SE548228C2 - Method and computer system for isolating a location of an error within a connectivity assembly - Google Patents

Abstract

The present disclosure generally relates to a computer implemented method for isolating an error within a connectivity assembly (202). This in line with the present disclosure achieved by performing a series of evaluations conducted at evaluation points that depends on the type of the connectivity assembly (202) in combination with results of performed evaluations. The scheme according to the present disclosure is useful in many different technical areas, for example applicable for identifying a location of an error within a wire harness. The present disclosure also relates to a corresponding computer system and a computer program product.

Description

[0001] The present disclosure generally relates to a computer implemented method for isolating an error within a connectivity assembly. This in line with the present disclosure achieved by performing a series of evaluations conducted at evaluation points that depends on the type of the connectivity assembly in combination with results of performed evaluations. The scheme according to the present disclosure is useful in many different technical areas, for example applicable for identifying a location of an error within a a wire harness. The present disclosure also relates to a corresponding computer system and a computer program product.

[0003] BACKGROUND

[0004] Recent advancements in technology have greatly enhanced the capability to diagnose and troubleshoot issues within complex systems such as electrical networks in vehicles. Traditionally, identifying and resolving errors in these systems has been a timeconsuming and expertise-intensive process. The reliance on manual diagnosis, often based on intuition and experience, can lead to inefficiencies and inaccuracies.

[0005] The complexity of modem vehicle electrical systems, with their intricate network of components and connections, exacerbates these challenges. Current methodologies, while advanced, still often fall short in swiftly and accurately pinpointing errors, leading to extended downtime and increased costs. Furthermore, the conventional diagnostic tools and methods may not be sufficiently equipped to handle the dynamic and interconnected nature of modem vehicle electrical systems, necessitating a more systematic and data-driven approach.

[0006] An example of a solution trying to overcome the above identified problem is presented in US7096101. In US7096101, vehicle diagnosis data is collected and transmitted to an external service center, where personnel at the service center may be able to provide additional assistance as compared to what is achievable at normal auto body and auto maintenance facilities. Even though US7096101 provides some improvements as compared to allowing the workshop operators to act on their own, the of the large amount of vehicle analysis data generated during e.g. operation of the vehicle will in reality be to complex also for the personnel at the service center to comprehend. Thus, the personnel at the service center will have to resort to provide the workshop operators with a "best guess", typically only based on gut feeling and previous knowledge of similar problems.

[0007] Accordingly, there remains a need for advancements in the methodologies employed to guide users, such as technicians, through complex diagnostic tasks. Such advancements would ideally enable users to conduct these tasks more effectively, relying on a systematic approach that minimizes guesswork and minimized the time spend for locating e.g. an error when performing a diagnostic task.

[0009] SUMMARY

[0010] According to another aspect of the present disclosure there is provided a computer system as defined by claim 1.

[0011] In line with the present disclosure, the process begins with the identification of the connectivity assembly type, a desirable step that may be used for targeted and efficient fault isolation. This identification is in line with the present disclosure used for the selection of measurement points, ensuring they are optimally chosen based on the specific characteristics and complexities of the connectivity assembly in question.

[0012] The subsequent selection and execution of measurements at these strategic points ensures that the effectiveness of the scheme according to the present disclosure can be used to provide an in comparison high level of reliability of the error isolation. By performing a series of measurements, each informed by the outcome of the previous one, the scheme systematically narrows down the potential locations of the error. This approach offers a significant advantage over more traditional methods. Once progress through the connectivity assembly, the isolation of the error location is achieved through the careful analysis and synthesis of data obtained from the measurements. The scheme according to the present disclosure not only streamlines the diagnostic process but also enhances the precision with which errors are located within the connectivity assembly. Such precision is particularly vital in systems where the connectivity assembly plays a critical role, ensuring that repairs and maintenance are carried out with the highest degree of accuracy and efficiency.

[0013] In one embodiment of the present disclosure, the isolation of the error location is further based on the type of the connectivity assembly. The inclusion of the connectivity assembly type as a determinant in the isolation process enhances the method’s precision. This approach acknowledges the diversity of connectivity assemblies, each with its unique configuration and potential fault areas. By integrating the type of the connectivity assembly into the decision-making process for isolating the error, the scheme of the present disclosure becomes more adaptive and responsive to the specific characteristics of the assembly in question.

[0014] By implementation of this embodiment, it is possible to augments the diagnostic process by aligning the selection of measurement points and the interpretation of measurement results more closely with the inherent properties of the connectivity assembly. Such an approach ensures that the error localization is not only systematic but also deeply informed by the nuances of the specific assembly being examined, leading to more accurate and efficient diagnostics.

