GB2613135A

GB2613135A - Brake performance monitoring system

Info

Publication number: GB2613135A
Application number: GB2110805.5A
Authority: GB
Inventors: Mesgarpour Mohammad; Watson Stephen; Onnis Alessia; Mesgarpour Mohsen; Raza Nadeem
Original assignee: MICROLISE Ltd
Current assignee: MICROLISE Ltd
Priority date: 2021-07-27
Filing date: 2021-07-27
Publication date: 2023-05-31
Also published as: WO2023007139A1; EP4377175A1; GB202110805D0

Abstract

A computer implemented method 100, for use in electronically monitoring braking performance of a vehicle braking system. The method comprises: receiving 101 brake measurement data from at least one sensor (301; fig. 3); determining 102 context data associated with the measurement data, based on received input data; and determining 103 braking performance data by inputting the measurement data and associated context data into a trained braking performance model that has been generated via at least one machine learning system (205; fig. 2). The brake measurement data is indicative of vehicle braking during a braking event, for example braking demand or deceleration. The context data may include the status of a brake assist system such as Vehicle Dynamic Control (VDC), Electronic Stability Control (ESC), engine braking or exhaust braking; and/or vehicle load, manoeuvre, or operating environment during the event; and/or the status of brake warnings, firmware, or a brake configuration of the brake system. The method may include sending the measurement and context data to a server. The method may include generating an alert based on a determination that a braking performance value has crossed a threshold, for example a notification regarding brake degradation indicating a time for brake maintenance.

Description

TITLE

Brake Performance Monitoring System

TECHNOLOGICAL FIELD

Examples of the present disclosure relate to methods, apparatuses and systems for Monitoring Braking Performance. Some examples, though without prejudice to the foregoing, relate to a method, apparatus and system for an electronic system for monitoring braking performance. Certain examples, though without prejudice to the foregoing, relate to a method, apparatus and system for monitoring trailer brake performance.

BACKGROUND

Braking performance of a vehicle (e.g., car, van, truck, tractor and trailer -not least such as a Heavy Goods Vehicle (HGV)), can be tested and monitored using an Electronic System for Monitoring Braking Performance (ESMBP).

Many countries define a set of minimum requirements to be satisfied to ensure vehicles comply with a required brake performance standard, e.g., by defining acceptable bands of brake performance across different vehicles and specifications.

The UK's Driver and Vehicle Standards Agency (DVSA) uses industry standard specification (e.g., ISO 21069) to assess a vehicle operator's maintenance arrangement obligations and suitability of a manufacturers' ESMBP. There are many different approaches across the EU for braking performance monitoring with different minimum criteria. The UNECE (United Nations Economic Commission of Europe) regulation for heavy vehicle braking standard is set out in regulation No. 13, which covers general braking systems, fitments and compatibilities.

Typically, a vehicle must be periodically tested with a Roller Brake Tester (RBT) or a decelerometer brake test. However, such tests impose considerable limitations and cost to the vehicle operator, not least such as downtime of the vehicle.

In general, it is the operator's responsibility to ensure their vehicles are operating safely. Many organisations, like the UK's DVSA, acknowledge but not approve an industry standard specification for ESMBP, and it is up to manufacturers of ESMBPs to demonstrate their systems' adequately monitor braking performance.

Conventional brake monitoring systems and ESMBPs are not always optimal.

In some circumstances, it may be desirable to provide improved braking performance monitoring of a vehicle. In some circumstances, it may be desirable to provide braking performance monitoring that better enables a vehicle operator to determine/predict when brake maintenance is likely to be required so that the vehicle operator can duly schedule maintenance work in order to maximise utilisation of the vehicle and minimise unscheduled services on the vehicle. In some circumstances, it may be desirable to enable an operator to identify when a vehicle's brake performance started to degrade, e.g., so as to enable the vehicle operator to investigate changes in the operating conditions of a vehicle that might have led to the brake performance degradation (not least such as software, hardware and firmware changes of the vehicles, connected vehicles and their braking systems).

The listing or discussion of any prior-published document or any background in this specification should not necessarily be taken as an acknowledgement that the document or background is part of the state of the art or is common general knowledge.

One or more aspects/examples of the present disclosure may or may not address one or more of the background issues.

BRIEF SUMMARY

The scope of protection sought for various embodiments of the invention is set out by the independent claims.

Any examples/embodiments and features described in this specification that do not fall under the scope of the independent claims are to be interpreted as examples useful for understanding various embodiments of the invention.

According to various, but not necessarily all, examples of the disclosure there is provided a method for use in an electronic system for monitoring braking performance for a braking system of a vehicle, the method comprising causing, at least in part, actions that result in: receiving, from at least one sensor, brake measurement data indicative of at least one value of at least one brake measurement parameter for at least one brake event of at least one brake of at least one braking system of at least one vehicle; determining, based at least in part on received input data, context data associated with the brake measurement data, wherein the context data is indicative of at least one value of at least one context parameter for the at least one brake event; determining braking performance data indicative of at least one value of at least one braking performance parameter for the least one brake; wherein the braking performance data is determined by inputting the brake measurement data and the associated context data into a trained braking performance model; and wherein the trained braking performance model is a model that has been generated via at least one machine learning system and configured to: receive, as an input, data indicative of one or more brake measurement parameter values and data indicative of associated one or more context parameter values, and output data indicative of one or more braking performance parameter values for the same.

According to various, but not necessarily all, examples of the disclosure there is provided a chipset comprising processing circuitry configured to perform the above-mentioned method.

According to various, but not necessarily all, examples of the disclosure there is provided a module, device and/or system comprising means for performing the above-mentioned method.

According to at least some examples of the disclosure there is provided an apparatus comprising means for: receiving, from at least one sensor, brake measurement data indicative of at least one value of at least one brake measurement parameter for at least one brake event of at least one brake of at least one braking system of at least one vehicle; determining, based at least in part on received input data, context data associated with the brake measurement data, wherein the context data is indicative of at least one value of at least one context parameter for the at least one brake event; determining braking performance data indicative of at least one value of at least one braking performance parameter for the least one brake; wherein the braking performance data is determined by inputting the brake measurement data and the associated context data into a trained braking performance model; and wherein the trained braking performance model is a model that has been generated via at least one machine learning system and configured to: receive, as an input, data indicative of one or more brake measurement parameter values and data indicative of associated one or more context parameter values, and output data indicative of one or more braking performance parameter values for the same.

According to various, but not necessarily all, examples of the disclosure there is provided computer program instructions for causing an apparatus to perform: receiving, from at least one sensor, brake measurement data indicative of at least one value of at least one brake measurement parameter for at least one brake event of at least one brake of at least one braking system of at least one vehicle; determining, based at least in part on received input data, context data associated with the brake measurement data, wherein the context data is indicative of at least one value of at least one context parameter for the at least one brake event; determining braking performance data indicative of at least one value of at least one braking performance parameter for the least one brake; wherein the braking performance data is determined by inputting the brake measurement data and the associated context data into a trained braking performance model; and wherein the trained braking performance model is a model that has been generated via at least one machine learning system and configured to: receive, as an input, data indicative of one or more brake measurement parameter values and data indicative of associated one or more context parameter values, and output data indicative of one or more braking performance parameter values for the same.

