Augmented deep learning using combined regression and artificial neural network modeling

Abstract

A method for initiating and automatically improving model-driven operations in a low-data scenario includes creating a regression model using pre-operation data prior to initiating the model-driven operations, using the regression model to initiate and perform the model-driven operations during an operational stage, collecting operational data during the operational stage, creating a first artificial neural network model using the operational data, transitioning from using the regression model to perform the model-driven operations to using the first artificial neural network model to perform the model-driven operations responsive to the operational data satisfying a first sufficiency threshold.

1 - 20 . (canceled) 
     
     
         21 . A method for operating a building management system for a physical plant, the method comprising:
 creating a model using simulated or generated plant data during a pre-operational stage of physical plant;   identifying a plurality of data groups generated by physical plant data during an operational stage of the physical plant;   determining whether the plurality of data groups exceeds a first data sufficiency threshold;   in response to a determination that the plurality of data groups exceeds the first data sufficiency threshold, creating a first artificial neural network model using the plurality of data groups;   determining whether new physical plant data meets a first similarity criterion of at least one of the plurality of data groups;   in response to a determination that the new physical plant data meets the first similarity criterion, making a first artificial neural network prediction using the first artificial neural network model; and   modifying a characteristic of the physical plant according to the first artificial neural network prediction.   
     
     
         22 . The method of  claim 21 , wherein the simulated or generated plant data comprises at least one of manufacturing data and offsite data. 
     
     
         23 . The method of  claim 21 , wherein the physical plant data comprises at least one of plant input data or plant output data, wherein the data groups are data clusters and wherein the model is a linear regression model. 
     
     
         24 . The method of  claim 21 , wherein the first data sufficiency threshold is based on a quantity of physical plant data. 
     
     
         25 . The method of  claim 21 , wherein the method further comprises:
 in response to a determination that the plurality of data groups does not exceed the first data sufficiency threshold, making a regression model prediction using the regression model;   utilizing the regression model prediction to perform at least one of a fault detection task, a fault diagnosis task, or a control task.   
     
     
         26 . The method of  claim 21 , wherein the method further comprises utilizing the first artificial neural network prediction as an input to the regression model, the first artificial neural network prediction configured to improve a quality of the regression model. 
     
     
         27 . A method for initiating and automatically improving model-driven operations in a low-data scenario, the method comprising:
 creating a regression model using simulated or generated plant data prior to initiating the model-driven operations;   using the regression model to initiate and perform the model-driven operations during an operational stage;   collecting operational data during the operational stage;   creating a first artificial intelligence model using the operational data;   transitioning from using the regression model to perform the model-driven operations to using the first artificial neural network model to perform the model-driven operations responsive to the operational data satisfying a first sufficiency threshold.   
     
     
         28 . The method of  claim 27 , further comprising creating a second artificial intelligence model using the operational data; and
 transitioning from using the first artificial intelligence model to perform the model-driven operations to using the second artificial model to perform the model-driven operations responsive to the operational data satisfying a second sufficiency threshold.   
     
     
         29 . The method of  claim 27 , wherein the first sufficiency threshold is satisfied when at least a threshold quantity of the operational data is collected. 
     
     
         30 . The method of  claim 27 , wherein transitioning from using the regression model to using the first artificial intelligence model is further responsive to satisfying a criterion indicative of similarity between the operational data and new operational data. 
     
     
         31 . The method of  claim 30 , wherein the criterion indicative of similarity between the operational data and the new operational data is based on a distance between the new operational data and a cluster of the operational data. 
     
     
         32 . The method of  claim 27 , wherein transitioning from using the regression model and using the first artificial intelligence model comprises calculating a combined output using both the regression model and the first artificial artificial intelligence model and using the combined output to perform the model-driven operations, wherein the first artificial intelligence model is a neural network model. 
     
     
         33 . A method for initiating and automatically improving model-driven operations in a low-data scenario, the method comprising:
 creating a regression model using simulated or generated plant data prior to initiating the model-driven operations;   using the regression model to initiate and perform the model-driven operations during an operational stage;   creating a first artificial neural network model using operational data associated with the model driven operations responsive to determining that a first amount of the operational data bring available; and   using the first artificial neural network model to continue performing the model-driven operations during the operational stage.   
     
     
         34 . The method of  claim 33 , wherein using the first neural network model to continue performing the model-driven operations during the operational stage comprises combining outputs of the first artificial neural network model and the regression model to generate a combined output and using the combined output to perform the model-driven operations. 
     
     
         35 . The method of  claim 34 , wherein combining the outputs of the first artificial neural network model and the regression model comprises calculating a weighted average, wherein the weighted average is weighted based on a distance between a new data sample of the operational data and a cluster of previous data samples of the operational data. 
     
     
         36 . The method of  claim 33 , wherein using the first neural network model to continue performing the model-driven operations during the operational stage comprises determining whether to use the first artificial neural network model or the regression model based on a quantification of similarity between a new data sample of the operational data and one or more previous samples of the operational data. 
     
     
         37 . The method of  claim 33 , wherein performing the model-driven operations during the operational stage comprises collecting more of the operational data, the method further comprising:
 creating a second artificial neural network model using the operational data responsive to determining that a second amount of the operational data has been collected; and   using the second artificial neural network model to continue performing the model-driven operations during the operational stage.   
     
     
         38 . The method of  claim 37 , wherein using the second artificial neural network model to continue performing the model-driven operations during the operational stage comprises combining outputs of the first artificial neural network model and the second artificial neural network model to generate a combined output and using the combined output to perform the model-driven operations. 
     
     
         39 . The method of  claim 33 , wherein performing the model-driven operations during the operational stage comprises controlling a system using a prediction of the regression model, the first artificial neural network model, or a combination of the regression model and the first artificial neural network model. 
     
     
         40 . The method of  claim 39 , wherein the system comprises HVAC equipment.