Intelligent grid-connected control method and system for diesel generator in power plant

Abstract

The invention discloses a power plant diesel generator intelligent grid-connected control method and system, and relates to the technical field of grid-connected control, and the method comprises the steps: constructing a pseudo potential energy field, calculating Hamiltonian, screening a window with the minimum Hamiltonian standard deviation, defining the window as an optimal window, constructing a power scheduling shape function, and generating scheduling power. The method comprises the following steps: extracting stator winding shell temperature and rotating shaft temperature rise, constructing a thermal diffusion difference function, calculating time migration caused by thermal drift, correcting a time axis, mapping voltage to the correction time axis, extracting sine weight and cosine weight, reconstructing periodic components of frequency deviation, and generating an optimized frequency sequence; future frequency is predicted, and a phase control signal is generated. According to the method, the voltage time axis is corrected through the thermal diffusion difference function, the synchronism of voltage and frequency analysis is improved, and the response accuracy of the scheduling power is enhanced by constructing the pseudo potential energy field and screening the Hamiltonian standard deviation minimum window.

Description

Technical Field

[0001] The present invention relates to the technical field of grid-connected control, and in particular to an intelligent grid-connected control method and system for diesel generators in power plants. Background Art

[0002] With the rapid development of the electric power industry, intelligent grid-connected control of power plant backup power systems has become a key technical field to ensure the stability and reliability of the power grid. The grid-connected control technology of power plant diesel generator sets has evolved from mechanical to electronic automation control. Early systems mainly relied on relays and simple voltage monitors to start and switch backup power supplies, aiming to quickly respond to power grid failures. With the advancement of microprocessor and sensor technology, the integration of artificial intelligence and big data analysis has promoted further innovation in this field.

[0003] Existing diesel generator grid-connected control schemes still have the following problems: in scenarios where load power fluctuates drastically, traditional control strategies fail to make proactive responses based on the inherent evolutionary trends of power fluctuations, resulting in inaccurate power scheduling and affecting grid stability. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an intelligent grid-connected control method and system for diesel generators in power plants to solve the problem that in scenarios where load power changes drastically, traditional control strategies fail to make forward-looking responses based on the inherent evolution trend of power fluctuations, resulting in inaccurate power scheduling and affecting grid stability.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, the present invention provides a method for intelligent grid-connected control of a diesel generator in a power plant, which comprises: Collect and preprocess operating data, extract load power, calculate power difference, generate cumulative increment sequence, construct pseudo potential energy field, calculate Hamiltonian, select the window with the smallest Hamiltonian standard deviation, define it as the optimal window, construct power scheduling shape function, and generate scheduling power; Extract the stator winding shell temperature and shaft temperature rise, construct a heat diffusion difference function, calculate the time offset caused by thermal drift, correct the time axis, map the voltage to the corrected time axis, use linear interpolation to generate a continuous voltage sequence, segment the voltage sequence into fixed windows, calculate the instantaneous frequency within each fixed window, splice them into a continuous instantaneous frequency sequence, perform Fourier transform on the frequency deviation sequence, extract sine weights and cosine weights, reconstruct the periodic components of the frequency deviation, and generate an optimized frequency sequence; Calculate the phase trajectory of the optimized frequency sequence, generate a continuous differential phase sequence, predict future frequencies, generate a phase control signal, adjust the phase control signal based on the predicted future frequencies, and build a visual interface to display the adjusted phase control signal.

[0007] As a preferred solution of the intelligent grid-connected control method for diesel generators in power plants according to the present invention, the method of screening the window with the smallest Hamiltonian standard deviation is defined as the optimal window, constructing the power scheduling shape function, and generating the scheduling power includes: Extract normalized load power from operating data, calculate the power difference between adjacent time points, generate a cumulative increment sequence, perform sliding window segmentation on the cumulative increment sequence, and construct a pseudo potential energy field; Calculate the Hamiltonian and the standard deviation, and select the window with the smallest Hamiltonian standard deviation, which is defined as the optimal window; The average power and duration of the optimal window are extracted, the power scheduling shape function is constructed, and the scheduling power is generated.

