Method and device for detecting test state of gas compressor of gas turbine

Abstract

The invention provides a gas turbine compressor test state detection method and device. The method comprises the steps that a first frequency domain characteristic value and a first time domain characteristic value of a first pressure signal and a second frequency domain characteristic value and a second time domain characteristic value of a second pressure signal are obtained; according to the first frequency domain characteristic value, the first early warning threshold value, the first time domain characteristic value and the second early warning threshold value, the first test state of the gas turbine compressor to be detected is determined; according to the second frequency domain characteristic value, the first early warning threshold value, the second time domain characteristic value and the second early warning threshold value, a second test state of the gas turbine compressor to be detected is determined; and determining the target test state of the to-be-detected gas turbine compressor based on the first test state and the second test state, thereby improving the accuracy and reliability of determining the target test state of the to-be-detected gas turbine compressor, and effectively monitoring the safety in the gas turbine compressor test based on the target test state.

Description

Technical Field

[0001] The present invention relates to the technical field of gas turbines, and in particular to a method and device for detecting a test state of a gas turbine compressor. Background Art

[0002] In the related technologies, the detection of the test status of gas turbine compressors is mostly based on the technology in the field of aviation gas turbine engine compressor testing. However, there are huge differences between gas turbine compressor components and aviation gas turbine engine compressor components in terms of operating environment, technical status, geometric volume, mass / weight, air flow, etc. Although the aerodynamic instability mechanism of the gas turbine compressor entering an unstable working state is basically the same as that of the aviation gas turbine engine compressor, the actual engineering characterization phenomena are inconsistent. Therefore, how to accurately and reliably detect the test status of the gas turbine compressor has become an urgent problem to be solved. Summary of the Invention

[0003] The present application aims to solve one of the technical problems in the related art at least to a certain extent.

[0004] According to a first aspect of the present application, a method for detecting a test state of a gas turbine compressor is provided, comprising: obtaining a first pressure signal and a second pressure signal at an inlet of a gas turbine compressor to be detected; obtaining a first frequency domain eigenvalue and a first time domain eigenvalue of the first pressure signal and a second frequency domain eigenvalue and a second time domain eigenvalue of the second pressure signal; determining a first test state of the gas turbine compressor to be detected based on the first frequency domain eigenvalue and a first warning threshold and the first time domain eigenvalue and the second warning threshold; determining a second test state of the gas turbine compressor to be detected based on the second frequency domain eigenvalue and the first warning threshold and the second time domain eigenvalue and the second warning threshold; and determining a target test state of the gas turbine compressor to be detected based on the first test state and the second test state.

[0005] According to a second aspect of the present application, a device for detecting the test state of a gas turbine compressor is provided, comprising: a first acquisition module for acquiring a first pressure signal and a second pressure signal at the inlet of a gas turbine compressor to be detected; a second acquisition module for acquiring a first frequency domain eigenvalue and a first time domain eigenvalue of the first pressure signal and a second frequency domain eigenvalue and a second time domain eigenvalue of the second pressure signal; a first determination module for determining a first test state of the gas turbine compressor to be detected based on the first frequency domain eigenvalue and a first warning threshold and the first time domain eigenvalue and the second warning threshold; a second determination module for determining a second test state of the gas turbine compressor to be detected based on the second frequency domain eigenvalue and the first warning threshold and the second time domain eigenvalue and the second warning threshold; and a third determination module for determining a target test state of the gas turbine compressor to be detected based on the first test state and the second test state.

[0006] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the instructions to implement the method for detecting the test state of a gas turbine compressor as described in the first aspect of the embodiment of the present disclosure.

[0007] According to the fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method for detecting the test state of a gas turbine compressor as described in the first aspect of the embodiment of the present disclosure.

