Method and system for simplifying multi-parameter operation curve of gas turbine

Abstract

The invention provides a gas turbine multi-parameter operation curve simplification method and system, and relates to the technical field of gas turbines. The method specifically comprises the steps of performing normalization processing on a plurality of parameter operation curves; setting the number of key working condition point targets; calculating the vertical distance from each data point to the end-to-end connection line of the curve based on the thought of a Douglas-Peucker algorithm; performing weighted summation on the vertical distances of all the curves at the same moment to obtain a comprehensive feature distance; selecting a time point corresponding to the maximum value of the comprehensive distance as a key working condition point record; recursively dividing the curves by taking the key working condition points as boundaries, repeatedly calculating until the number of the key working condition points reaches the standard, and connecting the key working condition points of the curves to form a simplified curve. According to the method, the problems that manual screening is low in efficiency and poor in consistency, and an existing single-curve simplification method cannot keep the coupling relation among multiple parameters are solved, automatic and collaborative high-fidelity curve simplification is achieved, and the efficiency and precision of gas turbine operation data analysis and simulation are remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of gas turbine technology, and more specifically to a method and system for simplifying multi-parameter operating curves of a gas turbine. Background Technology

[0002] In the field of gas turbine operation and control, operating curves describe the trajectory of key parameters such as speed, temperature, pressure, and flow rate over time during transient processes such as start-up, shutdown, loading, and unloading of the gas turbine. These curves are the core basis for transient simulation, performance analysis, condition monitoring, and fault diagnosis. However, high-fidelity original operating curves are usually densely packed with data points, which can impose a huge computational and storage burden when meeting real-time simulation or resource-constrained embedded applications. Therefore, how to efficiently simplify operating curves under limited resources and time constraints—that is, to approximate the original curve with as few but highly representative data points as possible while preserving its physical and geometric characteristics to the greatest extent possible—has become a key technical problem in the digital application of gas turbines.

[0003] Traditional processing methods rely on manual screening of key operating points on the operating curve to simplify data analysis and improve simulation efficiency. However, this manual screening method has the following significant drawbacks: (1) It is time-consuming. Faced with a large-scale dataset containing multiple parameters such as rotational speed, temperature, and pressure, engineers need to spend a lot of time comparing and weighing them one by one, which is a cumbersome process; (2) It has poor consistency. Due to the lack of objective and unified standards, the screening results are easily affected by personal subjective experience. Different people may select different feature point sets, which reduces the comparability and reliability of subsequent simulation analysis results; (3) It is difficult to balance efficiency and accuracy. The manual method has a bottleneck in speed and lacks quantitative basis to ensure that all key physical features are preserved in a balanced and sufficient manner.

[0004] Existing patent CN118377921A discloses an adaptive generation method for characteristic curves of gas turbine components. Its core lies in synthesizing high-precision static characteristic curves of components by constructing a database. However, the purpose of this method is to generate characteristic diagrams for performance calculations, rather than to simplify existing dynamic operating curves of the entire machine. Therefore, it does not address the issue of selecting key operating points for the operating curves.

[0005] Existing patent CN116485940A discloses an adaptive curve thinning method that uses the Douglas-Puk algorithm combined with Friesian distance to optimize the simplification result of a single curve. However, its paradigm of independently processing a single curve cannot guarantee the alignment of multiple parametric curves at key time points after simplification, thus disrupting the synchronous coupling relationship between parameters.

[0006] In summary, the existing technology does not provide a method that can automatically coordinate and process the multi-parameter operating curves of a gas turbine and ensure that the simplified results are preserved with high fidelity in terms of both engineering physical characteristics and multi-parameter consistency. Summary of the Invention

[0007] Based on the aforementioned problems in the existing technology, this invention proposes a method and system for simplifying multi-parameter operating curves of gas turbines, in order to solve the problem that existing methods cannot efficiently and coordinately simplify multi-parameter operating curves while maintaining the consistency between their engineering characteristics and parameters.

