Traditional Inspection Methods Research Articles

Interface Waves for Detecting Defects in Bonded Hybrid Joints

Damage nucleation and growth can be complex in hybrid bonded structures composed of metals and laminated composites. There are limited reliable analytical and empirical methods to evaluate the bond integrity of such structures and to quantify the state of bonding in hybrid joints. Depending on the geometry and accessibility to hybrid joint sections, ultrasonic Nondestructive Testing (NDT) techniques are available for inspection of these structures. The interfacial damages at the bondline of structural joints represent challenging detection tasks for traditional ultrasonic nondestructive inspection (NDI) methods such as the pulse–echo method. This work investigates a method for bonded joint inspection that uses interface guided ultrasonic waves propagating along the bondline of these hybrid joints. An analysis, based on the use of finite element models for hybrid structures, is conducted to examine the use of interface waves to detect common defects found at or in the vicinity of interfaces of hybrid isotropic-anisotropic structures. Both cohesive and adhesive damage in a bonded joint are examined. Several damage scenarios are numerically studied and the guided wave time of flight (TOF) is shown to be sensitive to the size and location of interfacial damages. The results of this study suggest that interface guided waves can be used for integrity assessment and damage detection in hybrid structures.

Ground Crack Recognition Based on Fully Convolutional Network With Multi-Scale Input

Daily inspection of ground crack over mine goaf is a necessary task for environmental protection and mining safety. However, the traditional manual inspection method is time-consuming, misjudgement-prone and with potential dangers because the goaf normally locates in remote regions and inevitably induces complicated and gullies-cross landform. Therefore, Unmanned Aerial Vehicle(UAV) is adopted to capture aerial images of the ground crack, which provides a convenient way for goaf inspection. Though aerial images display a full view for the region containing cracks, the rugged terrain results in rich noises that have the similar characteristics with cracks in an image, such as shadow, cliff, terrace and so on, which may lead to misclassification of cracks. To overcome the obstacles, an improved semantic segmentation framework called MSI-FCN is proposed in the paper. Firstly, a statistic pre-processing method is employed to remove useless patches before training, with the purpose of decreasing the training complexity. Following that, a multi-scale input method is applied to integrate the patches with the output tensor of each stage based on FCN, which precisely recognizes pixel-level crack. Furthermore, a multi-scale connection module is constructed to select the most important contextual information from the features under multiple scales and help for recovering high-dimension features. In particular, a statistic weighted softmax cross-entropy loss function is presented so as to classify crack pixels more rationally. The experimental results for three groups of images under various environmental conditions indicate that MSI-FCN is superior to the FCN-8, FCD-56 and DeepCrack-GF. In addition, the proposed method also shows high performance on CFD and deepcrack dataset. Thus, multi-scale information embedded in the proposed method can provide more local details of low-level features to high-level stages and improve the recognition performances.

A New System for Steam Boiler Tubes Using Artificial Neural Network

A major inspection challenge facing the boiler industries is to satisfy the welds in tubing and plate during the manufacturing, erection and commissioning stages. During commercial operation the plant boiler tubes that leaks due to downtime. As the main part of the boiler, the water wall tube which runs on dangerous environment may lead to serious boiler accidents, causing of the tubes failure. For this reason, inspecting the defects on the steam boiler tube comprehensively is extremely required. However, single traditional NDT inspection method is limited .In terms of the ability of identifying different kinds of defects. In order to meet the requirement of fullscale inspection, in this paper, a new system foe steam boiler tubes are experimented. After experiment, the new system can effectively measure the remaining wall thickness and identify different kinds of defects including pinholes and circumferential cracks with the sensor being moved outside the tubes using artificial neural networks.