[0008] The technical solutions provided by the embodiments of the present application include at least the following beneficial effects:

[0009] The present application provides a method for detecting the test state of a gas turbine compressor. The method obtains a first pressure signal and a second pressure signal at the inlet of a gas turbine compressor to be detected, obtains a first frequency domain eigenvalue and a first time domain eigenvalue of the first pressure signal, and a second frequency domain eigenvalue and a second time domain eigenvalue of the second pressure signal, determines a first test state of the gas turbine compressor to be detected based on the first frequency domain eigenvalue and a first warning threshold as well as the first time domain eigenvalue and the second warning threshold, determines a second test state of the gas turbine compressor to be detected based on the second frequency domain eigenvalue and the first warning threshold as well as the second time domain eigenvalue and the second warning threshold, and determines a target test state of the gas turbine compressor to be detected based on the first test state and the second test state. Thus, the present application determines the target test state of the gas turbine compressor to be detected based on the first test state and the second test state, thereby improving the accuracy and reliability of determining the target test state of the gas turbine compressor to be detected. Based on the target test state, the safety of the gas turbine compressor test can be effectively monitored.

[0010] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present application.

[0012] Figure 1 A schematic flow chart of a method for detecting a test state of a gas turbine compressor provided in an embodiment of the present application;

[0013] Figure 2 A schematic diagram of decomposition based on Db8 orthogonal wavelet basis functions provided in an embodiment of the present application;

[0014] Figure 3 A schematic flow chart of another method for detecting the test status of a gas turbine compressor provided in an embodiment of the present application;

[0015] Figure 4 A schematic diagram of a multiply-accumulate wavelet decomposition and convolution operation provided in an embodiment of the present application;

[0016] Figure 5 A schematic structural diagram of a gas turbine compressor test status detection device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] The following description of exemplary embodiments of the present application is made in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0018] The following examples illustrate in detail the method for detecting the test state of a gas turbine compressor of the present application.

[0019] Figure 1 A flow chart of a method for detecting the test status of a gas turbine compressor provided in an embodiment of the present application.

[0020] like Figure 1 As shown, the method for detecting the test state of a gas turbine compressor proposed in this embodiment specifically includes the following steps:

[0021] S101 , obtaining a first pressure signal and a second pressure signal at an inlet of a compressor of a gas turbine to be detected.

[0022] It should be noted that during the engineering test of the gas turbine compressor, before entering the unstable working state, some airflow disturbances with a certain regularity and different from the manifestation of the unstable state will appear in the flow channel. The time from the beginning of the compressor unstable state to its complete development is relatively short. In particular, the unstable state of high-power compressor components is sudden, requiring the ability to continuously collect, quickly analyze in real time, and distinguish the state of the selected parameters. At present, during the test of the gas turbine compressor, the working state is usually displayed by dynamic parameters such as pressure, speed, temperature, and vibration. The ideal state detection signal is: the value of the signal during stable operation is significantly different from the value when it is about to work unstably, and the longer the time interval from the identifiable signal to the complete instability, the better, which can be used as an alarm signal to indicate the occurrence of an unstable working state.

[0023] It should be noted that for gas turbine compressor components, considering the starting position of the unstable working state and the complex external pipeline structure that severely limits the sensor installation position, and considering factors such as test safety, in the engineering test, the pressure signal (pulsating total pressure) at the compressor inlet is selected, that is, the pulsating total pressure on the test inlet flow tube is selected as the online detection parameter of the test status of the gas turbine compressor components.

[0024] It should be noted that the present application does not limit the specific method for obtaining the first pressure signal and the second pressure signal at the inlet of the gas turbine compressor to be detected, and they can be selected according to actual conditions.

[0025] Optionally, two dynamic probes can be symmetrically arranged in advance in the test section of the gas turbine compressor inlet to be tested, wherein one dynamic probe collects the first initial pressure signal of the gas turbine compressor inlet to be tested, and the other dynamic probe collects the second initial pressure signal of the gas turbine compressor inlet to be tested.

