Rotating machine rubbing determination device, rubbing determination method, and rubbing determination program

Abstract

This rubbing determination device determines rubbing of a rotary machine which comprises a fixed part and a rotary part. The present device acquires an AE signal detected by means of an AE sensor provided in the rotary machine and acquires a gap amount between the fixed part and the rotary part. A rubbing determination evaluation index is generated on the basis of the AE signal and the gap amount, and rubbing in the rotary machine is determined on the basis of the rubbing determination evaluation index.

Description

Technical Field

[0001] The present disclosure relates to a rubbing determination device for a rotating machine, a rubbing determination method, and a rubbing determination program. This application claims priority based on Japanese Patent Application No. 2022-042114 filed with the Japan Patent Office on March 17, 2022, the content of which is incorporated herein by reference.

Background Art

[0002] In a rotating machine such as a steam turbine, during operation, as the gap in the seal part shrinks due to thermal deformation of the external or internal casing, rubbing (contact) may occur between a stationary part such as a seal fin and a rotating part such as a rotor. The occurrence of such rubbing causes an increase in the shaft vibration of the rotating machine and a performance degradation due to an increase in the gap, and thus a technique for early detection is required.

[0003] As an example of this type of rotating machine, there is a steam turbine connected to a generator in a power plant. In such applications, in order to cover fluctuations in the amount of power generated by renewable energy in the power grid, an operation for the steam turbine to cope with load fluctuations is required. Therefore, in recent steam turbines, the gap tends to shrink for the purpose of coping with such load fluctuations and improving the performance of the rotating machine, and the possibility of rubbing is increasing.

[0004] For example, in Patent Documents 1 and 2, as a technique for detecting rubbing in such a rotating machine, based on the result of detecting an AE (Acoustic Emission) signal generated at the time of rubbing with an AE sensor, a technique for determining the presence or absence of rubbing and its position is disclosed.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Patent Document 2

SUMMARY OF THE INVENTION

PROBLEMS TO BE SOLVED BY THE INVENTION

[0006] In the above Patent Documents 1 and 2, as described above, rubbing determination is performed based on the AE signal detected by the AE sensor. However, depending on the degree and occurrence position of rubbing, the AE signal may be weakened due to the influence of noise or the like, making it difficult to perform accurate rubbing determination.

[0007] In addition, as another method for rubbing determination, there is also a technique for measuring or estimating the gap. However, when directly measuring the gap using a sensor, the cost and labor involved in installing a new sensor become problems. There is also a method of estimating the gap by inputting operating parameters such as the temperature of the rotating machine into an estimation model corresponding to the rotating machine. Such a method is advantageous in that it does not require the installation of a new sensor. However, for example, when aging deterioration such as wear occurs in the rotating machine, a deviation may occur between the rotating machine and the estimation model, and the accuracy of rubbing determination may decrease.

[0008] At least one embodiment of the present disclosure has been made in view of the above circumstances, and an object thereof is to provide a rubbing determination device, a rubbing determination method, and a rubbing determination program for a rotating machine that can accurately determine rubbing occurring in the rotating machine.

MEANS FOR SOLVING THE PROBLEMS

[0009] In order to solve the above problems, a rubbing determination device for a rotating machine according to at least one embodiment of the present disclosure (1) A rubbing determination device for a rotating machine according to one aspect is a rubbing determination device for a rotating machine including a fixed part and a rotating part, an AE signal acquisition unit for acquiring an AE signal detected by an AE sensor provided in the rotating machine, a gap amount acquisition unit for acquiring a gap amount between the fixed part and the rotating part, A rubbing determination evaluation index generation unit for generating a rubbing determination evaluation index based on the AE signal and the gap amount; A rubbing determination unit for determining rubbing in the rotating machine based on the rubbing determination evaluation index; It is provided with.

[0010] In order to solve the above problems, a rubbing determination method for a rotating machine according to at least one embodiment of the present disclosure is A rubbing determination method for a rotating machine including a fixed part and a rotating part, A step of acquiring an AE signal detected by an AE sensor provided in the rotating machine; A step of acquiring the gap amount between the fixed part and the rotating part; A step of generating a rubbing determination evaluation index based on the AE signal and the gap amount; A step of determining rubbing in the rotating machine based on the rubbing determination evaluation index; It is provided with.

[0011] In order to solve the above problems, a rubbing program for a rotating machine according to at least one embodiment of the present disclosure is A rubbing determination program for a rotating machine including a fixed part and a rotating part, Using a computer, A step of acquiring an AE signal detected by an AE sensor provided in the rotating machine; A step of acquiring the gap amount between the fixed part and the rotating part; A step of generating a rubbing determination evaluation index based on the AE signal and the gap amount; A step of determining rubbing in the rotating machine based on the rubbing determination evaluation index is executable.

Effect of the Invention

[0012] According to at least one embodiment of the present disclosure, it is possible to provide a rubbing determination device, a rubbing determination method, and a rubbing determination program for a rotating machine that can accurately determine rubbing occurring in the rotating machine.

Brief Description of the Drawings

[0013]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11A

Figure 11B

Figure 12

Figure 13

Modes for Carrying Out the Invention

[0014] Hereinafter, some embodiments of the present disclosure will be described with reference to the accompanying drawings. However, the dimensions, materials, shapes, relative arrangements, etc. of the components described as embodiments or shown in the drawings are not intended to limit the scope of the present disclosure, but are merely illustrative examples.

[0015] First, the rotating machine 1 that is the object to be determined by the rubbing determination device 100 according to at least one embodiment of the present disclosure will be described. FIG. 1 is a cross-sectional structure diagram of the rotating machine 1 according to one embodiment.

[0016] The rotating machine 1 includes a stationary part 2 and a rotating part 4 that is rotatable with respect to the stationary part 2. The stationary part 2 is the casing of the rotating machine 1 and is stationary with respect to the outside. The rotating part 4 is rotatably supported with respect to the stationary part 2 via a pair of bearings 6a and 6b.

[0017] A gap D is provided between the stationary part 2 and the rotating part 4. The rotating part 4 is driven by supplying the working fluid W from the supply part 3 provided in the stationary part 2 to the gap D. The working fluid W that has driven the rotating part 4 is discharged to the outside from the discharge part 5 provided in the stationary part 2. During the operation of the rotating machine 1, at least one of the stationary part 2 or the rotating part 4 may be deformed by the influence of heat or the like, so that the gap D is reduced and rubbing may occur. The presence or absence of such rubbing can be determined based on the AE signal detected by the AE sensor 10 described later and the measured value or estimated value of the gap D.

[0018] The rotating part 4 is, for example, a rotor (rotating shaft) that can be rotated by the power of the working fluid W. The rotating part 4 has moving blades 4a for receiving the working fluid W, and the rotating part 4 is rotationally driven by receiving the working fluid W with the moving blades 4a. The rotating machine 1 is, for example, a steam turbine that uses steam as the working fluid W.

[0019] The rotating part 4 is rotatably supported by a pair of bearings 6a and 6b (radial bearings). The bearing 6a is provided on one end side of the rotating part 4, and the bearing 6b is provided on the other end side of the rotating part 4. The bearings 6a and 6b are respectively housed in bearing boxes 7a and 7b.

[0020] The AE sensor 10 is a sensor for detecting the AE signal of the rotating machine 1. The AE wave generated at the location where rubbing occurs propagates as an elastic wave through the stationary part 2 and the rotating part 4, and is detected as an AE signal by each AE sensor 10 installed in the rotating machine 1. The AE wave generally has a frequency in the sound wave region of several tens of kHz to several MHz and is detected as an AE signal by the AE sensor 10. In the present embodiment, a single AE sensor 10 is provided in the bearing 6a (bearing housing 7a), so that it is configured to be able to detect the AE wave from the location where rubbing occurs. In addition, the position where the AE sensor 10 is attached is not limited. For example, it may be attached to a bearing part including the bearings 6a and 6b. In FIG. 1, as a configuration example, the case where the AE sensor 10 is attached to a bearing part including the bearing 6a is shown. More specifically, it is attached to the bearing housing 7a that houses the bearing 6a.

[0021] The rubbing determination device 100 is a device for determining rubbing in the rotating machine 1 having the above configuration, and is composed of, for example, a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), and a computer-readable storage medium, etc. And a series of processes for realizing various functions are stored in a storage medium or the like in the form of a program as an example. The CPU reads this program into the RAM or the like and executes information processing and arithmetic processing, whereby various functions are realized. In addition, the program may be applied in a form in which it is pre-installed in a ROM or other storage medium, a form in which it is provided in a state stored in a computer-readable storage medium, a form in which it is distributed via a wired or wireless communication means, etc. A computer-readable storage medium is a magnetic disk, a magneto-optical disk, a CD-ROM, a DVD-ROM, a semiconductor memory, etc.

[0022] FIG. 2 is a block diagram showing the internal configuration of the rubbing determination device 100 in FIG. 1. The rubbing determination device 100 includes an AE signal acquisition unit 102, a gap amount acquisition unit 104, a rubbing determination evaluation index generation unit 106, and a rubbing determination unit 108.

[0023] The AE signal acquisition unit 102 is a configuration for acquiring the AE signal detected by the aforementioned AE sensor 10 disposed in the rotating machine 1.

[0024] The gap amount acquisition unit 104 is a configuration for acquiring a gap amount De corresponding to the size of the gap D of the rotating machine 1. Regarding the gap amount De acquired by the gap amount acquisition unit 104, there are several modes as described below, and it may be an estimated value or a measured value.

[0025] For example, the gap amount De acquired by the gap amount acquisition unit 104 may be an estimated value calculated based on the operation data Po of the rotating machine 1. Here, FIG. 3 is a flowchart schematically showing the calculation process of the estimated value of the gap amount De. In this example, the case of calculating the estimated value of the gap amount De using the finite element method is shown. The operation data Po includes at least one parameter related to the operation state of the rotating machine 1 and is input to the estimation model Me corresponding to the rotating machine 1 constructed by the finite element method. In the present embodiment, as the operation data Po, the metal temperature of the stationary part 2, the rotation speed of the rotating part 4, the output of the rotating machine 1, or the operation time is input to the estimation model Me, and the gap amount De, which is an estimated value, is output from the estimation model.

[0026] Also, the gap amount De obtained by the gap amount acquisition unit 104 may be an estimated value calculated by being input to the machine learning model Mm. Here, FIG. 4 is a flowchart schematically showing the calculation process of the estimated value of the gap amount De using the machine learning model Mm. The machine learning model Mm is, for example, a neural network model including an input layer 110, an intermediate layer 112, and an output layer 114, and the coefficients are optimized by learning using prepared learning data (past operation data Po and actual measurement values of the gap amount). The gap amount acquisition unit 104 inputs the operation data Po of the rotating machine 1 to such a machine learning model Mm to obtain an estimated value of the gap amount De.

[0027] In this case, the machine learning model Mm used for calculating the estimated quantity may be corrected by feedback of the rubbing determination result in the rubbing determination unit 108. Thereby, by updating the machine learning model Mm by learning the latest rubbing determination result, the rubbing determination accuracy of the rotating machine 1 can be improved.

[0028] Also, the gap amount De obtained by the gap amount acquisition unit 104 may be an actual measurement value detected by a gap sensor 13 disposed in the rotating machine 1. The gap sensor 13 is disposed, for example, at a position facing the rotating part 4 on the inner surface of the stationary part 2 as shown in FIG. 1 to detect the actual measurement value of the gap amount De.

[0029] The rubbing determination evaluation index generation unit 106 is a configuration for generating a rubbing determination evaluation index based on the AE signal acquired by the AE signal acquisition unit 102 and the gap amount De acquired by the gap amount acquisition unit 104. By generating the rubbing determination evaluation index in consideration of both the AE signal and the gap amount De in this way, it is possible to perform a more accurate rubbing determination than when considering only one of the AE signal or the gap amount De.

[0030] The rubbing determination evaluation index generation unit 106 may calculate a combined index of the AE signal and the gap amount as a rubbing determination evaluation index. By combining the AE signal and the gap amount De in this way to generate a rubbing determination evaluation index, accurate rubbing determination becomes possible.

[0031] Here, the method for generating the rubbing determination evaluation index in the rubbing determination evaluation index generation unit 106 will be specifically described. FIG. 5 is a block diagram showing the internal configuration of the rubbing determination evaluation index generation unit 106 in FIG. 1, and FIG. 6 is a graph showing the relationship between the difference ΔAE with respect to the threshold value of the AE signal and the first rubbing occurrence index P AE and FIG. 7 is a graph showing the relationship between the gap amount De and the second rubbing occurrence index P VS and FIG. 8 is a map M1 showing the distribution of the rubbing occurrence probability Pj, which is an example of the rubbing determination evaluation index with respect to the first rubbing occurrence index P AE and the second rubbing occurrence index P VS .

[0032] The rubbing determination evaluation index generation unit 106 according to one aspect includes, as shown in FIG. 5, a first rubbing occurrence index calculation unit 120, a second rubbing occurrence index calculation unit 122, and a rubbing determination evaluation index calculation unit 124. In this aspect, the rubbing determination evaluation index generation unit 106 handles the rubbing occurrence probability Pj as the rubbing determination evaluation index.

[0033] The first rubbing occurrence index calculation unit 120 is a configuration for calculating a first rubbing occurrence index P AE that is the rubbing occurrence probability based on the AE signal. As shown in the inset of FIG. 6, the intensity of the AE signal acquired by the AE signal acquisition unit 102 has a peak waveform that changes continuously with respect to time t. If the difference between the maximum value (peak value) included in such a peak waveform of the AE signal and a preset threshold value is ΔAE, then the difference ΔAE and the first rubbing occurrence index probability P AEThe correlation with [it] is prepared in advance as a characteristic graph shown in FIG. 6. The first rubbing occurrence index calculation unit 120 applies the difference ΔAE corresponding to the AE signal acquired by the AE signal acquisition unit 102 to such a characteristic graph, thereby obtaining the first rubbing occurrence index P which is the rubbing occurrence probability. AE is calculated.

[0034] The second rubbing occurrence index calculation unit 122 is configured to calculate the second rubbing occurrence index P which is the rubbing occurrence probability based on the gap amount De. As shown in the inserted figure of FIG. 7, the gap amount De acquired by the gap amount acquisition unit 104 indicates the size of the gap D between the stationary part 2 and the rotating part 4. The correlation between the gap amount De and the second rubbing occurrence index P VS is prepared in advance as a characteristic graph shown in FIG. 7. The second rubbing occurrence index calculation unit 122 applies the gap amount De acquired by the gap amount acquisition unit 104 to such a characteristic graph, thereby obtaining the second rubbing occurrence index P which is the rubbing occurrence probability. VS is calculated. VS is calculated.

[0035] The rubbing determination evaluation index calculation unit 124 prepares in advance a map M1 that defines the correlation between the first rubbing occurrence index P AE , the second rubbing occurrence index P VS , and the rubbing occurrence probability Pj which is the rubbing determination evaluation index, and based on the map M1, the first rubbing occurrence index P calculated by the first rubbing occurrence index calculation unit 120 AE , and the second rubbing occurrence index P calculated by the second rubbing occurrence index calculation unit 122 VS to calculate the corresponding rubbing occurrence probability Pj. As shown in FIG. 8, the map M1 defines the distribution of the rubbing occurrence probability Pj with respect to the first rubbing occurrence index P AE and the second rubbing occurrence index P VS .

[0036] The rubbing determination evaluation index generation unit 106 generates the thus calculated rubbing occurrence probability Pj as a rubbing determination evaluation index which is a combined index of the AE signal and the gap amount De.

[0037] The rubbing determination unit 108 is configured to determine rubbing in the rotating machine 1 based on the rubbing determination evaluation index generated by the rubbing determination evaluation index generation unit 106. When it is determined in the rubbing determination unit 108 that there is rubbing, an alarm or a screen display may be performed by an output device (not shown).

[0038] Next, a rubbing determination method implemented by the rubbing determination device 100 having the above configuration will be described. FIG. 9 is a flowchart showing a rubbing determination method according to an embodiment.

[0039] First, the AE signal acquisition unit 102 acquires an AE signal (step S100), and the gap amount acquisition unit 104 acquires the gap amount De (step S101). Subsequently, the rubbing determination evaluation index generation unit 106 generates a rubbing determination evaluation index, which is the rubbing occurrence probability Pj, based on the AE signal acquired in step S100 and the gap amount De acquired in step S101 (step S102). The rubbing determination unit 108 determines whether or not the rubbing determination evaluation index, which is the rubbing occurrence probability Pj generated in step S102, exceeds a preset threshold value Pj0 (step S103). As a result, when the rubbing occurrence probability Pj, which is the rubbing determination evaluation index, exceeds the threshold value Pj0 (step S103: YES), a "rubbing present" determination is made (step S104). On the other hand, when the rubbing occurrence probability Pj, which is the rubbing determination evaluation index, is equal to or less than the threshold value Pj0 (step S103: NO), a "rubbing absent" determination is made (step S105).

[0040] FIG. 10 shows an example of the temporal change of the rubbing occurrence probability Pj, which is an example of the rubbing determination evaluation index. FIG. 10 shows a behavior in which the rubbing occurrence probability Pj increases with the passage of time. At times t-1 and t-2, the rubbing occurrence probability Pj is equal to or less than the threshold value Pj0, which is the reference value for determination, but at time t-3, it is determined that rubbing has occurred because the threshold value Pj0 is exceeded.

[0041] The rubbing determination evaluation index generation unit 106 according to another aspect generates a rubbing determination evaluation index including the first rubbing occurrence index calculated by the first rubbing occurrence index calculation unit 120 and the second rubbing occurrence index calculated by the second rubbing occurrence index calculation unit 122, and the rubbing determination unit 108 may determine the presence or absence of rubbing based on the rubbing determination evaluation index.

[0042] In this aspect, a sufficient number of past data including the first rubbing occurrence index, the second rubbing occurrence index, and the rubbing determination result are prepared in advance. FIG. 11A is a diagram showing past data, and FIG. 11B is a map M2 showing the correlation between the rubbing determination evaluation index and the rubbing determination result based on the past data of FIG. 11A. As shown in FIG. 11A, the past data includes a plurality of measurement data 1, 2,... in which the AE signal detected by the AE sensor 10 and the gap amount De which is the aforementioned estimated value or measured value are associated with the rubbing determination result based on the measurement. By including a sufficient amount of such measurement data in the past data, when plotted for the AE signal and the gap amount De as shown in FIG. 11B, a map M2 is created in which an area A where the rubbing determination result is "rubbing present" and an area B where the rubbing determination result is "rubbing absent" are specified.

[0043] The rubbing determination evaluation index generation unit 106 acquires the AE signal detected by the AE sensor 10 as the first rubbing occurrence index, and acquires the gap amount De which is an estimated value or a measured value as the second rubbing occurrence index. The rubbing determination unit 108 determines the presence or absence of rubbing by applying these to the map M2 shown in FIG. 11B.

[0044] In another embodiment, the rubbing determination evaluation index generation unit 106 may generate a rubbing determination evaluation index by correcting the gap amount De acquired by the gap amount acquisition unit 104 based on the combination index. In the present embodiment, the rubbing determination evaluation index generation unit 106 generates a rubbing determination evaluation index by correcting the gap amount De acquired by the gap amount acquisition unit 104 to be zero at the timing when the rubbing occurrence probability Pj which is the aforementioned combination index exceeds the threshold value Pj0.

[0045] FIG. 12 is a flowchart showing a rubbing determination method according to another embodiment. Steps S200 to S205 are the same as steps S100 to S105 in FIG. 10. When it is determined that "rubbing exists" in step S204, it is determined whether the gap amount De acquired by the gap amount acquisition unit 104 in step S201 is greater than zero (step S206). As a result, when the gap amount De is greater than zero (step S206: YES), the rubbing determination evaluation index generation unit 106 performs correction so that the gap amount De becomes zero (step S207). Thereafter, the process returns to step S100, and a series of processes are repeatedly performed. In this case, in the subsequent processes, the correction performed in step S207 is applied to the gap amount De acquired in step S201, and the subsequent rubbing determination is performed based on the corrected gap amount De.

[0046] FIG. 13 is a graph showing the temporal change of the rubbing determination evaluation index before and after correction. In FIG. 13, the temporal change of the gap amount De acquired by the gap amount acquisition unit 104 from time t0 is shown. When the rubbing occurrence probability Pj exceeds the threshold value Pj0 at time t1, the rubbing determination evaluation index generation unit 106 corrects the rubbing determination evaluation index so that the gap amount De becomes zero. After time t1, the gap amount De corrected at time t1 is output as the rubbing determination evaluation index. The behavior of the gap amount De corrected in this way is shifted by a certain amount with respect to the gap amount De acquired by the gap amount acquisition unit 104 before time t1 (in FIG. 13, the behavior of the gap amount De when it is not corrected after time t1 is shown by a broken line).

[0047] In this way, when the rubbing occurrence probability Pj, which is a combined index, reaches the threshold value Pj0 and the rubbing presence is accurately determined, by correcting the gap amount De so that it becomes zero, for example, even when the conditions of the rotating machine 1 change due to aging, an accurate gap amount De can be obtained. Therefore, by using the gap amount De corrected in this way as the rubbing determination evaluation index, an accurate rubbing determination becomes possible.

[0048] As described above, according to each of the above embodiments, rubbing determination is performed based on the AE signal detected by the AE sensor and the rubbing determination evaluation index generated based on the gap amount which is a measured value or an estimated value. Thereby, better determination accuracy can be obtained as compared with the rubbing determination based on only either the AE signal or the gap information.

[0049] In addition, within the scope not departing from the gist of the present disclosure, it is possible to appropriately replace the components in the above-described embodiments with well-known components, and the above-described embodiments may also be appropriately combined.

[0050] The content described in each of the above embodiments is understood as follows, for example.

[0051] (1) A rubbing determination device for a rotating machine according to one aspect is A rubbing determination device (100) for a rotating machine including a fixed part and a rotating part, an AE signal acquisition unit (102) for acquiring an AE signal detected by an AE sensor provided in the rotating machine, a gap amount acquisition unit (104) for acquiring a gap amount between the fixed part and the rotating part, a rubbing determination evaluation index generation unit (106) for generating a rubbing determination evaluation index based on the AE signal and the gap amount, a rubbing determination unit (108) for determining rubbing in the rotating machine based on the rubbing determination evaluation index, and includes.

[0052] According to the aspect of (1) above, rubbing determination is performed based on the AE signal detected by the AE sensor and the rubbing determination evaluation index generated based on the gap amount which is a measured value or an estimated value. Thereby, better determination accuracy can be obtained as compared with the rubbing determination based on only either the AE signal or the gap information.

[0053] (2) In another aspect, in the aspect of (1) above, The rubbing determination evaluation index generation unit calculates a combined index of the AE signal and the gap amount as the rubbing determination evaluation index.

[0054] According to the aspect of (2) above, by generating a rubbing determination evaluation index by combining the AE signal and the gap amount, accurate rubbing determination becomes possible.

[0055] (3) In another aspect, in the aspect of (2) above, the rubbing determination evaluation index generation unit a first rubbing occurrence index calculation unit for calculating a first rubbing occurrence probability based on the AE signal, a second rubbing occurrence index calculation unit for calculating a second rubbing occurrence probability based on the gap amount, using a map that defines the rubbing occurrence probability for the first rubbing occurrence index and the second rubbing occurrence index, the first rubbing occurrence index calculated by the first rubbing occurrence index calculation unit, and the rubbing occurrence probability corresponding to the second rubbing occurrence index calculated by the second rubbing occurrence index calculation unit, a rubbing determination evaluation index calculation unit for calculating as the combined index, is provided.

[0056] According to the aspect of (3) above, by using the rubbing occurrence probability calculated based on the first rubbing occurrence index corresponding to the AE signal and the second rubbing occurrence index corresponding to the gap amount as the rubbing determination evaluation index, accurate rubbing determination becomes possible.

[0057] (4) In another aspect, in the aspect of (2) or (3) above, the rubbing determination evaluation index generation unit generates the rubbing determination evaluation index by correcting the gap amount based on the combined index.

[0058] According to the aspect (4) above, by correcting the gap amount using a combined index that enables accurate rubbing determination, for example, even when the conditions of the rotating machine change due to aging, it is possible to accurately evaluate the gap amount.

[0059] (5) In another aspect, in the aspect (4) above, When the combined index reaches a preset threshold value, the rubbing determination evaluation index generation unit corrects the gap amount to zero.

[0060] According to the aspect (5) above, when the combined index reaches the threshold value and the occurrence of rubbing is accurately determined, the acquired value of the gap amount is corrected to zero. Thereby, for example, even when the conditions of the rotating machine change due to aging, it is possible to accurately evaluate the gap amount by correcting the gap amount.

[0061] (6) In another aspect, in any one of the aspects (1) to (5) above, The gap amount is an estimated value calculated based on the operation data of the rotating machine.

[0062] According to the aspect (6) above, an estimated value calculated based on the operation data of the rotating machine is used as the gap amount. Even when such an estimated value is used as the gap amount, by using it together with the AE signal in the generation of the rubbing determination evaluation index, accurate rubbing determination is possible.

[0063] (7) In another aspect, in any one of the aspects (1) to (5) above, The gap amount is an estimated value calculated by inputting the operation data of the rotating machine into a machine learning model, and the machine learning model is corrected by feeding back the rubbing determination evaluation index.

[0064] According to the aspect (7) above, as the gap amount, an estimated value is calculated by inputting the operation data of the rotating machine into the machine learning model. Even when the estimated value calculated using the machine learning model is adopted as the gap amount in this way, by using it together with the AE signal to generate the rubbing determination evaluation index, accurate rubbing determination becomes possible. Further, the machine learning model is corrected based on the rubbing determination evaluation index generated based on the AE signal and the gap amount (estimated value), thereby improving the estimation accuracy of the gap amount and enabling more excellent accuracy rubbing determination.

[0065] (8) In other aspects, in any one of the aspects (1) to (5) above, The gap amount is the measured value detected by a gap sensor provided in the rotating machine.

[0066] According to the aspect (8) above, even when the sensor measured value is used as the gap amount, accurate rubbing determination is possible.

[0067] (9) In other aspects, in any one of the aspects (1) to (8) above, The AE signal is acquired from an AE sensor provided in a bearing portion that rotatably supports the rotating portion with respect to the stationary portion.

[0068] According to the aspect (9) above, the AE signal used to generate the rubbing determination evaluation index can be acquired from an AE sensor installed in the bearing portion.

[0069] (10) In other aspects, in any one of the aspects (1) to (9) above, The rotating machine is a steam turbine.

[0070] According to the aspect (10) above, a rubbing determination device capable of accurately determining rubbing in a steam turbine can be realized.

[0071] (11) A method for determining rubbing of a rotating machine according to one aspect is A method for determining rubbing of a rotating machine including a fixed part and a rotating part, comprising: obtaining an AE signal detected by an AE sensor provided in the rotating machine; obtaining a gap amount between the fixed part and the rotating part; generating a rubbing determination evaluation index based on the AE signal and the gap amount; determining rubbing in the rotating machine based on the rubbing determination evaluation index. The method comprises the steps above.

[0072] According to the aspect of (11) above, rubbing determination is performed based on the AE signal detected by the AE sensor and the rubbing determination evaluation index generated based on the gap amount which is a measured value or an estimated value. Thereby, better determination accuracy can be obtained compared with the rubbing determination based on only either the AE signal or the gap information.

[0073] (12) A rubbing determination program for a rotating machine according to an aspect includes: a rubbing determination program for a rotating machine including a fixed part and a rotating part, which causes a computer to perform: using a computer, obtaining an AE signal detected by an AE sensor provided in the rotating machine; obtaining a gap amount between the fixed part and the rotating part; generating a rubbing determination evaluation index based on the AE signal and the gap amount; determining rubbing in the rotating machine based on the rubbing determination evaluation index. The program is executable.

[0074] According to the aspect of (12) above, rubbing determination is performed based on the AE signal detected by the AE sensor and the rubbing determination evaluation index generated based on the gap amount which is a measured value or an estimated value. Thereby, better determination accuracy can be obtained compared with the rubbing determination based on only either the AE signal or the gap information.

