Method, device, and medium for determining component degradation state of a rotating device under variable operating conditions

Abstract

The present invention relates to a method, device and medium for determining the component degradation state of a rotating device under variable working conditions. The method includes: calculating vibration spectrum baselines corresponding to different working conditions of a rotating device in a steady state based on historical vibration data and historical working condition data; obtaining a real-time spectrum of the real-time vibration data based on the acquired real-time vibration data and real-time working condition data; obtaining the vibration spectrum baseline corresponding to the real-time working condition based on the real-time working condition and the vibration spectrum baselines under the different working conditions; subtracting the vibration spectrum baseline corresponding to the real-time working condition from the real-time spectrum of the real-time vibration data to obtain a working condition-fault spectrum; and determining a frequency energy factor based on the working condition-fault spectrum for determining the component degradation state of the rotating device. Thus, the present invention can effectively and accurately evaluate the component degradation state of a rotating device under variable working conditions and in a sub-healthy state.

Description

Technical Field

[0001] The present invention generally relates to fault detection of rotating equipment, and specifically, to a method, a computing device, and a computer-readable storage medium for determining the component degradation state of a rotating equipment under varying operating conditions. Background Art

[0002] Traditional methods for determining the component degradation state of rotating equipment mainly rely on extracting frequency spectrum and time-domain features under stable operating conditions to build a degradation model. Since the features under stable operating conditions are relatively stable, the model performs well under stable operating conditions. However, the rotating equipment in current enterprises usually faces varying operating conditions. Therefore, the generalization performance of traditional methods for determining the component degradation state of rotating equipment based on stable operating conditions is poor, and it is difficult to accurately evaluate the component degradation trend of rotating equipment under varying operating conditions. In addition, existing diagnostic technologies are mainly built based on healthy rotating equipment. Since healthy equipment has no obvious characteristic frequencies in its initial state, a full-cycle evaluation model can be built. However, in actual production, due to the influence of comprehensive factors such as installation and environment, it is easy for rotating equipment to be in a sub-healthy state at the beginning (for example, this sub-healthy state means that the vibration of the rotating equipment is close to the GB or ISO standard, but certain characteristic frequency energies begin to appear in its frequency spectrum). During the process of determining the component degradation state of the rotating equipment, the influence of the initial energy concentration point will be amplified, resulting in the failure to highlight the influence of other characteristic frequency points with fast energy changes. Therefore, traditional methods for determining the component degradation state of rotating equipment cannot accurately evaluate the component degradation state of rotating equipment in a sub-healthy state.

[0003] In summary, the deficiencies of traditional methods for determining the component degradation trend of rotating equipment are as follows: they cannot accurately evaluate the component degradation state of rotating equipment under varying operating conditions and in a sub-healthy state. Summary of the Invention

[0004] In view of the above problems, the present invention provides a method, a computing device, and a computer-readable storage medium for determining the component degradation state of a rotating equipment under varying operating conditions, which can effectively and accurately evaluate the component degradation state of rotating equipment under varying operating conditions and in a sub-healthy state.

[0005] According to a first aspect of the present invention, a method for determining the degradation state of components of a rotating device under varying operating conditions is provided. The method includes: caching the acquired real-time vibration data and real-time operating condition data of the rotating device to generate historical vibration data and historical operating condition data, and thereby calculating vibration spectrum baselines corresponding to different operating conditions of the rotating device in a steady state based on the vibration data and the operating condition data; acquiring the real-time spectrum of the real-time vibration data based on the acquired real-time vibration data and real-time operating condition data; acquiring the vibration spectrum baseline corresponding to the real-time operating condition based on the real-time operating condition and the vibration spectrum baselines under the different operating conditions; subtracting the vibration spectrum baseline corresponding to the real-time operating condition from the real-time spectrum of the real-time vibration data to obtain a condition-fault spectrum; and determining a frequency energy factor based on the condition-fault spectrum for determining the degradation state of components of the rotating device.

[0006] In some embodiments, determining the change of the frequency energy factor based on the condition-fault spectrum includes: calculating the frequency energy factor corresponding to each characteristic frequency in the condition-fault spectrum based on the condition-fault spectrum; and determining the component degradation trend of the rotating device based on the change of the frequency energy factor.

[0007] In some embodiments, calculating the frequency energy factor corresponding to each characteristic frequency in the condition-fault spectrum based on the condition-fault spectrum includes: calculating the frequency energy proportion and the frequency energy change rate corresponding to each characteristic frequency in the condition-fault spectrum based on the condition-fault spectrum; and calculating the frequency energy factor corresponding to each characteristic frequency based on the frequency energy proportion and the frequency energy change rate.

[0008] In some embodiments, calculating the frequency energy factor corresponding to each characteristic frequency based on the frequency energy proportion and the frequency energy change rate includes: multiplying the frequency energy proportion and the frequency energy change rate to obtain the frequency energy factor corresponding to each characteristic frequency.

[0009] In some embodiments, calculating the frequency energy proportion and the frequency energy change rate corresponding to each characteristic frequency in the condition-fault spectrum includes: calculating the frequency peak energy based on the amplitude of the condition-fault spectrum at each characteristic frequency; calculating the total frequency energy based on the sum of the squares of the amplitudes of the condition-fault spectrum under the current operating condition; and calculating the ratio of the frequency peak energy to the total frequency energy to obtain the frequency energy proportion.

[0010] In some embodiments, the frequency energy ratio and the frequency energy change rate corresponding to each characteristic frequency in the calculation condition-fault spectrum include: caching the frequency energy under a predetermined condition calculated to obtain a frequency energy sequence corresponding to the predetermined condition; and based on the frequency energy sequence, constructing a linear model of time and frequency energy to calculate the slope of the change of the frequency energy sequence corresponding to the predetermined condition, so as to obtain the frequency energy change rate.