[0008] As a preferred solution of the intelligent grid-connected control method for diesel generators in power plants according to the present invention, the steps of constructing a heat diffusion difference function, calculating the time offset caused by thermal drift, correcting the time axis, and mapping the voltage to the corrected time axis include: Extract the normalized stator winding shell temperature and shaft temperature rise from the operating data, calculate the rate of change of the stator and shaft temperatures, construct a thermal diffusion difference function, and calculate the time offset caused by thermal drift based on the thermal diffusion difference function; Correct the time axis based on time offset; Extracting normalized voltage from the operating data, mapping the voltage to the calibrated time axis, and generating a continuous voltage series using linear interpolation; The normalized voltage is subjected to Hilbert transform to generate an analytical signal. The instantaneous phase of the analytical signal is calculated and phase unwrapping is performed to generate a grid phase sequence.

[0009] As a preferred solution of the intelligent grid-connected control method for diesel generators in power plants according to the present invention, the extraction of sine weights and cosine weights, reconstruction of the periodic components of the frequency deviation, and generation of the optimized frequency sequence include: The voltage sequence is segmented into fixed windows, the differential phase is calculated, the instantaneous frequency in each fixed window is calculated based on the differential phase, and the instantaneous frequencies in each fixed window are spliced ​​into a continuous instantaneous frequency sequence; Based on the instantaneous frequency sequence, the frequency deviation sequence is calculated, the frequency deviation sequence is Fourier transformed, and the sine weight and cosine weight are extracted; Based on the sine weight and the cosine weight, the periodic component of the frequency deviation is reconstructed, and based on the reconstructed periodic component of the frequency deviation, an optimized frequency sequence is generated.

[0010] As a preferred solution of the intelligent grid-connected control method for diesel generators in power plants according to the present invention, the method of predicting the future frequency, generating a phase control signal, and adjusting the phase control signal in combination with the predicted future frequency includes: Based on the optimized frequency sequence, the phase trajectory is calculated using numerical integration, and phase unwrapping is performed to generate a continuous differential phase sequence; Based on the optimized frequency sequence, the first-order linear fitting is performed using the least squares method to predict future frequencies; Based on the grid phase sequence and differential phase sequence, a phase control signal is generated, and the phase control signal is adjusted in combination with the predicted future frequency.

[0011] As a preferred solution of the intelligent grid-connected control method for diesel generators in power plants according to the present invention, the step of constructing a visual interface to display the adjusted phase control signal includes: Use the visualization tool Matplotlib to build a visualization interface to display the dispatch power and adjusted phase control signal in real time; Users who have passed real-name verification are allowed to view it.

[0012] As a preferred solution of the intelligent grid-connected control method for diesel generators in power plants of the present invention, the collecting and pre-processing of operating data includes: Use smart sensors to collect diesel generator operating data and perform denoising and normalization processing; The smart sensors include Hall effect, voltage and thermocouple sensors; The operating data includes load power, voltage, stator winding shell temperature and shaft temperature rise data.

[0013] In a second aspect, the present invention provides an intelligent grid-connected control system for diesel generators in power plants, comprising: The collection and scheduling module is used to collect and preprocess operating data, extract load power, calculate power difference, generate cumulative increment sequence, construct pseudo potential energy field, calculate Hamiltonian, select the window with the smallest Hamiltonian standard deviation, define it as the optimal window, construct power scheduling shape function, and generate scheduling power; The correction and optimization module is used to extract the stator winding shell temperature and shaft temperature rise, construct a heat diffusion difference function, calculate the time offset caused by thermal drift, correct the time axis, map the voltage to the corrected time axis, use linear interpolation to generate a continuous voltage sequence, segment the voltage sequence into fixed windows, calculate the instantaneous frequency within each fixed window, splice it into a continuous instantaneous frequency sequence, perform Fourier transform on the frequency deviation sequence, extract sine weights and cosine weights, reconstruct the periodic components of the frequency deviation, and generate an optimized frequency sequence; The prediction and display module is used to calculate the phase trajectory of the optimized frequency sequence, generate a continuous differential phase sequence, predict future frequencies, generate a phase control signal, adjust the phase control signal based on the predicted future frequencies, and build a visual interface to display the adjusted phase control signal.

[0014] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the intelligent grid-connected control method for a power plant diesel generator as described in the first aspect of the present invention is implemented.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the intelligent grid-connected control method for a power plant diesel generator as described in the first aspect of the present invention.