[0015] Preferably, the step of identifying the type of the connectivity assembly comprises the steps of acquiring an image of the connectivity assembly, applying an image processing scheme to the acquired image to extract identifiable features of the connectivity assembly, and determining the type of the connectivity assembly based on the extracted identifiable features.

[0016] As indicated, the acquired image of the connectivity assembly is provided to a sophisticated image processing scheme, where the focus is on extracting identifiable features from the image. These features, which can vary from physical dimensions and color patterns to more intricate details such as connector types or wire arrangements, are subsequently used in determining the specific type of the connectivity assembly.

[0017] The effectiveness of this embodiment is connected to its ability to transform visual information into actionable data, thereby adding a layer of detail that might be elusive in traditional diagnostic methods. By extracting and analyzing these features, it is made possible to provide a comprehensive understanding of the connectivity assembly, which is useful for accurate error isolation with high precision. This precision is particularly advantageous in intricate systems, where even minor errors can lead to significant operational challenges.

[0018] Within the context of the present disclosure, the image of the connectivity assembly may for example be acquired using one or a plurality of many different sensor systems. Examples of such sensor systems that may for example include an image capturing device (e.g. a camera), a Lidar, a radar, a laser scanner, a heat sensor, sensors for Timedomain reflectometry measurements. Other sensors systems, present and future, are of course possible and within the scope of the present disclosure. It may of course be possible to combine more than one sensor with the object capturing device, such for example an image capturing device and a Lidar.

[0019] Preferably, the image processing scheme employed in according to one embodiment of the present disclosure includes a machine learning component, which is pretrained on a diverse array of connectivity assembly types. This training equips the machine learning component to efficiently and accurately recognize a wide range of connectivity assemblies based on their visual characteristics.

[0020] The application of a machine learning-based image processing scheme in this embodiment significantly enhances the overall effectiveness of the error isolation methodology according to the present disclosure. By being pre-trained on various types of connectivity assemblies, the machine learning component rapidly identifies the assembly type, streamlining the error isolation process. This pre-training means the scheme does not require individual training for each computer system it is implemented on, but rather benefits from a generalized, comprehensive training approach developed in advance.

[0021] In some embodiments, this machine learning component might be executed as a supervised learning process. In such cases, it allows for operator or user intervention, enabling corrections in the recognition process based on operator feedback. This supervised aspect can be particularly useful during the initial implementation stages of the image processing scheme. Conversely, implementing the machine learning component as an unsupervised process allows for complete autonomy in identification and decision-making, making the scheme highly efficient and reducing the need for human intervention. A hybrid approach, combining both supervised and unsupervised learning, can also be employed, offering flexibility and adaptability in different stages of the machine learning scheme’s implementation. This machine learning approach, whether supervised, unsupervised, or a combination of both, represents a significant advancement over traditional image processing methods. By leveraging sophisticated algorithms, including neural networks and other machine learning techniques, the method offers a high level of precision and adaptability in identifying the types of connectivity assemblies, crucial for accurate and efficient error isolation.

[0022] In a further embodiment of the present disclosure, the method for isolating an error within a connectivity assembly, such as a wire harness, integrates the use of Time-Domain Reflectometry (TDR) in at least one of the measurements. TDR is a well-established technique used for identifying faults in electrical lines by sending a signal along the conductor and observing the reflected signal.

[0023] The incorporation of TDR measurements in this method is particularly advantageous for pinpointing faults within complex connectivity assemblies. When performing a measurement at a selected point in the assembly, TDR can provide valuable insights into the condition of the conductor, such as breaks or imperfections, by analyzing the characteristics of the reflected signal. This signal reflection is influenced by changes in the conductor’s impedance, which can indicate the presence and location of faults. In the context of the method, applying TDR at the first measurement point provides an initial assessment of the wire harness. Based on the results of this TDR measurement, which include details like the distance to a fault from the measurement point, the method then guides the selection of a subsequent measurement point. This systematic approach allows for a more focused and efficient error isolation process.

[0024] The use of TDR is particularly beneficial in systems where the wire harness is lengthy or has a complex routing, as it enables the identification of faults that might be challenging to locate through visual inspection or other traditional methods. By leveraging TDR’s precise fault localization capabilities, the method enhances the accuracy and efficiency of the diagnostic process, ensuring more reliable maintenance and repair of the connectivity assembly.

[0025] However, it should be understood that also other, alternative measurement techniques are possible and within the scope of the present disclosure. Such alternative measurement techniques could for example include voltage drop measurements, which can detect resistance changes indicating faults, and insulation resistance testing, useful for identifying degradations or breaches in insulation. Additionally, capacitance measurements may be employed to detect changes in the electrical properties of the wire harness, indicative of issues like moisture ingress or insulation deterioration.