[0026] Optionally, for the first initial pressure signal, a simple resistor-capacitor hardware filtering circuit can be used to process the collected first initial pressure signal to limit the frequency band of the first initial pressure signal to a certain extent, filter out the high-frequency part outside the analysis frequency range, and prevent frequency aliasing in the subsequent sampling process. The signal after hardware filtering is sampled according to a certain sampling frequency. Although the sampled signal has undergone hardware filtering, there may still be some residual noise or unnecessary frequency components. The signal can be further processed using a digital real-time filtering method to obtain the first pressure signal.

[0027] S102 : Acquire a first frequency domain eigenvalue and a first time domain eigenvalue of the first pressure signal and a second frequency domain eigenvalue and a second time domain eigenvalue of the second pressure signal.

[0028] It should be noted that the specific process of obtaining the first frequency domain eigenvalue of the first pressure signal is the same as that of obtaining the second frequency domain eigenvalue of the second pressure signal, and the specific process of obtaining the first time domain eigenvalue of the first pressure signal is the same as that of obtaining the second time domain eigenvalue of the second pressure signal.

[0029] In an embodiment of the present application, for any pressure signal among the first pressure signal and the second pressure signal, feature extraction is performed on any pressure signal to obtain any pressure signal feature, and any pressure signal feature is normalized to obtain any target pressure signal feature, and based on any target pressure signal feature, frequency domain feature value and time domain feature value of any pressure signal are obtained.

[0030] For example, for the first pressure signal, the Db8 orthogonal wavelet basis function can decompose the first pressure signal into a low-frequency approximate signal A and a high-frequency detail signal D at different scales. Different scales have different time and frequency resolutions, such as Figure 2 As shown, the first pressure signal is decomposed into N layers, and the approximate signal A is further decomposed in each layer, while the detail signal D is not considered. The decomposition relationship is S = An + Dn + ... + D2 + D1. The low-frequency part containing the main frequency components of the signal (i.e., the low-frequency approximate signal A of each layer) is analyzed. n ), the low-frequency approximate signal reflects the main trends and characteristics of the first pressure signal. By analyzing the amplitude changes, the characteristic signal related to the compressor operating state can be extracted to obtain the characteristics of the first pressure signal.

[0031] It should be noted that, because the amplitude of the collected pressure signal may vary greatly under different compressor operating conditions, if normalization is not performed, the results of subsequent test conditions will often be inaccurate.

[0032] For example, for the first pressure signal feature, the first pressure signal feature is normalized to the same level to eliminate inaccurate results of subsequent test states caused by differences in operating states, so that subsequent warning thresholds are selected uniformly.

[0033] In an embodiment of the present application, the total window length and window sliding step of any pressure signal can be obtained, the length of the analysis window and the length of the reference window of any pressure signal and the time interval between the analysis window and the reference window can be obtained, and the characteristics of any target pressure signal can be divided according to the total window length, the window sliding step, the length of the analysis window, the length of the reference window and the time interval, and the first target pressure signal characteristics in each divided analysis window and the second target pressure signal characteristics in the reference window are obtained, and based on the first target pressure signal characteristics and the second target pressure signal characteristics, the frequency domain characteristic values ​​and time domain characteristic values ​​of any pressure signal are obtained.

[0034] S103 : Determine a first test state of the gas turbine compressor to be tested according to the first frequency domain eigenvalue and the first warning threshold and the first time domain eigenvalue and the second warning threshold.

[0035] The first warning threshold and the second warning threshold can be preset.

[0036] In an embodiment of the present application, the first frequency domain eigenvalue and the first warning threshold as well as the first time domain eigenvalue and the second warning threshold can be compared. In response to the first frequency domain eigenvalue being less than or equal to the first warning threshold and the first time domain eigenvalue being less than or equal to the first warning threshold, the first test state is determined to be a normal state. In response to the first frequency domain eigenvalue being greater than the first warning threshold and the first time domain eigenvalue being greater than the first warning threshold, the first test state is determined to be a warning state.

