Method and system for automatically adjusting gas flow of gas generator

Abstract

The invention provides an automatic adjusting method and system for the gas flow of a gas generator, and relates to the technical field of self-adaptive adjusting.The method comprises the steps that historical data and real-time data are collected, and the historical data are integrated into a training set; establishing a control model, wherein the control model comprises a BI-LSTM sub-model; the training set is adopted to train the BI-LSTM sub-model, and a trained BI-LSTM sub-model is obtained; the target gas flow and the current pressure intensity of the gas generator are input into the trained BI-LSTM sub-model, the target valve opening degree is obtained, and the current valve opening degree is adjusted to the target valve opening degree, the BI-LSTM sub-model is trained through historical data, influences of various factors are considered in the training process, and the control precision of the valve is improved.

Description

Technical Field

[0001] The present application relates to the technical field of adaptive regulation, and in particular to a method and system for automatically regulating the gas flow of a gas generator. Background Art

[0002] In industrial production, energy conversion and many scientific research fields, gas generators are key equipment. The stability and efficiency of their performance are directly related to the operating effect and cost-effectiveness of the entire system. Accurate control of gas flow is one of the core elements for efficient and safe operation of gas generators. Traditional gas flow control methods mostly rely on empirical formulas, PID (proportional-integral-differential) controllers or simple open-loop control systems. These control methods are often difficult to achieve ideal control effects when faced with complex and changeable working conditions.

[0003] Traditional control methods are usually based on fixed mathematical models or empirical parameters, but the actual operating conditions of the gas generator are affected by many factors, such as changes in the gas generator pressure, valve aging, etc. These factors will lead to deviations between the model parameters and the actual conditions, and the changes in gas flow are often time-varying and nonlinear. Traditional linear control strategies are difficult to effectively cope with this complex change pattern, which seriously affects the control accuracy of the valve. Summary of the invention

[0004] In order to improve the control accuracy of the valve, the present application provides a method and system for automatically adjusting the gas flow of a gas generator.

[0005] In the first aspect, the present application provides a method for automatically adjusting the gas flow of a gas generator, which adopts the following technical solution: A method for automatically adjusting the gas flow of a gas generator comprises the following steps: Data collection: including the first collection and the second collection; First collection: collect historical gas flow, historical pressure data of gas generators and historical valve opening, and integrate the historical gas flow, historical pressure data of gas generators and historical valve opening into a training set; Second collection: collecting target gas flow and current pressure data of the gas generator; First modeling: establishing a control model, wherein the control model includes a BI-LSTM sub-model; Model training: Use the training set to train the BI-LSTM sub-model to obtain the trained BI-LSTM sub-model; First prediction: input the target gas flow rate and the current pressure of the gas generator into the trained BI-LSTM sub-model to obtain the target valve opening; Adjustment: Adjust the current valve opening to the target valve opening.

[0006] By adopting the above technical solution, the present application collects historical gas flow, historical pressure data of gas generators and historical valve opening, providing a rich data set for the model training step. These data cover the performance of gas generators under different working conditions, which helps the control model learn the complex relationship between gas flow, pressure and valve opening. The control model of the present application includes a BI-LSTM sub-model, which can capture long-term dependencies in time series data, while considering past and future information, and is suitable for predicting problems with time series characteristics such as gas flow. The present application also uses a training set to train the BI-LSTM sub-model so that it can learn the mapping relationship between gas flow, pressure and valve opening. Through training, the BI-LSTM sub-model can more accurately predict the target valve opening under a given target gas flow and current pressure, can adapt to different working conditions and gas generator characteristics, and has a strong generalization ability. By combining data-driven and BI-LSTM models, the present application can achieve precise control of gas flow and improve the working efficiency and stability of the gas generator.

[0007] Optionally, the control model further includes a BP neural network sub-model, and in the model training step, the following steps are also included: The third collection: collect the weight coefficients of the BI-LSTM sub-model during each training process, recorded as the first data; Fourth collection: collecting controller parameters corresponding to the historical gas flow rate during each training process, and recording them as second data; First training: using the first data and the second data to train the BP neural network sub-model to obtain a trained BP neural network sub-model; Fifth collection: collect the weight coefficients of the trained BI-LSTM sub-model, recorded as the third data; Second prediction: input the third data into the trained BP neural network sub-model to obtain predicted controller parameters; Parameter update: Update the current controller parameters to the predicted controller parameters.

[0008] By adopting the above technical solution, the BP (back propagation) neural network is good at processing complex nonlinear mapping relationships. Introducing it into the control model can complement the time series data processed by the BI-LSTM sub-model, further improving the prediction accuracy and generalization ability of the control model. This application collects the weight coefficients (first data) and corresponding controller parameters (second data) during the training process of the BI-LSTM sub-model, and provides a wealth of training samples for the BP neural network sub-model. These training samples not only include the learning process of the BI-LSTM sub-model, but also directly relate to the controller parameters. This application uses the first data and the second data to train the BP neural network sub-model so that it can predict the controller parameters under the given BI-LSTM sub-model weight coefficients. By collecting the weight coefficients (third data) of the trained BI-LSTM sub-model and inputting them into the trained BP neural network sub-model, the predicted controller parameters are obtained. This step realizes the direct mapping from the BI-LSTM sub-model to the controller parameters, improving the accuracy and efficiency of the prediction.

