System and method for automatic calibration of stator ground fault protection for generator

Abstract

A system (200) and method (400) for automatic calibration of stator ground fault protection for a generator is disclosed. The system (200) includes an intelligent electronic device, IED, (202) configured to operate in a first calibration mode to connect with a ground terminal (204) and in a second calibration mode to connect with a digital potentiometer (206). The system (200) further comprises a processing unit (104) to: obtain a phase angle value and a fault resistance value from the IED (202) by operating the IED (202) in its first calibration mode; determining one or more of a correct phase angle value and a correct fault resistance value of the IED (202) based on deviations from the respective desired values using linear regression algorithm (s); evaluating the determined values at different resistance values by operating the IED (202) in its second calibration mode; and configuring the IED with the correction value (202) if the evaluation for stator ground fault protection is successful.

Description

Technical Field

[0001] This invention belongs to the field of generator protection systems. More specifically, this invention relates to an automated system and method for using machine learning techniques to calibrate stator ground fault protection in a generator to enhance accuracy, reliability, and efficiency. Background Technology

[0002] In power generation systems, generators are expensive and critical pieces of equipment. Appropriate protection mechanisms ensure that generators are protected from faults, abnormal operating conditions, and potential damage. Generator protection plays a vital role in maintaining power system stability and enabling continuous operation. 100% stator ground fault protection is essential for generators to detect and mitigate specific types of faults (which, if left unaddressed, could have serious consequences), ensure personnel safety, protect generator equipment, maintain power system stability, and comply with industry regulations. Neglecting such protection measures can lead to safety hazards, equipment damage, power system instability, and non-compliance with regulatory requirements.

[0003] Current existing technologies for generator protection involve the use of intelligent electronic devices (IEDs) to detect and mitigate stator ground faults, which are crucial for the safe and efficient operation of generators. These IEDs are manually calibrated to ensure they accurately detect faults and protect the generator from damage and power interruption. Manual calibration involves adjusting settings based on empirical data, expert knowledge, and testing under various conditions. This approach is widely used across power plants to maintain power system stability and ensure continuous operation.

[0004] However, manual calibration of stator ground fault protection systems presents several challenges. Manual calibration is a time-consuming, tedious, and complex activity requiring significant expertise and potentially taking four to eight hours to complete, regardless of location. The effectiveness of manual calibration relies heavily on individual expertise and experience, which can vary considerably. This can lead to inaccurate current threshold picking, time delays, or other parameters, and may result in false tripping, delayed fault detection, or failure to detect actual faults, thus compromising the effectiveness of the protection system. Manual calibration is not only laborious but also repetitive, requiring considerable effort to accurately determine the compensation angle and grounding resistance. This involves multiple instances of ground faults to determine precise compensation values, making the process time-consuming.

[0005] Furthermore, given that stator ground faults typically involve low fault currents, manual calibration without proper equipment and expertise can lead to insufficient sensitivity of the protection system. This can hinder the detection of faults with lower magnitudes, increasing the risk of equipment damage, safety hazards, and potential system instability. Manual calibration can also result in longer response times for stator ground fault protection. If the calibration settings are not optimized or if the manual adjustments are inaccurate, the time delay in tripping the generator may be longer than necessary. Delayed response times allow the fault to escalate, leading to further damage to the generator and potential power system outages. It should also be noted that generator protection systems typically involve multiple protective relays and devices that need to coordinate to operate correctly. Manual calibration can lead to inappropriate coordination between the settings within the equipment and the actual values.

[0006] Traditional solutions to these problems are limited. Existing technologies are constrained by their inability to adapt to real-time changes, the significant time requirements of calibration, and the risk of human error. Manual processes remain the standard practice, accompanied by all their associated drawbacks. This lack of automation in the calibration process underscores the need for a solution that addresses the accuracy, time efficiency, and reliability issues inherent in manual calibration. This invention aims to solve these problems to significantly enhance the accuracy, reliability, and efficiency of the calibration process, thereby reducing the risk of false trips and power interruptions, minimizing human error, and allowing real-time adaptation to changing conditions. Summary of the Invention

[0007] The object of this invention is achieved by a system for automatic calibration of stator ground fault protection for generators. The system includes an intelligent electronic device (IED) configured to operate in a first calibration mode and a second calibration mode. The system further includes a grounding terminal adapted to connect to the IED when it operates in its first calibration mode. The grounding terminal is configured to provide a controlled path from the IED to ground. The system further includes a digital potentiometer adapted to connect to the IED when it operates in its second calibration mode. The digital potentiometer is configured to simulate a series of ground fault conditions for the IED at different resistance values. The system further includes a processing unit. The processing unit is configured to obtain a phase angle value and a fault resistance value from the IED by operating the IED in its first calibration mode. The processing unit is further configured to determine one or more of the correct phase angle value and the correct fault resistance value of the IED based on the deviations of the obtained phase angle value and the fault resistance value from their respective expected values ​​using (multiple) linear regression algorithms. The processing unit is further configured to: evaluate one or more of the correct phase angle value and correct fault resistance value of the determined IED for stator ground fault protection at different resistance values ​​by operating the IED in its second calibration mode. The processing unit is further configured to: if the evaluation for stator ground fault protection is successful, configure the IED using one or more of the correct phase angle value and correct fault resistance value.

[0008] In one or more embodiments, the processing unit is configured to close the contact between the ground terminal and the IED to operate the IED in its first calibration mode.

[0009] In one or more embodiments, the processing unit is configured to disconnect the contact between the ground terminal and the IED, and close the contact between the digital potentiometer and the IED to operate the IED in its second calibration mode.

