简体   繁体   English

Model 用于预测冰箱的温度数据

[英]Model for predicting temperature data of fridge

I set up a sensor which measures temperature data every 3 seconds.我设置了一个传感器,每 3 秒测量一次温度数据。 I collected the data for 3 days and have 60.000 rows in my csv export.我收集了 3 天的数据,在我的 csv 导出中有 60.000 行。 Now I would like to forecast the next few days.现在我想预测未来几天。 When looking at the data you can already see a "seasonality" which displays the fridges heating and cooling cycle so I guess it shouldn't be too difficult to predict.在查看数据时,您已经可以看到显示冰箱加热和冷却循环的“季节性”,所以我想预测应该不难。 I am not really sure if my data is too granular and if I should do some kind of undersampling.我不太确定我的数据是否过于精细,是否应该进行某种欠采样。 I thought about using a seasonal ARIMA model but I am having difficulties with picking parameters.我考虑过使用季节性 ARIMA model 但我在选择参数时遇到困难。 As the seasonality in the data is pretty obious is there maybe a model that fits better?由于数据中的季节性非常明显,是否有 model 更合适? Please bear with me I'm pretty new to machine learning.请耐心等待我是机器学习的新手。

在此处输入图像描述

When the goal is to forecast rising temperatures, you can forecast the lower and upper peaks, ie, their hight and distances.当目标是预测上升的温度时,您可以预测较低和较高的峰值,即它们的高度和距离。 Assuming (simplified model) that the temperature change in between is linear we can, model each complete peak starting from a first lower peak of the temperature curve to the next upper peak down to next lower peak.假设(简化模型)之间的温度变化是线性的,我们可以 model 每个完整的峰从温度曲线的第一个下峰开始到下一个上峰再到下一个下峰。 So a complete peak can be seen as triangle which we easily integrate (calculate its area + the area of the rectangle below of it).所以一个完整的峰可以看作是我们很容易积分的三角形(计算它的面积+它下面的矩形的面积)。 The estimation can now be done by a integrating a number of complete peaks we have already measured.现在可以通过对我们已经测量的多个完整峰值进行积分来完成估算。 By repeating this procedure, we can do now a linear regression on the average temperatures and alert when the slope is above a defined threshold.通过重复此过程,我们现在可以对平均温度进行线性回归,并在斜率高于定义的阈值时发出警报。

As this only tackles a certain kind of errors, one can do the same for the average distances between the upper peaks and the also for the lower peaks.由于这只能解决某种类型的错误,因此可以对上峰和下峰之间的平均距离执行相同的操作。 Ie, take the times between them for a certain periode, fit a curve (linear regression can possibly be sufficient) and alert when the slope of the curve is indicating too long distances.也就是说,将它们之间的时间取一定的时间,拟合一条曲线(线性回归可能就足够了),并在曲线的斜率表明距离太长时发出警报。

It's mission impossible.这是不可能完成的任务。 If fridge work without interference, then graph always looks the same.如果冰箱在不受干扰的情况下工作,那么图表看起来总是一样的。 The change can be caused, for example, by opening a door, a breakdown, a major change in external conditions.例如,打开门、发生故障、外部条件发生重大变化可能会导致这种变化。 But you cannot predict such events.但是您无法预测此类事件。 Instead, you can try to warn about the possibility of problems in the near future, for example, based on a constant increase in average temperature.相反,您可以尝试警告在不久的将来出现问题的可能性,例如,基于平均温度的持续升高。 This situation may indicate a leak in the cooling system.这种情况可能表明冷却系统存在泄漏。 By the way, have you considered logging the temperature every 3 seconds?顺便问一下,您是否考虑过每 3 秒记录一次温度? This is usually unjustified, because it is physically impossible for the temperature to change to a measurable degree in such an interval.这通常是不合理的,因为在这样的时间间隔内,温度在物理上不可能变化到可测量的程度。 Our team usually sets the login interval to 30 or 60 seconds in such cases.在这种情况下,我们团队通常将登录间隔设置为 30 或 60 秒。 Sometimes even more.有时甚至更多。 Depending on the size of the chamber, the way the air is circulated, the ratio of volume to power of the refrigeration unit, etc.取决于腔室的大小、空气的循环方式、制冷机组的容积功率比等。

声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM