System and method for detecting pressure loss rate and related events in automobile tires

Abstract

Disclosed herein are systems and methods for tire condition monitoring, and more specifically for detecting slow leaks of inflation pressure. A data acquisition device (e.g., a tire pressure monitoring system sensor) is mounted on a vehicle and collects data samples corresponding to at least tire inflation pressure. The collected data samples can be transmitted for analysis, for example, only while the vehicle is in a fleet yard or otherwise has an effectively matched ambient temperature. An elapsed time is calculated from a first data sample within a defined sampling period, and a statistical model is applied to the data samples corresponding to at least the inflation pressure versus the elapsed time. A tire slow leak event is identified based on an estimated decrease in inflation pressure from the statistical model, and an output signal is selectively generated in response to the identified slow leak event.

Description

[Technical field]

[0001] The present disclosure relates generally to quantifying performance aspects of tires of wheeled motor vehicles. More specifically, the systems, methods, and associated algorithms disclosed herein relate to detecting tire pressure events, such as slow leaks, in tires of wheeled motor vehicles, including but not limited to motorcycles, consumer vehicles (e.g., cars and light trucks), commercial vehicles, and off-road (OTR) vehicles. [Background technology]

[0002] Undetected internal air pressure leaks are critical to optimal performance of any tire on the market, and this is true for individual automobile owners, but even more so for owners and operators of heavy equipment and transportation vehicles who are understandably concerned about losing air in their tires for safety, performance, and environmental reasons.

[0003] Air leaks can pose a variety of challenges for businesses operating on tight schedules. Many of these issues can range from downtime, potential delivery delays, and even serious damage to expensive equipment. There are many conventional solutions on the market, including various vehicle monitoring systems that include the ability to notify users of operational information such as vehicle speed, vehicle load, vehicle longitude and latitude coordinates, etc. However, conventional solutions fail to specifically and accurately address the problem of air pressure leaks from each wheel position of a vehicle.

[0004] For example, it is conventionally known to monitor the operating pressure history of tires obtained by a Tire Pressure Monitoring System (TPMS), and further calculate the amount of internal pressure loss of each tire by comparative analysis between each of the tires installed on the same vehicle to detect slow leaks. In general, the internal air pressure and the contained air temperature can be considered to be in a proportional relationship, and therefore the change in the internal air pressure can be considered to depend on the change in the external (ambient) temperature and the vehicle temperature. By applying the known relationship between the pressure, temperature, and volume of the object, a "corrected" internal pressure value due to temperature variations can be ascertained.

[0005] However, tire temperature during operation depends at least in part on the relevant operating conditions. Tire temperature measurements from TPMS sensors during normal operation may vary, for example, from close to the temperature of the ambient air up to about 70° C. depending on the operating and / or environmental conditions. Temperature-compensated internal pressure can still be derived, but it usually takes into account a larger variability in the measurement error. Summary of the Invention [Problem to be solved by the invention]

[0006] When the variability of the internal pressure measurements is relatively large, it is difficult to properly evaluate the amount of decrease over time, and therefore there is a possibility that false positives or negatives of slow leaks will occur frequently.

[0007] In view of the aforementioned deficiencies in conventional systems, the machine learning techniques disclosed herein may be implemented to accurately detect slow tire leaks, for example, in-yard monitoring units.

[0008] Generally speaking, various embodiments of the slow leak detection systems and methods disclosed herein can implement detected operating and / or environmental conditions associated with a vehicle, including, for example, an internal air pressure measurement and a contained air temperature (CAT) measurement associated with a given tire. The response can preferably be measured directly using a data acquisition system, such as, for example, a tire pressure monitoring system (TPMS) mounted in, on, or otherwise associated with the tire. The data acquisition system can preferably transmit data or have associated data otherwise collected therefrom while the vehicle is parked at the fleet yard, where variability in the internal pressure measurements is reduced.

[0009] A random forest machine learning methodology may be preferably implemented in the embodiments disclosed herein to achieve detection of slow leaks, and more particularly to correlate slow leaks that occur while each automobile is found within a monitored fleet yard environment, such that the methods disclosed herein can easily alert a user to a possible slow leak occurring in a vehicle and can intervene to align the vehicle's tires to specifications to provide optimal performance.

[0010] An exemplary embodiment of a tire monitoring method disclosed herein includes collecting data samples corresponding to at least an inflation pressure of at least one of the plurality of tires via at least one data acquisition device mounted on a vehicle having a plurality of tires. An elapsed time may be calculated from a first data sample within a defined sampling period, and a statistical model may be applied to the data sample corresponding to at least the inflation pressure versus the elapsed time. A slow leak event may be identified based on an estimated decrease in the inflation pressure from the statistical model, and an output signal may be selectively generated in response to the identified slow leak event of at least one of the plurality of tires.

[0011] In one exemplary aspect according to the embodiment referenced above, the statistical model may require at least a first threshold of data samples within a defined sampling period, and the elapsed time from the first data sample must exceed a second threshold.

[0012] In another exemplary aspect according to the above-referenced embodiment, data samples are collected for the statistical model only if the vehicle's speed is determined to be zero for a third threshold of time.

[0013] In another exemplary aspect according to the above-referenced embodiments, data samples are collected only while the data acquisition device is within range of one or more data collection units of the fleetyard monitoring system.

[0014] The above-referenced embodiments may further include collecting, via at least one data acquisition device mounted on a vehicle having a plurality of tires, a contained air temperature associated with a data sample corresponding to at least an inflation pressure of at least one of the plurality of tires. For example, a temperature-compensated inflation pressure value may be generated for each of the data samples, where a statistical model implements the temperature-compensated inflation pressure value to confirm a slow leak event. In another example, it may be determined whether to selectively generate an output signal corresponding to a confirmed slow leak event based at least in part on the associated contained air temperature. In another example, it may be determined whether to selectively generate an output signal corresponding to a confirmed slow leak event based on a time rate of change of the associated contained air temperature relative to a threshold value.

[0015] In another exemplary aspect according to the above referenced embodiment, the slow leak event may be further confirmed for a second defined sampling period by considering the median value of a metric corresponding to the estimated decrease in inflation pressure.

[0016] In another exemplary aspect according to the above-referenced embodiment, the statistical model may include a linear regression model having a target variable including the inflation pressure and a descriptive variable including the elapsed time. Additionally or alternatively, the statistical model may include a random forest model.

[0017] In another embodiment disclosed herein, a tire monitoring system includes at least one data acquisition device mounted on a vehicle having a plurality of tires and configured to collect data samples corresponding to at least an inflation pressure of at least one of the plurality of tires, and at least one data collection unit configured to receive the collected data samples from the on-board data acquisition device, for example, when the vehicle is in a yard and not operating on a road. A processing unit is linked to the at least one data collection unit and configured to direct the execution of operations according to one or more of the above-referenced method embodiments and optionally the above-mentioned related exemplary aspects.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present invention belongs. The invention disclosed herein may be embodied in other specific forms without departing from its spirit or essential characteristics, and therefore, it is desired that the various embodiments be considered in all respects as illustrative and not restrictive. The headings used herein are for convenience only and have no legal or restrictive effect. Many objects, features, and advantages of the embodiments described herein will be readily apparent to those skilled in the art upon reading the following disclosure in conjunction with the accompanying drawings. [Brief description of the drawings]

[0019] Hereinafter, embodiments of the present invention will be illustrated in more detail with reference to the drawings.

[0020] [Figure 1] FIG. 1 is a block diagram illustrating one embodiment of a tire monitoring system disclosed herein. [Figure 2A] FIG. 2a is a graphical representation illustrating the presence of normal and slow leak conditions, respectively, based on collected time series data. [Figure 2B] FIG. 2b is a graphical representation illustrating the presence of normal and slow leak conditions, respectively, based on the collected time series data. [Diagram 3] FIG. 3 is a graphical diagram depicting exemplary pattern recognition steps according to one embodiment of the systems / methods disclosed herein. [Figure 4] FIG. 4 is a graphical diagram depicting exemplary pattern recognition steps according to one embodiment of the systems / methods disclosed herein. [Diagram 5] FIG. 5 is a graphical diagram depicting exemplary pattern recognition steps according to one embodiment of the systems / methods disclosed herein. [Figure 6] FIG. 6 is a graphical diagram illustrating exemplary pattern recognition steps according to one embodiment of the systems / methods disclosed herein. [Figure 7] FIG. 7 is a graphical diagram depicting exemplary pattern recognition steps according to one embodiment of the systems / methods disclosed herein. [Figure 8] FIG. 8 is a graph illustrating an exemplary slope line for a best fit of the internal air pressure measurements over time. [Figure 9] FIG. 9 is a graphical diagram illustrating an example defined sampling period according to the present disclosure. [Figure 10] FIG. 10 is a graphical diagram illustrating an exemplary defined sampling period according to the present disclosure. [Figure 11A] FIG. 11a is a graphical diagram illustrating exemplary time series data associated with true positive event detection, false negative event detection, false positive event detection, and true negative event detection, respectively. [Figure 11B] FIG. 11b is a graphical diagram illustrating exemplary time series data associated with true positive event detection, false negative event detection, false positive event detection, and true negative event detection, respectively. [Figure 11C]FIG. 11c is a graphical diagram illustrating exemplary time series data associated with true positive event detection, false negative event detection, false positive event detection, and true negative event detection, respectively. [Figure 11D] FIG. 11d is a graph diagram illustrating exemplary time series data associated with true positive event detection, false negative event detection, false positive event detection, and true negative event detection, respectively. [Figure 12] FIG. 12 is a flow chart illustrating one embodiment of a tire monitoring method disclosed herein. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0021] Various exemplary embodiments of the present invention may now be described in detail, generally with reference to Figures 1-12. Where various figures may illustrate embodiments that share various common elements and features with other embodiments, similar elements and features may be given the same reference numerals and duplicate descriptions thereof may be omitted below.

[0022] Referring initially to FIG. 1, an exemplary embodiment of the system 100 includes a data acquisition device 110 mounted on a vehicle and configured to acquire at least data and transmit said data to one or more downstream computing devices (e.g., a remote server) for performing associated calculations as disclosed herein. The data acquisition device may be a standalone sensor unit suitably configured to collect raw measurement signals, such as signals corresponding to tire internal air temperature 112 and / or internal air pressure 114, and transmit such signals continuously or selectively. The data acquisition device may include an on-board computing device in communication with one or more distributed sensors, which may be portable or modular as part of a distributed vehicle data collection and control system, or may be provided integrally to a central vehicle data collection and control system. The data acquisition device may include a processor and memory (not shown) on which program logic resides, and in various embodiments may include a vehicle electronic control unit (ECU) or components thereof, or may otherwise be, for example, permanent, discrete in nature, or removably mounted to a vehicle mount.

[0023] Generally speaking, the system 100 disclosed herein may implement a number of components distributed across one or more vehicles, for example, a central server network or an event-driven serverless platform not necessarily associated with a fleet management entity, but further functionally communicating with each of the vehicle motors via a communication network. Exemplary vehicle components may typically include one or more sensors, for example, position sensors such as body accelerometers, gyroscopes, inertial measurement units (IMUs), global positioning system (GPS) transponders, tire pressure monitoring system (TPMS) sensor transmitters and associated on-board receivers, gateway devices, etc., linked, for example, to a controller area network (CAN) bus network, thereby providing signals to a local processing unit. The illustrated embodiment may include, for illustrative purposes, a tire-mounted TPMS sensor unit, an ambient temperature sensor, a vehicle speed sensor configured to collect acceleration data associated with the vehicle, for example, and a DC power source, without specifically limiting the scope of the invention.

[0024] One or more of the sensors disclosed herein may be integrated or otherwise collectively arranged within a given modular structure, rather than being individually and distributed within the structure. For example, a tire-mounted TPMS sensor as referred to herein may be configured to generate an output signal corresponding to each of a number of tire-specific conditions (e.g., inflation pressure, contained air temperature). The TPMS sensor may be mounted, for example, within the tire's air cavity, slightly elevated, and isolated from the metal rim so as not to be adversely affected by the metal rim.

[0025] Various bus interfaces, protocols, and associated networks are well known in the art for communication between respective data sources and local computing devices, and those skilled in the art will recognize the wide range of such tools and means for implementing the same.

[0026] In various embodiments, the data acquisition devices and equivalent data sources 110 disclosed herein are not necessarily limited to vehicle-specific sensors and / or gateway devices, but may also include third party entities and associated networks, program applications resident on user computing devices such as driver interfaces, fleet management interfaces, and any enterprise devices or other providers of raw streams of log data as may be deemed appropriate for the algorithms and models disclosed herein.

[0027] 1, a data pipeline stage 120 may be provided in which data collected from one or more data sources 110 is sent to a data processing stage 130. The data processing stage 130 further interacts with a data storage stage 140, including, for example, one or more database services, where the data processing stage 130 and / or the data storage stage 140 selectively interact with external devices 150 and / or users of a network, for example via respective Application Program Interface (API) requests.

[0028] In one embodiment, the exemplary data pipeline stage 120 may include an event-driven serverless architecture, where one or more event hubs are configured to facilitate the capture of raw data from respective sources, generate normalized data streams therefrom, and further copy the ingested events to a data storage resource at time intervals appropriate for the relevant data. The normalized and enriched data streams may be further submitted for analytical processing, for example, via a data lake platform as known in the art. Non-limiting examples of data lakes known in the art may include Azure Data Lake®, Kafka®, Hadoop®, etc.

[0029] 1 is not intended to limit the scope of the systems or methods disclosed herein, and in alternative embodiments, one or more pressure loss rate models may be implemented locally on an on-board computing device (e.g., an electronic control unit) rather than at a downstream computer stage. For example, models may be generated and trained over time at a server level and downloaded to an on-board computing device for local execution of one or more steps or operations disclosed herein.

[0030] In other alternative embodiments, one or more of the various sensors 112, 114 may be configured to communicate with the downstream platform without a local on-board device or gateway component, for example, via a cellular communications network or via a mobile computing device (not shown) carried by a user of the vehicle.

[0031] The term "user interface" as used herein, unless otherwise specified, may include any input / output module that facilitates user interaction with a user device with a processing unit, server, device, etc. disclosed herein, including, but not limited to, downloaded or otherwise resident program applications, web browsers, web portals such as individual web pages or web pages collectively defining a hosted website, etc. The user interface, with respect to a personal mobile computing device, may further be described in the context of buttons and display portions, which may be independently located or otherwise associated with one another, for example, with a touch screen, and may further include voice and / or visual input / output capabilities without explicit user interaction capabilities.

[0032] The vehicle and tire sensors 112, 114, etc. may further be provided with unique identifiers in one embodiment, whereby the on-board device processor may distinguish between signals provided from respective sensors on the same vehicle, and in further particular embodiments, the central processing unit and / or fleet maintenance oversight client device may distinguish between signals provided from tires and associated vehicles and / or tire sensors across multiple vehicles. In other words, the sensor output values ​​may be associated with a particular tire, a particular vehicle, and / or a particular tire-vehicle system for purposes of on-board or remote / downstream data storage and implementation for calculations as disclosed herein, in various embodiments. The on-board data acquisition device may directly communicate with the downstream processing stage 130 as shown in FIG. 1, or alternatively, the driver's mobile device or a computing device on-board the truck may be configured to receive, process, and transmit the on-board device output data to one or more downstream processing units.

[0033] Raw signals received from a particular vehicle and / or tire sensor 112, 114, etc. may be stored in an on-board device memory, or an equivalent local data storage network operatively linked to an on-board device processor, for selective retrieval and transmission via the data pipeline stage 120 as required for computation according to the methods disclosed herein. A local or downstream "data storage network," as used herein, generally refers to a separate, centralized, or distributed logical and / or physical entity configured to store data and enable selective retrieval therefrom, and may include, for example, but not limited to, memories, look-up tables, files, registers, databases, database services, etc. In some embodiments, raw data signals from the various sensors 112, 114, etc. may be communicated in substantially real-time from the vehicle to a downstream processing unit. Alternatively, taking into account the inherent inefficiencies in continuous data transmission of high frequency data, the data may be compiled, encoded, and / or summarized, for example, for more efficient (e.g., periodic time-based, or alternatively defined event-based) transmission from the vehicle to a processing unit via a suitable (e.g., cellular) communication network.

[0034] Once transmitted to the downstream processing unit via the communications network, the vehicle data and / or tire data 112, 114, etc. may be stored, for example, in a database associated therewith, further processed for processing via one or more algorithmic models as disclosed herein, or may be made retrievable as input. The models may be implemented at least in part via execution by a processor and may enable selective retrieval of the vehicle data and / or tire data, as well as electronic communication for inputting any additional data or algorithms from databases, look-up tables, etc. stored in association with the processing unit.

[0035] The terms "processor" or "processing unit" or "processing stage" 130 as used herein may refer to at least general purpose or special purpose processing devices and / or logic, including but not limited to microprocessors, microcontrollers, state machines, etc., as can be understood by one of ordinary skill in the art. A processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.

[0036] The various illustrative logic blocks, modules, and algorithm steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or a combination of both. To clearly illustrate this interchangeability of hardware and software, the various illustrative components, blocks, modules, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the particular application and design constraints imposed on the overall system. The described functionality can be implemented in various ways for each particular application, and such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

[0037] The various illustrative logic blocks and modules described in connection with the embodiments disclosed herein may be implemented or performed by a machine, such as a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but alternatively the processor may be a controller, microcontroller, or state machine, combinations thereof, and the like. A processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.

[0038] The steps of a method, process, or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or any other form of computer readable medium known in the art. An exemplary computer readable medium may be coupled to the processor such that the processor can read information from and write information to the memory / storage medium. Alternatively, the medium may be integral to the processor. The processor and the medium may reside in an ASIC. The ASIC may reside in a user terminal. Alternatively, the processor and the medium may reside as separate components in a user terminal.

[0039] In the following, with reference to Figs. 2 to 12, an exemplary method 200 for quantifying performance aspects of an automobile tire, more specifically for detecting a slow leak phenomenon of the internal air pressure at an early stage, may be described. A slow leak event, an example of which is shown in Fig. 2b, may be defined as a phenomenon in which the internal pressure drops rapidly compared to a natural pressure reduction, an example of which is shown in Fig. 2a. If a vehicle continues to run with one or more tires with very low internal pressure, the risk of permanent damage to the tires generally increases. However, if a slow leak event can be identified at an early stage, such a risk may be dramatically reduced by implementing interventions such as tire repair and replacement.

[0040] Method 200 begins with signals collected in a data acquisition stage (step 210), which may implement a conventional on-board data acquisition device, such as a tire pressure monitoring system (TPMS) mounted in or on the tire as previously described, which may generate signals corresponding to one or more of contained air temperature, ambient temperature, inflation pressure, tire identifier, vertical load, speed, etc. The data acquisition device may in some embodiments be configured to collect data as the tire rolls over different roads and surfaces, although the system may be configured such that only data considered in subsequent steps is collected while the automobile is stopped or otherwise parked in a fleet yard.

[0041] In other words, the data collection unit that provides tire data to the processing unit may be geographically limited in its ability to communicate with the data acquisition device and may be fixed in location with respect to the fleet yard such that only time data samples from specific vehicles are collected when those vehicles are in the fleet yard. In one embodiment, the wireless communication network associated with the in-yard monitoring unit may include one or more wireless routers that receive signals from the data acquisition device (e.g., directly from a TPMS sensor or indirectly via an on-board computing device), decode the signals, and forward the decoded signals for downstream processing. One exemplary data transmission frequency may be approximately 2.5 readings per minute while the vehicle is in the fleet yard.

[0042] As previously discussed, conventional methods utilizing tire inflation pressure data during vehicle operation may result in false positives or false negatives due to associated temperature compensation variations. It may also be appreciated that if data is only collected periodically, corresponding to time, when the vehicle is in the fleet yard, the varying frequency of readings may introduce noise into subsequent calculations, at least potentially resulting in false positives or false negatives. Thus, the data models disclosed herein may implement various techniques to filter data and label and recognize time series data patterns to accurately identify associated pressure loss events.

[0043] 3, in an exemplary data set, the cold inflation pressure value 310 for a given tire is shown to gradually decrease from a first time 340 to a second time 350 when a significant inflation event occurs in the United States. At the first time 340, the measurement 310 is well between the recommended threshold 302 and the warning threshold 304. As time progresses, the measurement 310 falls below the warning threshold 304 and even below the critical threshold 306 well before the second time 350, and is not substantially in line with the variations in the associated temperature value 320, as shown by the gradual decrease that continues for several hours or more. In other words, while the measured temperature value 320 fluctuates continuously within the band 330, the gradual decrease in tire inflation pressure is clearly not a function of temperature.

[0044] 4, another exemplary data set shows a gradual decline in inflation pressure values ​​310 over another few days, punctuated by a downward spike and returning to the mainstream trend. Despite this downward spike, which may correspond to an inflation pressure check, for example, the overall trend is indicative of a slow leak event, as would preferably be identified by the model disclosed herein. Also, while time series data corresponding to slow leak events are often bounded by a tire inflation event at a first and second end (as shown here), this is not necessarily true for all such slow leak events. For example, as shown in FIG. 5, a gradual decline in tire inflation pressure measurements 310 over two subsequent days may preferably be labeled as two separate events.

[0045] Another exemplary data set, such as that shown in FIG. 6, illustrates the importance of focusing on the overall trend of the inflation pressure measurements 310, rather than determining a false positive for a slow leak event based on intermittent downward spikes (e.g., corresponding to pressure checks). In this case, the overall trend of the pressure measurements is plateauing. In contrast, in FIG. 7, a sudden (i.e., not gradual) drop in the internal pressure measurements 310 is shown without a return to trend, such as may indicate a major failure of the tire, such as a puncture due to a nail or other obstruction. While such an event may be characterized in some embodiments as equivalent to a slow leak event for purposes of generating an alert, such as an intervention, in other embodiments, it may be preferable for a data set such as that seen in FIG. 7 to be defined separately from slow leak events.

[0046] Returning to FIG. 12, the method 200 may continue by compiling data samples over a defined sampling period (step 220). In one embodiment, this involves creating a subset of internal pressure measurements collected over the past 20 hours. Further thresholds are set to define data acquisition gates such that the amount of data used to estimate the pressure loss rate is sufficient and therefore the results of the algorithm are less susceptible to noise. In step 230, the number of samples in the created subset is compared to a predefined first threshold. If the first threshold is met, then in step 240, the method continues by calculating the difference between the time of the first observation in the created subset and the time of the latest observation in the created subset and comparing the difference to a predefined second threshold. In one example, the number of samples required is 5 and the required period between the first and latest samples is 30 minutes, although various alternative values ​​and thresholds may be implemented within the scope of this disclosure.

[0047] If the first and second thresholds (or their equivalents) are met, the method 200 may continue by applying a statistical model to determine a metric related to the pressure loss rate, as disclosed herein (step 250). In the following example, by constructing a linear regression model where the target variable is the tire internal pressure in pounds per square inch (psi) (or temperature compensated internal pressure as described in more detail below) and the descriptive variable is elapsed time, the hourly pressure loss rate (hPLR) may be estimated using the following least squares method: Pressure (psi) = α + β x (elapsed time)

[0048] In this context, as shown in FIG. 8, the regression coefficient β is estimated as the hourly pressure loss rate (hPLR) over a defined time frame (e.g., 20 hours), while the pressure loss rate itself can be the slope of a line 360 ​​that best fits the internal pressure over time, calculated using a linear regression model.

[0049] In various embodiments (not shown in FIG. 2), a “corrected” internal pressure value (i.e., temperature compensation) can further be utilized in the equations referenced above, e.g., obtained by applying the ideal gas law to the sampled temperature and internal pressure values.

[0050] At step 260, the method 200 continues by comparing the estimated metric (eg, hPLR) to a third predetermined threshold, and if the threshold is exceeded, a slow leak event is determined.

[0051] In the embodiment shown in FIG. 9, individual hPLR estimates are determined for each new measurement over a defined sampling period, starting from the current time T1. For each new estimate, a median hPLR value is determined for each block of data (e.g., 45 minutes), and in this example, three different median values ​​hplr1, hplr2, hplr3 are defined for three consecutive 45 minute blocks. If the median hPLR value of each block of individual estimates is determined to be less than, for example, -1.0 psi, a slow leak event may be determined for the corresponding tire. As further shown in FIG. 10, with each new estimated hPLR value, the individual past hPLR values ​​may be regrouped, as long as they fall within a defined sampling window (e.g., 20 hours), and the median value is calculated and again compared to a threshold value (e.g., -1.0 psi).

[0052] Method 200 may optionally include step 270, in which the determined slow leak event may be suppressed or dismissed based on a further determination that a temperature-based metric is applied, such as, for example, an hourly temperature change rate (hTCR) of more than 20° F. over a corresponding time period.

[0053] Referring now to Figures 11a-11d, sample slow leak events and non-events are shown from the random forest approach. The highlighted portion of Figure 11a represents the "true positive" (TP) system output corresponding to a properly detected actual slow leak event. The highlighted portion of Figure 11b represents the "false negative" (FN) system output corresponding to an undetected actual slow leak event. The highlighted portion of Figure 11c (arrow) represents the "false positive" (FP) system output corresponding to an improperly detected slow leak event, where there was no significant change in the tire internal pressure trend and a downward slope from a short upward spike correlated with the slow leak event. Figure 11d represents the "true negative" (TN) system output corresponding to a properly detected non-event.

[0054] It will be understood that the various thresholds provided herein for the method 200 are merely exemplary, and that such values ​​may be optimized over time for a given application.

[0055] The statistical model evaluation methodology referenced above can be treated as a classification problem in the context of machine learning, and in the following example, the evaluation can maximize precision, recall, and accuracy over time. "Precision" in this context can relate to, for example, the probability that an alert corresponds to a real condition if it is triggered, and can be quantified as {Precision = TP / (TP + FP)}. "Recall" in this context can relate to, for example, the probability that a corresponding alert is triggered if a realistic slow leak condition exists, and can be quantified as {Recall = TP / (TP + FN)}. "Precision" in this context can consider both precision and recall to indicate how often an alert is correctly triggered. For example, if a single FP alert is triggered for one wheel position on one car, precision and accuracy will be equal to 0. If the same single FP alert occurs in a population of 100 wheel positions, precision will still be 0, but accuracy will be 99% (since there are 99 TN readings). This can be quantified as {Accuracy = (TP + TN) / population parameter}. Since the metrics of precision and recall are effectively traded off against each other, an additional score (F1) can be implemented to balance them by taking the average of precision and recall. To calculate the index, it is necessary to define correct and incorrect answers to the classification problem. In the evaluation example, the answer for the "slow leak" sample was correct if the extracted sub-time series had an alert at least once in 6 days. The answer for the "normal" tire sample was correct if the sub-time series had no alerts.

[0056] In various embodiments, the method 200 may further include generating an output signal (step 280) corresponding to the detected slow leak event, such as, for example, in the form of an alert or message to a user interface or display unit. The output signal may be generated programmatically in response to the detected slow leak event. The output signal may be generated in response to a received user request, such as by recording events over time and delivering reports in a batch format. The output signal may further be generated to automatically trigger or otherwise facilitate a control response or intervention for vehicle or fleet management control.

[0057] In one embodiment, the slow leak event output from the system 100 and method 200 may be further implemented to predict future timing of tire interventions, such as suggested or required inflation or replacement schedules.

[0058] Throughout this specification and claims, unless context dictates otherwise, the following terms take at least the meaning explicitly associated therewith. The meanings identified below do not necessarily limit the terms, but merely provide illustrative examples of the terms. The meanings of "a," "an," and "the" may include plural references, and the meaning of "in" may include "in" and "on." As used herein, the phrase "in one embodiment" does not necessarily refer to the same embodiment, but may.

[0059] As used herein, conditional language, such as "can," "might," "may," "eg," among others, is generally intended to convey that certain embodiments include certain features, elements, and / or conditions, but other embodiments do not include those particular features, elements, and / or conditions, unless specifically stated otherwise or otherwise understood within the context in which it is used. Thus, such conditional language is generally not intended to suggest that features, elements, and / or conditions are in any way required for one or more embodiments, nor is it generally intended to suggest that one or more embodiments necessarily include logic for determining, with or without author input or prompting, whether those features, elements, and / or conditions should be included in or implemented in any particular embodiment.

[0060] Although certain preferred embodiments of the present invention may be described in this disclosure with respect to methods typically performed by or for a fleet management system, and more specifically for an autonomous vehicle fleet or commercial truck application, the present invention is in no way expressly limited thereto, and the term "vehicle" as used herein, unless otherwise indicated, refers to an automobile, truck, or equivalent of either, whether self-propelled or not, which may include one or more tires, and thus may require accurate estimation or prediction of internal tire pressure loss and possible failure, replacement, or intervention.

[0061] As used herein, unless otherwise noted, the term "user" may refer to, for example, a driver, passenger, mechanic, technician, fleet management personnel, or any other person or entity that may be associated with a device having a user interface for providing the features and steps disclosed herein.

[0062] The foregoing detailed description has been provided for purposes of illustration and description. Thus, while novel and useful specific embodiments of the invention have been described, it is not intended that such references be construed as limitations on the scope of the invention, except as set forth in the following claims.

Claims

1. A computer-implemented tire monitoring method (200), comprising: collecting (210) via at least one data acquisition device (110, 112, 114) mounted on a vehicle having a plurality of tires, data samples corresponding to at least an inflation pressure of at least one of the plurality of tires; Calculating (220) an elapsed time from a first data sample within a sampling period of a defined length of time; if the number of data samples within the defined sampling period exceeds a first threshold (230) and the elapsed time since the first data sample exceeds a second threshold (240), applying a statistical model to the data samples corresponding to at least inflation pressure versus elapsed time (250); identifying a slow leak event based on the estimated decrease in inflation pressure from the statistical model (260); and generating (280) an output signal corresponding to the confirmed slow leak event of the at least one of the plurality of tires.

2. if the speed of the vehicle is determined to have been zero for a third threshold length of time; or 2. The tire monitoring method of claim 1, wherein the data samples are collected for the statistical model only while the vehicle is in a fleet yard where it can be parked and the data acquisition device is within communication range of one or more data collection units in a fleet yard monitoring system that monitors the fleet yard.

3. collecting, via the at least one data acquisition device mounted on a vehicle having a plurality of tires, contained air temperature associated with the data sample corresponding to the at least one inflation pressure of the at least one of the plurality of tires; and generating a temperature compensated inflation pressure value for each of the data samples, the statistical model implementing the temperature compensated inflation pressure value to identify the slow leak event; or 3. The tire monitoring method of claim 2, further comprising: determining whether to selectively generate the output signal corresponding to a confirmed slow leak event based at least in part on a time rate of change of the associated contained air temperature relative to a threshold value.

4. the slow leak event is further identified by considering a median hourly pressure loss rate corresponding to the estimated decrease in the inflation pressure for a second defined sampling period having a defined length of time; 2. The tire monitoring method of claim 1, wherein the output signal corresponding to the confirmed slow leak event is implemented to predict timing of a tire intervention event including one or more of a recommended inflation pressure for a tire, a required inflation pressure for a tire, and when to change a tire.

5. A tire monitoring system (100), comprising: at least one data acquisition device (110, 112, 114) mounted on a vehicle having a plurality of tires and configured to collect data samples corresponding to at least an inflation pressure of at least one of the plurality of tires; at least one data collection unit configured to receive the collected data samples from the on-board data acquisition devices (120, 140); A tire monitoring system (100) comprising: a processing unit (130) linked to the at least one data collection unit, the processing unit and / or the at least one data acquisition device being configured to direct the execution of each step of the method according to any one of claims 1 to 4.

Images