Apparatus, computer program product, and method for evaluating course of degradation in air handling units
Methods, apparatuses, and computer program products are disclosed for monitoring cooling coil degradation. An example method receives a first data set comprising heat transfer data over a first time interval. The method generates, with a machine learning model, a data prediction based upon the first data set, wherein the data prediction comprises expected heat transfer data over a second time interval. The method receives a second data set comprising heat transfer data over the second time interval. The method determines a cooling coil degradation level based on a difference between the data prediction and the second data set.
1 . An apparatus for determining cooling coil degradation, the apparatus comprising at least one processor and at least one non-transitory memory including computer-coded instructions thereon, the computer-coded instructions configured to, with the at least one processor, cause the apparatus to:
receive a first data set comprising heat transfer data over a first time interval;
generate, with a machine learning model, a data prediction based at least on the first data set, wherein the data prediction comprises heat transfer data over a second time interval;
receive a second data set comprising heat transfer data over the second time interval;
determine a cooling coil degradation level based on a difference between the data prediction and the second data set; and
wherein the apparatus further caused to:
determine a mixing ratio associated with the data prediction;
determine a mixing ratio associated with the second data set; and
determine an energy waste level based on a difference between the mixing ratio associated with the data prediction and the mixing ratio associated with the second data set.
2 . The apparatus of claim 1 , wherein the first data set and the second data set comprise a difference between chilled water supply temperature and chilled water return temperature.
3 . The apparatus of claim 1 , wherein the first data set, data prediction, and second data set comprise loss in latent heat.
4 . The apparatus of claim 1 , wherein the cooling coil degradation level is determined based at least on a difference between a heat transfer coefficient associated with the data prediction and a heat transfer coefficient associated with the second data set.
5 . The apparatus of claim 1 , wherein the cooling coil degradation level is determined based at least on a difference between a logarithmic mean temperature difference associated with the data prediction and a logarithmic mean temperature difference associated with the second data set.
6 . The apparatus of claim 1 , the apparatus further caused to:
determine a chiller efficiency level associated with the data prediction;
determine a chiller efficiency level associated with the second data set; and
determine an energy waste level based on a difference between the chiller efficiency level associated with the data prediction and the chiller efficiency level associated with the second data set.
7 . The apparatus of claim 1 , the apparatus further caused to:
determine an excess expenditure value based on the energy waste level.
8 . The apparatus of claim 7 , the apparatus further caused to:
determine an optimal maintenance time based on the excess expenditure value and a cost of maintenance.
9 . The apparatus of claim 1 , wherein the first time interval is determined based at least on a rate of expected degradation.
10 . The apparatus of claim 1 , the apparatus further caused to:
smooth the first data set, wherein the first data set is smoothed based at least on a third time interval that is longer than a basic sampling time interval and encompasses the basic sampling time interval.
11 . The apparatus of claim 1 , wherein the machine learning model comprises a regression model.
12 . The apparatus of claim 1 , wherein the machine learning model is trained based on the first data set.
13 . A computer-implemented method, comprising:
receiving a first data set comprising heat transfer data over a first time interval;
generating, with a machine learning model, a data prediction based upon the first data set, wherein the data prediction comprises expected heat transfer data over a second time interval;
receiving a second data set comprising heat transfer data over the second time interval; and
determining a cooling coil degradation level based on a difference between the data prediction and the second data set; and
wherein the computer-implemented method further comprising:
determining a mixing ratio associated with the data prediction;
determining a mixing ratio associated with the second data set; and
determining an energy waste level based on a difference between the mixing ratio associated with the data prediction and the mixing ratio associated with the second data set.
14 . The computer-implemented method of claim 13 , wherein the first data set and the second data set comprise a difference between chilled water supply temperature and chilled water return temperature.
15 . The computer-implemented method of claim 13 , wherein the first data set, data prediction, and second data set comprise loss in latent heat.
16 . The computer-implemented method of claim 13 , wherein the cooling coil degradation level is determined based at least on a difference between a heat transfer coefficient associated with the data prediction and a heat transfer coefficient associated with the second data set.
17 . The computer-implemented method of claim 13 , wherein the cooling coil degradation level is determined based at least on a difference between a logarithmic mean temperature difference associated with the data prediction and a logarithmic mean temperature difference associated with the second data set.
18 . A computer program product comprising at least one non-transitory computer-readable storage medium having computer program code stored thereon that, in execution with at least one processor, is configured for:
receiving a first data set comprising heat transfer data over a first time interval;
generating, with a machine learning model, a data prediction based upon the first data set, wherein the data prediction comprises expected heat transfer data over a second time interval;
receiving a second data set comprising heat transfer data over the second time interval; and
determining a cooling coil degradation level based on a difference between the data prediction and the second data set; and
wherein the processor is further configured to:
determining a mixing ratio associated with the data prediction;
determining a mixing ratio associated with the second data set; and
determining an energy waste level based on a difference between the mixing ratio associated with the data prediction and the mixing ratio associated with the second data set.
19 . The computer program product of claim 18 , wherein the first data set and the second data set comprise a difference between chilled water supply temperature and chilled water return temperature.