[0008] To achieve the above objectives, the first aspect of this invention proposes a method for simplifying multi-parameter operating curves of a gas turbine, the specific technical solution of which is as follows: A method for simplifying multi-parameter operating curves of a gas turbine includes the following steps: S1. Obtain the original operating curve dataset of the gas turbine and preprocess each parameter operating curve in the dataset; S2. Pre-set the target number of key operating points to be retained in the end; S3. For each parameter running curve, calculate the vertical distance from each data point on it to the line connecting the beginning and end points of the curve; S4. Sum the vertical distances of all parameter curves at the same time point to obtain the comprehensive characteristic distances at each time point. S5. Select the time point corresponding to the maximum value of the comprehensive feature distance and record it as the key operating point; S6. Based on the key operating points, the parameter operation curve is recursively divided, and steps S3 to S5 are repeated on each sub-curve segment until the number of key operating points reaches the preset target number. Finally, the key operating points of each parameter operation curve are connected to generate its simplified curve.

[0009] Furthermore, in step S4, the weighted summation is performed based on different weighting coefficients preset in the running curves of each parameter, and on the vertical distance calculated in step S3.

[0010] Furthermore, in step S4, for each sampling time, the vertical distance of the running curve of each parameter is multiplied by its corresponding weighting coefficient, and the product of all parameters is summed to obtain the comprehensive feature distance at that time.

[0011] Furthermore, in step S4, the formula for calculating the weighted sum is as follows:

[0012] Where N represents the total number of parameter running curves, d n(t) represents the vertical distance from the nth parameter running curve at time t to the line connecting the beginning and end points of its current processing curve segment. This represents the preset weighting coefficient for each parameter's running curve.

[0013] Furthermore, the weighting coefficients are set according to the engineering importance of the corresponding parameters in the characterization of the gas turbine's operating status.

[0014] Furthermore, the specific values ​​of the weighting coefficients are determined based on the experience of domain experts or statistical analysis of historical operating data.

[0015] Furthermore, step S5 specifically includes: traversing the comprehensive feature distances obtained in step S4 at each time point, selecting the maximum value, and recording the time point corresponding to the maximum value and the values ​​of the corresponding parameter operation curves as key operating points.

[0016] Furthermore, step S6 includes: iteratively dividing and filtering the parameter operation curves based on the recorded key operating points until the number of key operating points reaches the preset target number in step S2.

[0017] Furthermore, the iterative division and filtering specifically includes: using the latest recorded key operating point as the dividing point, dividing the currently processed parameter running curve segment into two sub-curve segments, and repeating steps S3 to S5 on each sub-curve segment.

[0018] Furthermore, step S6 also includes: when the number of key operating points reaches the preset target number, for each parameter running curve, all the recorded key operating points are connected sequentially in chronological order to form a simplified curve.

[0019] Furthermore, the preprocessing described in step S1 is a normalization process, specifically mapping the data values ​​of each parameter running curve to the [0, 1] interval.

[0020] Furthermore, step S2 specifically includes: the setting of the number of targets mentioned in step S2 is specifically determined based on the requirements of gas turbine transient simulation for computational efficiency and accuracy.

[0021] To achieve the above objectives, a second aspect of the present invention proposes a system for simplifying multi-parameter operating curves of a gas turbine, the specific technical solution of which is as follows: A gas turbine multi-parameter operating curve simplification system, used to execute the above-mentioned gas turbine multi-parameter operating curve simplification method, includes: The data preprocessing module is used to preprocess the acquired parameter running curves; The feature calculation module is used to calculate the vertical distance from the data point on the running curve of each parameter to the line connecting its first and last points; The feature synthesis module is used to perform a weighted summation of the vertical distances of the running curves of all parameters at the same time to obtain the comprehensive feature distance; The key point extraction module is used to select the time point corresponding to the maximum distance of the comprehensive features as the key working condition point; The iterative control module is used to recursively segment the parameter operation curve based on key operating points, and control the calculation module, fusion module and selection module to iteratively run on the new curve segment until the number of key operating points reaches the target. The curve generation module is used to connect the key operating points of the running curves of various parameters and output simplified curves.

[0022] By applying the above-described technical solution of the present invention, at least the following technical effects are achieved: 1. This invention achieves the coordination and simplification of multi-parameter operating curves. By introducing weighting coefficients and comprehensively evaluating the geometric characteristics of all parameters at the same moment, it ensures that all the key operating points selected in the end are strictly aligned on the time axis, fundamentally preserving the inherent dynamic coupling relationship between parameters and overcoming the problem of inconsistent key moments caused by the independent processing of a single curve in traditional methods.

[0023] 2. This invention significantly improves the automation level and objectivity of the curve simplification process. The simplification method is based on an improved algorithm framework to achieve automatic iterative screening, completely replacing the manual selection mode that relies on personal experience. This not only improves processing efficiency but also eliminates subjective bias and ensures the consistency and repeatability of the simplification results.

