Abnormal behavior detection of vehicles

Abstract

The present application relates to abnormal behavior detection of a vehicle. A vehicle includes a first system (104), a first sensor (150), a second sensor (152), and a processor (120). The first sensor is configured to generate first sensor data (151) indicating an operating state of the first system. The second sensor is configured to generate second sensor data (153) associated with an adaptive performance metric adjustment (135). The processor is configured to: in response to determining that the second sensor data meets the adaptive performance metric adjustment standard (135), determine an adaptive performance metric (137) to be compared with the first sensor data based on the second sensor data to identify abnormal behavior of the first system. The processor (120) is also configured to compare the first sensor data (151) with the adaptive performance metric (137), and generate a maintenance alarm (139) in response to determining that the first sensor data (151) does not meet the adaptive performance metric (137).

Description

Technical Field

[0001] The present disclosure generally relates to vehicle abnormal behavior detection. Background Art

[0002] Maintenance and fault detection limits (or thresholds) are typically based on vehicle type (e.g., model or make) across the fleet. As an example of such maintenance limits, the engine air filter for each specific type of aircraft in the fleet may be changed annually (based on a one-year service time threshold for the engine air filter). As an example of such a fault detection limit, the fault threshold for the engine air filter may be set to a specific pressure drop for each specific type of aircraft in the fleet.

[0003] Typically, such limits are established assuming a worst-case operating environment for the vehicles in the fleet or an average operating environment for the vehicles in the fleet, and do not take into account individual vehicle conditions. For most vehicles in the fleet, maintenance and fault detection limits based on a worst-case operating environment will be too conservative, resulting in higher maintenance costs than necessary. However, maintenance and fault detection limits based on an average operating environment for the vehicles in the fleet may not be applicable to vehicles operating in an operating environment that is different from (e.g., better or worse than) the expected (e.g., average or worst-case) operating environment. Summary of the invention

[0004] In a particular embodiment, a vehicle includes a first system, a first sensor, a second sensor, a memory, and a processor. The first system is a first system type, and the first sensor is configured to generate first sensor data indicating an operating state of the first system. The second sensor is configured to generate second sensor data associated with an adaptive performance metric adjustment criterion. The memory is configured to store the first sensor data and the second sensor data during one or more operations of the vehicle. The processor is configured to determine whether the second sensor data meets the adaptive performance metric adjustment criterion. The processor is also configured to determine an adaptive performance metric to be compared with the first sensor data based on the second sensor data in response to determining that the second sensor data meets the adaptive performance metric adjustment criterion to identify abnormal behavior of the first system. The processor is also configured to compare the first sensor data with the adaptive performance metric, and generate a maintenance alert in response to determining that the first sensor data does not meet the adaptive performance metric.

[0005] In another specific embodiment, a method includes: receiving, at a device, first sensor data from a first sensor indicating an operating state of a first system of a first system type. The method also includes receiving, at the device, second sensor data associated with an adaptive performance metric adjustment criterion from a second sensor. The method also includes determining, at the device, whether the second sensor data satisfies the adaptive performance metric adjustment criterion. The method also includes, based on determining that the second sensor data satisfies the adaptive performance metric adjustment criterion, determining an adaptive performance metric based on the second sensor data. The method also includes comparing, at the device, the first sensor data with the adaptive performance metric to identify abnormal behavior of the first system; and generating a maintenance alert at the device based on determining that the first sensor data does not satisfy the adaptive performance metric.

[0006] In another specific embodiment, a computer readable storage device stores instructions that, when executed by a processor, cause the processor to perform operations including: receiving first sensor data indicating an operating state of a first system of a first system type from a first sensor. The operations also include receiving second sensor data associated with an adaptive performance metric adjustment criterion from a second sensor. The operations also include determining whether the second sensor data satisfies the adaptive performance metric adjustment criterion. The operations also include, based on determining that the second sensor data satisfies the adaptive performance metric adjustment criterion, selectively determining an adaptive performance metric based on the second sensor data. The operations also include comparing the first sensor data to the adaptive performance metric to identify abnormal behavior of the first system; and generating a maintenance alert based on determining that the first sensor data does not satisfy the adaptive performance metric.

[0007] The features, functions, and advantages described herein can be achieved independently in various embodiments or may be combined in yet other embodiments further details of which can be found with reference to the following description and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 is a block diagram illustrating a system operable to detect abnormal behavior in a vehicle;

[0009] Figure 2 is an exemplary flow chart of a method for detecting abnormal behavior of a vehicle; and

[0010] Figure 3 is an illustration of a block diagram of a vehicle configured to support aspects of computer-implemented methods and computer-executable program instructions (or code) according to the present disclosure. DETAILED DESCRIPTION

[0011] Embodiments described herein are dedicated to abnormal behavior detection of vehicles. A vehicle includes a first system and a plurality of sensors. For example, the vehicle may include at least one of an airplane, a ship, a truck, a train, or a car. In this example, the first system may include an air conditioning system, a braking system, an actuator, a charging system, an engine, a starting system, or other systems of the vehicle. A plurality of sensors include a first sensor (or a plurality of first sensors), and the first sensor is configured to generate first sensor data indicating the operating state of the first system. For example, the first sensor may directly or indirectly measure a parameter indicating the state of the first system (e.g., whether the first system is turned on, stopped (off), turned on, turned off, etc.). The plurality of sensors also include a second sensor (or a plurality of second sensors), and the second sensor is configured to generate a second sensor data for selecting or determining an adaptive performance metric for the first system. For example, the second sensor may directly or indirectly measure a parameter for changing or adjusting an adaptive performance metric based on a specific condition of the vehicle. Therefore, although the vehicle fleet can initially use the same performance metric to identify abnormal behavior, as conditions change and the vehicles operate in different environments, the second sensor data varies for different vehicles in the vehicle fleet, resulting in different adaptive performance metrics being used to detect abnormal behavior associated with different vehicles in the vehicle fleet. To illustrate, in a specific embodiment, the first system includes an actuator, the first sensor data indicates a measured time to open the actuator, and the second sensor data indicates a transition count of the actuator from a closed state to an open state, an average time to open the actuator, and an operating hour of the actuator. In this embodiment, the adaptive performance metric changes after a specific number of transitions of the actuator. Therefore, although each vehicle in the vehicle fleet can initially use an actuator opening time threshold to detect abnormal behavior of the actuator, after a period of time, one vehicle may use the actuator more frequently than another vehicle in the vehicle fleet. The adaptive performance metric of the vehicle that uses the actuator more frequently can be updated, resulting in different vehicles in the vehicle fleet using different performance metrics. This adjustment of the performance metric avoids the use of overly conservative performance metrics (e.g., performance metrics based on worst-case operating conditions) while avoiding the use of performance metrics that do not provide sufficient margin (e.g., performance metrics based on average operating conditions). As a result, the operation and maintenance of each vehicle in the fleet is personalized, resulting in improved uptime for vehicles in the fleet that typically operate under conditions less severe than the worst-case operating conditions, and improved fault detection for vehicles in the fleet that typically operate under conditions more severe than the average operating conditions of the fleet.

