Surge data processing method, device and equipment and storage medium

Abstract

The application discloses a surge data processing method, device and equipment and a storage medium. The method comprises the following steps: obtaining a plurality of initial surge samples, and obtaining an initial power set based on each initial surge sample; comparing the initial power set corresponding to each initial surge sample set with a reference power to obtain a comparison result, and determining each initial surge sample based on the comparison result to obtain a target surge sample; obtaining a corrected surge sample set based on the target surge sample and a historical surge sample set; and a surge boundary model is self-corrected based on the corrected surge sample set to obtain a corrected surge boundary model. According to the technical scheme, different historical surge sample sets and self-learning strategies of the surge boundary model are adopted for different stages of the centrifugal compressor, and the self-learning efficiency of the historical surge sample set and the surge boundary model can be improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of compressors, and particularly relates to a surge data processing method and device, equipment and a storage medium. BACKGROUND

[0002] Surge is a kind of abnormal vibration of a turbocompressor such as a centrifugal compressor when the flow rate decreases to a certain extent. Surge can destroy the flow regularity of the medium in the compressor, produce mechanical noise, cause strong vibration of the compressor, and accelerate damage to the bearing and seal. Once the surge causes resonance of the system pipeline, the compressor and its foundation, it can also cause serious consequences. To prevent surge, the centrifugal compressor must be operated outside the surge area. Therefore, the centrifugal compressor generally provides a pressure-flow characteristic curve and a determined surge point and surge boundary. The system in which the centrifugal compressor is located usually adopts a minimum flow rate, flow rate-speed, or flow rate-pressure difference to prevent surge control. For a centrifugal compressor, the refrigerant flow rate is not measured, so the inlet guide vane opening-pressure ratio (pressure difference, temperature difference), speed + inlet guide vane opening-pressure ratio (pressure difference, temperature difference) and other methods are used for surge control.

[0003] However, the current surge control method has the following problems:

[0004] 1) The surge data test quantity is too large, which requires high experimental, equipment, time and labor costs, and may have a large human error.

[0005] 2) The initial surge control may fail due to the environment, resulting in frequent surge; to handle the surge failure and correct the surge boundary, a very high maintenance cost is required, and the user experience is affected. SUMMARY

[0006] The present application aims to at least solve one of the technical problems in the related art. To this end, one object of the present application is to provide a surge data processing method, device, equipment and storage medium.

[0007] To solve the above technical problems, the embodiments of the present application provide the following technical solutions:

[0008] A surge data processing method, comprising:

[0009] obtaining a plurality of initial surge samples, and obtaining an initial power set based on each initial surge sample;

[0010] The initial power set corresponding to each of the initial surge sample sets is compared with a reference power, comparison results are obtained, and a plurality of the initial surge samples are determined based on the comparison results, to obtain a target surge sample;

[0011] Based on the target surge sample and a historical surge sample set, a revised surge sample set is obtained;

[0012] The surge boundary model is self-corrected based on the revised surge sample set, to obtain a revised surge boundary model.

[0013] Optionally, the plurality of initial surge samples are obtained, and based on each of the initial surge samples, an initial power set is obtained, including:

[0014] A plurality of groups of detection data are obtained; wherein each group of the detection data includes a plurality of operating parameters;

[0015] The plurality of groups of detection data are processed based on a sliding window, and a dispersion coefficient of a signal corresponding to each of the sliding windows is obtained; wherein each of the sliding windows corresponds to M groups of the detection data, and M is a positive integer;

[0016] Each of the dispersion coefficients is compared with a dispersion coefficient threshold value;

[0017] When the dispersion coefficient is greater than the dispersion coefficient threshold value, one of the initial surge samples is obtained based on the sliding window; wherein each of the initial surge samples includes L groups of the detection data, and L is a positive integer;

[0018] Power calculation is performed on each of the initial surge samples, to obtain a corresponding initial power set; wherein each of the initial power sets includes a plurality of initial powers, and each of the initial powers is obtained based on a group of detection data.

[0019] Optionally, the initial power set corresponding to each of the initial surge sample sets is compared with a reference power, to obtain comparison results, including:

[0020] A first initial power is determined based on each of the initial power sets, and the first initial power is compared with the reference power, to obtain a first sub-comparison result;

[0021] Each of the initial power sets is divided into a first sub-initial power set and a second sub-initial power set;

[0022] Each of the initial powers in the first sub-initial power set is compared with the reference power, to obtain a second sub-comparison result;

[0023] Each of the initial powers in the second sub-initial power set is compared with the reference power, to obtain a third sub-comparison result;

[0024] determine the comparison result based on the first sub-comparison result, the second sub-comparison result and the third sub-comparison result.

[0025] Optionally, the corrected surge sample set is obtained based on the target surge sample and the historical surge sample set, and the method comprises:

[0026] After the target surge sample is obtained, a first determination parameter of the historical surge sample set is calculated;

[0027] The first determination parameter is compared with a determination parameter threshold value;

[0028] When the first determination parameter is greater than the determination parameter threshold value, the corrected surge sample set is obtained based on a first correction method; or when the first determination parameter is less than or equal to the determination parameter threshold value, the corrected surge sample set is obtained based on a second correction method.