[0011] In some embodiments, determining the component degradation state of a rotating device includes: calculating the mean and standard deviation of multiple frequency energy factors under a predetermined condition at the current time; calculating a frequency energy factor threshold based on the mean and standard deviation; screening the frequency energy factors exceeding the frequency energy factor threshold; and based on the characteristic frequencies corresponding to the frequency energy factors exceeding the frequency energy factor threshold and the corresponding relationship between the characteristic frequencies and the component failures of the rotating device, determining the degradation state of the components of the rotating device.

[0012] In some embodiments, calculating the vibration spectrum baseline under different conditions of a rotating device corresponding to a steady state includes: respectively generating a vibration spectrum sequence and a condition data sequence of the rotating device under a steady state based on the historical vibration data and historical condition data, where the vibration spectrum sequence indicates the correspondence between time and the vibration spectrum, and the condition data sequence indicates the correspondence between time and the condition data; for each condition, calculating the vibration spectra of all detection positions to obtain the mean value of the vibration spectra of all detection positions corresponding to each condition; and based on the mean value, generating the vibration spectrum baseline under different conditions of the rotating device under a steady state.

[0013] In some embodiments, determining the component degradation trend of a rotating device based on the change of the frequency energy factor includes: for different conditions at the current time point, determining the frequency energy factors exceeding the frequency energy factor threshold; performing weighted summation on the frequency energy factors exceeding the frequency energy factor threshold to obtain the weighted frequency energy factors corresponding to different conditions at the current time point; sorting the weighted frequency energy factors corresponding to different conditions to determine the most likely component failure category under different conditions at the current time point based on the sorting result; for multiple historical time points, respectively calculating the weighted frequency energy factors corresponding to each condition to construct a time series-frequency energy factor prediction model for each condition based on the weighted frequency energy factors corresponding to each condition at the current time point and multiple historical time points; and based on the time series-frequency energy factor prediction model for each condition, predicting the weighted frequency energy factors corresponding to each condition at a future time point to determine the most likely component failure category under each condition at the future time point.

[0014] According to a second aspect of the present invention, there is provided a computing device, the computing device comprising: at least one processing unit; at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions when executed by the at least one processing unit causing the device to perform the steps of the method according to the first aspect.

[0015] According to a third aspect of the present invention, there is provided a computer-readable storage medium having stored thereon a computer program, which when executed by a machine implements the method according to the first aspect.

[0016] The summary of the invention is provided to introduce a selection of concepts in a simplified form, which will be further described in the detailed description below. The summary of the invention is not intended to identify the key features or main features of the present invention, nor is it intended to limit the scope of the present invention. Brief Description of the Drawings

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings according to the provided drawings without creative efforts.

[0018] Figure 1 A schematic diagram showing a system for implementing a method for determining the component degradation state of a rotating device under variable operating conditions according to an embodiment of the present invention is shown.

[0019] Figure 2 A flowchart showing a method for determining the component degradation state of a rotating device under variable operating conditions according to an embodiment of the present invention is shown.

[0020] Figure 3 Schematically shown are the vibration spectrum and the fault spectrum of a rotating device under steady state according to an embodiment of the present invention.

[0021] Figure 4 Schematically shown are the vibration spectrum and the fault spectrum of a rotating device in a fault state according to an embodiment of the present invention.

[0022] Figure 5 A flowchart showing a method for determining the degradation state of components of a rotating device according to an embodiment of the present invention is illustrated.

[0023] Figure 6 A flowchart showing a method for determining the most likely component fault category under each operating condition at a future time point according to an embodiment of the present invention is illustrated.

[0024] Figure 7 A schematic diagram showing the change trend of different component weighted frequency energy factors according to an embodiment of the present invention.

[0025] Figure 8 A block diagram of an electronic device suitable for implementing an embodiment of the present invention is schematically shown. Detailed implementation manners

[0026] Preferred embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the preferred embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure will be more thorough and complete, and can fully convey the scope of the present disclosure to those skilled in the art.

[0027] The term "including" and its variants used herein mean open inclusion, i.e., "including but not limited to". Unless otherwise specified, the term "or" means "and / or". The term "based on" means "at least partially based on". The term "an example embodiment" and "an embodiment" mean "at least one example embodiment". The term "another embodiment" means "at least one additional embodiment". The terms "first", "second", etc. may refer to different or the same objects.

[0028] As described above, the disadvantage of the traditional method for determining the component degradation state of a rotating device is that it cannot accurately evaluate the component degradation state of a rotating device under variable working conditions and sub-healthy states.

[0029] To at least partially solve one or more of the above problems and other potential problems, the present invention proposes a method for determining the component degradation state of a rotating device under variable operating conditions. In the solution of the present invention, by calculating the vibration spectrum baseline corresponding to different operating conditions of the rotating device under steady state based on historical vibration data and operating condition data, the present invention can not only effectively correct the influence of different operating conditions on the vibration spectrum, improve the applicability and generalization for rotating devices under variable operating conditions; but also obtain the original spectrum of the vibration spectrum of the rotating device under steady state. In addition, by obtaining the real-time spectrum of the real-time vibration data based on the obtained real-time vibration data and real-time operating condition data; obtaining the vibration spectrum baseline corresponding to the operating condition based on the real-time operating condition and the vibration spectrum baselines under different operating conditions; and subtracting the vibration spectrum baseline from the real-time spectrum of the real-time vibration data to obtain the operating condition-fault spectrum, the present invention can effectively eliminate the influence of the sub-healthy state and reduce the influence of the main energy in the original spectrum, thereby highlighting the change of the frequency components in the original spectrum diagram. Furthermore, by determining the frequency energy factor based on the operating condition-fault spectrum for determining the component degradation state of the rotating device, the present invention can accurately evaluate the component degradation state of the rotating device through the dimension of the change of the frequency energy. Therefore, the present invention can effectively correct the influence of variable operating conditions and sub-healthy states on the evaluation of the component degradation state of the rotating device, and thus can effectively and accurately evaluate the component degradation trend of the rotating device under variable operating conditions and sub-healthy states.

[0030] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments, and they should not be construed as limiting the protection scope of the present application. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0031] Figure 1 FIG. shows a schematic diagram of a system 100 for implementing a method for determining the component degradation state of a rotating device under variable operating conditions according to an embodiment of the present invention. As Figure 1 shown, the system 100 includes: a computing device 110, a rotating device 130, and an acceleration sensor 140.