[0037] S104 : Determine a second test state of the gas turbine compressor to be tested based on the second frequency domain eigenvalue and the first warning threshold and the second time domain eigenvalue and the second warning threshold.

[0038] In an embodiment of the present application, the second frequency domain eigenvalue and the first warning threshold as well as the second time domain eigenvalue and the second warning threshold can be compared. In response to the second frequency domain eigenvalue being less than or equal to the first warning threshold and the second time domain eigenvalue being less than or equal to the first warning threshold, the second test state is determined to be a normal state. In response to the second frequency domain eigenvalue being greater than the first warning threshold and the second time domain eigenvalue being greater than the first warning threshold, the second test state is determined to be a warning state.

[0039] S105: Determine a target test state of the gas turbine compressor to be tested based on the first test state and the second test state.

[0040] In the embodiment of the present application, after the first test state and the second test state are acquired, the target test state of the gas turbine compressor to be inspected can be determined based on the first test state and the second test state.

[0041] For example, in response to the first test state and the second test state being both normal states, it is determined that the target test state of the gas turbine compressor to be inspected is the normal state.

[0042] The present application provides a method for detecting the test state of a gas turbine compressor. The method obtains a first pressure signal and a second pressure signal at the inlet of a gas turbine compressor to be detected, obtains a first frequency domain eigenvalue and a first time domain eigenvalue of the first pressure signal, and a second frequency domain eigenvalue and a second time domain eigenvalue of the second pressure signal, determines a first test state of the gas turbine compressor to be detected based on the first frequency domain eigenvalue and a first warning threshold as well as the first time domain eigenvalue and the second warning threshold, determines a second test state of the gas turbine compressor to be detected based on the second frequency domain eigenvalue and the first warning threshold as well as the second time domain eigenvalue and the second warning threshold, and determines a target test state of the gas turbine compressor to be detected based on the first test state and the second test state. Thus, the present application determines the target test state of the gas turbine compressor to be detected based on the first test state and the second test state, thereby improving the accuracy and reliability of determining the target test state of the gas turbine compressor to be detected. Based on the target test state, the safety of the gas turbine compressor test can be effectively monitored.

[0043] Figure 3 A flow chart of a method for detecting the test status of a gas turbine compressor provided in an embodiment of the present application.

[0044] like Figure 3 As shown, the method for detecting the test state of a gas turbine compressor proposed in this embodiment specifically includes the following steps:

[0045] S301: Acquire a first pressure signal and a second pressure signal at an inlet of a compressor of a gas turbine to be tested.

[0046] S302 : Acquire a first frequency domain eigenvalue and a first time domain eigenvalue of the first pressure signal and a second frequency domain eigenvalue and a second time domain eigenvalue of the second pressure signal.

[0047] In an embodiment of the present application, the first target pressure signal characteristics and the second target pressure signal characteristics are respectively subjected to multiplication and accumulation wavelet decomposition and convolution operations to obtain the first energy in each divided analysis window and the second energy in the reference window, and the ratio between the first energy in the analysis window and the second energy in the reference window is used as the frequency domain characteristic value of any pressure signal.

[0048] For example, for the first frequency domain eigenvalue, such as Figure 4 As shown, the horizontal data is a set of 8 first target pressure signal characteristic data acquisition values ​​(D0~D7), and the vertical data is a set of filter coefficients corresponding to the same width (LO_D0~LO_D7). The two sets of data are calculated in one cycle (A0~A7). Each time the horizontal data is calculated, the horizontal data is calculated according to the Figure 4 As shown, it is updated from front to back, and the longitudinal data moves cyclically as shown in 4. Finally, the transverse data and the longitudinal data are multiplied and added accordingly to obtain the processing results (B0~B7) to obtain the first energy in the analysis window and the second energy in the reference window each time. The ratio between the first energy in the analysis window and the second energy in the reference window is used as the first frequency domain eigenvalue of the first pressure signal.