According to various, but not necessarily all, examples of the disclosure there is provided an apparatus comprising: at least one processor; and at least one memory including computer program instructions; the at least one memory and the computer program instructions configured to, with the at least one processor, cause the apparatus at least to perform: receiving, from at least one sensor, brake measurement data indicative of at least one value of at least one brake measurement parameter for at least one brake event of at least one brake of at least one braking system of at least one vehicle; determining, based at least in pad on received input data, context data associated with the brake measurement data, wherein the context data is indicative of at least one value of at least one context parameter for the at least one brake event; determining braking performance data indicative of at least one value of at least one braking performance parameter for the least one brake; wherein the braking performance data is determined by inputting the brake measurement data and the associated context data into a trained braking performance model; and wherein the trained braking performance model is a model that has been generated via at least one machine learning system and configured to: receive, as an input, data indicative of one or more brake measurement parameter values and data indicative of associated one or more context parameter values, and output data indicative of one or more braking performance parameter values for the same.

According to various, but not necessarily all, examples of the disclosure there is provided a non-transitory computer readable medium encoded with instructions that, when performed by at least one processor, causes at least the following to be performed receiving, from at least one sensor, brake measurement data indicative of at least one value of at least one brake measurement parameter for at least one brake event of at least one brake of at least one braking system of at least one vehicle; determining, based at least in part on received input data, context data associated with the brake measurement data, wherein the context data is indicative of at least one value of at least one context parameter for the at least one brake event; determining braking performance data indicative of at least one value of at least one braking performance parameter for the least one brake; wherein the braking performance data is determined by inputting the brake measurement data and the associated context data into a trained braking performance model; and wherein the trained braking performance model is a model that has been generated via at least one machine learning system and configured to: receive, as an input, data indicative of one or more brake measurement parameter values and data indicative of associated one or more context parameter values, and output data indicative of one or more braking performance parameter values for the same.

According to various, but not necessarily all, examples of the disclosure there is provided a method of providing and/or manufacturing an apparatus and/or system as described herein.

According to various, but not necessarily all, examples of the disclosure there is provided a method of using an apparatus and/or system as described herein.

The following portion of this 'Brief Summary' section describes various features that can be features of any of the examples described in the foregoing portion of the 'Brief

Summary' section.

In some but not necessarily all examples, the brake measurement data comprises data indicative of one or more of: at least one braking event; at least one application of the at least one brake; a braking demand; and a deceleration of the at least one vehicle.

In some but not necessarily all examples, the input data comprises one or more of: sensor data received from one or more sensors of the vehicle; user input data received from a user; data received from at least one data source local to the vehicle; and data received from at least one remote server.

In some but not necessarily all examples, the trained braking performance model has been trained on at least one training dataset comprising data indicative of a plurality of brake measurement parameter values and associated context parameter values for a plurality of brake events whose brake performance parameter values have been pre-determined.

In some but not necessarily all examples, the trained braking performance model has been generated via the at least one machine learning system and trained on at least one training dataset to determine one or more correlations between: brake measurement parameter values; context parameter values; and braking performance parameter values.

In some but not necessarily all examples, the method further comprises: determining whether the braking performance parameter value crosses a predetermined threshold value; generating an alert based on a determination that the braking performance parameter value crosses the predetermined threshold value.

In some but not necessarily all examples, the method further comprises: updating the trained braking performance model based at least in part on the brake measurement data and the context data.

In some but not necessarily all examples, the method further comprises determining, based at least in part on the braking performance data, braking degradation data indicative of at least one braking degradation parameter value.

In some but not necessarily all examples, the method further comprises: determining, based at least in part on the braking degradation data, brake maintenance schedule data indicative of a time to service the at least one brake.

In some but not necessarily all examples, the method further comprises: generating at least one notification comprising the time to service the at least one brake.

In some but not necessarily all examples, the method further comprises: sending the brake measurement data and/or the context data to at least one server to enable the at least one server to, at least one of: determine the braking performance data using the trained brake performance model; and further train the brake performance model.

In some but not necessarily all examples, the method further comprises, prior to sending the brake measurement data and/or the context data to the server, one or more of: filtering the brake measurement data and/or the context data; transforming the brake measurement data and/or the context data; and amalgamating the brake measurement data and/or the context data.

In some but not necessarily all examples, the context data comprises data indicative of at least one status of at least one brake assist system.

In some but not necessarily all examples, the brake assist system comprises one or more of: Vehicle Dynamic Control, Electronic Stability Control, Engine Brake, Exhaust Brake, and turn-brake assist brakes.

In some but not necessarily all examples, the context data comprises data indicative of one or more of: at least one type of braking event; and at least one frequency of braking events.

In some but not necessarily all examples, the context data comprises data indicative of one or more of: load characteristics; a type of load; and vehicle characteristics.

In some but not necessarily all examples, the context data comprises data indicative of at least one road type.

In some but not necessarily all examples, the context data comprises data indicative of at least one status of brake warnings for the at least one braking system.

In some but not necessarily all examples, the context data comprises data indicative of one or more of: brake firmware of the at least one brake; and brake configuration of the braking system.

In some but not necessarily all examples, the context data comprises data indicative of one or more of: a manoeuvre of the vehicle, and an operating environment of the vehicle.

In some but not necessarily all examples, determining braking performance data comprises determining braking performance data indicative of one or more of: at least one braking performance parameter value for each individual brake of the at least one braking system; at least one braking performance parameter value for one or more brakes of an individual axle; at least one braking performance parameter value for at least some or all brakes of the at least one braking system; at least one braking performance parameter value for each individual brake or all brakes of a tractor's braking system; and at least one braking performance parameter value for each individual brake or all brakes of a trailer's braking system.

While the above examples of the disclosure and optional features are described separately, it is to be understood that their provision in all possible combinations and permutations is contained within the disclosure. Also, it is to be understood that various examples of the disclosure may comprise any or all of the features described in respect of other examples of the disclosure, and vice versa.

According to various, but not necessarily all, examples of the disclosure there are provided examples as claimed in the appended claims.

BRIEF DESCRIPTION OF THE DRAWINGS

For a better understanding of various examples of the present disclosure that are useful for understanding the detailed description and certain examples of the present disclosure, reference will now be made by way of example only to the accompanying drawings in which: FIG. 1 shows an example of a method as described herein; FIG. 2 shows an example of the subject matter described herein; FIG. 3 shows an example of a system as described herein; FIG. 4 shows an example of an apparatus as described herein; FIG. 5 shows an example of a computer program as described herein; FIG. 6 shows an example of the subject matter described herein; FIG. 7 shows an example of the subject matter described herein; FIG. 8 shows an example of the subject matter described herein; FIG. 9 shows an example of the subject matter described herein; The figures are not necessarily to scale. Certain features and views of the figures may be shown schematically or exaggerated in scale in the interest of clarity and conciseness. For example, the dimensions of some elements in the figures can be exaggerated relative to other elements to aid explication. Similar reference numerals are used in the figures to designate similar features. For clarity, all reference numerals are not necessarily displayed in all figures.

DETAILED DESCRIPTION

The figures schematically illustrate, and the following description describes, various examples of the disclosure including a computer implemented method 100 for use in an Electronic System for Monitoring Braking Performance (ESMBP) 301 for a braking system of a vehicle, the method comprising causing, at least in part, actions that result in: receiving 101, from at least one sensor 302 (such as at least one telematics unit/telemetry units, loggers), brake measurement data 201 indicative of at least one value of at least one brake measurement parameter for at least one brake event of at least one brake of at least one braking system of at least one vehicle; determining 102, based at least in part on received input data 202a, context data 202 associated with the brake measurement data, wherein the context data is indicative of at least one value of at least one context parameter for the at least one brake event; determining 103 braking performance data 203 indicative of at least one value of at least one braking performance parameter for the least one brake; wherein the braking performance data is determined based at least in part by inputting the brake measurement data and the associated context data into a trained braking performance model 204; and wherein the trained braking performance model is a model that has been generated via at least one machine learning system 205 and configured to: receive, as an input, data indicative of one or more brake measurement parameter values and data indicative of associated one or more context parameter values, and output data indicative of one or more braking performance parameter values for the same.