[0032] Regarding the rotating device 130, it is, for example but not limited to, a pump (such as a variable-frequency drive pump or a power-frequency drive pump to be detected), a motor, a bearing, or a generator, etc.

[0033] Regarding the acceleration sensor 140 (e.g., a triaxial acceleration sensor or a uniaxial sensor), it collects acceleration waveform data at various detection positions of the rotating device. Taking a pump as an example, the various detection positions of the rotating device include but are not limited to: the non-drive end detection position of the pump, the drive end detection position of the pump, the drive end detection position of the motor, and the non-drive end detection position of the motor. The acceleration waveform data for each detection position includes, for example: the acceleration waveform data in the vertical direction of the bearing, the acceleration waveform data in the horizontal direction of the bearing, and the acceleration waveform data of the axial data of the bearing.

[0034] Regarding the computing device 110, it is used to determine the component degradation state of the rotating device under varying operating conditions. Specifically, the computing device 110 is used to calculate the vibration spectrum baselines under different operating conditions corresponding to the steady-state rotating device; and based on the acquired real-time vibration data and real-time operating condition data, obtain the real-time spectrum of the real-time vibration data. The computing device 110 is also used to obtain the vibration spectrum baseline corresponding to the real-time operating condition based on the real-time operating condition and the vibration spectrum baselines under the different operating conditions; subtract the vibration spectrum baseline corresponding to the real-time operating condition from the real-time spectrum of the real-time vibration data to obtain the operating condition-fault spectrum; and based on the operating condition-fault spectrum, determine the frequency energy factor to be used to determine the component degradation state of the rotating device. In some embodiments, the computing device 110 is also used to determine the component degradation trend of the rotating device under varying operating conditions.

[0035] In some embodiments, the computing device 110 may have one or more processing units, including dedicated processing units such as GPUs, FPGAs, and ASICs, as well as general-purpose processing units such as CPUs. Additionally, one or more virtual machines may also be running on each computing device. The computing device 110 includes, for example: a steady-state vibration spectrum baseline calculation unit 112, a real-time spectrum acquisition unit 114, a vibration spectrum baseline acquisition unit 116 corresponding to the real-time operating condition, an operating condition-fault spectrum obtaining unit 118, and a component degradation state determination unit 120. The above-mentioned steady-state vibration spectrum baseline calculation unit 112, real-time spectrum acquisition unit 114, vibration spectrum baseline acquisition unit 116 corresponding to the real-time operating condition, operating condition-fault spectrum obtaining unit 118, and component degradation state determination unit 120 may be configured on one or more computing devices 110.

[0036] Regarding the steady-state vibration spectrum baseline calculation unit 112, it is used to cache the acquired real-time vibration data and real-time operating condition data of the rotating device to generate historical vibration data and historical operating condition data, and thus calculate the vibration spectrum baselines under different operating conditions corresponding to the steady-state rotating device based on the historical vibration data and historical operating condition data.

[0037] Regarding the real-time spectrum acquisition unit 114, it is configured to obtain the real-time spectrum of the real-time vibration data based on the acquired real-time vibration data and real-time operating condition data.

[0038] Regarding the vibration spectrum baseline acquisition unit 116 corresponding to the real-time operating condition, it is configured to obtain the vibration spectrum baseline corresponding to the real-time operating condition based on the real-time operating condition and the vibration spectrum baselines under different operating conditions.

[0039] Regarding the operating condition-fault spectrum acquisition unit 118, it is configured to subtract the vibration spectrum baseline corresponding to the real-time operating condition from the real-time spectrum of the real-time vibration data to obtain the operating condition-fault spectrum.

[0040] Regarding the component degradation state determination unit 120, it is configured to determine the frequency energy factor based on the operating condition-fault spectrum for determining the component degradation state of the rotating equipment.

[0041] Figure 2 The flowchart of a method 200 for determining the component degradation state of a rotating equipment under variable operating conditions according to an embodiment of the present invention is shown. It should be understood that the method 200 can be executed, for example, at the Figure 8 described electronic device 800. It can also be executed at the Figure 1 described computing device 110. It should be understood that the method 200 may further include additional actions not shown and / or may omit the shown actions, and the scope of the present invention is not limited in this regard.

[0042] At step 202, the computing device 110 caches the acquired real-time vibration data and real-time operating condition data of the rotating equipment to generate historical vibration data and historical operating condition data, so as to calculate the vibration spectrum baselines under different operating conditions corresponding to the steady-state rotating equipment based on the historical vibration data and historical operating condition data.

[0043] Regarding the operating condition, it includes, for example, speed, load, etc. In some embodiments, the operating condition further includes temperature, etc. For example, different speeds or different loads represent different operating conditions. It should be understood that the operating conditions of the present invention are multiple and can be enumerated.

[0044] It should be understood that rotating equipment generally includes at least a shaft and a rotor (or rotating part). Under different operating conditions, there are differences in the rotational speed and load of the rotating equipment, and its vibration spectrum may also be different. Taking the rotational speed as an example, the shaft may cause resonance at different rotational speeds, especially when starting rotation (for example, when starting a pump). When the rotational speed of the shaft reaches a certain value, its vibration will increase significantly; if the rotational speed exceeds this value, its vibration will decrease significantly. Thus, it can be seen that the rotational speed has a relevant impact on the vibration of rotating equipment. Taking the load as another example, for instance, when a pump is working, liquid vaporization will occur at the inlet of the impeller due to a certain vacuum pressure. Under the impact of liquid particles, the vaporized bubbles will cause spalling on the metal surfaces such as the impeller, thereby damaging the metal such as the impeller, that is, cavitation occurs. At this time, the vacuum pressure is the vaporization pressure. It can be seen that under different loads, there are also relevant impacts on the vibration of rotating equipment and the degradation of components. Therefore, constructing vibration spectrum baselines under different operating conditions can be effectively used to correct the influence of different operating conditions on the spectrum.