[0049] It should be noted that the specific process of obtaining the second frequency domain eigenvalue of the second pressure signal is the same as the specific process of obtaining the first frequency domain eigenvalue, and will not be repeated here.

[0050] In an embodiment of the present application, based on the first target pressure signal characteristics, the first variance value within each divided analysis window is determined, and based on the second target pressure signal characteristics, the second variance value within each divided reference window is determined, and the ratio between the first variance value within the analysis window and the second variance value within the reference window is used as the time domain characteristic value of any pressure signal.

[0051] S303: Determine a first test state of the gas turbine compressor to be tested according to the first frequency domain eigenvalue and the first warning threshold and the first time domain eigenvalue and the second warning threshold.

[0052] S304: Determine a second test state of the gas turbine compressor to be tested based on the second frequency domain eigenvalue and the first warning threshold and the second time domain eigenvalue and the second warning threshold.

[0053] S305 : In response to the first test state and the second test state being both normal states, determining that the target test state of the gas turbine compressor to be tested is a normal state.

[0054] It should be noted that, in response to the target test state of the gas turbine compressor to be tested being a normal state, the first pressure signal and the second pressure signal at the inlet of the gas turbine compressor to be tested can continue to be collected, and the test state of the gas turbine compressor can continue to be tested based on the collected first pressure signal and second pressure signal.

[0055] S306: In response to one of the first test state and the second test state being in a warning state, determine that the target test state of the gas turbine compressor to be inspected is a warning state.

[0056] In an embodiment of the present application, in response to the target test state of the gas turbine compressor to be tested being a warning state, a warning prompt message may be generated.

[0057] S307 : In response to the first test state and the second test state being both in the warning state, determining that the target test state of the gas turbine compressor to be tested is an unstable state.

[0058] In an embodiment of the present application, in response to the target test state of the gas turbine compressor to be detected being an unstable state, the length of the analysis window of the first pressure signal and the second pressure signal and the length of the reference window and the time interval between the analysis window and the reference window are adjusted to re-acquire the first updated frequency domain eigenvalue and the first updated time domain eigenvalue of the first pressure signal and the second updated frequency domain eigenvalue and the second updated time domain eigenvalue of the second pressure signal, and determine the first updated test state of the gas turbine compressor to be detected based on the first updated frequency domain eigenvalue and the first warning threshold and the first updated time domain eigenvalue and the second warning threshold, and determine the second updated test state of the gas turbine compressor to be detected based on the second updated frequency domain eigenvalue and the first updated warning threshold and the second updated time domain eigenvalue and the second updated warning threshold, so as to determine the updated test state of the gas turbine compressor to be detected based on the first updated test state and the second updated test state, so as to verify the target test state of the gas turbine compressor to be detected.

[0059] Optionally, if it is determined that the updated test state of the gas turbine compressor to be tested is still in an unstable state, an alarm message may be generated, such as an audible and visual warning message, a voice warning message, and the like.

[0060] Optionally, if the first update test status is a warning status and the second update test status is a normal status, or if the first update test status is a normal status and the second update test status is a warning status, corresponding warning prompt information is generated.

[0061] In summary, the method for detecting the test state of a gas turbine compressor provided in the present application obtains a first pressure signal and a second pressure signal at the inlet of the gas turbine compressor to be detected, obtains a first frequency domain eigenvalue and a first time domain eigenvalue of the first pressure signal and a second frequency domain eigenvalue and a second time domain eigenvalue of the second pressure signal, determines a first test state of the gas turbine compressor to be detected based on the first frequency domain eigenvalue and the first warning threshold as well as the first time domain eigenvalue and the second warning threshold, determines a second test state of the gas turbine compressor to be detected based on the second frequency domain eigenvalue and the first warning threshold as well as the second time domain eigenvalue and the second warning threshold, and in response to the first test state and the second test state being both normal states, determines that the target test state of the gas turbine compressor to be detected is a normal state, and in response to the first test state One of the test states in the first and second test states is a warning state, and the target test state of the gas turbine compressor to be tested is determined to be a warning state. In response to the first test state and the second test state being both warning states, the target test state of the gas turbine compressor to be tested is determined to be an unstable state. Therefore, the present application obtains two pressure signals and performs cross-discrimination based on the two pressure signals to obtain the detection result of the gas turbine compressor test state, thereby improving the detection speed of the gas turbine compressor test state, and can obtain the target test state of the gas turbine compressor more accurately and timely. When the target test state is a warning state, a warning prompt message is generated in time, and when the target test state is an unstable state, an alarm message is generated in time, which can effectively monitor the safety of the gas turbine compressor test.

