Dual-function system and method for underground utility mapping and electrical cable fault detection

A portable system with integrated sensors and AI-driven analysis addresses inefficiencies in underground utility mapping and fault detection by providing real-time, precise localization and fault classification, enhancing operational efficiency and reducing manual intervention.

WO2026239233A1PCT designated stage Publication Date: 2026-11-19SARASWAT HARSHITA
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/IB2026/054611
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2025-05-15
Filing Date
2026-05-09
Publication Date
2026-11-19

AI Technical Summary

Technical Problem

Existing technologies for underground utility mapping and electrical cable fault detection lack real-time data interpretation, are susceptible to environmental noise, fail to differentiate utility types, and require skilled personnel, often operating as separate systems, leading to inefficiencies and operational delays.

Method used

A portable system integrating multiple sensors, a probe-based signal mechanism, and artificial intelligence (AI)-driven analysis to identify and classify underground utilities and faults in real-time, using a relay unit to manage signal paths and transmit comprehensive data to a computing device.

Benefits of technology

Enables accurate, real-time mapping and fault localization with minimal human intervention, providing precise utility mapping and fault detection in complex environments, enhancing decision-making and reducing operational downtime.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure IB2026054611_19112026_PF_FP_ABST
    Figure IB2026054611_19112026_PF_FP_ABST
Patent Text Reader

Abstract

A system (102) and method (300) for underground utility mapping and electrical cable fault detection are disclosed. The system (102) includes a portable device (104) equipped with one or more downward-facing sensors (106) for detecting underground utilities and a probe assembly for interfacing underground electrical cables. A processor (110) receives data from the sensors and signals from the probe, identifies utility types, depth, and location, and generates utility mapping data. Faults in the cables are identified by matching received signal patterns with stored references and are classified using artificial intelligence (AI) techniques to determine fault types and locations. A relay unit (112) with AI-controlled switchable relays dynamically reconfigures signal paths to isolate or further analyse fault zones. The system (102) transmits output data, including geospatial mapping and fault diagnostics, to an external computing device (120). The proposed system (102) improves accuracy and responsiveness in underground utility detection and fault localisation.
Need to check novelty before this filing date? Find Prior Art

Description

DUAL-FUNCTION SYSTEM AND METHOD FOR UNDERGROUND UTILITY MAPPING AND ELECTRICAL CABLE FAULT DETECTIONTECHNICAL FIELD

[0001] The present disclosure relates to the field of underground utility detection and electrical fault diagnostics. More specifically, it pertains to a system for mapping underground utility infrastructures and detecting faults in underground electrical cables.BACKGROUND

[0002] Background description includes information that may be useful in understanding the present invention. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed disclosure, or that any publication specifically or implicitly referenced is prior art.

[0003] Detection and mapping of underground utility infrastructures, such as electrical cables, water pipelines, and communication lines, is a critical task in construction, maintenance, and urban planning operations. Various sensor-based systems, such as Ground Penetrating Radar (GPR), electromagnetic induction sensors, and magnetometers, are currently utilised for subsurface utility detection. Additionally, fault detection in underground electrical cables is typically performed using time-domain reflectometry (TDR), thumping methods, or voltage gradient detection.

[0004] Despite advancements, existing technologies face significant limitations. Conventional utility mapping systems often lack real-time data interpretation, are highly susceptible to environmental noise, and provide insufficient differentiation between utility types. Fault detection systems, on the other hand, are generally bulky, expensive, and require skilled personnel for accurate operation. Many existing devices do not integrate mapping and fault detection in a single workflow, resulting in inefficiencies and operational delays.

[0005] Furthermore, current methods offer limited automation and adaptability to dynamic field conditions. They often fail to provide actionable insights or precise localisation, especially in dense or complex underground networks.

[0006] Therefore, there is a need for an improved solution that can address these challenges through enhanced detection accuracy, integrated operation, and intelligent automation, while remaining portable and user-friendly.OBJECTS OF THE PRESENT DISCLOSURE

[0007] A general object of the present disclosure is to provide a compact and portable solution for underground utility mapping and electrical cable fault detection.

[0008] An object of the present disclosure is to provide a system and method capable of identifying different types of underground utilities using sensor data interpretation.

[0009] Another object of the present disclosure is to provide a system and method that integrates both utility detection and cable fault classification into a unified device.

[0010] Another object of the present disclosure is to provide intelligent fault classification using artificial intelligence techniques based on signal pattern analysis.

[0011] Another object of the present disclosure is to provide a real-time data processing mechanism for utility mapping and fault localisation.

[0012] Another object of the present disclosure is to provide an Al-driven relay unit that dynamically reconfigures signal paths to isolate or further examine suspected fault zones.

[0013] Another object of the present disclosure is to provide a solution capable of operating with minimal human intervention while improving accuracy and decision reliability.

[0014] Another object of the present disclosure is to provide a solution that transmits comprehensive output data, including utility maps and fault locations, to an external computing device for visualisation and analysis.

[0015] Another object of the present disclosure is to provide a cost-effective and field-deployable diagnostic solution for subsurface infrastructure monitoring.