[0016] The beneficial effects of the present invention are as follows: the present invention corrects the voltage time axis through the heat diffusion difference function, improves the synchronization of voltage and frequency analysis, and enhances the response accuracy of the dispatching power by constructing a pseudo potential energy field and screening the minimum window of the Hamiltonian standard deviation. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 This is a flow chart of the intelligent grid-connected control method for diesel generators in a power plant in Example 1.

[0019] Figure 2 Schematic diagram of the intelligent grid-connected control system for diesel generators in a power plant in Example 1. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0021] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0023] Example 1, with reference to Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a method for intelligent grid-connected control of diesel generators in a power plant, comprising the following steps: S1. Collect and preprocess operating data, extract load power, calculate power difference, generate cumulative increment sequence, construct pseudo potential energy field, calculate Hamiltonian, select the window with the smallest Hamiltonian standard deviation, define it as the optimal window, construct power scheduling shape function, and generate scheduling power; Specifically, collect and pre-process operational data, including: Use smart sensors to collect diesel generator operating data and perform denoising and normalization processing; The smart sensors include Hall effect, voltage and thermocouple sensors; The operating data includes load power, voltage, stator winding shell temperature and shaft temperature rise data.

[0024] Through normalization processing and denoising algorithms, the versatility and anti-interference ability of the data are improved, the stability of subsequent model analysis is significantly enhanced, the system's adaptability to complex dynamic environments is improved, and calculation errors caused by signal distortion are avoided.

[0025] Furthermore, the window with the smallest Hamiltonian standard deviation is selected and defined as the optimal window. The power scheduling shape function is constructed to generate the scheduling power, including: Extract the normalized load power from the operating data, calculate the power difference between adjacent time points, and generate a cumulative increment sequence. The formula is: , , in is the i-th power difference, For time point The normalized load power, and are the i-th and k-th time points respectively, i is the sampling point index, k is the accumulated sampling point index, For time point The cumulative increment sequence of ; The cumulative increment sequence is segmented into sliding windows to construct a pseudo potential energy field. The formula is: , , in is the w-th sliding window, is the starting time of the sliding window, L is the sliding window, is the time step, is the time point in the sliding window Pseudo potential energy field; Calculate the Hamiltonian and the standard deviation, and select the window with the smallest Hamiltonian standard deviation, which is defined as the optimal window. The formula is: , , in is the time point in the sliding window The Hamiltonian of is the derivative of the cumulative increment sequence, calculated using the difference formula, is the optimal window, is the standard deviation of the Hamiltonian, w is the index of the sliding window; Extract the average power and duration of the optimal window using the formula: , , in is the average power of the optimal window, is the duration of the optimal window; Construct the power scheduling shape function, the formula is: , in is the power scheduling shape function at time t, The power ramp time is set based on the average of the historical generator power ramp response time. Generate scheduling power, the formula is: , in is the dispatch power at time t.

[0026] Based on the sliding window Hamiltonian standard deviation screening mechanism, it can accurately identify the time window with the smallest system fluctuation and the most stable state from multiple candidate time periods, thereby determining the optimal scheduling period. The pseudo potential field and Hamiltonian are used to construct micro-fluctuation characteristic quantities, which has the dual meanings of data-driven and physical abstraction, greatly improving the interpretability and generalization ability of the model. The identification of the optimal window helps to limit the scheduling behavior to the time segment with the most responsive stability, thereby improving the frequency regulation control accuracy and avoiding the large overshoot or undershoot problems of traditional PID and other fixed structure controllers in the power mutation response. The scheduling behavior is modeled by mathematical functions to provide a stable frequency basis for subsequent phase control, effectively supporting the grid synchronization logic. The chain modeling method of potential field-Hamiltonian-scheduling function is adopted to transform the traditional point-to-point scheduling logic into a continuous dynamic response structure, effectively solving the bottlenecks of "inability to achieve continuous power adjustment", "nonlinear response time" and "limited scheduling accuracy" in the existing technology.