[0026] Other techniques might encompass the use of electromagnetic field analysis, beneficial in detecting discontinuities in the wire’s conductive path, or the application of acoustic emission testing, where sound waves produced by defects or stresses in the wire harness are analyzed. These methods, along with others like optical fiber testing for wire harnesses incorporating fiber optics, or thermal imaging to visualize and quantify temperature differences caused by faults, offer a comprehensive range of diagnostic tools. Each of these alternative measurement techniques brings unique advantages and can be selected based on the specific requirements of the connectivity assembly under examination. The integration of diverse measurement methods within the method ensures a versatile and comprehensive approach to error isolation in various types of connectivity assemblies, enhancing the method’s applicability and effectiveness in a wide range of scenarios.

[0027] In another embodiment of this disclosure, the method for isolating an error within a connectivity assembly is further refined by incorporating the identification of an electrical component connected to the assembly. This addition brings an extra dimension to the diagnostic process, enhancing its precision and relevance. The identification of the connected electrical component is a crucial step that informs the selection of the measurement points. Understanding which component is connected to the assembly allows for a more targeted approach in choosing the measurement points, as different components can impact the connectivity assembly in various ways. This could include considering the electrical characteristics of the component, such as its resistance, capacitance, or inductance, which might influence where potential faults are most likely to occur.

[0028] For instance, if a high-power component is connected to the assembly, the method might prioritize measurement points that are more prone to heat-induced damage or wear. Alternatively, if a sensitive signal-processing component is involved, the method might focus on points where signal integrity issues are more likely to arise.

[0029] By taking into account the specific electrical components connected to the connectivity assembly, the method becomes more adaptive and tailored to the actual operational context of the assembly. This leads to a more efficient and accurate diagnostic process, as the measurement points are selected based on a comprehensive understanding of the assembly’s real-world functioning. Accordingly, the inclusion of this step enhances the method’s applicability in complex systems, where multiple components with varying electrical characteristics interact with the connectivity assembly. It ensures that the error isolation process is not only systematic but also deeply informed by the specific conditions and requirements of the system being examined.

[0030] In an embodiment, the electrical component forms part of a mobile platform, and the selection of at least one of the first and the second measurement point is dependent on the type of the mobile platform. This embodiment recognizes the significance of the mobile platform’s type in influencing the characteristics and potential fault profiles of the connectivity assembly. By integrating the mobile platform type into the decision-making process for measurement point selection, the method tailors its approach to the specific operational and environmental conditions the platform encounters.

[0031] For instance, the connectivity assembly in a commercial vehicle, which may endure rigorous usage and varying environmental conditions, might require a different diagnostic focus compared to a connectivity assembly in a more controlled environment, like a marine vessel or an airborne vessel. The method may as such adapt its measurement point selection, accordingly, targeting areas more prone to wear, environmental stress, or specific usage patterns based on the mobile platform’s type. This tailored approach leads to more relevant and effective diagnostics, as it considers the unique stresses and demands placed on the connectivity assembly by the mobile platform. It ensures that the error isolation process is not only systematic but also contextually informed, enhancing the accuracy and reliability of the diagnostics.

[0032] In a further embodiment of the present disclosure, the method addresses the isolation of specific types of errors within a connectivity assembly. These errors include any form of electrical failures, such as for example but are not limited to a short-circuit within the connectivity assembly, a broken connection within the connectivity assembly, and corrosion in a connector comprised within the connectivity assembly. Each of these errors presents unique challenges and can have significant impacts on the functionality and reliability of the connectivity assembly.

[0033] A short-circuit, for example, can lead to power loss or damage to connected components and requires precise localization to prevent potential system failures. The method’s systematic approach to measurement and analysis is particularly adept at identifying the location of such faults, even in complex wire harness configurations.

[0034] Similarly, addressing a broken connection within the connectivity assembly is crucial for maintaining the integrity of the electrical system. The method’s focused measurements at strategically chosen points enable the detection of discontinuities or breaks in the connectivity path, facilitating timely repairs and avoiding further complications.

[0035] Corrosion in connectors, another common issue, particularly in environments with moisture or chemical exposure, can degrade the connectivity and signal quality. The method’s capability to pinpoint the exact location of such corrosion through targeted measurements is a significant advantage, allowing for the restoration of optimal connectivity and preventing the spread of corrosion-related damage.

[0036] By specifically addressing these common but critical errors, the method according to the present disclosure provides a comprehensive solution for maintaining and repairing connectivity assemblies in a variety of applications. This targeted approach ensures that the most prevalent and impactful types of errors are efficiently and accurately isolated, enhancing the overall reliability and performance of the connectivity assembly.