[0010] In one or more embodiments, the processing unit is further configured to determine at least one of the IED's pick-up value and trip value based on the IED's configuration.

[0011] In one or more embodiments, the processing unit is further configured to initiate IED calibration in response to any deviation of the phase angle value and the fault resistance value from their respective expected values.

[0012] In one or more embodiments, automatic calibration for stator ground fault protection of the generator is implemented as part of a separate application or incorporated into the digital twin of the generator.

[0013] In one or more embodiments, the system further includes a communication module configured to transmit calibration results and configuration updates to a user.

[0014] In one or more embodiments, the linear regression algorithm utilized by the processing unit is configured to adjust the weighting factor based on historical calibration data of the IED in detecting stator ground faults to determine one or more of the correct phase angle value and the correct fault resistance value.

[0015] The object of the present invention is also achieved by a method for automatic calibration of stator ground fault protection for a generator. The method includes operating the intelligent electronic device (IED) in a first calibration mode by connecting an IED to a grounding terminal. The grounding terminal is configured to provide a controlled path from the IED to the ground. The method further includes obtaining a phase angle value and a fault resistance value from the IED by operating the IED in its first calibration mode. The method further includes determining one or more of the correct phase angle value and correct fault resistance value of the IED based on the deviations of the obtained phase angle value and fault resistance value from their respective expected values ​​using (multiple) linear regression algorithms. The method further includes operating the IED in a second calibration mode by connecting the IED to a digital potentiometer. The method further includes using the digital potentiometer to simulate a series of ground fault conditions for the IED at different resistance values. The method further includes evaluating one or more of the determined correct phase angle value and correct fault resistance value of the IED for stator ground fault protection at different resistance values ​​by operating the IED in its second calibration mode. The method further includes configuring the IED using one or more of the correct phase angle value and correct fault resistance value if the evaluation for stator ground fault protection is successful.

[0016] The object of the present invention is further achieved by a computer program product having machine-readable instructions stored therein, which, when executed by one or more processing units, cause one or more processing units to perform the above-described method steps.

[0017] Nevertheless, other aspects, features, and advantages of the invention will become apparent from the following detailed description—merely by illustrating several specific embodiments and implementations, including the best mode contemplated for carrying out the invention. The invention is also capable of other and different embodiments, and certain details thereof may be modified in various obvious ways, all without departing from the scope of the invention. Therefore, the drawings and description should be considered illustrative in nature and not restrictive. Attached Figure Description

[0018] A more complete understanding of the invention and its many accompanying aspects will become readily apparent and better understood when considered in conjunction with the accompanying drawings, which are as follows: Figure 1This is a block diagram representation of a computational system for automatic calibration of stator ground fault protection for a generator according to one or more embodiments of the present disclosure; Figure 2 This is a circuit diagram of an automatic calibration system for stator ground fault protection of a generator according to one or more embodiments of the present invention; Figure 3 This is an architecture for an automatic calibration function for stator ground fault protection of a generator, according to one or more embodiments of the present invention. Figure 4 This is a flowchart of a method for an automatic calibration function of automatic calibration for stator ground fault protection of a generator according to one or more embodiments of the present invention; and Figure 5 This is a flowchart of an automatic calibration function according to one or more embodiments of the present invention. Detailed Implementation

[0019] Various embodiments are described with reference to the accompanying drawings, wherein the same reference numerals are used throughout to refer to the same elements. In the following description, numerous specific details are set forth for purposes of explanation in order to provide a thorough understanding of one or more embodiments. It will be apparent that such embodiments can be practiced without these specific details.

[0020] This document discloses examples of methods, systems, and computer program products for automatic calibration of stator ground fault protection for generators. In the following description, numerous specific details are set forth for purposes of explanation in order to provide a comprehensive understanding of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention can be practiced without these specific details, or with equivalent arrangements. In other instances, well-known structures and devices are shown in block diagram form to avoid unnecessarily obscuring embodiments of the invention.

[0021] For the purposes of this invention, a stator ground fault is an electrical fault condition in the stator windings of a generator or motor, where an insulation failure allows current to flow to ground, potentially leading to damage or operational problems. It can occur due to insulation breakdown from aging, thermal stress, mechanical vibration, or environmental conditions. Calibration is required to ensure that the protective system accurately detects such faults, thereby preventing further damage and maintaining system reliability. Proper calibration helps to set the sensitivity of the detection system to strike a balance between avoiding false alarms and ensuring timely detection and handling of genuine faults.

[0022] refer to Figure 1The illustration shows a block diagram of a computational arrangement 100 for automatic calibration of stator ground fault protection for a generator according to one or more embodiments of the present invention. It will be understood that the computational arrangement 100 described herein can be implemented in various forms of hardware, software, firmware, dedicated processors, or combinations thereof. One or more of these embodiments may take the form of a computer program product, including program modules accessible from a computer-usable or computer-readable medium that stores program code for use by or in connection with one or more computers, processors, or instruction execution systems. For the purposes of this specification, the computer-usable or computer-readable medium may be any device that can contain, store, transmit, propagate, or deliver the program for use by or in connection with an instruction execution system, device, or apparatus. The medium can be an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system (or device or apparatus), or the transmission medium itself, which serves as a signal carrier, is not included in the definition of a physical computer-readable medium, including semiconductor or solid-state memory, magnetic tape, removable computer floppy disks, random access memory (RAM), read-only memory (ROM), rigid magnetic disks, and optical disks, such as CD-ROMs, CD-ROMs, and DVDs. As is known to those skilled in the art, both the processor and program code used to implement each aspect of this technology can be centralized or distributed (or a combination thereof).

