Abnormality diagnosis device and abnormality diagnosis system

Abstract

To provide a malfunction diagnosis apparatus which can suppress erroneous diagnosis occurring regardless of the number of samples of normal data and can suppress deterioration in discrimination performance resulting from lack of the samples of the normal data in number.SOLUTION: A malfunction diagnosis apparatus 3 according to the present invention has a first processing unit 42 for calculating a first index indicating similarity between a diagnosis data indicating a frequency spectrum of vibration of an object device and a first model constructed based on normal data indicating a frequency spectrum of vibration of the object device obtained when the object device is operated normally, a second processing unit 43 for calculating a second index indicating an abnormality level of the object device based on the diagnosis data and a second model constructed based on the normal data and abnormal data indicating the frequency spectrum of vibration of the object device obtained when the object device is operated abnormally, and a diagnosis unit 45 for diagnosing, based on the first index and the second index, whether or not the object device is operated abnormally.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present invention relates to an abnormality diagnosis device and an abnormality diagnosis system. [Background technology]

[0002] 2. Description of the Related Art There is known a method of performing abnormality diagnosis based on vibration data output from a vibration sensor that detects vibrations of an electric motor or the like, which is subjected to fast Fourier series transformation.

[0003] For example, in a method (Method 1) described in Patent Document 1, a diagnostic model is generated by applying multivariate statistical process control (MSPC) to statistics (e.g., average value, maximum value, etc.) of a Fourier spectrum for vibration data under normal conditions. Then, in Method 1, the diagnostic model is used to perform an abnormality diagnosis on the vibration data to be diagnosed.

[0004] Moreover, in the method (Method 2) described in Patent Document 2, an abnormality diagnosis is performed on the vibration data of the diagnosis target based on a correlation coefficient between a Fourier spectrum of the vibration data in a normal state and a Fourier spectrum of the vibration data of the diagnosis target. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2004-279056 A [Patent Document 2] JP 2018-091033 A Summary of the Invention [Problem to be solved by the invention]

[0006] However, in method 1, even if the shape of the Fourier spectrum for the vibration data to be diagnosed is significantly different from that of normal data due to an abnormality in the motor, if the statistics such as the average value and maximum value are within the normal range, the data may be diagnosed as normal despite being abnormal. Note that the frequency with which such a misdiagnosis occurs in method 1 does not depend on the number of samples of normal data.

[0007] Furthermore, compared to method 2, method 1 requires more samples of normal data, and if the number of normal data samples is insufficient, the discrimination performance deteriorates significantly.

[0008] In addition, since the method 2 can perform a diagnosis taking into consideration the shape of the Fourier spectrum for the vibration data of the diagnosis target, it is possible to suppress the above-mentioned erroneous diagnosis. However, the discrimination performance of the method 2 is generally inferior to that of the method 1.

[0009] An object of the present invention is to provide an abnormality diagnosis device that can suppress erroneous diagnosis that occurs regardless of the number of normal data samples, and can suppress deterioration of discrimination performance due to an insufficient number of normal data samples. [Means for solving the problem]

[0010] One invention for achieving the above object is an abnormality diagnosis device including: a first processing unit that calculates a first index indicating a similarity between diagnostic data indicating a frequency spectrum of vibration of a target device and a first model constructed based on normal data indicating a frequency spectrum of vibration of the target device when the target device is normal; a second processing unit that calculates a second index indicating an abnormality degree of the target device based on the normal data and abnormal data indicating a frequency spectrum of vibration of the target device when the target device is abnormal, and the diagnostic data; and a diagnosis unit that diagnoses whether the target device is abnormal based on the first index and the second index. Other features of the present invention will become clear from the description of this specification. Effect of the Invention