[0029] Optionally, the corrected surge sample set is obtained based on the first correction method, and the method comprises:

[0030] It is determined whether the target surge sample is below a boundary of the surge boundary model;

[0031] If the target surge sample is below the boundary, a first reference surface is obtained based on the target surge sample and the historical surge sample set; or if the target surge sample is not below the boundary, the target surge sample is invalid;

[0032] It is determined whether the first reference surface conforms to a first preset rule;

[0033] If the first reference surface conforms to the first preset rule, a first sub-corrected surge sample set is obtained based on the target surge sample; or if the first reference surface does not conform to the first preset rule, a second sub-corrected surge sample set is obtained based on the target surge sample.

[0034] Optionally, the corrected surge sample set is obtained based on the second correction method, and the method comprises:

[0035] It is determined whether the historical surge sample set includes the target surge sample;

[0036] If the target surge sample includes the target surge sample, it is determined that the target surge sample is invalid;

[0037] Or if the target surge sample does not include the target surge sample, a second reference surface is obtained based on the target surge sample and the historical surge sample set, and it is determined whether the second reference surface conforms to a second preset rule.

[0038] If the second reference curve meets the second preset rule, a third sub-modified surge sample set is obtained based on the target surge sample; or if the second reference curve does not meet the second preset rule, a fourth sub-modified surge sample set is obtained based on the target surge sample.

[0039] Optionally, the surge boundary model is self-modified based on the modified surge sample set to obtain a modified surge boundary model, including:

[0040] The surge boundary model is modified based on the first modification method and the modified surge sample set to obtain the modified surge boundary model; or the surge boundary model is modified based on the second modification method and the modified surge sample set to obtain the modified surge boundary model.

[0041] Optionally, the surge boundary model is modified based on the second modification method and the modified surge sample set to obtain the modified surge boundary model, including:

[0042] The modified surge boundary model is obtained based on self-modification of the third sub-modified surge sample set model; or

[0043] The modified surge boundary model is obtained based on self-fitting of the fourth sub-modified surge sample set model.

[0044] A second determination parameter of the fourth sub-modified surge sample set is calculated.

[0045] The second determination parameter is compared with the determination parameter threshold value, if the second determination parameter is greater than the determination parameter threshold value, the plurality of to-be-determined surge boundary models are screened based on the fourth sub-modified surge sample set, and the modified surge boundary model is determined.

[0046] Embodiments of the present application also provide a surge data processing device, including:

[0047] A first obtaining module is configured to obtain a plurality of initial surge samples, and obtain an initial power set based on each initial surge sample.

[0048] A determination module is configured to compare the initial power set corresponding to each initial surge sample set with a reference power to obtain a comparison result, and determine a plurality of initial surge samples based on the comparison result to obtain a target surge sample.

[0049] A second obtaining module is configured to obtain a modified surge sample set based on the target surge sample.

[0050] A correction module is configured to correct the surge boundary model based on the corrected surge sample set, and obtain a corrected surge boundary model.

[0051] Embodiments of the present application also provide an electronic device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the method as described above when executing the computer program.

[0052] Embodiments of the present application also provide a computer readable storage medium comprising a stored computer program, wherein the computer readable storage medium controls a device where the computer readable storage medium is located to execute the method as described above when the computer program runs.

[0053] Embodiments of the present application have the following technical effects:

[0054] The above technical solutions of the present application have the following advantages:

[0055] 2) The target surge sample is further determined, and a corrected surge sample set is obtained, thereby improving the accuracy of the boundary of the historical surge sample set and the surge boundary model.

[0056] 3) The self-learning strategy of the historical surge sample set and the surge boundary model is realized for different application stages of the centrifugal compressor, which can improve the self-learning efficiency of the historical surge sample set and the surge boundary model, ensure the accuracy of the surge boundary model, solve the problem that the initial surge control may fail due to the environment, leading to frequent surges, and the high maintenance cost required for handling surge failure and correcting the surge boundary, and improve the user experience.

[0057] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0058] Figure 1 FIG. 1 is a flowchart of a surge data processing method provided by an embodiment of the present application;

[0059] Figure 2 FIG. 3 is a flowchart of a determination method provided by an embodiment of the present application;

[0060] Figure 3 FIG. 5 is a flowchart of a method for determining whether a target surge sample is valid based on a first curved surface provided by an embodiment of the present application;

[0061] Figure 4is an example diagram provided by an embodiment of the present application for determining whether a target surge sample is valid based on a first curved surface;

[0062] Figure 5 is a flow diagram provided by an embodiment of the present application for determining whether a target surge sample is valid based on a second curved surface;

[0063] Figure 6 is a flow diagram provided by an embodiment of the present application for modifying a surge boundary model;

[0064] Figure 7 is a structural diagram of a surge data processing device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0065] Embodiments of the present application are described in detail below with reference to the accompanying drawings, in which the same or similar elements or elements having the same or similar functions are denoted by the same or similar reference numerals throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application, and cannot be understood as limiting the present application.

[0066] As shown in Figure 1 An embodiment of the present application provides a surge data processing method, comprising:

[0067] Step S11: obtaining a plurality of initial surge samples, and based on each initial surge sample, obtaining an initial power set;

[0068] In an optional embodiment of the present application, the obtaining of the plurality of initial surge samples and the obtaining of the initial power set based on each initial surge sample comprises:

[0069] obtaining a plurality of groups of detection data; wherein each group of detection data comprises a plurality of operating parameters;

[0070] processing the plurality of groups of detection data based on a sliding window, and obtaining a dispersion coefficient of a signal corresponding to each sliding window; wherein each sliding window corresponds to M groups of detection data, and M is a positive integer;

[0071] comparing each dispersion coefficient with a dispersion coefficient threshold;

[0072] when the dispersion coefficient is greater than the dispersion coefficient threshold, obtaining an initial surge sample based on the sliding window; wherein each initial surge sample comprises L groups of detection data, and L is a positive integer;

[0073] performing power calculation on each initial surge sample to obtain a corresponding initial power set; wherein each initial power set comprises a plurality of initial powers, and each initial power is obtained based on a group of detection data.

