Comparison of Sensor-Based and Audible Detection of Milking Liner Slips during Machine Milking of Dairy Cows.

On-farm milk flow meter technology facilitates real-time assessment of individual cow milking observations and could be used to detect milking liner slips during machine milking of dairy cows. Here, we compared the accuracy of on-farm milk flow meters for detecting milking liner slips with that of audible detection and that of a portable vacuum recording system. Compared to audible detection methods, the on-farm milk flow meter facilitated the detection of milking liner slips with moderate accuracy. Using the vacuum recording system as the gold standard, the milk flow meter system failed to detect most of the liner slips, leading to poor agreement between the two devices. We conclude that the on-farm milk flow meter system tested here compared well with audible detection; however, when vacuum recordings were considered, we found significant levels of under-detection. Taken together, dairy operators may use the on-farm milk flow meter system to inform adjustments of the milking machine settings and monitor milking routine performance. However, the system is not suitable for monitoring short-duration vacuum fluctuations. Future research is warranted to optimize the sensor-based detection of milking liner slips.

Vacuum Dynamics as an Alternative Method for Detection of Bimodal Milk Ejection in Dairy Cows.

The primary objective of our study was to assess the ability of a vacuum recorder to detect the presence of bimodal milk flow curves in dairy cows compared with a portable milk flow meter. In a cross-sectional study, 241 individual cow milking observations were analyzed. We simultaneously collected (1) individual cow vacuum events during milking using portable vacuum recorders, and (2) individual cow milk flow curves by attaching a portable milk flow meter to the same milking unit. Presence of bimodality was assessed with the vacuum recorder visually (BIMVA) and with the gold standard method of a milk flow meter through automatic detection (BIMLA). Kappa statistics revealed moderate agreement between BIMVA and BIMLA [κ, 95% confidence intervals (95% CI) = 0.59 (0.46-0.71)]. Diagnostic test statistics for BIMVA for detection of bimodality indicated moderate performance for sensitivity [0.65 (0.52-0.76)] and positive predictive value [0.71 (0.58-0.82)] and high values for specificity [0.92 (0.87-0.95)] and negative predictive value [0.93 (0.84-0.93)]. We conclude that milking vacuum dynamics are a suitable measure to assess bimodal milk flow curves in dairy cows.