[0045] Regarding the method for obtaining vibration spectrum baselines under different operating conditions corresponding to a rotating equipment in a steady state, for example, it includes: calculating that the device 110 generates a vibration spectrum sequence and a working condition data sequence of the rotating equipment in a steady state respectively based on the historical vibration data and historical working condition data. The vibration spectrum sequence indicates the corresponding relationship between time and the vibration spectrum, and the working condition data sequence indicates the corresponding relationship between time and the working condition data; for each working condition, calculating the vibration spectra of all detection positions to obtain the mean value of the vibration spectra of all detection positions corresponding to each working condition; generating vibration spectrum baselines under different operating conditions of the rotating equipment in a steady state based on the mean value.

[0046] Regarding real-time vibration data, for example, it is obtained from the acceleration waveform data of each detection position of a triaxial acceleration sensor. Each detection position includes, for example: the non-driving end measuring point of the pump, the driving end measuring point of the pump, the driving end measuring point of the motor, and the non-driving end measuring point of the motor. The acceleration waveform data for each detection position includes, for example: the acceleration waveform data in the vertical direction of the bearing, the acceleration waveform data in the horizontal direction of the bearing, and the acceleration waveform data in the axial direction of the bearing. The sampling period of the real-time vibration data is, for example, not less than 30 minutes each time.

[0047] Regarding the method for caching real-time vibration data, for example, it includes: caching the real-time vibration data during the operation of the rotating equipment within a predetermined buffer period obtained, so as to form a vibration data sequence based on the cached real-time vibration data (i.e., historical vibration data). The predetermined buffer period is, for example, but not limited to, greater than or equal to 2 weeks.

[0048] The following expression (1) exemplifies the vibration data sequence.

[0049] (1).

[0050] In the above expression (1), represents the vibration acceleration at the m-th detection position. represents the time at the n-th time point.

[0051] Regarding the method for caching condition data, for example, it includes: caching the condition data during the operation of rotating equipment within a predetermined buffer period obtained, so as to form a condition data sequence based on the cached condition data. The predetermined buffer period is, for example but not limited to, greater than or equal to 2 weeks.

[0052] The following expression (2) exemplifies the condition data sequence.

[0053] (2).

[0054] In the above expression (2), represents the k-th condition. represents the time at the n-th time point.

[0055] Regarding the method for signal processing of the vibration data sequence to obtain the spectrum of real-time vibration data, it will be described below in conjunction with formulas (3) to (6). The following formulas (3) to (6) schematically show the algorithm for signal transformation of the vibration acceleration signal. Among them, formula (3) schematically shows the calculation method of the vibration acceleration signal at any frequency.

[0056] (3).

[0057] In the above formula (3), represents the Fourier component of the vibration acceleration signal at frequency ; A represents the corresponding coefficient. j represents the imaginary number. represents the frequency. t represents the time.

[0058] The following formula (4) schematically shows: when the initial velocity component is 0, the velocity signal component obtained by performing time-domain integration on the vibration acceleration signal component.

[0059] (4).

[0060] In the above formula (4), represents the velocity signal component. V represents the corresponding coefficient. represents the acceleration signal component. represents the integration variable with respect to the acceleration signal component to be integrated. A tiny increment of the integral variable representing the acceleration signal component.

[0061] The following formula (5) schematically shows the displacement signal component obtained by performing two-time time-domain integration on the acceleration signal component when both the initial velocity and the initial displacement components are 0.

[0062] (5).

[0063] In the above formula (5), represents the Fourier component of the displacement signal at frequency ; X represents the corresponding coefficient. represents the acceleration signal component. represents the integral variable with respect to the to be integrated (i.e., the velocity signal component). represents the integral variable of the velocity signal component tiny increment.

[0064] For the signal transformation of the spectrum in the present invention, the fast Fourier transform is mainly adopted, and this method is a fast algorithm of the discrete Fourier transform. The following formula (4) schematically shows the algorithm of the discrete Fourier transform.

[0065] (6).

[0066] In the above formula (6), represents the amplitude and phase information of the sine and cosine components at frequency ; represents the nth point in the discrete time series. N represents the length of the sequence.

[0067] Regarding the vibration spectrum sequence of the rotating equipment under steady state, the following expression (7) schematically shows the vibration spectrum sequence of the rotating equipment under steady state.

[0068] (7).

[0069] In the above expression (7), represents the vibration spectrum at the mth detection position. represents the time at the nth time point. represents the vibration spectrum corresponding to the time at the nth time point and from the 1st to the mth detection positions.

[0070] Regarding the corresponding relationship between the operating conditions and the vibration spectrum of the rotating equipment under steady state. The following expression (8) schematically shows it.

[0071] (8).

[0072] In the above expression (8), represents the vibration spectrum at the m-th detection position. represents the time at the n-th time point. represents the k-th working condition.

[0073] It should be understood that each working condition corresponds to multiple vibration spectra. Therefore, the computing device 110 obtains multiple sets of vibration spectra corresponding to each working condition. The following expression (9) schematically shows multiple sets of vibration spectra corresponding to one working condition.

[0074] (9).

[0075] In the above expression (9), represents the vibration spectrum at the m-th detection position. represents the time at the i-th time point. represents the k-th working condition corresponding to the i-th time point. represents the time points covered by this working condition, and the corresponding multiple sets of vibration spectra (i.e., the vibration spectra at the 1st to the m-th detection positions).

[0076] For example, the following expression (10) schematically shows the vibration spectrum baseline corresponding to one working condition.

[0077] (10).

[0078] In the above expression (10), represents the working condition the mean value of the vibration spectrum at the m-th detection position corresponding to. m represents the m-th detection position. represents the time at the i-th time point. represents the k-th working condition corresponding to the i-th time point. represents the working condition the corresponding vibration spectrum baseline.

[0079] At step 204, the computing device 110 obtains the real-time spectrum of the real-time vibration data based on the acquired real-time vibration data and real-time working condition data.