[0016] Another object of the present disclosure is to provide a solution capable of maintaining signal integrity validation through feedback mechanisms within the relay unit.SUMMARY

[0017] Aspects of the present disclosure relate to the field of underground utility detection and electrical fault diagnostics. More specifically, it pertains to a system for mapping underground utility infrastructures and detecting faults in subsurface electrical cables. The disclosed system integrates multiple sensor technologies and a probe-based signal mechanism, coupled with artificial intelligence (Al)-driven analysis and relay logic, to accurately identify the type, location, and condition of underground utilities and electrical faults in real-time.

[0018] An aspect of the present disclosure relates to a system for underground utility mapping and electrical cable fault detection. The system includes a device equipped with one or more sensors positioned on its lower surface and oriented downward to interact with the ground. These sensors are configured to emit controlled electromagnetic signals into the ground,receive reflected signals from underground utilities or electrical cables, and generate data indicating the location and depth of such utilities or faults. In addition, a probe assembly is positioned on the device and interfaces with underground electrical cables. This operates using a 10-switch mechanism to inject various pulses or signals into the cables, thereby generating signals indicative of fault locations. A test cable is provided to connect phase-wise to the electrical cables under inspection, enabling individual phase testing.

[0019] The system further includes a processor connected to the sensors, the probe assembly, and a memory. The memory stores instructions which, when executed by the processor, enable it to receive and analyse sensor data to generate utility mapping data, and receive signals from the probe assembly. The processor extracts signal patterns by comparing them with stored reference patterns and identifies faults in the cables. It uses artificial intelligence techniques to classify these faults and determine their locations. Based on predefined thresholds, anomaly detection algorithms, and error-checking routines, the processor generates instructions and transmits output data to a computing device. This output includes utility mapping data, identified faults, and their locations.

[0020] Further, a relay unit is housed within the device and connected to the processor. This consists of multiple switchable relays that alter signal paths according to the instructions generated by the processor. The relay unit uses artificial intelligence logic to manage signal routing, isolate fault zones, or re-route signals for further identification.

[0021] In an aspect, the utility mapping data includes geospatial coordinates, depth, type, orientation, and material of the detected utilities and is displayed on a computing device.

[0022] In an aspect, the artificial intelligence techniques used in the system include supervised machine learning models trained on labeled signal patterns for accurate fault classification.

[0023] In an aspect, the relay unit dynamically reconfigures diagnostic signal paths in response to detected anomalies to ensure real-time validation of signal integrity.

[0024] In an aspect, the system also includes a feedback mechanism that validates signal integrity after each reconfiguration and logs response time and Al-based decisions for performance evaluation.

[0025] Another aspect of the present disclosure pertains to a method for underground utility mapping and electrical cable fault detection using a device. The method begins with emitting, by sensors positioned on a lower surface of the device, controlled electromagnetic signals into the ground. The sensors receive reflected signals from underground utilities or electrical cables and generate data related to the location and depth of the underground utilities or faults in theelectrical cables. A test cable is connected phase-wise to an electrical cable under inspection, and each phase is tested individually. A probe assembly injects one or more types of pulses or signals into the electrical cables using a 10-switch mechanism to generate signals indicative of fault location.

[0026] In addition, a processor receives the data from the sensors and the signals from the probe assembly. Based on the received data, the processor identifies the types of underground utilities and generates utility mapping data. The processor extracts signal patterns by matching the received signals with stored reference patterns and identifies faults in the electrical cables based on the matched signal patterns. Using artificial intelligence techniques, the processor classifies the identified faults in the electrical cables and determines their respective locations. The processor then generates instructions by evaluating the classified fault data against predefined thresholds, applying anomaly detection algorithms, and performing error-checking routines to ensure data integrity.

[0027] The processor operates a relay unit consisting of a plurality of switchable relays. The relay unit alters signal paths based on the generated instructions and adjusts signal routing using artificial intelligence logic to isolate fault regions or re-route signals for additional fault identification. Further, the processor transmits output data to a computing device. This output data includes the utility mapping data, the identified faults, and the fault locations.

[0028] Various objects, features, aspects, and advantages of the inventive subject matter will become more apparent from the following detailed description of preferred embodiments, along with the accompanying drawing figures in which like numerals represent components.BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings are included to provide a further understanding of the present disclosure and are incorporated in and constitute a part of this specification. The drawings illustrate exemplary embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0030] FIG. 1 illustrates an exemplary block diagram of a system for underground utility mapping and electrical cable fault detection, in accordance with an embodiment of the present disclosure.

[0031] FIG. 2 illustrates exemplary functional units of a processor associated with the proposed system, in accordance with an embodiment of the present invention.

[0032] FIG. 3 illustrates an exemplary flow chart for a method for underground utility mapping and electrical cable fault detection, in accordance with an embodiment of the present disclosure.DETAILED DESCRIPTION

[0033] The following is a detailed description of embodiments of the disclosure depicted in the accompanying drawings. The embodiments are in such detail as to clearly communicate the disclosure. However, the amount of detail offered is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the present disclosures as defined by the appended claims.