A convolutional neural network approach for counting and geolocating citrus-trees in UAV multispectral imagery

Visual inspection has been a common practice to determine the number of plants in orchards, which is a labor-intensive and time-consuming task. Deep learning algorithms have demonstrated great potential for counting plants on unmanned aerial vehicle (UAV)-borne sensor imagery. This paper presents a convolutional neural network (CNN) approach to address the challenge of estimating the number of citrus trees in highly dense orchards from UAV multispectral images. The method estimates a dense map with the confidence that a plant occurs in each pixel. A flight was conducted over an orchard of Valencia-orange trees planted in linear fashion, using a multispectral camera with four bands in green, red, red-edge and near-infrared. The approach was assessed considering the individual bands and their combinations. A total of 37,353 trees were adopted in point feature to evaluate the method. A variation of σ (0.5; 1.0 and 1.5) was used to generate different ground truth confidence maps. Different stages (T) were also used to refine the confidence map predicted. To evaluate the robustness of our method, we compared it with two state-of-the-art object detection CNN methods (Faster R-CNN and RetinaNet). The results show better performance with the combination of green, red and near-infrared bands, achieving a Mean Absolute Error (MAE), Mean Square Error (MSE), R2 and Normalized Root-Mean-Squared Error (NRMSE) of 2.28, 9.82, 0.96 and 0.05, respectively. This band combination, when adopting σ = 1 and a stage (T = 8), resulted in an R2, MAE, Precision, Recall and F1 of 0.97, 2.05, 0.95, 0.96 and 0.95, respectively. Our method outperforms significantly object detection methods for counting and geolocation. It was concluded that our CNN approach developed to estimate the number and geolocation of citrus trees in high-density orchards is satisfactory and is an effective strategy to replace the traditional visual inspection method to determine the number of plants in orchards trees.

Automatic sleep stages classification using optimize flexible analytic wavelet transform

Sleep stages classification avails the diagnosis and treatment of sleep-related disorders. The traditional visual inspection methods used by sleep-experts are time-consuming and error-prone. This framework proposes, an automatic sleep stages classification method based on optimize flexible analytic wavelet transform (OFAWT) for electroencephalogram (EEG) signals. In OFAWT, the parametric optimization is performed to obtain the most appropriate basis for the representation of EEG signals. The OFAWT parameters are selected by solving inequality constraints problem using the genetic algorithm. OFAWT decomposes EEG signal into band-limited basis or sub-bands (SBs). Time domain measures of SBs are used as features for the sleep stages EEG signals. The statistical significance of extracted features is assessed by multiple-comparison post hoc analysis of Kruskal–Wallis test, which ensures that reported features are statistically significant for the discrimination of sleep stages. The SB-wise features set is tested through the variants of decision tree, discriminant analysis, k-nearest neighbor, and ensemble classifiers for sleep stages classification. The ensemble classification model bagged-tree yields better classification accuracies for the classification of six to two sleep stages 96.03%, 96.39%, 96.48%, 97.56%, and 99.36%, respectively as compared to other existing methods.

Design of patrol and control platform for power network based on UAV and VR

Since the beginning of the twenty-one th century, with the rapid development of China’s economy and the continuous progress of China’s power industry, it has contributed an indelible force to the development of China’s socialist undertakings The construction of power grid is very important to the development of society. The normal operation of the power grid can not be separated from regular inspection of power grid equipment and lines, so as to keep abreast of and understand the operation of power transmission lines and changes in the surrounding environment and Line Protection Areas Is the power supply enterprise a heavy daily work. Manual inspection is a traditional inspection method, but also the main way of transmission line inspection. Due to the complex terrain of the transmission line corridor, there are almost no patrol roads in some sections along the route in some harsh conditions such as river-crossing or high mountains and steep mountains. This patrol method has great labor intensity and difficult working conditions Transmission lines can not get timely feedback, and can not observe the real-time intuitive operation of lines and equipment. In this case, in response to the national “Internet +” strategic thinking, we initiated the “Internet +”, “UAV +” and “VR +” all-ecological power grid patrol mode Realize the power network equipment long-distance inspection, all-round inspection, real-time simulation inspection, inspection in bad environment, so that the cause of power inspection can take off.