[0080] For example, the computing device 110 obtains the real-time vibration data and real-time working condition data of the rotating device at the current time; performs signal processing based on the acquired vibration data and working condition data at the current time to generate a vibration spectrum regarding the real-time vibration data.

[0081] Regarding the method of generating the vibration spectrum of the real-time vibration data, the computing device 110 adopts, for example, the method shown in the above-mentioned formulas (3) to (7), which will not be described in detail here.

[0082] At step 206 , the computing device 110 acquires a vibration spectrum baseline corresponding to the real-time operating condition based on the real-time operating condition and the vibration spectrum baselines under the different operating conditions.

[0083] The computing device 110 queries the vibration spectrum baselines under different working conditions of the rotating equipment in a steady state based on the real-time working condition, so as to obtain the vibration spectrum baseline corresponding to the real-time working condition.

[0084] At step 208 , the computing device 110 subtracts the vibration spectrum baseline corresponding to the real-time operating condition from the real-time spectrum of the real-time vibration data to obtain an operating condition-fault spectrum.

[0085] For example, the computing device 110 calculates the difference between the real-time spectrum of the acquired real-time vibration data and the acquired vibration spectrum baseline corresponding to the real-time operating condition, and takes an absolute value of the calculated difference to obtain the operating condition-fault spectrum.

[0086] For example, Figure 3 The vibration spectrum and fault spectrum of the rotating equipment in a steady state according to an embodiment of the present invention are schematically shown. Figure 3 The mark 310 in the middle indicates the original vibration spectrum of the rotating device in a steady state, in which the first, second and third frequencies are relatively high. The mark 312 indicates the vibration spectrum of the real-time (for example, at a certain time) vibration data of the rotating device in a steady state, in which the first, second and third frequencies are also relatively high. The vibration spectrum on the right side indicated by the mark 320 is the fault spectrum of the rotating device in a steady state. The fault spectrum 320 of the rotating device in a steady state shows a lot of noise, and no obvious energy peak is seen, in which the first, second and third frequencies are eliminated.

[0087] For another example, Figure 4 The vibration spectrum and fault spectrum of the rotating equipment under the fault state according to the embodiment of the present invention are schematically shown. Figure 4 The mark 410 indicates the original vibration spectrum of the rotating device in the fault state, and the mark 412 indicates the vibration spectrum of the real-time (for example, at a certain time) vibration data of the rotating device in the fault state. The mark 420 indicates the fault spectrum of the rotating device in the fault state. Figure 4 As shown, in addition to the rotation frequency peak, other frequency peaks appear in the fault spectrum 420 of the rotating equipment in the fault state, which indicates that the rotating equipment has an abnormality at this characteristic frequency.

[0088] Therefore, by subtracting the vibration spectrum baseline from the real-time spectrum of real-time vibration data to obtain the working condition-fault spectrum, the present invention can reduce the influence of the main energy in the original spectrum corresponding to the steady-state rotating equipment, thereby highlighting the changes in the frequency components in the vibration spectrum.

[0089] At step 210, the computing device 110 determines a frequency energy factor based on the working condition-fault spectrum for determining the component degradation state of the rotating equipment.

[0090] It should be understood that the working condition-fault spectrum shows that the evolution of the faults of the rotating equipment is related to the changes in certain specific frequencies.

[0091] Regarding the method for determining the frequency energy factor, in some embodiments, it includes, for example: the computing device 110 calculates the frequency energy proportion and the frequency energy change rate corresponding to each characteristic frequency in the working condition-fault spectrum based on the working condition-fault spectrum; and calculates the frequency energy factor corresponding to each characteristic frequency based on the frequency energy proportion and the frequency energy change rate. It should be understood that by taking into account the influence of the frequency energy proportion and the frequency energy change rate when calculating the frequency energy factor, the present invention can highlight the influence of the characteristic frequency points with fast energy changes. For example, for points with small initial energy, their change rate may be relatively fast, and with the evolution of the fault, the influence of the fault that dominates.

[0092] Regarding the calculation method of the frequency energy proportion, it includes, for example: calculating the frequency peak energy based on the amplitude of the working condition-fault spectrum at each characteristic frequency; calculating the total frequency energy based on the sum of the squares of the amplitudes of the working condition-fault spectrum under the current working condition; and calculating the ratio of the frequency peak energy to the total frequency energy to obtain the frequency energy proportion. For example, the frequency energy proportion of each characteristic frequency is obtained. The frequency energy proportion is used to characterize the energy proportion of the frequency energy of this characteristic frequency in the entire spectrum. The following formulas (11) to (13) show the algorithm for the frequency energy proportion of any characteristic frequency in the working condition-fault spectrum.

[0093] (11).

[0094] (12).

[0095] (13).

[0096] In the above formulas (11) to (13), represents the peak energy. represents the amplitude of the working condition-fault spectrum at a predetermined frequency (characteristic frequency). represents the total frequency energy. represents the frequency energy proportion.

[0097] Regarding the frequency energy change rate, it indicates how fast the frequency energy changes within a certain period of time. In some embodiments, regarding the method for obtaining the frequency energy change rate, for example, it includes: the computing device 110 caches the computed frequency energy under a predetermined operating condition to obtain a frequency energy sequence corresponding to the predetermined operating condition; and based on the frequency energy sequence, a linear model of time and frequency energy is constructed to calculate the slope of the change of the frequency energy sequence corresponding to the predetermined operating condition, thereby obtaining the frequency energy change rate.

[0098] For example, the following expression (14) shows the frequency energy sequence corresponding to a predetermined operating condition.

[0099] (14).

[0100] In the above formula (14), represents the frequency energy of time. represents time. represents the operating condition. represents the frequency energy sequence corresponding to the operating condition.

[0101] Regarding the frequency energy factor, in some embodiments, the computing device 110 can multiply the frequency energy ratio and the frequency energy change rate to obtain the frequency energy factor.

[0102] The following formula (15) shows the algorithm of the frequency energy factor.

[0103] (15).

[0104] In the above formula (15), represents the frequency energy change rate. represents the frequency energy ratio. represents the frequency energy factor.