[0009] Optionally, after executing the step of updating the parameters and before executing the step of first prediction, the method further includes: Sixth acquisition: obtaining the negative adjustment amount of the gas generator under each second data, recorded as fourth data; obtaining the negative adjustment amount of the gas generator under the predicted controller parameters, recorded as fifth data; Sorting: sorting the fourth data in ascending order to obtain a fourth data sequence; Calculate the distance: calculate the distance between the fifth data and the first fourth data in the fourth data sequence, recorded as the first distance; calculate the distance between the fifth data and the second fourth data in the fourth data sequence, recorded as the second distance; calculate the distance between the fifth data and the third fourth data in the fourth data sequence, recorded as the third distance; Obtaining the minimum value: recording the minimum value among the first distance, the second distance and the third distance as the sixth data; Distance judgment: judging whether the sixth data is greater than a preset distance threshold, if so, executing the step of adding data; if not, executing the step of first prediction; Add data: Add the predicted controller parameters to the parameter set consisting of the second data and perform the steps of the first prediction.

[0010] By adopting the above technical solution, by obtaining the negative adjustment (fourth data) of the gas generator under each historical controller parameter (second data) and the negative adjustment (fifth data) under the predicted controller parameter, a practical basis is provided for evaluating the rationality of the predicted parameters. The present application sorts the fourth data, obtains the fourth data sequence, and calculates the distance between the fifth data and the first three fourth data in the fourth data sequence, which can intuitively evaluate the closeness between the predicted parameters and the historical optimal parameters. The present application selects the value with the smallest distance (sixth data) as the evaluation standard. When the sixth data is greater than the preset distance, it indicates that the distance between the fifth data and the fourth data is relatively far, that is, the current controller parameters are different from the historical controller parameter distribution, and there may be a new working condition or the gas generator is abnormal, which requires further processing and analysis. The present application sets a preset distance threshold to judge the sixth data and determines whether to add the predicted controller parameters to the parameter set, that is, only when the predicted controller parameters are good enough (that is, close enough to the historical optimal parameters) will they be adopted, reducing the situation of performance degradation due to poor parameters.

[0011] Optionally, after executing the step of distance determination and before executing the step of adding data, the method further includes: Pressure judgment: judge whether the current pressure of the gas generator meets the expectation. If so, execute the step of adding data; if not, execute the step of early warning; Early warning: Send out an alarm signal.

[0012] By adopting the above technical solution, when the controller parameters do not conform to the historical controller parameter distribution, it is determined whether the gas generator is abnormal (whether the gas generator fails) by verifying whether the current pressure of the gas generator meets expectations. If an abnormality occurs, an early warning is issued. Otherwise, it indicates that the current controller parameters are due to new operating conditions, and the first prediction step is executed.

[0013] Optionally, after executing the step of data collection and before executing the step of first modeling, the method further includes: Data processing: including calculation of correlation, correlation judgment, retention and deletion; Calculate correlation: Calculate the correlation between historical gas flow and historical valve opening; Degree of association judgment: judging whether the degree of association is greater than zero, if so, executing the retaining step; if not, executing the deleting step; Retention: retain the historical gas flow corresponding to the current correlation, the historical pressure data of the gas generator corresponding to the historical gas flow, and the historical valve opening, and use the retained historical gas flow, the historical pressure data of the gas generator corresponding to the historical gas flow, and the historical valve opening as a new training set; Deletion: Delete the historical gas flow corresponding to the current correlation, the historical pressure data of the gas generator corresponding to the historical gas flow, and the historical valve opening.

[0014] By adopting the above technical solution, in the process of adjusting the valve opening so that the current gas flow reaches the target gas flow, the phenomenon of negative adjustment will occur. This application can quantify the degree of correlation between the historical gas flow and the historical valve opening by calculating the correlation between the historical gas flow and the historical valve opening. When the valve is adjusted, the gas generator is in the stage of increasing negative adjustment, and the historical gas flow and the historical valve opening are negatively correlated (that is, the gas flow decreases when the valve opening increases, or the gas flow increases when the valve opening decreases). After the stage of increasing negative adjustment, the two are positively correlated. This application deletes the historical gas flow corresponding to the stage of increasing negative adjustment, the historical pressure data of the gas generator corresponding to the historical gas flow, and the historical valve opening, that is, the data that is confusing to the control model is deleted, the training set is optimized, and the risk of the model learning the data characteristics of the negative correlation stage during the training process is reduced.