[0034] Embodiments explained herein relate to the field of underground utility detection and electrical fault diagnostics. More specifically, it pertains to a system for mapping underground utility infrastructures and detecting faults in subsurface electrical cables. The disclosed system integrates multiple sensor technologies and a probe-based signal mechanism, coupled with artificial intelligence (Al)-driven analysis and relay logic, to accurately identify the type, location, and condition of underground utilities and electrical faults in real-time.

[0035] An embodiment of the present disclosure relates to a system for underground utility mapping and electrical cable fault detection. The system includes a device equipped with one or more sensors positioned on its lower surface and oriented downward to interact with the ground. These sensors are configured to emit controlled electromagnetic signals into the ground, receive reflected signals from underground utilities or electrical cables, and generate data indicating the location and depth of such utilities or faults. In addition, a probe assembly is positioned on the device and interfaces with underground electrical cables. This operates using a 10-switch mechanism to inject various pulses or signals into the cables, thereby generating signals indicative of fault locations. A test cable is provided to connect phase-wise to the electrical cables under inspection, enabling individual phase testing.

[0036] The system further includes a processor connected to the sensors, the probe assembly, and a memory. The memory stores instructions which, when executed by the processor, enable it to receive and analyze sensor data to generate utility mapping data and receive signals from the probe assembly. The processor extracts signal patterns by comparing them with stored reference patterns and identifies faults in the cables. It uses artificial intelligence techniques to classify these faults and determine their locations. Based on predefined thresholds, anomaly detection algorithms, and error-checking routines, the processor generates instructions andtransmits output data to a computing device. This output includes utility mapping data, identified faults, and their locations.

[0037] Further, a relay unit is housed within the device and connected to the processor. This consists of multiple switchable relays that alter signal paths according to the instructions generated by the processor. The relay unit uses artificial intelligence logic to manage signal routing, isolate fault zones, or re-route signals for further identification.

[0038] In an embodiment, the utility mapping data includes geospatial coordinates, depth, type, orientation, and material of the detected utilities and is displayed on a computing device.

[0039] In an embodiment, the artificial intelligence techniques used in the system include supervised machine learning models trained on labeled signal patterns for accurate fault classification.

[0040] In an embodiment, the relay unit dynamically reconfigures diagnostic signal paths in response to detected anomalies to ensure real-time validation of signal integrity.

[0041] In an embodiment, the system also includes a feedback mechanism that validates signal integrity after each reconfiguration and logs response time and Al-based decisions for performance evaluation.

[0042] Various embodiments with respect to the present disclosure will be explained in detail with reference to FIGs. 1-3.

[0043] Referring to FIG. 1, an exemplary block diagram (100) of a system (102) for underground utility mapping and electrical cable fault detection is disclosed. The system (102) is configured for deployment in the field and may be used in urban or remote areas to identify subsurface utilities and diagnose faults in underground electrical cables with minimal manual intervention. The system (102) includes a portable device (104) that may either be handheld or mounted on a movable platform such as a trolley or a ground robot, allowing flexibility in operation across different terrains and environments. The device (104) serves as the main body that houses and supports all functional components. Positioned on the lower surface of the device (104) are one or more sensors (106), oriented downward toward the ground. These sensors (106) are electromagnetic sensors configured to detect and generate data related to underground utilities such as water pipelines, fiber optic cables, sewage lines, or gas conduits. The sensors (106) emit controlled electromagnetic signals into the ground and receive reflected signals from underground utilities. Based on the reflected signals, the sensors (106) generate data corresponding to the location and depth of these utilities and faults in electrical cables. The positioning of the sensors (106) close to the ground ensures optimal data capture byminimizing interference from surface-level objects and enhancing the resolution of the detected signals, thus providing more accurate utility mapping.

[0044] In addition, the system (102) includes a probe assembly (108) configured specifically to interface with underground electrical cables. This is positioned on the device (104) to facilitate seamless connectivity during field operations. The primary function of the probe assembly (108) is to generate signals that are indicative of fault locations within the electrical cables. To achieve this, the assembly employs a 10-switch mechanism. This mechanism enables the injection of one or more types of pulses or signals into the electrical cables under inspection. These injected signals travel along the cable and are partially reflected when they encounter irregularities such as discontinuities, breaks, or insulation defects. By analysing the characteristics of these reflected signals, such as time delay, amplitude, or waveform distortion, the system (102) can determine the presence and location of faults.

[0045] The use of a 10-switch mechanism allows for flexibility in signal generation, enabling the device to adapt to different testing requirements, cable types, and diagnostic scenarios. This capability supports comprehensive fault detection without the need for multiple testing devices or manual reconfiguration.