[0012] To enable use of the adaptive performance metric, a memory accessible to (e.g., communicatively coupled to) a vehicle includes the adaptive performance metric and the adaptive performance metric adjustment criteria. For example, the adaptive performance metric is based on a default value, a configuration setting, or both. In a specific example, multiple vehicles in a fleet of vehicles are configured to have the same initial adaptive performance metric. The adaptive performance metric adjustment criteria indicate when to adjust the adaptive performance metric of the vehicle.

[0013] The vehicle includes a sensor data analyzer configured to update the adaptive performance metric in response to determining that the sensor data (e.g., the second sensor data) meets the adaptive performance metric adjustment criteria. For illustration, continuing the above example, in response to determining that the operating hours of the actuator are greater than the operating hours threshold and the average time of opening is greater than the average time threshold, the sensor data analyzer can determine that the sensor data (e.g., the second sensor data) meets the adaptive performance metric adjustment criteria. Other examples can also be considered. For illustration, the second sensor data can be compared with the average value of the vehicle fleet range to determine whether to adjust the adaptive performance metric. As another illustrative example, the second data from multiple second sensors can be compared with multiple adaptive performance metric adjustment criteria to determine whether to adjust the adaptive performance metric and how to adjust the adaptive performance metric. In this example, the result of comparing the second sensor data with multiple adaptive performance metric adjustment criteria can be combined algebraically (e.g., using a weighted sum or a weighted average) or logically (e.g., using Boolean operations such as "or", "and", or "non-or", etc.) to determine whether and / or how to adjust the adaptive performance metric.

[0014] The sensor data analyzer determines (e.g., updates) the adaptive performance metric in response to determining that the sensor data meets the adaptive performance metric adjustment criteria. How to update the adaptive performance metric may vary depending on the type of system being evaluated, the data compared with the adaptive performance metric, and the specific implementation. As a simple example, the adaptive performance metric may have a first predetermined value (e.g., a first constant value) before the adaptive performance metric adjustment criteria are met, and may have a second predetermined value (e.g., a second constant value) after the adaptive performance metric adjustment criteria are met. In a more complex example, the adaptive performance metric may have a first predetermined value (e.g., a first constant value) before the adaptive performance metric adjustment criteria are met, and may have a variable value after the adaptive performance metric adjustment criteria are met. In this example, after determining that the adaptive performance metric adjustment criteria are met, the variable value may be calculated based on the first sensor data, the second sensor data, other data, or any combination thereof. Optionally, after determining that the adaptive performance metric adjustment criteria are met, the variable value may be retrieved from a query table or other data structure (e.g., a decision tree, an artificial neural network, or other learning model). In a more complex example, the adaptive performance metric may indicate that the first sensor data is compared to a threshold value (e.g., a first constant value or a first variable value) before the adaptive performance metric adjustment criteria are met, and indicates that after the adaptive performance metric adjustment criteria are met, data from one or more other sensors are compared to one or more different threshold values ​​(e.g., a set of constant values, a set of variable values, or any combination thereof). In this example, the one or more other sensors may include the first sensor (which generates the first sensor data) as well as the other sensors, or the first sensor may be ignored for the purpose of evaluating the adaptive performance metric after the adaptive performance metric adjustment criteria are met.

[0015] The sensor data analyzer generates a maintenance alert in response to determining that the sensor data (eg, the first sensor data) does not satisfy the adaptive performance metric (eg, the updated value of the adaptive performance metric). Thus, the sensor data analyzer adjusts the adaptive performance metric based on conditions detected on the vehicle.

[0016] Figure 1 1 is a block diagram of a system 100 that can be used to perform vehicle abnormal behavior detection. The system 100 includes a vehicle 102 that is communicatively coupled to (e.g., includes) a display 110. The vehicle 102 includes, but is not limited to, a car, a truck, an airplane, a boat, a train, an unmanned vehicle, a manned vehicle, or any combination thereof. It should be noted that in the following description, the vehicle 102 is referred to as a vehicle 102. Figure 1Various functions performed by the system 100 are described as being performed by certain components or modules. However, this division of components and modules is for illustration only. On the other hand, functions described herein as being performed by a particular component or module are divided among multiple components or modules. In addition, on the other hand, Figure 1 Two or more components or modules of are integrated into a single component or module. In a specific aspect, one or more functions performed by the vehicle 102 described herein are divided among multiple devices (e.g., the vehicle 102, a central server, a distributed system, or any combination thereof). Figure 1 Each component or module shown may be implemented using hardware (e.g., a field programmable gate array (FPGA) device, an application specific integrated circuit (ASIC), a digital signal processor (DSP), a controller, etc.), software (e.g., instructions executable by a processor), or any combination thereof.

[0017] The vehicle 102 is communicatively coupled to the sensor data analyzer 120, the memory 132, the input interface 128, the display interface 126, the plurality of sensors 160, the plurality of systems (including the system 104), or any combination thereof. In a specific aspect, the vehicle 102 includes the sensor data analyzer 120, the memory 132, the input interface 128, the display interface 126, the plurality of sensors 160, the plurality of systems (including the system 104), or any combination thereof. In a specific aspect, one or more of the sensor data analyzer 120, the memory 132, the input interface 128, the display interface 126, the plurality of sensors 160, or the plurality of systems (including the system 104) are external to the vehicle 102 (e.g., remote from the vehicle 102). The memory 132 includes a volatile memory device (e.g., a random access memory (RAM) device), a non-volatile memory device (e.g., a read-only memory (ROM) device, a programmable read-only memory, and a flash memory), or both. In particular aspects, the memory 132 includes one or more applications (e.g., instructions) executable by the sensor data analyzer 120 to initiate, control, or perform one or more operations described herein. In the illustrative example, a computer-readable storage device (e.g., the memory 132) includes instructions that, when executed by a processor (e.g., the sensor data analyzer 120), cause the processor to initiate, perform, or control the operations described herein.

[0018] The display interface 126 is configured to be communicatively coupled to the display 110. In a specific aspect, the display 110 is external to the vehicle 102. In another aspect, the display 110 is internal to the vehicle 102. The input interface 128 is configured to be communicatively coupled to an input device, such as a keyboard, a mouse, a motion sensor, a camera, or a microphone. In a specific example, the input interface 128 is configured to receive user input 147 from the user 101.

[0019] The plurality of systems include system 104. For illustration, in various embodiments, system 104 includes an environmental control system (e.g., an air conditioning system), a braking system, a charging system, an actuator, an engine, a starting system, other vehicle systems, or any combination thereof. System 104 includes one or more components. For example, in Figure 1 , system 104 includes a first component 182, a second component 184, and a third component 186. It should be understood that as an illustrative example, system 104 is described as including three components. In some examples, system 104 includes less than three components, and in other examples, system 104 includes more than three components. Figure 1 , the plurality of sensors 160 includes a first sensor 150, a second sensor 152, a third sensor 154, a fourth sensor 156, and a fifth sensor 158. It should be understood that as an illustrative example, the plurality of sensors 160 is described as including five sensors. In some examples, the plurality of sensors 160 includes less than five sensors, and in other examples, the plurality of sensors 160 includes more than five sensors.

