Function mapping management method for data acquisition system and analog simulation software

Abstract

The invention provides a function mapping management method for a data acquisition system and analog simulation software, and relates to the technical field of data processing, the method comprises the following steps: acquiring an original data set from target equipment; performing noise filtering and abnormal value detection on the original data set; extracting a plurality of feature data corresponding to the analog simulation software model; generating an initial mapping parameter set according to a mapping rule between the feature data and an analog simulation software model input parameter; dynamically adjusting the initial mapping parameter set; converting the feature data into input format data required by a simulation software model; consistency verification is carried out; inputting analog simulation software; verifying the simulation result data, and if the verification is not passed, generating a feedback adjustment parameter according to the difference degree between the simulation result data and the feature data; if the verification is passed, taking the simulation result data as output data of operation evaluation of the target equipment; according to the invention, the autonomy and accuracy of function mapping are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a function mapping management method between a data acquisition system and simulation software. Background Art

[0002] With the rapid development of industrial simulation and digital modeling technology, data acquisition systems and simulation software have been widely used in many fields such as manufacturing, transportation, and energy. In the prior art, the data acquisition system collects the operating data of physical equipment in real time through sensors or monitoring equipment, and converts it into input data that can be used for simulation software, thereby realizing the prediction, optimization and evaluation of the operation of complex systems. For example, in the manufacturing industry, it is common to collect operating data such as vibration and temperature of mechanical equipment and input it into simulation software to predict equipment failure. However, the existing technical implementation usually requires manual definition of the mapping relationship between the collected data and the input parameters of the simulation software. This manual definition method is prone to configuration errors in complex data scenarios, resulting in inaccurate data mapping.

[0003] In specific application scenarios, such as status monitoring and simulation of wind power generation equipment, the acquisition system needs to map data of multiple dimensions, such as wind speed, blade angle, and power generation, to the operating model of the simulation software. However, due to the lack of dynamic adaptive management capabilities for data acquisition and simulation software model parameters in existing technologies, the mapping relationship may need to be updated frequently under different equipment states, and most existing methods rely on static mapping configurations. This static configuration may lead to omissions or incorrect mapping of key parameters when the equipment state changes, thereby affecting the simulation software's accurate assessment of wind power system performance. Summary of the invention

[0004] The purpose of the present invention is to provide a method for managing function mapping between a data acquisition system and simulation software, aiming to solve the problems mentioned in the background technology.

[0005] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0006] A method for managing function mapping between a data acquisition system and simulation software, the method comprising:

[0007] S100, collecting an original data set from a target device, wherein the original data set includes at least one data dimension;

[0008] S200, performing noise filtering and outlier detection on the original data set to obtain a preprocessed data set;

[0009] S300, extracting a plurality of feature data corresponding to the simulation software model according to the preprocessed data set, and generating a comprehensive feature data set, wherein the feature data includes independent data sets for different physical properties;

[0010] S400, generating an initial mapping parameter set according to a mapping rule between feature data and input parameters of a simulation software model;

[0011] S500, dynamically adjusting the initial mapping parameter set according to the real-time operating state of the target device, wherein the dynamic adjustment includes detecting a change in the operating state of the target device, selecting a corresponding preset adjustment strategy according to the change, and generating an adaptation mapping parameter set;

[0012] S600, converting the characteristic data into input format data required by the simulation software model according to the adaptation mapping parameter set, wherein the conversion includes format normalization processing for different types of simulation software models, and outputting a simulation input data set;

[0013] S700: Perform consistency verification on the adaptation mapping parameter set and the simulation input data set, wherein:

[0014] If the verification is passed, the adaptation mapping parameter set is stored as a mapping model configuration; if the verification is not passed, the adaptation mapping parameter set is adjusted according to a predefined correction rule and a simulation input data set is regenerated;

[0015] S800, inputting the simulation input data set into the simulation software to obtain simulation result data;

[0016] S900, verify the simulation result data. If the verification fails, generate feedback adjustment parameters according to the difference between the simulation result data and the characteristic data, where:

[0017] Compare the key indicator differences between the simulation result data and the target equipment operation data to generate a set of difference factors;

[0018] Calculate feedback adjustment weights according to the difference factor set, and update the adaptation mapping parameter set;

[0019] The updated adaptation mapping parameter set is input into step S500 for dynamic adjustment; if the verification passes, the simulation result data is used as the output data of the target device operation evaluation.

[0020] Preferably, the extracting of a plurality of feature data corresponding to the simulation software model according to the preprocessed data set includes:

[0021] According to the preprocessed data set, the trend characteristics and period characteristics in the time series are extracted by dimension-by-dimension analysis to obtain the trend data set and period data set;

[0022] Based on the trend data set, the segmented statistical method is used to generate a multi-interval key statistical data set;

[0023] Perform spectrum analysis on the periodic data set, extract frequency feature data and classify them into frequency domain feature sets;

[0024] Perform feature fusion on trend data, statistical data and frequency feature data to generate a comprehensive feature data set.

[0025] Preferably, the method of generating a multi-interval key statistics data set by using a segmented statistical method based on the trend data set includes:

[0026] The trend data set is divided into multiple time intervals according to the time axis, and the length of each time interval is dynamically set according to the operation cycle of the target device;

[0027] Perform statistical analysis on trend data in each time interval and calculate the mean, median, variance and maximum value of the interval;

[0028] According to the predefined key indicator screening rules, statistics with significant fluctuations or change trends are selected as key statistics;

[0029] The key statistics in all time intervals are normalized to generate a multi-interval key statistics data set.

[0030] Preferably, performing spectrum analysis on the periodic data set, extracting frequency feature data and classifying it into a frequency domain feature set, comprises:

[0031] Perform fast Fourier transform on the periodic data set to convert the time domain data into frequency domain data;

[0032] Extract the main frequency components in the spectrum and calculate the corresponding amplitude, phase and power density;

[0033] According to the amplitude of the frequency component, the frequency component exceeding the preset amplitude threshold is selected as the main frequency feature;

[0034] The amplitude, phase, and power density of the main frequency components are classified and a frequency domain feature set is generated.

[0035] Preferably, the generating of the initial mapping parameter set according to the mapping rules between the characteristic data and the input parameters of the simulation software model comprises:

[0036] Group the comprehensive feature data set and the simulation software model input parameter set into corresponding groups, and establish feature grouping mapping rules;

[0037] According to the feature grouping mapping rule, the correlation of the feature data is weightedly calculated to generate an initial mapping parameter matrix; the generation formula of the initial mapping parameter matrix is: ,in, is the first Line The parameter value of the column, For the The characteristic data and The correlation coefficient between the input parameters, and is the adjustment coefficient, The feature data set eigenvalues, Input parameter set for simulation software model The nominal value of the parameter, is the total number of features in the feature dataset, is the base of natural logarithms; , For the The characteristic data is in The values ​​in the dimensions, For the The input parameters are The values ​​in the dimensions, is the mean of the feature data, is the mean of the input parameters, For the The weight coefficient of the dimension, is the total number of data dimensions;

[0038] According to the initial mapping parameter matrix, each parameter value is extracted, and range normalization and structure processing are performed on it to generate an initial mapping parameter set.

[0039] Preferably, the initial mapping parameter set is dynamically adjusted according to the real-time operating state of the target device, and the dynamic adjustment includes detecting the change amount of the operating state of the target device, selecting a corresponding preset adjustment strategy according to the change amount, and generating an adaptation mapping parameter set, including:

[0040] According to the real-time operating status of the target device, the operating status change is extracted to form a state change indicator data set;

[0041] According to the state change indicator data set, the weight factors in the initial mapping parameter matrix are recalculated to generate an adjustment mapping parameter matrix; the generation formula of the adjustment mapping parameter matrix is: ,in, is the first in the adjusted mapping parameter matrix Line The parameter value of the column, is the first mapping parameter matrix before adjustment Line The parameter value of the column, is the adjustment coefficient, For the The real-time running status change of feature data, , For the The actual operating status of the characteristic data, For the The expected operating state of the characteristic data, is the total number of state changes, For the The real-time running status change of feature data, is the adjustment coefficient;

[0042] The initial mapping parameter set is adjusted according to the adjustment mapping parameter matrix to generate an adapted mapping parameter set.

[0043] Preferably, the feature data is converted into input format data required by the simulation software model according to the adaptation mapping parameter set, wherein the conversion includes format normalization processing for different types of simulation software models, and outputting a simulation input data set, including:

[0044] According to the adaptation mapping parameter set, the comprehensive feature data set is grouped and decomposed to form a formatted feature data set;

[0045] For each set of data in the formatted feature data set, unit normalization is performed to generate a normalized feature data set;

[0046] According to the input requirements of different simulation software models, the arrangement order in the normalized feature data set is adjusted and encapsulated as a simulation input data packet;

[0047] Output the simulation input data packet as the simulation input data set.