[0011] According to the present invention, it is possible to provide an abnormality diagnosis device that can suppress erroneous diagnosis that occurs regardless of the number of normal data samples, and can suppress deterioration of discrimination performance due to an insufficient number of normal data samples. [Brief description of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram showing an overview of an abnormality diagnosis system. [Diagram 2] FIG. 2 is a diagram illustrating an example of a hardware configuration of an abnormality diagnosis device. [Diagram 3] FIG. 2 is a diagram illustrating an example of a functional block realized in the abnormality diagnosis device. [Figure 4] FIG. 11 is a diagram illustrating an example of diagnostic data. [Diagram 5] FIG. 11 is a diagram illustrating an example of processed diagnostic data. [Figure 6] FIG. 11 is a diagram showing an example of diagnostic data and normal data. [Figure 7] FIG. 13 is a diagram illustrating an example of a calculation result of a correlation coefficient. [Figure 8] FIG. 13 is a diagram showing an example of a calculation result of Q statistics. [Figure 9] 4 is a flowchart showing an example of a process executed by the abnormality diagnosis device. [Figure 10] FIG. 2 is a diagram illustrating an example of a functional block realized in the abnormality diagnosis device. [Figure 11] 4 is a flowchart showing an example of a process executed by the abnormality diagnosis device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] ==First embodiment== <Abnormality diagnosis system> Fig. 1 is a diagram showing an overview of an abnormality diagnosis system 1 of this embodiment. The abnormality diagnosis system 1 is a system for detecting abnormalities such as bearing abnormalities of an electric motor 62 driven by an inverter 61 in production equipment such as rolling equipment, based on information from a vibration sensor 2 that detects vibrations of the electric motor 62. The abnormality diagnosis system 1 includes the vibration sensor 2 and an abnormality diagnosis device 3. Each of them will be described below.

[0014] [Vibration sensor] The vibration sensor 2 is provided in a drive device 6 for driving a load. The drive device 6 has a power supply facility 60, an inverter 61, and an electric motor 62. The inverter 61 has a switching circuit that operates at a predetermined switching frequency, and drives the electric motor 62. In this embodiment, the electric motor 62 corresponds to the "target device (or target equipment)" that is the target of an abnormality diagnosis.

[0015] The vibration sensor 2 detects vibration of the electric motor 62. The vibration sensor 2 may be of a contact type or a non-contact type. The vibration sensor 2 outputs time-series data of the detected vibration as vibration data to an acquisition unit 40 (described later) of the abnormality diagnosis device 3.

[0016] [Abnormality diagnosis device] 2 is a diagram showing an example of a hardware configuration of the abnormality diagnosis device 3. The abnormality diagnosis device 3 is a computer including a CPU (Central Processing Unit) 30, a memory 31, a storage device 32, an input device 33, a display device 34, and a communication device 35.

[0017] The CPU 30 executes programs stored in the memory 31 and the storage device 32 to realize various functions of the abnormality diagnostic device 3 .

[0018] The memory 31 is, for example, a RAM (Random-Aaccess Memory) and is used as a temporary storage area for programs, data, and the like.

[0019] The storage device 32 is a non-volatile storage device that stores a first model M1, a second model M2, a third model M3, an abnormality diagnosis program P executed or processed by the CPU 30, and the like, which will be described later.

[0020] The abnormality diagnosis program P is a program for implementing various functions of the abnormality diagnosis device 3, and includes, for example, an OS (Operating System) and the like.

[0021] The input device 33 is a device that accepts commands and data input by a user, and includes an input interface such as a keyboard and a touch sensor that detects a touch position on a touch panel display.

[0022] The display device 34 is, for example, a device such as a display, etc. The communication device 35 exchanges data and various programs with the vibration sensor 2 and other computers via a network.

[0023] 3 is a diagram showing an example of functional blocks realized in the abnormality diagnosis device 3. When the CPU 30 of the abnormality diagnosis device 3 executes the abnormality diagnosis program P, an acquisition unit 40, a diagnosis data generation unit 41, a first processing unit 42, a second processing unit 43, a third processing unit 44, and a diagnosis unit 45 are realized in the abnormality diagnosis device 3.

[0024] The acquiring unit 40 acquires the vibration data output by the vibration sensor 2. The acquiring unit 40 may constantly acquire the vibration data output while the drive device 6 is in operation, or may acquire the vibration data output at a fixed time at a predetermined cycle. When acquiring the vibration data, the acquiring unit 40 outputs the vibration data to the diagnostic data generating unit 41.

[0025] The diagnostic data generating unit 41 generates diagnostic data based on the vibration data. The diagnostic data is data indicating a frequency spectrum of vibration of the electric motor 62. The diagnostic data will be described below with reference to Fig. 4. Fig. 4 is a diagram for explaining an example of the diagnostic data.

[0026] The diagnostic data generating unit 41 detects the vibration data x(t) at time t i The diagnostic data a is obtained by performing a Fourier transform shown in the following (Equation 1) on the range from in Generate. TIFF0007618971000001.tif9170

[0027] Diagnostic data a in In this case, the subscript i represents time t i From time t i +T. The subscript n indicates that the frequency component is n / T [Hz]. n ranges from 0 to a predetermined upper limit n max is an integer up to

[0028] In this embodiment, the time interval T is set to 50 μsec. max was set to 200. Then, the diagnostic data a in (n=0 to 200) is data extracted at 50 Hz intervals from the frequency spectrum in the range of 0 to 10 kHz.