[0046] In addition, a probe assembly (108) is mounted on the device (104), and may use contact or non-contact methods depending on the cable type and depth. The probe assembly (108) is configured to establish an interface with underground electrical cables, allowing it to transmit and receive signals from electrical conductors or terminals of the electrical cables. These signals assist in identifying abnormalities such as short circuits, insulation breakdowns, open circuits, or grounding faults. The probe assembly (108) may use contact pins, inductive clamps, or capacitive coupling techniques, depending on the type and accessibility of the electrical cable. This functionality enables the system (102) to assess cable integrity and pinpoint fault locations without the need for excavation. All components, including the sensors (106) and probe assembly (108), are operatively connected to ensure synchronised data collection. The arrangement enables the device (104) to perform dual functions of mapping underground infrastructure and diagnosing electrical faults in a single operational pass, making this suitable for applications like urban planning, maintenance of underground power networks, and construction site assessments.

[0047] In an embodiment, a test cable (109) is provided and is configured to be connected phase-wise to the electrical cables under inspection. The test cable (109) is manually connected to each phase of the electrical system suspected to have a fault. By isolating and testing each phase separately, the system (102) ensures accurate identification of faults specific to aparticular phase, without interference from other phases. This enhances diagnostic precision and allows the system to detect phase-specific issues such as open circuits, short circuits, or insulation breakdowns with greater reliability. The phase-wise connection is essential for comprehensive fault analysis in multi -phase electrical networks.

[0048] In an embodiment, the system (102) includes one or more processor(s) (110) configured to receive data from the sensors (106) and signals from the probe assembly (108). The processor (110) processes the data to identify underground utilities and generates utility mapping information. Further, the processor (110) extracts and analyses signal patterns to detect cable faults using reference data and artificial intelligence techniques. Based on this analysis, the processor (110) classifies the faults, determines their locations, and generates instructions through threshold evaluation, anomaly detection, and integrity checks. Further, the processor (110) transmits the output, including utility mapping and fault details, to a connected computing device (120) for visualisation.

[0049] In an embodiment, the computing device (120) is communicatively coupled to the processor (110) through a communication network (122). The communication network (122) can be a wireless network, a wired network or a combination thereof that can be implemented as one of the different types of networks, such as Intranet, Local Area Network (LAN), Wide Area Network (WAN), Internet, and the like. Furthermore, the communication network (122) can either be a dedicated network or a shared network. The shared network can represent an association of different types of networks that can use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol / Intemet Protocol (TCP / IP), Wireless Application Protocol (WAP), and the like.

[0050] In an embodiment, the computing device (120) may include smartphones, tablets, laptops, desktops, or any other internet-enabled devices that allow the user to access the proposed system (102). The processor (110) may interact with the computing device (120) through a website or an application residing within the proposed system (102). In an implementation, the proposed system (102) may be accessed via a website or an application compatible with any operating system, including but not limited to Android™, iOS™, and the like.

[0051] In an embodiment, the system (102) incorporates a relay unit (112) housed within the device (104) and operatively connected to the processor (110). The relay unit (112) includes multiple switchable relays (114) configured for signal management during fault diagnostics. These switchable relays (114) are configured to dynamically alter the signal pathways in response to instructions received from the processor (110), which are based on artificialintelligence (Al) logic. This Al logic enables the system (102) to make decisions such as isolating specific fault zones to prevent further disruption or re-routing diagnostic signals through alternate paths for deeper fault verification. As a result, the relay unit (112) ensures flexible and intelligent control over signal flow, helping the system (102) adapt in real-time to different fault scenarios and maintain diagnostic efficiency. The relay unit (112) further includes a feedback mechanism to validate the integrity of the signal after each reconfiguration and logs the response time and decision outcomes for ongoing performance evaluation and system optimisation.

[0052] In an exemplary implementation, during active infrastructure development, the system (102) may be used to detect faults in newly laid underground cables before they are buried permanently. For instance, if a power line is installed for a metro project, the system ensures no breaks or phase mismatches exist before final commissioning.

[0053] In an exemplary implementation, in cases of accidental drilling or demolition, the system (102) helps verify damage to underground electrical cables. For example, if a construction crew hits a buried line while digging, the system can quickly identify the type and exact location of the fault to guide immediate repair.

[0054] In an exemplary implementation, for routine maintenance in electrical or industrial systems, the system (102) supports periodic checks of underground cabling. For example, utility providers or facility managers can use it to test for insulation degradation or early-stage faults in critical power lines without needing to dig or disrupt operations.

[0055] Referring to FIG. 2, exemplary functional units of the processor (110) are disclosed. The processor (110) may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuits, and / or any devices that manipulate data based on operational instructions. Among other capabilities, the processor (110) may be configured to fetch and execute computer-readable instructions stored in the memory (204) of the system (102). The memory (204) may store one or more computer-readable instructions or routines, which may be used for mapping underground utility infrastructures and fault analysis. The memory (204) may include any non-transitory storage device, including, for example, volatile memory such as Random-Access Memory (RAM), or non-volatile memory such as Erasable Programmable Read-Only Memory (EPROM), flash memory, and the like.