[0105] Regarding the method for determining the component degradation state of a rotating device, in some embodiments, the computing device 110 can calculate the frequency energy factor of each frequency at each time point for each operating condition, thereby constructing a time series - frequency energy factor prediction model for each frequency energy factor under each operating condition. For example, for the operating condition the time series - frequency energy factor prediction model of the predetermined frequency under the operating condition is . It should be understood that the time series - frequency energy factor prediction model is, for example, a time series model or a linear model.

[0106] The following Table 1 shows the frequency energy factors at different times under the operating condition .

[0107] Table 1

[0108] 。

[0109] The following formula (16) shows the time - frequency energy factor prediction model under the operating conditions.

[0110] (16).

[0111] In the above formula (16), represents the operating condition. represents the frequency energy factor of the second frequency. represents the frequency energy factor of the first frequency. represents the first time point. represents the second time point. represents the frequency energy factors of each characteristic frequency at the first time point T1. represents the frequency energy factors of each characteristic frequency at the second time point T2.

[0112] In the above solution, by calculating the vibration spectrum baselines corresponding to different operating conditions of the rotating equipment under steady state based on historical vibration data and operating condition data, the present invention can not only effectively correct the influence of different operating conditions on the vibration spectrum, improve the applicability and generalization for rotating equipment under variable operating conditions; but also can obtain the original spectrum of the vibration spectrum of the rotating equipment under steady state. Additionally, by obtaining the real - time spectrum of the real - time vibration data based on the acquired real - time vibration data and real - time operating condition data; obtaining the vibration spectrum baseline corresponding to the operating condition based on the real - time operating condition and the vibration spectrum baselines under different operating conditions; and subtracting the vibration spectrum baseline from the real - time spectrum of the real - time vibration data to obtain the operating condition - fault spectrum, the present invention can effectively eliminate the influence of the sub - healthy state, reduce the influence of the main energy in the original spectrum, thereby highlighting the change of the frequency components in the original spectrum diagram. Furthermore, by determining the frequency energy factor based on the operating condition - fault spectrum for determining the component degradation state of the rotating equipment, the present invention can accurately evaluate the component degradation state of the rotating equipment through the dimension of the frequency energy change. Therefore, the present invention can effectively correct the influence of variable operating conditions and sub - healthy states on the evaluation of the component degradation state of the rotating equipment, and thus can accurately evaluate the component degradation trend of the rotating equipment under variable operating conditions and sub - healthy states.

[0113] Figure 5 FIG. shows a flowchart of a method 500 for determining the degradation state of components of a rotating equipment according to an embodiment of the present invention. It should be understood that the method 500 can be executed, for example, at Figure 8 the described electronic device 800. It can also be at Figure 1Execute at the described computing device 110. It should be understood that method 500 may also include additional actions not shown and / or the actions shown may be omitted, and the scope of the present invention is not limited in this regard.

[0114] At step 502, computing device 110 calculates the mean and standard deviation of a plurality of frequency energy factors under the current time predetermined operating condition.

[0115] Regarding the predetermined operating condition, which is, for example, a standard operating condition or a non-rated operating condition.

[0116] Regarding the method of calculating the mean and standard deviation of a plurality of frequency energy factors, for example: based on the plurality of frequency energy factors included in the frequency energy factor sequence under the current time predetermined operating condition, calculate the mean and standard deviation.

[0117] Regarding the frequency energy factor sequence, for example, as shown in the following formula (17).

[0118] (17).

[0119] In the above formula (17), represents the frequency energy factor sequence composed of a plurality of frequency energy factors under a certain operating condition. represents the frequency energy factor for the second frequency. represents the frequency energy factor for the first frequency.

[0120] At step 504, computing device 110 calculates the frequency energy factor threshold based on the mean and standard deviation.

[0121] Regarding the frequency energy factor threshold, for example, it is calculated based on the following formula (18).

[0122] (18).

[0123] In the above formula (18), represents the mean of a plurality of frequency energy factors under a certain operating condition at the current time. represents the standard deviation of a plurality of frequency energy factors under a certain operating condition at the current time. represents the frequency energy factor threshold.

[0124] At step 506, computing device 110 filters out the frequency energy factors that exceed the frequency energy factor threshold.

[0125] It should be understood that since the frequency energy factor is calculated based on the operating condition-fault spectrum, and the operating condition-fault spectrum eliminates the influence of the original high energy in the original spectrum, for a certain operating condition, all frequency energy factors should be in a state of random fluctuation. If there is an abnormal frequency energy factor exceeding the frequency energy factor threshold, it means that the fault corresponding to this frequency energy factor is very likely to occur.

[0126] At step 508, the computing device 110 determines the degradation state of the components of the rotating device based on the characteristic frequencies corresponding to the frequency energy factors exceeding the frequency energy factor threshold, and the correspondence between the characteristic frequencies and the component faults of the rotating device.

[0127] Regarding the correspondence between the characteristic frequencies and the component faults of the rotating device, for example, it is a correspondence table between abnormal frequency energy factors and component faults. Table 2 below schematically shows the association table between the component faults of the rotating device and the characteristic frequencies. For example, if the characteristic frequencies corresponding to the frequency energy factors exceeding the frequency energy factor threshold are the radial 2x rotational frequency and the axial 1x rotational frequency, it is determined that there is a coupling fault in the components of the rotating device.

[0128] Table 2

[0129] 。

[0130] In some embodiments, if the computing device 110 determines that multiple abnormal frequency energy factors jointly affect the components of the rotating device, a weighted sum is performed on the multiple abnormal frequency energy factors, so as to determine the degradation state of the components of the rotating device based on the weighted sum result.

[0131] Figure 6 The flowchart of a method 600 for determining the most likely component fault category for each operating condition at a future time point according to an embodiment of the present invention is illustrated. Figure 7 The schematic diagram of the change trends of different component weighted frequency energy factors according to an embodiment of the present invention is illustrated. It should be understood that the method 600 can be executed, for example, at Figure 8 the electronic device 800 described. It can also be executed at Figure 1 the computing device 110 described. It should be understood that the method 600 may further include additional actions not shown and / or may omit the actions shown, and the scope of the present invention is not limited in this regard.