[0062] In order to implement the above embodiment, this embodiment provides a device for detecting the test state of a gas turbine compressor. Figure 5 A schematic structural diagram of a gas turbine compressor test status detection device provided in an embodiment of the present application.

[0063] like Figure 5 As shown, the gas turbine compressor test state detection device 1000 includes: a first acquisition module 110 , a second acquisition module 120 , a third acquisition module 130 and a correction module 140 .

[0064] A first acquisition module 110 is configured to acquire a first pressure signal and a second pressure signal at an inlet of a compressor of a gas turbine to be detected;

[0065] A second acquisition module 120 is configured to acquire a first frequency domain eigenvalue and a first time domain eigenvalue of the first pressure signal and a second frequency domain eigenvalue and a second time domain eigenvalue of the second pressure signal;

[0066] A first determining module 130 is configured to determine a first test state of the gas turbine compressor to be tested based on the first frequency domain characteristic value and the first warning threshold and the first time domain characteristic value and the second warning threshold;

[0067] a second determining module 140, configured to determine a second test state of the gas turbine compressor to be tested based on the second frequency domain characteristic value and the first warning threshold, and the second time domain characteristic value and the second warning threshold;

[0068] The third determining module 150 is configured to determine a target test state of the gas turbine compressor to be tested based on the first test state and the second test state.

[0069] In one embodiment of the present application, the second acquisition module 120 is further used to: perform feature extraction on any pressure signal among the first pressure signal and the second pressure signal to obtain any pressure signal feature, and normalize the any pressure signal feature to obtain any target pressure signal feature; and obtain frequency domain feature values ​​and time domain feature values ​​of any pressure signal based on any target pressure signal feature.

[0070] In one embodiment of the present application, the second acquisition module 120 is further used to: obtain the total window length and window sliding step of any pressure signal; obtain the length of the analysis window and the length of the reference window of any pressure signal and the time interval between the analysis window and the reference window; divide the characteristics of any target pressure signal according to the total window length, the window sliding step, the length of the analysis window, the length of the reference window and the time interval, and obtain the first target pressure signal characteristics in each divided analysis window and the second target pressure signal characteristics in the reference window; based on the first target pressure signal characteristics and the second target pressure signal characteristics, obtain the frequency domain characteristic value and the time domain characteristic value of any pressure signal.

[0071] In one embodiment of the present application, the second acquisition module 120 is further used to: perform multiplication and accumulation wavelet decomposition and convolution operations on the first target pressure signal characteristics and the second target pressure signal characteristics, respectively, to obtain the first energy in the analysis window and the second energy in the reference window for each division; and use the ratio between the first energy in the analysis window and the second energy in the reference window as the frequency domain characteristic value of any pressure signal.

[0072] In one embodiment of the present application, the second acquisition module 120 is further used to: determine the first variance value within the analysis window divided each time based on the first target pressure signal characteristics, and determine the second variance value of the reference window divided each time based on the second target pressure signal characteristics; and use the ratio between the first variance value within the analysis window and the second variance value within the reference window as the time domain characteristic value of any pressure signal.