[0024] 3. This invention sets different weighting coefficients for different parameters, allowing the curve simplification process to flexibly reflect the relative importance of each parameter in safety monitoring, performance analysis, and other aspects. This enables the final retained key operating points to more accurately reflect the operational characteristics that have core value for engineering practice.

[0025] 4. Based on the robustness of classic algorithms, this invention achieves a balance between simplification accuracy and computational resources through mechanisms such as setting the number of target points and adjusting weighting coefficients. It can also be customized to meet the needs of different gas turbine models or analysis scenarios, and has good versatility and engineering applicability.

[0026] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0027] The accompanying drawings, which form part of this specification, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings: Figure 1 A flowchart illustrating a method for simplifying multi-parameter operating curves of a gas turbine, as proposed in this invention, is shown. Figure 2 A schematic diagram illustrating the calculation of the vertical distance of the multi-parameter running curve in an embodiment of the present invention is provided; Figure 3 A schematic diagram illustrating the comprehensive features of multi-parameter operating curves in an embodiment of the present invention is provided; Figure 4 A schematic diagram of the multi-parameter operation curve division in an embodiment of the present invention is shown; Figure 5 A schematic diagram of iterative screening of multi-parameter running curves in an embodiment of the present invention is shown; Figure 6 A schematic diagram of a simplified system for multi-parameter operating curves of a gas turbine, as proposed in this invention, is shown. Figure 7 A computer system architecture diagram for running a computer program, as proposed in this invention, is shown. Figure 8 An electronic device proposed in this invention is presented. Detailed Implementation

[0028] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0029] The present invention will be further described in detail below with reference to specific embodiments, which should not be construed as limiting the scope of protection claimed by the present invention.

[0030] Existing methods for simplifying gas turbine parameter operation often rely on manual experience for screening or only process a single curve independently. These methods suffer from low efficiency, strong subjectivity, and an inability to maintain time synchronization and physical coupling between multiple parameters, making it difficult to achieve a good balance between accuracy and efficiency.

[0031] To address this, the present invention proposes a method and system for simplifying multi-parameter operating curves of gas turbines. By improving the classic Douglas-Pock algorithm and introducing a weighted fusion mechanism and a collaborative iteration framework, the invention achieves automated, collaborative, and high-fidelity simplification of multiple parameter operating curves. Under the premise of strictly ensuring time alignment and feature preservation of key operating points, the invention significantly improves data processing efficiency and the engineering practicality of the results.

[0032] According to a first aspect of the present invention, a method for simplifying multi-parameter operating curves of a gas turbine is proposed, see reference. Figure 1 As shown, the method includes the following steps: S1. Obtain the original operating curve dataset of the gas turbine and normalize each parameter operating curve in it; S2. Based on specific analysis requirements and computational resource constraints, pre-set the target number of key operating points that must be retained in the end; S3. For each parameter running curve, calculate the vertical distance from each data point to the line connecting the beginning and end of the current processing curve segment; S4. Based on the preset weighting coefficients, the vertical distances of the running curves of all parameters at the same time are weighted and summed to obtain the comprehensive characteristic distance at each time. S5. Select the time point corresponding to the maximum value of the comprehensive feature distance and record it as the key operating point. S6. Divide the curve into segments based on the critical operating points. Repeat steps S3 to S5 for the new curve segments until the number of retained time points reaches the preset target number. Then connect the critical operating points of each curve in chronological order to form a simplified curve.

[0033] Specifically, step S1 includes: monitoring the operating status of the gas turbine in real time through a data acquisition system and automatically collecting parameter operating curve data to ensure the timeliness and accuracy of the input data. Based on this, each parameter operating curve in the acquired gas turbine operating curve dataset is normalized. Normalization aims to eliminate differences in dimensions and value ranges between different physical parameters, enabling all data to be compared and analyzed on the same scale, thus establishing a fair benchmark for subsequent multi-parameter collaborative simplification.

[0034] In this embodiment, an automated data acquisition and processing workflow is employed, which can promptly capture dynamic changes during gas turbine operation and provide high-quality basic data for simplifying subsequent parameter operating curves. This helps improve the overall efficiency and reliability of data processing. The acquired parameter operating curves include turbine outlet flow rate curves, compressor outlet temperature curves, and turbine inlet temperature curves.