[0020] The plurality of sensors 160 are configured to generate sensor data 149 indicating an operating state of the system 104. For example, the first sensor 150, the second sensor 152, the third sensor 154, the fourth sensor 156, and the fifth sensor 158 are configured to respectively generate first sensor data 151, second sensor data 153, third sensor data 155, fourth sensor data 157, and fifth sensor data 159. The first sensor data 151, the second sensor data 153, the third sensor data 155, the fourth sensor data 157, the fifth sensor data 159, or any combination thereof indicates an operating state of the first component 182, the second component 184, the third component 186, or any combination thereof.

[0021] In a specific aspect, the memory 132 is configured to store a plurality of "execution stacks". The execution stack includes one or more "execution attributes" in a specific order. The specific order indicates the order in which the sensor data analyzer 120 processes the one or more "execution attributes". The execution attributes specify one or more information processing actions, identify information used to perform one or more information processing actions, or any combination thereof. In a specific embodiment, the one or more information processing actions include, but are not limited to, identifying, receiving, analyzing, changing, storing, and reporting. In some examples, the execution stack includes execution attributes such as those disclosed in U.S. Patent No. 9,633,489 ("Schmitz et al."), the entire contents of which are incorporated herein by reference.

[0022] In a particular example, memory 132 is configured to store first execution stack 161, second execution stack 163, adaptive performance metric adjustment execution stack 165, adaptive performance metric execution stack 167, or any combination thereof. It should be understood that as an illustrative example, memory 132 is described as being configured to store four execution stacks. In some examples, memory 132 is configured to store less than four execution stacks, and in other examples, memory 132 is configured to store more than four execution stacks.

[0023] The first execution stack 161 is executable to determine when to store sensor data in the memory 132. For example, Figure 1 , the first execution stack 161 includes one or more first execution attributes indicating a first condition 171, and one or more second execution attributes indicating that the first sensor data 151 is stored in the memory 132 in response to determining that the first condition 171 is satisfied. The first condition 171 indicates when the first sensor data 151 is stored in the memory 132. In this example, the first condition 171 may be satisfied based on the value of the first sensor data 151, the time since the previous sensor data was stored in the memory 132, the time since the system 100 was initialized or turned on, the values ​​of other sensor data (e.g., the value of the fifth sensor data 159), etc. Similarly, in Figure 1 , the second execution stack 163 includes one or more third execution attributes indicating the second condition 173, and one or more fourth execution attributes indicating that the second sensor data 153 is stored in the memory 132 in response to determining that the second condition 173 is satisfied. The second condition 173 indicates when the second sensor data 153 is stored in the memory 132. The adaptive performance metric adjustment execution stack 165 includes one or more fifth execution attributes indicating the adaptive performance metric adjustment criteria 135, and one or more sixth execution attributes indicating how the adaptive performance metric 137 is to be updated in response to determining that the adaptive performance metric adjustment criteria 135 is satisfied. The adaptive performance metric adjustment criteria 135 indicates when to update the adaptive performance metric 137. The adaptive performance metric execution stack 167 includes one or more seventh execution attributes indicating the adaptive performance metric 137, and one or more eighth execution attributes indicating that the maintenance alert 139 is to be generated in response to determining that the adaptive performance metric 137 is not satisfied.

[0024] It should be understood that although each of the first execution stack 161, the second execution stack 163, the adaptive performance metric adjustment execution stack 165, and the adaptive performance metric execution stack 167 is described as a single execution stack, in some embodiments, one or more of the first execution stack 161, the second execution stack 163, the adaptive performance metric adjustment execution stack 165, or the adaptive performance metric execution stack 167 corresponds to multiple execution stacks. In a specific example, the adaptive performance metric adjustment execution stack 165 corresponds to a first execution stack including one or more fifth execution attributes and a second execution stack including one or more sixth execution attributes. The sensor data analyzer 120 executes the second execution stack in response to determining that the adaptive performance metric adjustment criteria 135 indicated by the first execution stack are met. Similarly, in a specific example, the adaptive performance metric execution stack 167 corresponds to a first specific execution stack including one or more seventh execution attributes and a second specific execution stack including one or more eighth execution attributes. The sensor data analyzer 120 executes the second specific execution stack in response to determining that the adaptive performance metric 137 indicated by the first specific execution stack is not met.

[0025] In a particular embodiment, the sensor data analyzer 120 places the first, third, fifth, and seventh execution attributes and the corresponding second, fourth, sixth, and eighth execution attributes in separate processing queues. The sensor data analyzer 120 automatically processes the first, third, fifth, and seventh execution attributes to determine whether the first condition 171, the second condition 173, the adaptive performance metric adjustment criteria 135, and the adaptive performance metric 137 are satisfied, respectively. The sensor data analyzer 120 processes the corresponding second, fourth, sixth, and / or eighth execution attributes in response to determining that at least one of the first condition 171, the second condition 173, the adaptive performance metric adjustment criteria 135, or the adaptive performance metric 137 is satisfied. In a particular example, the sensor data analyzer 120 executes a plurality of execution stacks in response to detecting an update of data from a plurality of sensors 160. In a particular example, the plurality of execution stacks depends on data from a single sensor, and the sensor data analyzer 120 executes the plurality of execution stacks in response to detecting an update of data from a single sensor.

[0026] In a specific aspect, the memory 132 stores processing attributes (e.g., configuration settings, default values, or both) indicating when the execution attributes (e.g., the first execution attribute, the third execution attribute, and the fifth execution attribute) in each processing queue will be processed. Optionally, the memory 132 stores processing attributes associated with a specific execution attribute (e.g., the first execution attribute, the third execution attribute, or the fifth execution attribute), which indicates when the specific execution attribute is to be processed.

[0027] In certain embodiments, new execution attributes may be generated to implement changes to information processing on the vehicle 102. For example, the new execution attributes define a plurality of new information processing actions to be performed by the sensor data analyzer 120 running on the vehicle 102 without changing the sensor data analyzer 120 on the vehicle 102. The new execution attributes may be loaded onto the vehicle 102 by adding the new execution attributes to execution attributes already in one or more execution stacks 161-167, by modifying execution attributes already in one or more execution stacks 161-167, or both. For example, the user 101 may provide user input 147 to update the adaptive performance metric adjustment criteria 135, the first condition 171, the second condition 173, or any combination thereof. In a specific aspect, the sensor data analyzer 120 determines (e.g., updates) the adaptive performance metric adjustment criteria 135 based on a lookup table or other data structure (e.g., a decision tree, an artificial neural network, or other learning model). In a specific aspect, the processor of the vehicle 102 updates one or more execution properties of the execution stack 161-167 (e.g., the adaptive performance metric adjustment criteria 135, the adaptive performance metric 137, the first condition 171, the second condition 173, or any combination thereof) in response to receiving a request from another device (e.g., a maintenance device).