[0073] In one embodiment of the present application, the device 1000 is further used to: for any frequency domain eigenvalue of the first frequency domain eigenvalue and the second frequency domain eigenvalue and any time domain eigenvalue of the second time domain eigenvalue, compare the any frequency domain eigenvalue with the first warning threshold and compare the any time domain eigenvalue with the second warning threshold; in response to any frequency domain eigenvalue being less than or equal to the first warning threshold and any time domain eigenvalue being less than or equal to the first warning threshold, determine that any test state of the first test state and the second test state is a normal state, or; in response to any frequency domain eigenvalue being greater than the first warning threshold and any time domain eigenvalue being greater than the first warning threshold, determine that any test state of the first test state and the second test state is a warning state.

[0074] In one embodiment of the present application, the third determination module 150 is further used to: in response to the first test state and the second test state being both normal states, determine that the target test state of the gas turbine compressor to be tested is a normal state; in response to the presence of one of the first test state and the second test state being a warning state, determine that the target test state of the gas turbine compressor to be tested is a warning state; in response to the first test state and the second test state being both warning states, determine that the target test state of the gas turbine compressor to be tested is an unstable state.

[0075] In one embodiment of the present application, the device 1000 is further used to: in response to the target test state of the gas turbine compressor to be tested being an unstable state, adjust the length of the analysis window of the first pressure signal and the second pressure signal and the length of the reference window and the time interval between the analysis window and the reference window to verify the target test state of the gas turbine compressor to be tested.

[0076] The gas turbine compressor test state detection device provided in the present application obtains a first pressure signal and a second pressure signal at the inlet of the gas turbine compressor to be detected, obtains a first frequency domain eigenvalue and a first time domain eigenvalue of the first pressure signal, and a second frequency domain eigenvalue and a second time domain eigenvalue of the second pressure signal, determines a first test state of the gas turbine compressor to be detected based on the first frequency domain eigenvalue and a first warning threshold, as well as the first time domain eigenvalue and the second warning threshold, determines a second test state of the gas turbine compressor to be detected based on the second frequency domain eigenvalue and the first warning threshold, as well as the second time domain eigenvalue and the second warning threshold, and determines a target test state of the gas turbine compressor to be detected based on the first test state and the second test state. Thus, the present application determines the target test state of the gas turbine compressor to be detected based on the first test state and the second test state, thereby improving the accuracy and reliability of determining the target test state of the gas turbine compressor to be detected. Based on the target test state, the safety of the gas turbine compressor test can be effectively monitored.

[0077] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this application can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this application can be achieved. This is not a limitation herein.

[0078] The above specific embodiments do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles disclosed in this application shall be included in the scope of protection of this application.

Claims

1. A method for detecting the test status of a gas turbine compressor, characterized in that: The method comprises: Acquiring a first pressure signal and a second pressure signal at an inlet of a compressor of a gas turbine to be detected; Acquire a first frequency domain eigenvalue and a first time domain eigenvalue of the first pressure signal and a second frequency domain eigenvalue and a second time domain eigenvalue of the second pressure signal; determining a first test state of the gas turbine compressor to be tested based on the first frequency domain eigenvalue and the first warning threshold and the first time domain eigenvalue and the second warning threshold; determining a second test state of the gas turbine compressor to be tested based on the second frequency domain eigenvalue and the first warning threshold and the second time domain eigenvalue and the second warning threshold; Based on the first test state and the second test state, a target test state of the gas turbine compressor to be tested is determined.

2. The method according to claim 1, characterized in that The method further comprises: For any one of the first pressure signal and the second pressure signal, perform feature extraction on the any one pressure signal to obtain any pressure signal feature, and normalize the any one pressure signal feature to obtain any target pressure signal feature; Based on any target pressure signal feature, a frequency domain feature value and a time domain feature value of the any pressure signal are obtained.