[0056] In an embodiment, the processor (110) may also include an interface(s) (206). The interface(s) (206) may include a variety of interfaces, for example, a variety of interfaces, interfaces for data input and output devices, referred to as I / O devices, storage devices, and thelike. The interface(s) (206) may facilitate communication of the system (102) with various devices coupled to it. The interface(s) (206) may also provide a communication pathway for one or more components of the system (102). Examples of such components include, but are not limited to, processing engine(s) (208) and a database (210). The database (210) may include data that is either stored or generated as a result of functionalities implemented by any of the components of the processing engine(s) (208).

[0057] In an embodiment, the processing engine(s) (208) may be implemented as a combination of hardware and programming (for example, programmable instructions) to implement one or more functionalities of the processing engine(s) (208). In the examples described herein, such combinations of hardware and programming may be implemented in several different ways. For example, the programming for the processing engine(s) (208) may be processor executable instructions stored on a non-transitory machine -readable storage medium, and the hardware for the processor(s) (110) may comprise a processing resource (for example, one or more processors), to execute such instructions. In the present examples, the machine-readable storage medium may store instructions that, when executed by the processing resource, implement the processing engine(s) (208).

[0058] In such examples, the system (102) may include the machine-readable storage medium storing the instructions and the processing resource to execute the instructions, or the machine -readable storage medium may be separate but accessible to the system (102) and the processing resource. In other examples, the processing engine(s) (208) may be implemented by an electronic circuitry. The processing engine(s) (208) may include a sensor data processing module (212), a signal analysis and fault classification module (214), a relay control module (216), and other module(s) (218). The other module(s) (218) may implement functionalities that supplement applications / functions performed by the processing engine(s) (208).

[0059] In an embodiment, the sensor data processing module (212) is configured to handle the data received from the sensors (106). This sensor data processing module (212) processes the received data to identify types of underground utilities, such as electrical cables, water pipes, gas pipelines, or telecommunication cables, based on their distinct electromagnetic signal characteristics. Once identified, the sensor data processing module (212) generates utility mapping data, which includes geospatial coordinates, depth, type, orientation, material, and the like of the detected utilities. This mapping data is displayed on the computing device (120) and is essential for generating a visual representation of the underground infrastructure, enabling informed decision-making and facilitating safe planning without the need for physical excavation.

[0060] In an embodiment, the signal analysis and fault classification module (214) may be configured to perform a series of systematic operations to analyse signals and identify electrical cable faults with high accuracy. The signal analysis and fault classification module (214) extracts signal patterns by comparing the signals received from the probe assembly (108) with pre-stored reference patterns in the memory (204). These reference patterns represent known signal behaviours for both healthy and faulty cables. For instance, a sudden drop in amplitude or an irregular frequency response may indicate a short circuit or an insulation breakdown.

[0061] Once the patterns are extracted, the signal analysis and fault classification module (214) identifies the type of fault, such as open circuit, short circuit, grounding fault, or insulation failure, by recognising deviations from standard signal profiles. The module applies artificial intelligence (Al) techniques to the extracted patterns to enhance classification accuracy. The artificial intelligence techniques include a supervised machine learning model trained to classify the type of faults based on labelled signal patterns. These models use historical fault data to learn signal characteristics associated with different types of failures and apply this learning to current data. The signal analysis and fault classification module (214) further determines the location of the faults by analysing signal delay, strength, and sensor input in correlation with geospatial coordinates. This enables accurate pinpointing of fault positions along the underground cable. Based on the classified data, the signal analysis and fault classification module (214) generates instructions by evaluating whether the signal values exceed pre-defined thresholds, employing anomaly detection algorithms to flag unexpected behaviours, and executing error-checking routines to validate the fault data.

[0062] Furthermore, output data, including utility mapping data, the identified faults, and their respective locations, is transmitted to the connected computing device (120). The utility mapping data includes geospatial coordinates corresponding to the detected underground utilities and is displayed on the computing device for visualization and analysis. This real-time feedback allows operators to assess infrastructure conditions efficiently and make informed decisions for maintenance and repair.

[0063] In an embodiment, the signal analysis and fault classification module (214) calculates the exact distance of a fault from the test point using signal delay and echo behaviour. When the signal is injected into the cable, it travels through a conductor, and if it encounters any faults, such as a break or a short circuit, part of the signal reflects back toward the test point. The Al techniques measure the time it takes for the reflected signal to return. By knowing the speed at which the signal travels through the specific type of cable, the Al techniques calculate the distance to the fault. This distance is further displayed in meters or feet, providing a preciselocation of the fault along the cable. This functionality allows field engineers to quickly pinpoint where the fault has occurred without having to excavate or dig up the entire cable, making the process much faster and more efficient. For instance, if the signal returns after a delay corresponding to 50 meters, the Al will calculate that the fault is located 50 meters from the point where the signal is being injected. This capability helps save time and resources by focusing attention on the exact location of the fault, improving overall maintenance efficiency, and reducing operational downtime.