[0035] This embodiment specifically employs the minimum-maximum normalization technique to uniformly map the data values ​​of each parameter to the interval [0, 1]. The normalization calculation formula is as follows:

[0036] Among them, y new y(t) represents the normalized value of the parameter at time t; y(t) represents the original measured or simulated value of the parameter at time t; min With y max These are the minimum and maximum values ​​of the operating parameter curve throughout the entire time series, respectively.

[0037] The above normalization process provides input data with uniform scale for subsequent steps, ensuring the comparability of curve features of different magnitudes during multi-parameter collaborative screening. This supports accurate and efficient screening of key operating points and enhances the consistency of the simplified results. In different application scenarios, other suitable normalization methods, such as z-score normalization, can be selected based on specific data distribution characteristics and requirements.

[0038] Specifically, step S2 above includes: based on specific analysis needs and computational resource limitations, setting the target number tnumber of key operating points that the parameter running curve must ultimately retain, thereby achieving a balance between curve simplification accuracy and computational efficiency.

[0039] The appropriate selection of the target number tnumber ensures that the simplified curve retains key features while maintaining a moderate data volume, thereby guaranteeing the accuracy of subsequent analysis and the realism of the gas turbine operating condition simulation. This effectively avoids information loss due to oversimplification and prevents unnecessary computational burden caused by data redundancy. In different application scenarios, the target number tnumber can be adjusted according to the desired data compression rate or the trade-off between computational efficiency and accuracy to adapt to the needs of accurate description and efficient processing of various complex operating conditions. In this embodiment, the value of the target number number typically does not exceed 10% to 30% of the total number of original data points. This empirical range ensures that key operating condition features are not omitted while effectively compressing the data.

[0040] Specifically, step S3 includes: based on the core idea of ​​the classic Douglas-Puk algorithm, for each parameter running curve, calculating the vertical distance from each data point to the line connecting the beginning and end points of the current processing curve segment, so as to quantify the local geometric deviation of the data points at each time point relative to the overall trend, and provide a unified quantitative basis for subsequent collaborative screening.

[0041] In this embodiment, the basic geometric discrimination criteria of the Douglas-Puk algorithm are inherited and applied. For each current parameter running curve, its starting point A and ending point B are connected to form a baseline segment AB, and all data points P on the curve are calculated. i The vertical distance d from line segment AB. This vertical distance precisely represents the degree of geometric deviation between each data point and the overall trend line. See also Figure 2 The diagram shown is a schematic representation of the vertical distance from each data point on the operating curve of various parameters of a gas turbine to the baseline AB.

[0042] The difference between this invention and the classic Douglas-Puk algorithm lies in the fact that the above calculation is merely a basic step in the multi-parameter collaborative simplification process. Through this calculation process, key geometric features such as local extrema, inflection points, and abrupt changes in rate of change can be effectively identified and extracted from each parameter's operating curve. The resulting distance value sequence provides a unified quantitative input for subsequent steps of feature alignment and weighted synthesis among multiple parameter curves, thereby ensuring that the simplification process can systematically preserve the dynamic change characteristics of various key parameters.

[0043] Specifically, step S4 above includes: introducing parameter weighting coefficients, performing weighted summation of the vertical distances of all parameter running curves at the same time, and generating a comprehensive distance value that characterizes the overall running characteristics at that time.

[0044] In this embodiment, a weighting coefficient ε is assigned to each parameter running curve. n This coefficient is determined based on the physical meaning of the corresponding parameter, its engineering importance in safety monitoring or performance analysis, and its criticality in characterizing the overall operating status. The specific value of the weighting coefficient can be directly assigned based on the experience of domain experts, or determined through statistical analysis of historical operating data.

[0045] Preferably, a systematic method incorporating iterative optimization and model self-learning can also be used to determine the weighting coefficients. Specific operations include: simulation calibration: using the average weight condition (i.e., ε) n Using 1 / N (where N is the total number of parameters) as the starting point for iteration, construct multiple different combinations of weighted coefficients. For each set of coefficients, perform whole-machine temperature field simulation calculations using extracted key points. By comparing the simulation results of each set with high-confidence test benchmark data, select the set of coefficients that minimizes the simulation error or best meets the predetermined conservatism requirements as the engineering calibration coefficient set. Model training: Repeat the above simulation calibration operation multiple times, changing the target number tnumber of key operating points and the conservatism requirement for the simulation results each time, thereby accumulating a training dataset. In this dataset, the input features of each data point must include at least the target number tnumber and the conservatism requirement, and the output label is the corresponding engineering calibration coefficient set. Use this dataset to train a regression prediction model, such as a fully connected neural network or random forest. Coefficient generation: In practical applications, input the target number tnumber and the conservatism requirement set for the current task into the trained regression prediction model to obtain a suitable set of weighted coefficients.