[0028] The sensor data analyzer 120 is configured to update the sensor data 149 in the memory 132 in response to determining whether one or more conditions are satisfied. For example, the sensor data analyzer 120 is configured to update the sensor data 149 in the memory 132 to include the first sensor data 151 in response to determining that the first condition 171 is satisfied. As another example, the sensor data analyzer 120 is configured to update the sensor data 149 in the memory 132 to include the second sensor data 153 in response to determining that the second condition 173 is satisfied.

[0029] The sensor data analyzer 120 is configured to determine (e.g., update) an adaptive performance metric 137 in response to determining that the adaptive performance metric adjustment criteria 135 are met based on the sensor data 149. In a specific aspect, the system 104 is a first system type (e.g., a braking system, a navigation system, etc.). Typically, multiple vehicles in the vehicle fleet include systems of the first system type. In a specific embodiment, the initial value of the adaptive performance metric 137 is based on the operation of multiple systems of the vehicles corresponding to the vehicle fleet. For example, the vehicle fleet includes a vehicle 102, a second vehicle, and one or more additional vehicles. In this example, the vehicle 102 includes a system 104 of the first system type, the second vehicle includes a second system of the first system type, and so on. In addition, in this example, the vehicle 102 and the second vehicle include the same initial value of the adaptive performance metric 137 associated with the system 104 and the second system, respectively. The initial value can be based on, for example, the expected operating environment of the vehicle, historical data, manufacturer recommendations, etc.

[0030] The sensor data analyzer 120 is configured to update the adaptive performance metric adjustment criteria 135, the adaptive performance metric 137, or both based on conditions detected over time at the vehicle 102 (e.g., the sensor data 149). The sensor data analyzer 120 is also configured to generate a maintenance alert 139 in response to determining that the sensor data 149 does not satisfy the adaptive performance metric 137. The sensor data analyzer 120 thus generates the maintenance alert 139 based on the adaptive performance metric 137 that is applicable to the conditions detected at the vehicle 102.

[0031] During operation, the sensor 160 generates first sensor data 151 , second sensor data 153 , third sensor data 155 , fourth sensor data 157 , fifth sensor data 159 , or any combination thereof. In various non-limiting examples, one or more of the first component 182, the second component 184, or the third component 186 includes a stabilizer, a rudder, an elevator, an exhaust nozzle, a flight data recorder, a cockpit voice recorder, a pressure valve, a wing, an aileron, a tail, a lift control device, a flap, a slat, a spoiler, a propeller, a propulsion device, an engine, an intake valve, a fan, a compressor, a combustion chamber, a turbine, a landing gear, a nose landing gear, a main landing gear, a cockpit, a navigation device, an information device, a communication device, a hydraulic system, an electrical system, a pneumatic system, a light, a fuel outlet, an air duct, an accessory belt, a camshaft, a connecting rod, an actuator, a door, a window, a windshield, a gauge, an instrument, an ignition system, electrical wires, a brake, a brake pad, a brake disc, a distributor, a radiator, an oil filter, an oil gasket, or other vehicle components.

[0032] In a specific example, the first sensor data 151 indicates when the first component 182 transitions from a first state to a second state. For illustration, if the first component 182 is an actuator, the first sensor data 151 indicates when the actuator transitions from a closed state to an open state or from an open state to a closed state. The first sensor 150 detects that the first component 182 transitions from a first state at a first time to a second state at a second time. In a specific example, when the first component 182 is in a first state (e.g., a closed state), the third sensor 154 generates a third sensor data 155 having a first value (e.g., 0); when the first component 182 is in an intermediate state (e.g., a transition state), a third sensor data having a second value (e.g., 1) is generated; and when the first component 182 is in a second state (e.g., an open state), a third sensor data having a third value (e.g., 2) is generated. The first sensor 150 detects that the third sensor data 155 transitions from a first value (e.g., 0) to an intermediate value (e.g., 1) at a first time. The first sensor 150 detects that the third sensor data 155 transitions from the intermediate value (e.g., 1) to the second value (e.g., 2) at the second time. The first sensor 150 generates the first sensor data 151 indicating the measured transition time (e.g., the measured opening time) based on the difference between the first time and the second time in response to determining that the third sensor data 155 indicates that the first component 182 transitions from the first state to the second state. In a specific aspect, the first sensor data 151 indicates that the first time corresponds to the first state, the second time corresponds to the second state, the measured transition time corresponds to the difference between the first time and the second time, or any combination thereof.

[0033] In a specific non-limiting example, the second sensor 152 counts the operating cycles or state changes of the first component 182. In this example, the second sensor 152 detects that the third sensor data 155 changes from a first value (e.g., 0) to an intermediate value (e.g., 1) at a first time. The second sensor 152 detects that the third sensor data 155 changes from an intermediate value (e.g., 1) to a second value (e.g., 2) at a second time. In this example, the second sensor 152 increases the count based on detecting the change from the first value (e.g., 0) to the third value (e.g., 2). Optionally, the second sensor 152 may include one or more limit switches for counting the cycles or state changes of the first component 182.

[0034] In certain embodiments, the sensor data analyzer 120 stores the average conversion time in a first register (or another portion of the memory 132) and stores the conversion count in a second register (or another portion of the memory 132). In this embodiment, the sensor data analyzer 120 determines the average conversion time based on Formula 1:

[0035]

[0036] Among them, "Ave. Transition Time N+1 ” corresponds to the updated value of the average transition time, “Ave.TransitionTime N ” corresponds to the previous value of the average transition time, “Transition Count N ” corresponds to the previous value of the conversion count. As an example, in response to receiving the second sensor data 153, the sensor data analyzer 120 updates the average conversion time based on Formula 1 and updates (eg, increases by 1) the conversion count in the memory 132.

[0037] In a specific aspect, the sensor data analyzer 120 determines whether the first condition 171 is satisfied, for example, in response to receiving the first sensor data 151. For example, the sensor data analyzer 120 executes a first execution attribute of the first execution stack 161 to determine whether the sensor data 149 satisfies the first condition 171. For illustration, the sensor data analyzer 120 determines that the first condition 171 is satisfied in response to determining that the third sensor data 155 indicates that the first component 182 (e.g., an actuator) transitions from a first state (e.g., a closed state) to a second state (e.g., an open state). The sensor data analyzer 120 executes a second execution attribute of the first execution stack 161 in response to determining that the first condition 171 is satisfied to store (e.g., update) the first sensor data 151 (e.g., indicating a measured transition time or a measured open time) in the memory 132. Optionally, the sensor data analyzer 120 prohibits execution of the second execution attribute in response to determining that the first condition 171 is not satisfied. For example, the sensor data analyzer 120 prohibits storing (or updating) the first sensor data 151 in the memory 132 in response to determining that the first condition 171 is not satisfied.