The inventors of the present invention have appreciated that the performance/effectiveness of a vehicle's brakes and braking system is dependent upon a multitude of contextual factors, i.e. contexts, prevailing at the time the brakes are applied. Such differing contexts, and differing combinations of contexts, can significantly affect the behaviour of braking systems. Accordingly, when determining a braking performance metric for one or more brakes of a braking system, it would be beneficial to take into account such contexts and their differing combinations.

Advantageously, in various examples of the invention, a trained braking performance model is provided and utilised that enables a determination, based on brake sensor measurement data for a braking event, of a braking performance metric, i.e. braking performance parameter value, that can accommodate and take into account the context at the time of a braking event. This may thereby provide a more accurate indication of the braking performance/effectiveness of the brakes of the braking system, particularly under different contexts (e.g. not least differing configurations of tractors and trailers, as well as operating conditions). Examples may thereby provide a method and decision support system for monitoring brakes' health and performance.

As will be discussed further below, advantages of various examples of the present disclosure may include: estimating a brake's performance/effectiveness more accurately, by enabling an adjustment and accounting for a wide variety of differing contexts/factors that affect brake performance. For example, braking type (like short brakes, continuous brakes, and harsh brakes), load characteristics, and different manoeuvres can significantly affect the brake performance and can be taken into account in examples of the present disclosure when determining brake performance data; predicting brake degradation rate and scheduling next brake maintenance with higher accuracy and precision; improving brake event identification, by filtering out invalid brake measurement data/brake events, reducing unexplained outlier brake measurement data, and by including braking mode metadata; being able to model a large variety of braking systems under different conditions and manoeuvres; adjusting for temporal patterns, like usage characteristics of vehicles, trailers and brakes; and detecting sudden changes in brake performance associated with changes of: operating conditions, hardware, software and firmware of brake systems.

FIG. 1 schematically illustrates a flow chart of a method 100 for use in an Electronic System for Monitoring Braking Performance (ESMBP) for a braking system of a vehicle. The vehicle may be one or more of: a tractor unit alone, a trailer unit alone, combined tractor and trailer units, an HGV, a lorry, a truck, construction machines and any other powered or unpowered vehicle with a braking system.

The blocks illustrated in FIG. 1, and the method steps discussed below, can represent: sections of instructions/code in a computer program, such as shown in FIG. 5, which can be executed by an apparatus, such as shown in FIG. 4, thereby providing means for implementing the method.

In block 101 brake measurement data is received from at least one sensor. The brake measurement data is indicative of least one value of at least one brake measurement parameter for at least one brake event of at least one brake of at least one braking system of at least one vehicle. In this regard, the brake measurement data provides brake-related sensor data for detecting, determining and defining a brake event, such a brake event corresponding to an application/actuation of one or more brakes of one or more braking systems of the vehicle and the resultant braking force/deceleration of the same. The brake measurement data may comprise data representative of one or more of: at least one braking event, e.g., data sufficient to define a brake event including not least a start time and/or duration of the brake event; at least one application of the at least one brake, e.g., data sufficient to detect the application/actuation of a brake such as depressing of a brake pedal; a braking demand e.g., data sufficient to determine an amount of braking desired/required, such as brake pressure or how hard a brake is actuated (e.g., how hard a brake pedal is depressed). In some examples the braking demand is a demand from a brake other than a hand brake; and a deceleration of the at least one vehicle.

In block 102, context data is determined which is representative of the context of the at least one brake event and brake measurement of the same. The context data is indicative of at least one value of at least one context parameter for the at least one brake event. Such a determination of the context data is based at least in part on received input data. The input data may comprise supplemental data/raw data from which the various types of context, as will be discussed further below, can be derived.

The context data, i.e., the parameter values for the same, may be determined substantially at the time of the brake event/brake measurement, i.e., so as to provide the contemporaneous context for the brake event/brake measurement. In such a manner, the context data is thereby associated with the brake measurement data in that is provides an indication of the context prevailing at the time of the brake event/brake measurement. Each brake measurement/brake event may have plural differing contexts associated therewith.

The input data from which the context data is derived may comprises one or more of: sensor data received from one or more sensors of the vehicle; user input data received from a user; data received from at least one data source local to the vehicle, e.g., a subsystem of the vehicle; and data received from at least one remote server.

In block 103, braking performance data is determined, which is representative of an effectiveness of the at least one brake. The braking performance data is indicative of at least one value of at least one braking performance parameter for the least one brake. The braking performance data is determined at least in part by inputting the brake measurement data and the associated context data into a trained braking performance model. The trained braking performance model is a model that has been generated via at least one machine learning system and configured to: receive, as an input, data indicative of one or more brake measurement parameter values and data indicative of associated one or more context parameter values, and output data indicative of one or more braking performance parameter values for the same.

The trained model may be further configured to output data indicative of one or more braking performance parameter values based on historical usage data, road conditions and characteristics data (e.g. of the vehicle, its braking systems, the vehicle's load, and other vehicles connected to the vehicle such as trailers) to assess the performance of brakes.

In some examples, the machine learning system may involve artificial intelligence, machine learning algorithms and/or a machine learning network. The machine learning system may be a supervised machine learning system comprising a multilabel classifier. The machine learning system may be based on a deep neural network. The machine learning system may use linear regression, logistic regression, vector support machines or an acyclic machine learning network such as a single or multi hidden layer neural network. In some example, the machine learning system can be supervised or semi-supervised. In some examples, a reinforcement machine learning method could be used. In some examples, a specific modelling method can be used.

The trained braking performance model may be trained on at least one training dataset comprising data indicative of a plurality of brake measurement parameter values and associated context parameter values for a plurality of brake events whose brake performance parameter values have been pre-determined.

The trained braking performance model may be generated via at least one machine learning system and trained on at least one training dataset so as to determine one or more correlations/relationships between: brake measurement parameter values; context parameter values; and braking performance parameter values.

Then, having established such correlations/relationships, the trained braking performance model is configured to generate an output of a braking performance parameter value based on an input of: a brake measurement parameter value and associated context parameter value.

The context data derived from the input data (such input data sourced from sensors, user input, data sources local to the vehicle and/or data sources remote of the vehicle such as stored on a remote server) may be indicative/representative of one or more many differing types of context prevailing when the braking event occurred.

In some examples, the context data comprises data indicative of at least one status of at least one brake assist system when the braking event occurred. For example, the context data may be indicative an operational status of: Electronic Stability Control (ESC). ESC is an extension to Electronic Braking System (EBS). ESC aims to increase vehicle stability during manoeuvres. ESC can work with all brake control systems, including conventional braking system, Anti-lock Braking System (ABS) and EBS. One example of ESC is Vehicle Dynamic Control (VDC) which can help prevent under and oversteer by reducing engine speed and applying the brakes on specific wheels; Engine Brake; Exhaust Brake; turn-brake assist brakes; and other systems that directly affect brake performance.

In some examples, the context data comprises data indicative of a type of braking event, e.g. a braking event of a pre-determined duration, short brakes, continuous brakes, harsh brakes and/or type of brake applied.