[0046] For each sampling time t, extract the vertical distance d of each parameter running curve at that time. n (t), and compare it with the corresponding weighting coefficient ε nAfter multiplication, the product results of the curves of all parameters are summed to obtain the comprehensive characteristic distance D(t) at that moment. The specific calculation formula is as follows:

[0047] Where N represents the total number of parameter running curves, d n (t) represents the vertical distance from the nth parameter's running curve at time t to the line connecting the beginning and end points of its current processed curve segment, with weighting coefficient ε. n It can be configured according to different analysis objectives and application scenarios.

[0048] By iterating through all sampling times and repeating the above calculation, a comprehensive feature distance sequence {D(t)} corresponding to the time series is finally formed.

[0049] This step integrates the geometric deviations of multiple parameter operating curves across different dimensions into a unified, comprehensive characteristic distance D(t) with clear physical and engineering implications. This achieves two objectives: first, it quantifies the overall deviation of multiple parameter operating states from the overall trend at any given time, and reflects the relative importance of different parameters through weighting; second, it uses weighting coefficients to reflect the relative importance of different parameters, strengthening the influence of key parameters; and third, it ensures the synchronization of multiple parameter states in subsequent screening, guaranteeing that all retained operating points are fully aligned on the time axis, thus fully preserving the coupling relationships between parameters and making the final simplified result more aligned with the actual needs of engineering analysis.

[0050] Specifically, step S5 includes: within the processing time period corresponding to step S4, selecting the time point corresponding to the maximum value of the comprehensive feature distance D(t) and recording it as the key working condition point.

[0051] In this embodiment, for the comprehensive feature distance sequence {D(t)} obtained in step S4, the maximum value D is found by traversing it. max and the corresponding specific time t C Time t C This is identified as a critical operating point, and the specific values ​​of each parameter's operating curve at this point are recorded together in the critical point set. (See also...) Figure 3 As shown, the maximum value of the comprehensive feature distance is t in the figure. C The corresponding critical operating conditions.

[0052] This step selects key points based on the criterion of maximizing the comprehensive feature distance at the same moment, ensuring that the retained operating points represent the synchronous state where the overall feature deviation of multiple parameter operating curves is most significant. This not only extracts and preserves the geometric and physical features of the original curves to the greatest extent at the data level, but also ensures the strict alignment of the key points of all parameters on the time axis, thus fully preserving the inherent dynamic coupling relationship between parameters for subsequent analysis.

[0053] Specifically, step S6 includes: using the key operating points recorded in step S5 as dividing points, dividing each parameter operation curve currently being processed into two new curve segments, and repeating steps S3, S4 and S5 on the new curve segments until the total number of key operating points retained reaches the preset target number, and finally connecting the key points selected from each curve in chronological order to form simplified parameter operation curves.

[0054] Specifically, the key operating point selected in step S5 corresponds to time t. C Using these as dividing points, each parameter operation curve is divided into two parts: the initial curve segment from point A to point C, and the subsequent curve segment from point C to point B. Connecting point A and point C, and connecting point C and point B, generates new line segments AC and CB. Each newly generated line segment serves as a new baseline for calculating the vertical distance in the next iteration. Steps S3 to S5 are repeated on these two new line segments. Specifically, within each curve segment, the vertical distance from each data value of the corresponding parameter operation curve to its new baseline is recalculated, and the distances at the same time point are weighted and summed to obtain a new comprehensive characteristic distance. The time point corresponding to the maximum value of this comprehensive characteristic distance is then selected as a new critical operating point for recording.

[0055] See Figure 4 As shown, after selecting the key operating point C, the original curve segment AB is divided into two sub-segments, AC and CB, with C as the boundary; see reference. Figure 5 As shown, repeat steps S3 to S5 on segments AC and CB respectively to perform the next round of screening.

[0056] The above division and screening process is repeated cyclically. In each iteration, the curve is further divided based on the latest key operating points, and the most significant features are dynamically focused on for key operating point screening. The entire iterative screening process continues until the cumulative number of recorded key operating points reaches the preset target number. For each parameter operating curve, its corresponding key operating points are connected sequentially in chronological order to form a simplified curve represented by continuous line segments, thus completing the simplification of the operating parameter curve.

