**4. Conclusions**

In this paper, a testbed for conducting a pick-up operation using a vacuum gripper with a single suction cup was prepared. Using the proposed method, the air pressure in the Venturi line was automatically monitored in real time. When a command for starting suction was provided to the gripper, a sharp decrease in the collected air pressure signals appeared at approximately 0.5 s. However, the same decrease was not observed in the signal for faulty box surfaces; consequently, the suction action and the corresponding gripper operation were not performed owing to insufficient contact between suction cup(s) and the contact surface of the object. Using the early detection results derived from the air pressure signal analysis, a prediction-based process adjustment method for the pick-up operation was proposed. Through pick-up experiments using the developed testbed, it was revealed that the z-position of the suction cup significantly affects whether an object is properly gripped by the vacuum gripper or not. Therefore, it is possible to determine a possible error situation in advance (before failure of the lifting operation) and provide appropriate feedback control commands so that the target operation is finished successfully without stopping machine operations.

However, for stable operation and generalization, it is necessary to conduct further research on the following: (i) identifying the appropriate depth for the z-position that does not generate any defects on a contact surface but maximizes the rate of success of the pick-up operation; (ii) generalizing the results for different materials, sizes, weights, or shapes of handled objects and various configurations of vacuum grippers; and (iii) combining the machine-status monitoring result and product defect detection result to improve the productivity and product quality of an industrial production system.

**Author Contributions:** Conceptualization, methodology, validation, formal analysis, investigation, resources, data curation, writing, visualization, supervision, project administration, funding acquisition, S.B.; Experiment, D.O.K. All authors have read and agreed to the published version of the manuscript.

**Funding:** This work was supported by the National Research Foundation of Korea (NRF) gran<sup>t</sup> funded by the Korea governmen<sup>t</sup> (MSIT) (No. NRF-2019R1G1A1097478) and was also supported by Korea Institute for Advancement of Technology (KIAT) gran<sup>t</sup> funded by the Korea Government (MOTIE) (P0012744, The Competency Development Program for Industry Specialist). In addition, this research was supported by the research fund of Hanbat National University in 2020.

**Data Availability Statement:** Not applicable.

**Acknowledgments:** The staffs of GL Company (Republic of Korea) provided immense support in building the experimental system.

**Conflicts of Interest:** The authors declare no conflict of interest. The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript; or in the decision to publish the results.