In some examples, the context data comprises data indicative of: a frequency of braking events (e.g., wherein there are a number of consecutive braking events of short duration and with short gaps therebetween).

In some examples, the context data comprises data indicative of one or more of: load characteristics of the vehicle when the braking event occurred, e.g., characteristics of a load borne by the vehicle (not least a trailer of a tractor, contents of the trailer, and of plant/equipment attached to the vehicle), a type of load of the vehicle when the braking event occurred, not least for example such as: obnoxious loads (e.g. food/animal/human waste), livestock (e.g. horses, sheep, cattle), fixed plant/equipment (e.g. white lining vehicle, road sweeper, access platforms), perishable liquids/goods (contamination liquid/powder tankers, concrete mixers), and load sensed across axles; and characteristics of the vehicle when the braking event occurred, not least such as: load-bearing ability, weight when unladen [for instance, bin Lorries can have >50% design-axle-weight when unladen]; vehicle type, vehicle model, vehicle range, vehicle model, vehicle series, distance travelled, trailer type, number of axles, towing status, and driving mode.

In some examples, the context data comprises data indicative of a road type the vehicle was travelling along when the braking event occurred. For example, the context data may be indicative of whether the vehicle was travelling along a: motorway, A road, B road, city roads, or country road when the braking event occurred. The road type may be determined using sensors such as location sensor (e.g. a satellite navigation/positioning system such as GPS), Inertial Measurement Units (IMUs -e.g. accelerometer, gyroscope and/or magnetometer), a determined speed, a road-surface-sensing traction control software, a road network map or other external sources.

In some examples, the context data comprises data indicative of a status of brake warnings for the braking system of the vehicle when the braking event occurred. For example, error and warning signals that can affect the performance of brake system indirectly (like Amber Warning Signal) or directly (like Red Warning Signals) may be monitored and the context data may be indicative of any such warnings occurring when the brake event occurred.

In some examples, the context data comprises data indicative of: brake warnings of the at least one brake, e.g., an identification of the firmware/brake manufacture software that controls brake system and the version of the same installed at the time of the brake event; and brake configuration of the braking system, thereby enabling a monitoring/tracking of changes to the brake configuration to identify any changes in characteristics and identifying configurations that can introduce bias or effects in the brake performance values. In this regard, all software, hardware and firmware changes may be captured and recorded.

In some examples, the context data comprises data indicative of a manoeuvre of the vehicle (e.g., whether the vehicle is performing a turn, or reversing) and an operating environment/environmental condition of the vehicle at the time of the brake event. This may enable account to be made of the real-life manoeuvres and operational environments the vehicle is operating under at the time of the braking event when determining the braking performance data. This may enable, unlike the roller brake test, the identification of over braking and under braking more accurately. Different Manoeuvres may be identified by using sensors such as Inertial Measurement Units (IMUs), speed detectors, wheel turn detectors, a road-surface-sensing traction control software, a road network map or other external sources.

The braking performance data may be determined separately for: each individual brake of a braking system of the vehicle; one or more brakes of an individual axle of the vehicle; and some or all brakes of a braking system of the vehicle.

Where the vehicle comprises a tractor and a trailer, braking performance data may be determined separately for: each individual brake or all brakes of a tractor's braking system; and each individual brake or all brakes of a trailer's braking system.

In some examples, the method further comprises determining whether the braking performance parameter value crosses (exceeds or is below) a predetermined threshold value. An alert, warning message or notification may be generated based on a determination that the braking performance parameter value crosses the predetermined threshold value. Where such determination and generation steps are performed by an apparatus local to the vehicle, the alert, warning message or notification may be presented to a user of the vehicle, e.g. via a user interface output (e.g. display/audio output) of the vehicle. Where such determination and generation steps are performed by a remote server, the alert, warning message or notification may be sent to the vehicle for presentation to the user, or may be sent to another server, e.g. of the vehicle's operator/maintenance/servicing staff or fleet manager responsible for the vehicle. The alert may be indicative of a sub-optimal or deficient braking performance necessitating maintenance/servicing of the brake. Examples of the present disclosure may thereby enable the determination of when maintenance is likely to be required based on both historical data, and current data so that maintenance work can be scheduled in order to maximise utilisation of the vehicle and minimise unscheduled services. In addition, examples of the present disclosure may enable operators to potentially identify when the brake performance started to degrade, and investigate changes in the operating conditions of vehicles that may have led to the degradation.

In some examples, the method further comprises updating the trained braking performance model based at least in part on the brake measurement data and the context data (i.e. utilising the brake measurement data and the context data in training datasets for further training the model).

In some examples, the method further comprises determining, based at least in part on the braking performance data, braking degradation data representative of a rate of reduction in the effectiveness of the one or more brakes. The braking degradation data is indicative of at least one braking degradation parameter value. For instance, the current value of the braking performance parameter may be compared to a previous/past/historic braking performance parameter value. Based on a time difference between the current and past braking performance parameter values (i.e. when the brake measurements for the same was captured) and optionally an estimation of typical usage of the vehicle in the intervening time period, a rate of braking degradation may be determined.

In some examples, brake maintenance schedule data is determined based at least in part on the braking degradation data. The brake maintenance schedule data being indicative of a predicted/estimated/suggested time when service of at least one brake is due/should take place. At least one notification, comprising the time to service the at least one brake, may be generated for sending and/or presenting to a user of the vehicle or vehicle/fleet operator.

Examples of the disclosure may thereby help drivers and operators to monitor braking systems, monitor degradation of braking systems, schedule next services, and compare vehicles based on their usage and braking system performance over time.

In some examples, the component blocks of FIG. 1 and the method actions described above may be performed by a single physical entity, such as the apparatus of FIG. 4.

For instance, the functions described may be performed by an apparatus, such as in FIG 4, wherein the apparatus is provided at a vehicle. In some examples, the component blocks of FIG. 1 and the method actions described above may be performed by an apparatus, such as in FIG 4, wherein the apparatus is provided at a remote server.

In some examples, the component blocks of FIG. 1 and the method actions described above may be performed by two or more physical entities forming a distributed system, e.g. a plurality of distributed apparatuses, each such as in FIG.4, forming parts of a distributed system that provides (or implements) one or more features which collectively implement the described functions. For instance, one or more of the functions (e.g., 101 and 102) may be performed by a first apparatus (e.g., an apparatus as per FIG. 4 provided at a vehicle), and one or more of the functions (e.g., 102 and/or 103) may be performed by a second apparatus (e.g., an apparatus as per FIG. 4 provided at/as a remoter server).

In some examples, such as where method steps 101 and/or 102 are performed by an apparatus local to the vehicle, the method further comprises: sending the brake measurement data and/or the context data to at least one server to enable the at least one server to, at least one of: determine the braking performance data using the trained brake performance model (i.e., such that the server performs step 103); and further train the brake performance model (whereupon the server can update trained brake performance models locally stored in vehicles).

In some examples, prior to sending the brake measurement data and/or the context data to the server, the method further comprises one or more of: filtering the brake measurement data and/or the context data. Artificial Intelligence and statistical methods may be used for detection of data outliers using predetermined probabilities and/or working characteristics (e.g., mechanical, usage, and physical characteristics. For instance, disproportionally very high deceleration compared with brake pressure and contextual data can be due to sensor error or delay in data transmission), invalid data can be discarded locally (e.g., by the controller or telematics units of the vehicle) or remotely (e.g., at a remote server/central system).; transforming the brake measurement data and/or the context data; and amalgamating the brake measurement data and/or the context data.