[0057] This step establishes an automated iterative screening process. By recursively dividing and comprehensively evaluating the parameter operation curves, it achieves the goal of synchronizing and collaboratively simplifying multiple parameter operation curves, thereby ensuring strict alignment of all key points on the time axis, as well as the efficiency of the simplification process and the consistency of the results.

[0058] The proposed method for simplifying multi-parameter operating curves of gas turbines is applicable to various types of gas turbines, including heavy-duty, light-duty, and micro-gas turbines. By employing an improved Douglas-Pock algorithm and configurable weighting coefficients, corresponding curve simplification strategies can be formulated based on the operating characteristics of different gas turbines. This ensures that the operating characteristics of various gas turbines are preserved to the maximum extent while limiting the number of key points. This design effectively overcomes the subjectivity and inefficiency of manual selection, providing efficient, consistent, and reliable data processing support for the research and simulation of different types of gas turbines.

[0059] Furthermore, the simplified curves generated by this method can directly serve various subsequent engineering analysis tasks. Specifically, the simplified operation provides more efficient and accurate input data for transient simulation calculations of gas turbines; in performance evaluation, the retained key points ensure the comprehensiveness and depth of the analysis results; simultaneously, the simplified curves also aid in fault detection and diagnosis, allowing for timely identification of operational anomalies through monitoring key feature points. In summary, this technical solution significantly improves the automation level and result quality of gas turbine operation data processing, providing a solid data foundation and decision support for optimizing R&D processes and improving operation and maintenance efficiency.

[0060] According to a second aspect of the present invention, a system for simplifying multi-parameter operating curves of a gas turbine is proposed, see reference. Figure 6 As shown, the system includes a data preprocessing module, a parameter setting module, a feature calculation module, a feature synthesis module, a key point extraction module, an iteration control module, and a curve generation module.

[0061] The data preprocessing module is responsible for data acquisition and standardization. This module acquires the original operating curves of the gas turbine, which contain multiple parameters, and normalizes each parameter operating curve to eliminate dimensional differences, providing input data with uniform scale for subsequent processing.

[0062] The parameter setting module provides user-defined or system-preset key control parameters to simplify the process. Its main functions include: receiving or setting the target number of critical operating points to be retained; and setting weighting coefficients for each parameter's operating curve, which can be determined based on the parameter's engineering importance through expert experience or data analysis.

[0063] The feature calculation module is based on the core idea of ​​the Douglas-Puk algorithm and performs basic geometric feature extraction. For the currently processed parameter running curve, this module calculates the vertical distance from each data point on the parameter running curve to the line connecting the beginning and end points of the curve segment, and outputs the distance sequence of each parameter running curve at each time step.

[0064] The feature synthesis module enables the coordination and integration of multi-parameter features. This module receives the distance sequence of the running curves of each parameter from the feature calculation module and the weighting coefficients provided by the parameter setting module. It performs a weighted summation of the vertical distances of the running curves of all parameters at the same sampling time to calculate the comprehensive feature distance, which characterizes the overall significance of the features at that time, and generates the corresponding sequence.

[0065] The key point extraction module is responsible for making decisions and recording key operating points. This module iterates through the comprehensive feature distance sequence output by the feature fusion module, identifies and selects the time corresponding to the maximum value. The specific values ​​of that time and all corresponding parameter curves are recorded as a key operating point.

[0066] The iterative control module drives the recursive and iterative execution of the entire simplified process. When the key point extraction module selects a new key operating point, it uses this key operating point as a dividing point to divide each currently processed parameter running curve into two new sub-curve segments. For each new sub-curve segment, the feature calculation module, feature fusion module, and key point extraction module are called again in sequence for the next round of key point filtering. This "division-filtering" loop continues, and the total number of recorded key points is monitored in real time. When the total number reaches the preset target number in the parameter setting module, the iteration stops and the output process is triggered.

[0067] The curve generation module generates the final simplified result. When the iteration control module triggers termination, this module reads all recorded key operating points. For each parameter running curve, it connects all its corresponding key points in chronological order to form a simplified curve composed of continuous line segments, which serves as the final simplified output of that parameter running curve.

[0068] According to a third aspect of the present invention, a computer program product comprising a computer program is provided.