[0048] Preferably, the consistency verification of the adaptation mapping parameter set and the simulation input data set includes:

[0049] Verify whether each parameter in the simulation input data package meets the input requirements of the simulation software model;

[0050] Compare the key parameters in the adaptation mapping parameter set with the constraints of the simulation software model to determine their consistency;

[0051] If a parameter conflict is detected, a correction data set is generated based on the type of conflicting parameters, where:

[0052] For parameters that exceed the input range of the simulation software model, adjust their normalized values ​​to the input range of the simulation software model;

[0053] For missing parameters, find the closest alternative value from the adaptation mapping parameter set;

[0054] For repeated or redundant parameters, delete conflicting items and maintain the uniqueness of key parameters;

[0055] The adaptation mapping parameter set is updated according to the correction data set, and the simulation input data set is regenerated.

[0056] Preferably, the comparing the key indicator differences between the simulation result data and the target device operation data to generate a difference factor set includes:

[0057] Extracting key indicator values ​​of target device operation data, wherein the key indicators include fluctuation range, statistical characteristics and frequency characteristics of time series parameters;

[0058] Extracting key indicator values ​​of the simulation result data, wherein the key indicators correspond one-to-one with the key indicators in the target device operation data;

[0059] Compare the differences between the simulation result data and each key indicator in the target equipment operation data, including calculating the mean deviation, extreme value deviation and deviation degree of the change trend of the corresponding indicator;

[0060] Based on the differences in key indicators, a set of difference factors is generated according to preset weight rules, and the preset weight rules are set according to the degree of influence of the key indicators on the simulation results, wherein the degree of influence of the key indicators is determined by sensitivity analysis in the simulation software model.

[0061] Preferably, the calculation formula of the feedback adjustment weight is: ,in, is the adjusted feedback weight, expressed as The simulation result data parameter values, is the feedback weight before adjustment, expressed as The simulation result data parameter values, inherited from the adaptation mapping parameter set of the previous round, is the adjustment coefficient, For the The simulation result data and The actual operation data is in The key indicator difference of the parameter value is , For the The simulation result data parameter values, No. The actual operation data parameter values, For the The difference factor The weight coefficient of the parameter value, is the number of difference factors involved in the adjustment calculation, For the The simulation result data and The actual operation data is in The key indicator difference of parameter values ​​is is the total number of difference factors.

[0062] The above solution of the present invention includes at least the following beneficial effects:

[0063] The present invention can acquire multi-dimensional data in the operation process of the equipment in real time by collecting the original data set from the target equipment. These data cover information such as equipment operating status, environmental parameters and external interference, and provide comprehensive basic data support for subsequent simulations. Compared with the traditional method that relies on manual collection and sorting, this method automatically collects data through sensors and transmits it in real time, which not only significantly improves the data acquisition efficiency, but also covers more dimensional key parameters, such as wind speed, blade angle and power generation in wind power generation. In response to the noise and outliers in the original data, this method can effectively identify and eliminate invalid data through noise filtering and outlier detection technology, thereby ensuring the high quality and reliability of data input.

[0064] Furthermore, this method generates a comprehensive feature data set by extracting multiple feature data related to the simulation software model from the preprocessed data set, which completely solves the problem that complex multidimensional data cannot be effectively processed in the prior art. For example, in a wind power generation simulation scenario, the trend characteristics of wind speed, the dynamic change characteristics of blade angles, and the periodic characteristics of power generation can be extracted by grouping to form a comprehensive feature data set. This feature extraction and integration method ensures the comprehensiveness and accuracy of the simulation software model input, and avoids the problem of insufficient simulation accuracy caused by the single dimension of input data.

[0065] The core innovation of this method lies in the introduction of dynamic adjustment and feedback mechanism. By dynamically adjusting the initial mapping parameter set according to the real-time operating status of the target device, this method can quickly respond to changes in the device status, solving the problem that static mapping relationships in the prior art are difficult to adapt to complex scenarios. For example, in a wind farm, when the wind speed changes suddenly or the blade angle is adjusted, the change in the operating status can be detected in real time, and the mapping parameter set can be recalculated through a preset adjustment strategy, so that the input parameters can be adapted to the needs of the simulation software model in real time. This dynamic adjustment capability greatly improves the flexibility and adaptability of the simulation, and avoids the problem of missing or incorrect mapping of key parameters.

[0066] In addition, through consistency verification and feedback adjustment mechanism, this method establishes a closed-loop optimization process from simulation results to input parameters. In the simulation result data verification step, the simulation result data can be compared and analyzed with the actual operation data of the target device, feedback adjustment weights can be generated based on the difference factor set, and the adaptation mapping parameter set can be updated. This closed-loop feedback mechanism can continuously optimize the simulation input parameters so that the simulation results gradually approach the actual operating state of the equipment. For example, in the performance evaluation of wind power generation systems, by comparing the generated power output of the simulation with the actual power generation data, a deviation correction factor is generated to adjust the mapping parameters, thereby improving the accuracy and credibility of the next round of simulation.

[0067] Compared with the prior art, the mapping management method of the present invention has significant advantages in many aspects. First, this method eliminates the error sources that rely on manual configuration in traditional methods through automated collection and dynamic adjustment, thereby improving the accuracy and efficiency of data mapping. Secondly, this method constructs a full-process dynamic management system between data input and simulation software models through feature extraction, dynamic adjustment, and feedback optimization, which can adapt to changes in the operating status of different equipment and significantly improve the flexibility and stability of the simulation software model. Finally, the closed-loop optimization process of this method enables the accuracy of the simulation results to gradually improve with the operating cycle, which is particularly suitable for high-precision scenarios such as equipment performance evaluation and fault prediction.

[0068] In general, the present invention solves the problems of inaccurate data mapping and insufficient adaptability caused by static configuration and manual intervention in the prior art by integrating data collection, dynamic adjustment and feedback optimization technologies, and provides smarter, more efficient and more reliable technical support for the simulation of complex systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 It is a flowchart of a method for managing function mapping between a data acquisition system and simulation software provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0070] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0071] like Figure 1 As shown, an embodiment of the present invention provides a method for managing function mapping between a data acquisition system and simulation software, the method comprising:

[0072] S100, collecting an original data set from a target device, wherein the original data set includes at least one data dimension;

[0073] S200, performing noise filtering and outlier detection on the original data set to obtain a preprocessed data set;

[0074] S300, extracting a plurality of feature data corresponding to the simulation software model according to the preprocessed data set, and generating a comprehensive feature data set, wherein the feature data includes independent data sets for different physical properties;

[0075] S400, generating an initial mapping parameter set according to a mapping rule between feature data and input parameters of a simulation software model;

[0076] S500, dynamically adjusting the initial mapping parameter set according to the real-time operating state of the target device, wherein the dynamic adjustment includes detecting a change in the operating state of the target device, selecting a corresponding preset adjustment strategy according to the change, and generating an adaptation mapping parameter set;

[0077] S600, converting the characteristic data into input format data required by the simulation software model according to the adaptation mapping parameter set, wherein the conversion includes format normalization processing for different types of simulation software models, and outputting a simulation input data set;

[0078] S700: Perform consistency verification on the adaptation mapping parameter set and the simulation input data set, wherein:

[0079] If the verification is passed, the adaptation mapping parameter set is stored as a mapping model configuration; if the verification is not passed, the adaptation mapping parameter set is adjusted according to a predefined correction rule and a simulation input data set is regenerated;

[0080] S800, inputting the simulation input data set into the simulation software to obtain simulation result data;

[0081] S900, verify the simulation result data. If the verification fails, generate feedback adjustment parameters according to the difference between the simulation result data and the characteristic data, where:

[0082] Compare the key indicator differences between the simulation result data and the target equipment operation data to generate a set of difference factors;

[0083] Calculate feedback adjustment weights according to the difference factor set, and update the adaptation mapping parameter set;

[0084] The updated adaptation mapping parameter set is input into step S500 for dynamic adjustment; if the verification passes, the simulation result data is used as the output data of the target device operation evaluation.