[0029] The diagnostic data generating unit 41 executes the above-mentioned Fourier transform process using a fast Fourier transform algorithm.

[0030] The diagnostic data generating unit 41 of the present embodiment processes the diagnostic data shown in Fig. 4 obtained by Fourier transforming the vibration data, and generates the processed diagnostic data. Hereinafter, a detailed description will be given with reference to Figs. 4 and 5.

[0031] 4 is the diagnostic data before processing, and the diagnostic data before processing has sharp peaks near the frequencies of 4 kHz, 6 kHz, 8 kHz, and 10 kHz. These peaks are noise caused by the switching frequency of the switching circuit of the inverter 61. In other words, such noise is not caused by an abnormality in the electric motor 62.

[0032] Therefore, the diagnostic data is processed so that the contribution of noise caused by the switching frequency of the switching circuit is not reflected in the abnormality diagnosis process described later. Specifically, the diagnostic data in this embodiment is data that indicates the frequency spectrum of the vibration of the electric motor 62, and in which the frequency spectrum of the frequency band corresponding to the switching frequency of the switching circuit of the inverter 61 is suppressed.

[0033] FIG. 5 is a diagram for explaining an example of the processed diagnostic data. In the processed diagnostic data shown in FIG. 5, the frequency spectrum corresponding to the frequency band of 400 Hz around each of the frequencies of 4 kHz, 6 kHz, 8 kHz, and 10 kHz is set to 0, in comparison with the unprocessed diagnostic data shown in FIG. 4. In other words, the processed diagnostic data a in In (n=0 to 200), the components of n=76 to 85, 116 to 124, 156 to 164, and 196 to 200 are set to 0. Hereinafter, the processed diagnostic data will be simply referred to as diagnostic data.

[0034] The first processing unit 42 calculates a first index indicating the similarity between the diagnostic data and the first model M1. The first model M1 is a model constructed based on normal data. The normal data is data indicating the frequency spectrum of vibration of the electric motor 62 when the electric motor 626 is normal. This will be described in detail below.

[0035] First, normal data will be described. Fig. 6 is a diagram showing an example of diagnostic data and normal data. In Fig. 6, an example of diagnostic data is shown by a solid line, and an example of normal data is shown by a dashed line.

[0036] In the following explanation, normal data is jn (j=1~j max , n=0~n max ) where the subscript j is used to distinguish between multiple normal data, each of which is based on vibration data output at a different time. The subscript n indicates that the frequency component has an amplitude of n / T [Hz], just like the diagnostic data. jnis data obtained by performing a Fourier transform on the vibration data output by the vibration sensor 2 when the electric motor 62 is normal, in the same manner as in (Equation 1) above.

[0037] Next, the first model M1 will be described. The first model M1 of this embodiment is a model that uses a plurality of normal data b jn The average value of M1 n (n=0~n max ) where the subscript n indicates that the frequency component has an amplitude of n / T [Hz], just like the diagnostic data. In other words, the first model M1 n is multiple normal data b jn The sum of j for j is max This is the value divided by .

[0038] Next, the first index indicating the similarity will be described. In this embodiment, the first processing unit 42 calculates the diagnostic data a jn (n=0~n max ) and the first model M1 n (n=0~n max ) and the correlation coefficient r, which indicates the degree of similarity i is calculated as the first index. The correlation coefficient r i is defined as follows (Equation 2). In TIFF0007618971000002.tif13170 (Equation 2), Defined as TIFF0007618971000003.tif22170.

[0039] The correlation coefficient is a value between 0 and 1, and the closer to 1 the correlation coefficient is, the higher the similarity between the diagnostic data and the first model M1. In other words, the closer the correlation coefficient r is to 1, the more likely it is that the motor 62 is operating normally at the time when the disturbance data based on the diagnostic data is output. In particular, if the correlation coefficient is about 0.6 or more, it can be considered that the motor is operating normally. Also, when the correlation coefficient is 1, the diagnostic data a jn (n=0~n max ) and the first model M1 n (n=0~n max ) is the same.