[0074] Embodiments of the present application can automatically detect and obtain multiple sets of detection data, reduce or even replace a large number of surge tests in the research and development stage of the centrifugal compressor, simplify the operation, reduce the labor cost, and improve the efficiency.

[0075] In an optional embodiment of the present application, the running state data of the centrifugal compressor is automatically detected based on a preset frequency (for example, 50-100 Hz) to obtain multiple sets of detection data, wherein each set of detection data includes multiple running parameters, including but not limited to the compressor speed SPD, the guide vane opening IGV, the power Pow, the suction temperature Tsuc, the discharge temperature Tdis, the suction pressure Psuc, and the discharge pressure Pdis at one time.

[0076] Specifically, the multiple sets of detection data can include X1, X2, X3,..., Xn. n ; X n are used to represent the nth set of detection data, and n is a positive integer.

[0077] X n = (SPD n , IGV n , Pow n , Tsuc n , Tdis n , Psuc n , Pdis n ).

[0078] Further, the size and step length of the sliding window are set; for example, the size of the sliding window can be 3 (i.e., L=3), and the step length of the sliding window can be 3; the dispersion coefficient of the signal in each sliding window is continuously calculated.

[0079] For example, the ith sliding window corresponds to the ith dispersion coefficient S i , and i is a positive integer.

[0080] wherein, is the average value calculated based on the multiple sets of detection data; j is the time sequence of the detection data in the last sliding window in the sliding window, and 1≤j≤n, and j is an integer.

[0081] Further, a preset dispersion coefficient threshold δ S is compared with the ith dispersion coefficient S i of the ith sliding window and the dispersion coefficient threshold δ S .

[0082] If S i > δ S, which indicates that the centrifugal compressor enters the surge region, and the ith sliding window is determined as the starting point of the surge region, or the ith sliding window is determined as the starting point close to the surge region;

[0083] Then, 8 groups of data (i.e., M=8) in the ith sliding window, 1 group of detection data before the sliding window, and 4 groups of detection data after the sliding window are determined as an initial surge sample.

[0084] That is, an initial surge sample can be characterized in the following manner:

[0085] Initial surge sample = (X i-1 , X i , X i+1 , X i+2 , X i+3 , X i+4 , X i+5 , X i+6 );

[0086] Embodiments of the present application store the initial surge sample after obtaining the initial surge sample, so as to facilitate subsequent algorithm calling.

[0087] Step S12: comparing the initial power set corresponding to each initial surge sample set with reference power, obtaining a comparison result, and determining each initial surge sample based on the comparison result to obtain a target surge sample;

[0088] In an optional embodiment of the present application, the comparison of the initial power set corresponding to each initial surge sample set with reference power to obtain a comparison result comprises:

[0089] determining a first initial power based on each initial power set, and comparing the first initial power with the reference power to obtain a first sub-comparison result;

[0090] dividing each initial power set into a first sub-initial power set and a second sub-initial power set;

[0091] comparing each initial power in the first sub-initial power set with the reference power to obtain a second sub-comparison result;

[0092] comparing each initial power in the second sub-initial power set with the reference power to obtain a third sub-comparison result;

[0093] determining the comparison result based on the first sub-comparison result, the second sub-comparison result, and the third sub-comparison result.

[0094] The embodiment of the application determines whether the initial surge sample is valid after obtaining the initial surge sample. If the initial surge sample is valid, the initial surge sample is determined as the target surge sample. If the initial surge sample is invalid, the initial surge sample is eliminated. The valid initial surge sample is the demarcation point at which the centrifugal compressor is switched from the normal operation state to the surge instability state. Automatic detection may determine the normal dynamic state as the surge, and may also delay detection, that is, the obtained initial surge sample is already in the surge instability state. Therefore, it is necessary to further determine whether the initial surge sample is valid after obtaining the initial surge sample.

[0095] In an optional embodiment of the application, in order to solve the above problem and determine whether each initial surge sample is valid, a preset power model of the centrifugal compressor is used to calculate the power value of the normal state corresponding to each sampling point based on the multiple sets of detection data in each initial surge sample, that is, each sampling point corresponds to an initial power, and each initial surge sample corresponds to an initial power set.

[0096] The initial surge sample is:

[0097] (X i-1 、X i 、X i+1 、X i+2 、X i+3 、X i+4 、X i+5 、X i+6 );

[0098] Then, an initial power is calculated based on each set of detection data in the initial surge sample, and an initial power set is obtained.

[0099] The initial power corresponding to X i-1 is determined as the first initial power.

[0100] A first sub-initial power set is obtained based on the first four initial powers in the initial power set.

[0101] A second sub-initial power set is obtained based on the last four initial powers in the initial power set.

[0102] The first initial power is compared with the reference power to obtain a first deviation, and the first deviation is compared with a deviation threshold (δ P ) to obtain a first comparison result.