[0085] In an embodiment of the present invention, by collecting raw data sets from the target device and performing multi-step processing on them, full-process optimization from data acquisition to simulation result evaluation can be achieved. First, data acquisition can capture multi-dimensional dynamic information during the operation of the target device, including time series characteristics, environmental parameters, and internal operating indicators of the device. This multi-dimensional data acquisition method effectively adapts to the needs of different devices and scenarios. For industrial scenarios, the collected data may include temperature, pressure, vibration amplitude, etc.; in intelligent transportation applications, data collection may cover vehicle speed, position, and environmental conditions.

[0086] After data collection is completed, the raw data is preprocessed through noise filtering and outlier detection steps. This process can significantly improve the quality and credibility of the data. By filtering out invalid data and outliers, the problem of inaccurate simulation results due to data bias can be avoided. For example, in equipment fault monitoring, sensors may record abnormally high values ​​due to external interference. Through detection technology, such data can be identified and eliminated, thereby generating a reliable preprocessed data set.

[0087] Subsequently, various characteristic data related to the simulation software model are extracted, including trend characteristics, frequency characteristics and other key characteristics. These characteristic data not only cover the static operating state of the target equipment, but also reflect its dynamic change behavior. After the extraction is completed, the generation of a comprehensive characteristic data set significantly improves the accuracy of the simulation input and ensures that the model input is more diversified and comprehensive. For example, in wind power generation simulation, comprehensive characteristic data can accurately characterize the relationship between wind speed, power output and blade vibration, thereby improving the predictive ability of the simulation software model.

[0088] The initial mapping parameter set is generated through the mapping relationship between the characteristic data and the input parameters of the simulation software. This process fully combines the complex relationship between the data characteristics and the simulation software model requirements. Combined with the detection and dynamic adjustment of the real-time operating state changes, the adaptive optimization of the initial mapping parameter set can be achieved. This dynamic adjustment is particularly important when the operating state of the equipment changes significantly. For example, in the process of switching the manufacturing equipment from high-speed mode to low-speed mode, the adjusted mapping parameters can promptly reflect the changes in operating characteristics and ensure the adaptability of the simulation software model.

[0089] In addition, by converting the mapping parameters into simulation software input data and performing consistency verification, it can be ensured that the simulation input data package generated finally meets the model requirements. If the verification fails, new parameter inputs are generated through predefined correction rules, thus forming a closed-loop optimization process. This process greatly improves the adaptability of the data and the accuracy of the model calculation, avoiding simulation failures caused by input data not meeting model requirements.

[0090] Finally, by inputting the simulation input data into the simulation software model, the simulation result data is obtained, and by comparing the key indicators with the actual operation data, the mapping parameters can be further optimized. This dynamic feedback mechanism based on the adjustment of the difference factor provides strong support for the long-term optimization of the simulation software model. Through complete process design and multi-level data processing and optimization technology, the entire method not only improves the adaptability of the simulation, but also significantly improves the accuracy and reliability of the simulation results.

[0091] In a preferred embodiment of the present invention, the extracting of a plurality of feature data corresponding to the simulation software model according to the preprocessed data set includes:

[0092] According to the preprocessed data set, the trend characteristics and period characteristics in the time series are extracted by dimension-by-dimension analysis to obtain the trend data set and period data set;

[0093] Based on the trend data set, the segmented statistical method is used to generate a multi-interval key statistical data set;

[0094] Perform spectrum analysis on the periodic data set, extract frequency feature data and classify them into frequency domain feature sets;

[0095] Perform feature fusion on trend data, statistical data and frequency feature data to generate a comprehensive feature data set.

[0096] In the embodiment of the present invention, by establishing a connection between the preprocessed data set and the feature data corresponding to the simulation software model, the logical classification and structural optimization of the data can be efficiently achieved. The dimension-by-dimension analysis method can gradually extract key features for different dimensions of the data. For example, trend feature extraction enables the capture of long-term changes in equipment operation data, while period feature extraction can highlight repetitive patterns or fixed fluctuations in the data. This segmented analysis method ensures the integrity and accuracy of feature extraction.

[0097] Furthermore, by generating a multi-interval key statistics data set through a segmented statistical method, the trend characteristics can be deeply analyzed, for example, key statistics such as mean, variance, and maximum value can be extracted according to different intervals of the time series data. These statistics can effectively summarize the operating rules of each time period, thereby providing an accurate description for the input of the simulation software model. In addition, spectral analysis of the periodic data set can convert time domain information into frequency domain information and extract key spectral features such as frequency and amplitude. This frequency domain information is particularly suitable for vibration analysis or periodic signal modeling, providing high-quality input data for simulation software.

[0098] Combining the above technologies, the trend features, statistical features and frequency features are integrated into a comprehensive feature data set through the feature fusion step, which can significantly improve the adaptability of simulation software models to complex systems. For example, in the operation simulation of complex mechanical equipment, these comprehensive features can significantly enhance the robustness and reliability of the model, thereby achieving more accurate prediction and optimization.

[0099] More specifically, the method of extracting trend features and period features in the time series by dimension-by-dimension analysis based on the preprocessed data set to obtain a trend data set and a period data set includes:

[0100] Trend characteristics refer to the direction or pattern of long-term changes in data. In this method, each dimension of data can be processed separately through dimension-by-dimension analysis. For example, for the temperature series data of a certain device, it can be observed that the temperature gradually increases over time. In specific implementation, short-term fluctuations can be eliminated through commonly used methods in the prior art (such as the sliding average method or the cumulative sum analysis method) to extract the overall change trend of the data.

[0101] For complex scenarios, you can also identify trend change points by setting thresholds. For example, the time point when the temperature changes from rising to falling can be marked by threshold difference technology to further extract segmented characteristics of different trend stages.

[0102] Periodic features refer to repetitive or periodic patterns in data. For example, in vibration monitoring, periodic fluctuations can indicate that the equipment is in normal operation. Periodic features can be extracted by frequency domain conversion techniques, such as fast Fourier transform, which converts time domain data into frequency domain data to identify the main frequency and harmonic frequency of the signal.

[0103] In addition, repetitive changes can also be detected directly in the time domain through the sliding window method. For example, by applying window calculation to the change sequence of the vibration amplitude of a certain device, the change of the peak amplitude within a fixed time interval can be found, which can be used as a direct reflection of the periodic characteristics.

[0104] By processing the data of each dimension in a dimension-by-dimension analysis manner, the respective trend features and period features can be extracted. The trend dataset and period dataset respectively record the long-term change patterns and periodic characteristics of the target device in different dimensions, providing independent and detailed data support for subsequent feature fusion.

[0105] More specifically, the feature fusion of the trend data, the statistical data and the frequency feature data to generate a comprehensive feature data set includes:

[0106] Trend data describes the overall change pattern of the time series, while statistical data provides quantitative analysis results, such as mean, variance, maximum, minimum, etc. The fusion of trend data and statistical data can be achieved by segmenting the trend data and calculating the statistical characteristics of each time period. For example, after dividing the rising trend of temperature into multiple time periods, the average temperature and fluctuation range of each period can be calculated. These statistics can more accurately describe the quantitative characteristics of the trend.

[0107] Frequency feature data provides periodic information about the dynamic behavior of the device, such as main frequency and power density. These frequency features can be combined with trend and statistics data as separate feature dimensions. When fused, the corresponding frequency features can be matched for each time period. For example, the fluctuation of temperature data can be combined with the main frequency components of the device operation to further analyze the relationship between temperature fluctuation and operating status.

[0108] In the specific implementation, the above features can be fused in a table structure or a multi-dimensional matrix. For example, the data of each time period contains multiple fields of trend data, statistical data, and frequency feature data, and finally forms a comprehensive feature data set. For time periods of different lengths, feature fusion can align the data through interpolation methods to ensure consistency between different features.

[0109] The generation of a comprehensive feature data set organically combines the static state and dynamic behavior of the equipment, providing a multi-level and comprehensive feature description for subsequent model input.

[0110] In a preferred embodiment of the present invention, the method of generating a multi-interval key statistics data set based on the trend data set by using a segmented statistical method includes:

[0111] The trend data set is divided into multiple time intervals according to the time axis, and the length of each time interval is dynamically set according to the operation cycle of the target device;

[0112] Perform statistical analysis on trend data in each time interval and calculate the mean, median, variance and maximum value of the interval;

[0113] According to the predefined key indicator screening rules, statistics with significant fluctuations or change trends are selected as key statistics;

[0114] The key statistics in all time intervals are normalized to generate a multi-interval key statistics data set.

[0115] In the embodiment of the present invention, the segmented statistical method is used to generate a multi-interval key statistic data set, which can make feature extraction more refined. The trend data set is divided into multiple time intervals according to the time axis, and the interval length is dynamically adjusted according to the operating cycle of the target device, which can adapt to the characteristics of different devices and working conditions. For example, in short-cycle equipment, the intervals can be divided more densely, while for long-term operating equipment, the intervals can be set more loosely, thereby achieving adaptive processing of data characteristics.