Research and Application of Inspecting Mode of Converter Station Equipment in the Background of Smart Grid

The inspection of equipment at the converter station is a basic work to discover equipment defects in time, ensure the safe and stable operation of the equipment in the converter station, and improve the reliability of the operation of the inter-area power grid. It mainly relies on the operation and maintenance personnel to perform periodic and regular periodic inspections. In order to ensure the safety and stability of the operation of the converter station equipment, ensure the patrol personnel arrival rate, realize the goal of scientific, standardized and intelligent inspection. On the basis of manual inspection, the advanced robot patrol system is used to design the intelligence of the converter station. The system was patrolled and the modules of the system’s back-end management system were analyzed. The system’s patrol management, defect management, equipment management, query analysis and system management functions are introduced in detail and applied to the actual patrol management work. The inspection method is compared with the traditional inspection method, and good practice results are obtained.

Inspection method for random simulation of runoff sequence based on sample entropy and statistical parameters

The traditional inspection method of runoff simulation sequences is based on statistical parameters. While the method can reflect the coincidence of statistical parameters of runoff simulation series and observed data at different time intersections, it ignores the characteristics of runoff as time series (e.g., nonlinearity, dissipation and complexity) which might be required in hydrological engineering. By introducing the concept of sample entropy to quantify complexity, we proposed a new method based on sample entropy and statistical parameters for inspecting random simulation runoff sequences, which can supplement the previous test method. To test the new method, we used the monthly runoff simulation series of Luohe Hydrological Station in Huaihe River Basin, Tanghe Hydrological Station in Yangtze River Basin and Heishiguan Hydrological Station in Yellow River Basin as examples. Our evaluation revealed that this new inspection method can effectively find anomalies (ignored by statistical parameters) about flow value and distribution location of the monthly runoff; and estimate the error values of flow and distribution location in simulation sequences of three basins. Compared to the previous inspection method, this new method can screen out the simulation sequences of higher accuracy more effectively, which offers a new way to improve the accuracy of simulation sequences.

Rapid Acquisition and Identification of Structural Defects of Metro Tunnel.

Metro systems in urban cities demand rapid inspection methods, in order to identify critical structural defects in a timely manner. However, traditional inspection methods are only specific to one kind of structural defect, which reduces the overall efficiency of inspection. This study proposes an integrated solution for rapidly acquiring and identifying two kinds of structural defects (surface defects and cross-sectional deformation) in a metro tunnel, using a cart equipped with non-metric cameras. The integrity and rapidity are considered in formulating a systematic design for the development of the acquisition device. Methodologies based on image processing and photogrammetry are proposed to identify the structural defects of the metro tunnel. A series of on-site tests validate that the proposed method has enough speed and has acceptable accuracy in detecting critical structural defects of metro tunnels. The cost and efficiency analysis shows that the proposed method is competitive, which will greatly improve the efficiency and reduce the costs of the inspection of metro tunnels.

A high precision crack classification system using multi-layered image processing and deep belief learning

Road surfaces experience fatigue stress and loading, which often lead to cracks on the surface. The cracks might cause serious damage, and therefore, early detection can reduce the road maintenance cost. Traditional inspection methods are carried out by humans and are slow, costly and hazardous. To improve accuracy and reduce the hazards of current crack detection methods, this paper proposes a new autonomous crack detection system (ACDS) that can be used in any autonomous vehicles (UAVs). ACDS consists of three stages: image acquisition, image processing, and classification. The image processing stage consists of five parallel filtering methods, which remove noise and extract features from the images. In the classification stage, five deep belief network (DBN) classifiers separately analyse the images to detect cracks. The dataset used in this paper contains 15,000 RGB and infrared images, with or without cracks. The results show the high precision of the proposed system.