[0064] In an embodiment, the relay control module (216) is responsible for managing how electrical signals flow within the system based on intelligent decisions made by the processor (110). Once the processor evaluates the classified fault data and generates specific instructions, the relay control module executes these instructions by activating a set of switchable relays to alter the internal signal pathways. These changes help redirect the flow of diagnostic signals depending on the situation. This relay control module(216) applies artificial intelligence logic to interpret the processor's instructions more effectively. For instance, if the Al identifies a region in the cable network with a high probability of fault, the relay control module may isolate that section by opening certain relay paths to prevent further signal propagation in that region. Simultaneously, this can reroute diagnostic signals to adjacent or unaffected regions to continue fault detection and ensure that the rest of the network remains operational.

[0065] For instance, if a grounding fault is detected in a section of cable near a power distribution box, the relay control module (216) may deactivate relays connected to that section while rerouting analysis to alternate paths connected to neighbouring segments. This dynamic control not only helps in narrowing down the exact fault location but also minimizes unnecessary signal loss and improves the accuracy of the diagnostic process. This relay control module (216) ensures adaptive and responsive signal routing within the system (102).

[0066] In an embodiment, Java and Python or similar programming languages may be used to implement the machine learning algorithms, signal processing logic, and real-time system control functionalities within the signal analysis, fault classification, and relay control modules of the system (102).

[0067] In an exemplary implementation, the proposed system (102) may be deployed during routine maintenance and inspection of underground utility networks in an urban infrastructure setting. A technician mounts the portable device (104) onto a wheeled cart and moves it along pre-marked survey lines on a city street. As the device is rolled over the surface, the downwardfacing sensors (106) continuously scan the subsurface layers and collect data related to buried pipelines, electrical cables, and other utility lines. Simultaneously, the probe assembly (108)interfaces with accessible electrical cables through designated inspection ports or exposed terminals, allowing the system to gather diagnostic signals. The system (102) processes this real-time data to generate a utility map showing the position and type of underground services along the surveyed path.

[0068] When a fault, such as an insulation breakdown or open circuit, is detected in a section of cable, the system (102) accurately identifies its location and transmits the fault coordinates and utility map to a connected computing device for visualisation. This enables field personnel to quickly assess the situation and decide on targeted excavation or repair activities, thereby saving time, reducing costs, and minimizing disruption to surrounding infrastructure. The ability of the system (102) to operate with minimal manual input makes the system (102) especially suitable for use in dense urban environments or post-disaster recovery scenarios where quick diagnostics are essential.

[0069] Referring to FIG. 3 , an exemplary flow chart of a method (300) for underground utility mapping and electrical cable fault detection using a portable device (104) is disclosed. The method (300) begins by emitting controlled electromagnetic signals into the ground by one or more sensors (106) positioned on a lower surface of the device (104). These sensors (106) are electromagnetic and are designed to detect various types of underground infrastructure, such as water pipelines, fiber optic cables, sewage systems, and gas lines. The data generated from this detection process provides information on the presence and characteristics of these underground utilities.

[0070] At step (304), the method (300) includes receiving by the sensors (106) reflected signals from underground utilities or electrical cables. These reflections are then used to interpret the position, depth, and possibly type of the detected structures or faults in the underground utilities.

[0071] At step (306), the method (300) includes generating data by the sensors (106), data corresponding to the location and depth of the underground utilities or faults in the electrical cables. After emitting and receiving the electromagnetic signals (as described in earlier steps), the sensors (106) process the reflected signals to calculate how far below the surface the utilities or faults are located and where exactly they are positioned horizontally. This data is essential for creating an accurate underground map and for identifying specific fault areas in buried electrical infrastructure.

[0072] At step (308), the method (300) includes connecting a test cable (not shown) phasewise to an electrical cable under inspection. The test cable is manually connected to each phase (typically, R, Y, and B in a three-phase system) of the suspected faulty cable, one at a time. Bytesting each phase separately, the method (300) can isolate and identify faults specific to a particular phase, ensuring more accurate fault detection and diagnosis within the electrical cable under inspection.

[0073] At step (310), the method (300) includes injecting by a probe assembly (108), one or more types of pulses or signals into the electrical cables using a 10-switch mechanism. The probe assembly (108) is configured for sending out pulses or signals into the electrical cable being tested. These signals are used to test the condition of the cable and identify faults. The 10-switch mechanism is an integral part of the probe assembly that controls the different types of signals being injected into the cable. It allows for the generation of different types of pulses or signals that can trigger reflections when they encounter a fault in the cable, such as a break, short circuit, or other discontinuities. The reflected signals are further analysed to indicate the location of faults within the electrical cable, which helps in pinpointing where the issue lies.

[0074] At step (312), the method (300) includes receiving by the processor (110) data from both the sensors (106) and the probe assembly (108). The sensors (106) provide the reflected signals from underground utilities or electrical cables, while the probe assembly delivers the signals used to detect faults in the electrical cables. Based on the received data, the processor (110) identifies the types of underground utilities, such as water pipelines, fiber optic cables, sewage lines, or gas conduits. It then generates utility mapping data that includes the geospatial coordinates of the underground utilities. This utility mapping data is visualised in real-time on a connected computing device, offering an up-to-date map of the underground utilities and fault locations. This step enables efficient detection of both utilities and cable faults while providing real-time visualisation for better decision-making.

