Defect inspection of glass bottles in the beverage industrial is of significance to prevent unexpected losses caused by the damage of bottles during manufacturing and transporting. The commonly used manual methods suffer from inefficiency, excessive space consumption, and beverage wastes after filling. To replace the manual operations in the pre-filling detection with improved efficiency and reduced costs, this paper proposes a machine learning based Acoustic Defect Detection (LearningADD) system. Moreover, to realize scalable deployment on edge and cloud computing platforms, deployment strategies especially partitioning and allocation of functionalities need to be compared and optimized under realistic constraints such as latency, complexity, and capacity of the platforms. In particular, to distinguish the defects in glass bottles efficiently, the improved Hilbert-Huang transform (HHT) is employed to extend the extracted feature sets, and then Shuffled Frog Leaping Algorithm (SFLA) based feature selection is applied to optimize the feature sets. Five deployment strategies are quantitatively compared to optimize real-time performances based on the constraints measured from a real edge and cloud environment. The LearningADD algorithms are validated by the datasets from a real-life beverage factory, and the F-measure of the system reaches 98.48 %. The proposed deployment strategies are verified by experiments on private cloud platforms, which shows that the Distributed Heavy Edge deployment outperforms other strategies, benefited from the parallel computing and edge computing, where the Defect Detection Time for one bottle is less than 2.061 s in 99 % probability.

在饮料工业中对玻璃瓶进行缺陷检查对于防止在制造和运输过程中由于玻璃瓶的损坏而引起的意外损失非常重要。常用的手动方法效率低下，空间消耗过多以及灌装后饮料浪费。为了以更高的效率和更低的成本代替预填充检测中的手动操作，本文提出了一种基于机器学习的声学缺陷检测（LearningADD）系统。此外，为了在边缘和云计算平台上实现可扩展的部署，需要在现实的约束条件（例如平台的延迟，复杂性和容量）下比较和优化部署策略，尤其是功能的分区和分配。特别是为了有效地识别玻璃瓶中的缺陷，改进的希尔伯特-黄变换（HHT）被用来扩展提取的特征集，然后基于随机蛙跳算法（SFLA）的特征选择被用于优化特征集。根据从真实边缘和云环境测得的约束，定量比较了五种部署策略，以优化实时性能。LearningADD算法已通过现实生活中的饮料工厂的数据集进行了验证，系统的F值达到98.48％。通过在私有云平台上进行的实验验证了所提出的部署策略，该结果表明分布式重边部署优于其他策略，这得益于并行计算和边缘计算，其中一瓶的缺陷检测时间在99％内小于2.061 s可能性。