This may reduce the amount of data transmitted to the server and the amount of processing required to be performed by the server.

It will be understood that each block illustrated in FIG. 1, and each method step discussed above, can be implemented by various means, such as hardware, firmware, and/or software including one or more computer program instructions. For example, one or more of the procedures described above can be embodied by computer program instructions, such as shown in FIG. 5. In this regard, the computer program instructions which embody the procedures described above can be stored by a memory storage device and performed by a processor, such as shown in FIG. 4.

As will be appreciated, any such computer program instructions can be loaded onto a computer or other programmable apparatus (i.e., hardware) to produce a machine, such that the instructions when performed on the programmable apparatus create means for implementing the functions specified in the blocks. These computer program instructions can also be stored in a computer-readable medium that can direct a programmable apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the blocks. The computer program instructions can also be loaded onto a programmable apparatus to cause a series of operational actions to be performed on the programmable apparatus to produce a computer-implemented process such that the instructions which are performed on the programmable apparatus provide actions for implementing the functions specified in the blocks.

Various, but not necessarily all, examples of the present disclosure can take the form of a method, an apparatus or a computer program. Accordingly, various, but not necessarily all, examples can be implemented in hardware, software or a combination of hardware and software.

Various, but not necessarily all, examples of the present disclosure are described using flowchart illustrations and schematic block diagrams. It will be understood that each block (of the flowchart illustrations and block diagrams), and combinations of blocks, can be implemented by computer program instructions of a computer program. These program instructions can be provided to one or more processor(s), processing circuitry or controller(s) such that the instructions which execute on the same create means for causing implementing the functions specified in the block or blocks, i.e., such that the method can be computer implemented. The computer program instructions can be executed by the processor(s) to cause a series of operational steps/actions to be performed by the processor(s) to produce a computer implemented process such that the instructions which execute on the processor(s) provide steps for implementing the functions specified in the block or blocks.

Accordingly, the blocks support: combinations of means for performing the specified functions; combinations of actions for performing the specified functions; and computer program instructions/algorithm for performing the specified functions. It will also be understood that each block, and combinations of blocks, can be implemented by special purpose hardware-based systems which perform the specified functions or actions, or combinations of special purpose hardware and computer program instructions.

FIG. 2 schematically illustrates an example of the subject matter described herein, wherein a trained braking performance model 204 is trained by a machine learning system 205 based on training datasets 201td, 202td and 202td. The training datasets 30 comprise: training data 201td indicative of a plurality of brake measurement parameter values for one or more brakes for a plurality of brake events, training data 202td indicative of a plurality of context parameter values associated with the plurality of brake events, and training data 202td indicative of a plurality of pre-determined brake performance parameter values of the one or more brakes following the brake events.

The trained braking performance model is generated via the machine learning system and trained on the training datasets so as to determine one or more correlations/relationships between: brake measurement parameter values; context parameter values; and braking performance parameter values.

The trained braking performance model is configured such that, based on an input of a brake measurement data 201 (e.g. one or more brake measurement parameter values) and associated context data 202 (e.g. one or more context parameter values), to generate an output of braking performance data 201 (i.e. one or more braking performance parameter values).

The context data 202 may, itself, be determined from input data 202a, e.g.: sensor data received from one or more sensors of the vehicle; user input data received from a user; data received from at least one data source local to the vehicle, e.g., a subsystem of the vehicle; and data received from at least one remote server.

Such input data may be data sufficient to enable to determination of the differing types of context data discussed above, not least for example contexts prevailing at the time of the braking event being measured such as: a status of at least one brake assist system, a type of braking event, a frequency of braking events, load characteristics, vehicle characteristics, a road type, brake warnings, brake configuration, a vehicle manoeuvre and an operating environment.

Brake measurement data 201 and context data 202 may also be provided to the machine learning system to further train/update the trained braking performance model, thereby enabling the model to be dynamically updated based on newly captured/measured data.

FIG. 3 schematically illustrates a system 300 according to an example of the present disclosure, wherein a controller 11 (as discussed further below with respect to FIG. 4) implements at least some of the method steps described above and shown with respect to FIG. 1). The controller is in communication with: a plurality of sensors 301, from which the controller may receive brake measurement data as well as receive input data therefrom from which context data can be derived; input user interface 302a, from which the controller may receive user input data from which context data can be derived (e.g. not least information provided by a user/driver indicative of a load characteristics of the vehicle such as: mass, if load is liquid/powder/gas/solid); databases of vehicle subsystems 302(b), from which the controller may receive input data from which context data can be derived (e.g., not least information and identification of the brakes, braking system and vehicle); and remote servers/external sources of data 302c, from which the controller may receive input data from which context data can be derived (e.g. not least information indicative of a load characteristics of the vehicle such as: mass, if load is liquid/powder/gas/solid).

The controller may be directly or indirectly in communication with the above. Such communication may be wired or wireless and may involve a wireless communication network such as a cellular network.

The controller receives brake measurement data from sensors and input data from the sensors and other data sources mentioned above and determines context data therefrom. The brake measurement data and context data are applied to the trained braking performance model, from which braking performance data is generated indicative of an effectiveness of the brakes. The braking performance data may be output via an output user interface 307 and/or it may be transmitted to a remote server (e.g., a remote EPBMS server of an EPBMS service provider, the vehicle operator or a vehicle fleet manager).

The controller may also be in communication with a database of historic braking performance data 306, which newly calculated braking performance data can be added to. Furthermore, the historic braking performance data can be utilised along with newly calculated braking performance data to determine braking degradation data indicative of at least one braking degradation parameter value which can be used to estimate a time when a brake service/maintenance ought to be scheduled.

In some examples, the system 300 is built into the vehicle itself, e.g., integrated into the vehicle's ESMBP and/or provided as one or more devices/modules located on the vehicle (such a vehicle including both a tractor along as well as a tractor in combination with a connected trailer). It should be noted that the elements and devices of the system need not be mandatory and thus some can be omitted in certain examples of the present disclosure, or provided remotely of the system.

In some examples, the system 300 is distributed over several devices, which may be separate from one another. For example, certain of the components may not be local to the controller, e.g., one or more of the databases, interfaces, model and sensors may be remote of the controller and may reside at a remote location. In some examples, some of the sensors may not be located on the tractor and may be located on a trailer.

Various, but not necessarily all, examples of the present disclosure provide both a method and corresponding apparatus and system comprising various modules, means or circuitry that provide the functionality for performing/applying the actions of the method. The modules, means or circuitry can be implemented as hardware, or can be implemented as software or firmware to be performed by a computer processor. In the case of firmware or software, examples of the present disclosure can be provided as a computer program product including a computer readable storage structure embodying computer program instructions (i.e., the software or firmware) thereon for performing by the computer processor.

FIG. 4 schematically illustrates a block diagram of an apparatus 10 for performing the methods, processes, procedures and signalling described in the present disclosure and also as illustrated in FIGs. 1 and 6 -9. The component blocks of FIG. 4 are functional and the functions described may or may not be performed by a single physical entity.

The apparatus comprises a controller 11, which can be embodied by a computing device that can be provided within a vehicle or can be provided in a remote server.

In some, but not necessarily all examples, the apparatus can be embodied as a chip, chip set or module, i.e. for use in any of the foregoing. As used here 'module' refers to a unit or apparatus that excludes certain parts/components that would be added by an end manufacturer or a user.