[0075] At step (314), the method (300) includes extracting by the processor (110) signal patterns from the received signals by matching them to stored reference patterns. This process includes analysing the signals that were received from the sensors and probe assembly, and comparing them against pre-existing reference patterns that have been stored in a memory (204) of the processor (110). These reference patterns are used to recognise and classify the signals based on their characteristics. By identifying similarities and differences between the received signals and the stored reference patterns, the processor can identify specific features or anomalies, such as faults or disturbances, within the electrical cables or underground utilities. This step is essential for fault detection and classification, enabling the method (300) to accurately determine the nature of the issue and its location.

[0076] At step (316), the method (300) includes identifying by the processor (110) faults in the electrical cables based on the matched signal patterns. After the signal patterns arecompared to the stored reference patterns, the processor uses this data to detect any irregularities or deviations in the signals that may indicate a fault in the electrical cables. These faults could include issues such as breaks, short circuits, insulation failures, or other types of disturbances that affect the integrity of the cables. By analysing the discrepancies between the received signals and the reference patterns, the processor can pinpoint the exact location and nature of the faults within the electrical system. This step is essential for providing accurate diagnostics and ensuring proper fault detection.

[0077] At step (318), the method (300) includes classifying by the processor (110), using an artificial intelligence (Al) technique, the identified faults in the electrical cables and determining respective locations. The artificial intelligence techniques comprise a supervised machine learning model trained to classify the type of faults based on labelled signal patterns.

[0078] At step (320), the method (300) includes generating by the processor (110), instructions by evaluating the classified fault data against pre-defined thresholds, applying anomaly detection algorithms, and performing error-checking routines.

[0079] At step (320), the method (300) includes operating by the processor (110), a relay unit (112) including a plurality of switchable relays to alter signal paths based on the generated instructions, and adjusting signal routing using Al logic to isolate fault regions or re-route signals for further fault identification. The relay unit (112) dynamically reconfigures internal diagnostic signal paths based on the instructions for real-time signal integrity validation. In addition, the relay unit (112) comprises a feedback mechanism to validate the integrity of the signal after each reconfiguration, and logs response time and decision outcomes for performance evaluation.

[0080] At step (322), the method (300) includes transmitting the processor (110), output data to a computing device (120). The output data includes the utility mapping data, the identified faults, and the fault locations. This output data consists of several important pieces of information: the utility mapping data, the identified faults in the electrical cables, and the corresponding fault locations. The utility mapping data provides details about the underground utilities detected by the system, such as their type, location, and depth, while the identified faults include information about any issues found in the electrical cables. Additionally, the fault locations are provided to help identify the precise points where the faults occurred along the cable system. The computing device (120) receives this data, which can then be visualised in real-time, allowing users to assess the condition of the utilities and cables and make informed decisions for further action, such as repairs or maintenance.

[0081] The method (300) further includes logging relay response times and Al-based decision outcomes for evaluating and optimising the performance of the method (300). The relay response times refer to the duration it takes for the relay unit to alter the signal pathways in response to commands or instructions from the processor. By logging these response times, the method (300) can assess how efficiently it is handling the diagnostic processes in real time. Additionally, the Al-based decision outcomes, which are the results of the artificial intelligence algorithms used to make decisions about fault isolation, signal routing, and other processes, are also logged. This data is valuable for evaluating how well the Al logic is functioning and whether it can be improved over time to make the method (300) more accurate and efficient. These logs serve as a basis for performance evaluation and further optimisation of the method (300).

[0082] Thus, the proposed system (102) and the method (300) enable efficient underground utility mapping and electrical cable fault detection by combining advanced sensors, Al -driven analysis, and adaptive signal management. This solution offers real-time fault detection, precise utility mapping, and optimised performance through continuous data evaluation and feedback.

[0083] While the foregoing describes various embodiments of the disclosure, other and further embodiments of the invention may be devised without departing from the basic scope thereof. The scope of the disclosure is determined by the claims that follow. The disclosure is not limited to the described embodiments, versions, or examples, which are included to enable a person having ordinary skill in the art to make and use the disclosure when combined with information and knowledge available to the person having ordinary skill in the art.ADVANTAGES OF THE PRESENT DISCLOSURE

[0084] The present disclosure provides a compact and portable solution for mapping underground utilities and detecting electrical cable faults.

[0085] The present disclosure provides a system and method capable of identifying various types of underground utilities through sensor data interpretation.

[0086] The present disclosure provides a system and method that combines both utility detection and cable fault classification into a single integrated device.

[0087] The present disclosure provides intelligent fault classification through the use of artificial intelligence techniques that analyse signal patterns.

[0088] The present disclosure provides a real-time data processing mechanism for accurate utility mapping and fault localisation.

[0089] The present disclosure provides an Al-driven relay unit that dynamically adjusts signal paths to isolate or further examine potential fault zones.

[0090] The present disclosure provides a solution that operates with minimal human intervention while enhancing accuracy and decision-making reliability.

