This PDF file contains the front matter associated with SPIE Proceedings Volume 12049, including the Title Page, Copyright information, Table of Contents, and Conference Committee listings.

In my plenary lecture at the SPIE symposium “Smart Structures and NDE” 2017, I introduced the name NDE 4.0 for the first time as part of the Industrial Revolution 4.0. That was almost exactly 5 years ago. A few months later, several organizations started activities and working groups for NDE 4.0. So we can say that NDE 4.0 was born at our SPIE symposium. We are now seeing a surge in activity in this area around the world. The first Handbook for NDE 4.0 is online. We see new books, a YouTube channel, two special editions of the Journal of NDE, several conferences and many papers. The key is, that manufacturing and inspection systems are linked in one cyber-controlled word. We still need excellent measurement systems and inspector decisions. However, this is recharged by creating, managing, and analyzing enormous amounts of data. We see a transition from physics to computer science as the driving force behind NDE. This paper is a look back at these 5 years of NDE 4.0 and an outlook to the future.

Today’s maintenance tasks are time-consuming and therefore cost-intensive, in particular the manual inspection of commercial airliners. The joint project ”AI-Inspection Drone” aims to provide a complete process chain for the surface damage detection of airliners based on an unmanned aerial system (UAS). To achieve this goal, visual data is gathered, which can later be evaluated by artificial intelligence models. The process chain is explained in detail, beginning with the simulation of the hangar environment, followed by insights about the indoor navigation of the UAS. Finally, it is validated through test flights around the airplane, respecting strict security and safety requirements. The 3D-simulation based on Gazebo was expanded with hardware-in-the-loop testing functionality by utilizing a camera-based motion capture system to track the UAS’s position in real-time and feed the position data back into the simulation, to test different inspection tasks. For the deployment of the UAS in the hangar, a 3D-LiDAR based SLAM algorithm is used to provide position and orientation data in relation to the airplane. Using a 3D model, which can be gathered beforehand with LiDAR scans, the airplane’s surface area is estimated to determine the mission waypoints and the corresponding inspection views for a high-resolution camera. A path planning algorithm controls the procedure of the inspection by evaluating an efficient path based on these waypoints and enables obstacle avoidance based on LiDAR data. With the proposed autonomous aerial inspection platform, the ground time of airplanes can be reduced, thus increasing the efficiency of the airplane inspection process.

The ever-increasing usage of multi-copters goes along with the necessity of guaranteeing a safe operation before, during and after the flight. As of today, Maintenance, Repair and Operations (MRO) aspects are not sufficiently considered, however, they will quickly gain importance as UAV operation becomes more professional, more frequent and more competitive. The key element of the UAV’s propulsion system are the propellers, which tend to be easily damaged by strikes or during the handling of the vehicles. The consequence is a reduced thrust and higher vibration, stressing the system as well as reducing its performance. Since the main source of sound is the propulsion system, we propose the use of acoustics as a means to detect damaged or imbalanced propellers at an early stage and without impairing UAV operation. In this paper, we present the concept for such non-destructive testing of a multi-copter. The fault diagnosis aims at identifying different system conditions such as an undamaged reference and an impaired propeller. The method is based on a machine learning algorithm with a neural network architecture. A prototype based on the structure of a single propeller is designed for a first experimental approach and the generation of data. In order to identify relevant features, this set-up is used to systematically explore the impact of recording procedures and setups on a successful diagnosis. Pertinent time and frequency domain features are then analyzed and the most promising ones are identified. From the results obtained, rules are derived for the implementation of an acoustic monitoring system for UAVs.

Quality assurance of complex parts, produced by elaborate process chains such as in industrialized additive manufacturing, requires the repeated digitization of products before and after each process step in order to detect any deviation from the planned geometry. This is necessary to enable the efficient production of small lot sizes in smart factories by counteracting those deviations through adaptive process control of downstream processes. The digitization of complex parts during production is often only feasible through a combination of different geometrical measurement technologies, e.g. CMM, xCT or optical 3D scanners, resulting in convoluted data sets consisting of incompatible measurement data from different points in time. In order to effectively utilize the generated data to its full potential, it is necessary to link related data while minimizing redundancy. For this purpose, the “Geometrical Digital Shadow” is proposed as a framework, which provides a way to condense all acquired geometrical data related to a physical object into a single source of truth. This work presents a methodology for a reversible fusion of geometrical data in form of meshes from different measurement technologies but also from different production steps along the process chain into a single evolving 3D model. By calculating and only saving the differences between the existing mesh and a newly generated measurement, just the relevant data is taken into account for further processing. The resulting 3D model encapsulates the data and origin of multiple measurements while reducing the overall data footprint and therefore offers the envisioned increase in information density.

