Description:RELATED APPLICATION
[0001] The present application claims priority to U.S. Non-Provisional Patent Application No. 17/534,875 filed on 24 November 2021 and titled “DETECTION OF DEGRADATION OR AN ANOMALOUS STATE ACROSS HETEROGENOUS INTERNET-OF-THINGS DEVICES USING SYNTHESIZED SENSORS” the entire disclosure of which is hereby incorporated by reference.

TECHNICAL FIELD
[0001] Embodiments generally relate to identifying and developing a baseline model comprising synthesized sensors that generate an output. The output is compared with an output of a machine to detect a fault and/or anomaly based upon differences between the outputs.

BACKGROUND
[0002] Numerous industries include complex systems (e.g., collections of machines, devices, processors, and sensors in automobiles, manufacturing, industrial, etc. that work together in some manner) that are dictated by performance, efficiency and criterions for safety, reliability, ecology, and profitability. As the technology and design complexity increases, monitoring health conditions may become challenging. Thus, errors may be difficult to detect if at all.

BRIEF DESCRIPTION OF THE DRAWINGS
[0003] The various advantages of the embodiments will become apparent to one skilled in the art by reading the following specification and appended claims, and by referencing the following drawings, in which:
[0004] FIG. 1 is a block diagram of an example of a fault detection and processing architecture according to an embodiment;
[0005] FIG. 2 is a flowchart of an example of a method of detecting anomalous events and/or a degraded state according to an embodiment;
[0006] FIG. 3 is an example of pressure curves showing pressure as function of valve position, speed and temperature according to an embodiment;
[0007] FIG. 4 is an example of pressure curves showing pressure as function of valve position, speed, and with temperature being set to 100° F according to an embodiment;
[0008] FIG. 5 is an example of a graph mapping the coefficient A as a function of speed N and constant temperature according to an embodiment;
[0009] FIG. 6 is an example of a graph of coefficient B as a function of speed N and constant temperature according to an embodiment;
[0010] FIG. 7 is an example of a graph of coefficient C as a function of speed N and constant temperature according to an embodiment;
[0011] FIG. 8 is a block diagram of an example of a synthesized sensor generation and processing architecture according to an embodiment;
[0012] FIG. 9 is an example of an actual and synthesized graphs and comparison graphs according to an embodiment;
[0013] FIG. 10 is an example of graphs for an Electrical Vehicle (EV) platform according to an embodiment;
[0014] FIG. 11 is a flowchart of an example of a method of assigning states to a system according to an embodiment;
[0015] FIG. 12 is a block diagram of an example of a security and robustness enhanced computing system according to an embodiment;
[0016] FIG. 13 is an illustration of an example of a semiconductor apparatus according to an embodiment;
[0017] FIG. 14 is a block diagram of an example of a processor according to an embodiment; and
[0018] FIG. 15 is a block diagram of an example of a multi-processor based computing system according to an embodiment.

DESCRIPTION OF EMBODIMENTS
[0019] Some embodiments develop a baseline (e.g., a “healthy”) model that is compared with a system under consideration. A delta may be generated based on outputs of the baseline model and the system. The delta may guide decision making processes, such as detecting a fault or anomaly. For example, some embodiments generate generic composite functions that are transformed into synthesized sensors. The synthesized sensors may correspond to actual sensors of a system so as to provide a healthy baseline for the actual sensors. Combining and transforming the composite functions to form synthesized sensors may be a broad-based approach that models non-linear effects resulting from mutual interactions between subsystems of the system.
[0020] Turning now to FIG. 1, a fault detection and processing architecture 100 is illustrated. For example, a system 104 (e.g., an internet-of-things device) includes physical sensors 106 (e.g., a first plurality of sensors) that sense operating conditions (e.g., temperature, pressure, etc.) of the system 104. The sensed operating conditions may be set as an actual sensor output 112 (e.g., first output). A synthesizer 116 generates synthesized operations that synthesize operations of physical sensors 106 of a system 104. For example, the synthesizer 116 develops composite functions. The composite functions may be reused and adjusted across a plurality of different systems. For example, after developing these composite functions, the synthesizer 116 reuses the composite functions for many other machines. Even though the various machines are different from each other, the responses of the machines to the inputs follow the various laws (e.g., gravity, interaction, thermal, chemical reaction, etc.). Indeed, these composite functions may be derived to capture these behaviors and interactions (e.g., 1st, 2nd, or 3rd Order) between processes of the system. Thus, the synthesizer 116 may operate with a plurality of different systems by adjusting the composite functions to generate synthesized sensors 122. In this example, the composite functions are adjusted based on the system 104.
, Claims:1. A computing system comprising:
a network controller to communicate with a device having a first plurality of sensors that senses conditions of operations of a system as the system executes a process based on a first input, wherein the conditions are stored as a first output;
a processor coupled to the network controller; and
a memory coupled to the processor, the memory including a set of executable program instructions, which when executed by the processor, cause the computing system to:
generate synthesized sensors that synthesize operations of the first plurality of sensors,
generate a second output based on the synthesized sensors and the first input, and
detect whether one or more of a degradation and an anomalous state exists based on a comparison of the first output to the second output.