[0037] In one possible embodiment according to the present disclosure, isolation of the error within a connectivity assembly is further enhanced by incorporating a modeling step that utilizes previously collected data. This modeling involves comparing the results of the first and second measurements with existing data for the same type of connectivity assembly, or for a connectivity assembly of a corresponding type. The integration of this comparative modeling step is a significant advancement in the diagnostic process. By referencing previously collected data, the method leverages historical insights and patterns, which can provide a more informed basis for isolating the error location. This historical data may include measurements from similar connectivity assemblies under various conditions, offering a rich repository of information that can be crucial in accurately identifying the error’s location.

[0038] For example, if a particular type of wire harness in a specific vehicle model has shown a tendency for certain errors at specific points, this information can be invaluable. The method uses such data to refme its analysis of current measurements, making the process of isolating the error more precise and efficient. This approach is particularly beneficial when dealing with complex or recurrent issues, where patterns from past instances can provide crucial clues for current diagnostics. Furthermore, the method’s ability to draw upon a diverse range of historical data means that it can adapt to a wide variety of connectivity assemblies and error types. This adaptability ensures that the method remains effective across different scenarios, continually enhancing its diagnostic capabilities as more data becomes available. Also, by incorporating modeling with previously collected data, the method not only becomes more robust in its error isolation capabilities but also evolves with each application, constantly improving its accuracy and reliability for future diagnostics.

[0039] Preferably, the modeling comprises applying a machine learning process to the selected portion of the different sets of data comprised with the first collection of vehicle diagnosis data. The utilization of a machine learning process in this context allows for a more nuanced and dynamic analysis of the collected data. By applying advanced algorithms and computational techniques, the machine learning process can identify patterns and correlations within the data that may not be immediately apparent through conventional analysis methods. This capability is particularly beneficial in dealing with complex connectivity assemblies where the error symptoms might be subtle or influenced by multiple factors.

[0040] The machine learning process may for example be adapted to handle large sets of data and extracting meaningful insights, which are crucial in accurately isolating the error location. For instance, it can determine subtle variations in measurement data that indicate specific types of faults, or it can track gradual changes over time that point to emerging issues. Moreover, the adaptability of the machine learning process means that the method can continually improve its diagnostic accuracy. As more data is collected and analyzed over time, the machine learning model can be refined and adjusted, increasing its effectiveness in isolating errors within various types of connectivity assemblies.

[0041] According to a further aspect of the present disclosure, there is provided a computer system adapted to isolate a location of an error within a connectivity assembly as defined by claim 12. Also this aspect of the present disclosure provides similar advantages as discussed above in relation to the previous aspect of the present disclosure.

[0042] For example, the control system may be used in relation to the automotive industry, for general manufacturing and/or for an assembly process.

[0043] According to an additional aspect of the present disclosure, there is provided a computer program product as defined by claim 14. Also this aspect of the present disclosure provides similar advantages as discussed above in relation to the previous aspects of the present disclosure.

[0044] A software executed by the processing unit for operation in accordance to the present disclosure may be stored on a computer readable medium, being any type of memory device, including one of a removable nonvolatile random access memory, a hard disk drive, a floppy disk, a CD-ROM, a DVD-ROM, a USB memory, an SD memory card, a solid state drive, other non-volatile flash based storage mediums, or a similar computer readable medium known in the art.

[0045] Further features of, and advantages with, the present disclosure will become apparent when studying the appended claims and the following description. The skilled addressee realize that different features of the present disclosure may be combined to create embodiments other than those described in the following, without departing from the scope of the present disclosure.

[0047] BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The various aspects of the present disclosure, including its particular features and advantages, will be readily understood from the following detailed description and the accompanying drawings, in which:

[0049] Fig. 1 conceptually illustrate a computer system according to a currently preferred embodiment of the present disclosure,

[0050] Figs. 2A and 2B exemplifies two possible implementations of the present computer system for isolating physical locations of different types of elements within different types of physical structures, and

[0051] Fig. 3 is a flow chart illustrating the steps of performing the method according to a currently preferred embodiment of the present disclosure.

[0053] DETAILED DESCRIPTION

[0054] The present disclosure will now be described more fully hereinafter with reference to the accompanying drawings, in which currently preferred embodiments of the present disclosure are shown. This present disclosure may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided for thoroughness and completeness, and fully convey the scope of the present disclosure to the skilled person. Like reference characters refer to like elements throughout. The following examples illustrate the present disclosure and are not intended to limit the same.

[0055] Turning now to the drawings and to Fig. 1 in particular, there is conceptually illustrated a computer system 100 adapted for isolating a physical location of an element within a physical structure. The computer system 100 comprises at least computing device in the form of an exemplary control unit 102 arranged as a component of a server (the server is not explicitly presented in Fig. 1).

