Protection method and system for shutdown of medium-voltage generator based on reverse power

Abstract

The invention relates to a protection method and system for shutdown of a medium-voltage generator based on reverse power, and the method comprises the steps: collecting three-phase voltage and current signals of the medium-voltage generator, and carrying out the preprocessing of the three-phase voltage and current signals; calculating real-time power based on the preprocessed three-phase voltage and current signals; judging whether the current medium-voltage generator generates reverse power or not based on a reverse power generation judgment rule and the real-time power, if so, calculating a reverse power quantized value, and comparing the reverse power quantized value with a reverse power grading threshold value to obtain a reverse power grade; executing corresponding shutdown protection measures of the medium-voltage generator based on the reverse power level; wherein the reverse power grading threshold value is optimized through reinforcement learning. The method is high in response speed, high in control precision, high in adaptability and suitable for safety protection requirements of the medium-voltage generator in multiple scenes.

Description

Technical Field

[0001] This invention relates to the field of generator safety technology, and mainly to a protection method and system for medium-voltage generator shutdown caused by reverse power. Background Technology

[0002] Medium-voltage generators are critical power supply equipment in industrial production, power backup, and new energy support scenarios. Their continuous and stable operation directly determines the continuity of industrial production and the reliability of power supply. In actual operation, medium-voltage generators often face various operating conditions, including parallel grid operation and independent load carrying. Affected by factors such as sudden load reduction, grid frequency fluctuations, and load imbalance, they are highly susceptible to reverse power phenomena. This means the generator transforms from a power output terminal to a power absorption terminal, continuously absorbing active power from the grid or other power sources. If reverse power issues are not managed promptly and effectively, it can lead to mechanical damage to the generator, instability in the power supply system, and even large-scale power outages. Therefore, reverse power protection is one of the core technical requirements for ensuring the safe operation of medium-voltage generators.

[0003] Chinese invention patent application CN115514025A discloses a nuclear power diesel generator set with an anti-reverse power device. This technical solution includes a main controller in the anti-reverse power device built into the nuclear power diesel generator set, which determines the real-time output power based on the collected real-time voltage and current values ​​of the generator set, and performs PID regulation on the difference between the target output power and the real-time output power to generate a power regulation signal. However, the above technical method only focuses on PID regulation based on the difference between the real-time output power and the target output power, without specifically designing a system for anti-reverse power as a specific abnormal operating condition. It lacks precise identification logic for anti-reverse power conditions and only covers general power regulation, failing to meet the needs of specialized anti-reverse power monitoring. Furthermore, the above technical solution only focuses on power difference regulation, without designing a quantitative analysis process related to anti-reverse power, or anti-reverse power grading thresholds and corresponding grading evaluation standards. It lacks protection measures of different strengths to match different levels of anti-reverse power, resulting in an inability to implement precise protection based on the severity of anti-reverse power, and insufficient targeting and effectiveness of safety protection. Summary of the Invention

[0004] To address the problems existing in the prior art, this invention proposes a protection method and system based on reverse power causing medium-voltage generator shutdown.

[0005] The technical solution of the present invention is as follows: On one hand, this invention proposes a protection method for medium-voltage generator shutdown caused by reverse power, the method comprising: Acquire the three-phase voltage and current signals of the medium-voltage generator and perform preprocessing; Real-time power is calculated based on the preprocessed three-phase voltage and current signals; Based on the reverse power occurrence judgment rules and real-time power judgment, it is determined whether the current medium-voltage generator has reverse power. If it has, the reverse power quantization value is calculated and compared with the reverse power classification threshold to obtain the reverse power level. Based on the reverse power level, the corresponding medium-voltage generator shutdown protection measures are implemented; The inverse power grading threshold is optimized through reinforcement learning.

[0006] Preferably, if the real-time power is less than 0 and the duration is greater than or equal to a preset time threshold, then it is determined that an inverse power state has occurred. The inverse power quantization value is obtained based on the proportion of the absolute value of real-time power in the rated power of the medium-voltage generator.

[0007] Preferably, the inverse power grading threshold is optimized through reinforcement learning, specifically through the following steps: Collect the operating status vector of the medium-voltage generator, including the current reverse power value, reverse power change rate, terminal voltage deviation rate, reverse power event frequency per unit time, preset temperature influence factor, and current reverse power classification threshold; Input the current running state vector into the policy function, output the corresponding adjustment action, and update the current inverse power classification threshold; Calculate the reward function for the adjustment action, and calculate the advantage function based on the reward function to evaluate the merits of performing the adjustment action under the current running state vector; The loss function is constructed with the objective of minimizing the squared error of the advantage function; Iterate through the above process until the preset maximum number of iterations is reached or the loss function converges, then stop iterating and output the optimal running state vector. The inverse power classification threshold extracted from the optimal operating state vector is the optimized inverse power classification threshold.