[0132] At step 602, the computing device 110 determines the frequency energy factors exceeding the frequency energy factor threshold for different operating conditions at the current time point.

[0133] At step 604, if the computing device 110 performs weighted summation on frequency energy factors exceeding the frequency energy factor threshold to obtain weighted frequency energy factors corresponding to different operating conditions at the current time point.

[0134] For example, as shown in Table 3 below. For operating condition W1, its abnormal frequency energy factor is . The weighted frequency energy factor corresponding to operating condition W1 is + . This weighted frequency energy factor corresponds to component failure 1.

[0135] Table 3

[0136] .

[0137] At step 606, the computing device 110 sorts the weighted frequency energy factors corresponding to different operating conditions to determine the most likely component failure category under different operating conditions at the current time point based on the sorting result. Thus, the present invention can identify the state of the components of the current rotating device.

[0138] At step 608, the computing device 110 calculates the weighted frequency energy factors corresponding to each operating condition for multiple historical time points respectively, for constructing a time series - frequency energy factor prediction model for each operating condition based on the weighted frequency energy factors corresponding to each operating condition at the current time point and multiple historical time points.

[0139] Regarding the method of calculating the weighted frequency energy factors corresponding to each operating condition for multiple historical time points respectively, it is similar to the method of calculating the weighted frequency energy factors corresponding to each operating condition for the current time in steps 602 and 604, and will not be elaborated here.

[0140] It should be understood that the time series - frequency energy factor prediction model indicates the change trend of the frequency energy factor under different operating conditions in the time series dimension. As Figure 7 shown, each curve represents the change trend of the weighted frequency energy factor of different components, which indicates the evolution trend of the associated component failure. The solid line part of each curve is the weighted frequency energy factor at the current time point and historical time points, and the dashed line is the predicted weighted frequency energy factor trend at future time points.

[0141] At step 610, the computing device 110 predicts the weighted frequency energy factors corresponding to each operating condition at future time points based on the time series - frequency energy factor prediction model for each operating condition, for determining the most likely component failure category under each operating condition at future time points.

[0142] Thus, the present invention can predict the frequency energy factor corresponding to a certain period in the future, and thus can be used to evaluate the development trend of the components of the rotating equipment in the future.

[0143] For example, as shown in Table 4 below. The weighted frequency energy factor at the current time point is . This weighted frequency energy factor corresponds to a coupling failure. The weighted frequency energy factor at future time point 1 is .

[0144] Table 4

[0145] .

[0146] In some embodiments, a higher weight can be assigned to the weighted frequency energy factor at the current time point. For example, the closer the frequency energy factor is to the current time point, the higher the weight assigned. On the other hand, in the later stage of the deployment of the time series - frequency energy factor prediction model, a higher weight can be assigned to the evaluation result of the future state of the component. This is because in the early stage of the deployment of the time series - frequency energy factor prediction model, the data cache is less, and the prediction model will be more accurate as the data accumulates.

[0147] By adopting the above means, the present invention can evaluate the state of the components of the rotating equipment under each working condition in real time, and can effectively target and evaluate the decline trend of the components of the future rotating equipment.

[0148] Figure 8 A block diagram of an electronic device 800 suitable for implementing the embodiments of the present invention is schematically shown. The electronic device 800 can be used to implement the execution of Figure 2 , 5 , the methods 200, 500, 600 shown in FIG. 6. As Figure 8 shown, the electronic device 800 includes a central processing unit (i.e., CPU 801), which can execute various appropriate actions and processes according to the computer program instructions stored in the read - only memory (i.e., ROM 802) or the computer program instructions loaded from the storage unit 808 into the random access memory (i.e., RAM 803). In the RAM 803, various programs and data required for the operation of the electronic device 800 can also be stored. The CPU 801, ROM 802, and RAM 803 are connected to each other through a bus 804. The input / output interface (i.e., I / O interface 805) is also connected to the bus 804.

[0149] Multiple components in the electronic device 800 are connected to the I / O interface 805, including: an input unit 806, an output unit 807, and a storage unit 808. The CPU 801 executes the various methods and processes described above, such as executing methods 200, 500, and 600. For example, in some embodiments, methods 200, 500, and 6000 may be implemented as computer software programs, which are stored in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the CPU 801, one or more operations of the methods 200, 500, and 600 described above may be performed. Alternatively, in other embodiments, the CPU 801 may be configured to perform one or more actions of the methods 200, 500, and 600 by any other suitable means (e.g., by means of firmware).

[0150] It should be further noted that the present invention may be a method, an apparatus, a system, and / or a computer program product. The computer program product may include a computer-readable storage medium having thereon computer-readable program instructions for performing various aspects of the present invention.

[0151] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanically encoded device, such as a punched card or raised structures in a groove having instructions stored thereon, and any suitable combination of the foregoing. The computer-readable storage medium used herein is not construed as an instantaneous signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated through a waveguide or other transmission medium (e.g., an optical pulse through an optical fiber cable), or an electrical signal transmitted through a wire.

[0152] The computer-readable program instructions described herein can be downloaded to various computing / processing devices from a computer-readable storage medium or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing / processing device.

[0153] The computer program instructions for carrying out operations of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state-setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages - such as Smalltalk, C++, etc., and conventional procedural programming languages - such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network - including a local area network (LAN) or a wide area network (WAN) - or, alternatively, may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, by using the state information of the computer-readable program instructions to customize an electronic circuit, such as a programmable logic circuit, a field-programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer-readable program instructions to implement various aspects of the present invention.