[0103] Each initial power in the first sub-initial power set is compared with the reference power to obtain a deviation, respectively, and the deviations are averaged to obtain a second deviation. The second deviation is compared with the deviation threshold to obtain a second comparison result.

[0104] Each initial power in the second sub-initial power set is compared with the reference power to obtain the deviation. The deviations are averaged to obtain the third deviation. The third deviation is compared with the deviation threshold to obtain the third sub-comparison result.

[0105] Then, by combining the results of the first sub-alignment, the second sub-alignment, and the third sub-alignment, it is determined whether the initial surge sample is valid.

[0106] Specifically, if the first sub-alignment result is a first deviation greater than or equal to the deviation threshold; the second sub-alignment result is a second deviation greater than or equal to the deviation threshold; and the third sub-alignment result is a third deviation greater than the deviation threshold, then it indicates that the initial surge sample record is delayed and invalid.

[0107] If the first sub-alignment result is that the first deviation is greater than the deviation threshold, the second sub-alignment result is that the second deviation is less than the deviation threshold, and the third sub-alignment result is that the third deviation is less than the deviation threshold, then it indicates that the initial surge sample is a misjudgment and is invalid.

[0108] Alternatively, if the first sub-alignment result shows a first deviation greater than the deviation threshold; the second sub-alignment result shows a second deviation less than the deviation threshold; and the third sub-alignment result shows a third deviation greater than or equal to the deviation threshold, then the initial surge sample is considered valid, and this initial surge sample is identified as the target surge sample. The X value in the target surge sample is then... i The value was determined as the surge boundary point value.

[0109] An optional embodiment of this application is based on POWM. j Characterizes the reference power (i.e., the power corresponding to the compressor under normal conditions);

[0110] POWM j =f(SPD) j IGV j Tsuc j Psuc j Pdis j );

[0111] j = i-1, i, ..., i+6;

[0112] based on Characterizing the first four sets of detection data in each initial surge sample; based on Characterizes the last four sets of detection data in each initial surge sample;

[0113] Then, 1) If the first sub-alignment result is that the first deviation is greater than the deviation threshold, and

[0114]

[0115] indicates that the initial surge sample record delay is invalid.

[0116] 2) If the first sub-comparison result is that the first deviation is greater than the deviation threshold, and

[0117]

[0118] indicates that the initial surge sample is a false positive, and is invalid;

[0119] 3) If the first sub-comparison result is that the first deviation is greater than the deviation threshold, and

[0120]

[0121] indicates that the initial surge sample is valid, and the initial surge sample is determined as the target surge sample.

[0122] Step S13: Based on the target surge sample and the historical surge sample set, a corrected surge sample set is obtained.

[0123] As shown in FIG. 13, in an optional embodiment of the present application, in step S13, the obtaining of the corrected surge sample set based on the target surge sample and the historical surge sample set comprises: Figure 2 Step S131: After the target surge sample is obtained, a first determination parameter of the historical surge sample set is calculated.

[0124] Step S132: The first determination parameter is compared with a determination parameter threshold.

[0125] Step S133: When the first determination parameter is greater than the determination parameter threshold, the corrected surge sample set is obtained based on a first correction method.

[0126] Step S134: Or when the first determination parameter is less than or equal to the determination parameter threshold, the corrected surge sample set is obtained based on a second correction method.

[0127] Embodiments of the present application further determine the target surge sample, and obtain a corrected surge sample set, thereby improving the accuracy of the boundary of the historical surge sample set and the surge boundary model.

[0128] Embodiments of the present application preset the first correction method and the second correction method to correct the historical surge sample set and the current surge boundary model, which is used for different application scenarios and operation stages of the centrifugal compressor.

[0129] As shown in FIG. 13, in an optional embodiment of the present application, in step S13, the obtaining of the corrected surge sample set based on the target surge sample and the historical surge sample set comprises:

[0130] Figure 3 ​As shown in an optional embodiment of this application, step S133, which involves obtaining the corrected surge sample set based on the first correction method, includes:

[0131] Step S1331: Determine whether the target surge sample is below the boundary of the surge boundary model;

[0132] Step S1332: If the target surge sample is below the boundary, then obtain a first reference surface based on the target surge sample and the historical surge sample set; or

[0133] Step S1333: If the target surge sample is not below the boundary, then the target surge sample is invalid;

[0134] Step S1334: Determine whether the first reference surface conforms to the first preset rule;

[0135] Step S1335: If the first reference surface conforms to the first preset rule, then based on the target surge sample, obtain the first sub-corrected surge sample set;

[0136] Step S13336: Or if the first reference surface does not conform to the first preset rule, then obtain a second sub-corrected surge sample set based on the target surge sample.

[0137] In an optional embodiment of this application, when the centrifugal compressor is in operation and the number of historical surge samples and the coverage rate (judgment parameter) of the historical surge sample set are greater than the judgment parameter threshold, a first correction method is used to correct the historical surge sample set and the surge boundary model; conversely, when the number of historical surge samples and the coverage rate of the historical surge samples are less than the judgment parameter threshold, a second correction method is used to correct the historical surge sample set and the surge boundary model.

[0138] In an optional embodiment of this application, after determining that the first correction method is adopted, it is determined whether the target surge sample obtained based on automatic detection is below the boundary of the surge boundary model;

[0139] Specifically, such as Figure 4 As shown, a schematic diagram of the boundary corresponding to a surge boundary model is provided, and an example of a target surge sample below the boundary of the surge boundary model is provided.