[0015] Optionally, the control model further includes a Bayesian network sub-model, and after executing the step of data processing and before executing the step of first modeling, further includes: Determine nodes: the deleted historical gas flow, the historical pressure data of the gas generator corresponding to the historical gas flow, and the historical valve opening are used as nodes of the Bayesian network sub-model, and the directed edges of the Bayesian network sub-model are the dependency relationships between the nodes; Reasoning: Input the target gas flow rate and the current pressure of the gas generator into the Bayesian network sub-model, and output the inference value of the valve opening, which is recorded as the seventh data; Calculate the mean: calculate the average value of the seventh data and the target valve opening, and use the average value as the new target valve opening.

[0016] By adopting the above technical solution, the deleted historical data (including historical gas flow, historical gas generator pressure data corresponding to the historical gas flow, and historical valve opening) are used as nodes of the Bayesian network sub-model, thereby realizing the reuse of these deleted data. These deleted data correspond to the stage of increasing negative regulation of the gas generator. Through the reasoning mechanism of the Bayesian network, the data characteristics of the stage of increasing negative regulation are specifically learned. These data not only provide additional information for the control model, but also help the control model to more comprehensively understand the behavior patterns of the gas generator in different operating stages. By learning the data characteristics of the stage of increasing negative regulation, the Bayesian network sub-model can more accurately predict the gas flow and valve opening requirements under similar conditions.

[0017] Optionally, after executing the step of calculating the degree of association and before executing the step of determining the degree of association, the method further includes: Second modeling: obtaining valve degradation data, and establishing a degradation model based on the degradation data. The calculation model of the degradation model is as follows: ; in, is the actual measured gas flow; is the theoretical maximum gas flow rate; is the degradation coefficient; t is the service time of the valve; Updating the correlation degree: updating the correlation degree based on the degradation coefficient, and using the updated correlation degree as a new correlation degree.

[0018] By adopting the above technical solution, the performance of the valve as a key component in the gas generator will gradually degrade over time, and this degradation will directly affect the relationship between the valve opening and the gas flow. By introducing the degradation model, the performance changes of the valve in actual use can be more accurately reflected, thereby improving the accuracy of the correlation. Traditional correlation calculations are often based on static historical data, while ignoring the dynamic factor of valve degradation. Updating the correlation by the degradation coefficient calculated by the degradation model can make the correlation closer to the current actual situation and improve the timeliness of the control model. When establishing a gas flow prediction model, incorporating the degradation information of the valve can enable the control model to more accurately predict the future trend of gas flow. Based on the updated correlation, the control parameters (such as valve opening) can be adjusted more intelligently to adapt to the performance changes caused by valve degradation, which helps to reduce control errors and improve the stability and accuracy of gas flow.

[0019] Optionally, after executing the step of data collection and before executing the step of first modeling, the method further includes: Quantity judgment: judge whether the number of training samples in the training set is greater than a preset threshold. If so, execute the first modeling step; if not, execute the step of expanding the training set; Expand the training set: Based on the training set, use the generative adversarial network to generate new training samples, and add the new training samples to the training set.

[0020] By adopting the above technical solution, by judging whether the number of training samples in the training set is greater than the preset threshold, there is sufficient data support before training the model. When the number of training samples is insufficient, a generative adversarial network (GAN) is used to generate new training samples, thereby increasing the diversity and richness of the training set. A diverse training set can help the control model better learn the essential characteristics of the data, rather than just remembering specific samples in the training set. By expanding the training set, the model can learn more data features, thereby improving the prediction accuracy of gas flow.

[0021] Optionally, the step of expanding the training set further includes: Calculate similarity: Calculate the similarity between the new training samples and the training samples in the original sample set; Similarity judgment: judge whether the similarity is greater than a preset threshold, if so, do not retain the new training sample; if not, retain the new training sample.

[0022] By adopting the above technical solution, the difference between the new sample and the existing sample can be quantified by calculating the similarity between the new training sample and the training sample in the original sample set. If the new sample is too similar to a sample in the original sample set, it means that the information they provide may be repeated. At this time, the new training sample is no longer retained. Otherwise, the new training sample is retained. This step can improve the diversity and information richness of the training set.

[0023] In the second aspect, the present application provides a gas generator gas flow automatic regulation system, which adopts the following technical solution: A gas generator gas flow automatic regulation system, comprising: The data acquisition module includes a first acquisition unit and a second acquisition unit; The first collection unit is used to collect historical gas flow, historical pressure data of the gas generator and historical valve opening, and integrate the historical gas flow, historical pressure data of the gas generator and historical valve opening into a training set; The second collection unit is used to collect the target gas flow rate and the current pressure of the gas generator; A first modeling module, used to establish a control model, wherein the control model includes a BI-LSTM sub-model; A model training module is connected to the first acquisition unit and the first modeling module for training the BI-LSTM sub-model using the training set to obtain a trained BI-LSTM sub-model; The first prediction module is connected to the second acquisition unit and the model training module for inputting the target gas flow rate and the current pressure of the gas generator into the trained BI-LSTM sub-model to obtain the target valve opening; The regulating module is in communication with the first prediction module and is used for regulating the current valve opening to the target valve opening.