[0023] In the example, computing arrangement 100 may be embodied as a computer program product programmed for automatic calibration of stator ground fault protection for a generator. Computing arrangement 100 may be incorporated into one or more physical packages (e.g., chips). As an example, a physical package includes an arrangement of one or more materials, components, and / or lines on a structural assembly (e.g., a substrate) to provide one or more properties, such as physical strength, size conservation, and / or limitation of electrical interactions. It is contemplated that, in some embodiments, the computing device may be implemented in a single chip. As illustrated, computing arrangement 100 includes communication mechanisms, such as a bus 102 for transferring information between components of computing arrangement 100. Computing arrangement 100 includes one or more processing units 104 and one or more memory units 106. Here, memory units 106 are communicatively coupled to processing units 104. In the example, memory unit 106 may be embodied as a computer-readable medium storing program code segments of a computer program that can be loaded into and / or executed in a system to cause computing arrangement 100 to perform steps for performing the stated purpose.

[0024] Generally, as used herein, the term "processing unit" refers to a computing element operable to respond to and process instructions driving the computing arrangement 100. Optionally, a processing unit includes, but is not limited to, a microprocessor, microcontroller, Complex Instruction Set Computing (CISC) microprocessor, Reduced Instruction Set Computing (RISC) microprocessor, Very Long Instruction Word (VLIW) microprocessor, or any other type of processing circuitry. Furthermore, the term "processing unit" can refer to one or more individual processors, processing devices, and various elements associated with processing devices that can be shared by other processing devices. Additionally, one or more individual processors, processing devices, and elements are arranged in various architectures to respond to and process instructions driving the computing arrangement 100.

[0025] Here, memory unit 106 may be volatile memory and / or non-volatile memory. Memory unit 106 may be coupled to communicate with processing unit 104. Processing unit 104 may execute instructions and / or code stored in memory unit 106. Various computer-readable storage media may be stored in and accessed from memory unit 106. Memory unit 106 may include any suitable elements for storing data and machine-readable instructions, such as read-only memory, random access memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, hard disk drive, removable media drive for handling compressed disks, digital video disks, floppy disks, magnetic tape cassettes, memory cards, etc.

[0026] Specifically, processing unit 104 has a connection to bus 102 to execute instructions and process information stored in memory unit 106. Processing unit 104 may include one or more processing cores, each configured to execute independently. Multi-core processors enable multiprocessing within a single physical package. Examples of multi-core processors include two, four, eight, or more processing cores. Alternatively or additionally, processing unit 104 may include one or more microprocessors configured in series via bus 102 to enable independent execution of instructions, pipelines, and multithreading. Processing unit 104 may also include one or more dedicated components to perform certain processing functions and tasks, such as one or more digital signal processors (DSPs) and / or one or more application-specific integrated circuits (ASICs). Other dedicated components that help perform the functions of the invention described herein include one or more field-programmable gate arrays (FPGAs) (not shown), one or more controllers (not shown), or one or more other dedicated computer chips.

[0027] The computing arrangement 100 may further include an interface 108, such as a communication module (the terms are used interchangeably hereafter), which enables the computing arrangement 100 to communicate with other systems to receive and transmit information. The communication module 108 may include a medium (e.g., a communication channel) through which the computing arrangement 100 communicates with other systems. Examples of the communication module 108 may include, but are not limited to, communication channels in a computer cluster, local area communication channels (LANs), cellular communication channels, wireless sensor communication channels (WSNs), cloud communication channels, metropolitan area communication channels (MANs), and / or the Internet. Optionally, the communication module 108 may include one or more of wired connections, wireless networks, cellular networks (such as 1G mobile networks, 3G mobile networks, 4G mobile networks, 5G mobile networks), and Zigbee connections.

[0028] Computing setup 100 also includes a database 110. As used herein, database 110 is an organized collection of structured data, typically stored in a computer system and designed to be easily accessed, managed, and updated. Database 110 may take the form of a central repository of information that can be queried, analyzed, and processed to support various applications and business processes. In computing setup 100, database 110 provides mechanisms for storing, retrieving, updating, and deleting data, and typically includes features such as data validation, security, backup and recovery, and data modeling.

[0029] The computing arrangement 100 further includes an input device 112 and an output device 114. Depending on the specific application of the computing arrangement 100, the input device 112 can take various forms. In this example, the input device 112 may include one or more of a keyboard, mouse, touchscreen display, microphone, camera, or any other hardware component that enables a user to interact with the computing arrangement 100. Furthermore, the output device 114 may be in the form of a display, printer, communication channel, etc., without any limitations.

[0030] In this computing arrangement 100, the processing unit 104 and auxiliary components are connected to the memory unit 106 via bus 102. The memory unit 106 includes both dynamic memory (e.g., RAM, disk, writable optical disc, etc.) and static memory (e.g., ROM, CD-ROM, etc.) for storing executable instructions that, when executed, perform the steps described herein for automatic calibration of stator ground fault protection of a generator. Specifically, the memory unit 106 includes a calibration module 116 for performing the steps for said purpose.

[0031] refer to Figure 2The illustration shows an exemplary circuit diagram of a system 200 (denoted by reference numeral 200) for automatic calibration of stator ground fault protection for a generator according to one or more embodiments of the present invention, system 200 being part of a larger stator ground fault protection system 10. System 200 of the present invention is designed to automate and refine the calibration process, thereby ensuring optimal operation of the stator ground fault protection system 10. System 200 introduces a structured approach to such calibration using machine learning algorithms. Traditional manual calibration methods, which rely on operator expertise and experience, present numerous challenges, including the risk of inaccurate setup, the time-intensive nature of the calibration process, and the potential for reduced sensitivity and increased response time of the protection system. System 200 for automatic calibration aims to overcome these challenges by providing a structured and automated calibration process, which enhances the accuracy, reliability, and efficiency of stator ground fault protection.