[0116] Furthermore, by performing statistical analysis on the trend data in each time interval, key statistics reflecting the equipment status can be extracted, such as mean, median, variance, and maximum value. These statistics can effectively describe the fluctuation range and change trend of the data. For example, in the monitoring of wind power generation equipment, the wind speed changes and power output fluctuations in different time periods can be effectively characterized by these statistics.

[0117] By pre-defining the screening rules of key indicators, statistics with significant change trends or fluctuations can be extracted, thereby filtering out irrelevant or noisy data. Finally, all key statistics are normalized to adapt them to the input requirements of the simulation software model and avoid model calculation errors caused by different data dimensions. This process greatly improves the quality and consistency of simulation input data, thereby providing a reliable basis for subsequent mapping parameter generation.

[0118] More specifically, the trend data set is divided into multiple time intervals according to the time axis, and the length of each time interval is dynamically set according to the operation cycle of the target device, including:

[0119] The operation cycle of a device is usually determined by the working characteristics of the device. For example, for industrial equipment, the operation cycle may include stages such as start, run, and stop, while for transportation equipment (such as vehicles), the operation cycle may be related to driving speed or road condition changes. Therefore, the length of the time interval can be dynamically adjusted according to the operating status of the device. For example, in the stable stage of equipment operation, the time interval can be divided more loosely; while in the stage of drastic state changes, the time interval can be divided more densely.

[0120] In practical applications, dynamic adjustment of the time interval length can be achieved by real-time monitoring of the state changes of the equipment. For example, by monitoring the vibration frequency of the equipment, when the frequency remains constant, a longer time interval can be used; when the frequency changes significantly, the time interval can be shortened to capture more details. This dynamic adjustment strategy can be combined with the sliding window method to adjust the interval length in real time at different time periods.

[0121] For example, in the simulation of a wind turbine, when the wind speed changes slightly, the time interval can be set to 1 minute; when the wind speed changes dramatically, it can be adjusted to 30 seconds, thereby more accurately reflecting the operating characteristics of the equipment.

[0122] Through dynamic time interval division, the accuracy and adaptability of feature extraction can be significantly improved, ensuring that the data in each time period can accurately reflect the actual operating status of the equipment.

[0123] More specifically, the selection of statistics with significant fluctuations or changing trends as key statistics according to the predefined key indicator screening rules includes:

[0124] Key indicator screening rules can be set according to the operating characteristics of the target equipment and simulation requirements. For example, for wind power generation simulation, the variance of wind speed and power generation may be important key indicators because they can reflect the volatility of the system; while for temperature monitoring of industrial equipment, the maximum and minimum values ​​may be more important because they can reflect the characteristics of extreme states.

[0125] First, the statistics in each time interval are calculated, such as mean, variance, maximum, minimum, etc. Then, these statistics are compared with the predefined screening rules to filter out the statistics that meet the conditions. For example, a fluctuation threshold is set, and if the variance of a statistic exceeds the threshold, it is marked as a key statistic.

[0126] The selected key statistics will be used as the main data for the next step of processing, and the remaining non-key statistics can be ignored. This processing method can significantly reduce the amount of data and increase the influence of key features on the simulation software model.

[0127] By screening key statistics, we can ensure that the input data can effectively reflect the operating characteristics of the target device and avoid simulation deviations caused by irrelevant or noisy data.

[0128] In a preferred embodiment of the present invention, the step of performing spectrum analysis on the periodic data set, extracting frequency feature data and classifying the frequency feature data into a frequency domain feature set includes:

[0129] Perform fast Fourier transform on the periodic data set to convert the time domain data into frequency domain data;

[0130] Extract the main frequency components in the spectrum and calculate the corresponding amplitude, phase and power density;

[0131] According to the amplitude of the frequency component, the frequency component exceeding the preset amplitude threshold is selected as the main frequency feature;

[0132] The amplitude, phase, and power density of the main frequency components are classified and a frequency domain feature set is generated.

[0133] In an embodiment of the present invention, spectrum analysis of a periodic data set can effectively capture periodic information in the data. By fast Fourier transforming, the time domain data is converted into frequency domain data, so that the implicit frequency components, amplitude distribution and phase characteristics in the data can be intuitively displayed. For example, in the monitoring of rotating machinery, spectrum analysis can reveal the main frequency and harmonic components of the equipment, providing a basis for fault diagnosis and performance optimization.

[0134] Extracting the main frequency components in the spectrum and calculating the corresponding amplitude, phase and power density can provide in-depth analysis of the energy distribution and characteristic position of the signal. Furthermore, by setting a preset amplitude threshold, noise signals and unimportant frequency components can be filtered out to ensure that the extracted frequency features can accurately reflect the periodic behavior of the device.

[0135] By classifying the amplitude, phase and power density of the main frequency components, a set of frequency domain features with clear physical meaning can be formed. These frequency domain features can not only be used as input for simulation software models, but can also be directly applied to the monitoring and evaluation of equipment operating status. For example, in vibration analysis, frequency domain features can be used to determine whether the equipment is in an abnormal operating state, providing decision support for equipment maintenance and optimization.

[0136] In a preferred embodiment of the present invention, the initial mapping parameter set is generated according to the mapping rules between the characteristic data and the input parameters of the simulation software model, including:

[0137] Group the comprehensive feature data set and the simulation software model input parameter set into corresponding groups, and establish feature grouping mapping rules;

[0138] According to the feature grouping mapping rule, the correlation of the feature data is weightedly calculated to generate an initial mapping parameter matrix; the generation formula of the initial mapping parameter matrix is: ,in, is the first Line The parameter value of the column, For the The characteristic data and The correlation coefficient between the input parameters, and is the adjustment coefficient, The feature data set eigenvalues, Input parameter set for simulation software model The nominal value of the parameter, is the total number of features in the feature dataset, is the base of natural logarithms; , For the The characteristic data is in The values ​​in the dimensions, For the The input parameters are The values ​​in the dimensions, is the mean of the feature data, is the mean of the input parameters, For the The weight coefficient of the dimension, is the total number of data dimensions;

[0139] According to the initial mapping parameter matrix, each parameter value is extracted, and range normalization and structure processing are performed on it to generate an initial mapping parameter set.

[0140] In an embodiment of the present invention, an initial mapping parameter set is generated through an initial mapping parameter matrix, so that efficient docking of feature data with input parameters of a simulation software model can be achieved. This process is based on feature grouping mapping rules, and the comprehensive feature data set is grouped and matched with the model input parameters, so that the design of mapping rules is more in line with the needs of actual application scenarios. For example, for industrial equipment simulation, mapping rules can be grouped according to physical characteristics such as temperature, pressure, and vibration, thereby improving the correlation between input parameters and feature data.

[0141] In the process of generating the mapping parameter matrix, the correlation between the feature data and the input parameters is weighted to ensure that the generated parameter matrix can fully reflect the data characteristics and model requirements. This process uses a mathematical model to accurately describe the nonlinear relationship between the feature data and the input parameters, and quantifies these complex relationships through the weighting factors and adjustment coefficients of the mapping matrix. Through this mapping matrix, a large amount of scattered feature data can be integrated into a logically clear and adaptable mapping parameter set.

[0142] In addition, by performing range standardization on the parameter values ​​of the initial mapping parameter matrix, it can be further ensured that all parameter values ​​meet the unified input requirements. Range standardization not only improves the consistency of mapping parameters, but also enhances the stability of input data in model calculations. Especially in multi-dimensional data applications, standardization can avoid calculation errors caused by inconsistent dimensions or ranges. For example, when involving data sets of different units (such as temperature and pressure), through standardization, the values ​​of the parameter matrix can be uniformly mapped to a specified range, thereby ensuring the reliability of model calculations.

[0143] Finally, through structured processing, the generated initial mapping parameter set can meet the input requirements of different types of simulation software models. The flexibility of this set makes it suitable for a variety of application scenarios. For example, in traffic simulation, the set can contain vehicle dynamic characteristics; in industrial equipment monitoring, the set may contain dynamic data of key performance indicators. The parameter set generated by this process provides a solid foundation for subsequent dynamic adjustment and simulation optimization, significantly improving the adaptability of the system and the computational efficiency of the simulation software model.