An Examination of Measurement Procedures and Characteristics of Baseline Outcome Data in Single-Case Research

There has been growing interest in using statistical methods to analyze data and estimate effect size indices from studies that use single-case designs (SCDs), as a complement to traditional visual inspection methods. The validity of a statistical method rests on whether its assumptions are plausible representations of the process by which the data were collected, yet there is evidence that some assumptions-particularly regarding normality of error distributions-may be inappropriate for single-case data. To develop more appropriate modeling assumptions and statistical methods, researchers must attend to the features of real SCD data. In this study, we examine several features of SCDs with behavioral outcome measures in order to inform development of statistical methods. Drawing on a corpus of over 300 studies, including approximately 1,800 cases, from seven systematic reviews that cover a range of interventions and outcome constructs, we report the distribution of study designs, distribution of outcome measurement procedures, and features of baseline outcome data distributions for the most common types of measurements used in single-case research. We discuss implications for the development of more realistic assumptions regarding outcome distributions in SCD studies, as well as the design of Monte Carlo simulation studies evaluating the performance of statistical analysis techniques for SCD data.

Inspection Method for Satellite Grounding Network based on 3D model

This paper reviews the traditional grounding network inspection method based on 2D drawings in assembly and integration process of satellite. Due to the huge difference between different satellites grounding network, the symmetry of the satellite structure and the similarity of the deck structure, the grounding network assembly and inspection is error-prone. An effective and accurate grounding network assembly information transmission method from designers to inspectors is designed, the dedicated 3D model and 2D catalogue are created, and the AR technology is used to check the integrity and continuity of the grounding network. The successful application of this method provides a new solution for satellite grounding network inspection.

Towards Automatic Segmentation and Recognition of Multiple Precast Concrete Elements in Outdoor Laser Scan Data

To date, to improve construction quality and efficiency and reduce environmental pollution, the use of precast concrete elements (PCEs) has become popular in civil engineering. As PCEs are manufactured in a batch manner and possess complicated shapes, traditional manual inspection methods cannot meet today’s requirements in terms of production rate of PCEs. The manual inspection of PCEs needs to be conducted one by one after the production, resulting in the excessive storage of finished PCEs in the storage yards. Therefore, many studies have proposed the use of terrestrial laser scanners (TLSs) for the quality inspection of PCEs. However, all these studies focus on the data of a single PCE or a single surface of PCE, which is acquired from a unique or predefined scanning angle. It is thus still inefficient and impractical in reality, where hundred types of PCEs with different properties may exist. Taking this cue, this study proposes to scan multiple PCEs simultaneously to improve the inspection efficiency by using TLSs. In particular, a segmentation and recognition approach is proposed to automatically extract and identify the different types of PCEs in a large amount of outdoor laser scan data. For the data segmentation, 3D data is first converted into 2D images. Image processing is then combined with radially bounded nearest neighbor graph (RBNN) algorithm to speed up the laser scan data segmentation. For the PCE recognition, based on the as-designed models of PCEs in building information modeling (BIM), the proposed method uses a coarse matching and a fine matching to recognize the type of each PCE data. To the best of our knowledge, no research work has been conducted on the automatic recognition of PCEs from a million or even ten million of the outdoor laser scan points, which contain many different types of PCEs. To verify the feasibility of the proposed method, experimental studies have been conducted on the PCE outdoor laser scan data, considering the shape, type, and amount of PCEs. In total, 22 PCEs including 12 different types are involved in this paper. Experiment results confirm the effectiveness and efficiency of the proposed approach for automatic segmentation and recognition of different PCEs.

Use of gaming technology to bring bridge inspection to the office

This paper proposes a novel method for bridge inspection that essentially digitises bridges using Light Detection and Ranging (LIDAR) so that they can be later inspected in a virtual reality (VR) environment. The work uses conventional terrestrial LIDAR together with affordable VR hardware and freely available software development kits originally intended for authoring computer games. The resulting VR app is evaluated for a case study involving a typical masonry bridge, comparing the proposed technique with traditional inspection methods. The new approach promises to be highly effective in terms of interpretation of results, accessibility to critical areas and safety of inspectors. The work represents an important step towards the creation of digital twins of important assets in the built environment. Recent bridge collapse incidents have affected local economies, traffic congestion, and in some extreme cases led to a loss of life. The work is timely as law making agencies are paying greater attention to structural rehabilitation. This paper will be of particular interest to bridge engineers, construction professionals and law makers and could lead to future revisions of bridge inspection processes and standards.