[0069] Figure 7 A schematic block diagram of a computer system architecture for implementing an electronic device according to embodiments of the present invention is shown.

[0070] It should be noted that, Figure 7 The computer system 700 of the illustrated electronic device is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0071] like Figure 7 As shown, the computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 702 or programs loaded from storage section 708 into random access memory (RAM) 703. The RAM 703 also stores various programs and data required for system operation. The CPU 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output interface 705 (I / O interface) is also connected to the bus 704.

[0072] The following components are connected to the input / output interface 705: an input section 706 including a keyboard, mouse, etc.; an output section 707 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a local area network card, modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the input / output interface 705 as needed. A removable medium 711, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 710 as needed so that computer programs read from it can be installed into the storage section 708 as needed.

[0073] In particular, according to embodiments of the present invention, the processes described in the various method flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 709, and / or installed from a removable medium. When the computer program is executed by central processing unit 701, it performs various functions defined in the gas turbine multi-parameter operating curve simplification system of the present invention.

[0074] According to a fourth aspect of the present invention, an electronic device is also provided. This embodiment will be described using the electronic device as an example of a terminal device. Figure 8As shown, the electronic device includes a memory 802 and a processor 804. The memory 802 stores a computer program, and the processor 804 is configured to execute the data processing and calculation steps in the above-mentioned method for simplifying the multi-parameter operating curve of a gas turbine through the computer program.

[0075] Optionally, in this embodiment, the aforementioned electronic device may be located in at least one of a plurality of network devices in a computer network.

[0076] Alternatively, as those skilled in the art will understand, Figure 8 The structure shown is for illustrative purposes only. Figure 8 This does not limit the structure of the aforementioned electronic devices. For example, the electronic device may also include components that are more... Figure 8 The more or fewer components shown (such as network interfaces, etc.), or having the same Figure 8 The different configurations shown.

[0077] The memory 802 can be used to store software programs and modules, such as the program instructions / modules corresponding to the data processing and calculation steps in the gas turbine multi-parameter operating curve simplification method in this embodiment of the invention. The processor 804 executes various functional applications and data processing by running the software programs and modules stored in the memory 802. The memory 802 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. Specifically, the memory 802 may be used, but is not limited to, storing collected operating curve data and processing results. As an example, such as... Figure 8 As shown, the memory 802 may include, but is not limited to, the data processing and calculation module in the gas turbine multi-parameter operating curve simplification system. Furthermore, it may include, but is not limited to, other module units in the aforementioned device, which will not be elaborated upon in this example.

[0078] Optionally, the transmission device 806 described above is used to receive or send data via a network. Specific examples of the network described above may include wired networks and wireless networks.

[0079] In addition, the aforementioned electronic device also includes: a display 808 for displaying the aforementioned test data and processing results; and a connection bus 810 for connecting the various module components in the aforementioned electronic device.

[0080] According to a fifth aspect of the present invention, a computer-readable storage medium is provided, wherein a processor of an electronic device reads computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the data processing and calculation steps in the above-described method for simplifying the multi-parameter operating curves of a gas turbine.

[0081] Optionally, in this embodiment, those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0082] The above are merely several specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

[0083] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0084] It should be noted that, in the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

Claims

1. A method for simplifying multi-parameter operating curves of a gas turbine, characterized in that: S1. Obtain the original operating curve dataset of the gas turbine and preprocess each parameter operating curve in the dataset; S2. Pre-set the target number of key operating points to be retained in the end; S3. For each parameter running curve, calculate the vertical distance from each data point on it to the line connecting the beginning and end points of the curve; S4. Sum the vertical distances of all parameter curves at the same time point to obtain the comprehensive characteristic distances at each time point. S5. Select the time point corresponding to the maximum value of the comprehensive feature distance and record it as the key operating point; S6. Based on the key operating points, the parameter operation curve is recursively divided, and steps S3 to S5 are repeated on each sub-curve segment until the number of key operating points reaches the preset target number. Finally, the key operating points of each parameter operation curve are connected to generate its simplified curve.

2. The method for simplifying multi-parameter operating curves of a gas turbine according to claim 1, characterized in that: In step S4, the weighted summation is performed based on different weighting coefficients preset in the running curves of each parameter, and on the vertical distance calculated in step S3.