[0027] S2. Extract the stator winding shell temperature and shaft temperature rise, construct a heat diffusion difference function, calculate the time offset caused by thermal drift, correct the time axis, map the voltage to the corrected time axis, use linear interpolation to generate a continuous voltage sequence, segment the voltage sequence into fixed windows, calculate the instantaneous frequency within each fixed window, splice them into a continuous instantaneous frequency sequence, perform Fourier transform on the frequency deviation sequence, extract the sine weight and cosine weight, reconstruct the periodic component of the frequency deviation, and generate an optimized frequency sequence; Specifically, a thermal diffusion difference function is constructed, the time offset caused by thermal drift is calculated, the time axis is corrected, and the voltage is mapped to the corrected time axis, including: The normalized stator winding shell temperature and shaft temperature rise are extracted from the operating data, the rates of change of the stator and shaft temperatures are calculated, and a heat diffusion difference function is constructed to quantify the thermal dynamic difference between the stator and shaft. The formula is: , in is the thermal diffusion difference function at time t, and are the rates of change of stator winding shell temperature and shaft temperature rise, respectively, which are calculated using numerical differentiation method; Based on the thermal diffusion difference function, the time offset caused by thermal drift is calculated to correct the time axis of the voltage signal. The formula is: , in is the time offset of time t, is the thermal diffusivity, is the integration time window, is the integral variable; Based on the time offset, the time axis is corrected. The formula is: , in is the time axis after correction; Extracting normalized voltage from the operating data, mapping the voltage to the calibrated time axis, and generating a continuous voltage series using linear interpolation; Perform Hilbert transform on the normalized voltage to generate an analytical signal. Calculate the instantaneous phase of the analytical signal and perform phase unwrapping to generate the grid phase sequence. The formula is: , , in is the analytical signal at time t, is the normalized voltage at time t, is the Hilbert transform result, j is the imaginary unit, is the complex phase extraction function, is the instantaneous phase at time t.

[0028] This step introduces a heat diffusion difference function based on the rate of change of thermal gradient to eliminate the offset interference of thermal hysteresis on frequency judgment, improve the accuracy of frequency offset detection, enhance the time alignment of control signal generation based on phase and frequency, effectively suppress signal pseudo mismatch caused by inconsistent sensor response, and enhance the robustness of the model to time domain offset caused by heat accumulation under long-term operation. It is particularly suitable for large-scale power generation equipment operating continuously at high temperatures. It lays a unified time foundation for subsequent Fourier analysis and phase extraction, ensures the accurate decomposition of the frequency components of the Fourier transform, processes the voltage signal in the complex domain, and derives the instantaneous phase as the core quantity of frequency extraction, thereby improving the stability of phase estimation. Based on the phase unwrapping method, the grid phase trajectory is constructed to support subsequent frequency offset estimation and synchronous control. Voltage interpolation enhances the sampling resolution, provides sufficient data density for the frequency extraction algorithm, establishes a continuous mapping relationship between voltage, phase and frequency, and provides a stable foundation for dynamic frequency scheduling.

[0029] Furthermore, the sine weights and cosine weights are extracted to reconstruct the periodic components of the frequency deviation and generate an optimized frequency sequence, including: The voltage sequence is segmented into fixed windows and the differential phase is calculated using the formula: , in is the differential phase of the mth fixed window, m is the index of the fixed window, For the time interval, use the Nyquist criterion to set, is the complex conjugate of the voltage subsequence of the mth fixed window, is the voltage subsequence of the mth window; Based on the differential phase, the instantaneous frequency within each fixed window is calculated using the formula: , in is the instantaneous frequency of the mth fixed window; The instantaneous frequencies within each fixed window are spliced ​​into a continuous instantaneous frequency sequence. The formula is: , in is the instantaneous frequency sequence; Based on the instantaneous frequency sequence, the frequency deviation sequence is calculated using the formula: , in is the frequency deviation sequence, It is the grid reference frequency, set by the State Grid Corporation of China standards; Perform Fourier transform on the frequency deviation sequence and extract the sine weight and cosine weight to remove the slow drift component and retain the periodic characteristics related to grid synchronization. The formula is: , , in and are the sine weight and cosine weight of the rth harmonic, N is the number of sampling points in the time window, c is the Fourier transform normalization constant, is the grid reference period, r is the harmonic order, is the discrete time point of the lth corrected time axis; Based on the sine weight and cosine weight, the periodic component of the frequency deviation is reconstructed to separate the regular fluctuations related to grid synchronization. The formula is: , in is the periodic component of the reconstructed frequency deviation, is the maximum harmonic order; Based on the periodic component of the reconstructed frequency deviation, the slow drift component is stripped from the frequency deviation sequence to generate the optimized frequency sequence. The formula is: , in is the optimized frequency sequence.