[0024] By adopting the above-mentioned technical scheme, the present application realizes comprehensive and targeted data collection by integrating the first acquisition unit and the second acquisition unit, constructs an advanced control model using the BI-LSTM sub-model, and realizes efficient and precise gas flow automatic control through steps such as model training, real-time prediction and precise adjustment. The system has a high degree of automation, high-precision control, strong adaptability and good scalability, which provides strong support for the stable operation and energy efficiency optimization of the gas generator.

[0025] In summary, the present application includes at least one of the following beneficial technical effects: 1. This application collects historical gas flow, historical pressure data of gas generators and historical valve openings, providing a rich data set for the model training step. These data cover the performance of gas generators under different working conditions, which helps the control model learn the complex relationship between gas flow, pressure and valve opening. The control model of this application includes a BI-LSTM sub-model, which can capture long-term dependencies in time series data, while considering past and future information, and is suitable for predicting problems with time series characteristics such as gas flow. This application also uses a training set to train the BI-LSTM sub-model so that it can learn the mapping relationship between gas flow, pressure and valve opening. Through training, the BI-LSTM sub-model can more accurately predict the target valve opening under a given target gas flow and current pressure, can adapt to different working conditions and gas generator characteristics, and has a strong generalization ability. By combining data-driven and BI-LSTM models, this application can achieve precise control of gas flow and improve the working efficiency and stability of the gas generator.

[0026] 2.BP (back propagation) neural network is good at processing complex nonlinear mapping relationships. Introducing it into the control model can complement the time series data processed by the BI-LSTM sub-model, further improving the prediction accuracy and generalization ability of the control model. This application collects the weight coefficients (first data) and corresponding controller parameters (second data) during the training process of the BI-LSTM sub-model, and provides a wealth of training samples for the BP neural network sub-model. These training samples not only include the learning process of the BI-LSTM sub-model, but also directly relate to the controller parameters. This application uses the first data and the second data to train the BP neural network sub-model so that it can predict the controller parameters under the given BI-LSTM sub-model weight coefficients. By collecting the weight coefficients (third data) of the trained BI-LSTM sub-model and inputting them into the trained BP neural network sub-model, the predicted controller parameters are obtained. This step realizes the direct mapping from the BI-LSTM sub-model to the controller parameters, improving the accuracy and efficiency of the prediction.

[0027] 3. By obtaining the negative adjustment amount (fourth data) of the gas generator under each historical controller parameter (second data) and the negative adjustment amount (fifth data) under the predicted controller parameter, a practical basis is provided for evaluating the rationality of the predicted parameters. The present application sorts the fourth data, obtains the fourth data sequence, and calculates the distance between the fifth data and the first three fourth data in the fourth data sequence, which can intuitively evaluate the closeness between the predicted parameters and the historical optimal parameters. The present application selects the value with the smallest distance (sixth data) as the evaluation standard. When the sixth data is greater than the preset distance, it indicates that the distance between the fifth data and the fourth data is relatively far, that is, the current controller parameters are different from the historical controller parameter distribution, and there may be a new working condition or the gas generator is abnormal, which requires further processing and analysis. The present application sets a preset distance threshold to judge the sixth data and determines whether to add the predicted controller parameters to the parameter set, that is, only when the predicted controller parameters are good enough (that is, close enough to the historical optimal parameters) will they be adopted, reducing the situation where performance degradation occurs due to poor parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 is a flow chart of Example 1 of the present application; Figure 2 This is a flow chart of the third acquisition from S31 to parameter update from S36 in Example 2 of the present application; Figure 3 This is a flow chart from S61 sixth acquisition to S68 adding data in Example 2 of the present application; Figure 4 This is a flow chart of data processing from S7 to mean value calculation in S83 in Example 3 of the present application. DETAILED DESCRIPTION

[0029] The following combination Figures 1 to 4 This application is described in further detail.

[0030] Embodiment 1: This embodiment discloses a method for automatically adjusting the gas flow rate of a gas generator, referring to Figure 1 The method includes: S1 data collection, S2 first modeling, S3 model training, S4 first prediction and S5 adjustment. First, historical data and real-time data are collected, then a control model is established, then the control model is trained using historical data, then the real-time data is input into the trained control model, and the predicted target valve opening is output, and then the current valve opening is adjusted according to the target valve opening. This embodiment includes the following steps: S1 data collection, including S11 first collection and S12 second collection.

[0031] S11 is the first collection, extracting the historical gas flow, the historical pressure data of the gas generator and the historical valve opening, and integrating the historical gas flow, the historical pressure data of the gas generator and the historical valve opening into a training set.

[0032] The historical gas flow, historical pressure data of the gas generator and historical valve opening are collected at the same time.