3. The method for simplifying multi-parameter operating curves of a gas turbine according to claim 2, characterized in that: In step S4, for each sampling time, the vertical distance of the running curve of each parameter is multiplied by its corresponding weighting coefficient, and the product of all parameters is summed to obtain the comprehensive feature distance at that time.

4. The method for simplifying multi-parameter operating curves of a gas turbine according to claim 3, characterized in that: In step S4, the formula for calculating the weighted sum is: Where N represents the total number of parameter operation curves, d n (t) represents the vertical distance from the nth parameter running curve at time t to the line connecting the beginning and end points of its current processed curve segment. This represents the preset weighting coefficient for each parameter's running curve.

5. The method for simplifying multi-parameter operating curves of a gas turbine according to any one of claims 2-4, characterized in that: The weighting coefficients are set according to the engineering importance of the corresponding parameters in the characterization of the gas turbine's operating status.

6. The method for simplifying multi-parameter operating curves of a gas turbine according to claim 5, characterized in that: The specific values ​​of the weighting coefficients are determined based on the experience of domain experts or statistical analysis of historical operating data.

7. The method for simplifying multi-parameter operating curves of a gas turbine according to claim 5, characterized in that, The specific values ​​of the weighting coefficients are determined by a method that includes iterative optimization and model self-learning. The method includes: performing simulation calibration of multiple sets of weighting coefficient combinations starting from the average weight condition, obtaining an engineering calibration coefficient set by comparing with experimental benchmark data; training a regression prediction model based on the data accumulated from multiple calibrations; and in practical applications, inputting the number of key point targets and the simulation conservatism requirements into the regression prediction model to generate a set of weighting coefficients.

8. The method for simplifying multi-parameter operating curves of a gas turbine according to claim 3, characterized in that, Step S5 specifically includes: traversing the comprehensive feature distances obtained in step S4 at each time point, selecting the maximum value, and recording the time point corresponding to the maximum value and the values ​​of the corresponding parameter operation curves as key operating points.

9. The method for simplifying multi-parameter operating curves of a gas turbine according to claim 1, characterized in that, Step S6 includes: iteratively dividing and filtering the parameter operation curves based on the recorded key operating points until the number of key operating points reaches the preset target number in step S2.

10. The method for simplifying multi-parameter operating curves of a gas turbine according to claim 9, characterized in that, The iterative division and filtering specifically includes: using the latest recorded key operating point as the dividing point, dividing the currently processed parameter running curve segment into two sub-curve segments, and repeating steps S3 to S5 on each sub-curve segment.

11. The method for simplifying multi-parameter operating curves of a gas turbine according to claim 10, characterized in that, Step S6 also includes: when the number of key operating points reaches the preset target number, for each parameter running curve, connect all the recorded key operating points in chronological order to form a simplified curve.

12. The method for simplifying multi-parameter operating curves of a gas turbine according to claim 1, characterized in that: The preprocessing described in step S1 is a normalization process, which specifically involves mapping the data values ​​of each parameter running curve to the interval [0, 1].

13. The method for simplifying multi-parameter operating curves of a gas turbine according to claim 1, characterized in that: Step S2 specifically includes: In step S2, the target number is determined based on the requirements of gas turbine transient simulation for computational efficiency and accuracy.

14. A gas turbine multi-parameter operating curve simplification system, used to execute the gas turbine multi-parameter operating curve simplification method according to any one of claims 1-13, characterized in that, include: The data preprocessing module is used to preprocess the acquired parameter running curves; The feature calculation module is used to calculate the vertical distance from the data point on the running curve of each parameter to the line connecting its first and last points; The feature synthesis module is used to perform a weighted summation of the vertical distances of the running curves of all parameters at the same time to obtain the comprehensive feature distance; The key point extraction module is used to select the time point corresponding to the maximum distance of the comprehensive features as the key working condition point; The iterative control module is used to recursively segment the parameter operation curve based on key operating points, and control the calculation module, fusion module and selection module to iteratively run on the new curve segment until the number of key operating points reaches the target. The curve generation module is used to connect the key operating points of the running curves of various parameters and output simplified curves.

15. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps in the method for simplifying the multi-parameter operating curve of a gas turbine as described in any one of claims 1 to 13.

16. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the steps in the gas turbine multi-parameter operating curve simplification method according to any one of claims 1 to 13 through the computer program.

17. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein the computer program can be executed by an electronic device to perform the steps of the gas turbine multi-parameter operating curve simplification method according to any one of claims 1 to 13.

Images