[0030] The frequency extraction method based on differential phase can significantly improve the time resolution of the instantaneous frequency response, form a complete instantaneous frequency sequence by splicing, avoid the adverse effects of frequency interruptions or faults on Fourier analysis, and accurately separate the fast periodic components and slow drift components in the deviation sequence, so that the frequency control logic can focus on the periodic core signal, reduce the frequency offset misjudgment caused by environmental interference, significantly improve the response accuracy of the frequency prediction and phase control model, reduce the prediction error, minimize the impact of non-structural drift, and improve the real-time and stability of generator synchronization control. Through the reconstruction of periodic components and the suppression of non-periodic components, the structured optimization of the frequency signal is achieved, forming an advanced control strategy with "data-driven + frequency control" dual-wheel drive.

[0031] S3. Calculate the phase trajectory of the optimized frequency sequence, generate a continuous differential phase sequence, predict future frequencies, generate a phase control signal, adjust the phase control signal based on the predicted future frequencies, and build a visualization interface to display the adjusted phase control signal; Specifically, predicting the future frequency, generating a phase control signal, and adjusting the phase control signal based on the predicted future frequency include: Based on the optimized frequency sequence, the phase trajectory is calculated using numerical integration, and phase unwrapping is performed to generate a continuous differential phase sequence. The formula is: , in is the phase trajectory, and are the start and end time of the integration interval respectively; Based on the optimized frequency sequence, the least squares method is used to perform first-order linear fitting to predict future frequencies. The formula is: , , in To predict future frequencies, is the prediction time step, C is the frequency change rate, and are the means of time and frequency, respectively, and n is the number of sampling points for regression analysis; Based on the grid phase sequence and differential phase sequence, the phase control signal is generated, and the formula is: , in is the phase control signal at time t, is the proportional gain, set using the rule of thumb, and They are grid phase sequence and differential phase sequence respectively; Combined with the predicted future frequency, the phase control signal is adjusted. The formula is: , in is the adjusted phase control signal, is the feedforward gain, set using the rule of thumb.

[0032] The continuous differential phase sequence realizes high-fidelity mapping from frequency to phase space, which is used for subsequent phase difference judgment and synchronization strategy formulation. The unwrapping operation ensures that the phase trajectory is continuous on the time axis, provides a stable and differentiable phase basis for the control strategy, and provides data support for the control signal generation mechanism based on phase difference, thereby improving the stability and response consistency of the system, avoiding sudden changes in the response of the control system due to phase jumps, and helping to build a continuous adjustment mechanism, enhance the control system's dynamic prediction capability for load mutations and grid fluctuations, realize an advance adjustment mechanism, improve the adaptability of the grid-connected power supply to the main grid frequency disturbance, reduce transient overshoot and adjustment hysteresis, ensure that the phase error is corrected in time through proportional control, realize real-time phase locking between the generator and the grid, introduce a predictive frequency adjustment mechanism, realize a dual-channel control structure with parallel prediction and response, improve the stability of the system under rapid disturbances, enhance the system's phase adjustment robustness and tracking performance, and provide a stable signal basis for subsequent automatic power scheduling.

[0033] Furthermore, a visual interface is constructed to display the adjusted phase control signal, including: Use the visualization tool Matplotlib to build a visualization interface to display the dispatch power and adjusted phase control signal in real time; Users who have passed real-name verification are allowed to view it.

[0034] Building a graphical interface improves the system's interpretability, enabling operators or intelligent algorithms to intuitively judge the system's operating status, compare historical trajectories with predicted trajectories, support operation optimization and troubleshooting, and real-name user authority control improves the system's security protection level and prevents key control parameters from being leaked or illegally tampered with.