3. The method according to claim 2, characterized in that The acquiring, based on any target pressure signal feature, a frequency domain feature value and a time domain feature value of any pressure signal, includes: Obtaining a total window length and a window sliding step length of any pressure signal; Acquire the length of the analysis window and the length of the reference window of any one of the pressure signals and the time interval between the analysis window and the reference window; Dividing any target pressure signal feature according to the total window length, the window sliding step length, the length of the analysis window, the length of the reference window, and the time interval, and obtaining a first target pressure signal feature within each divided analysis window and a second target pressure signal feature within the reference window; Based on the first target pressure signal feature and the second target pressure signal feature, a frequency domain feature value and a time domain feature value of any one of the pressure signals are obtained.

4. The method according to claim 3, characterized in that The acquiring, based on the first target pressure signal characteristic and the second target pressure signal characteristic, a frequency domain characteristic value of any one of the pressure signals, includes: Performing multiplication-accumulation wavelet decomposition and convolution operations on the first target pressure signal feature and the second target pressure signal feature respectively to obtain a first energy in each divided analysis window and a second energy in a reference window; The ratio between the first energy in the analysis window and the second energy in the reference window is used as the frequency domain characteristic value of any pressure signal.

5. The method according to claim 3, characterized in that The acquiring, based on the first target pressure signal feature and the second target pressure signal feature, a time domain feature value of any one of the pressure signals includes: determining a first variance value within each divided analysis window based on the first target pressure signal characteristic, and determining a second variance value within each divided reference window based on the second target pressure signal characteristic; The ratio between the first variance value in the analysis window and the second variance value in the reference window is used as the time domain characteristic value of any pressure signal.

6. The method according to claim 1, characterized in that The method further comprises: For any frequency domain eigenvalue of the first frequency domain eigenvalue and the second frequency domain eigenvalue and any time domain eigenvalue of the second time domain eigenvalue and the second time domain eigenvalue, compare the any frequency domain eigenvalue with the first warning threshold and compare the any time domain eigenvalue with the second warning threshold; In response to any one of the frequency domain characteristic values ​​being less than or equal to the first warning threshold, and any one of the time domain characteristic values ​​being less than or equal to the first warning threshold, determining that any one of the first test state and the second test state is a normal state, or; In response to any one of the frequency domain characteristic values ​​being greater than the first warning threshold and any one of the time domain characteristic values ​​being greater than the first warning threshold, determining any one of the first test state and the second test state as a warning state.

7. The method according to claim 1, characterized in that The determining, based on the first test state and the second test state, a target test state of the gas turbine compressor to be tested includes: In response to the first test state and the second test state being both normal states, determining that the target test state of the gas turbine compressor to be tested is a normal state; In response to one of the first test state and the second test state being in a warning state, determining that a target test state of the gas turbine compressor to be inspected is a warning state; In response to the first test state and the second test state being both warning states, it is determined that the target test state of the gas turbine compressor to be tested is an unstable state.

8. The method according to claim 7, characterized in that The method further comprises: In response to the target test state of the gas turbine compressor to be tested being an unstable state, the length of the analysis window of the first pressure signal and the second pressure signal, the length of the reference window, and the time interval between the analysis window and the reference window are adjusted to verify the target test state of the gas turbine compressor to be tested.

9. A gas turbine compressor test status detection device, characterized in that: The device comprises: A first acquisition module is used to acquire a first pressure signal and a second pressure signal of an inlet of a compressor of a gas turbine to be detected; a second acquisition module, configured to acquire a first frequency domain eigenvalue and a first time domain eigenvalue of the first pressure signal and a second frequency domain eigenvalue and a second time domain eigenvalue of the second pressure signal; a first determining module, configured to determine a first test state of the gas turbine compressor to be tested based on the first frequency domain eigenvalue and the first warning threshold and the first time domain eigenvalue and the second warning threshold; a second determining module, configured to determine a second test state of the gas turbine compressor to be tested based on the second frequency domain eigenvalue and the first warning threshold and the second time domain eigenvalue and the second warning threshold; The third determination module is configured to determine a target test state of the gas turbine compressor to be tested based on the first test state and the second test state.

10. An electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method according to any one of claims 1 to 8.

Images