[0140] Among them, SPD[Hz], IGV[-], and PR[-] are used to characterize the three coordinate axes in the figure, respectively;

[0141] PR c =f surge (SPD, IGV, Tsuc, Tdis), PRc -PR > 0;

[0142] wherein, f surge for representing the current surge margin model; PR c is calculated based on the surge margin model, the surge point pressure ratio of the surge margin model under the working condition corresponding to the target surge sample; PR = Pdis / Psuc, the surge point pressure ratio corresponding to the target surge sample;

[0143] That is, when PR c -PR > 0, it indicates whether the target surge sample is below the boundary of the surge margin model;

[0144] On the contrary, if the target surge sample is not below the boundary of the surge margin model, it can be determined that the target surge sample is invalid, and the current surge margin model does not need to be self-corrected;

[0145] In an optional embodiment of the present application, based on the target surge sample obtained by automatic detection and the historical surge sample set, a first curve is obtained, and it is judged whether the trend of the first curve conforms to a first preset rule (the embodiments of the present application do not make specific limitations on this). That is, it is judged whether the trend of the first curve is reasonable. If the trend of the first curve conforms to the first preset rule, a second sub-modified surge sample is added to the historical surge sample set based on the target surge sample, and a first sub-modified surge sample set is obtained. If the trend of the first curve does not conform to the first preset rule, the target surge sample is reserved, and the historical surge sample set is searched based on the target surge sample, the historical surge sample conflicting with the target surge sample is determined, and the historical surge sample is removed from the historical surge sample set, and the target surge sample is added to the historical surge sample set, and a second sub-modified surge sample set is obtained.

[0146] Specifically, the first preset rule is determined based on the following formula:

[0147] (PR-PR IGV，i ) / (SPD-SPD i ) > 0;

[0148] (PR-PR SPD，i ) / (IGV-IGV i ) > 0;

[0149] Wherein, SPD i is the centrifugal compressor speed of any historical surge sample i in the historical surge sample set; IGV i is the guide vane opening of any historical surge sample i in the historical surge sample set; PR IGV，iPR SPD，i PR

[0150] As shown in Figure 5 The step S134 of obtaining the modified surge sample set based on the second correction method includes:

[0151] Step S1341: determining whether the historical surge sample set includes the target surge sample;

[0152] Step S1342: if the target surge sample is included in the target surge sample, determining that the target surge sample is invalid;

[0153] Step S1343: or if the target surge sample is not included in the target surge sample, obtaining a second reference surface based on the target surge sample and the historical surge sample set;

[0154] Step S1344: determining whether the second reference surface meets a second preset rule;

[0155] Step S1345: if the second reference surface meets the second preset rule, obtaining a third sub-modified surge sample set based on the target surge sample;

[0156] Step S1346: or if the second reference surface does not meet the second preset rule, obtaining a fourth sub-modified surge sample set based on the target surge sample.

[0157] In an optional embodiment of the present application, a second surface is obtained based on the target surge sample obtained by automatic detection and the historical surge sample set, and it is determined whether the trend of the second surface meets a second preset rule. If the trend of the second surface meets the second preset rule, a third sub-modified surge sample set is obtained based on the target surge sample and the historical surge sample set. If the trend of the second surface does not meet the second preset rule, the target surge sample with the minimum Euclidean distance from the boundary of the current surge boundary model is reserved, and the target surge sample is added to the historical surge sample set to obtain a fourth sub-modified surge sample set.

[0158] Specifically, the second preset rule is determined based on the following formula:

[0159] (PR-PRIGV，i ) / (SPD-SPD i ) > 0;

[0160] (PR-PR SPD，i ) / (IGV-IGV i ) > 0.

[0161] Step S14: The surge margin model is self-corrected based on the corrected surge sample set to obtain a corrected surge margin model.

[0162] In an optional embodiment of the present application, the surge margin model is self-corrected based on the corrected surge sample set to obtain a corrected surge margin model, and the method comprises the following steps:

[0163] The surge margin model is corrected based on the first correction method and the corrected surge sample set to obtain the corrected surge margin model, or the surge margin model is corrected based on the second correction method and the corrected surge sample set to obtain the corrected surge margin model.

[0164] In an optional embodiment of the present application, after the corresponding corrected surge sample set is obtained, the surge margin model is further corrected based on the corresponding first correction method or second correction method based on the corrected surge sample set, and finally the corrected surge margin model is obtained.

[0165] In an optional embodiment of the present application, after the first sub corrected surge sample set is obtained, the current surge margin model is self-corrected based on the first sub corrected surge sample set to obtain a first initial surge margin model, or after the second sub corrected surge sample set is obtained, the current surge margin model is self-corrected based on the second sub corrected surge sample set to obtain a corrected surge margin model.

[0166] In the embodiments of the present application, when the centrifugal compressor is formally running, that is, the number of historical surge samples in the historical surge sample set and the coverage rate of the historical surge samples are greater than the determination parameter threshold, in this working condition, the corrected surge margin model obtained is the same in form as the surge margin model, and the output value based on the corrected surge margin model is the target value of the anti-surge control of the centrifugal compressor; it is realized that when the anti-surge fails due to performance degradation of the centrifugal compressor and the like and the centrifugal compressor surges, the corrected target surge sample set is obtained by means of surge automatic detection for self-correction of the surge margin model, to ensure that the surge margin model is continuously updated according to the state of the centrifugal compressor, and to avoid continuous failure of the anti-surge control.