[0035] This embodiment also provides a power plant diesel generator intelligent grid-connected control system, including: The collection and scheduling module is used to collect and preprocess operating data, extract load power, calculate power difference, generate cumulative increment sequence, construct pseudo potential energy field, calculate Hamiltonian, select the window with the smallest Hamiltonian standard deviation, define it as the optimal window, construct power scheduling shape function, and generate scheduling power; The correction and optimization module is used to extract the stator winding shell temperature and shaft temperature rise, construct a heat diffusion difference function, calculate the time offset caused by thermal drift, correct the time axis, map the voltage to the corrected time axis, use linear interpolation to generate a continuous voltage sequence, segment the voltage sequence into fixed windows, calculate the instantaneous frequency within each fixed window, splice it into a continuous instantaneous frequency sequence, perform Fourier transform on the frequency deviation sequence, extract sine weights and cosine weights, reconstruct the periodic components of the frequency deviation, and generate an optimized frequency sequence; The prediction and display module is used to calculate the phase trajectory of the optimized frequency sequence, generate a continuous differential phase sequence, predict future frequencies, generate a phase control signal, adjust the phase control signal based on the predicted future frequencies, and build a visual interface to display the adjusted phase control signal.

[0036] This embodiment also provides a computer device, which is suitable for the intelligent grid-connected control method of power plant diesel generators, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the intelligent grid-connected control method of power plant diesel generators proposed in the above embodiment.

[0037] The computer device may be a terminal, comprising a processor, memory, a communication interface, a display, and an input device connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores an operating system and computer programs. The internal memory provides an environment for the operating system and computer programs stored in the non-volatile storage media. The communication interface of the computer device is used to communicate with external terminals via wired or wireless communication. Wireless communication may be achieved via Wi-Fi, a carrier network, NFC (near-field communication), or other technologies. The display of the computer device may be a liquid crystal display or an electronic ink display. The input device may be a touchscreen overlay on the display, buttons, a trackball, or a touchpad on the computer device housing, or an external keyboard, touchpad, or mouse.

[0038] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for realizing intelligent grid-connected control of diesel generators in power plants as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0039] In summary, the present invention corrects the voltage time axis through the heat diffusion difference function, improves the synchronization of voltage and frequency analysis, and enhances the response accuracy of the dispatching power by constructing a pseudo potential energy field and screening the minimum window of the Hamiltonian standard deviation.

[0040] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for intelligent grid-connected control of diesel generators in power plants, characterized by: include, Collect and preprocess operating data, extract load power, calculate power difference, generate cumulative increment sequence, construct pseudo potential energy field, calculate Hamiltonian, select the window with the smallest Hamiltonian standard deviation, define it as the optimal window, construct power scheduling shape function, and generate scheduling power; Extract the stator winding shell temperature and shaft temperature rise, construct a heat diffusion difference function, calculate the time offset caused by thermal drift, correct the time axis, map the voltage to the corrected time axis, use linear interpolation to generate a continuous voltage sequence, segment the voltage sequence into fixed windows, calculate the instantaneous frequency within each fixed window, splice them into a continuous instantaneous frequency sequence, perform Fourier transform on the frequency deviation sequence, extract sine weights and cosine weights, reconstruct the periodic components of the frequency deviation, and generate an optimized frequency sequence; Calculate the phase trajectory of the optimized frequency sequence, generate a continuous differential phase sequence, predict future frequencies, generate a phase control signal, adjust the phase control signal based on the predicted future frequencies, and build a visual interface to display the adjusted phase control signal.

2. The intelligent grid-connected control method for diesel generators in power plants according to claim 1, characterized in that: The window with the smallest Hamiltonian standard deviation is defined as the optimal window, and the power scheduling shape function is constructed to generate the scheduling power, including: Extract normalized load power from operating data, calculate the power difference between adjacent time points, generate a cumulative increment sequence, perform sliding window segmentation on the cumulative increment sequence, and construct a pseudo potential energy field; Calculate the Hamiltonian and the standard deviation, and select the window with the smallest Hamiltonian standard deviation, which is defined as the optimal window; The average power and duration of the optimal window are extracted, the power scheduling shape function is constructed, and the scheduling power is generated.

