Identifying and Characterizing Conveyor Belt Longitudinal Rip by 3D Point Cloud Processing

Abstract

Real-time and accurate longitudinal rip detection of a conveyor belt is crucial for the safety and efficiency of an industrial haulage system. However, the existing longitudinal detection methods possess drawbacks, often resulting in false alarms caused by tiny scratches on the belt surface. A method of identifying the longitudinal rip through three-dimensional (3D) point cloud processing is proposed to solve this issue. Specifically, the spatial point data of the belt surface are acquired by a binocular line laser stereo vision camera. Within these data, the suspected points induced by the rips and scratches were extracted. Subsequently, a clustering and discrimination mechanism was employed to distinguish the rips and scratches, and only the rip information was used as alarm criterion. Finally, the direction and maximum width of the rip can be effectively characterized in 3D space using the principal component analysis (PCA) method. This method was tested in practical experiments, and the experimental results indicate that this method can identify the longitudinal rip accurately in real time and simultaneously characterize it. Thus, applying this method can provide a more effective and appropriate solution to the identification scenes of longitudinal rip and other similar defects.

A novel method for necking detection and measurement in automotive sheet metal components

“…( (2) Result of NVP algorithm: Since there is no available 3D necking detection technique, we compared our 3D necking detection method with two other methods for 3D defect detection. In [35], a region growing algorithm was proposed, and in [36], a bilateral weighted algorithm was proposed to detect necking defects on sheet metal components. We compared the results of these methods with our proposed algorithm, as illustrated in figure 18.…”

“…As show in figures 18(a) and (d), the defect detection method proposed in [35] failed to detect necking defect information, resulting in incorrect outcomes. As shown in figures 18(b) and (e), the defect detection method presented in [36] managed to detect the characteristic regions where necking defects are present but erroneously misjudged other parts within those regions as necking defects, leading to erroneous detection results. The comparison experiments show that the methods proposed in [35] and [36] do not accurately extract necking defects when the sheet metal parts have more complex structural features, whereas the NVP algorithm can evade the similarity between the feature region and the necking defect region in terms of structure and accurately extract the necking defects of automotive sheet metal parts, which is a novel approach in the detection of necking defects in automotive sheet metal parts.…”

Graphene-Based Flexible Strain Sensor Based on PDMS for Strain Detection of Steel Wire Core Conveyor Belt Joints

“…A number of preventive and corrective measures were proposed in response to the problem of conveyor belt damage in order to prevent the occurrence of belt breakage and detect the wire rope twitching inside the belt in a timely manner. Many preventive and corrective measures, such as protection devices that use X-ray images to predict twitching of wire-core conveyor belt joints and various types of belt-break catching devices, were proposed in recent research [29][30][31]. Lv et al [32] proposed a technique for detecting longitudinal tears in conveyor belts by line laser, which can effectively eliminate the effect of variations in ambient light while also retaining the characteristics of longitudinal tears.…”