On-farm monitoring of milk composition can support close control of the udder and metabolic health of individual dairy cows. In previous studies, near-infrared (NIR) spectroscopy applied to milk analysis has proven useful for predicting the main components of raw milk (fat, protein, and lactose). In this contribution, we present and evaluate a precise tool for online milk composition analysis on the farm. For each milking, the online analyzer automatically collects and analyses a representative milk sample. The system acquires the NIR transmission spectra of the milk samples in the wavelength range from 960 to 1690 nm and performs a milk composition prediction afterward. Over a testing period of 8 weeks, the sensor collected 1165 NIR transmittance spectra of raw milk samples originating from 36 cows for which reference chemical analyses were performed for fat, protein, and lactose. For the same online sensor system, two calibration scenarios were evaluated: training post-hoc prediction models based on a representative set of calibration samples (n = 319) acquired over the entire testing period, and training real-time prediction models exclusively on the samples acquired in the first week of the testing period (n = 308). The obtained prediction models were thoroughly tested on all the remaining samples not included in the calibration sets (n respectively 846 and 857). For the post-hoc prediction models, this resulted in an overall prediction error (root-mean-squared error of prediction, RMSEP) smaller than 0.08% (all % are in w/w) for milk fat (range 1.5-6.3%), protein (2.6-4.3%) and lactose (4-5.1%), while for the real-time prediction models the RMSEP was smaller than 0.09% for milk fat and lactose, and smaller than 0.11% for protein. The milk lactose predictions could be further improved by taking into account a cow-specific bias. The presented online sensor system using the real-time prediction approach can thus be used for detailed and autonomous on-farm monitoring of milk composition after each individual milking, as its accuracy is well within the ICAR requirements for on-farm milk analyzers and even meet the ICAR standards for laboratory analysis systems for fat and lactose. For this real-time prediction approach, a drift was observed in the predictions, especially for protein. Therefore, further research on the development of online calibration maintenance techniques is required to correct for this model drift and further improve the performance of this sensor system.

中文翻译：

---

使用农场近红外传感器进行在线牛奶成分分析

农场对牛奶成分的监测可以支持对个别奶牛的乳房和新陈代谢健康进行严格控制。在先前的研究中，应用于牛奶分析的近红外（NIR）光谱已被证明可用于预测原料乳的主要成分（脂肪，蛋白质和乳糖）。在此贡献中，我们提出并评估了用于农场在线牛奶成分分析的精确工具。对于每次挤奶，在线分析仪都会自动收集并分析代表性的牛奶样品。该系统获取960至1690 nm波长范围内的牛奶样品的NIR透射光谱，然后执行牛奶成分预测。经过8周的测试，传感器收集了来自36头奶牛的生奶样品的1165个NIR透射光谱，对其进行了脂肪，蛋白质和乳糖的参考化学分析。对于同一在线传感器系统，评估了两种校准方案：基于在整个测试期间获取的一组代表性的校准样品（n = 319）来训练事后预测模型，以及仅对样品进行实时预测模型的训练在测试期间的第一周获得（n = 308）。对未包含在校准集中的所有其余样本（分别为n 846和857）进行了彻底测试，对获得的预测模型进行了测试。对于事后预测模型，这导致总的预测误差（预测的均方根误差，RMSEP）小于0。乳脂（范围1.5-6.3％），蛋白质（2.6-4.3％）和乳糖（4-5.1％）为08％（所有百分比均以重量计），而对于实时预测模型，RMSEP较小乳脂和乳糖的含量低于0.09％，蛋白质的含量低于0.11％。考虑到奶牛的特定偏见，可以进一步改善牛奶乳糖的预测。提出的使用实时预测方法的在线传感器系统可用于每次单独挤奶后对牛奶成分进行详细，自主的农场监控，因为其准确性完全符合农场牛奶分析仪的ICAR要求，甚至可以满足ICAR脂肪和乳糖实验室分析系统标准。对于这种实时预测方法，在预测中观察到漂移，尤其是对于蛋白质。因此，