Implementation of the controller 11 may be as controller circuitry. The controller 11 may be implemented in hardware alone, have certain aspects in software including firmware alone or can be a combination of hardware and software (including firmware).

The controller 11 may be implemented using instructions that enable hardware functionality, for example, by using executable instructions of a computer program 14 in a general-purpose or special-purpose processor 12 that may be stored on a computer readable storage medium 13, for example memory, or disk etc, to be executed by such a processor 12.

The processor 12 is configured to read from and write to the memory 13. The processor 12 may also comprise an output interface via which data and/or commands are output by the processor 12 and an input interface via which data and/or commands are input to the processor 12. The apparatus may be coupled to or comprise one or more other components 15 (not least for example: a radio transceiver, sensors, input/output user interface elements and/or other modules/devices/components for inputting and outputting data/commands).

The memory 13 stores a computer program 14 comprising computer program instructions (computer program code) that controls the operation of the apparatus 10 when loaded into the processor 12. The computer program instructions, of the computer program 14, provide the logic and routines that enables the apparatus to perform the methods, processes and procedures described in the present disclosure and illustrated in FIGs.1 and 6 -9. The processor 12, by reading the memory 13, is able to load and execute the computer program 14.

Although the memory 13 is illustrated as a single component/circuitry it may be implemented as one or more separate components/circuitry some or all of which may be integrated/removable and/or may provide permanent/semi-permanent/ dynamic/cached storage.

Although the processor 12 is illustrated as a single component/circuitry it may be implemented as one or more separate components/circuitry some or all of which may be integrated/removable. The processor 12 may be a single core or multi-core processor.

The apparatus may include one or more components for effecting the methods, processes and procedures described in the present disclosure and illustrated in FIGs.

1 and 6 -9. It is contemplated that the functions of these components can be combined in one or more components or performed by other components of equivalent functionality. The description of a function should additionally be considered to also disclose any means suitable for performing that function. Where a structural feature has been described, it can be replaced by means for performing one or more of the functions of the structural feature whether that function or those functions are explicitly or implicitly described.

Although examples of the apparatus have been described above in terms of comprising various components, it should be understood that the components can be embodied as or otherwise controlled by a corresponding controller or circuitry such as one or more processing elements or processors of the apparatus. In this regard, each of the components described above can be one or more of any device, means or circuitry embodied in hardware, software or a combination of hardware and software that is configured to perform the corresponding functions of the respective components as described above.

The apparatus can, for example, be a client device, a server device, a wireless communications device, a hand-portable electronic device. The apparatus can be embodied by a computing device, not least such as those mentioned above. However, in some examples, the apparatus can be embodied as a chip, chip set or module, i.e., for use in any of the foregoing.

In some examples, the apparatus 10 comprises: at least one processor 12; and at least one memory 13 including computer program code the at least one memory 13 and the computer program code configured to, with the at least one processor 12, cause the apparatus at least to perform: receiving, from at least one sensor, brake measurement data indicative of at least one value of at least one brake measurement parameter for at least one brake event of at least one brake of at least one braking system of at least one vehicle; determining, based at least in part on received input data, context data associated with the brake measurement data, wherein the context data is indicative of at least one value of at least one context parameter for the at least one brake event; determining braking performance data indicative of at least one value of at least one braking performance parameter for the least one brake; wherein the braking performance data is determined by inputting the brake measurement data and the associated context data into a trained braking performance model; and wherein the trained braking performance model is a model that has been generated via at least one machine learning system and configured to: receive, as an input, data indicative of one or more brake measurement parameter values and data indicative of associated one or more context parameter values, and output data indicative of one or more braking performance parameter values for the same.

The above-described examples find application as enabling components of: tracking systems, automotive systems; telecommunication systems; electronic systems; navigation systems; and related software and services.

of the present disclosure regardless of their intent to provide mobility.

FIG. 5, illustrates a computer program 14. The computer program may arrive at the apparatus 10 via any suitable delivery mechanism 20. The delivery mechanism 20 may be, for example, a machine-readable medium, a computer-readable medium, a non-transitory computer-readable storage medium, a computer program product, a memory device, a solid-state memory, a record medium such as a USB memory stick, Compact Disc Read-Only Memory (CD-ROM) or a Digital Versatile Disc (DVD) or an article of manufacture that comprises or tangibly embodies the computer program 14. The delivery mechanism may be a signal configured to reliably transfer the computer program. The apparatus 10 may receive, propagate or transmit the computer program as a computer data signal.

In certain examples of the present disclosure, there is provided computer program instructions for causing an apparatus to perform at least the following or for causing performing at least the following: receiving, from at least one sensor, brake measurement data indicative of at least one value of at least one brake measurement parameter for at least one brake event of at least one brake of at least one braking system of at least one vehicle; determining, based at least in part on received input data, context data associated with the brake measurement data, wherein the context data is indicative of at least one value of at least one context parameter for the at least one brake event; determining braking performance data indicative of at least one value of at least one braking performance parameter for the least one brake; wherein the braking performance data is determined by inputting the brake measurement data and the associated context data into a trained braking performance model; and wherein the trained braking performance model is a model that has been generated via at least one machine learning system and configured to: receive, as an input, data indicative of one or more brake measurement parameter values and data indicative of associated one or more context parameter values, and output data indicative of one or more braking performance parameter values for the same.

References to 'computer program', 'computer-readable storage medium', 'computer program product', 'tangibly embodied computer program' etc. or a 'controller', computer', 'processor' etc. should be understood to encompass not only computers having different architectures such as single /multi-processor architectures and sequential (Von Neumann)/parallel architectures but also specialized circuits such as field-programmable gate arrays (FPGA), application specific circuits (ASIC), signal processing devices and other devices. References to computer program, instructions, code etc. should be understood to encompass software for a programmable processor or firmware such as, for example, the programmable content of a hardware device whether instructions for a processor, or configuration settings for a fixed-function device, gate array or programmable logic device etc. Figure 6 illustrates a flow chart 600 of an example of an Electronic System for Monitoring Braking Performance (ESMBP) according to the present disclosure.

In block 601, following a detection of a trigger event, ESMBP performance data is collected, wherein the ESMBP performance data comprises brake measurement data and input data for determining context data associated with the brake measurement data (i.e., the current context/conditions/status at the time the brake measurements were made). In some examples, the trigger event/start trigger event may be based at least in part on brake pressure, e.g., a determination of a measured brake pressure exceeding a predetermined threshold brake pressure. The trigger event may also depend on contextual data and other conditions (such as speed and a time period since a previous brake event) and a determination of value of the same crossing a predetermined threshold value. In some examples, the trigger event may be based on an activity status (or a change in state) of: ABS, VOC, warning lights and/or brake warning indicators.

In block 602, sensor data from sensors of a vehicle (e.g., a tractor) and sensors of connected units, i.e., another vehicle connected to the vehicle (e.g., one or more towing units or trailers connected to the tractor), is collected. This is discussed further below in FIG. 7.

Such data is continued to be collected until a stop condition is determined in block 603. In some examples, the stop condition/stop trigger is based at least in part on the brake pressure, e.g., a determination of a measured brake pressure crossing a predetermined threshold brake pressure. The stop condition may also depend on contextual data and other conditions (such as speed, and duration of a braking event) and a determination of value of the same crossing a predetermined threshold value.