[0040] The first processing unit 42 calculates correlation coefficients for the diagnostic data sequentially output from the diagnostic data generating unit 41 according to the above procedure. FIG. 7 is a diagram showing an example of the calculation result of the correlation coefficient. FIG. 7 shows the correlation coefficients calculated for each of the diagnostic data sequentially output with sample numbers 1 to 17. The dashed line in the figure indicates the position where the correlation coefficient is 0.6. The sample numbers here are the correlation coefficients calculated for the diagnostic data a in corresponds to the subscript i in

[0041] In the above, the correlation coefficient has been exemplified as the first index showing the similarity in this embodiment, but the present invention is not limited to this. As another example, the inner product (cosine similarity) may be used. In this case, the diagnostic data a jn (n=0~n max ) and the first model M1 n (n=0~n max ) and the inner product of n i is defined as follows (Equation 5). TIFF0007618971000004.tif12170

[0042] The second processing unit 43 calculates a second index indicating the degree of abnormality of the motor 62 based on the second model M2 and the diagnosis data. The second model M2 is a model constructed based on normal data and abnormal data. The abnormal data is data indicating a frequency spectrum of vibration of the motor 62 when the motor 62 is abnormal.

[0043] In this embodiment, the second processing unit 43 calculates the second index using a second model M2 constructed by multivariate statistical process control. In this embodiment, the Q statistic is used as the second index. The smaller the Q statistic is, the lower the degree of abnormality of the motor 62 is, and the larger the Q statistic is, the higher the degree of abnormality of the motor 62 is. In particular, when the Q statistic is 1.0×10 4 If it is below this level, the motor 62 can be considered normal.

[0044] The second processing unit 43 calculates Q statistics for the diagnostic data sequentially output from the diagnostic data generating unit 41. FIG. 8 is a diagram showing an example of the calculation result of the Q statistics. FIG. 8 shows the Q statistics calculated for each of the sequentially output diagnostic data with sample numbers 1 to 17. The dashed line in the figure indicates the Q statistics calculated for each of the sequentially output diagnostic data with sample numbers 1 to 17. 4 The sample number indicates the location of the diagnostic data a in corresponds to the subscript i in

[0045] In the present embodiment, the second model M2 is constructed by multivariate statistical process control, but the present invention is not limited to this. As another example, the second model M2 may be constructed by using a machine learning model such as a support vector machine.

[0046] The third processing unit 44 calculates a third index indicating the degree of similarity between the statistics of the diagnostic data and the statistics of the third model M3. The third model M3 is a model constructed based on normal data. The third model M3 is constructed by calculating the average value of a plurality of normal data, similar to the above-mentioned first model M1. The third model M3 may be the same model as the first model M1. Alternatively, the third model M3 may be constructed using a set of normal data different from the set of normal data used when constructing the first model M1.

[0047] The statistics here include at least one of the average value, the maximum value, and the standard deviation. Here, the average value, the maximum value, and the standard deviation of the diagnostic data are in The subscript n is the sample number. The mean, maximum and standard deviation of the third model M3 are calculated in the same manner.

[0048] In this embodiment, the average value is used as the statistical quantity. in (n=1~n max ) is taken as A, and the third model M3 n (n=1~n max) is defined as a. The ratio of A to a (A / a) is defined as the third index. The closer the third index is to 1, the higher the similarity, and the farther it is from 1, the lower the similarity.

[0049] In particular, when an average value is used as a statistical quantity as in this embodiment, if the third index (A / a) is smaller than 0.5 or larger than 2, there is a high possibility that a bearing abnormality has occurred in the electric motor 62.

[0050] The diagnosing unit 45 diagnoses whether or not the electric motor 62 is abnormal based on the first to third indexes. For example, the diagnosing unit 45 may diagnose whether or not the electric motor 62 is abnormal based on a result obtained by weighting the normalized values ​​of each of the first index, the second index, and the third index.

[0051] Specifically, the first index (correlation coefficient), the second index (Q statistic), and the third index (similarity of statistics) are normalized to the range of 0 to 1 to be α, β, and γ, respectively.

[0052] In this normalization, the correlation coefficient r calculated by the first processing unit 42 is used. i can simply be used as α. Regarding the Q statistic, the lower the degree of anomaly (the smaller the Q statistic), the closer β is to 1, and the higher the degree of anomaly (the larger the Q statistic), the closer β is to 0. Regarding the similarity of the statistics, the closer the similarity of the statistics is to 1, the closer γ is to 1, and the further away the similarity of the statistics is from 1, the closer γ is to 0.