[0032] As illustrated, system 200 includes an intelligent electronic device (IED) 202. IED 202 is a microprocessor-based controller for system 200 (such as a generator), configured to collect, analyze, and act on data. IED 202 is capable of performing a wide range of functions, including protection, control, monitoring, and metering. IED 202 is configured to communicate with other devices in system 200 and is used in various parts of the substation and distribution network. System 200 also includes a grounding terminal 204. Grounding terminal 204 is adapted to connect to IED 202. Specifically, grounding terminal 204 is configured to provide a controlled path from IED 202 to the ground. The function of grounding terminal 204 is to simulate real-world grounding scenarios, enabling IED 202 to evaluate and calibrate the stator ground fault protection system under conditions that closely mimic actual operating environments. By providing a controlled grounding path, grounding terminal 204 ensures that IED 202 can accurately determine necessary adjustments to protection settings, thereby enhancing the accuracy of stator ground fault protection. System 200 further includes a digital potentiometer 206. The digital potentiometer 206 is configured to simulate a series of ground fault conditions of IED 202 at different resistance values. The inclusion of the digital potentiometer 206 allows for a high degree of accuracy when simulating fault conditions because it can accurately replicate different degrees of ground faults by adjusting its resistance. This simulation allows for the evaluation of the response of IED 202 to various fault scenarios to ensure the effectiveness and reliability of the stator ground fault protection system 10.

[0033] In this system 200, IED 202 is configured to operate in a first calibration mode and a second calibration mode. Here, grounding terminal 24 is adapted to connect to IED 202 when IED 202 is operating in its first calibration mode. That is, when IED 202 is operating in the first calibration mode, grounding terminal 204 is engaged to establish a direct and controlled path from IED 202 to ground. The first calibration mode of IED 202 establishes a basic calibration setup by connecting to grounding terminal 204, thereby providing a controlled path from IED 202 to ground. By providing a controlled grounding path, grounding terminal 204 ensures that IED 202 can accurately determine the necessary adjustments to the protection settings, thereby enhancing the accuracy of stator ground fault protection. The first calibration mode allows for the initial acquisition of phase angle values ​​and fault resistance values, which are key parameters in the calibration of the generator's stator ground fault protection. These initial values ​​serve as a benchmark for evaluating the accuracy and effectiveness of the stator ground fault protection system 10.

[0034] Furthermore, the digital potentiometer 206 is adapted to connect to the IED 202 when the IED 202 is operating in its second calibration mode. In the second calibration mode, the IED 202 is connected to the digital potentiometer 206, thus diverging from the grounding terminal connection utilized in the first calibration mode. In this mode, the digital potentiometer 206 simulates a series of ground fault conditions by changing the resistance value, thereby providing a test environment for the IED 202. This simulation allows for evaluation of the stator ground fault protection system 10 under different fault conditions and fine-tuning of the IED 202 settings to ensure optimal performance under different operating scenarios. The digital potentiometer 206 facilitates a dynamic and flexible calibration process, where the settings of the IED 202 can be fine-tuned based on the simulated fault conditions, thereby ensuring optimal protection for the generator. The digital potentiometer 206 provides a controlled and measurable means to test the calibration adjustments made in the first calibration mode. This testing ensures that the adjustments are effective across a series of fault conditions, thereby further enhancing the reliability and accuracy of the stator ground fault protection.

[0035] System 200 further implements processing unit 104 to perform various functions. This includes processing data, managing tasks, and ensuring efficient communication between the various components of system 200, thereby facilitating its overall functionality and performance. More specifically, processing unit 104 within system 200 is indispensable for orchestrating various operational and analytical tasks. Processing unit 104 interprets data from multiple sources, executes algorithms to process the information, and coordinates the activities of other components to ensure cohesive functionality. Processing unit 104 is configured to make real-time decisions based on processed data, optimize performance, and facilitate adaptive responses to changing conditions or inputs.

[0036] Processing unit 104 is configured to obtain phase angle and fault resistance values ​​from IED 202 by operating IED 202 in its first calibration mode. As discussed, the first calibration mode is designated for initial data acquisition, where IED 202, in conjunction with grounding terminal 204, establishes a controlled path to ground to simulate stator ground fault conditions. During this phase, processing unit 104 interfaces with IED 202 to extract phase angle and fault resistance values, both critical to the calibration process. The phase angle value indicates the angle difference between current and voltage at the fault point, which helps identify and diagnose the nature and severity of the stator ground fault. Similarly, the fault resistance value provides details about the resistance encountered by the fault current, thus providing valuable information about the characteristics of the fault and the effectiveness of the grounding path. By operating IED 202 in the first calibration mode, processing unit 104 ensures that these values ​​are obtained under controlled conditions that closely mimic actual fault scenarios. This approach allows for a more accurate and reliable calibration process because the obtained values ​​serve as a dataset upon which further calibration adjustments and evaluations are based.

[0037] In this embodiment, the processing unit 104 is configured to close the contacts between the ground terminal 204 and the IED 202 to operate the IED 202 in its first calibration mode. Specifically, the processing unit 104 within the system 200 is configured to initiate the first calibration mode of the IED 202 by closing the contacts between the ground terminal 204 and the IED 202. This action establishes a direct electrical connection between the IED 202 and the ground terminal 204, enabling the IED 202 to simulate ground fault conditions by providing a controlled path to ground. This connection allows the IED 202 to measure phase angle and fault resistance values ​​under conditions that closely mimic actual ground fault scenarios.