In block 604, the collected data is then aggregated, filtered and fused together, optionally along with data collected from external sources in block 605. The external sources are discussed further below in FIG. 8. In some examples, data from different sources is aggregated together based on a time associated with the data (e.g. a time when the data was created, sensed or measured). In some examples, at least part of the data or features of some of the data can be fused together to increase accuracy or correct or derive missing values. In some examples, at least part of the data can be sampled to reduce data size. In some examples, at least part of the data can be oversampled on multiple time-windows. In some examples, invalid data may be filtered out if features of the data do not satisfy predefined functions.

In block 606, the aggregated, filtered and fused data (and optionally the data collected from external sources) is used to update a trained braking performance model for generating braking performance data, such a model being locally stored on the vehicle. The aggregated, filtered and fused data may also be used to update the model for generating brake degradation data. This is discussed further below in FIG. 9. In some examples, a trained model can be updated with new data, if certain conditions are satisfied. In some examples, the trained model might have to be reconstructed if certain conditions are not met. In some examples, the model to be trained requires to have adequate data, and features must have satisfactory distribution. In some examples, predictions and estimates of the ESMBP are updated, including brake performance and time to next maintenance.

In optional block 607, following the update of the model, a brake performance interface may be likewise updated. In some examples the brake performance interface can output and visualise wide range of indicators that can be updated, not least such as: brake performance status, historical brake performance, brake status, future maintenance prediction, accuracy, precision and confidence of predictions, status of related systems and related indicators, and contextual data that can affect the performance.

In some examples, data, such as parameter values, representative of the above indicators may be re-calculated following the updating of the model and the brake performance interface may be updated to present the updated data/parameter values.

In block 608, historical data of the ESMBP may be updated and visualised, e.g., to output/visualise the historical and live braking performance data.

In block 609, reports and alerts may be generated for users, not least such as vehicle operators/fleet managers.

In block 610, the aggregated, filtered and fused data (and optionally the data collected from external sources) is sent to a central system or the Cloud, i.e., a remote server.

In block 611, a model stored at the remote server for determining brake performance data and brake degradation data may be updated based on the received data. This is discussed further below in FIG. 9.

In optional block 612, the data may be synchronised with telematics units. In some examples, submodules of the ESMBP might have to be updated on telematics units, e.g., with regards to data aggregation, data pre-processing, and training model.

Figure 7 schematically illustrates the collection of sensor data 602 from a vehicle, and also optionally a connected vehicle -e.g., a tractor and a connected trailer, used for determining braking measurement data.

A controller (not shown) listens for sensor data from plural differing sensors 301 or queries the sensors 301 to request sensor data. In such a manner, the collection of sensor data may involve the data being pushed from the sensors or pulled from the sensors for receipt by the controller.

The sensors may include one or more of: Telematics unit sensors, e.g., for continuously capturing brake data (such as acceleration/deceleration, retardation force of the vehicle before/during/after a braking event), as well as capturing data relating to: fuel used, travelled distance, speed, location and other telematics data; Vehicle sensors, e.g. brake sensors detecting a demand for braking (e.g. application of one or more brakes of a braking system of the vehicle), a duration magnitude of the brake event; Connected telematics units, i.e. telematics units of a connected vehicle (e.g a trailer connected to a tractor); and Connected vehicle's sensors.

Optionally, the collected sensor data may be pre-processed, e.g., aggregated, filtered and fused, before being used such as: applying the data to a trained braking performance model to determine braking performance data; updating/further training the braking performance model; and/or sending to data to a remote server (for the remote server to use its trained braking performance model to determine braking performance data and/or update/further train its trained braking performance model).

Figure 8 schematically illustrates external data sources 302c that may be used for the collection of external data 605. i.e., collection of input data from which context data may be derived.

A controller (not shown) may query/request/pull data from plural external data sources, i.e., external of the vehicle and its ESMBP.

The data from external sources may include one or more of: weather data; vehicle metadata, i.e., data which summarises vehicle characteristics, such as: vehicle make, model and series, trailer type, number of axles, towing status, brake model and connected trailers; linked unit/vehicles' telematics data, e.g., data from other telematics units such as sensor data and submodule data of the ESMBP; vehicle's maintenance failure data, e.g., data indicative of historical maintenance (such as brake maintenance), other vehicle related maintenance data, historical scheduled and unscheduled maintenance reports (such as, but not exclusively, braking systems maintenance) which could relay information about the current status of the systems under test; and other vehicle diagnostic data, e.g., data from vehicle diagnostic systems (such as Diagnostic Trouble Codes (DTCs)), data from third party diagnostic software (such as diagnostic modules on a telematics unit), and proprietary diagnostic data from a brake.

Figure 9 schematically illustrates further steps in the updating of a braking performance and a braking degradation model for determining data indicative of braking efficiency and predicting a service/maintenance schedule.

In block 701, a controller (not shown), e.g., provided in the vehicle or at a remote server, receives new observations, e.g., brake measurement data and context data.

In block 702, the data is are validated and filtered to remove any extraneous/outing data. In some examples, data range, distributions and correlation are validated against a set of criteria and invalid data are discarded.

In block 703, the resulting data is then used to update the trained braking performance model, e.g., in a manner similar to that of block 606.

In block 704, the data is also used to update the algorithms used to predict braking degradation. In some examples, hyper-parameters used for the prediction of the brake performance are updated which enables updated predictions and estimates of an ESMBP, including brake performance and time to next maintenance, to be determined.

In block 705, the predictions are validated. In some examples, a prediction is validated if it is calculated with acceptable confidence and/or over a suitable period of time and using sufficient data. A check may also be made as to whether there are is a significant change as to compared with historical predictions or acceptable operating conditions.

In block 706, a decision is made, e.g., based on the results of the validation, as to whether a recalibration is required.

In block 707, if a recalibration is required, hyperparameters may be configured and adjusted and fed into the model to update the model and blocks 703 -706 are repeated. In some examples, when recalibration is required, configuration and hyperparameters are re-configured based on a predefined function. This can involve a machine learning model that derives optimal or good configuration and hyperparameters. Hyperparameters are configurations of a model which can be tuned with the purpose of improving the predictive accuracy and cannot be estimated from the data.

In block 708, if no recalibration is required the predictions and related statistics are updated, then the decision support system is updated accordingly.

Although specific terms are employed herein, they are used in a generic and descriptive sense only and not for purposes of limitation.

Features described in the preceding description can be used in combinations other than the combinations explicitly described.

Although functions have been described with reference to certain features, those functions can be performable by other features whether described or not.

Although features have been described with reference to certain examples, those features can also be present in other examples whether described or not. Accordingly, features described in relation to one example/aspect of the disclosure can include any or all of the features described in relation to another example/aspect of the disclosure, and vice versa, to the extent that they are not mutually inconsistent.

Although various examples of the present disclosure have been described in the preceding paragraphs, it should be appreciated that modifications to the examples given can be made without departing from the scope of the invention as set out in the claims.

The term 'comprise' is used in this document with an inclusive not an exclusive meaning. That is any reference to X comprising Y indicates that X can comprise only one V or can comprise more than one Y. If it is intended to use 'comprise' with an exclusive meaning then it will be made clear in the context by referring to "comprising only one..," or by using "consisting".

In this description, the wording 'connect', 'couple' and 'communication' and their derivatives mean operationally connected/coupled/in communication. It should be appreciated that any number or combination of intervening components can exist (including no intervening components), i.e., so as to provide direct or indirect connection/coupling/communication. Any such intervening components can include hardware and/or software components.