[0038] In a specific aspect, the sensor data analyzer 120 determines whether the second condition 173 is satisfied, for example, in response to receiving the second sensor data 153. For example, the sensor data analyzer 120 executes a third execution attribute of the second execution stack 163 to determine whether the sensor data 149 satisfies the second condition 173. For illustration, the sensor data analyzer 120 determines that the second condition 173 is satisfied in response to determining that the third sensor data 155 indicates that the first component 182 (e.g., an actuator) transitions from a first state (e.g., a closed state) to a second state (e.g., an open state). The sensor data analyzer 120 executes a fourth execution attribute of the second execution stack 163 in response to determining that the second condition 173 is satisfied to store (e.g., update) the second sensor data 153 (e.g., indicating a measured transition time, a transition count, an average transition time, or any combination thereof) in the memory 132. Optionally, the sensor data analyzer 120 prohibits execution of the fourth execution attribute in response to determining that the second condition 173 is not satisfied. For example, the sensor data analyzer 120 prohibits storing (or updating) the second sensor data 153 in the memory 132 in response to determining that the second condition 173 is not satisfied. In a specific aspect, the first sensor 150 is the same as the second sensor 152. In another aspect, the first sensor 150 is different from the second sensor 152.

[0039] The sensor data analyzer 120 determines whether the adaptive performance metric adjustment criteria 135 are satisfied, for example, in response to determining that the sensor data 149 (the sensor data on which the adaptive performance metric adjustment criteria 135 depend) is stored (e.g., updated) in the memory 132. The sensor data analyzer 120 determines to update the sensor data 149 in the memory 132 in response to storing (e.g., updating) a value based on the first sensor data 151, the second sensor data 153, the third sensor data 155, the fourth sensor data 157, the fifth sensor data 159, or any combination thereof in the memory 132. In a specific example, the sensor data analyzer 120 executes the fifth execution attribute of the adaptive performance metric adjustment execution stack 165 to determine whether the sensor data 149 satisfies the adaptive performance metric adjustment criteria 135. For illustration, the second sensor data 153 indicates a first operating condition of the first component 182 (e.g., operating hours), a second operating condition of the first component 182 (e.g., average time to transition or average time to open an actuator), or both. The adaptive performance metric adjustment criteria 135 indicates a first operational threshold (eg, 100 hours), a second operational threshold (eg, an average time threshold), or both.

[0040] In an illustrative embodiment, the sensor data analyzer 120 determines the operating hours of the system 104 or one of the components 182-186 based on the fourth sensor data 157. In a specific aspect, the sensor data analyzer 120 receives the fourth sensor data 157 (e.g., a first timestamp) from the fourth sensor 156 (e.g., a clock). The sensor data analyzer 120 determines the operating hours based on the fourth sensor data 157, such as a difference between the first timestamp and a second timestamp, wherein the second timestamp indicates an installation time of one of the components 182-186 or the system 104. In another aspect, the fourth sensor 156 determines the fourth sensor data 157 based on the difference between the first timestamp and the second timestamp, and provides the fourth sensor data 157 to the sensor data analyzer 120 as the operating hours.

[0041] In a particular example, the adaptive performance metric 137 indicates a metric threshold (e.g., a predicted transition time or a predicted opening time). In this example, the sensor data analyzer 120 determines an average time threshold based on the metric threshold (e.g., average time threshold=0.95*metric threshold). As a specific example, the sensor data analyzer 120 may determine that the second sensor data 153 satisfies the adaptive performance metric adjustment criteria 135 in response to determining that the first operating condition (e.g., number of operating hours) is greater than a first operating threshold (e.g., 100 hours), the second operating condition (e.g., average time to transition the actuator or average time to open the actuator) is greater than a second operating threshold (e.g., average time threshold), or both.

[0042] In a specific aspect, the sensor data analyzer 120 determines whether the adaptive performance metric adjustment criteria 135 are satisfied based on sensor data from the plurality of sensors. For example, the sensor data analyzer 120 determines whether the second sensor data 153 and the fifth sensor data 159 satisfy the adaptive performance metric adjustment criteria 135. In a specific aspect, the sensor data analyzer 120 determines whether the adaptive performance metric adjustment criteria 135 are satisfied based at least in part on sensor data from a sensor associated with another component of the system 104 or another component of another system. For example, the fifth sensor 158 generates fifth sensor data 159 indicating an operating state of the second component 184, and the sensor data analyzer 120 determines whether the second sensor data 153 and the fifth sensor data 159 satisfy the adaptive performance metric adjustment criteria 135, wherein the adaptive performance metric 137 is associated with the first component 182.

[0043] The sensor data analyzer 120 determines (e.g., updates) the adaptive performance metric 137 in response to determining that the adaptive performance metric adjustment criteria 135 are met. For example, the sensor data analyzer 120 executes the sixth execution attribute of the adaptive performance metric adjustment execution stack 165 in response to determining that the adaptive performance metric adjustment criteria 135 are met to determine (e.g., update) the adaptive performance metric 137. In a specific aspect, the sensor data analyzer 120 determines (e.g., updates) the adaptive performance metric 137 to have a predetermined value (e.g., a constant value). In a more complex example, the sensor data analyzer 120 determines (e.g., updates) the adaptive performance metric 137 to have a variable value. The variable value can be calculated based on the sensor data 149. In a particular embodiment, the variable value can be retrieved from a lookup table or other data structure (e.g., a decision tree, an artificial neural network, or other learning model). In a more complex example, the sensor data analyzer 120 determines (e.g., updates) the adaptive performance metric 137 to indicate that the sensor data 149 (or a portion thereof) is to be compared with one or more different thresholds (e.g., a set of constant values, a set of variable values, or any combination thereof).

[0044] In a particular example, the adaptive performance metric 137 indicates a metric threshold (e.g., an expected transition time or an expected turn-on time), a failure factor (e.g., a tolerance factor, such as 1 ms), or both. In this example, the sensor data analyzer 120 updates the metric threshold, the failure factor, or both in response to determining that the adaptive performance metric adjustment criteria 135 are met. As a specific non-limiting example, the metric threshold is the expected turn-on time, and the sensor data analyzer 120 updates the metric threshold based on the average transition time (e.g., the updated value of the expected turn-on time = 0.5 * (previous value of the expected turn-on time + average transition time)). In this particular example, the sensor data analyzer 120 updates the failure factor based on the transition count (e.g., failure factor = 1 + (transition count / 1000)). Optionally, the sensor data analyzer 120 prohibits execution of the sixth execution attribute of the adaptive performance metric adjustment execution stack 165 in response to determining that the sensor data 149 does not meet the adaptive performance metric adjustment criteria 135. For example, sensor data analyzer 120 determines not to update adaptive performance metric 137 , and refrains from updating adaptive performance metric 137 , in response to determining that sensor data 149 does not satisfy adaptive performance metric adjustment criteria 135 .

[0045] For example, after updating the adaptive performance metric 137 or after determining not to update the adaptive performance metric 137, the sensor data analyzer 120 determines whether the sensor data 149 satisfies the adaptive performance metric 137. For example, the sensor data analyzer 120 executes the seventh execution attribute of the adaptive performance metric execution stack 167 to determine whether the adaptive performance metric 137 is satisfied. For illustration, in response to determining that the first sensor data 151 satisfies (e.g., one of less than, less than or equal to, greater than, greater than or equal to) the adaptive performance metric 137, the sensor data analyzer 120 determines that the sensor data 149 satisfies the adaptive performance metric 137.

