Search

Currently, the rapid development of the industrial Internet has led to the creation of a massive number of intelligent agents that are widely and distributively applied in various edge scenarios. The work conditions in these edge scenarios are complex, uncertain, and random. Traditional manual updates or human judgments are used for task decision-making in large-scale distributive intelligent agent edge work scenarios, which lack dynamic perception and autonomous recognition capabilities for edge work conditions. This inevitably leads to low decision-making accuracy, poor reliability, and ultimately, task failure. To address this issue, this study proposes an adaptive task identification strategy based on cloud-edge collaboration. This method utilizes a cloud-edge collaborative industrial intelligent application architecture to achieve cloud-based training and encapsulation of the task model, with online calling at the edge-end. Then, edge-end intelligent agents identify edge work conditions through multi-source data fusion, enabling accurate task decision-making. Finally, the edge-end requests the cloud for task model matching. The effectiveness of the proposed method is validated in an industrial safety situation virtual detection system. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Harbin Institute of Technology. Social Sciences Edition / Haerbin Gongye Daxue Xuebao. Shehui Kexue Ban is the property of Harbin Institute of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Fast and reliable industrial inspection is a main challenge in manufacturing scenarios. However, the defect detection performance is heavily dependent on manually defined features for defect representation. In this contribution, we investigate a new paradigm from machine learning, namely deep machine learning by examining design configurations of deep Convolutional Neural Networks (CNN) and the impact of different hyper-parameter settings towards the accuracy of defect detection results. In contrast to manually designed image processing solutions, deep CNN automatically generate powerful features by hierarchical learning strategies from massive amounts of training data with a minimum of human interaction or expert process knowledge. An application of the proposed method demonstrates excellent defect detection results with low false alarm rates. [ABSTRACT FROM AUTHOR]

Diagnosis of complex engineering systems requires the use of multiple sensor sources to acquire information. In this paper we present a survey of multimodal data acquisition systems for nondestructive testing (NDT) and engineering analysis. We begin with a summary of the relative strengths and weaknesses of individual NDT modalities. Thereafter we present existing multimodal inspection hardware systems that use complementary NDT sensors. The advantages of such multimodal data acquisition over conventional single modality sensors in inspection and analysis are highlighted. Possible approaches to fuse complementary multimodal sensor data are discussed. We conclude with possible directions for the future development of multimodal inspection systems. [ABSTRACT FROM AUTHOR]

With the fast growth of intelligent manufacturing industry, developing advanced industrial inspection robots is becoming a research and application hotspot in the fields of both computer vision and robotics. This kind of industrial inspection robots is expected to automatically detect anomalous structures (e.g. , defects, damages, rejects, etc.) from the images of the manufactured products. Generally, the existing visual anomaly detection (VAD) methods mainly focus on modeling the complex and high-dimensional distribution of normal data, while neglecting the specific visual properties of abnormal data since their frequency of occurrence is much less than that of the normal data. In this paper, inspired by the human cognition on extracting abstractly visual properties and to distinguish the anomaly patterns from the observed data, we propose a novel cognitive VAD method for industrial inspection robot. Specifically, we introduce a constrained latent space to mimic the cognitive ability of humans, where the abstraction learned from the observed normal and anomaly data are represented. We build our method based on a convolutional generative adversarial network and a denoising auto-encoder, where the adversarial learning mechanism is adopted to establish the boundary between the normal and anomaly data. In the experiment, we evaluate our method on a real-world dataset where the images are captured for the manufactured products. The comprehensive results comparing with several recent VAD methods show that the proposed method is effective to detect the anomaly images of different categories with a high accuracy. • This paper proposes a cognitive visual anomaly detection method for industrial inspection robot. • A constrained latent space is introduced to mimic the cognitive ability of humans. • A convolutional generative adversarial network along with denoising auto-encoder is built. [ABSTRACT FROM AUTHOR]