[0154] Aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0155] These computer-readable program instructions can be provided to a processing unit of a processor, general purpose computer, special purpose computer, or other programmable data processing apparatus in a voice interaction device, thereby producing a machine such that when these instructions are executed by the processing unit of the computer or other programmable data processing apparatus, a device is produced that implements the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other devices to operate in a particular manner, so that the computer-readable medium storing the instructions includes a manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0156] The computer-readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other devices, so that a series of operation steps are executed on the computer, other programmable data processing apparatus, or other devices to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other devices to implement the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0157] The flowcharts and block diagrams in the figures illustrate the possible architectures, functions, and operations of devices, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the figures. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0158] The embodiments of the present invention have been described above. The above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations are obvious to those of ordinary skill in the art in the technical field without departing from the scope and spirit of the described embodiments. The selection of the terms used herein is intended to best explain the principles of the embodiments, the practical application, or the improvement of the technology in the market, or to enable other ordinary skill in the art in the technical field to understand the embodiments disclosed herein.

[0159] The above are only alternative embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for determining the degradation state of a component of a rotating device under variable operating conditions, characterized in that: include: Cache the acquired real-time vibration data and real-time working condition data about the rotating equipment to generate historical vibration data and historical working condition data, so as to calculate the vibration spectrum baseline corresponding to different working conditions of the rotating equipment in a steady state based on the historical vibration data and historical working condition data; Based on the acquired real-time vibration data and real-time working condition data, a real-time spectrum of the real-time vibration data is acquired; Based on the real-time working condition and the vibration spectrum baselines under the different working conditions, obtaining the vibration spectrum baseline corresponding to the real-time working condition; Subtracting a vibration spectrum baseline corresponding to the real-time working condition from a real-time spectrum of the real-time vibration data to obtain a working condition-fault spectrum; as well as Based on the operating condition-fault spectrum, a frequency energy factor is determined to determine the degradation state of the components of the rotating equipment. The frequency energy factor is obtained by multiplying the frequency energy proportion and the frequency energy change rate.

2. The method according to claim 1, characterized in that Based on the operating condition-fault spectrum, determining the change of the frequency energy factor includes: Based on the working condition-fault spectrum, calculating the frequency energy factor corresponding to each characteristic frequency in the working condition-fault spectrum; and Determine the component degradation trend of rotating equipment based on the change of frequency energy factor.

3. The method according to claim 2, characterized in that Based on the working condition-fault spectrum, the frequency energy factor corresponding to each characteristic frequency in the working condition-fault spectrum is calculated including: Based on the working condition-fault spectrum, calculate the frequency energy proportion and frequency energy change rate corresponding to each characteristic frequency in the working condition-fault spectrum; and Based on the frequency energy proportion and the frequency energy change rate, a frequency energy factor corresponding to each characteristic frequency is calculated.

4. The method according to claim 3, characterized in that Based on the frequency energy proportion and the frequency energy change rate, calculating the frequency energy factor corresponding to each characteristic frequency includes: The frequency energy proportion and the frequency energy change rate are multiplied to obtain the frequency energy factor corresponding to each characteristic frequency.

5. The method according to claim 3, characterized in that: The frequency energy proportion and frequency energy change rate corresponding to each characteristic frequency in the calculation condition-fault spectrum include: Calculate the frequency peak energy based on the amplitude of the operating condition-fault spectrum at each characteristic frequency; Calculating the total frequency energy based on the sum of the squares of the amplitudes of the operating condition-fault spectrum under the current operating condition; and The ratio of the frequency peak energy to the total frequency energy is calculated to obtain the frequency energy contribution.

6. The method according to claim 3, characterized in that The frequency energy proportion and frequency energy change rate corresponding to each characteristic frequency in the calculation condition-fault spectrum include: caching the calculated frequency energy under the predetermined working condition so as to obtain a frequency energy sequence corresponding to the predetermined working condition; and Based on the frequency energy sequence, a linear model of time and frequency energy is constructed to calculate the slope of the frequency energy sequence change corresponding to the predetermined working condition, thereby obtaining the frequency energy change rate.

7. The method according to claim 2, characterized in that Determining the degradation state of rotating equipment components includes: Calculate the mean and standard deviation of multiple frequency energy factors under the current time and predetermined working conditions; Based on the mean and standard deviation, the frequency energy factor threshold is calculated; Screening frequency energy factors exceeding a frequency energy factor threshold; and Based on the characteristic frequency corresponding to the frequency energy factor exceeding the frequency energy factor threshold and the corresponding relationship between the characteristic frequency and the component failure of the rotating equipment, the degradation state of the component of the rotating equipment is determined.

8. The method according to claim 1, characterized in that Calculation of the vibration spectrum baseline for different operating conditions of the rotating equipment corresponding to the steady state includes: Based on the historical vibration data and the historical operating condition data, respectively generate a vibration spectrum sequence and an operating condition data sequence of the rotating equipment in a steady state, wherein the vibration spectrum sequence indicates a corresponding relationship between time and the vibration spectrum, and the operating condition data sequence indicates a corresponding relationship between time and the operating condition data; For each working condition, the vibration spectra of all detection positions are calculated to obtain the average value of the vibration spectra of all detection positions corresponding to each working condition; Based on the mean value, a vibration spectrum baseline of the rotating equipment in different working conditions in a steady state is generated.

9. The method according to claim 1, characterized in that: Based on the change of frequency energy factor, the degradation trend of rotating equipment components is determined including: According to different working conditions at the current time point, determine the frequency energy factor exceeding the frequency energy factor threshold; Performing weighted summation on the frequency energy factors exceeding the frequency energy factor threshold, so as to obtain the weighted frequency energy factors corresponding to different working conditions at the current time point; Sorting the weighted frequency energy factors corresponding to different operating conditions, so as to determine the component failure category most likely to occur under different operating conditions at the current time point based on the sorting results; For multiple historical time points, respectively calculating the weighted frequency energy factor corresponding to each operating condition, so as to construct a time series-frequency energy factor prediction model for each operating condition based on the weighted frequency energy factor corresponding to each operating condition at the current time point and multiple historical time points; and Based on the time series-frequency energy factor prediction model for each operating condition, the weighted frequency energy factor corresponding to each operating condition at a future time point is predicted to determine the component failure category most likely to occur under each operating condition at the future time point.

10. A computing device comprising: at least one processing unit; At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the computing device to perform the steps of the method according to any one of claims 1 to 9.

11. A computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the method according to any one of claims 1 to 9 when executed by a machine.

Images