[0046] In a particular example, the sensor data analyzer 120 generates a maintenance alert 139 in response to determining that the sensor data 149 does not satisfy the adaptive performance metric 137. For example, the sensor data analyzer 120 executes the eighth execution attribute of the adaptive performance metric execution stack 167 to generate the maintenance alert 139 in response to determining that the sensor data 149 does not satisfy the adaptive performance metric 137. The maintenance alert 139 indicates a request to perform a maintenance action associated with one or more of the sensor 160, the system 104, the first component 182, or any combination thereof. In a specific aspect, the sensor data analyzer 120 generates a graphical user interface GUI 141 indicating the maintenance alert 139 and provides the graphical user interface 141 to the display 110. The sensor data analyzer 120 stores the graphical user interface 141, the maintenance alert 139, or both in the memory 132. In a specific aspect, the sensor data analyzer 120 provides (e.g., sends) the maintenance alert 139 to a maintenance server, a communication device, a vehicle fleet management device, or any combination thereof. A maintenance technician (e.g., user 101) can perform maintenance on vehicle 102 based on graphical user interface 141, maintenance alert 139, or both. Optionally, sensor data analyzer 120 prohibits generating maintenance alert 139 in response to determining that sensor data 149 satisfies adaptive performance metric 137. For example, sensor data analyzer 120 prohibits performing an eighth performance attribute in response to determining that sensor data 149 satisfies adaptive performance metric 137.

[0047] Thus, the system 100 is able to adjust the adaptive performance metric 137 based on conditions detected at the vehicle 102. The adaptive performance metric 137 evolves to take into account the various conditions experienced by the vehicle 102, which may be different from another set of conditions experienced by another vehicle. For example, under a first set of conditions (e.g., a newer actuator), if the measured time for the first component 182 to transition from the first state to the second state (e.g., the measured opening time) does not meet the initial value of the adaptive performance metric, then a maintenance alert 139 is generated. Under a second set of conditions (e.g., an older actuator), the sensor data analyzer 120 updates the adaptive performance metric 137, and if the measured transition time does not meet the updated value of the adaptive performance metric 137, then a maintenance alert 139 is generated.

[0048] Figure 2 2 is a flow chart of a method 200 for performing abnormal vehicle behavior detection. The method 200 may be Figure 1 The method may be performed by the sensor data analyzer 120, the vehicle 102, the system 100, or any combination thereof.

[0049] The method 200 includes, at 202, receiving, at a device, first sensor data from a first sensor indicating an operating state of a first system (of a first system type). Figure 1 As described, Figure 1 The sensor data analyzer 120 receives first sensor data 151 from the first sensor 150. The first sensor data 151 indicates Figure 1 For illustration, in a non-limiting example, the first sensor data 151 indicates a measured time for a transition from a first state of the first component 182 to a second state of the first component 182, as shown in FIG. Figure 1 described.

[0050] The method 200 also includes, at 204, receiving, at the device, second sensor data associated with the adaptive performance metric adjustment criteria from a second sensor. Figure 1 As described, Figure 1 The sensor data analyzer 120 receives the second sensor data 153 from the second sensor 152 . The second sensor data 153 is associated with the adaptive performance metric adjustment criteria 135 .

[0051] The method 200 also includes determining at the device whether the second sensor data satisfies the adaptive performance metric adjustment criteria at 206. Figure 1 As described, Figure 1The sensor data analyzer 120 determines whether the second sensor data 153 satisfies the adaptive performance metric adjustment criteria 135. For illustration, the sensor data analyzer 120 executes the fifth execution attribute of the adaptive performance metric adjustment execution stack 165 to determine whether the second sensor data 153 satisfies the adaptive performance metric adjustment criteria 135, as shown in FIG. Figure 1 described.

[0052] The method 200 also includes, at 208, determining an adaptive performance metric based on the second sensor data based on determining that the second sensor data satisfies the adaptive performance metric adjustment criteria. Figure 1 As described, Figure 1 The sensor data analyzer 120 determines (e.g., updates) the adaptive performance metric 137 based on the second sensor data 153 based on the determination that the second sensor data 153 satisfies the adaptive performance metric adjustment criteria 135. For illustration, the sensor data analyzer 120 executes the sixth execution attribute of the adaptive performance metric adjustment execution stack 165 in response to determining that the second sensor data 153 satisfies the adaptive performance metric adjustment criteria 135 to determine (e.g., update) the adaptive performance metric 137, as shown in reference Figure 1 described.

[0053] The method 200 also includes, at 210, comparing the first sensor data and the adaptive performance metric at the device to identify abnormal behavior of the first system. For example, Figure 1 The sensor data analyzer 120 compares the first sensor data 151 to the adaptive performance metric 137 to identify abnormal behavior of the system 104. For illustration, the sensor data analyzer 120 determines that abnormal behavior is detected at at least one of the sensor 160, the first component 182, or the system 104 in response to determining that the first sensor data 151 does not satisfy the adaptive performance metric 137. In a specific aspect, the sensor data analyzer 120 executes the seventh execution attribute of the adaptive performance metric execution stack 167 to determine whether the first sensor data 151 satisfies the adaptive performance metric 137, as shown in FIG. Figure 1 The sensor data analyzer 120 determines that abnormal behavior is detected at at least one of the sensor 160 , the first component 182 , or the system 104 , in response to determining that the first sensor data 151 does not satisfy the adaptive performance metric 137 .

[0054] The method 200 also includes, at 212, generating a maintenance alert at the device based on determining that the first sensor data does not satisfy the adaptive performance metric. Figure 1 As described, Figure 1The sensor data analyzer 120 generates the maintenance alert 139 based on determining that the first sensor data 151 does not satisfy the adaptive performance metric 137. For illustration, the sensor data analyzer 120 executes the eighth execution attribute of the adaptive performance metric execution stack 167 to generate the maintenance alert 139 based on determining that the first sensor data 151 does not satisfy the adaptive performance metric 137, as shown in FIG. Figure 1 described.

[0055] Thus, the method 200 can determine an adaptive performance metric based on sensor data indicative of a detected condition. A maintenance alert is generated based on the adaptive performance metric.

[0056] Aspects of the present disclosure may be found in Figure 3 300 is described in the context of an aircraft 300 as shown. Aircraft 300 includes fuselage 318 and interior 322 with multiple systems 320 (e.g., high-level systems). Examples of systems 320 include propulsion system 324, electrical system 326, environmental system 328, hydraulic system 330, sensor data analyzer 120, one or more of system 104, or sensor 160. Other systems may also be included. Although system 104 is shown as a separate system, in other embodiments, system 104 includes one or more of systems 324-330 or is included in one or more of systems 324-330.