[0038] Processing unit 104 is further configured to determine one or more of the correct phase angle value and correct fault resistance value of IED 202 based on the deviation of the obtained phase angle value and fault resistance value from their respective expected values ​​using (multiple) linear regression algorithms. Specifically, processing unit 104 in system 200 has the capability to refine the calibration process by determining the correct phase angle value and correct fault resistance value of IED 202. This determination is based on analyzing the deviation of the initially obtained phase angle value and fault resistance value from their expected values. For this purpose, processing unit 104 employs linear regression algorithms that identify patterns in the data and predict results based on observed trends. For this purpose, these values ​​are then analyzed by processing unit 104 when IED 202 is operating in the first calibration mode and the necessary values ​​are obtained via close contact with grounding terminal 204. The linear regression algorithm evaluates how the obtained values ​​deviate from the expected values ​​under normal operating conditions. This deviation indicates the degree of adjustment required to align IED 202 with the actual operating environment of the generator, thereby ensuring that the stator ground fault protection is accurately adjusted.

[0039] In this embodiment, the linear regression algorithm utilized by the processing unit 104 is configured to adjust weighting factors based on historical calibration data of the IED 202 in detecting stator ground faults to determine one or more of the correct phase angle and fault resistance values. It will be understood that the historical calibration data provides information about past calibration settings, fault detection instances, and corresponding operating conditions of the IED 202, serving as a valuable reference point for the calibration process. By analyzing this historical calibration data, the linear regression algorithm can identify patterns and trends indicating the behavior of the IED 202 and its interaction with different fault conditions. This analysis allows the algorithm to determine the “weights” of different factors affecting the accuracy of the phase angle and fault resistance values ​​measured by the IED 202. For example, certain operating conditions may consistently lead to specific deviations in the fault resistance value, highlighting the need to adjust the weighting factors associated with that parameter in the calibration model. This ensures that the calibration of the IED 202 evolves dynamically based on operational insights, resulting in continuous improvements in stator ground fault detection and mitigation, thereby improving the reliability and effectiveness of stator ground fault protection.

[0040] Processing unit 104 is further configured to evaluate one or more of the determined correct phase angle and correct fault resistance values ​​of IED 202 for stator ground fault protection at different resistance values ​​by operating IED 202 in its second calibration mode. As discussed, in the second calibration mode, digital potentiometer 206 is used to create a series of ground fault conditions by varying the resistance value. This allows processing unit 104 to evaluate how well IED 202 performs under these different conditions with its newly calibrated settings for phase angle and fault resistance. The evaluation process involves comparing the response of IED 202 to these simulated faults with the expected results based on the calibrated settings. This step verifies the effectiveness of the calibration adjustments made based on the initial data obtained in the first calibration mode and refined by a linear regression algorithm. By testing IED 202 at different simulated resistance values, processing unit 104 ensures that stator ground fault protection is reliable across a range of fault scenarios.

[0041] In this embodiment, processing unit 104 is configured to disconnect the contacts between ground terminal 204 and IED 202, and close the contacts between digital potentiometer 206 and IED 202 to operate IED 202 in its second calibration mode. That is, processing unit 104 is configured to switch IED 202 from a first calibration mode to a second calibration mode through specific operations involving ground terminal 204 and digital potentiometer 206. To facilitate this switch, processing unit 104 first disconnects the contacts between ground terminal 204 and IED 202, thereby effectively breaking the direct ground path established during the first calibration mode. After disconnecting from ground terminal 204, processing unit 104 continues to close the contacts between digital potentiometer 206 and IED 202 to initiate the second calibration mode. This sequence of operations managed by processing unit 104 ensures proper transition between the two calibration modes, thereby facilitating the calibration process.

[0042] Processing unit 104 is further configured to configure IED 202 using one or more of the correct phase angle value and correct fault resistance value if the evaluation for stator ground fault protection is successful. Processing unit 104 completes the calibration process by configuring IED 202 using the determined correct phase angle value and correct fault resistance value. This configuration step depends on a successful evaluation of stator ground fault detection under simulated fault conditions created during the second calibration mode. The evaluation phase facilitated by digital potentiometer 206 allows processing unit 104 to evaluate the performance of IED 202 across a series of simulated ground fault scenarios using different resistance values. After obtaining satisfactory results from this evaluation—indicating that the response of IED 202 aligns with the expected results based on the newly calibrated settings—processing unit 104 continues to implement these settings into IED 202. This involves updating IED 202 using the correct phase angle value and correct fault resistance value, thereby optimizing its ability to accurately detect and mitigate stator ground faults. This, in turn, ensures that the IED 202 is equipped with the most reliable parameters for stator ground fault detection, thereby making a significant contribution to the safety and efficiency of generator operation within the power system.

[0043] In some embodiments, processing unit 104 is further configured to determine at least one of a pick-up value and a trip value of IED 202 based on the configuration of IED 202. This determination is an extension of a calibration process, wherein processing unit 104 establishes a threshold at which IED 202 initiates protective action using calibrated phase angle and fault resistance values. Here, the pick-up value refers to the minimum fault current or condition under which protection system 10 is designed to activate or “pick up” a signal indicating a fault condition. By simulating various resistance levels using digital potentiometer 206, system 200 can determine the minimum level of fault that can be reliably detected, thereby ensuring that protection system 10 is sufficiently sensitive to actual fault conditions. Similarly, the trip value is a point at which protection system 10 determines that the fault condition is significant enough to warrant protective action, such as isolating the affected portion of protection system 10. The variable resistance provided by the digital potentiometer 206 allows the system 200 to test at what fault severity the IED 202 should command a trip, thereby ensuring that the system 200 responds appropriately to actual fault conditions. By configuring the IED 202 with precise pick-up and trip values, the processing unit 104 ensures that protective actions are initiated at the appropriate time, enhancing the reliability and safety of the protection scheme.