[0008] On the other hand, the present invention also provides a protection system for medium-voltage generator shutdown caused by reverse power, employing the protection method described in any one of the embodiments, the system comprising: High-precision reverse power detection module, main controller, dynamic load adjustment module and adaptive excitation control module; The high-precision reverse power detection module is electrically connected to the output terminal of the medium-voltage generator. It calculates the real-time power based on the three-phase voltage and current signals of the generator, and performs reverse power detection on the real-time power based on the reverse power occurrence judgment rules. If reverse power occurs, it calculates the reverse power quantization value and transmits it to the main controller. The main controller compares the inverse power quantization value with the inverse power classification threshold to obtain the inverse power level; based on the inverse power level, it generates control commands for the corresponding shutdown protection measures of the medium-voltage generator and sends them to the dynamic load regulation module and the adaptive excitation control module. The dynamic load regulation module is connected to the medium-voltage generator and is used to perform corresponding load regulation operations on the medium-voltage generator in response to the control command. An adaptive excitation control module, connected to a medium-voltage generator, is used to adjust the excitation current of the medium-voltage generator in response to the control command.

[0009] Preferably, the high-precision inverse power detection module includes: High-precision power sensor; The anti-interference signal filtering unit uses the Kalman filtering algorithm to filter the acquired three-phase voltage and current signals; The reverse power intelligent determination unit is used to detect reverse power in real time. If the real-time power is less than 0 and the duration is greater than or equal to a preset time threshold, it is determined that the current medium-voltage generator is in reverse power state. Based on the proportion of the absolute value of the real-time power in the rated power of the medium-voltage generator, the reverse power quantification value is obtained.

[0010] Preferably, the load adjustment operation corresponding to the dynamic load adjustment module includes at least one of the following: standby load input, non-critical load shedding, and dynamic adjustment of load allocation ratio.

[0011] Preferably, the dynamic load adjustment module includes a load priority sorting unit with a built-in load priority database of different importance, a high-speed switching switch group, and a redundant standby load unit for storing redundant loads.

[0012] Preferably, the adaptive excitation control module adopts a PID adaptive adjustment algorithm, which collects the terminal voltage feedback signal of the medium-voltage generator in real time, compares it with the rated voltage value of the medium-voltage generator, and dynamically corrects the excitation current adjustment parameters.

[0013] In another aspect, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method described in the present invention.

[0014] In another aspect, the present invention also provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the method described in the present invention.

[0015] The present invention has the following beneficial effects: 1. This invention provides a protection method and system for medium-voltage generator shutdown caused by reverse power. It captures three-phase voltage and current signals through a high-precision power sensor, eliminates harmonics and electromagnetic interference through a Kalman filter algorithm, and then quantifies the reverse power value by an intelligent reverse power determination unit. This improves the detection response speed, enhances the reliability and real-time performance of the detection data, and provides accurate data support for subsequent control. 2. This invention provides a protection method and system for medium-voltage generator shutdown caused by reverse power. On the one hand, it optimizes the reverse power classification threshold through reinforcement learning and dynamically adjusts the threshold parameters in combination with the generator operating state vector. On the other hand, it connects the main controller to the dynamic load adjustment module and the adaptive excitation control module, which are connected to the medium-voltage generator. The load side performs operations such as adding standby load and cutting off non-critical loads, while the excitation side uses a PID adaptive algorithm to dynamically correct the excitation current. This improves the accuracy of reverse power regulation, enhances the regulation response efficiency, and strengthens the system's adaptability and suppression capability to reverse power changes. 3. This invention provides a protection method and system for medium-voltage generator shutdown caused by reverse power. It utilizes reinforcement learning algorithms to optimize the reverse power grading threshold, solving the problem of poor adaptability of traditional fixed thresholds, improving the adaptability of grading thresholds, enhancing the system's adaptability to complex operating conditions, and increasing the flexibility and pertinence of the protection strategy. Attached Figure Description

[0016] Figure 1 This is a detailed flowchart of an embodiment of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] It should be understood that the step numbers used in the text are for ease of description only and are not intended to limit the order in which the steps are performed.