[0057] The sensor data analyzer 120 is configured to support aspects of the computer-implemented methods and computer-executable program instructions (or codes) according to the present disclosure. For example, the sensor data analyzer 120 or a portion thereof is configured to execute instructions to initiate, execute, or control a reference Figure 1-Figure 3 One or more operations described. Although an aerospace example is shown, the present disclosure may be applied to other industries. For example, the system 104, sensor 160, and sensor data analyzer 120 may be used on a manned or unmanned vehicle (e.g., a satellite, a ship, or a land-based vehicle), in a building, or other structure.

[0058] although Figure 1-Figure 3 One or more of the illustrated systems, devices and / or methods according to the teachings of the present disclosure are illustrated, but the present disclosure is not limited to the illustrated systems, devices and / or methods. Figure 1-Figure 3 One or more functions or components of any of the Figure 1-3 One or more other parts of another. For example, Figure 2 One or more elements of method 200 may be performed in combination with other operations described herein. Accordingly, any single implementation described herein should not be interpreted as limiting, and the implementations of the present disclosure may be appropriately combined without departing from the teachings of the present disclosure. As an example, refer to Figure 1-Figure 2 One or more of the operations described may be optional, may be performed at least partially concurrently, and / or may be performed in an order different from that shown or described.

[0059] The above examples are illustrative and do not limit the present disclosure. It should be understood that many modifications and variations are possible according to the principles of the present disclosure.

[0060] Furthermore, the present disclosure includes embodiments according to the following items:

[0061] Item 1. A means of transport, comprising:

[0062] The first system of the first system type;

[0063] a first sensor configured to generate first sensor data indicative of an operating state of a first system;

[0064] a second sensor configured to generate second sensor data associated with the adaptive performance metric adjustment criteria;

[0065] a memory configured to store the first sensor data and the second sensor data during one or more operations of the vehicle; and

[0066] The processor is configured as:

[0067] determining whether the second sensor data satisfies an adaptive performance metric adjustment criterion;

[0068] In response to determining that the second sensor data satisfies the adaptive performance metric adjustment criteria, determining an adaptive performance metric to be compared to the first sensor data based on the second sensor data to identify abnormal behavior of the first system;

[0069] comparing the first sensor data to the adaptive performance metric; and

[0070] In response to determining that the first sensor data does not satisfy the adaptive performance metric, a maintenance alert is generated.

[0071] Item 2. The vehicle of Item 1, wherein the memory is further configured to store a first execution stack indicative of a first condition, and wherein the processor is further configured to store the first sensor data in the memory in response to determining that the first condition is satisfied.

[0072] Item 3. A vehicle according to any one of Items 1-2, wherein the memory is further configured to store a second execution stack indicating a second condition, and wherein the processor is further configured to store second sensor data in the memory in response to determining that the second condition is satisfied.

[0073] Item 4. A vehicle according to any one of Items 1-3, wherein the memory is further configured to store an adaptive performance metric adjustment execution stack indicating an adaptive performance metric adjustment criterion.

[0074] Item 5. The vehicle of any one of Items 1-4, further comprising a third sensor configured to generate third sensor data, wherein the processor is configured to update the adaptive performance metric further based on determining whether the third sensor data satisfies an adaptive performance metric adjustment criterion.

[0075] Item 6. A vehicle according to any one of items 1-5, wherein the processor is configured to determine whether the second sensor data satisfies the adaptive performance metric in response to detecting that the second sensor data is stored to the memory.

[0076] Item 7. A vehicle as described in any of Items 1-6, wherein the adaptive performance metric is based on the operation of a plurality of systems of the first system type, the plurality of systems being included in the vehicle fleet.

[0077] Item 8. A vehicle according to any of Items 1-7, wherein the first system includes an actuator, wherein the first sensor data indicates a measured time to open the actuator, wherein the adaptive performance metric indicates an expected time to open the actuator, and wherein the second sensor data indicates a transition count of the actuator from a closed state to an open state.

[0078] Item 9. A vehicle according to any one of Items 1-8, wherein the first system, the first sensor, the second sensor, the memory and the processor are integrated into at least one of an aircraft, a ship, a train or a truck.

[0079] Clause 10. The vehicle of any one of clauses 1-9, wherein the maintenance alert indicates a request to perform a maintenance action associated with the first sensor, the second sensor, the first system, or any combination thereof.

[0080] Item 11. A method comprising:

[0081] receiving, at the device, first sensor data from a first sensor indicating an operational state of a first system, the first system being of a first system type;

[0082] receiving, at the device, second sensor data associated with the adaptive performance metric adjustment criteria from a second sensor;

[0083] determining, at the device, whether the second sensor data satisfies an adaptive performance metric adjustment criterion;

[0084] determining an adaptive performance metric based on the second sensor data based on determining that the second sensor data satisfies an adaptive performance metric adjustment criterion;

[0085] comparing the first sensor data and the adaptive performance metric at the device to identify abnormal behavior of the first system; and

[0086] Based on determining that the first sensor data does not satisfy the adaptive performance metric, a maintenance alert is generated at the device.

[0087] Item 12. The method of Item 11 further includes storing the first sensor data in a memory based on determining that the first condition is satisfied.

[0088] Item 13. The method of Item 12, wherein a first execution stack stored in the memory indicates a first condition.

[0089] Item 14. The method of any one of Items 11-13 further includes storing second sensor data in a memory based on determining that a second condition is satisfied, wherein a second execution stack stored in the memory indicates the second condition.

[0090] Item 15. The method according to any one of Items 11-14 further includes receiving multiple sensor data from multiple sensors, the multiple sensors including a second sensor, wherein in response to determining that the multiple sensor data meets the adaptive performance metric adjustment criteria, the adaptive performance metric is based on the multiple sensor data.

[0091] Item 16. A computer-readable storage device storing instructions that, when executed by a processor, cause the processor to perform operations comprising:

[0092] receiving first sensor data indicative of an operating state of a first system from a first sensor, the first system being of a first system type;

[0093] receiving second sensor data associated with the adaptive performance metric adjustment criteria from a second sensor;

[0094] determining whether the second sensor data satisfies an adaptive performance metric adjustment criterion;

[0095] selectively determining an adaptive performance metric based on the second sensor data based on determining that the second sensor data satisfies an adaptive performance metric adjustment criterion;

[0096] comparing the first sensor data and the adaptive performance metric to identify abnormal behavior of the first system; and

[0097] Based on determining that the first sensor data does not satisfy the adaptive performance metric, a maintenance alert is generated.

[0098] Item 17. A computer-readable storage device according to Item 16, wherein the first system includes an actuator, wherein the first sensor data indicates a measured time to open the actuator, wherein the adaptive performance metric indicates an expected time to open the actuator, and wherein the second sensor data indicates a transition count of the actuator from a closed state to an open state and an average time to open the actuator.

[0099] Item 18. A computer-readable storage device according to Item 17, wherein the operation also includes determining that the second sensor data meets the adaptive performance metric adjustment criteria based at least in part on determining that the average time is greater than a time threshold, and determining the time threshold based on an expected time to open the actuator.

