System and methods for fault-isolation and fault-mitigation based on network modeling
A system and method for identifying a monitoring point in an electrical and electronic system (EES) in a vehicle. The method includes defining a network model of the EES where potential monitoring point locations in the model are identified as targets, such as nodes. The method then computes a betweenness centrality metric for each target in the model as a summation of a ratio of a number of shortest paths between each pair of targets in the model that pass through the target whose betweenness centrality metric is being determined to a total number of shortest paths between each pair of targets. The method identifies which of the betweenness centrality metrics are greater than a threshold that defines a minimum acceptable metric and determines which of those targets meets a predetermined model coverage. The monitoring point is selected as the target that best satisfies the minimum metric and the desired coverage.
1. A method for identifying an information monitoring point in an electrical and electronic system (EES) on a vehicle, said method comprising:
defining a network model of the EES where potential monitoring points in the model are identified as targets;
determining, using a microprocessor, a betweenness centrality metric for each target in the model as a summation of a ratio of a number of shortest paths between each pair of targets in the model that pass through the target whose betweenness centrality metric is being determined to a total number of shortest paths between each pair of targets;
selecting a minimum betweenness centrality metric threshold;
identifying which of the determined betweenness centrality metrics for each of the targets is greater than the threshold;
defining a minimum degree of neighbor factor that defines a predetermined coverage of a target relative to all of the other targets;
determining which of the targets having a betweenness centrality metric greater than the threshold has a degree of neighbor factor greater than the minimum degree of neighbor factor; and
identifying a target, from the determined targets having a betweenness centrality metric greater than the threshold and having a degree of neighbor factor greater than the minimum degree of neighbor factor, that has the highest betweenness centrality metric as the information monitoring point.
2. The method according to claim 1 wherein the model includes nodes that are selected from the group consisting of electronic control units and software components, and edges that are connections between the nodes.
3. The method according to claim 2 wherein the targets include edges in the network model.
4. The method according to claim 2 wherein the targets include nodes in the network model.
5. The method according to claim 1 wherein the network model is a layered model.
6. The method according to claim 5 wherein the network model includes a data flow network layer, a message network layer, a functional network layer, a physical network layer and an electrical network layer.
7. The method according to claim 1 wherein the betweenness centrality metric is a homogenous multi-partite betweenness centrality metric, an inverse multi-partite betweenness centrality metric, a designated multi-partite betweenness centrality metric, a homogenous multi-attribute betweenness centrality metric, an inverse multi-attribute betweenness centrality metric or an edge betweenness centrality metric.
8. The method according to claim 1 wherein the minimum degree of neighbor factor is a second degree of neighbor factor where a particular target is within two connections of another target.
9. The method according to claim 1 further comprising reducing the minimum betweenness centrality metric threshold if none of the targets satisfies the predetermined coverage provided by the minimum degree of neighbor factor.
10. The method according to claim 1 further comprising performing a target failure simulation for each target to determine whether a target has failed.
11. A method for identifying an information monitoring point in an electrical and electronic system (EES) on a vehicle, said method comprising:
defining a layered network model of the EES that includes nodes identifying one or more of electronic control units and software components in the EES;
determining, using a microprocessor, a betweenness centrality metric for each node in the model as a summation of a ratio of a number of shortest paths between each pair of nodes in the model that pass through the node whose betweenness centrality metric is being determined to a total number of shortest paths between each pair of nodes;
selecting a minimum betweenness centrality metric threshold;
identifying those nodes having a determined betweenness centrality metric is greater than the threshold to be potential monitoring points;
defining a minimum degree of neighbor factor that defines a predetermined coverage of a node relative to all of the other nodes; and
identifying one of the potential monitoring points which has a degree of neighbor factor greater than the minimum degree of neighbor factor and has a highest betweenness centrality metric as the information monitoring point.
12. The method according to claim 11 wherein the minimum degree of neighbor factor is a second degree of neighbor factor where a particular node is within two connections of another node.
13. The method according to claim 11 wherein the betweenness centrality metric is a homogenous multi-partite betweenness centrality metric, an inverse multi-partite betweenness centrality metric, a designated multi-partite betweenness centrality metric, a homogenous multi-attribute betweenness centrality metric, an inverse multi-attribute betweenness centrality metric or an edge betweenness centrality metric.
14. A system for identifying an information monitoring point in an electrical and electronic system (EES) on a vehicle, said system comprising:
a microprocessor coupled to a memory, where said microprocessor is configured with an algorithm, said algorithm including:
defining a network model of the EES where potential monitoring points in the model are identified as targets;
determining a betweenness centrality metric for each target in the model as a summation of a ratio of a number of shortest paths between each pair of targets in the model that pass through the target whose betweenness centrality metric is being determined to a total number of shortest paths between each pair of targets;
selecting a minimum betweenness centrality metric threshold;
identifying which of the determined betweenness centrality metrics for each of the targets is greater than the threshold;
defining a minimum degree of neighbor factor that defines a predetermined coverage of a target relative to all of the other targets;
determining which of the targets having a betweenness centrality metric greater than the threshold has a degree of neighbor factor greater than the minimum degree of neighbor factor; and
identifying a target, from the determined targets having a betweenness centrality metric greater than the threshold and having a degree of neighbor factor greater than the minimum degree of neighbor factor, that has the highest betweenness centrality metric as the information monitoring point.
15. The system according to claim 14 wherein defining a network model of the EES defines a model including nodes that are selected from the group consisting of electronic control units and software components, and edges that are connections between the nodes.
16. The system according to claim 15 wherein the targets include edges in the network model.
17. The system according to claim 15 wherein the targets include nodes in the network model.
18. The system according to claim 14 wherein determining a betweenness centrality metric selects the betweenness centrality metric as a homogenous multi-partite betweenness centrality metric, an inverse multi-partite betweenness centrality metric, a designated multi-partite betweenness centrality metric, a homogenous multi-attribute betweenness centrality metric, an inverse multi-attribute betweenness centrality metric or an edge betweenness centrality metric.
19. The system according to claim 14 wherein defining a minimum degree of neighbor factor defines the minimum degree of neighbor factor as a second degree of neighbor factor where a particular target is within two connections of another target.