Robotic manipulators provide advantages in working environments regarding efficiency and safety, which is further increased in the case of elastic joint manipulators, whose mechanical compliance reduces the energy involved in collisions with workers. Cable-driven manipulators are elastic joint manipulators particularly suitable for industrial inspection thanks to the relocation of actuators outside hostile environments, increasing the manipulator payload-to-weight ratio. Recently, synthetic fibre cables are substituting steel cables due to their better-performing mechanical properties, but their visco-elastic behaviour must be compensated in the controller design. The key novelty of this work is using the four elements model, which includes the viscous behaviour, to design a non-linear full-state feedback controller for cable-driven manipulators. Furthermore, the mathematical proof of the closed-loop Lyapunov stability is provided. • Elastic joints manipulators, like cable-driven manipulators, increase workers' safety. • Cable-driven manipulators are suitable for industrial inspection in harsh conditions. • Synthetic fibre cables perform better than steel cables but complicate control tasks. • Design of full-state feedback controller using four elements model for cable dynamics. • Lyapunov stability proof of the closed-loop non-linear system. [ABSTRACT FROM AUTHOR]

A neural network is a machine learning (ML) program or model that processes information and recognizes patterns, similar to the human brain. The neural network algorithm operates by training on data to learn and enhance its accuracy. If there is any mistake in the learning process, the machine will react unexpectedly and produce incorrect information. So, whenever a neural network model is developed, it is mandatory to evaluate its performance and ensure its output is accurate. Cameras, touchscreens, internet connectivity, and powerful CPUs have contributed to the popularity of smartphones. Mobile apps are software applications that run on smartphones. ML enhances mobile app functionality by offering features such as voice recognition, image analysis, natural language processing, personalization, and recommendations. Training ML models using mobile apps is challenging due to limited resources, data, and privacy concerns. Object recognition is a neural network-based technique that enables the identification and localization of objects in an image or video. This technique is used in driverless cars, disease identification, industrial inspection, robotics, and more. In this paper, the author introduces a new neural network-based algorithm that utilizes mobile devices for training and recognizing images. Although mobile devices have some technological limitations for training, well-established guidelines for systematically mapping verification and validation techniques have been used in the proposed neural network to ensure performance and correctness in on-device object training and recognition. [ABSTRACT FROM AUTHOR]

Nondestructive testing, which can monitor a product's interior without disassembly, is becoming increasingly essential for industrial inspection. Computed laminography (CL) is widely used in this application, as it can reconstruct a product, such as a printed circuit board, into a three‐dimensional (3D) high‐magnification image using X‐rays. However, such high‐magnification scanning environments can be affected by minute vibrations of the CL device, which can generate motion artifacts in the 3D reconstructed image. Since such vibrations are irregular, geometric corrections must be performed at every scan. In this paper, we propose a geometry calibration method that can correct the geometric information of CL scans based on the image without using geometry calibration phantoms. The proposed method compares the projection and digitally reconstructed radiography images to measure the geometric error. To validate the proposed method, we used both numerical phantom images at various magnifications and images obtained from real industrial CL equipment. The experiment results confirmed that sharpness and contrast‐to‐noise ratio (CNR) were improved. [ABSTRACT FROM AUTHOR]