Nowadays key factors in high technology industries are digitalization, networking, data management, informatization and automation. The mutual interactions between these factors led toward the quickly evolving industrial revolution called “Industry 4.0” (or IR4) defined as the integration of new technologies within the design, manufacturing, and maintenance processes. This dynamic scenario is made possible by the so-called Internet of Things (IoT). In this context the inspection sector is rapidly upgrading in order to cope with the new technology paradigm of industry. The application of new technologies in NDE can improve the effectiveness, in terms of time and costs, of many inspection processes and include much more data and details exploiting multiple devices and sensing systems (NDE 4.0). In this work a remote damage inspection device is introduced, based on a stereo-laser depth map system connected to a custom headset. A laser speckle pattern is projected on the inspected component and acquired through a stereo cameras system. Damage is detected as a change in the depth map. The detected damage is then superimposed on the structure and streamed to the headset. The proposed idea would be extremely beneficial during the inspection process of large structures to assess whether a damage is present. This, in turn, would make inspections and analysis faster with overall benefits in terms of cost efficiency and availability of the product.

In modern manufacturing industries, quality control systems are crucial components that are rising attention in production environments; companies are looking for new and innovative ways to identify and minimize the quantity of non-compliant products. Intelligent quality control is particularly important when evaluating the outcome of a production line is a complex task (for example when a visual inspection is not sufficient). The first step for building a smart process control system is the identification of all the process variables that are related to the final condition of a product. If key-variables are not directly accessible in real-time, their effect can be derived by means of sensor measurements, but, in this case, a learning model able to put in relation the available information to the inaccessible variables is needed. For all these reasons, in the last couples of decades the building of reliable and robust soft sensors gained a certain relevance in the academic world. In this research an automated rotating machinery is considered. The misalignment condition between two functional parts is the inaccessible process variable, whereas the signal of an accelerometer mounted on the machinery is available for a real time measurement. Changings in rotational speed, according to the production rate required, generate variations in acceleration’s amplitude and cycles’ length. A model based on neural networks is built to detect non-compliant products, while handling different operative conditions.

This paper presents a deep learning approach for detecting early fault in bearings. The identification of bearings defects represents an important problem in the field of rotating machines. Sudden failures may occur, leading to breakdown of the machinery. For this reason, the prediction of possible faults has become a major issue in the study of bearing elements. Different fault diagnosis techniques have been developed during the years based on aggregated parameters (i.e. features) that are computed starting from time domain, frequency domain or time frequency domain analysis, relying on prior knowledge about signal processing. These approaches present major limitations, that can be overcome by adopting a convolutional LSTM (long short-term memory) neural network model. In this case, a more complex architecture is built, and the algorithm can identify effective features from accelerometer signal, that could not be considered by a manual computation approach. The algorithm has been applied on data obtained from a complex test rig to assess bearings failure on high speed trains. The outcome of this work indicates that the adopted approach leads to satisfactory performances.

Vibroacoustic sensing is a method to investigate and enable tangible interaction on surfaces. One of the main challenges in this field is to make a sheet of paper on a surface interactive without either prefabrication or permanent instrumentation. This research presents VibroAware, a novel system that makes paper on a surface interactive as is by leveraging vibrations. The sheet of paper becomes interactive when users attach it to four thin piezoelectric transducers. Users interact with the sheet of paper on the surface by touching or blowing, which produces vibrations captured by our system. In this research, an algorithm is developed to enable localization and adapt to environmental noise without requiring analyzing material properties. VibroAware offers users the ability to test and prototype faster, and create interfaces using vibroacoustic sensing on a sheet of paper more intuitively. This research presents a future vision for using vibroacoustic sensing to enable interaction on a sheet of paper that opens opportunities to utilize inherent material properties, such as vibration.

Since wear and corrosion of materials currently causes large losses of GDP, surface engineering is a critical technology that currently supports the competitiveness of industry globally. Major sectors such as energy, aerospace, automotive and tool industries, are heavily dependent on surface treatments. It is estimated that almost 80% of all these industrial applications depend on protective coatings. Although different coatings have been developed in recent years, two types dominate the field of protective coatings, Hard Chrome and Cermet WC-Co coatings. Both types of coatings have very good mechanical and tribological properties, however, the extremely negative environmental impact of the hard chrome process related to the use of carcinogenic hexavalent chromium has led to a series of directives and legislation in several countries on limiting this method. Additionally, recent studies have shown that WC-Co particles are toxic in a dose and time-dependent manner. This was the driver for developing an innovative technology based on the incorporation of nanoparticles into the electrolytic deposition or thermal spray production line to create green protective nano-reinforced multifunctional coatings. The innovative green solution presented here is accompanied by significant benefits beyond their excellent performance. In particular, the new processes can be easily adopted combining flexibility with mass production, being environmentally friendly and nonharmful to health, combining low implementation costs with green footprint both in terms of materials and processes. Moreover, the novel coatings are being characterized with different destructive and nondestructive techniques and their performance is being compared with traditional coatings.