[0144] More specifically, the comprehensive feature data set is grouped into correspondence with the simulation software model input parameter set, and feature grouping mapping rules are established, including:

[0145] There is usually an inherent logical connection between each type of feature data in the comprehensive feature data set and the set of simulation software input parameters. For example, in wind power generation simulation, wind speed and blade angle data correspond to wind load parameters, and power generation data corresponds to power generation efficiency parameters. By analyzing the feature data and input parameters, they can be grouped according to physical meaning or application requirements.

[0146] First, each feature in the comprehensive feature data set is labeled, including the source, physical meaning, and dimensional information of the data. Then, according to the classification of the input parameters of the simulation software, the feature data is grouped and matched with the input parameters. For example, in wind power generation simulation, features such as wind speed and wind direction can be divided into one group, corresponding to the wind load input parameters, while features such as temperature and humidity can be divided into another group, corresponding to the environmental parameter input.

[0147] After grouping is completed, you need to define mapping rules for each group. Mapping rules include the following:

[0148] The mapping relationship between feature data and input parameters, such as direct mapping or mapping through weighted combination.

[0149] Processing steps required during the mapping process, such as normalization, denoising, or dimensionality conversion.

[0150] The priority of mapping, such as which feature data has a higher weight in the many-to-one mapping.

[0151] By establishing grouping and mapping rules, the automatic connection between comprehensive feature data sets and simulation input parameters can be effectively achieved, avoiding logical errors in manual configuration.

[0152] More specifically, the initial mapping parameter matrix is ​​used to extract each parameter value, and range normalization and structural processing are performed on the parameter value to generate an initial mapping parameter set, including:

[0153] Each element of the initial mapping parameter matrix corresponds to a mapping parameter value, which is usually calculated from the relationship between the feature data and the input parameters. In actual operation, each value in the matrix can be directly read and stored as a list or array for subsequent processing.

[0154] The extracted parameter values ​​may be distributed in different numerical ranges, and simulation software models usually have specific requirements for the range of input parameters. In order to ensure that these parameter values ​​are within a uniform range, standardization is required. For example, the parameter values ​​can be adjusted to the range of 0 to 1 through linear mapping, or adjusted to other ranges (such as -1 to 1) according to the actual needs of the model. This processing step can effectively avoid simulation calculation errors caused by parameter value ranges that are too large or too small.

[0155] After completing the range standardization, these parameter values ​​need to be reorganized into a structured format that meets the requirements of the simulation software model. For example, the parameter values ​​can be rearranged according to the row and column structure of the original matrix, or the parameter values ​​can be organized into key-value pairs according to the grouping correspondence rules. If the simulation software needs to input a multi-level data structure, the parameter values ​​can be further divided into different levels.

[0156] The generated initial mapping parameter set is ultimately used as the initial input of the simulation software model, providing a reliable data basis for model calculation.

[0157] In a preferred embodiment of the present invention, the initial mapping parameter set is dynamically adjusted according to the real-time operating state of the target device, and the dynamic adjustment includes detecting the change amount of the operating state of the target device, selecting a corresponding preset adjustment strategy according to the change amount, and generating an adaptation mapping parameter set, including:

[0158] According to the real-time operating status of the target device, the operating status change is extracted to form a state change indicator data set;

[0159] According to the state change indicator data set, the weight factors in the initial mapping parameter matrix are recalculated to generate an adjustment mapping parameter matrix; the generation formula of the adjustment mapping parameter matrix is: ,in, is the first in the adjusted mapping parameter matrix Line The parameter value of the column, is the first mapping parameter matrix before adjustment Line The parameter value of the column, is the adjustment coefficient, For the The real-time running status change of feature data, , For the The actual operating status of the characteristic data, For the The expected operating state of the characteristic data, is the total number of state changes, For the The real-time running status change of feature data, is the adjustment coefficient;

[0160] The initial mapping parameter set is adjusted according to the adjustment mapping parameter matrix to generate an adapted mapping parameter set.

[0161] In an embodiment of the present invention, the initial mapping parameter set is dynamically adjusted according to the real-time operating status of the target device, which can significantly improve the adaptability and flexibility of the parameter set. During the dynamic adjustment process, the change in the real-time operating status of the device is extracted and a state change indicator data set is generated, which can capture the changing characteristics of the device's operating status. This process is especially important for equipment under complex working conditions. For example, on a production line with high-frequency changes, real-time monitoring of the key indicators of the equipment (such as temperature, pressure, vibration amplitude, etc.) can dynamically reflect the current operating status of the equipment.

[0162] According to the state change indicator data set, the weight factors in the initial mapping parameter matrix are recalculated, and the adjusted mapping parameter matrix is ​​generated. This process adjusts the weight factors so that the mapping relationship can more accurately reflect the state characteristics of the current device. The recalculation of the weight factors is combined with the normalization of the real-time changes to ensure the stability and balance of the adjustment results. For example, for device parameters with large sudden changes, the weight factor adjustment will be larger, thereby increasing the sensitivity to these parameters.

[0163] By adjusting the mapping parameter matrix, a set of adaptive mapping parameters can be dynamically generated to better meet the real-time operation requirements of the device. This dynamic adjustment method is not only suitable for the real-time optimization of a single device, but also can improve the overall operating efficiency in multi-device collaborative operation scenarios. For example, in multi-machine joint simulation, the operating status of each device may affect the overall simulation results. Dynamic adjustment can achieve global optimization and ensure a high degree of consistency between the simulation results and the actual operating status.

[0164] More specifically, adjusting the initial mapping parameter set according to the adjustment mapping parameter matrix to generate the adaptation mapping parameter set includes:

[0165] The adjustment mapping parameter matrix is ​​generated based on the real-time operating status of the target device. For example, by monitoring the vibration frequency, temperature or other operating indicators of the device, the change in the device status can be calculated in real time. The adjustment mapping parameter matrix uses these changes as input and modifies the initial parameters according to certain rules.

[0166] Each element in the adjustment mapping parameter matrix represents a correction value for the initial parameter set. By adding the adjustment value to the initial parameter set, an adaptation mapping parameter set can be obtained. For example, if an initial parameter needs to be adjusted according to the temperature change of the device, the adjustment value can be calculated by the temperature change and the preset weight, and the adjusted parameter value reflects the best configuration under the current state.

[0167] The adjusted parameter set is stored in the form of an adapted mapping parameter set for the next step of input to the simulation software model. Compared with the initial mapping parameter set, the adapted mapping parameter set can better reflect the current operating state of the device, thereby improving the accuracy of the simulation results.

[0168] In a preferred embodiment of the present invention, the feature data is converted into input format data required by the simulation software model according to the adaptation mapping parameter set, wherein the conversion includes format normalization processing for different types of simulation software models, and outputting a simulation input data set, including:

[0169] According to the adaptation mapping parameter set, the comprehensive feature data set is grouped and decomposed to form a formatted feature data set;

[0170] For each set of data in the formatted feature data set, unit normalization is performed to generate a normalized feature data set;

[0171] According to the input requirements of different simulation software models, the arrangement order in the normalized feature data set is adjusted and encapsulated as a simulation input data packet;

[0172] Output the simulation input data packet as the simulation input data set.

[0173] In an embodiment of the present invention, the adaptation mapping parameter set is used for the conversion of feature data, which can meet the normalization requirements of the simulation software model for the input format. In this process, the comprehensive feature data set is first grouped and decomposed, which can effectively reduce the complexity of the input data, so that each group of data can correspond to the specific input requirements of the simulation software model. The grouped data not only improves the efficiency of the model input, but also facilitates the subsequent normalization and sorting processing.

[0174] Through unit normalization, the numerical range in the feature data can be adjusted to the unified standard required by the simulation software model. For example, for a model with strict input range requirements, the feature data can be adjusted to the range of zero to one to ensure the accuracy of the model calculation. In addition, by adjusting the arrangement order of the normalized feature data and encapsulating it as a simulation input data packet, the input data can be made to fully meet the format requirements of the simulation software model, avoiding calculation errors caused by data format problems.

[0175] The technical effect of this feature data conversion process significantly improves the quality and consistency of simulation input data. For example, in complex equipment simulation, different input features may come from multiple data sources. Through this conversion step, seamless data integration can be achieved to ensure the accuracy and efficiency of model input. At the same time, through data packet encapsulation, the security and stability of simulation software model input can be effectively improved. This encapsulation format is particularly important in remote simulation applications.

[0176] More specifically, the step of grouping and decomposing the comprehensive feature data set according to the adaptation mapping parameter set to form a formatted feature data set includes:

[0177] The comprehensive feature data set contains multi-dimensional and multi-type data, and the simulation software model may have more detailed requirements for input data. Therefore, according to the rules in the adaptation mapping parameter set, the comprehensive feature data set is grouped and decomposed according to different dimensions or categories. For example, temperature, pressure, and vibration features can be divided into independent groups, so that the simulation software model can process these data separately.