[0033] S12 is the second collection step, collecting target gas flow and current pressure data of the gas generator.

[0034] S2 first builds a control model, which includes a BI-LSTM sub-model. Through the BI-LSTM sub-model, the complex relationship between the gas flow, the pressure of the gas generator and the valve opening is learned, providing a basis for subsequent prediction and control.

[0035] S3 model training, using the training set collected in the first collection of S11 to train the BI-LSTM sub-model, to obtain the trained BI-LSTM sub-model.

[0036] In the process of training the BI-LSTM sub-model, the historical gas flow and historical pressure data of the gas generator in the training set are used as training data, and the historical valve opening is used as the true label of the training data.

[0037] In the first prediction of S4, the target gas flow rate and the current pressure of the gas generator collected in the second collection of S12 are input into the trained BI-LSTM sub-model to obtain the target valve opening.

[0038] S5 adjusts the current valve opening to the target valve opening.

[0039] This embodiment achieves efficient and accurate automated control of gas flow through the steps of data collection, first modeling, model training, first prediction and adjustment, thereby improving the operating efficiency and energy efficiency performance of the gas generator.

[0040] Example 2: Reference Figure 2 The difference between this embodiment and embodiment 1 is that the control model further includes a BP neural network sub-model, the BI-LSTM sub-model is communicatively connected with the BP neural network sub-model, and in the S3 model training, it also includes: S31 is the third collection. Each time the BI-LSTM sub-model is trained, its weight coefficient is recorded, and the weight coefficient is recorded as the first data. The first data reflects the degree of fit of the BI-LSTM sub-model to the data and the learned features.

[0041] S32 is the fourth collection, inputting the target gas flow and the current pressure of the gas generator into the BI-LSTM sub-model after each training, obtaining the target valve opening predicted by the BI-LSTM sub-model after each training, using a controller to control the valve to transition from the current opening to the target opening, obtaining the controller parameters in this process, and recording the controller parameters as the second data.

[0042] S33: first training, using the first data and the second data to train the BP neural network sub-model to obtain a trained BP neural network sub-model.

[0043] In the process of training the BP neural network sub-model, the first data is used as training data, and the second data is used as the true label of the first data.

[0044] S34 is the fifth collection, collecting the weight coefficients of the BI-LSTM sub-model trained in the S3 model training, and recording the weight coefficients as the third data.

[0045] S35 second prediction, inputting the third data into the trained BP neural network sub-model to obtain predicted controller parameters.

[0046] S36 parameter update, updating the current controller parameters to the controller parameters predicted in the second prediction of S35.

[0047] This embodiment achieves intelligent prediction and optimization of controller parameters by introducing a BP neural network sub-model to enhance the model training process, which not only improves the accuracy and stability of gas flow control, but also enhances the adaptability and robustness.

[0048] Reference Figure 3 In other embodiments, after executing S36 parameter update and before executing S4 first prediction, the method further includes: S61 is a sixth collection, in which the negative adjustment amount of the gas generator under each second data is obtained and recorded as the fourth data.

[0049] Then, the negative adjustment amount of the gas generator under the predicted controller parameters is obtained and recorded as the fifth data.

[0050] S62 sorting: sorting the fourth data in ascending order to form an ordered data sequence, which is recorded as a fourth data sequence.

[0051] S63 calculates the distance, calculates the distance between the fifth data and the fourth data ranked first in the fourth data sequence, recorded as the first distance; calculates the distance between the fifth data and the fourth data ranked second in the fourth data sequence, recorded as the second distance; calculates the distance between the fifth data and the fourth data ranked third in the fourth data sequence, recorded as the third distance.

[0052] For example, in the fourth data sequence, the first three fourth data are respectively: 3%, 5%, and 8%. The fifth data is 4%, and the distance between the fifth data and the first three fourth data is: First distance: |4% - 3%|=1%; Second distance: |4% - 5%|=1%; Third distance: |4% - 8%|=4%.

[0053] S64 obtains a minimum value by comparing the first distance, the second distance, and the third distance to obtain a minimum value among the three, and records the minimum value as sixth data.

[0054] Based on the first distance, the second distance, and the third distance calculated in S63 calculating the distance, the sixth data is 1%.

[0055] S65 distance judgment, judge whether the sixth data is greater than the preset distance threshold. If so, it means that the difference between the predicted controller parameters and the existing optimal parameters is large, which may correspond to different working conditions or there may be a fault in the gas generator. It is necessary to execute S66 pressure judgment for further analysis; if not, it means that the predicted controller parameters are close enough to the optimal parameters, and the parameters can be directly updated, and then the first prediction of S4 is executed.

[0056] Based on the comparison between the sixth data (1%) obtained in obtaining the minimum value in S64 and the preset distance threshold (eg, 0.5%), it is found that 1%>0.5%, and at this time, it is necessary to execute S66 pressure determination.