[0019] It should be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0020] The terms “comprising” and “including” indicate the presence of the described feature, whole, step, operation, element and / or component, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0021] The term “and / or” refers to any combination of one or more of the associated listed items, as well as all possible combinations, and includes these combinations.

[0022] Example 1: See Figure 1 This embodiment provides a protection method for medium-voltage generator shutdown caused by reverse power, the method comprising: S1. Acquire the three-phase voltage and current signals of the medium-voltage generator and perform preprocessing; S2. Calculate real-time power based on the preprocessed three-phase voltage and current signals; S3. Based on the reverse power occurrence judgment rule and real-time power, determine whether the current medium-voltage generator has reverse power. Specifically, if the real-time power is less than 0 and the duration is greater than or equal to the preset time threshold, then it is determined that a reverse power state has occurred. S4. If this occurs, calculate the inverse power quantization value. Specifically, the inverse power quantization value is obtained based on the percentage of the absolute value of the real-time power in the rated power of the medium-voltage generator. The calculation method is as follows: ; In the formula, Indicates the inverse power quantization value; express Real-time power at any given moment; This indicates the rated power of the medium-voltage generator; S5. The inverse power quantization value is compared with the inverse power classification threshold to obtain the inverse power level; The reverse power grading threshold includes a warning threshold, a control threshold, and an emergency protection threshold. The warning threshold ranges from -3% to -5% of the rated power of the medium-voltage generator; the control threshold ranges from -8% to -10% of the rated power of the medium-voltage generator; and the emergency protection threshold ranges from -12% to -15% of the rated power of the medium-voltage generator. If the reverse power quantization value is less than the warning threshold, the corresponding reverse power level is no reverse power level; If the quantized value of the reverse power is greater than or equal to the warning threshold and less than or equal to the control threshold, the corresponding reverse power level is the warning level reverse power. If the reverse power quantization value is greater than or equal to the control threshold and less than or equal to the emergency level reverse power, then the corresponding reverse power level is the control level reverse power. If the reverse power quantization value is greater than the emergency level reverse power, then the corresponding reverse power level is the emergency level reverse power. S6. Wherein, the inverse power grading threshold is optimized through reinforcement learning; The operating state vector of the acquired medium-voltage generator is represented as follows: Including the current reverse power value A negative value indicates an inverse power state; the larger the absolute value, the more severe the inverse power. (Inverse power change rate) The value represents the trend of reverse power change; a positive value indicates that reverse power is aggravated, and a negative value indicates that reverse power is alleviated; terminal voltage deviation rate. ,in, Indicates the real-time terminal voltage. Indicates the rated terminal voltage; frequency of reverse power events per unit time. The unit time is 1 hour, representing the frequency of reverse power occurrence; preset temperature influence factor. and the current inverse power grading threshold ,in Indicates time, This represents the threshold for the first inverse power classification. This indicates the threshold for the second inverse power grading; Input the current running state vector into the policy function, and output the corresponding adjustment action. ,in This indicates the adjustment amount for the first inverse power grading threshold. This indicates the adjustment amount for the second inverse power grading threshold; And update the current inverse power grading threshold, calculated as follows: ; ; In the formula, This represents the updated first inverse power grading threshold; This represents the updated second inverse power grading threshold; This represents the learning rate, with a value range of [value missing]. This is used to control the step size of threshold adjustment to avoid excessive adjustment. Calculate the reward function for the adjustment action The reward function mentioned above includes a security reward function. This is used to assess the degree to which adjustment actions ensure the safe operation of the generator; it is an economic reward function. Used to evaluate the energy consumption and cost-effectiveness, stability, and reward function of adjustment actions. It is used to evaluate the stability of system voltage and power and the action cost function after adjustment. It is used to assess the energy consumption and mechanical wear costs of the adjustment action itself; The reward function The calculation method is as follows: ; ; ; ; ; In the formula, Represents the weights of the security reward function; Represents the weights of the economic reward function; The weights represent the stability reward function; The weights represent the action cost function; Indicates the number of load shearings; Indicates the maximum number of resections allowed; Indicates the total adjustment duration; Indicates the statistical period; Indicates the maximum terminal voltage; This represents the preset inverse power grading threshold boundary value; The advantage function is calculated based on the reward function. This is used to evaluate the merits of performing an adjustment action relative to the average action in the current state, and is calculated as follows: ; In the formula, This represents the discount factor, with a value range of [value range missing]. This is used to weigh immediate rewards against future rewards; express State value function; express State value function; The loss function is constructed with the objective of minimizing the squared error of the advantage function, and is calculated as follows: ; In the formula, Represents the loss function; Expressing expectations; This represents the entropy regularization coefficient, with a value range of 1. This is used to increase the exploratory nature of the strategy and avoid getting trapped in local optima; Iterate through the above process until the preset maximum number of iterations is reached or the reward function converges, then stop iterating and output the optimal running state vector. The inverse power classification threshold extracted from the optimal operating state vector is the optimized inverse power classification threshold.

