untuk mengetahui model bukaan dengan kinerja deformasi akibat beban gempa. Hasil peneitian ini menunjukkan dari ke-12 tipe bukaan pada corewall, bukaan corewall pada model 11 lantai 7 untuk arah Y, kinerja simpangan antar lantai melebihi batasan simpangan antar lantai ijin sebesar 0,19%. Selain dari model 11, kinerja simpangan antar lantai pada model bukaan yang lain tidak melebihi dari batasan simpangan ijin. [EN] Structure equipped with shear wall is effective to reduce the effect of excessive deflection due to earthquake load. Core wall is a modification of shear wall that can withstand lateral loads and torsion effects due to eccentricity whilst also functioned as elevator room. Core wall is designed with openings that functioned as access path to elevators. The openings can influence the stiffness of core wall. This study discusses the analysis of irregular frame structure systems and core wall with openings against lateral loads. The method used in this paper is the dynamic response spectrum method based on Standar Nasional Indonesia (SNI) code 1726-2012. The initial stage of this research was to determine the position of the best core wall location. Having obtained the optimal core wall position, an investigation of 12 types of openings on the core wall was carried out to determine the opening model with the best lateral deformation performance due to earthquake load. The results of this research show the best lateral performance of 12 types of opening of core wall. The worst core wall openings model no. 11 shows the increasing inter-floor capacity by 0.19% from the requirements set by SNI 1726-2012. Meanwhile, other models show the performance of inter-floor deviation does not exceed the allowable deviation based on SNI the given code.