As used herein, the term "determine/determining" (and grammatical variants thereof) can include, not least: calculating, computing, processing, deriving, measuring, investigating, looking up (for example, looking up in a table, a database or another data structure), ascertaining and the like. Also, "determining" can include receiving (for example, receiving information), accessing (for example, accessing data in a memory), obtaining and the like. Also, " determine/determining" can include resolving, selecting, choosing, establishing, and the like.

References to a parameter/information (for example braking performance parameter/braking performance information, context parameter/context information, brake degradation parameter/brake degradation information) can be replaced by references to "data indicative of', "data defining" or "data representative of" the relevant parameter/information if not explicitly stated.

In this description, reference has been made to various examples. The description of features or functions in relation to an example indicates that those features or functions are present in that example. The use of the term 'example' or 'for example', 'can' or may' in the text denotes, whether explicitly stated or not, that such features or functions are present in at least the described example, whether described as an example or not, and that they can be, but are not necessarily, present in some or all other examples. Thus 'example', 'for example', 'can' or 'may' refers to a particular instance in a class of examples. A property of the instance can be a property of only that instance or a property of the class or a property of a sub-class of the class that includes some but not all of the instances in the class.

In this description, references to "a/an/the" [feature, element, component, means...] are to be interpreted as "at least one" [feature, element, component, means...] unless explicitly stated otherwise. That is any reference to X comprising a/the Y indicates that X can comprise only one Y or can comprise more than one Y unless the context clearly indicates the contrary. If it is intended to use 'a' or 'the' with an exclusive meaning then it will be made clear in the context. In some circumstances the use of at least one' or 'one or more' can be used to emphasise an inclusive meaning but the absence of these terms should not be taken to infer any exclusive meaning.

The presence of a feature (or combination of features) in a claim is a reference to that feature (or combination of features) itself and also to features that achieve substantially the same technical effect (equivalent features). The equivalent features include, for example, features that are variants and achieve substantially the same result in substantially the same way. The equivalent features include, for example, features that perform substantially the same function, in substantially the same way to achieve substantially the same result.

In this description, reference has been made to various examples using adjectives or adjectival phrases to describe characteristics of the examples. Such a description of a characteristic in relation to an example indicates that the characteristic is present in some examples exactly as described and is present in other examples substantially as described.

Whilst endeavouring in the foregoing specification to draw attention to those features of examples of the present disclosure believed to be of particular importance it should be understood that the applicant claims protection in respect of any patentable feature or combination of features hereinbefore referred to and/or shown in the drawings whether or not particular emphasis has been placed thereon.

The examples of the present disclosure and the accompanying claims can be suitably combined in any manner apparent to one of ordinary skill in the art.

Each and every claim is incorporated as further disclosure into the specification and the claims are embodiment(s) of the present invention. Further, while the claims herein are provided as comprising specific dependencies, it is contemplated that any claims can depend from any other claims and that to the extent that any alternative embodiments can result from combining, integrating, and/or omitting features of the various claims and/or changing dependencies of claims, any such alternative embodiments and their equivalents are also within the scope of the disclosure.

Claims

CLAIMSWe claim: 1. A computer implemented method for use in an electronic system for monitoring braking performance for a braking system of a vehicle, the method comprising causing, at least in part, actions that result in: receiving, from at least one sensor, brake measurement data indicative of at least one value of at least one brake measurement parameter for at least one brake event of at least one brake of at least one braking system of at least one vehicle; determining, based at least in part on received input data, context data associated with the brake measurement data, wherein the context data is indicative of at least one value of at least one context parameter for the at least one brake event; determining braking performance data indicative of at least one value of at least one braking performance parameter for the least one brake; wherein the braking performance data is determined by inputting the brake measurement data and the associated context data into a trained braking performance model; and wherein the trained braking performance model is a model that has been generated via at least one machine learning system and configured to: receive, as an input, data indicative of one or more brake measurement parameter values and data indicative of associated one or more context parameter values, and output data indicative of one or more braking performance parameter values for the same.
2. The method of any previous claim, wherein the brake measurement data comprises data indicative of one or more of: at least one braking event; at least one application of the at least one brake; a braking demand; and a deceleration of the at least one vehicle.
3. The method of any previous claim, wherein the input data comprises one or more of: sensor data received from one or more sensors of the vehicle; user input data received from a user; data received from at least one data source local to the vehicle and data received from at least one remote server.
4. The method of any previous claim, wherein the trained braking performance model has been trained on at least one training dataset comprising data indicative of a plurality of brake measurement parameter values and associated context parameter values for a plurality of brake events whose brake performance parameter values have been pre-determined.
5. The method of any previous claim, wherein the trained braking performance model has been generated via the at least one machine learning system and trained on at least one training dataset to determine one or more correlations between: brake measurement parameter values; context parameter values; and braking performance parameter values.
6. The method of any previous claim, further comprising: determining whether the braking performance parameter value crosses a predetermined threshold value; generating an alert based on a determination that the braking performance parameter value crosses the predetermined threshold value.
7. The method of any previous claim, further comprising: updating the trained braking performance model based at least in part on the brake measurement data and the context data.
8. The method of any previous claim, further comprising: determining, based at least in part on the braking performance data, braking degradation data indicative of at least one braking degradation parameter value.
9. The method of claim 8, further comprising: determining, based at least in part on the braking degradation data, brake maintenance schedule data indicative of a time to service the at least one brake.
10. The method of claim 9, further comprising: generating at least one notification comprising the time to service the at least one brake.
11. The method of any previous claim, further comprising: sending the brake measurement data and/or the context data to at least one server to enable the at least one server to, at least one of: determine the braking performance data using the trained brake performance model; and further train the brake performance model.
12. The method of claim 11, further comprising, prior to sending the brake measurement data and/or the context data to the server, one or more of: filtering the brake measurement data and/or the context data; transforming the brake measurement data and/or the context data; and amalgamating the brake measurement data and/or the context data
13. The method of any previous claim, wherein the context data comprises data indicative of at least one status of at least one brake assist system.
14. The method of claim 13, wherein the brake assist system comprises one or more of: Vehicle Dynamic Control, Electronic Stability Control, Engine Brake, Exhaust Brake, and turn-brake assist brakes.
15. The method of any previous claim, wherein the context data comprises data indicative of one or more of: at least one type of braking event; and at least one frequency of braking events.
16. The method of any previous claim, wherein the context data comprises data indicative of one or more of: load characteristics; a type of load; and vehicle characteristics.
17. The method of any previous claim, wherein the context data comprises data indicative of at least one road type.
18. The method of any previous claim, wherein the context data comprises data indicative of at least one status of brake warnings for the at least one braking system.
19. The method of any previous claim, wherein the context data comprises data indicative of one or more of: brake firmware of the at least one brake; and brake configuration of the braking system.
20. The method of any previous claim, wherein the context data comprises data indicative of one or more of: a manoeuvre of the vehicle, and an operating environment of the vehicle.
21. The method of any previous claim, wherein determining braking performance data comprises determining braking performance data indicative of one or more of: at least one braking performance parameter value for each individual brake of the at least one braking system; at least one braking performance parameter value for one or more brakes of an individual axle; at least one braking performance parameter value for at least some or all brakes of the at least one braking system; at least one braking performance parameter value for each individual brake or all brakes of a tractor's braking system; and at least one braking performance parameter value for each individual brake or all brakes of a trailer's braking system.
22. An apparatus comprising means configured to perform the method of any one or more of the previous claims.
23. A vehicle or server comprising the apparatus of claim 22.
24. A system comprising means configured to perform the method of any one or more of the previous claims.
25. Computer program instructions for causing an apparatus to perform the method as claimed in any of claims 1 -20