[0023] Example 2: This invention provides a protection system for medium-voltage generator shutdown caused by reverse power, the system comprising: High-precision reverse power detection module, main controller, dynamic load adjustment module and adaptive excitation control module; The high-precision reverse power detection module is electrically connected to the output terminal of the medium-voltage generator. It calculates the real-time power based on the three-phase voltage and current signals of the generator, and performs reverse power detection on the real-time power based on the reverse power occurrence judgment rules. If reverse power occurs, it calculates the reverse power quantization value and transmits it to the main controller. The main controller compares the inverse power quantization value with the inverse power classification threshold to obtain the inverse power level; based on the inverse power level, it generates control commands for the corresponding shutdown protection measures of the medium-voltage generator and sends them to the dynamic load regulation module and the adaptive excitation control module. In this embodiment, the control instructions generated by the main controller include: instructions to the dynamic load adjustment module: immediately put into operation a set of redundant standby loads (load priority: general load), with a response delay of ≤50ms; maintain the operation of current critical loads (such as power supply loads for core equipment in industrial production) and important loads (such as loads for security monitoring systems), and temporarily not adjust the load allocation ratio; Instructions to the adaptive excitation control module: Activate voltage stabilization mode, collect terminal voltage feedback signals in real time, dynamically correct excitation current adjustment parameters, maintain terminal voltage within ±1% of rated value, and avoid voltage fluctuations exacerbating reverse power. The dynamic load adjustment module is connected to the medium-voltage generator, communicates with the main controller, and is electrically connected to the load side of the generator. It is used to respond to the control commands to perform corresponding load adjustment operations on the medium-voltage generator, so as to realize rapid standby load input, intelligent non-critical load shedding, and dynamic optimization of load distribution ratio. An adaptive excitation control module is connected to a medium-voltage generator, communicates with the main controller, and is electrically connected to the generator's excitation winding. It is used to adjust the excitation current of the medium-voltage generator in response to the control commands.

[0024] Preferably, the high-precision inverse power detection module includes: High-precision power sensor with a sampling frequency of not less than 1kHz; The anti-interference signal filtering unit uses the Kalman filtering algorithm to filter the acquired three-phase voltage and current signals; The reverse power intelligent determination unit is used to detect reverse power in real time. If the real-time power is less than 0 and the duration is greater than or equal to a preset time threshold, it is determined that the current medium-voltage generator is in reverse power state. Based on the proportion of the absolute value of the real-time power in the rated power of the medium-voltage generator, the reverse power quantification value is obtained.

[0025] Preferably, the dynamic load adjustment module is configured to first activate the standby load and then adjust the load allocation according to the logic response control command. The load adjustment operation corresponding to the dynamic load adjustment module includes at least one of the following: standby load input, non-critical load shedding, and dynamic adjustment of load allocation ratio.

[0026] Preferably, the dynamic load adjustment module includes: The load priority sorting unit has a built-in load priority database of different importance levels, including critical loads, important loads, general loads and non-critical loads; High-speed switching group with a response delay of no more than 50ms; The redundant standby load unit is used to store redundant loads.

[0027] Preferably, the adaptive excitation control module adopts a PID adaptive adjustment algorithm, which collects the terminal voltage feedback signal of the medium-voltage generator in real time, compares it with the rated voltage value of the medium-voltage generator, and dynamically corrects the excitation current adjustment parameters.

[0028] Example 3: This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements a protection method for medium-voltage generator shutdown based on reverse power as described in any one of Embodiment 1.

[0029] Example 4: This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements a protection method for medium-voltage generator shutdown based on reverse power as described in any one of Embodiment 1.