[0057] S66 pressure judgment, judge whether the current pressure of the gas generator meets expectations. If so, it means that the sixth data is greater than the preset distance threshold due to new working conditions, and then execute S68 to add data; if not, it means that it is caused by a gas generator failure, and it is necessary to execute S67 warning.

[0058] The current pressure of the gas generator meets the expected standard: the current pressure of the gas generator is within a safe range.

[0059] S67 early warning, issuing an alarm signal.

[0060] S68 adds data, adds the predicted controller parameters to the parameter set composed of the second data, and executes S4 the first prediction.

[0061] This embodiment can intelligently identify new operating conditions or fault conditions by comparing the distance between the negative adjustment under the predicted controller parameters and the optimal parameters, and combining pressure judgment, so as to decide whether to update the parameter set or issue an early warning, thereby effectively improving the accuracy and safety of valve control.

[0062] Example 3: Reference Figure 4 The difference between this embodiment and embodiment 1 is that the control model further includes a Bayesian network sub-model, and after executing S1 data collection and before executing S2 first modeling, it also includes: S7 data processing includes S71 calculating the correlation, S72 second modeling, S73 updating the correlation, S74 judging the correlation, S75 retaining and S76 deleting.

[0063] S71 calculates the correlation, and calculates the correlation between the historical gas flow and the historical valve opening. By calculating the correlation between the two through statistical methods (such as correlation coefficient, mutual information, etc.), the linear or nonlinear relationship strength between them can be understood.

[0064] For example, the correlation between the historical gas flow and the historical valve opening is calculated by the correlation coefficient. The historical data records involved in this step are shown in Table 1.

[0065] Table 1 Historical gas flow and historical valve opening data table The calculation model of the correlation coefficient is as follows: ; in, is the historical gas flow at the i-th time point; is the historical valve opening at the i-th time point; is the mean value of historical gas flow; is the average of historical valve openings.

[0066] After calculation, we can know the average value of historical gas flow , the average value of historical valve opening .

[0067] ; ; .

[0068] S72: second modeling, obtaining valve degradation data, and establishing a degradation model based on the degradation data. The calculation model of the degradation model is as follows: ; in, is the actual measured gas flow rate, in m³ / h; The theoretical maximum gas flow rate, in m³ / h; is the degradation coefficient; t is the service life of the valve, unit is h. In the calculation model of the degradation model, t is only used as a numerical value without using a unit.

[0069] The degradation model describes the relationship between valve performance and time, especially its impact on gas flow. The degradation coefficient in the degradation model is a key parameter, which reflects the degree of performance degradation of the valve due to wear, aging and other factors. The degradation coefficient can be calculated through the actual measured gas flow, the theoretical maximum gas flow and the valve usage time.

[0070] S73 updates the correlation degree, updates the correlation degree based on the degradation coefficient, and uses the updated correlation degree as a new correlation degree.

[0071] Updating the correlation degree based on the degradation coefficient may be based on the original correlation degree, adding the degradation coefficient (or degradation coefficient multiples of), or directly multiply the original correlation by .

[0072] S74 correlation judgment, judge whether the updated correlation described in S73 updating the correlation is greater than zero. If so, it means that there is a positive correlation between the gas flow and the valve opening. At this time, the data corresponding to the correlation is not the data of the stage of increasing negative regulation. Then execute S75 to retain; if not, it means that there is a negative correlation between the gas flow and the valve opening. At this time, the data corresponding to the correlation is the data of the stage of increasing negative regulation. These data are no longer representative and need to be deleted by executing S76.

[0073] S75 retains the historical gas flow corresponding to the current correlation degree, the historical pressure data of the gas generator corresponding to the historical gas flow, and the historical valve opening, and integrates the retained historical gas flow, the historical pressure data of the gas generator corresponding to the historical gas flow, and the historical valve opening into a new training set.

[0074] S76 deletion deletes the historical gas flow corresponding to the current correlation, the historical pressure data of the gas generator corresponding to the historical gas flow, and the historical valve opening, so as to reduce the negative impact of these data on model training, so that the control model can learn and predict based on high-quality data.

[0075] S81 determines the nodes, and uses the deleted historical gas flow, the historical pressure data of the gas generator corresponding to the historical gas flow, and the historical valve opening as nodes of the Bayesian network sub-model, wherein the directed edges of the Bayesian network sub-model are the dependencies between the nodes.

[0076] S82 reasoning uses the conditional probability table (CPT) in the Bayesian network and known evidence variables (such as the target gas flow rate and the current pressure of the gas generator) to calculate the posterior probability distribution of unknown variables (such as valve opening).

[0077] This step takes the target gas flow rate and the current pressure of the gas generator as input, performs reasoning through the Bayesian network sub-model, and outputs the inference value of the valve opening, which is recorded as the seventh data. This inference value is calculated based on the dependency relationship between the current input and the historical data, and it reflects the most likely value of the valve opening under given conditions.