Comparison of Detection Effect of Cavities Behind Shield Tunnel Segment Using Transient Electromagnetic Radar and Ground Penetration Radar

Nowadays, evaluation of cavities behind shield lining segment is still a problem in the engineering inspection field. In order to make up the limitation of the traditional inspection method which is the transient electromagnetic method (TEM) and the ground penetration radar method (GPR). In this paper, a new detection technique is proposed, based on the principle of the TEM, a self-developed product, transient electromagnetic radar (TER) is applied for the research of the evaluation of cavities behind shield tunnel lining segment. The feasibility of cavities detection using TER is proved by designed modeling test, the pattern of resistivity changes during the test are summarized for distinguishing different contact status behind the tunnel segment. Meanwhile, a constructed shield tunnel is used for the field test to comparing the application effect between 900 MHz antenna GPR and TER. Through analysis test images and abnormal signals measured by TER and GPR, and verified by drilling tests, results show that TER has much clearer images than GPR in interpretation data. Development of the TER technique gives engineers a new solution for the detection of cavities behind the segment and has wide application prospects.

A routing algorithm for inspecting grid transmission system using suspended robot: Enhancing cost-effective and energy efficient infrastructure maintenance

The inspection of transmission line using suspended based robots has drawn great attention from many utility companies. Such an emerging smart technology has the advantages of energy efficiency, cost effectiveness, safety, non-service interruption, and the potential of substituting for the traditional inspection method using linemen with the help of helicopter. In this paper, we propose a routing algorithm to identify locations where the ground control station needs to be deployed when using suspended robot in transmission line inspection. The motion and location between the suspended robot and the ground team are coordinated. The bidirectional data transmission between two sides can be guaranteed so that the live signal can be received and processed, robot motion can be controlled, large size obstacles can be appropriately cleared, and health condition of the transmission line can be captured. A case study based on a segment of the transmission line in the state of Missouri of the United States is implemented to validate the effectiveness of the proposed routing algorithm. Results of the case study illustrate that the performance from both economic and environmental aspects can be significantly improved compared to the traditional inspection mode employing helicopter and linemen as well as an ad-hoc routing algorithm currently used by some utility companies to guide the suspended robot in transmission line inspection. Specifically, compared to the ad-hoc routing algorithm and helicopter with photoelectric stabilized pod, the proposed algorithm can reduce the unit cost by 7.55% and 8.04%; and cut the unit emission by 21% and 98%, respectively.

Exploring Technological Alternatives to the Visual Inspection Method in the Built Environment

Buildings show symptoms and suffer injuries or failures that demand efficient approaches and sustainable solutions in order to maintain or improve their condition. In previous studies, the authors of this paper proposed a network methodology which stores and analyzes information on the degradation of the built environment in different cities, based on a visual inspection methodology for data collection. The demand for accurate information analysis of facades, along with the inspection time for each facade, creates a need for new information collecting techniques. Therefore, this article aims to evaluate technological equipment incorporated in the traditional inspection methods that can work as a complement to achieve better and more advanced results. For this, an experiment was carried out in the city of Brno, Czech Republic, where five building facades in the city center were analyzed in order to qualify and validate a mobile georeferenced scanner, static georeferenced scanner and thermographic camera equipment for potential incorporation into the current inspection method. Quantitative and qualitative analyses are included, together with some of the capabilities and potential uses of these technological resources for an improvement in the network methodology.