[0044] Furthermore, in an embodiment, the processing unit 104 is further configured to initiate calibration of the IED 202 in response to any deviation of the phase angle value or the fault resistance value from their respective expected values. Here, the processing unit 104 within the system 200 is designed to proactively initiate the calibration process of the IED 202. This initiation is triggered in response to the detection that an operating parameter (specifically, the phase angle value or the fault resistance value) deviates from its respective expected standard. Specifically, when the phase angle value or the fault resistance value is detected to have deviated from its expected range, the processing unit 104 automatically triggers a calibration sequence for the IED 202. This ensures that the calibration of the IED 202 is responsive to real-time changes in the generator's operating environment. Therefore, the system 200 ensures that the IED 202 operates continuously with the latest and optimized settings.

[0045] In embodiments of the invention, automatic calibration for stator ground fault protection of a generator is implemented as part of a standalone application or incorporated into the generator's digital twin. That is, the system 200 provides versatility in its deployment because it can be implemented as part of a standalone application or integrated into the generator's digital twin. This flexibility allows the system 200 to be customized to specific operational needs, thereby enhancing its applicability across different generator systems and operational frameworks. When implemented as a standalone application, the system 200 acts as a dedicated calibration tool that operates independently to adjust and optimize the settings of the IED 202 for stator ground fault protection. Alternatively or additionally, incorporating the system 200 into the generator's digital twin extends its functionality and integration capabilities. The digital twin is a virtual model that mirrors the physical generator in real time, providing a platform for monitoring, analyzing, and simulating generator operation. By integrating the system 200 into this digital twin, the calibration process benefits from the extensive data and analytical capabilities of the digital twin environment.

[0046] In some embodiments, system 200 further implements a communication module 108 (from computing arrangement 100) to transmit calibration results and configuration updates to the user. The communication module 108 operates by compiling and sending detailed information about the calibration process, which may include, but is not limited to, corrected phase angle and fault resistance values ​​determined during calibration, any adjustments made to the pick-up and trip values ​​of IED 202, and a summary of calibration evaluation results under different simulated fault conditions. By providing this data, the communication module 108 allows the user to understand the modifications made to the settings of IED 202 and the implications of these changes for stator ground fault protection. Therefore, the communication module 108 ensures that the user remains informed of the status and results of the calibration process, enabling informed decision-making.

[0047] Now for reference Figure 3 The illustration shows the architecture of an automatic calibration function (denoted by reference numeral 300) for automatic calibration of stator ground fault protection of a generator according to one or more embodiments of the present invention. The automatic calibration function 300 includes an operating sequence. The automatic calibration function 300 begins with the prerequisite of setting the IED (denoted by box 302) to calibration mode. Specifically, the IED 302 operates in two calibration modes and provides measurements of the phase angle (Φ20 / 2311:310) (denoted by box 302a) and the fault resistance (Rf / 2311:309) (denoted by box 302b).

[0048] In the workflow of the automatic calibration function, at box 304, the set of data related to the compensation angle and compensation resistance values ​​recorded during the manual calibration process is used as the training dataset for the linear regression algorithm. At box 306, the linear regression algorithm, as a machine learning algorithm, is used to determine the correction angle and resistance values ​​based on the training dataset for accurate calibration. At box 308, assuming this represents the final output of the linear regression algorithm, which provides a corrected phase angle value (2311:15) based on the measured phase angle value from IED 302 (denoted by box 302c).

[0049] Further, similar to box 304, at box 310, the training dataset is used to calibrate the fault resistance value 302b. At box 312, another instance of the linear regression algorithm is implemented, specifically for determining the corrected fault resistance value. At box 314, it is assumed that the corrected fault resistance value (2311:309Rf) (represented by box 302d) is generated based on the measured Rf value from the IED and the output of the linear regression algorithm. Additionally, at box 316, a configuration tool is used to feed the corrected phase angle and fault resistance value back into the IED for calibration. A decision is implemented to check whether the corrected fault resistance value obtained from the linear regression algorithm is equal to 0.

[0050] If the calibrated fault resistance value is equal to 0, then at box 318 (Function 1), the digital potentiometer (POT) controller is activated to set the POT value for further testing and evaluation. At box 320, the digital potentiometer is used to perform a process of checking the calibration value by simulating various ground fault conditions using different resistance values ​​(Function 2). At box 322, based on the simulated ground fault conditions at different resistance values, the digital potentiometer is used to evaluate the pick-up and trip values ​​for stator ground fault protection (Function 3).

[0051] refer to Figure 4The diagram illustrates a flowchart (denoted by reference numeral 400) of a method for an automatic calibration function of stator ground fault protection for a generator according to one or more embodiments of the present invention. Various steps of method 400 (described below) are described, which may be performed in computational arrangement 100 or specifically in processing unit 104 of computational arrangement 100. It will be appreciated that although method 400 is illustrated and described as a sequence of steps, it is contemplated that various embodiments of method 400 may be performed in any order or different combinations, and it is not necessary to include all the illustrated steps.

[0052] At step 410, method 400 includes operating the intelligent electronic device (IED) in a first calibration mode by connecting it to a ground terminal, the ground terminal being configured to provide a controlled path from the IED to ground. That is, the process begins by setting the IED to operate in a first calibration mode, which is activated by establishing a connection between the IED and the ground terminal. The first calibration mode is specifically designed to create a controlled path from the IED to ground to simulate the grounding conditions the IED would encounter during an actual stator ground fault.