[0056] The control unit 102 is further arranged in communication, such as using a network connection, with an object capturing device 104, evaluation equipment 106 and an output interface 108 for presenting information to a user. In some embodiments of the present disclosure, the object capturing device 104, the evaluation equipment 106 and the output interface 108 may possibly be combined into a single mobile unit to be operated by the user. It should be noted that at least some elements of the processing functionality provided by the control unit could be integrated in such mobile unit.

[0057] In Fig. 1 the object capturing device 104, such as a video camera, is presented as embedded with the output interface 108, together provide as an augmented reality (AR) headset. The AR headset preferably comprises image and audio generating devices for providing information to the user/operator wearing the headset.

[0058] For reference, the control unit may for example be manifested as a generalpurpose processor, a graphics processing unit, an application specific processor, a circuit containing processing components, a group of distributed processing components, a group of distributed computers configured for processing, a field programmable gate array (FPGA), etc. The processor may be or include any number of hardware components for conducting data, signal and/or image processing or for executing computer code stored in memory. It may also be possible and within the scope to make use of system-on-chip (SOC) implementations. The memory may be one or more devices for storing data and/or computer code for completing or facilitating the various methods described in the present description. The memory may include volatile memory or non-volatile memory. The memory may include database components, object code components, script components, or any other type of information structure for supporting the various activities of the present description.

[0059] According to an exemplary embodiment, any distributed or local memory device may be utilized with the systems and methods of this description. According to an exemplary embodiment the memory is communicably connected to the processor (e.g., via a circuit or any other wired, wireless, or network connection) and includes computer code for executing one or more processes described herein.

[0060] The evaluation equipment 106 may in some embodiments comprise e.g. a signal generator and receptor adapted to provide and to receive signals, in an exemplary but not in any way limiting embodiment being adapted for Time-Domain Reflectometry (TDR) measurements. Specifically, in the context of TDR measurements, the signal generator is configured to transmit a signal along a connectivity assembly, such as a wire harness, and the receptor is designed to capture the reflected signal. The TDR technique involves analyzing these reflections to determine the location of faults, such as discontinuities or impedance changes, within the connectivity assembly. The precision and effectiveness of TDR in isolating faults, particularly in complex wire harnesses, make it an invaluable tool in the diagnostic process.

[0061] In addition to TDR, the evaluation equipment 106 can be adapted for a range of other diagnostic techniques. These may include, but are not limited to, electrical impedance spectroscopy, voltage drop testing, or continuity testing, each providing unique insights into the health and integrity of the connectivity assembly. The versatility of the evaluation equipment 106 lies in its ability to be configured or equipped with various sensors and modules, making it suitable for a broad spectrum of diagnostic scenarios.

[0062] Moreover, the integration of the evaluation equipment 106 with the control unit and the object capturing device 104 allows for a cohesive and interactive diagnostic environment. This integration facilitates the seamless flow of data and instructions between the components, enhancing the user’s ability to perform accurate and efficient diagnostics.

[0063] In some embodiments, the evaluation equipment 106 may also include advanced features such as automated signal adjustment, real-time data processing, and adaptive measurement protocols. These features contribute to the method’s adaptability and accuracy, ensuring that the equipment remains effective across different types and complexities of connectivity assemblies.

[0064] By encompassing both specific techniques like TDR and a range of other diagnostic capabilities, the evaluation equipment 106 in Fig. 1 serves as a cornerstone of the computer system’s functionality. It exemplifies the computer system’s 100 commitment to providing comprehensive, precise, and user-friendly diagnostic solutions.

[0065] It should be stressed that other types of evaluation equipment 106 could be used in relation to the computer system 100. Such other types of evaluation equipment 106 could for example be selected to comprise one or a combination of measurement equipment and geo location equipment, enabling a comprehensive approach to diagnosing and locating elements within various physical structures.

[0066] Measurement equipment, like the previously mentioned TDR systems, offers precision in identifying specific faults within connectivity assemblies, such as wire harnesses. However, in situations where the physical structure extends beyond electrical systems, other equipment such as e.g. evaluation equipment 106 of the measurement type may be selected from a group comprising 3D scanning equipment, ultrasonic testing equipment, thermal imaging cameras, magnetic field sensors, endoscopic cameras, acoustic emission sensors, near field communication (NFC), and radio frequency identification (RFID) readers may be used in conjunction with the computer system 100.

[0067] 3D scanning equipment can play a crucial role in mapping and visualizing the physical layout of complex structures, particularly useful for storage compartments. This technology creates detailed 3D models, offering a comprehensive view that aids in pinpointing optimal evaluation points. U1trasonic testing equipment is vital for nondestructive testing in various structures. Especially useful where maintaining physical integrity is essential, this equipment can detect internal flaws or anomalies, guiding the selection of evaluation points with precision. Thermal imaging cameras offer the ability to detect heat signatures within a structure. This is particularly advantageous for identifying overheating electrical components in electrical systems, aiding in isolating potential fault areas.