3. The intelligent grid-connected control method for diesel generators in power plants according to claim 2, characterized in that: The steps of constructing a thermal diffusion difference function, calculating a time offset caused by thermal drift, correcting a time axis, and mapping a voltage to the corrected time axis include: Extract the normalized stator winding shell temperature and shaft temperature rise from the operating data, calculate the rate of change of the stator and shaft temperatures, construct a thermal diffusion difference function, and calculate the time offset caused by thermal drift based on the thermal diffusion difference function; Correct the time axis based on time offset; Extracting normalized voltage from the operating data, mapping the voltage to the calibrated time axis, and generating a continuous voltage series using linear interpolation; The normalized voltage is subjected to Hilbert transform to generate an analytical signal. The instantaneous phase of the analytical signal is calculated and phase unwrapping is performed to generate a grid phase sequence.

4. The intelligent grid-connected control method for diesel generators in power plants according to claim 3, characterized in that: The extracting of sine weights and cosine weights, reconstructing the periodic component of the frequency deviation, and generating an optimized frequency sequence includes: The voltage sequence is segmented into fixed windows, the differential phase is calculated, the instantaneous frequency in each fixed window is calculated based on the differential phase, and the instantaneous frequencies in each fixed window are spliced ​​into a continuous instantaneous frequency sequence; Based on the instantaneous frequency sequence, the frequency deviation sequence is calculated, the frequency deviation sequence is Fourier transformed, and the sine weight and cosine weight are extracted; Based on the sine weight and the cosine weight, the periodic component of the frequency deviation is reconstructed, and based on the reconstructed periodic component of the frequency deviation, an optimized frequency sequence is generated.

5. The intelligent grid-connected control method for diesel generators in power plants according to claim 4, characterized in that: The predicting of the future frequency, generating a phase control signal, and adjusting the phase control signal in combination with the predicted future frequency include: Based on the optimized frequency sequence, the phase trajectory is calculated using numerical integration, and phase unwrapping is performed to generate a continuous differential phase sequence; Based on the optimized frequency sequence, the first-order linear fitting is performed using the least squares method to predict future frequencies; Based on the grid phase sequence and differential phase sequence, a phase control signal is generated, and the phase control signal is adjusted in combination with the predicted future frequency.

6. The intelligent grid-connected control method for diesel generators in power plants according to claim 5, characterized in that: The step of constructing a visual interface to display the adjusted phase control signal includes: Use the visualization tool Matplotlib to build a visualization interface to display the dispatch power and adjusted phase control signal in real time; Users who have passed real-name verification are allowed to view it.

7. The intelligent grid-connected control method for diesel generators in power plants according to claim 1, characterized in that: The collecting and pre-processing of the operating data includes: Use smart sensors to collect diesel generator operating data and perform denoising and normalization processing; The smart sensors include Hall effect, voltage and thermocouple sensors; The operating data includes load power, voltage, stator winding shell temperature and shaft temperature rise data.

8. An intelligent grid-connected control system for diesel generators in a power plant, based on the intelligent grid-connected control method for diesel generators in a power plant according to any one of claims 1 to 7, characterized in that: include, The collection and scheduling module is used to collect and preprocess operating data, extract load power, calculate power difference, generate cumulative increment sequence, construct pseudo potential energy field, calculate Hamiltonian, select the window with the smallest Hamiltonian standard deviation, define it as the optimal window, construct power scheduling shape function, and generate scheduling power; The correction and optimization module is used to extract the stator winding shell temperature and shaft temperature rise, construct a thermal diffusion difference function, calculate the time offset caused by thermal drift, correct the time axis, map the voltage to the corrected time axis, use linear interpolation to generate a continuous voltage sequence, segment the voltage sequence into fixed windows, calculate the instantaneous frequency within each fixed window, splice them into a continuous instantaneous frequency sequence, perform Fourier transform on the frequency deviation sequence, extract sine and cosine weights, reconstruct the periodic component of the frequency deviation, and generate an optimized frequency sequence; The prediction and display module is used to calculate the phase trajectory of the optimized frequency sequence, generate a continuous differential phase sequence, predict future frequencies, generate a phase control signal, adjust the phase control signal based on the predicted future frequencies, and build a visual interface to display the adjusted phase control signal.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent grid-connected control method for a power plant diesel generator are implemented as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent grid-connected control method for a power plant diesel generator are implemented as described in any one of claims 1 to 7.

Images