[0167] As Figure 6As shown, in an optional embodiment of the present application, in step S14, the surge boundary model is corrected based on the second correction method and the corrected surge sample set to obtain the corrected surge boundary model, including:

[0168] Step S141: determining whether a third sub corrected surge sample set is obtained;

[0169] Step S142: if yes, performing self-correction based on the third sub corrected surge sample set model to obtain the corrected surge boundary model; or

[0170] Step S143: if no, performing self-fitting based on a fourth sub corrected surge sample set model to obtain a plurality of to-be-determined surge boundary models;

[0171] Step S144: calculating a second determination parameter of the fourth sub corrected surge sample set;

[0172] Step S145: and comparing the second determination parameter with the determination parameter threshold;

[0173] Step S146: if the second determination parameter is not greater than the determination parameter threshold, repeating the above steps until the second determination parameter is greater than the determination parameter threshold.

[0174] Step S147: if the second determination parameter is greater than the determination parameter threshold, screening the plurality of to-be-determined surge boundary models based on the fourth sub corrected surge sample set, and determining the corrected surge boundary model.

[0175] In an optional embodiment of the present application, after obtaining the target surge sample, a third sub corrected surge sample set is obtained based on the target corrected surge sample, self-correction is performed based on the third sub corrected surge sample set model, and the corrected surge boundary model is determined.

[0176] In an optional embodiment of the present application, self-fitting is performed based on a fourth sub corrected surge sample set model to obtain a plurality of to-be-determined surge boundary models;

[0177] The number of corrected surge samples in the fourth sub corrected surge sample set and the coverage rate of the first sub corrected surge sample set, i.e., the second determination parameter, are calculated;

[0178] The number of corrected surge samples and the coverage rate of the first sub corrected surge sample set are compared with the determination parameter threshold, and if the number of corrected surge samples and the coverage rate of the first sub corrected surge sample set are both greater than the determination parameter threshold, the plurality of to-be-determined surge boundary models are screened based on the fourth sub corrected surge sample set, and the corrected surge boundary model is determined.

[0179] An optional embodiment of this application involves screening multiple surge boundary models to be determined based on a fourth sub-corrected surge sample set, and determining the corrected surge boundary model. This includes calculating the Euclidean distance between each target surge sample and the current boundary, and determining the surge boundary model to be determined with the smallest Euclidean distance as the corrected surge boundary model.

[0180] In the embodiments of this application, when the centrifugal compressor is in the trial operation stage or the anti-surge control has not yet been activated, that is, when the number of historical surge samples and the coverage of historical surge samples in the historical surge sample set are both less than the judgment parameter threshold, the centrifugal compressor runs while automatically detecting and improving the current historical surge sample set, and fitting various forms of surge boundary models to be determined based on the obtained corrected surge sample set; wherein, the form of the surge boundary model to be determined includes, but is not limited to, polynomials, exponential equations, neural network models, etc.

[0181] Furthermore, when the number of corrected surge samples and the coverage of corrected surge samples in the fourth sub-corrected surge sample set are both greater than the judgment parameter threshold, the surge boundary model to be determined with the smallest root mean square error with the current corrected surge sample set is selected as the current final corrected surge boundary model, and anti-surge control is initiated.

[0182] The embodiments of this application implement a self-learning strategy that adopts different historical surge sample sets and surge boundary models for different application stages of centrifugal compressors. This can improve the self-learning efficiency of historical surge sample sets and surge boundary models, and ensure the accuracy of surge boundary models. It solves the problems that the initial surge control may fail due to the environment, leading to frequent surges, and that it is necessary to consume extremely high maintenance costs to deal with surge faults and correct surge boundaries, and improves the user experience.

[0183] like Figure 7 As shown, embodiments of this application also provide a surge data processing device 70, comprising:

[0184] The first acquisition module 71 is used to acquire multiple initial surge samples and, based on each initial surge sample, acquire an initial power set;

[0185] The determination module 72 is used to compare the initial power set corresponding to each initial surge sample set with the reference power, obtain the comparison result, and determine the multiple initial surge samples based on the comparison result to obtain the target surge sample;

[0186] The second acquisition module 73 is used to obtain a corrected surge sample set based on the target surge sample;

[0187] The correction module 74 is used to perform self-correction of the surge boundary model based on the corrected surge sample set to obtain the corrected surge boundary model.

[0188] Optionally, obtaining multiple initial surge samples and, based on each initial surge sample, obtaining an initial power set includes:

[0189] Multiple sets of detection data are obtained; each set of detection data includes multiple operating parameters;

[0190] The detection data is processed using a sliding window, and the discrete coefficients of the signal corresponding to each sliding window are obtained; wherein each sliding window corresponds to M sets of detection data, and M is a positive integer;

[0191] Each of the discrete coefficients is compared with a discrete coefficient threshold;

[0192] When the discrete coefficient is greater than the discrete coefficient threshold, an initial surge sample is obtained based on the sliding window; wherein each initial surge sample includes L sets of detection data, where L is a positive integer;

[0193] Power calculation is performed on each initial surge sample to obtain the corresponding initial power set; wherein each initial power set includes multiple initial powers, and each initial power is obtained based on a set of detection data.