[0091] The present disclosure provides a solution that transmits comprehensive output data, including utility mapping and fault locations, to an external computing device for visualization and analysis.

[0092] The present disclosure provides a cost-effective and field-deployable diagnostic tool for monitoring subsurface infrastructure.

Claims

I Claim:

1. A system (102) for underground utility mapping and electrical cable fault detection, the system (102) comprising:a device (104);one or more sensors (106), positioned on a lower surface of the device and oriented downward toward the ground, wherein the one or more sensors are configured to:emit controlled electromagnetic signals into the ground;receive reflected signals from underground utilities or the electrical cables; and generate data corresponding to location and depth of the underground utilities or faults in the electrical cables;a probe assembly (108), positioned on the device and configured to interface with electrical cables underground, wherein the probe assembly (108) generates signals indicative of fault locations within the electrical cables using a 10-switch mechanism to inject one or more types of pulses or signals into the electrical cables;a test cable configured to be connected phase-wise to the electrical cables under inspection, wherein each phase of the system (102) suspected to have a fault is tested individually;a processor (110) operatively coupled to the one or more sensors, the probe assembly, and a memory (204, wherein the memory (204) stores instructions which, when executed by the processor (110), cause the processor (110) to:receive the data from the one or more sensors (106) and analyse the received data to generate utility mapping data;receive the signals generated by the probe assembly (108);extract signal patterns by matching the received signals against stored reference patterns, and correspondingly identify faults in the electrical cables;apply artificial intelligence (Al) techniques to the extracted signal patterns to classify the identified faults in the electrical cables and determine the location of the faults;generate instructions by evaluating the classified data against pre-defined thresholds, using anomaly detection algorithms, and applying error-checking routines to check integrity of the classified data;transmit output data to a computing device (120), wherein the output data comprises the utility mapping data, the identified faults in the electrical cables, and the location of the faults;a relay unit (112), disposed within the device (104) and connected to the processor(l 10), the relay unit comprising a plurality of switchable relays configured to:alter paths of the signal based on the instructions generated by the processor (110) and apply Al logic to the generated instructions; andadjust signal routing to manage fault-related decisions as determined by the Al logic, comprising isolating fault areas or re-routing the signals for further fault identification.

2. The system (102) as claimed in claim 1, wherein the utility mapping data comprises geospatial coordinates, depth, type, orientation, and material corresponding to the detected underground utilities, and is displayed to the computing device.

3. The system (102) as claimed in claim 1, wherein the artificial intelligence techniques comprise a supervised machine learning model trained to classify the type of faults based on labelled signal patterns.

4. The system (102) as claimed in claim 1, wherein the relay unit (112) dynamically reconfigures internal diagnostic pathways in response to the detected anomalies for real-time signal integrity validation.

5. The system (102) as claimed in claim 1, wherein the relay unit (112) comprises a feedback mechanism to validate integrity of the signal after each reconfiguration, and logs response time and decision outcomes for performance evaluation.

6. A method (300) for underground utility mapping and electrical cable fault detection using a device, the method (300) comprising:emitting (302), by one or more sensors positioned on a lower surface of the device, controlled electromagnetic signals into the ground;receiving (304), by the one or more sensors, reflected signals from underground utilities or electrical cables;generating (306), by the one or more sensors, data corresponding to location and depth of the underground utilities or faults in the electrical cables;connecting (308) a test cable phase-wise to an electrical cable under inspection, wherein each phase is tested individually;injecting (310), by a probe assembly, one or more types of pulses or signals into the electrical cables using a 10-switch mechanism to generate signals indicative of fault location;receiving (312), by a processor, the data from the one or more sensors and the signals from the probe assembly, and identifying types of underground utilities based on the received data and generating utility mapping data;extracting (314), by the processor, signal patterns from the received signals by matching the signals to stored reference patterns;identifying (316), by the processor, faults in the electrical cables based on the matched signal patterns;classifying (318), by the processor, using an artificial intelligence (Al) technique, the identified faults in the electrical cables and determining respective locations;generating (320), by the processor, instructions by evaluating the classified fault data against pre-defined thresholds, applying anomaly detection algorithms, and performing errorchecking routines;operating (322), by the processor, a relay unit comprising a plurality of switchable relays to alter signal paths based on the generated instructions, and adjusting signal routing using Al logic to isolate fault regions or re-route signals for further fault identification; and transmitting (324), by the processor, output data to a computing device, wherein the output data comprises the utility mapping data, the identified faults, and the fault locations.

7. The method (300) as claimed in claim 8, wherein the utility mapping data comprises geospatial coordinates of the underground utilities and is visualised in real-time on a connected computing device.

8. The method (300) as claimed in claim 8, wherein the artificial intelligence techniques comprise a supervised machine learning model trained to classify the type of faults based on labelled signal patterns.

9. The method (300) as claimed in claim 8, wherein the relay unit dynamically reconfigures internal diagnostic signal paths based on the instructions for real-time signal integrity validation.

10. The method (300) as claimed in claim 8, further comprises logging relay response times and Al-based decision outcomes for system performance evaluation and optimisation.