[0030] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, A and B simultaneously, or B alone. A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one of a, b, and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0031] Those skilled in the art will recognize that the units and algorithm steps described in the embodiments disclosed herein can be implemented using electronic hardware, computer software, or a combination of electronic hardware and software. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0032] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0033] In the several embodiments provided in this application, any function, if implemented as a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0034] The above description is merely an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A protection method for medium-voltage generator shutdown based on reverse power, characterized in that, The method includes: Acquire the three-phase voltage and current signals of the medium-voltage generator and perform preprocessing; Real-time power is calculated based on the preprocessed three-phase voltage and current signals; Based on the reverse power occurrence judgment rules and real-time power judgment, it is determined whether the current medium-voltage generator has reverse power. If it has, the reverse power quantization value is calculated and compared with the reverse power classification threshold to obtain the reverse power level. Based on the reverse power level, the corresponding medium-voltage generator shutdown protection measures are implemented; The inverse power grading threshold is optimized through reinforcement learning.

2. The protection method for medium-voltage generator shutdown based on reverse power as described in claim 1, characterized in that, If the real-time power is less than 0 and the duration is greater than or equal to the preset time threshold, then it is determined that an inverse power state has occurred. The inverse power quantization value is obtained based on the proportion of the absolute value of real-time power in the rated power of the medium-voltage generator.

3. The protection method for medium-voltage generator shutdown based on reverse power as described in claim 1, characterized in that, The inverse power grading threshold is optimized through reinforcement learning, and the specific steps are as follows: Collect the operating status vector of the medium-voltage generator, including the current reverse power value, reverse power change rate, terminal voltage deviation rate, reverse power event frequency per unit time, preset temperature influence factor, and current reverse power classification threshold; Input the current running state vector into the policy function, output the corresponding adjustment action, and update the current inverse power classification threshold; Calculate the reward function for the adjustment action, and calculate the advantage function based on the reward function to evaluate the merits of performing the adjustment action under the current running state vector; The loss function is constructed with the objective of minimizing the squared error of the advantage function; Iterate through the above process until the preset maximum number of iterations is reached or the loss function converges, then stop iterating and output the optimal running state vector. The inverse power classification threshold extracted from the optimal operating state vector is the optimized inverse power classification threshold.

4. A protection system for medium-voltage generator shutdown caused by reverse power, employing the protection method described in any one of claims 1-3, characterized in that, The system includes: High-precision reverse power detection module, main controller, dynamic load adjustment module and adaptive excitation control module; The high-precision reverse power detection module is electrically connected to the output terminal of the medium-voltage generator. It calculates the real-time power based on the three-phase voltage and current signals of the generator, and performs reverse power detection on the real-time power based on the reverse power occurrence judgment rules. If reverse power occurs, it calculates the reverse power quantization value and transmits it to the main controller. The main controller compares the inverse power quantization value with the inverse power classification threshold to obtain the inverse power level; based on the inverse power level, it generates control commands for the corresponding shutdown protection measures of the medium-voltage generator and sends them to the dynamic load regulation module and the adaptive excitation control module. The dynamic load regulation module is connected to the medium-voltage generator and is used to perform corresponding load regulation operations on the medium-voltage generator in response to the control command. An adaptive excitation control module, connected to a medium-voltage generator, is used to adjust the excitation current of the medium-voltage generator in response to the control command.

5. A protection system for medium-voltage generator shutdown based on reverse power as described in claim 4, characterized in that, The high-precision inverse power detection module includes: High-precision power sensor; The anti-interference signal filtering unit uses the Kalman filtering algorithm to filter the acquired three-phase voltage and current signals; The reverse power intelligent determination unit is used to detect reverse power in real time. If the real-time power is less than 0 and the duration is greater than or equal to a preset time threshold, it is determined that the current medium-voltage generator is in reverse power state. Based on the proportion of the absolute value of the real-time power in the rated power of the medium-voltage generator, the reverse power quantification value is obtained.

6. A protection system for medium-voltage generator shutdown based on reverse power as described in claim 4, characterized in that: The load adjustment operation corresponding to the dynamic load adjustment module includes at least one of the following: standby load input, non-critical load shedding, and dynamic adjustment of load allocation ratio.

7. A protection system for medium-voltage generator shutdown based on reverse power as described in claim 4, characterized in that, The dynamic load adjustment module includes a load priority sorting unit with a built-in load priority database of different importance, a high-speed switching switch group, and a redundant standby load unit for storing redundant loads.

8. A protection system for medium-voltage generator shutdown based on reverse power as described in claim 4, characterized in that, The adaptive excitation control module adopts a PID adaptive adjustment algorithm to collect the terminal voltage feedback signal of the medium-voltage generator in real time, compare it with the rated voltage value of the medium-voltage generator, and dynamically correct the excitation current adjustment parameters.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1 to 3.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 3.

Images