[0178] Each set of data is formatted according to the input format requirements of the simulation software model. For example, if the simulation software model needs to input a two-dimensional array, each set of data needs to be organized according to a fixed row and column structure. If the model requires hierarchical input data, the feature data can be stored hierarchically through a nested structure.

[0179] The formatted feature data set meets the input requirements of the simulation software model and can be directly used for model calculation. For example, in multi-device collaborative simulation, the formatted feature data set can represent the feature data of each device separately while maintaining the overall logical structure, which is convenient for model processing.

[0180] In a preferred embodiment of the present invention, the consistency verification of the adaptation mapping parameter set and the simulation input data set includes:

[0181] Verify whether each parameter in the simulation input data package meets the input requirements of the simulation software model;

[0182] Compare the key parameters in the adaptation mapping parameter set with the constraints of the simulation software model to determine their consistency;

[0183] If a parameter conflict is detected, a correction data set is generated based on the type of conflicting parameters, where:

[0184] For parameters that exceed the input range of the simulation software model, adjust their normalized values ​​to the input range of the simulation software model;

[0185] For missing parameters, find the closest alternative value from the adaptation mapping parameter set;

[0186] For repeated or redundant parameters, delete conflicting items and maintain the uniqueness of key parameters;

[0187] The adaptation mapping parameter set is updated according to the correction data set, and the simulation input data set is regenerated.

[0188] In an embodiment of the present invention, consistency verification is performed on the adaptation mapping parameter set and the simulation input data set to ensure the accuracy and rationality of the simulation software model input. In the consistency verification process, each parameter in the simulation input data packet is first checked to see if it meets the input requirements of the simulation software model. For example, for parameters that exceed the input range, their normalized values ​​can be adjusted to meet the model requirements again. This operation can significantly reduce the impact of the input data on the simulation software model.

[0189] By comparing the key parameters in the adaptation mapping parameter set with the constraints of the simulation software model, it is possible to further determine whether the parameters are consistent. In this process, if a parameter conflict is detected, such as a parameter duplication, missing, or out of range, a correction data set can be generated based on the specific type of conflict. The generation of the correction data set can ensure the integrity and validity of all input parameters.

[0190] For example, in high-precision industrial simulation, different models may have extremely high requirements for the integrity of input parameters, and any inconsistency in parameters may lead to invalid simulation results. Through this verification process, problems with input data can be discovered and corrected in a timely manner, thereby improving the model's computational efficiency and the reliability of output results. Finally, by regenerating the simulation input data set through the updated adaptation mapping parameter set, the final consistency of the simulation software model input can be ensured, providing reliable protection for subsequent simulation calculations.

[0191] More specifically, the verification of whether each parameter in the simulation input data packet meets the input requirements of the simulation software model includes:

[0192] Background and significance of parameter verification

[0193] The simulation input data packet usually consists of multiple parameters, including physical characteristics (such as temperature, pressure, speed, etc.), environmental variables (such as humidity, light intensity, etc.), and operating status data (such as equipment speed, power output, etc.). The simulation software model may have specific input requirements for these parameters, such as data format, value range, or data integrity. If the input data does not meet these requirements, it may cause simulation failure or distorted results.

[0194] Steps for parameter validation

[0195] Data format verification: Check whether each parameter conforms to the input format of the simulation software model. For example, some parameters may need to be entered in matrix form, while others may need to be entered in time series form. If the format is found to be inconsistent, it can be corrected through the format conversion tool.

[0196] Value range validation: Check the value of each parameter to ensure that it falls within the valid range required by the model. For example, a physical property may be required to be between 0 and 100, but the input value is negative, so it needs to be corrected.

[0197] Data integrity verification: Check whether there are missing or redundant parameters in the input data packet. For example, the simulation software model requires 10 input parameters, but only 8 parameters are provided in the data packet. In this case, the missing parameters need to be supplemented according to the actual situation.

[0198] Verification Method

[0199] In actual operation, you can use automated verification tools to check parameters one by one. For example, write a verification script to compare each parameter in the data package with the requirements of the simulation software model one by one, and output the verification results. If an abnormality is found, the error will be recorded and correction suggestions will be prompted.

[0200] More specifically, comparing the key parameters in the adaptation mapping parameter set with the constraints of the simulation software model to determine their consistency includes:

[0201] Definition of key parameters and constraints

[0202] Key parameters: refers to the parameters that have a great impact on the results of the simulation software model. For example, in mechanical equipment simulation, they may include temperature, vibration frequency and power output.

[0203] Constraints: refers to the restrictions on the logical relationship or range of parameters imposed by the simulation software model. For example, a model may require that temperature and pressure satisfy certain physical laws, or require that the sum of multiple input parameters equal a constant.

[0204] Specific steps for consistency verification

[0205] Parameter range constraints: Check whether the values ​​of key parameters are within the specified range of the simulation software model. For example, check whether the temperature parameter meets the specified upper and lower limits, or whether the frequency parameter is within the valid frequency band of the model.

[0206] Verification of logical relationships between parameters: Check whether multiple key parameters meet the logical constraints of the simulation software model. For example, in wind power generation simulation, there may be a certain logical relationship between power generation and wind speed and blade angle. If the wind speed is low but the power output is high, it means that the data may be abnormal.

[0207] Dynamic constraint verification: Verify whether the parameters generated in real time during operation meet the dynamic constraints of the model. For example, in vehicle simulation, whether the changes between speed and acceleration conform to the actual physical laws.

[0208] How to implement verification

[0209] Consistency verification usually needs to be combined with the constraints of the simulation software model and implemented through a rule engine or logic checking tool. For example, a set of parameters can be automatically verified through a pre-defined rule library. If inconsistencies are found, the system will prompt and mark the abnormal parameters.

[0210] More specifically, updating the adaptation mapping parameter set according to the modified data set and regenerating the simulation input data set includes:

[0211] The correction data set is a set of data that supplements or replaces the problematic parameters, and is mainly used to fix the anomalies found during the verification process. For example:

[0212] Supplementation of missing parameters: Generate missing parameters based on historical data or model default values. For example, if a certain operating status parameter is found to be missing, historical values ​​under similar scenarios can be extracted from the database as a supplement.

[0213] Correction of incorrect parameters: Correct out-of-range parameters. For example, if the value of an input parameter is below the lower limit, it can be adjusted to the lower limit value, or dynamically adjusted based on the relationship with other parameters.

[0214] Redundant parameter cleaning: Remove redundant parameters that are not required by the simulation software model to reduce the computational burden.

[0215] The new parameters or corrected values ​​in the correction data set are added to the adaptation mapping parameter set to replace the original erroneous values. During the update process, it is necessary to ensure that the corrected parameter set still meets the constraints of the simulation software model. For example, the updated parameter set needs to be verified for consistency again to ensure its logical integrity.

[0216] According to the updated adaptation mapping parameter set, the comprehensive feature data set is decomposed and formatted to generate a new simulation input data set. The following factors need to be considered in this process:

[0217] Format requirements: Make sure that the regenerated data set complies with the input format of the simulation software.

[0218] Dynamic adjustment: Dynamically optimize input data based on real-time operating status, such as enhancing the impact of certain key parameters through weighted methods.

[0219] Efficient generation: New data sets can be quickly generated through automated tools to avoid time delays caused by manual operations.

[0220] The regenerated simulation input data set needs to be verified and checked for consistency again to ensure that the corrected data can be correctly recognized and used by the simulation software model. Finally, the verified data set is input into the simulation software model to complete an iterative optimization.

[0221] In a preferred embodiment of the present invention, the comparison of key indicator differences between the simulation result data and the target device operation data to generate a difference factor set includes:

[0222] Extracting key indicator values ​​of target device operation data, wherein the key indicators include fluctuation range, statistical characteristics and frequency characteristics of time series parameters;

[0223] Extracting key indicator values ​​of the simulation result data, wherein the key indicators correspond one-to-one with the key indicators in the target device operation data;

[0224] Compare the differences between the simulation result data and each key indicator in the target equipment operation data, including calculating the mean deviation, extreme value deviation and deviation degree of the change trend of the corresponding indicator;

[0225] Based on the differences in key indicators, a set of difference factors is generated according to preset weight rules, and the preset weight rules are set according to the degree of influence of the key indicators on the simulation results, wherein the degree of influence of the key indicators is determined by sensitivity analysis in the simulation software model.

