Computer system and method for evaluating health of nodes in a manufacturing network

A computer-implemented method comprising:

• obtaining operating data for a manufacturing network arranged in a hierarchy having a plurality of different levels, wherein the manufacturing network comprises a plurality of edge nodes, a plurality of intermediate nodes, and a root node;
• based on the operating data, determining a respective critical state indicator for each node in at least a given segment of the manufacturing network that includes nodes from at least two different levels of the manufacturing network;
• based on the respective critical state indicator for each node in the given segment of the manufacturing network, recursively determining a respective health score for each node in the given segment of the manufacturing network on a level-by-level basis beginning with a lowest level of given segment and ending with a highest level of the given segment, wherein (1) if a given node in the given segment of the manufacturing network is an edge node in the manufacturing network, the determining of a respective health score for the given node is based on the respective critical state indicator for the given node, (2) if a given node in the given segment of the manufacturing network is an intermediary node in the manufacturing network having one or more nodes that sit beneath the intermediate node at one or more lower levels of the manufacturing network, the determining of a respective health score for the given node is based on the respective critical state indicator for the given node and the respective critical state indicator for each of the one or more nodes that sit beneath the given node in the manufacturing network, and (3) if a given node in the given segment of the manufacturing network is the root node in the manufacturing network, the determining of a respective health score for the given node is based on the respective critical state indicator for the given node and the respective critical state indicator for each other node in the manufacturing network;
• based on the respective health score for each node in the given segment of the manufacturing network, identifying one or more nodes in the given segment of the manufacturing network that are anomalous;
• and
• causing a client station to present a report of the one or more nodes that are identified to be anomalous.

A non-transitory computer-readable storage medium having program instructions stored thereon that are executable to cause a computing system to:

• obtain operating data for a manufacturing network arranged in a hierarchy having a plurality of different levels, wherein the manufacturing network comprises a plurality of edge nodes, a plurality of intermediate nodes, and a root node;
• based on the operating data, determine a respective critical state indicator for each node in at least a given segment of the manufacturing network that includes nodes from at least two different levels of the manufacturing network;
• based on the respective critical state indicator for each node in the given segment of the manufacturing network, recursively determine a respective health score for each node in the given segment of the manufacturing network on a level-by-level basis beginning with a lowest level of given segment and ending with a highest level of the given segment, wherein (1) if a given node in the given segment of the manufacturing network is an edge node in the manufacturing network, the determination of a respective health score for the given node is based on the respective critical state indicator for the given node, (2) if a given node in the given segment of the manufacturing network is an intermediary node in the manufacturing network having one or more nodes that sit beneath the intermediate node at one or more lower levels of the manufacturing network, the determination of a respective health score for the given node is based on the respective critical state indicator for the given node and the respective critical state indicator for each of the one or more nodes that sit beneath the given node in the manufacturing network, and (3) if a given node in the given segment of the manufacturing network is the root node in the manufacturing network, the determination of a respective health score for the given node is based on the respective critical state indicator for the given node and the respective critical state indicator for each other node in the manufacturing network;
• based on the respective health score for each node in the given segment of the manufacturing network, identify one or more nodes in the given segment of the manufacturing network that are anomalous;
• and
• cause a client station to present a report of the one or more nodes that are identified to be anomalous.