[0194] Optionally, the step of comparing the initial power set corresponding to each initial surge sample set with the reference power to obtain the comparison result includes:

[0195] A first initial power is determined based on each of the initial power sets, and the first initial power is compared with the reference power to obtain a first sub-comparison result;

[0196] Each of the initial power sets is divided into a first sub-initial power set and a second sub-initial power set;

[0197] Each initial power in the first sub-initial power set is compared with the reference power to obtain the second sub-comparison result;

[0198] Each initial power in the second sub-initial power set is compared with the reference power to obtain a third sub-comparison result;

[0199] The alignment result is determined based on the first sub-alignment result, the second sub-alignment result, and the third sub-alignment result.

[0200] Optionally, obtaining the corrected surge sample set based on the target surge sample and the historical surge sample set includes:

[0201] after obtaining the target surge sample, a first decision parameter of the historical surge sample set is calculated;

[0202] the first decision parameter is compared with a decision parameter threshold;

[0203] when the first decision parameter is greater than the decision parameter threshold, the modified surge sample set is obtained based on a first correction method; or when the first decision parameter is less than or equal to the decision parameter threshold, the modified surge sample set is obtained based on a second correction method.

[0204] Optionally, the modified surge sample set is obtained based on the first correction method, comprising:

[0205] it is judged whether the target surge sample is below a boundary of the surge boundary model;

[0206] if the target surge sample is below the boundary, a first reference surface is obtained based on the target surge sample and the historical surge sample set; or if the target surge sample is not below the boundary, the target surge sample is invalid;

[0207] it is judged whether the first reference surface conforms to a first preset rule;

[0208] if the first reference surface conforms to the first preset rule, a first sub-modified surge sample set is obtained based on the target surge sample; or if the first reference surface does not conform to the first preset rule, a second sub-modified surge sample set is obtained based on the target surge sample.

[0209] Optionally, the modified surge sample set is obtained based on the second correction method, comprising:

[0210] it is judged whether the historical surge sample set includes the target surge sample;

[0211] if the target surge sample includes the target surge sample, it is determined that the target surge sample is invalid;

[0212] or if the target surge sample does not include the target surge sample, a second reference surface is obtained based on the target surge sample and the historical surge sample set, and it is judged whether the second reference surface conforms to a second preset rule;

[0213] if the second reference surface conforms to the second preset rule, a third sub-modified surge sample set is obtained based on the target surge sample; or if the second reference surface does not conform to the second preset rule, a fourth sub-modified surge sample set is obtained based on the target surge sample.

[0214] Optionally, the surge margin model is self-corrected based on the corrected surge sample set to obtain a corrected surge margin model, including:

[0215] The surge margin model is corrected based on the first correction method and the corrected surge sample set to obtain the corrected surge margin model, or the surge margin model is corrected based on the second correction method and the corrected surge sample set to obtain the corrected surge margin model.

[0216] Optionally, the surge margin model is corrected based on the second correction method and the corrected surge sample set to obtain the corrected surge margin model, including:

[0217] The corrected surge margin model is obtained based on self-correction of the third sub-correction surge sample set model, or

[0218] The plurality of to-be-determined surge margin models are obtained based on self-fitting of the fourth sub-correction surge sample set model;

[0219] The second determination parameter of the fourth sub-correction surge sample set is calculated and obtained;

[0220] The second determination parameter is compared with the determination parameter threshold value, if the second determination parameter is greater than the determination parameter threshold value, the plurality of to-be-determined surge margin models are screened based on the fourth sub-correction surge sample set, and the corrected surge margin model is determined.

[0221] Embodiments of the present application also provide an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, when the processor executes the computer program, the method described above is implemented.

[0222] Embodiments of the present application also provide a computer readable storage medium, including a stored computer program, wherein when the computer program runs, the device where the computer readable storage medium is located executes the method described above.

[0223] In addition, other configurations and functions of the device of the embodiments of the present application are known to those skilled in the art, to reduce redundancy, which will not be described here.

[0224] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0225] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0226] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0227] In the description of the application, it should be understood that the orientation or positional relationship indicated by the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the application and simplifying the description, and does not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the application.

[0228] In addition, the terms "first", "second" are only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the application, the meaning of "a plurality of" is at least two, such as two, three, etc., unless otherwise explicitly specified and limited.

[0229] In this application, unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connecting", "fixing" and the like should be broadly understood, such as HYPERLINK, which can also be detachable connection, or integrated; can be mechanical connection, or electrical connection; can be directly connected, or indirectly connected through intermediate medium, can be the internal communication of two elements or the interaction relationship between two elements, unless otherwise explicitly limited. For ordinary skilled in the art, the specific meaning of the above terms in this application can be understood according to the specific circumstances.

[0230] In this application, unless otherwise explicitly specified and limited, the first feature is "on" or "under" the second feature, which can be direct contact between the first and second features, or indirect contact between the first and second features through intermediate medium. Moreover, the first feature "above", "above" and "above" the second feature can be directly above or obliquely above the first feature, or only indicate that the horizontal height of the first feature is higher than that of the second feature. The first feature "below", "below" and "below" the second feature can be directly below or obliquely below the first feature, or only indicate that the horizontal height of the first feature is less than that of the second feature.

[0231] Although the embodiments of the application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as a limitation on the application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the application.