Material attribute recognition from the visual appearance of attributes is an important problem in computer vision field. However, few works model the hierarchical relationship between material attributes and their deep-level semantics that occurs in the same image. Meanwhile, single image feature is insufficient to achieve high-quality material attribute classification. In this paper, we present methods for generating a new hierarchical material attribute representation mechanism using a new-designed feature mid-fusion algorithm and the state-of-the-art relative attribute (RA) model. The novel feature mid-fusion algorithm can improve the performance of material attribute classification. The deep-level semantics of material attributes are mined by the state-of-the-art RA model. They provide considerable useful and detailed knowledge on material attributes. We call the novel feature mid-fusion algorithm gene selection eXtreme gradient boosting (GS-XGBoost). This algorithm considers the state-of-the-art boosting idea (eXtreme gradient boosting) and the popular multi-feature fusion idea (effective range-based gene selection). To comprehensively describe material attributes, we also measure the relative degree of their deep-level semantics. A new hierarchical material attribute representation mechanism is constructed on the basis of the correctly classified material attributes and their deep-level semantics. The mechanism has two forms. One is binary attribute representation mechanism, and the other is relative attribute representation mechanism. We demonstrate the effectiveness of the proposed GS-XGBoost algorithm on two different datasets. The proposed GS-XGBoost algorithm is not an end-to-end framework but is efficient and practical for fine- and coarse-grained material attribute classification problems that can be applied in different scenarios in large-scale product image retrieval, robotics, and industrial inspection. The novel hierarchical material attribute representation mechanism will help humans or robotics accurately recognize diverse materials and their deep-level semantics. Our research contributes to not only computer science but also material science and engineering. • A new feature fusion algorithm GS-XGBoost based on XGBoost and ERGS is created. • Relative attribute model is used to measure the deep-level semantics of materials. • A representation mechanism based on materials and deep-level semantics is built. [ABSTRACT FROM AUTHOR]

Advanced sensing technologies have produced a significant amount of discrete point data in the past decade. Measurement uncertainty frequently occurs at the geometric discontinuity of mechanical parts. In this paper, a genetic search algorithm is developed for optimally-constrained multiple-line fitting of discrete data points. It contains two important technical components: (a) constrained least-squares fitting of multiple lines, and (b) genetic search for optimal corner/edge points. The algorithm is designed for both two-dimensional and three-dimensional cases. Numerical experiments demonstrate the effectiveness of the proposed approach, compared to the conventional least-squares fitting method as well as exhaustive search method. A comparative study with a particle swarm method indicates that both the genetic search and particle swarm search produce similar results in terms of minimum fitting errors. It can be used for the effective determination of sharp edges or corners based on discrete data points measured for high-precision industrial inspection and manufacturing. [ABSTRACT FROM AUTHOR]

Abstract: Image analysis techniques are being increasingly used to automate industrial inspection. The manual activity of inspection could be subjective and highly dependent on the experience of human personnel. In a previous work, the authors presented two approaches utilizing image analysis to inspect products visually. The product is accepted or rejected based on its conformance to specified tolerances, where conformance is analogy measured through statistical indices like correlation and root mean square error. In this work, the authors introduce a novel visual inspection approach that can be used on line to test simultaneously multiple quality characteristics. The approach utilizes image processing tools to deal with the product image; and extract features of its geometrical characteristics. Based on tolerance bands of each characteristic, an index is experimentally developed to reflect the deviation of a quality characteristic dimension from its nominal value; and one can decide whether a characteristic complies with the pre-specified tolerance. Statistical analysis proved that there is a strong association between the developed indices and the deviations of quality characteristics from their target values. Linear regression models are proved to model these associations; and are used to give the corresponding indices’ values relative to the tolerance specifications. The developed approach is proved to give a good performance experimentally in detecting non-conforming products; and, in specific, the defect location(s). [ABSTRACT FROM AUTHOR]

Copyright of Electronics & Electrical Engineering is the property of Electronics & Electrical Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Quarterly Bulletin of the International Association of Agricultural Information Specialists is the property of International Association of Agricultural Information Specialists (IAALD) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

A vision-based measurement system applicable for use in two-dimensional (2D) industrial inspection is described. The system embodies a five-stage approach to feature modeling comprising the use of multi-scale functions for filtering and feature location, image structure representation through a fusing of filter responses, extraction of edge information, edge building, and a determination of geometric feature attributes. The purpose of feature modeling is to describe and represent feature geometry and dimensions. In an inspection context, information on conformance to design can be provided by using this approach.The application of the system to the tasks of on-line steel plate and wheel rim inspection are described and, following an explanation ofthe use of scale-space methods for feature modeling, results of experimental tests are summarized. are summarized. [ABSTRACT FROM AUTHOR]