[0226] In an embodiment of the present invention, by comparing the key indicator differences between the simulation result data and the target device operation data, a set of difference factors is generated. This method can quantify the deviation between the simulation results and the actual operating status, and provide data support for subsequent feedback adjustment and simulation model optimization.

[0227] First, by extracting the key indicator values ​​of the target equipment operation data and the key indicator values ​​of the simulation result data, this method can make a detailed comparison of the most core parameters in the equipment operation process. These key indicators may include the fluctuation range of time series data, statistical characteristics (such as mean, variance, extreme value) and frequency characteristics (such as main frequency, harmonic amplitude, etc.). Through one-to-one comparison, the difference between the simulation results and the actual operation data can be comprehensively analyzed. For example, in the simulation of wind power generation equipment, key indicators such as blade angle, wind speed and power generation can be extracted to accurately analyze the degree of deviation of the simulation model in these parameters.

[0228] Secondly, through multi-dimensional calculation of key indicator differences, this method can comprehensively quantify the degree of match between the simulation results and the operating status of the target equipment. For example, through mean deviation calculation, it can be reflected whether the simulation results are consistent with the actual operation in terms of overall trend; through extreme value deviation analysis, it can be revealed whether the simulation model accurately captures the extreme state of the operating data; through trend deviation analysis, it can be determined whether there is a lag or prediction error in the dynamic change of the simulation results. This multi-dimensional deviation calculation method can cover the simulation errors that may exist in different scenarios, laying a solid foundation for the generation of difference factors.

[0229] In addition, this method also weights the differences in key indicators through preset weight rules to generate a set of difference factors. The setting of weight rules is based on the sensitivity analysis of key indicators to simulation results. For example, some indicators (such as power output) may have a much greater impact on simulation results than other indicators (such as ambient temperature), so they will be given a higher weight when calculating the difference factor. Through this weighted processing, this method can highlight the difference impact of key indicators and ensure that the generated set of difference factors can truly reflect the main optimization direction of the simulation model.

[0230] The generated difference factor set has important technical effects: on the one hand, it provides accurate input for subsequent feedback adjustments, can guide the optimization of simulation model parameters, and gradually reduce the difference between simulation results and actual operation data; on the other hand, the generation process of the difference factor set is traceable, which can help analyze the source of simulation errors and provide a basis for further model improvement. For example, in wind farm simulation optimization, if the difference factor set shows that the deviation of wind speed input has a greater impact on the simulation results, the mapping parameters related to wind speed can be adjusted first, thereby quickly improving the accuracy of the simulation model.

[0231] In general, this method builds a closed-loop optimization system from simulation results to actual operating status through a detailed analysis of key indicator differences and the quantitative generation of difference factors. It not only significantly improves the adaptability of simulation input parameters, but also enhances the dynamic adjustment capability of the simulation model, providing reliable technical support for high-precision simulation of complex systems.

[0232] More specifically, the preset weight rule is set according to the influence degree of the key indicator on the simulation result, wherein the influence degree of the key indicator is determined by its sensitivity analysis in the simulation software model, including:

[0233] In the simulation process of complex systems, the degree of influence of different key indicators on the simulation results may vary significantly. For example, in the simulation of wind power generation equipment, wind speed may have a greater impact on the prediction accuracy of power generation, while the impact of ambient temperature is smaller. Therefore, it is necessary to conduct a sensitivity analysis on the degree of influence of key indicators and set weight rules based on the analysis results to ensure that the importance of key indicators can be accurately reflected when calculating the difference factor.

[0234] The weight rule assigns different weights to the differences of key indicators, so that the difference factors can highlight the key points, thereby guiding the direction of simulation model optimization. For example, for some key indicators that have a greater impact on the simulation results, such as wind speed or vibration amplitude, the weight will be higher; while for indicators with less impact, such as ambient temperature and humidity, the weight will be lower.

[0235] Concepts and methods of sensitivity analysis

[0236] Sensitivity analysis is an analytical method to evaluate the impact of input parameters on simulation results. By changing the value of the input parameters and observing the degree of change in the simulation results, the sensitivity of each key indicator can be determined.

[0237] Sensitivity refers to the degree of influence of a key indicator on the simulation results. For example, when a small change in a key indicator causes a large change in the simulation results, the sensitivity of the indicator is high; otherwise, the sensitivity is low.

[0238] The goal of sensitivity analysis is to quantify the contribution of each key indicator to the simulation results, thereby providing a basis for subsequent weight setting.

[0239] Common methods for sensitivity analysis:

[0240] Local sensitivity analysis: By making a small change to a single indicator, such as increasing or decreasing a certain proportion, the change in the simulation results is observed. This method is suitable for sensitivity assessment of linear or quasi-linear models.

[0241] Global sensitivity analysis: By changing the values ​​of multiple key indicators at the same time, observe the overall trend of simulation results. This method is suitable for evaluating nonlinear, multi-dimensional complex models.

[0242] Sensitivity analysis based on historical data: In the past operation or simulation historical data, analyze the actual impact of changes in each key indicator on the results. This method can directly obtain sensitivity information from actual data.

[0243] The process of setting weight rules

[0244] Determine the impact of key indicators:

[0245] Through sensitivity analysis, we can obtain the contribution value of each key indicator to the simulation results. For example, in wind power generation simulation, we can observe the change trend of power generation by adjusting wind speed, blade angle and ambient temperature. If the change of wind speed causes a large change in power generation, while the ambient temperature only causes a small fluctuation, it can be judged that the wind speed has a greater impact on the simulation results.

[0246] Importance of key indicators for classification:

[0247] Based on the results of sensitivity analysis, key indicators are divided into three categories: high sensitivity, medium sensitivity and low sensitivity. Indicators in each category can be assigned similar weight values. For example:

[0248] High sensitivity: The weight is relatively high, for example, 50% to 60%.

[0249] Medium sensitivity: The weight is moderate, for example, 20% to 30%.

[0250] Low sensitivity: The weight is low, for example, less than 10%.

[0251] During the simulation process, the weights are adjusted dynamically according to the real-time operating status. For example, when the equipment is in a specific operating stage, such as when the wind speed fluctuates violently, the weight of wind speed-related indicators can be temporarily increased, while in the stable operating stage, the weight can be reduced. This dynamic adjustment mechanism can be achieved through the real-time results of sensitivity analysis.

[0252] In the calculation process of the difference factor, according to the classification results of the key indicators, the indicators with high sensitivity are given higher weights. For example, when calculating the difference of a key indicator, the corresponding weight value can be directly referenced according to the predefined weight table.

[0253] In a preferred embodiment of the present invention, the calculation formula of the feedback adjustment weight is: ,in, is the adjusted feedback weight, expressed as The simulation result data parameter values, is the feedback weight before adjustment, expressed as The simulation result data parameter values, inherited from the adaptation mapping parameter set of the previous round, is the adjustment coefficient, For the The simulation result data and The actual operation data is in The key indicator difference of parameter values ​​is , For the The simulation result data parameter values, No. The actual operation data parameter values, For the The difference factor The weight coefficient of the parameter value, is the number of difference factors involved in the adjustment calculation, For the The simulation result data and The actual operation data is in The key indicator difference of parameter values ​​is is the total number of difference factors.

[0254] In the embodiment of the present invention, the matching degree between the simulation result and the actual operation data can be dynamically optimized by calculating the feedback adjustment weight. In this process, by comparing the key indicator differences between the simulation result data and the actual operation data, a difference factor set can be generated. This set quantifies the shortcomings of the simulation results and provides a basis for subsequent adjustments.

[0255] By calculating the feedback adjustment weights based on the difference factor set, the mapping relationship of the simulation software model can be optimized by adjusting the parameter weights. For example, in the parameter dimensions with large differences, increasing their weights can significantly improve the model's adaptability to these key parameters. Through this dynamic adjustment process, the simulation results can gradually approach the actual operating data, thereby improving the prediction accuracy of the simulation.

[0256] Finally, by inputting the updated adaptation mapping parameter set into the dynamic adjustment step, a closed-loop optimization process can be formed. This closed-loop optimization can continuously correct the parameters and inputs of the model in multiple simulation cycles, and ultimately achieve the goal of high accuracy and high reliability of the simulation results. This process is not only applicable to static simulation, but can also be widely used in real-time dynamic simulation and multi-device collaborative simulation scenarios, providing strong support for the operation optimization of complex systems.

