Generating predictions and confidence therein for industrial conditions in monitoring and managing industrial settings

Abstract

A variety of kits are provided that are configured with components, systems and methods for monitoring various industrial settings, including kits with self-configuring sensor networks, communication gateways, and automatically configured back end systems.

What is claimed is: 
     
         1 . A method for monitoring an industrial setting using a sensor kit having a plurality of sensors and an edge device including a processing system, comprising:
 receiving, by the processing system, reporting packets from one or more respective sensors of the plurality of sensors, wherein each reporting packet includes routing data and one or more instances of sensor data;   generating, by the processing system, a set of feature vectors based on one or more respective instances of sensor data received in the reporting packets;   inputting, by the processing system, each respective feature vector into a respective machine-learned model of a plurality of machine-learned models that are each trained to predict or classify a respective condition of an industrial component of the industrial setting or of the industrial setting based on a set of features that are derived from instances of sensor data captured by one or more of the plurality of sensors;   obtaining, by the processing system, a respective prediction or classification and a degree of confidence corresponding to the respective prediction or classification from each respective machine-learned model based on the respective feature vector inputted into the respective machine-learned model;   selectively encoding, by the processing system, the one or more instances of sensor data based on the respective prediction or classification to obtain one or more sensor kit packets; and   transmitting, by the processing system, the sensor kit packets to a backend system via a public network.   
     
     
         2 . The method of  claim 1 , wherein the sensor kit includes a gateway device configured to receive sensor kit packets from the edge device via a wired communication link and transmit the sensor kit packets to the backend system via the public network on behalf of the edge device. 
     
     
         3 . The method of  claim 2 , wherein the gateway device includes a satellite terminal device that transmits the sensor kit packets to a satellite that routes the sensor kit packets to the public network. 
     
     
         4 . The method of  claim 2 , wherein the gateway device includes a cellular chipset that transmits the sensor kit packets to a cellphone tower of a preselected cellular provider. 
     
     
         5 . The method of  claim 1 , wherein receiving the reporting packets from the one or more respective sensors is performed using a first communication device implementing a first communication protocol and transmitting the sensor kit packets to the backend system is performed using a second communication device implementing a second communication protocol. 
     
     
         6 . The method of  claim 5 , wherein the second communication device of the edge device is a satellite terminal device and transmitting the sensor kit packets to the backend system includes transmitting, by the satellite terminal device, the sensor kit packets to a satellite that routes the sensor kit packets to the public network. 
     
     
         7 . The method of  claim 1 , further comprising:
 compressing, by the processing system, the one or more instances of sensor data using a lossy codec in response to obtaining one or more predictions or classifications relating to conditions of the respective industrial components of the industrial setting and the industrial setting that collectively indicate that there are likely no issues relating to any industrial component of the industrial setting and the industrial setting.   
     
     
         8 . The method of  claim 7 , wherein compressing the one or more instances of sensor data using the lossy codec includes:
 normalizing the one or more instances of sensor data into respective pixel values;   encoding the respective pixel values into a video frame; and   compressing a block of video frames using the lossy codec, wherein the lossy codec is a video codec and the block of video frames includes the video frame and one or more other video frames that include normalized pixel values of other instances of the sensor data.   
     
     
         9 . The method of  claim 7 , further comprising:
 compressing, by the processing system, the one or more instances of sensor data using a lossless codec in response to obtaining a prediction or classification relating to a condition of a particular industrial component or the industrial setting that indicates that there is likely an issue relating to the particular industrial component or the industrial setting.   
     
     
         10 . The method of  claim 7 , further comprising:
 refraining, by the processing system, from compressing the one or more instances of sensor data in response to obtaining a prediction or classification relating to a condition of a particular industrial component or the industrial setting that indicates that there is likely an issue relating to the particular industrial component or the industrial setting.   
     
     
         11 . The method of  claim 1 , wherein the edge communication device includes one or more storage devices that store the plurality of machine-learned models. 
     
     
         12 . The method of  claim 11 , wherein the one or more storage devices store instances of the sensor data captured by the plurality of sensors of the sensor kit. 
     
     
         13 . The method of  claim 12 , further comprising selectively storing, by the processing system, the one or more instances of sensor data in the one or more storage devices based on the respective predictions or classifications. 
     
     
         14 . The method of  claim 13 , further comprising:
 storing, by the processing system, the one or more instances of sensor data in the storage device with an expiry such that the one or more instances of sensor data are purged from the storage device in accordance with the expiry, wherein the processing system stores the one or more instances of sensor data in the storage device with the expiry in response to obtaining one or more predictions or classifications relating to conditions of respective industrial components of the industrial setting and the industrial setting that collectively indicate that there are likely no issues relating to any industrial component of the industrial setting and the industrial setting.   
     
     
         15 . The method of  claim 13 , further comprising:
 storing, by the processing system, the one or more instances of sensor data in the storage device indefinitely in response to obtaining a prediction or classification relating to a condition of a particular industrial component or the industrial setting that indicates that there is likely an issue relating to the particular industrial component or the industrial setting.   
     
     
         16 . The method of  claim 1 , further comprising:
 capturing, by the plurality of sensors, sensor data; and   transmitting, by the plurality of sensors, the sensor data via a self-configuring sensor kit network.   
     
     
         17 . The method of  claim 16 , wherein transmitting the sensor data via the self-configuring sensor kit network includes directly transmitting, by each sensor of the plurality of sensors, instances of sensor data with the edge device using a short-range communication protocol, wherein the self-configuring sensor kit network is a star network. 
     
     
         18 . The method of  claim 17 , further comprising initiating, by the processing system, configuration of the self-configuring sensor kit network. 
     
     
         19 . The method of  claim 16 , wherein the self-configuring sensor kit network is a mesh network and each sensor of the plurality of sensors includes a communication device. 
     
     
         20 . The method of  claim 19 , further comprising:
 establishing, by the communication device of each sensor of the plurality of sensors, a communication channel with at least one other sensor of the plurality of sensors;   receiving, by at least one sensor of the plurality of sensors, instances of sensor data from one or more other sensors of the plurality of sensors; and   routing, by the at least one sensor of the plurality of sensors, the received instances of the sensor data towards the edge device.   
     
     
         21 . The method of  claim 16 , wherein the self-configuring sensor kit network is a hierarchical network and the sensor kit includes one or more collection devices. 
     
     
         22 . The method of  claim 21 , further comprising:
 receiving, by at least one collection device of the plurality of collection devices, reporting packets from one or more sensors of the plurality of sensors; and   routing, by the at least one collection device of the plurality of collection devices, the reporting packets to the edge device.   
     
     
         23 . The method of  claim 1 , wherein the plurality of sensors includes a first set of sensors of a first sensor type and a second set of sensors of a second sensor type.