[0053] At step 420, method 400 includes obtaining phase angle and fault resistance values ​​from the IED by operating the IED in its first calibration mode. That is, when in the first calibration mode, method 400 involves obtaining key parameters from the IED, including phase angle and fault resistance values. These values ​​help determine the calibration status of the IED with respect to a stator ground fault. The obtained phase angle and fault resistance values ​​are compared with their expected values, which represent ideal conditions when no fault is present.

[0054] At step 430, method 400 includes: using (multiple) linear regression algorithms to determine one or more of the correct phase angle value and correct fault resistance value of the IED based on the deviations of the obtained phase angle value and fault resistance value from their respective expected values. That is, if there is any difference between the obtained values ​​and the expected values, method 400 continues to utilize (multiple) linear regression algorithms to determine the correct phase angle value and correct fault resistance value. Here, the linear regression algorithm analyzes the deviations and predicts the correct values ​​required for accurate calibration of the IED.

[0055] At step 440, method 400 includes operating the IED in a second calibration mode by connecting the IED to a digital potentiometer. This second calibration mode is characterized by the connection between the IED and the digital potentiometer. The digital potentiometer is configured to assess various ground fault scenarios that the IED may encounter, which is achieved by manipulating the resistance values ​​encountered by the IED.

[0056] At step 450, method 400 includes simulating a series of ground fault conditions for the IED at different resistance values ​​using a digital potentiometer. That is, once the IED is connected to the digital potentiometer and operating in a second calibration mode, method 400 continues simulating different ground fault conditions. The digital potentiometer systematically adjusts the resistance value, allowing the IED to experience these conditions as if they were faults occurring within a generator.

[0057] At step 460, method 400 includes: evaluating one or more of the determined correct phase angle value and correct fault resistance value of the IED for stator ground fault protection at different resistance values ​​by operating the IED in its second calibration mode. That is, method 400 then involves evaluating the determined correct phase angle value and fault resistance value. This evaluation is performed by observing the performance of the IED in the second calibration mode as the IED responds to simulated fault conditions presented by a digital potentiometer.

[0058] At step 470, method 400 includes: if the evaluation for stator ground fault protection is successful, configuring the IED using one or more of the correct phase angle value and the correct fault resistance value. That is, if the evaluation confirms that the IED's response to simulated fault conditions is within acceptable parameters, method 400 terminates by configuring the IED using the verified correct phase angle value and fault resistance value. This configuration ensures that the stator ground fault protection is fine-tuned and calibrated to respond appropriately under actual fault conditions.

[0059] refer to Figure 5 The diagram illustrates a flowchart of an automatic calibration function (denoted by reference numeral 500) according to one or more embodiments of the present invention. Automatic calibration function 500 provides an algorithm for automatic calibration of stator ground fault protection for a generator. At block 502, process 500 begins. At block 504, process 500 begins by initializing variables and configuration parameters to the device from a calibration tool (such as Digsi). Subsequently, at block 506, the stator is connected to the grounding terminal (calibration terminal), thereby establishing the necessary physical interface for calibration. After the connection, at block 508, process 500 involves reading the phase angle value (φ20) and fault resistance value (Rf) from the intelligent electronic device (IED). These readings are used during the calibration process because they provide the initial data required for calibration evaluation.

[0060] At box 510, process 500 proceeds to the decision step, where it determines whether calibration is required based on predefined conditions or threshold levels. If calibration is not required, process 500 stops; otherwise, it continues to the next box 512. If calibration is required, process 500 employs a linear regression algorithm to automatically calculate the necessary compensation angle and primary resistance values. The linear regression algorithm utilizes existing data patterns to predict and set the optimal calibration values ​​for the IED. After calculating the calibration data, at box 514, the calibrated values ​​are then applied to the IED using a calibration tool. This application ensures that the IED settings reflect the updated calibration values.

[0061] After applying the calibrated data, at box 516, process 500 involves performing checks or verifications to ensure successful calibration. This may involve verifying that the IED's response to simulated fault conditions is consistent with the expected results. If the system confirms successful calibration, process 500 moves to box 518 to perform post-calibration checks. This includes setting pick-up (alarm) and trip values ​​in the IED to ensure it responds correctly under fault conditions. Further, process 500 includes a decision step at box 520. Here, process 500 involves evaluating whether the system performance meets the expected post-calibration criteria. If the performance is satisfactory, the calibration process ends at box 522; if the performance is not satisfactory, additional adjustments and recalibration may be required.

[0062] This invention provides a system 200 and a method 400 for automatic calibration of stator ground fault protection for generators. System 200 and method 400 take into account the dynamic characteristics of the generator system and various influencing factors during fault conditions, such as system impedance, fault location, and fault inception angle. System 200 and method 400 provide automatic calibration to facilitate periodic verification of resistance changes during fault conditions, thereby simplifying the calibration process and enhancing operational efficiency. It can be understood that manual calibration of a 100% stator ground fault detection system can be a time-consuming process, requiring expert knowledge and extensive testing. System 200, which provides automatic calibration, significantly reduces the time and effort required for calibration, enabling faster commissioning, maintenance, and troubleshooting activities. The normal time for calibrating a 100% ground fault is at least 4 to 8 hours. Using this solution, it can be reduced to less than 5 minutes.