[0068] Magnetic field sensors are instrumental in electrical systems for detecting magnetic fields generated by electrical currents. Their use can help in localizing areas within electrical systems for focused evaluation. Endoscopic cameras provide the capability to inspect hard-to-reach or visually obstructed areas within structures. Their application is invaluable in examining intricate wiring conduits or hidden compartments within storage systems. Acoustic emission sensors detect sound waves emitted from structural faults such as cracks. They are highly effective in both electrical systems and physical storage spaces, pinpointing areas where structural integrity might be compromised.

[0069] Additionally, near field communication (NFC) readers are ideal for scenarios where elements within a structure are tagged with NFC chips. They enable quick and accurate identification and location of tagged items, simplifying the process of isolating elements within a structure.

[0070] Each of these types of measurement-based evaluation equipment 106 enhances the versatility and effectiveness of the computer system 100. They can be used individually or in combination, depending on the specific requirements of the structure being analyzed. This adaptability ensures that the system is capable of addressing a wide array of diagnostic scenarios, from intricate electrical systems to expansive storage facilities.

[0071] As indicated above, the evaluation equipment 106 may also or instead comprise e.g. geolocation equipment, selected from a group comprising NFC-based systems, BLE beacons, Wi-Fi-based indoor positioning systems, and smart shelving. NFC-based systems, which can swiftly locate specific tagged items within a storage environment. Ble beacons offer a similar function, providing short-range tracking that is particularly useful in confined spaces. For larger areas, Wi-Fi-based indoor positioning systems use existing network infrastructure to locate items, while UWB technology delivers unparalleled precision in dense and complex environments.

[0072] Smart shelving with integrated sensors represents an IOT approach, transforming storage areas into intelligent systems capable of real-time monitoring and management. These shelves can automatically track inventory, providing valuable insights into the contents of a storage area.

[0073] Additionally, computer vision systems enhanced with AI-driven image recognition can identify and locate items based on visual characteristics. This technology is especially useful for untagged items or in situations where NFC or BEE tagging is impractical.

[0074] By combining these different technologies, the evaluation equipment 106 can adapt to a wide range of diagnostic and location scenarios. For example, a combination of TDR and NFC systems could be used to diagnose faults within a vehicle’s electrical system and simultaneously manage the inventory of spare parts in a workshop. Similarly, smart shelving equipped with UWB technology could provide both inventory management and precise item location within a warehouse.

[0075] Turning now to Fig. 2A, presenting a possible implementation of the scheme according to the present disclosure, for example using a computer system as outlined in relation to Fig. 1.

[0076] In Fig. 2A, and with further reference to Fig. 3, a physical structure is provided, here in the form of a vehicle 200 comprising a wire harness 202. The embodiment presented in relation to Fig. 2A relates to isolating or locating an error within the wire harness 202. This is achieved by initially identifying, SI, a type of physical structure, here defines as e.g. the vehicle 200, the wire harness 202, or possibly an electrical connector 204 of the wire harness 202. The identification may for example be performed using the above discussed AR headset 203, comprising the mentioned object capturing device 104 and output interface 108, here arranged with a user, specifically in the form of an automotive technician.

[0077] As indicated above, such an identification may for example be achieved using the object capturing device 104 at the AR headset 203. As has been discussed previously, the object capturing device 104 may for example capture an image of e.g. the vehicle 200, the wire harness 202, or possibly an electrical connector 204 of the wire harness 202 and provide the captured image to e.g. the control unit 102. The control unit 102 may in turn be provided with e.g. a machine learning component (not explicitly illustrated) that has been pre-train in relation to a large plurality of different vehicle, wire harnesses, electrical connectors, etc. and to swiftly be able to thereby identify the type of the physical structure.

[0078] Once the type of the physical structure has been identified, a first evaluation point 206 is selected, S2, where the selection is based on the identified physical structure. In Fig. 2A, the first evaluation point is an electrical junction point that is designated for measurements, for example using one of the above discussed evaluation/measurement equipment 106.

[0079] The evaluation/measurement equipment 106 is at this point used for conducting, S3 a first evaluation, which in turn will result some form of data that can be evaluated. At this point, it is likely so that the error within the wire harness 202 has not been isolated. Therefore, and with the intention to progress closer to the error, a further (second) evaluation point 208 is selected, S4. The second evaluation point is in turn selected based on the result of the first evaluation, and also selected to be different from the first evaluation point, typically selected at another position within the wire harness 202.