A Fast Algorithm for Rail Extraction Using Mobile Laser Scanning Data

Railroads companies conduct regular inspections of their tracks to maintain and update the geographic data for railway management. Traditional railroad inspection methods, such as onsite inspections and semi-automated analysis of imagery and video data, are time consuming and ineffective. This study presents an automated effective method to detect tracks on the basis of their physical shape, geometrical properties, and reflection intensity feature. This study aims to investigate the feasibility of fast extraction of railroad using onboard Velodyne puck data collected by mobile laser scanning (MLS) system. Results show that the proposed method can be executed rapidly on an i5 computer with at least 10 Hz. The MLS system used in this study comprises a Velodyne puck/onboard GNSS receiver/inertial measurement unit. The range accuracy of Velodyne puck equipment is 2 cm, which fulfills the need of precise mapping. Notably, positioning STD is lower than 4 cm in most areas. Experiments are also undertaken to evaluate the timing of the proposed method. Experimental results indicate that the proposed method can extract 3D tracks in real-time and correctly recognize pairs of tracks. Accuracy, precision, and sensitivity of total test area are 99.68%, 97.55%, and 66.55%, respectively. Results suggest that in a multi-track area, close collaboration between MLS platforms mounted on several trains is required.

Planning and executing construction inspections with unmanned aerial vehicles

Abstract Unmanned aerial vehicles (UAV) are increasingly recognised as a utility for inspection applications in construction. In order to create measurable benefit over traditional inspection methods, an inspection concept for UAVs must be integrated and automated. This work is the result of an ongoing effort to create a workflow for the structured planning, simulation and execution of inspection tasks. An application was developed that allows the operator to plan inspections in a 3D environment. The application automatically generates collision-free flight paths based on Building Information Modelling (BIM) data. A realistic simulation environment provides a good understanding of the flight dynamics caused by inhibiting factors, such as disturbances of the positioning system. A case study confirms the hypothesis of the inspection concept and hints at technical limitations of autonomous UAVs that need to be overcome in subsequent development efforts.

An Accurate Mura Defect Vision Inspection Method Using Outlier-Prejudging-Based Image Background Construction and Region-Gradient-Based Level Set

The visual inspection of Mura defects is still a challenging task in the quality control of panel displays because of the intrinsically nonuniform brightness and blurry contours of these defects. The current methods cannot detect all Mura defect types simultaneously, especially small defects. In this paper, we introduce an accurate Mura defect visual inspection (AMVI) method for the fast simultaneous inspection of various Mura defect types. The method consists of two parts: an outlier-prejudging-based image background construction (OPBC) algorithm is proposed to quickly reduce the influence of image backgrounds with uneven brightness and to coarsely estimate the candidate regions of Mura defects. Then, a novel region-gradient-based level set (RGLS) algorithm is applied only to these candidate regions to quickly and accurately segment the contours of the Mura defects. To demonstrate the performance of AMVI, several experiments are conducted to compare AMVI with other popular visual inspection methods are conducted. The experimental results show that AMVI tends to achieve better inspection performance and can quickly and accurately inspect a greater number of Mura defect types, especially for small and large Mura defects with uneven backlight. Note to Practitioners —The traditional Mura visual inspection method can address only medium-sized Mura defects, such as region Mura, cluster Mura, and vertical-band Mura, and is not suitable for small Mura defects, for example, spot Mura. The proposed accurate Mura defect visual inspection (AMVI) method can accurately and simultaneously inspect not only medium-sized Mura defects but also small and large Mura defects. The proposed outlier-prejudging-based image background construction (OPBC) algorithm of the AMVI method is employed to improve the Mura true detection rate, while the proposed region-gradient-based level set (RGLS) algorithm is used to reduce the Mura false detection rate. Moreover, this method can be applied to online vision inspection: OPBC can be implemented in parallel processing units, while RGLS is applied only to the candidate regions of the inspected image. In addition, AMVI can be extended to other low-contrast defect vision inspection tasks, such as the inspection of glass, steel strips, and ceramic tiles.