[0100] Item 19. A computer-readable storage device as described in any of Items 17-18, wherein the operations further include, in response to determining that the second sensor data does not meet the adaptive performance metric adjustment criteria, determining the adaptive performance metric based on the expected time to open the actuator.

[0101] Item 20. A computer-readable storage device according to any one of items 17-19, wherein the operation also includes, in response to determining that the second sensor data meets the adaptive performance metric adjustment criteria, determining an adaptive performance metric based on a transition count, an average time, an expected time to open the actuator, or any combination thereof.

[0102] The description of the examples described herein is intended to provide a general understanding of the structures of various implementations. These descriptions are not intended to be a complete description of all elements and features of the devices and systems utilizing the structures or methods described herein. After reading this disclosure, many other embodiments may be apparent to those skilled in the art. Other embodiments may be derived from this disclosure, so structural and logical replacements and variations may be realized without departing from the scope of protection of the present disclosure. For example, method operations may be performed in an order different from that shown in the accompanying drawings, or one or more method operations may be omitted. Therefore, this disclosure and the accompanying drawings should be considered illustrative, rather than restrictive.

[0103] In addition, although specific examples have been shown and described herein, it should be understood that any subsequent arrangement designed to achieve the same or similar results may replace the specific embodiments shown. This disclosure is intended to cover any and all subsequent variations or changes of various embodiments. Combinations of the above embodiments and other embodiments not specifically described herein will be apparent to those skilled in the art after reading the specification.

[0104] It should be understood that the abstract of the present disclosure submitted will not be used to interpret or limit the scope or meaning of the claims. In addition, in the foregoing detailed description, in order to simplify the present disclosure, various features may be combined together or described in a single embodiment. The above examples are illustrative and do not limit the present disclosure. It should be understood that many modifications and variations are possible according to the principles of the present disclosure. As reflected in the following claims, the subject matter claimed for protection may be directed to less than all the features of any disclosed example. Therefore, the scope of the present disclosure is defined by the following claims and their equivalents.

Claims

1. A means of transport (102, 300), comprising: a first system (104) of a first system type; a first sensor (150) configured to generate first sensor data (151) indicative of an operating state of the first system (104); a second sensor (152) configured to generate second sensor data (153) associated with the adaptive performance metric adjustment criteria (135); a memory (132) configured to store the first sensor data (151) and the second sensor data (153) during one or more operations of the vehicle (102, 300); as well as The processor (120) is configured to: determining whether the second sensor data (153) satisfies the adaptive performance metric adjustment criteria (135); In response to determining that the second sensor data (153) satisfies the adaptive performance metric adjustment criteria (135), determining an adaptive performance metric (137) to be compared with the first sensor data (151) based on the second sensor data (153) to identify abnormal behavior of the first system (104); comparing the first sensor data (151) to the adaptive performance metric (137); as well as In response to determining that the first sensor data (151) does not satisfy the adaptive performance metric (137), a maintenance alert (139) is generated.

2. The vehicle (102, 300) according to claim 1, wherein: The memory (132) is further configured to store a first execution stack (161) indicating a first condition (171), and wherein the processor (120) is further configured to store the first sensor data (151) in the memory (132) in response to determining that the first condition (171) is satisfied.

3. The vehicle (102, 300) according to any one of claims 1-2, wherein: The memory (132) is further configured to store a second execution stack (163) indicating a second condition (173), and wherein the processor (120) is further configured to store the second sensor data (153) in the memory (132) in response to determining that the second condition (173) is satisfied.

4. The vehicle (102, 300) according to any one of claims 1-2, wherein: The memory (132) is also configured to store an adaptive performance metric adjustment execution stack (165) indicating the adaptive performance metric adjustment criteria (135).

5. The vehicle (102, 300) according to any one of claims 1-2, further comprising a third sensor (154) configured to generate third sensor data (155), wherein: The processor (120) is configured to update the adaptive performance metric (137) based further on determining whether the third sensor data (155) satisfies the adaptive performance metric adjustment criteria (135).

6. The vehicle (102, 300) according to any one of claims 1-2, wherein: The processor (120) is configured to determine whether the second sensor data (153) satisfies the adaptive performance metric (137) in response to detecting that the second sensor data (153) is stored in the memory (132).

7. The vehicle (102, 300) according to any one of claims 1-2, wherein: The adaptive performance metric (137) is based on the operation of a plurality of systems of the first system type, including the plurality of systems in a fleet of vehicles.

8. The vehicle (102, 300) according to any one of claims 1-2, wherein: The first system (104) includes an actuator, wherein the first sensor data (151) indicates a measured time to open the actuator, wherein the adaptive performance metric (137) indicates an expected time to open the actuator, and wherein the second sensor data (153) indicates a transition count of the actuator from a closed state to an open state.

9. The vehicle (102, 300) according to any one of claims 1-2, wherein: The first system (104), the first sensor (150), the second sensor (152), the memory (132), and the processor (120) are integrated into at least one of an airplane, a ship, a train, and a truck.

10. The vehicle (102, 300) according to any one of claims 1-2, wherein: The maintenance alert (139) indicates a request to perform a maintenance action associated with the first sensor (150), the second sensor (152), the first system (104), or any combination thereof.

11. A method for detecting abnormal behavior of a vehicle, comprising: receiving, at a device (120), first sensor data (151) indicative of an operational state of a first system (104) from a first sensor (150), the first system (104) being of a first system type; receiving, at the device (120), from a second sensor (152), second sensor data (153) associated with an adaptive performance metric adjustment criterion (135); determining, at the device (120), whether the second sensor data (153) satisfies the adaptive performance metric adjustment criteria (135); Based on determining that the second sensor data (153) satisfies the adaptive performance metric adjustment criteria (135), determining an adaptive performance metric (137) based on the second sensor data (153); comparing, at the device (120), the first sensor data (151) to the adaptive performance metric (137) to identify abnormal behavior of the first system (104); as well as Based on determining that the first sensor data (151) does not satisfy the adaptive performance metric (137), a maintenance alert (139) is generated at the device (120).

12. The method of claim 11, further comprising storing the first sensor data (151) in a memory (132) based on determining that a first condition (171) is satisfied.

13. The method according to claim 12, wherein: A first execution stack (161) stored in the memory (132) indicates the first condition (171).

14. The method according to any one of claims 11-12, further comprising storing the second sensor data (153) in a memory (132) based on determining that a second condition (173) is satisfied, wherein: A second execution stack (163) stored in the memory (132) indicates the second condition (173).

15. The method according to any one of claims 11-12, further comprising receiving a plurality of sensor data (149, 151, 153, 155, 157, 159) from a plurality of sensors (150, 152, 154, 156, 158, 160), the plurality of sensors (150, 152, 154, 156, 158, 160) including the second sensor (152), wherein In response to determining that the plurality of sensor data (149, 151, 153, 155, 157, 159) satisfies the adaptive performance metric adjustment criteria (135), the adaptive performance metric (137) is based on the plurality of sensor data (149, 151, 153, 155, 157, 159).

Images