[0063] The ability of System 200 to enhance the accuracy of 100% stator ground fault detection represents a significant advancement compared to existing technologies. System 200 enhances the accuracy of 100% stator ground fault detection by ensuring the detection system is properly calibrated to accurately identify and detect 100% stator ground faults, thereby minimizing the risk of false positives or false negatives. By automating the calibration process, System 200 helps maintain the reliability of the 100% stator ground fault detection system. System 200 continuously monitors generator operation and adjusts calibration parameters as needed, ensuring optimal performance and minimizing the possibility of missed detections or false alarms. System 200 further ensures that the stator ground fault detection system remains accurate over time, even in the presence of environmental changes or component aging. System 200 continuously monitors and adjusts calibration parameters as needed, allowing for real-time adaptation and maintaining optimal performance.

[0064] Furthermore, inaccurate or improperly calibrated stator ground fault detection systems can lead to false alarms, causing unnecessary downtime and maintenance. This System 200 helps minimize false alarms by maintaining the accuracy of the stator ground fault detection system, thereby reducing the risk of unnecessary intervention. In addition, automating the calibration process using this System 200 can lead to cost savings. It reduces the need for manual calibration processes, specialized equipment, and expert personnel, resulting in lower maintenance costs and increased operational efficiency. Generally, 100% accurate detection of stator ground faults is crucial for ensuring the safety of electrical systems and personnel. An automatically calibrated system minimizes the risk of undetected ground faults, thus helping to prevent electrical accidents, equipment damage, and potential hazards. Incorporating this feature will also benefit end users and significantly increase the market share of such products.

[0065] While the invention has been described in detail with reference to certain embodiments, it should be understood that the invention is not limited to these embodiments. In view of the invention, many modifications and variations may appear to those skilled in the art without departing from the scope of the various embodiments of the invention as described herein. Therefore, the scope of the invention is indicated by the following claims, rather than by the foregoing description. All changes, modifications, and variations within the meaning and equivalence of the claims should be considered within its scope.

Claims

1. A system (200) for automatic calibration of stator ground fault protection for a generator, the system (200) comprising: Intelligent electronic device IED (202), IED (202) is configured to operate in a first calibration mode and a second calibration mode; A grounding terminal (204) is adapted to connect to the IED (202) when the IED (202) is operating in its first calibration mode, and the grounding terminal (204) is configured to provide a controlled path from the IED (202) to the ground; A digital potentiometer (206) is adapted to connect to the IED (202) when the IED (202) is operating in its second calibration mode. The digital potentiometer (206) is configured to simulate a series of ground fault conditions of the IED (202) at different resistance values. as well as The processing unit (104) is configured to: The phase angle and fault resistance values ​​are obtained from IED(202) by operating IED(202) in its first calibration mode. One or more linear regression algorithms are used to determine one or more of the correct phase angle value and correct fault resistance value of IED(202) based on the deviations of the obtained phase angle value and fault resistance value from their respective expected values. By operating the IED (202) in its second calibration mode, one or more of the determined correct phase angle value and correct fault resistance value of the IED (202) are evaluated for stator ground fault protection at different resistance values. If the assessment for stator ground fault protection is successful, configure IED (202) using one or more of the correct phase angle value and the correct fault resistance value.

2. The system (200) according to claim 1, wherein the processing unit (104) is configured to close the contact between the ground terminal (204) and the IED (202) to operate the IED (202) in its first calibration mode.

3. The system (200) according to claim 2, wherein the processing unit (104) is configured to disconnect the contact between the ground terminal (204) and the IED (202), and close the contact between the digital potentiometer (206) and the IED (202) to operate the IED (202) in its second calibration mode.

4. The system (200) according to claim 1, wherein the processing unit (104) is further configured to determine at least one of the pick-up value and trip value of the IED (202) based on the configuration of the IED (202).

5. The system (200) according to claim 1, wherein the processing unit (104) is further configured to initiate calibration of the IED (202) in response to any deviation of the phase angle value and the fault resistance value from their respective expected values.

6. The system (200) of claim 1, wherein automatic calibration for stator ground fault protection of the generator is implemented as part of a separate application or incorporated into the digital twin of the generator.

7. The system (200) according to claim 1, the system (200) further includes a communication module (108) configured to transmit calibration results and configuration updates to a user.

8. The system (200) of claim 1, wherein one or more linear regression algorithms utilized by the processing unit (104) are configured to adjust weighting factors based on historical calibration data of the IED (202) in detecting stator ground faults to determine one or more of the correct phase angle value and the correct fault resistance value.

9. A method (400) for automatic calibration of stator ground fault protection for a generator, the method (400) comprising: By connecting the intelligent electronic device IED (202) to the ground terminal (204), the IED (202) is operated in the first calibration mode, and the ground terminal (204) is configured to provide a controlled path from the IED (202) to the ground; The phase angle value and fault resistance value are obtained from the IED(202) by operating the IED(202) in its first calibration mode; One or more linear regression algorithms are used to determine one or more of the correct phase angle value and correct fault resistance value of IED(202) based on the deviation of the obtained phase angle value and fault resistance value from their respective expected values; The IED (202) is operated in the second calibration mode by connecting the IED (202) to the digital potentiometer (206); A digital potentiometer (206) was used to simulate a series of ground fault conditions of the IED (202) under different resistance values; By operating the IED (202) in its second calibration mode, the correct phase angle value and the correct fault resistance value of the determined IED (202) are evaluated for stator ground fault protection at different resistance values, and if the evaluation for stator ground fault protection is successful, the IED (202) is configured using the correct phase angle value and the correct fault resistance value.

10. A computer program product having machine-readable instructions stored therein, which, when executed by a processing unit (104), cause the processing unit (104) to perform the method (400) according to claim 9.

Images