Claims

1. A surge data processing method, characterized by, The method comprises: obtaining a plurality of initial surge samples, and based on each of the initial surge samples, obtaining an initial power set; The method comprises: obtaining a plurality of sets of detection data; wherein each set of the detection data comprises a plurality of operating parameters; processing the plurality of sets of detection data based on a sliding window, and obtaining a dispersion coefficient of a signal corresponding to each of the sliding windows; wherein each of the sliding windows corresponds to M sets of the detection data, and M is a positive integer; comparing each of the dispersion coefficients with a dispersion coefficient threshold value; when the dispersion coefficient is greater than the dispersion coefficient threshold value, obtaining an initial surge sample based on the sliding window; wherein each of the initial surge samples comprises L sets of the detection data, and L is a positive integer; performing power calculation on each of the initial surge samples to obtain a corresponding initial power set; wherein each of the initial power sets comprises a plurality of initial powers, and each of the initial powers is obtained based on a set of detection data; comparing the initial power set corresponding to each of the initial surge samples with a reference power to obtain a comparison result, comprising: determining a first initial power based on each of the initial power sets, and comparing the first initial power with the reference power to obtain a first sub-comparison result; dividing each of the initial power sets into a first sub-initial power set and a second sub-initial power set; comparing each of the initial powers in the first sub-initial power set with the reference power to obtain a second sub-comparison result; comparing each of the initial powers in the second sub-initial power set with the reference power to obtain a third sub-comparison result; determining the comparison result based on the first sub-comparison result, the second sub-comparison result, and the third sub-comparison result; and based on the comparison result, determining each of the initial surge samples to obtain a target surge sample; based on the target surge sample and a historical surge sample set, obtaining a corrected surge sample set, comprising: after obtaining the target surge sample, calculating a first determination parameter of the historical surge sample set; comparing the first determination parameter with a determination parameter threshold value; when the first determination parameter is greater than the determination parameter threshold value, obtaining the corrected surge sample set based on a first correction method; or when the first determination parameter is less than or equal to the determination parameter threshold value, obtaining the corrected surge sample set based on a second correction method; The surge boundary model is self-corrected based on the corrected surge sample set to obtain a corrected surge boundary model.

2. The method of claim 1, wherein, The corrected surge sample set is obtained based on the first correction method, comprising: determining whether the target surge sample is below a boundary of the surge boundary model; if the target surge sample is below the boundary, obtaining a first reference surface based on the target surge sample and the historical surge sample set; or if the target surge sample is not below the boundary, the target surge sample is invalid; determining whether the first reference surface meets a first preset rule; If the first reference curve meets the first preset rule, a first sub-modified surge sample set is obtained based on the target surge sample; or if the first reference curve does not meet the first preset rule, a second sub-modified surge sample set is obtained based on the target surge sample.

3. The method of claim 1, wherein, The obtaining of the modified surge sample set based on the second modification method comprises: determining whether the target surge sample is included in the historical surge sample set; if the target surge sample is included in the target surge sample, determining that the target surge sample is invalid; or if the target surge sample is not included in the target surge sample, obtaining a second reference curve based on the target surge sample and the historical surge sample set, and determining whether the second reference curve meets a second preset rule; if the second reference curve meets the second preset rule, a third sub-modified surge sample set is obtained based on the target surge sample; or if the second reference curve does not meet the second preset rule, a fourth sub-modified surge sample set is obtained based on the target surge sample.

4. The method of claim 1, wherein, The surge boundary model is self-modified based on the modified surge sample set to obtain a modified surge boundary model, comprising: the surge boundary model is modified based on the first modification method and the modified surge sample set to obtain the modified surge boundary model; or the surge boundary model is modified based on the second modification method and the modified surge sample set to obtain the modified surge boundary model.

5. The method of claim 4, wherein, The modification of the surge boundary model based on the second modification method and the modified surge sample set to obtain the modified surge boundary model comprises: based on the third sub-modified surge sample set model, self-modification is performed to obtain the modified surge boundary model; or based on the fourth sub-modified surge sample set model, self-fitting is performed to obtain a plurality of to-be-determined surge boundary models; a second determination parameter of the fourth sub-modified surge sample set is calculated; and the second determination parameter is compared with the determination parameter threshold value, if the second determination parameter is greater than the determination parameter threshold value, a plurality of the to-be-determined surge boundary models are screened based on the fourth sub-modified surge sample set, and the modified surge boundary model is determined.

6. A surge data processing apparatus which applies the surge data processing method as claimed in any one of claims 1 to 5, characterized by The device comprises: a first obtaining module for obtaining a plurality of initial surge samples, and obtaining an initial power set based on each initial surge sample; a determination module for comparing the initial power set corresponding to each initial surge sample with a reference power to obtain a comparison result, and determining a plurality of initial surge samples based on the comparison result to obtain a target surge sample; a second obtaining module for obtaining a modified surge sample set based on the target surge sample; a modification module for self-modification of a surge boundary model based on the modified surge sample set to obtain a modified surge boundary model.

7. An electronic device, comprising: A processor, a memory, and a computer program stored in the memory and configured to be executed by the processor are included, and the processor implements the method according to any one of claims 1 to 5 when executing the computer program. A processor, a memory, and a computer program stored in the memory and configured to be executed by the processor are included, and the processor implements the method according to any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium includes a stored computer program, wherein the computer readable storage medium controls a device where the computer readable storage medium is located to execute the method as claimed in any one of claims 1 to 5 when the computer program is running.

Images