[0078] S83 calculates the average value, calculates the average value of the seventh data and the target valve opening, and uses the average value as the new target valve opening.

[0079] This embodiment deletes the relevant data in the negative regulation increasing stage, and reuses the deleted data. The Bayesian network model is used to learn the data characteristics of the negative regulation increasing stage, and the Bayesian network is used to infer the data based on the negative regulation increasing stage to obtain the inferred value of the valve opening. Then, the target valve opening and the mean of the seventh data are solved to obtain the new target valve opening.

[0080] Embodiment 4: This embodiment differs from Embodiment 1 in that, after executing S1 data collection and before executing S2 first modeling, it further includes: S91 quantity judgment, determines whether the number of training samples in the training set is greater than the preset threshold. If so, it is considered that the data volume of the training set is sufficient, and S2 first modeling is executed; if not, it is considered that the data volume of the training set is insufficient, and it is necessary to execute S92 to expand the training set and increase the training data in the training set.

[0081] S92 expands the training set and generates new training samples based on the training set using a generative adversarial network.

[0082] In other embodiments, the S92 expanded training set further includes: S921 calculates similarity, using algorithms such as Euclidean distance and cosine similarity to calculate the similarity between the new training sample and the training samples in the original sample set.

[0083] S922: similarity determination, determining whether the similarity is greater than a preset threshold. If so, the new training sample is not retained; if not, the new training sample is retained and the retained training sample is added to the training set.

[0084] This embodiment enables the training set to meet the modeling requirements in terms of data volume and diversity, thereby improving the accuracy and generalization ability of the control model.

[0085] Embodiment 5: This embodiment discloses a gas generator gas flow automatic regulation system, the system comprising: The data acquisition module includes a first acquisition unit and a second acquisition unit.

[0086] The first acquisition unit is used to collect historical data, where the historical data includes historical gas flow, historical pressure data of the gas generator, and historical valve opening information.

[0087] Then the historical gas flow, historical pressure data of the gas generator and historical valve opening are integrated into the training set.

[0088] The second collection unit is used to collect the target gas flow rate and the current pressure of the gas generator.

[0089] The first modeling module is used to establish a control model, and the control model includes a BI-LSTM sub-model.

[0090] The model training module is connected to the first acquisition unit and the first modeling module for training the BI-LSTM sub-model using the training set to obtain the trained BI-LSTM sub-model. Through iterative learning, the BI-LSTM sub-model can accurately predict the relationship between gas flow, pressure and valve opening.

[0091] The first prediction module is communicatively connected with the second acquisition unit and the model training module, and is used to input the target gas flow rate and the current pressure of the gas generator into the trained BI-LSTM sub-model to obtain the target valve opening.

[0092] The regulating module is in communication with the first prediction module and is used for regulating the current valve opening to the target valve opening.

[0093] This embodiment realizes precise control of the gas generator valve opening through the collaborative work of multiple modules such as data acquisition, first modeling, model training, first prediction and adjustment. This control method based on the BI-LSTM sub-model can make full use of historical data and real-time data to improve the accurate control of the valve.

[0094] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for automatically adjusting the gas flow of a gas generator, characterized in that: include: Data collection: including the first collection and the second collection; First collection: collect historical gas flow, historical pressure data of gas generators and historical valve opening, and integrate the historical gas flow, historical pressure data of gas generators and historical valve opening into a training set; Second collection: collecting target gas flow and current pressure data of the gas generator; First modeling: establishing a control model, wherein the control model includes a BI-LSTM sub-model; Model training: Use the training set to train the BI-LSTM sub-model to obtain the trained BI-LSTM sub-model; First prediction: input the target gas flow rate and the current pressure of the gas generator into the trained BI-LSTM sub-model to obtain the target valve opening; Adjustment: Adjust the current valve opening to the target valve opening.

2. The method for automatically adjusting the gas flow of a gas generator according to claim 1, characterized in that: The control model also includes a BP neural network sub-model, and in the model training step, also includes: The third collection: collect the weight coefficients of the BI-LSTM sub-model during each training process, recorded as the first data; Fourth collection: collecting controller parameters corresponding to the historical gas flow rate during each training process, and recording them as second data; First training: using the first data and the second data to train the BP neural network sub-model to obtain a trained BP neural network sub-model; Fifth collection: collect the weight coefficients of the trained BI-LSTM sub-model, recorded as the third data; Second prediction: input the third data into the trained BP neural network sub-model to obtain predicted controller parameters; Parameter update: Update the current controller parameters to the predicted controller parameters.