In the context of Industry 4.0, Predictive Maintenance becomes one of the main challenges for manufacturers. The monitoring of machinery health status results in huge cost savings. For this reason, the industry of automated machinery is moving in this direction, by acquiring large volumes of data, even if without full awareness of which physical variables are important to predict the status of a machine nor, consequently, which sensors to use and where to place them. This paper presents a general approach for the selection of sensors arrangement for the development of a condition monitoring system. The algorithm is based on multibody simulation tool and gives guidelines about the physical quantities to monitor and the parameters to extract. A machine learning model is then trained to demonstrate the ability of the obtained setup in identifying possible faults. The main benefit of this work regards the generality of the approach: it can be applied to different application cases (not only automated machineries), with the only constraint of developing a validated multibody model of the system.

High performance multifunctional structural components and other system components are evolving for applications in the aerospace industry. The efficient operation and reliability of these structures must be ensured by suitable means for inspection and maintenance. However, inspection on complex structural elements via traditional non-destructive testing (NDT) methods presents challenges for the accurate detection and characterization of flaws. The combination of NDT methods offers considerable advantages over existing NDT technologies and ensures not only accuracy in the inspection, but also another perspective on flaws which otherwise would not have been identified. Large sets of data are generated through these inspections and require robust data fusion technologies for visualisation and interpretation. Emerging technologies such as artificial intelligence, internet of things and automation direct towards the new paradigms NDT 4.0 and digital twin. The measurement data for assessing the health and faulty conditions of the structure using integrated sensors and NDT methods can be represented in a digital replication of the structure called the digital twin. Technologies such as drones, augmented reality and remote NDT can help to improve the efficiency of inspections. Therefore, this review represents current technologies and concepts for NDT 4.0 and the digital twin concepts which are suitable to save time, optimize processes and maintenance costs.

In this contribution, we study the applicability of non-contact vibration analysis for flaw detection on the example of a ceramic electrolyte cup. These components are key parts in a prospective power cells design. First, extensive numerical modal analysis was performed using finite element modelling (FEM). Beside the complete mode spectrum of the freefloating perfect component, the influence of the suspension as well as deviations from the ideal geometry to the eigenmodes were studied. Additionally, the impact of different defect parameters, such as shape, location, and size, on the eigenmodes was investigated. For experimental investigation a soft suspension, impact excitation pendulum and near-surface microphone array rack were designed and built. Initially the samples with reference geometry and no defects have been measured. Eigenfrequencies, damping ratios and mode shapes have been extracted from the microphone array records using the operational modal analysis (OMA) algorithms, as the impact excitation signal was not traced. Experimental and numerical data have shown the good agreement. Further, the samples with reference defects, induced by laser cuts of different length and position, as well as laser drilled holes were studied. Depending on their type, size and position, the defects lead to a decrease of some eigenfrequencies and to a splitting of formerly degenerate modes. Same effects for a real crack are shown. Based on these results, preliminary application boundaries and potential development patterns for non-contact modal testing using a microphone array for defect detection are discussed.

The present study aims to accent the effect of nano-reinforcements such as CNTs and graphene nanoplatelets, on the electrical and thermal behavior of nano-modified concrete. The dispersion agent used is a water-based superplasticizer since this type of agent does not induce air in the specimens and is also chemically compatible. The assessment of the specimens includes evaluation of different physical properties, such as electrical resistivity and thermal behavior. The enhancement of these physical properties by the nano-reinforcement phase, induces multifunctionalities in the concrete specimens. Such innovative nano-reinforced concrete mixtures would enable the use of concrete in new areas like energy harvesting, real time health monitoring and self-sensing of critical structural elements.

Defect detection is of great significance for assessing and controlling the quality of fabrics. However, most traditional detection processes rely on manual visual inspection, resulting in low detection efficiency, ambiguous detection results, and high monitoring costs. In this work, a centroid warp-weft graph-based (C2WG) statistical analysis method is proposed for the detection and evaluation of fabric defects. To reflect the fabric texture variation, the C2WG method is first proposed to find abnormal texture centers. Subsequently, by dual monitoring of local slope and curvature, the location of the abnormal centroid can be accurately determined as texture defects and displayed. Finally, the defect evaluation results under different detection accuracy are obtained by changing the monitoring threshold. Consequently, the defects are classified into different classes. A case study on an industrial design fabric product validates the good performance of the proposed method.

With the growth of the economy, electricity consumption is also increasing. To ensure the regular running of substations, operation and maintenance personnel need to inspect the equipment on-site, but they are also exposed to a hazardous environment. Since the source of danger cannot be eliminated entirely, the safety behavior of the operation and maintenance personnel in the substation needs to be identified. For this purpose, we propose an automated approach based on deep learning. We first collected images of operation and maintenance personnel on a substation as a dataset. Then, an object detection model based on YOLO v5 is proposed, which can accurately detect the substation's operation and maintenance personnel, and the personal protective equipment (PPE). Combining with individual posture estimation, using a one-dimensional convolutional neural network (1D-CNN), it is able to determine whether the PPEs are being worn correctly. Finally, the safety behavior identification is verified by an experiment, and satisfactory results are obtained. With the method in this paper, it is possible to automatically identify whether substation operations and maintenance personnel are wearing PPE correctly according to the regulations, which has a positive impact on improving the efficiency of safety management of substations.