[0080] A second measurement and following evaluation is conducted, S4, at the second evaluation at the second evaluation point 208. The evaluation performed at the second evaluation point 208 may in some embodiments be the same as the one performed at the first evaluation point, however the scheme according to the present disclosure allows for a mix of evaluation techniques/equipment to be performed at the different evaluation points 206, 208. As such, the scheme according to the present disclosure allows for a hybrid evaluation within e.g. the wire harness 202, where the computer system 100, through e.g. the AR headset 110 may direct the user to the different evaluation points 206, 208 as well as instructing the user as to what type of equipment to use for performing the evaluations.

[0081] Once both the first and the second evaluation has been performed, the chances of pin-pointing the physical location of the error has greatly increase. Specifically, in line with the present disclosure this is achieved by basing the determination, S6, on a combination of the results of the first and second evaluations and the first 206 and the second 208 evaluation points.

[0082] The results from the first and second evaluations may for example in one embodiment be provided to another machine learning component comprised with the control unit 102, were also this machine learning component has been pre-trained on different errors and measurement results that may be expected in different types of physical structures, such as the exemplary wire harness 202 of Fig. 2A.

[0083] Once the location of the error within the wire harness 202 has been determined, it may for example be presented within the AR headset 203.

[0084] It should be understood that it in some embodiments may be necessary to perform more than just two separate measurements/evaluations, such as for example, three, four, five or even further evaluations, for being able to determine e.g. the location of the error. However, within the context of the present disclosure is has been determined that at least two measurements/evaluations are needed to guide the user in the most suitable way and with an adequate level of reliability.

[0085] In Fig. 2B, the present disclosure is exemplified in a different context, where the physical structure is a warehouse 260 with a set of shelves 250. The objective here is to isolate the location of an element, specifically an electrical relay 240, within this storage environment. The embodiment showcases the versatility of the computer system 100 in adapting to various types of physical structures and elements.

[0086] The user, equipped with a mobile phone 230, initiates the process by identifying, SI, the type of the physical structure and the element. In this scenario, the mobile phone 230, functioning as the object capturing device 104, captures images of the warehouse 260 and the shelves 250. Utilizing a machine learning component integrated within the mobile phone 230 or connected to the control unit 102, these images are analyzed to identify the specific characteristics of the warehouse 260 and the shelves 250, as well as the electrical relay 240 to be located.

[0087] Once the type of the physical structure and the element has been identified, the system progresses to select, S2, a first evaluation point within the warehouse 260. This selection is informed by the identified characteristics of the warehouse and the potential locations of the relay 240. The first evaluation point might be a specific shelf or a section of the warehouse where the relay is likely to be found.

[0088] The user then conducts, S3, a first evaluation at this point using the mobile phone 230, possibly augmented with additional sensor attachments, to search for the electrical relay 240. The evaluation might involve scanning NFC tags, using image recognition technologies, or employing other sensor-based methods to detect the relay’s presence. In Fig. 2B the mobile phone 230 is used for scanning QR codes 232, 234 arranged throughout the warehouse 260 and/or at the shelves 250.

[0089] Based on the outcome of this first evaluation, a second evaluation point is selected, S4. This point is determined to be different from the first, guiding the user to another potential location of the relay within the warehouse 260. The selection is driven by an intelligent analysis of the first evaluation results, considering various factors like relay type, shelf organization, and warehouse layout. At the second evaluation point, another round of evaluation is conducted, S5, using the mobile phone 230. The method allows for a dynamic approach, where different types of evaluations can be employed at each point, depending on the evolving requirements of the search process.

[0090] Finally, the physical location of the electrical relay 240 is determined, S6, based on a synthesis of the results from both the first and second evaluations. This determination is facilitated by the machine learning component, which has been trained on diverse scenarios and types of elements typically found in warehouse settings. The system, through this intelligent processing, effectively guides the user towards the precise location of the electrical relay 240, showcasing the adaptability and efficiency of the method in a storage-centric environment like a warehouse 260.

[0091] It should be noted, the control functionality of the present disclosure may be implemented using existing computer processors, or by a special purpose computer processor for an appropriate system, incorporated for this or another purpose, or by a hardwire system. Embodiments within the scope of the present disclosure include program products comprising machine-readable medium for carrying or having machine-executable instructions or data structures stored thereon. Such machine-readable media can be any available media that can be accessed by a general purpose or special purpose computer or other machine with a processor. By way of example, such machine-readable media can comprise RAM, ROM, EPROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, solid state drives or other non-volatile flash based storage devices, or any other medium which can be used to carry or store desired program code in the form of machine-executable instructions or data structures and which can be accessed by a general purpose or special purpose computer or other machine with a processor. When information is transferred or provided over a network or another communications connection (either hardwired, wireless, or a combination of hardwired or wireless) to a machine, the machine properly views the connection as a machine-readable medium. Thus, any such connection is properly termed a machine-readable medium.