3. The method for automatically adjusting the gas flow of a gas generator according to claim 2, characterized in that: After executing the step of updating the parameters and before executing the step of first prediction, the method further includes: Sixth acquisition: obtaining the negative adjustment amount of the gas generator under each second data, recorded as fourth data; obtaining the negative adjustment amount of the gas generator under the predicted controller parameters, recorded as fifth data; Sorting: sorting the fourth data in ascending order to obtain a fourth data sequence; Calculate the distance: calculate the distance between the fifth data and the first fourth data in the fourth data sequence, recorded as the first distance; calculate the distance between the fifth data and the second fourth data in the fourth data sequence, recorded as the second distance; calculate the distance between the fifth data and the third fourth data in the fourth data sequence, recorded as the third distance; Obtaining the minimum value: recording the minimum value among the first distance, the second distance and the third distance as the sixth data; Distance judgment: judging whether the sixth data is greater than a preset distance threshold, if so, executing the step of adding data; if not, executing the step of first prediction; Add data: Add the predicted controller parameters to the parameter set consisting of the second data and perform the steps of the first prediction.

4. The method for automatically adjusting the gas flow of a gas generator according to claim 3, characterized in that: After executing the step of distance determination and before executing the step of adding data, the method further includes: Pressure judgment: judge whether the current pressure of the gas generator meets the expectation. If so, execute the step of adding data; if not, execute the step of early warning; Early warning: Send out an alarm signal.

5. The method for automatically adjusting the gas flow of a gas generator according to any one of claims 1 to 4, characterized in that: After executing the step of data collection and before executing the step of first modeling, the method further includes: Data processing: including calculation of correlation, correlation judgment, retention and deletion; Calculate correlation: Calculate the correlation between historical gas flow and historical valve opening; Degree of association judgment: judging whether the degree of association is greater than zero, if so, executing the retaining step; if not, executing the deleting step; Retention: retain the historical gas flow corresponding to the current correlation, the historical pressure data of the gas generator corresponding to the historical gas flow, and the historical valve opening, and use the retained historical gas flow, the historical pressure data of the gas generator corresponding to the historical gas flow, and the historical valve opening as a new training set; Deletion: Delete the historical gas flow corresponding to the current correlation, the historical pressure data of the gas generator corresponding to the historical gas flow, and the historical valve opening.

6. The method for automatically adjusting the gas flow of a gas generator according to claim 5, characterized in that: The control model further includes a Bayesian network sub-model, and after executing the step of data processing and before executing the step of first modeling, further includes: Determine nodes: the deleted historical gas flow, the historical pressure data of the gas generator corresponding to the historical gas flow, and the historical valve opening are used as nodes of the Bayesian network sub-model, and the directed edges of the Bayesian network sub-model are the dependency relationships between the nodes; Reasoning: Input the target gas flow rate and the current pressure of the gas generator into the Bayesian network sub-model, and output the inference value of the valve opening, which is recorded as the seventh data; Calculate the mean: calculate the average value of the seventh data and the target valve opening, and use the average value as the new target valve opening.

7. The method for automatically adjusting the gas flow of a gas generator according to claim 6, characterized in that: After executing the step of calculating the degree of association and before executing the step of determining the degree of association, the method further includes: Second modeling: obtaining valve degradation data, and establishing a degradation model based on the degradation data. The calculation model of the degradation model is as follows: ； in, is the actual measured gas flow; is the theoretical maximum gas flow rate; is the degradation coefficient; t is the service time of the valve; Updating the correlation degree: updating the correlation degree based on the degradation coefficient, and using the updated correlation degree as a new correlation degree.

8. The method for automatically adjusting the gas flow of a gas generator according to any one of claims 1 to 4, characterized in that: After executing the step of data collection and before executing the step of first modeling, the method further includes: Quantity judgment: judge whether the number of training samples in the training set is greater than a preset threshold. If so, execute the first modeling step; if not, execute the step of expanding the training set; Expand the training set: Based on the training set, use the generative adversarial network to generate new training samples, and add the new training samples to the training set.

9. The method for automatically adjusting the gas flow of a gas generator according to claim 8, characterized in that: The step of expanding the training set also includes: Calculate similarity: Calculate the similarity between the new training samples and the training samples in the original sample set; Similarity judgment: judge whether the similarity is greater than a preset threshold, if so, do not retain the new training sample; if not, retain the new training sample.

10. A gas generator gas flow automatic regulation system, the system is used to execute the method according to any one of claims 1 to 9, characterized in that: include: The data acquisition module includes a first acquisition unit and a second acquisition unit; The first collection unit is used to collect historical gas flow, historical pressure data of the gas generator and historical valve opening, and integrate the historical gas flow, historical pressure data of the gas generator and historical valve opening into a training set; The second collection unit is used to collect the target gas flow rate and the current pressure of the gas generator; A first modeling module, used to establish a control model, wherein the control model includes a BI-LSTM sub-model; A model training module is connected to the first acquisition unit and the first modeling module for training the BI-LSTM sub-model using the training set to obtain a trained BI-LSTM sub-model; The first prediction module is connected to the second acquisition unit and the model training module for inputting the target gas flow rate and the current pressure of the gas generator into the trained BI-LSTM sub-model to obtain the target valve opening; The regulating module is in communication with the first prediction module and is used for regulating the current valve opening to the target valve opening.

Images