Explanation of Signs

[0075] 1 Rotating machine 2 Stationary part 3 Supply part 4 Rotating part 4a Moving blade 5 Discharge part 6a, 6b Bearing 7a, 7b Bearing housing 10 Sensor 13 Clearance sensor 100 Rubbing determination device 102 Signal acquisition part 104 Clearance amount acquisition part 106 Rubbing determination evaluation index generation part 108 Rubbing determination part 110 Input layer 112 Intermediate layer 114 Output layer 120 First rubbing occurrence index calculation part 122 Second rubbing occurrence index calculation part 124 Rubbing determination evaluation index calculation part

Claims

1. A rubbing determination device for a rotating machine including a fixed part and a rotating part, an AE signal acquisition unit for acquiring an AE signal detected by an AE sensor provided in the rotating machine; a gap amount acquisition unit for acquiring a gap amount between the fixed part and the rotating part; a rubbing determination evaluation index generation unit for generating a rubbing determination evaluation index related to the occurrence probability of rubbing in the rotating machine based on the AE signal and the gap amount; a rubbing determination unit for determining the rubbing based on the rubbing determination evaluation index; A rubbing determination device for a rotating machine, comprising:

2. The rubbing determination evaluation index generation unit calculates a combined index of the AE signal and the gap amount as the rubbing determination evaluation index. The rubbing determination device for a rotating machine according to claim 1.

3. The rubbing determination evaluation index generation unit includes a first rubbing occurrence index calculation unit for calculating a first rubbing occurrence probability, which is a first rubbing occurrence index, based on the AE signal; a second rubbing occurrence index calculation unit for calculating a second rubbing occurrence probability, which is a second rubbing occurrence index, based on the gap amount; and a rubbing determination evaluation index calculation unit for calculating, as the combined index, the rubbing occurrence probability corresponding to the first rubbing occurrence index calculated by the first rubbing occurrence index calculation unit and the second rubbing occurrence index calculated by the second rubbing occurrence index calculation unit by using a map that defines the rubbing occurrence probability for the first rubbing occurrence index and the second rubbing occurrence index. The rubbing determination device for a rotating machine according to claim 2, comprising:

4. The rubbing determination evaluation index generation unit generates the rubbing determination evaluation index by correcting the gap amount based on the combined index. The rubbing determination device for a rotating machine according to claim 2.

5. The rubbing determination evaluation index generation unit corrects the gap amount to zero when the combination index reaches a preset threshold value. The rubbing determination device for a rotating machine according to claim 4.

6. The gap amount is an estimated value calculated based on the operation data of the rotating machine. The rubbing determination device for a rotating machine according to claim 1 or 2.

7. The gap amount is an estimated value calculated by inputting the operation data of the rotating machine into a machine learning model. The machine learning model is corrected by feeding back the rubbing determination evaluation index. The rubbing determination device for a rotating machine according to claim 1 or 2.

8. The gap amount is a measured value detected by a gap sensor provided in the rotating machine. The rubbing determination device for a rotating machine according to claim 1 or 2.

9. The AE signal is acquired from an AE sensor provided in a bearing portion that rotatably supports the rotating portion with respect to the fixed portion. The rubbing determination device for a rotating machine according to claim 1 or 2.

10. The rotating machine is a steam turbine. The rubbing determination device for a rotating machine according to claim 1 or 2.

11. A rubbing determination method for a rotating machine including a fixed portion and a rotating portion, comprising: acquiring an AE signal detected by an AE sensor provided in the rotating machine; acquiring a gap amount between the fixed portion and the rotating portion; generating a rubbing determination evaluation index related to the occurrence probability of rubbing in the rotating machine based on the AE signal and the gap amount; determining the rubbing based on the rubbing determination evaluation index; and a rubbing determination method for a rotating machine.

12. A rubbing determination program for a rotating machine having a fixed part and a rotating part, using a computer, obtaining an AE signal detected by an AE sensor provided in the rotating machine; obtaining a clearance amount between the fixed part and the rotating part; generating a rubbing determination evaluation index regarding the occurrence probability of rubbing in the rotating machine based on the AE signal and the clearance amount; determining the rubbing based on the rubbing determination evaluation index; A rubbing determination program for a rotating machine that can execute the above steps.

Images