[0092] Combinations of the above are also included within the scope of machine-readable media. Machine-executable instructions include, for example, instructions and data which cause a general-purpose computer, special purpose computer, or special purpose processing machines to perform a certain function or group of functions.

[0093] Although the figures may show a sequence the order of the steps may differ from what is depicted. Also two or more steps may be performed concurrently or with partial concurrence. Such variation will depend on the software and hardware systems chosen and on designer choice. All such variations are within the scope of the disclosure. Likewise, software implementations could be accomplished with standard programming techniques with rule-based logic and other logic to accomplish the various connection steps, processing steps, comparison steps and decision steps. Additionally, even though the present disclosure has been described with reference to specific exemplifying embodiments thereof, many different alterations, modifications and the like will become apparent for those skilled in the art.

[0094] In addition, variations to the disclosed embodiments can be understood and effected by the skilled addressee in practicing the claimed present disclosure, from a study of the drawings, the disclosure, and the appended claims. Furthermore, in the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality.

Claims (14)

1. A computer-implemented method for isolating a location of a fault within a connection unit (202), comprising the steps of: identifying a type of the connection unit (202), selecting, based on the identified type of the connection unit (202), a first measurement point (206) at the connection unit (202), performing a first measurement at the first measurement point (206), selecting a second measurement point (208) at the connection unit (202) based on the result of the first measurement, wherein the second measurement point (208) is separate from the first measurement point, performing a second measurement at the second measurement point (208), and isolating the fault location within the connection unit (202) based on the result of the first measurement and a result of the second measurement. The computer-implemented method of claim 1, wherein the isolation of the fault location is further based on the type of the connection unit (202). 3. The computer-implemented method of any one of claims 1 and 2, wherein the step of identifying the type of the connection unit (202) comprises the steps of: obtaining an image of the connection unit (202), applying an image processing scheme to the obtained image to extract identifiable characteristics of the connection unit (202), and determining the type of the connection unit (202) based on the extracted identifiable characteristics. The computer-implemented method of claim 3, wherein the image processing scheme includes a machine learning component that is pre-trained on a variety of different types of connection devices (202). 5. The computer-implemented method of any one of the preceding claims, wherein at least one of the first and second measurements comprises performing time domain reflectometry (TDR) measurements. 6. The computer-implemented method of any one of the preceding claims, further comprising the step of: identifying an electrical component (204, 240) connected to the connection unit (202), wherein the selection of at least one of the first (206) and the second (208) measurement points is dependent on the identified electrical component (204, 240). 7. The computer-implemented method of claim 6, wherein the electrical component (204, 240) forms part of a mobile platform, and the selection of at least one of the first (206) and the second (208) measurement points is dependent on the type of the mobile platform. The computer-implemented method of claim 6, wherein the mobile platform is selected from a group comprising at least one of a vehicle (200), a ship, and an aircraft. 9. The computer-implemented method of any one of the preceding claims, wherein the fault is at least one of a short circuit within the connection unit (202), an open circuit within the connection unit (202), and a corrosion in a contact (204) included in the connection unit (202). 10. The computer-implemented method according to any one of the preceding claims, wherein the step of isolating the fault location comprises performing a modeling of the result of the first and second measurements with previously collected corresponding data for the same type of connection unit (202) or a corresponding type of the connection unit (202). 11. The computer-implemented method of claim 10, wherein the modeling comprises applying a machine learning process to the selected portion of the various data sets included in the first collection of vehicle diagnostic data. 12. A computer system (100) adapted to isolate a location of a fault within a connection unit (202), the computer system (100) comprising a control unit (102) configured to: identify a type of the connection unit (202), select, based on the identified type of the connection unit (202), a first measurement point (206) at the connection unit (202), perform a first measurement at the first measurement point (206), select a second measurement point (208) at the connection unit (202) based on the result of the first measurement, the second measurement point (208) being separate from the first measurement point (206), perform a second measurement at the second measurement point (208), and isolate the fault location within the connection unit (202) based on the result of the first measurement and a result of the second measurement. 13. An electronic user device (203, 230), comprising a computer system (100) according to claim 12. 14. A computer program product comprising a non-volatile computer-readable medium having stored computer program means for isolating a location of a fault within a connection unit (202), the computer program product comprising: code for identifying a type of the connection unit (202), code for selecting, based on the identified type of the connection unit (202), a first measurement point (206) at the connection unit (202), code for performing a first measurement at the first measurement point (206), code for selecting a second measurement point (208) at the connection unit (202) based on the result of the first measurement, the second measurement point (208) being separate from the first measurement point, code for performing a second measurement at the second measurement point (208), and code for isolating the fault location within the connection unit (202) based on the result of the first measurement and a result of the second measurement.