[0257] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for managing the function mapping between a data acquisition system and simulation software, characterized in that: The method comprises: S100, collecting an original data set from a target device, wherein the original data set includes at least one data dimension; S200, performing noise filtering and outlier detection on the original data set to obtain a preprocessed data set; S300, extracting a plurality of feature data corresponding to the simulation software model according to the preprocessed data set, and generating a comprehensive feature data set, wherein the feature data includes independent data sets for different physical properties; S400, generating an initial mapping parameter set according to a mapping rule between feature data and input parameters of a simulation software model; S500, dynamically adjusting the initial mapping parameter set according to the real-time operating state of the target device, wherein the dynamic adjustment includes detecting a change in the operating state of the target device, selecting a corresponding preset adjustment strategy according to the change, and generating an adaptation mapping parameter set; S600, according to the adaptation mapping parameter set, converting the characteristic data into input format data required by the simulation software model, wherein the conversion includes format normalization processing for different types of simulation software models, and outputting a simulation input data set; S700: Perform consistency verification on the adaptation mapping parameter set and the simulation input data set, wherein: If the verification is passed, the adaptation mapping parameter set is stored as a mapping model configuration; if the verification is not passed, the adaptation mapping parameter set is adjusted according to a predefined correction rule and a simulation input data set is regenerated; S800, inputting the simulation input data set into the simulation software to obtain simulation result data; S900, verify the simulation result data. If the verification fails, generate feedback adjustment parameters according to the difference between the simulation result data and the characteristic data, where: Compare the key indicator differences between the simulation result data and the target equipment operation data to generate a set of difference factors; Calculate feedback adjustment weights according to the difference factor set, and update the adaptation mapping parameter set; The updated adaptation mapping parameter set is input into step S500 for dynamic adjustment; if the verification passes, the simulation result data is used as the output data of the target device operation evaluation.

2. A method for managing function mapping of a data acquisition system and simulation software according to claim 1, characterized in that: The step of extracting a plurality of feature data corresponding to the simulation software model according to the preprocessed data set includes: According to the preprocessed data set, the trend characteristics and period characteristics in the time series are extracted by dimension-by-dimension analysis to obtain the trend data set and period data set; Based on the trend data set, the segmented statistical method is used to generate a multi-interval key statistical data set; Perform spectrum analysis on the periodic data set, extract frequency feature data and classify them into frequency domain feature sets; Perform feature fusion on trend data, statistical data and frequency feature data to generate a comprehensive feature data set.

3. A method for managing function mapping of a data acquisition system and simulation software according to claim 2, characterized in that: The method of generating a multi-interval key statistics data set based on the trend data set by using a segmented statistical method includes: The trend data set is divided into multiple time intervals according to the time axis, and the length of each time interval is dynamically set according to the operation cycle of the target device; Perform statistical analysis on trend data in each time interval and calculate the mean, median, variance and maximum value of the interval; According to the predefined key indicator screening rules, statistics with significant fluctuations or change trends are selected as key statistics; The key statistics in all time intervals are normalized to generate a multi-interval key statistics data set.

4. A method for managing function mapping of a data acquisition system and simulation software according to claim 3, characterized in that: The process of performing spectrum analysis on the periodic data set, extracting frequency feature data and classifying the data into a frequency domain feature set includes: Perform fast Fourier transform on the periodic data set to convert the time domain data into frequency domain data; Extract the main frequency components in the spectrum and calculate the corresponding amplitude, phase and power density; According to the amplitude of the frequency component, the frequency component exceeding the preset amplitude threshold is selected as the main frequency feature; The amplitude, phase, and power density of the main frequency components are classified and a frequency domain feature set is generated.

5. A method for managing function mapping of a data acquisition system and simulation software according to claim 4, characterized in that: The generating of the initial mapping parameter set according to the mapping rules between the characteristic data and the input parameters of the simulation software model comprises: Group the comprehensive feature data set and the simulation software model input parameter set into corresponding groups, and establish feature grouping mapping rules; According to the feature grouping mapping rule, the correlation of the feature data is weightedly calculated to generate an initial mapping parameter matrix; the generation formula of the initial mapping parameter matrix is: ,in, is the first Line The parameter value of the column, For the The characteristic data and The correlation coefficient between the input parameters, and is the adjustment coefficient, The feature data set eigenvalues, Input parameter set for simulation software model The nominal value of the parameter, is the total number of features in the feature dataset, is the base of natural logarithms; , For the The characteristic data is in The values ​​in the dimensions, For the The input parameters are The values ​​in the dimensions, is the mean of the feature data, is the mean of the input parameters, For the The weight coefficient of the dimension, is the total number of data dimensions; According to the initial mapping parameter matrix, each parameter value is extracted, and range normalization and structure processing are performed on it to generate an initial mapping parameter set.

6. A method for managing function mapping of a data acquisition system and simulation software according to claim 5, characterized in that: The method of dynamically adjusting the initial mapping parameter set according to the real-time operating state of the target device includes detecting the change in the operating state of the target device, selecting a corresponding preset adjustment strategy according to the change, and generating an adaptation mapping parameter set, including: According to the real-time operating status of the target device, the operating status change is extracted to form a state change indicator data set; According to the state change indicator data set, the weight factors in the initial mapping parameter matrix are recalculated to generate an adjustment mapping parameter matrix; the generation formula of the adjustment mapping parameter matrix is: ,in, is the first in the adjusted mapping parameter matrix Line The parameter value of the column, is the first mapping parameter matrix before adjustment Line The parameter value of the column, is the adjustment coefficient, For the The real-time running status change of feature data, , For the The actual operating status of the characteristic data, For the The expected operating state of the characteristic data, is the total number of state changes, For the The real-time running status change of feature data, is the adjustment coefficient; The initial mapping parameter set is adjusted according to the adjustment mapping parameter matrix to generate an adapted mapping parameter set.

7. A method for managing function mapping of a data acquisition system and simulation software according to claim 6, characterized in that: The method converts the characteristic data into input format data required by the simulation software model according to the adaptation mapping parameter set, wherein the conversion includes format normalization processing for different types of simulation software models, and outputs a simulation input data set, including: According to the adaptation mapping parameter set, the comprehensive feature data set is grouped and decomposed to form a formatted feature data set; For each set of data in the formatted feature data set, unit normalization is performed to generate a normalized feature data set; According to the input requirements of different simulation software models, the arrangement order in the normalized feature data set is adjusted and encapsulated as a simulation input data packet; Output the simulation input data packet as the simulation input data set.

8. A method for managing function mapping of a data acquisition system and simulation software according to claim 7, characterized in that: The consistency verification of the adaptation mapping parameter set and the simulation input data set includes: Verify whether each parameter in the simulation input data package meets the input requirements of the simulation software model; Compare the key parameters in the adaptation mapping parameter set with the constraints of the simulation software model to determine their consistency; If a parameter conflict is detected, a correction data set is generated based on the type of conflicting parameters, where: For parameters that exceed the input range of the simulation software model, adjust their normalized values ​​to the input range of the simulation software model; For missing parameters, find the closest alternative value from the adaptation mapping parameter set; For repeated or redundant parameters, delete conflicting items and maintain the uniqueness of key parameters; The adaptation mapping parameter set is updated according to the correction data set, and the simulation input data set is regenerated.

9. A method for managing function mapping of a data acquisition system and simulation software according to claim 8, characterized in that: The comparison of the key indicator differences between the simulation result data and the target device operation data generates a set of difference factors, including: Extracting key indicator values ​​of target device operation data, wherein the key indicators include fluctuation range, statistical characteristics and frequency characteristics of time series parameters; Extracting key indicator values ​​of the simulation result data, wherein the key indicators correspond one-to-one with the key indicators in the target device operation data; Compare the differences between the simulation result data and each key indicator in the target equipment operation data, including calculating the mean deviation, extreme value deviation and deviation degree of the change trend of the corresponding indicator; Based on the differences in key indicators, a set of difference factors is generated according to preset weight rules, and the preset weight rules are set according to the degree of influence of the key indicators on the simulation results, wherein the degree of influence of the key indicators is determined by sensitivity analysis in the simulation software model.

10. A method for managing function mapping of a data acquisition system and simulation software according to claim 9, characterized in that: The calculation formula of the feedback adjustment weight is: ,in, is the adjusted feedback weight, expressed as The simulation result data parameter values, is the feedback weight before adjustment, expressed as The simulation result data parameter values, inherited from the adaptation mapping parameter set of the previous round, is the adjustment coefficient, For the The simulation result data and The actual operation data is in The key indicator difference of the parameter value is , For the The simulation result data parameter values, For the The actual operation data parameter values, For the The difference factor The weight coefficient of the parameter value, is the number of difference factors involved in the adjustment calculation, For the The simulation result data and The actual operation data is in The key indicator difference of the parameter value is is the total number of difference factors.

Images