Lin Li, Mingheng Fu, Tie Zhang and He Ying Wu
To improve production efficiency, industrial robots are expected to replace humans to complete the traditional manual operation on grasping, sorting and assembling workpieces…
Abstract
Purpose
To improve production efficiency, industrial robots are expected to replace humans to complete the traditional manual operation on grasping, sorting and assembling workpieces. These implementations are closely related to the accuracy of workpiece location. However, workpiece location methods based on conventional machine vision are sensitive to the factors such as light intensity and surface roughness. To enhance the robustness of the workpiece location method and improve the location accuracy, a workpiece location algorithm based on improved Single Shot MultiBox Detector (SSD) is proposed.
Design/methodology/approach
The proposed algorithm integrates a weighted bi-directional feature pyramid network into SSD. A feature fusion architecture is structured by the combination of low-resolution, strong semantic features and high-resolution, weak semantic features. The architecture is built through a top-down pathway, bottom-up pathway, lateral connections and skip connections. To avoid treating all features equally, learnable weights are introduced into each feature layer to characterize its importance. More detailed information from the low-level layers is injected into the high-level layers, which could improve the accuracy of workpiece location.
Findings
It is found that the maximum location error at the center point calculated from the proposed algorithm is decreased by more than 22% compared with that of the SSD algorithm. Besides, the average location error evolves a decrease by at least 5%. In the trajectory prediction experiment of the workpiece center point, the results of the proposed algorithm demonstrate that the average location error is below 0.13 mm and the maximum error is no more than 0.23 mm.
Originality/value
In this work, a workpiece location algorithm based on improved SSD is developed to extract the center point of the workpiece. The results demonstrate that the proposed algorithm is beneficial for workpiece location. The proposed algorithm can be readily used in a variety of workpieces or adapted to other similar tasks.
Details
Keywords
Yanqiu Chen, Xiaodong Zhou, Taolin Zhang, Zhijian Fu, Yuqi Hu and Lizhong Yang
– The purpose of this paper is to study the behavior of smoke flow in building fires and optimize the design of smoke control systems.
Abstract
Purpose
The purpose of this paper is to study the behavior of smoke flow in building fires and optimize the design of smoke control systems.
Design/methodology/approach
A total of 435 3-D fire simulations were conducted through NIST fire dynamics simulator to analyze thermal behavior of combined buoyancy-induced and pressure-driven smoke flow in complex vertical shafts, under consideration of influence of heat release rate (HRR) and locations of heat sources. This influence was evaluated through neutral pressure plane (NPP), which is a critical plane depicting the flow velocity distributions. Hot smoke flows out of shafts beyond the NPP and cold air flows into shafts below the NPP.
Findings
Numerical simulation results show that HRR of heat source has little influence on NPP, while location of heat source can make a significant difference to NPP, particularly in cases of multi-heat source. Identifying the location of NPP helps to develop a more effective way to control the smoke with less energy consumption. Through putting an emphasis on smoke exhausting beyond the NPP and air supplying below the NPP, the smoke control systems can make the best use of energy.
Research limitations/implications
Because of the chosen research approach, the research results may need to be tested by further experiments.
Practical implications
The paper includes implications for the optimization of smoke control systems design in buildings.
Originality/value
This paper fulfills an identified need to research the behavior of hot smoke in building fires and optimize the design of smoke control systems.