Building management system with supervisory fault detection layer
A method for detecting faults in a building management system (BMS) is shown. The method includes receiving time series data characterizing an operating performance of one or more BMS devices. The method further includes processing the time series data using multiple different fault detection methods to generate multiple fault detection results. The method includes providing the multiple fault detection results as outputs from the multiple different fault detection methods. The method includes applying the multiple fault detection results as inputs to a neural network that determines whether the multiple fault detection results are indicative of a fault condition in the BMS.
1. A method for detecting faults in a building management system (BMS), the method comprising:
receiving time series data characterizing an operating performance of one or more BMS devices;
generating a first fault detection result by processing the time series data using a first fault detection technique;
generating a second fault detection result by processing the time series data using a second fault detection technique different than the first fault detection technique, wherein the second fault detection result conflicts with the first fault detection result;
applying both the first fault detection result and the second fault detection result as inputs to a neural network configured to output an indication of whether a fault condition is occurring in the BMS; and
initiating an action to resolve the fault condition in response to the indication indicating that the fault condition is occurring in the BMS,
wherein processing the time series data using the second fault detection technique comprises using a temporal detection method comprising:
determining an expected value of the time series data based on inferences made by a regression model;
calculating a residual value between an actual value of the time series data and the expected value of the time series data;
generating statistical inferences based on the residual value; and
providing the statistical inferences as the second fault detection result, and
wherein generating the statistical inferences based on the residual value comprises generating a cumulated sum (CUSUM) of the time series data or cumulated sum squared (CUSUMSQ) of the time series data or a recursive residual of the time series data.
2. The method of claim 1 , wherein processing the time series data using the first fault detection technique comprises executing an artificial intelligence (AI) fault detection method comprising:
determining a second expected value of the time series data based on second inferences made by a second neural network;
calculating a second residual value between the actual value of the time series data and the second expected value of the time series data;
generating second statistical inferences based on the second residual value; and
providing the second statistical inferences as the first fault detection result.
3. The method of claim 2 , wherein generating the second statistical inferences based on the second residual value comprises generating at least one of a mean squared error of the second residual value or a determinant of a covariance of the second residual value.
4. The method of claim 1 , wherein processing the time series data using the first fault detection technique comprises using a peer fault detection method to identify whether the one or more BMS devices are operating atypically by:
comparing the time series data to performance metrics of the one or more BMS devices to determine that the one or more BMS devices are operating atypically, the time series data including operational data relating to the one or more BMS devices; and
providing the first fault detection result in response to determining that the one or more BMS devices are operating atypically.
5. The method of claim 1 , where the neural network is at least one of: a feed forward neural network, a convolutional neural network, a long short term neural network, or a recurrent neural network.
6. The method of claim 1 , wherein the neural network is trained using historical user confirmed faults and a plurality of historical fault detection results generated using the first fault detection technique and the second fault detection technique.
7. The method of claim 1 , wherein applying both the first fault detection result and the second fault detection result as the inputs to the neural network comprises adding additional inputs of at least one of an outdoor environmental condition, day of the week, or time of day.
8. The method of claim 1 , wherein processing the time series data using the first fault detection technique comprises:
using a peer fault detection method to identify whether the one or more BMS devices operate atypically by calculating one or more performance metrics of the one or more devices;
calculating device statistics for each of the one or more devices;
determining the device statistics exceed a critical value; and
providing one of the multiple fault detection results in response to determining that the one or more device statistics of the BMS have exceeded the critical value.
9. The method of claim 1 , wherein initiating the action to resolve the fault condition comprises scheduling maintenance.
10. One or more non-transitory computer-readable media having computer-executable instructions stored thereon that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
receiving time series data characterizing an operating performance of one or more BMS devices;
generating a first fault detection result by processing the time series data using a first fault detection technique;
generating a second fault detection result by processing the time series data using a second fault detection technique different than the first fault detection technique, wherein the second fault detection result conflicts with the first fault detection result;
applying both the first fault detection result and the second fault detection result as inputs to a neural network configured to output an indication of whether a fault condition is occurring in the BMS; and
initiating an action to resolve the fault condition in response to the indication indicating that the fault condition is occurring in the BMS,
wherein processing the time series data using the second fault detection technique comprises using a temporal detection method comprising:
determining an expected value of the time series data based on inferences made by a regression model;
calculating a residual value between an actual value of the time series data and the expected value of the time series data;
generating statistical inferences based on the residual value; and
providing the statistical inferences as the second fault detection result, and
wherein generating the statistical inferences based on the residual value comprises generating a cumulated sum (CUSUM) of the time series data or cumulated sum squared (CUSUMSQ) of the time series data or a recursive residual of the time series data.
11. The media of claim 10 , wherein processing the time series data using the first fault detection technique comprises executing an artificial intelligence (AI) fault detection method comprising:
determining a second expected value of the time series data based on second inferences made by a second neural network;
calculating a second residual value between the actual value of the time series data and the second expected value of the time series data;
generating second statistical inferences based on the second residual value; and
providing the second statistical inferences as the first fault detection result.
12. The media of claim 11 , wherein generating the second statistical inferences based on the second residual value comprises generating at least one of a mean squared error of the second residual value or a determinant of a covariance of the second residual value.
13. The media of claim 10 , wherein processing the time series data using the first fault detection technique comprises using a peer fault detection method to identify whether the one or more BMS devices operating atypically by:
generating a model of typical operation of the one or more BMS devices;
comparing the time series data to the model of typical operation to determine whether the one or more BMS devices are operating atypically, the time series data including operational data relating to the one or more BMS devices; and
providing the first fault detection result in response to determining that the one or more BMS devices are operating atypically.
14. A controller comprising one or more processors and memory storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
receiving time series data characterizing an operating performance of one or more BMS devices;
generating a first fault detection result by processing the time series data using a first fault detection technique;
generating a second fault detection result by processing the time series data using a second fault detection technique different than the first fault detection technique, wherein the second fault detection result conflicts with the first fault detection result;
applying both the first fault detection result and the second fault detection result as inputs to a neural network configured to output an indication of whether a fault condition is occurring in the BMS; and
initiating an action to resolve the fault condition in response to the indication indicating that the fault condition is occurring in the BMS,
wherein processing the time series data using the second fault detection technique comprises using a temporal detection method comprising:
determining an expected value of the time series data based on inferences made by a regression model;
calculating a residual value between an actual value of the time series data and the expected value of the time series data;
generating statistical inferences based on the residual value; and
providing the statistical inferences as the second fault detection result, and
wherein generating the statistical inferences based on the residual value comprises generating a cumulated sum (CUSUM) of the time series data or cumulated sum squared (CUSUMSQ) of the time series data or a recursive residual of the time series data.
15. The controller of claim 14 , wherein processing the time series data using the first fault detection technique comprises using an artificial intelligence (AI) fault detection method comprising:
determining a second expected value of the time series data based on second inferences made by a second neural network;
calculating a second residual value between the actual value of the time series data and the second expected value of the time series data;
generating second statistical inferences based on the second residual value; and
providing the second statistical inferences as the first fault detection result.
16. The controller of claim 14 , wherein initiating the action to resolve the fault condition comprises scheduling maintenance.