[0053] The weights for α, β, and γ are w α , w β and w γ Then, the weighted quantity W(=w α α+w β β+w γ Based on this, it is determined whether the motor 62 is abnormal.

[0054] Here, w α , w βand w γ If these weights are determined so that the sum of these is 1, the weighted amount W will be equal to or greater than 0 and equal to or less than 1. Therefore, a threshold value, for example 0.5, may be set in advance, and the diagnosing unit 45 may diagnose the weighted amount W as normal when it is greater than the threshold value, and diagnose the weighted amount W as abnormal in other cases.

[0055] Weight w α , w β and w γ A method for determining the number of normal data items used in constructing the first to third models (M1 to M3) can be considered, for example. This will be described in detail below.

[0056] When constructing the first to third models (M1 to M3), the number of normal data required differs depending on each model. Here, the number of normal data required is the number of normal data required to obtain calculation results of reliable indices (first to third indices). Here, the calculation results of reliable indices are calculation results of indices that are reproduced with a certain level or more of uniqueness.

[0057] For example, in general, the number of pieces of normal data required to construct the second model M2 is greater than the number of pieces of normal data required to construct the first model M1 or the third model M3.

[0058] In addition, in general, the reliability of the Q statistic calculated using the number of normal data required to construct the second model M2 is higher than the reliability of the correlation coefficient calculated using the same number of normal data.

[0059] Therefore, if the number of normal data used in constructing the second model M2 is equal to or greater than the number required to construct the second model M2, it is preferable to give the largest weight to the normalized value β of the Q statistic. α , w β , w γ Weightings such as 0.25, 0.50, 0.25 may also be used.

[0060] On the other hand, when the number of normal data used is less than the number required to construct the second model M2 but is equal to or greater than the number required to construct the first model M1, the reliability of the calculated Q statistic is lower than the reliability of the calculated correlation coefficient.

[0061] Therefore, in such a case, it is preferable to give the smallest weight to the normalized value β of the Q statistic. α , w β , w γ Weighting such as 0.40, 0.20, 0.40 may also be used.

[0062] <Abnormality diagnosis processing> An example of the process executed by each functional block will be described below with reference to Fig. 9 etc. Fig. 9 is a flowchart showing an example of the process executed by the abnormality check device 3.

[0063] First, the acquisition unit 40 acquires vibration data output by the vibration sensor 2 (S10). Next, the diagnostic data generation unit 41 generates diagnostic data a based on the vibration data. in is generated (S11).

[0064] Next, the first processing unit 42 calculates a first index indicating the similarity between the diagnostic data and the first model M1 (S12). The first model M1 is constructed in advance based on a plurality of normal data. In addition, the first index indicating the similarity in this embodiment is a correlation coefficient.

[0065] Next, the second processing unit 43 calculates a second index indicating the degree of abnormality of the motor 62 based on the second model M2 and the diagnosis data (S13). The second model M2 is constructed in advance by applying a plurality of normal data and a plurality of abnormal data to multivariate statistical process control. The second index in this embodiment is a Q statistic.

[0066] Next, the third processing unit 44 calculates a third index indicating the similarity between the statistics of the diagnostic data and the statistics of the third model M3 (S14). The third model M3 is constructed in advance based on a plurality of normal data. In addition, the third index indicating the similarity in this embodiment is the ratio (A / a) of the average value A of the diagnostic data to the average value a of the third model M3.

[0067] Next, the diagnosis unit 45 diagnoses whether or not the electric motor 62 is abnormal based on the first to third indexes, and outputs the diagnosis result (S15). The diagnosis unit 45 diagnoses whether or not the electric motor 62 is abnormal based on the result obtained by weighting the normalized values ​​of each of the first index, the second index, and the third index, for example.

[0068] The order in which S12, S13, and S14 are executed is arbitrary and is not limited to the above example. Also, S12, S13, and S14 may be executed in parallel.

[0069] ==Second embodiment== 10 is a diagram showing an example of functional blocks of this embodiment realized in the abnormality diagnosis device 3. The functions of this embodiment realized in the abnormality diagnosis device 3 are different from the functions of the first embodiment realized in the abnormality diagnosis device 3 in a first processing unit 52, a second processing unit 53, a third processing unit 54, and a diagnosis unit 55. The acquisition unit 50 and the diagnosis data generation unit 51 are similar to the acquisition unit 40 and the diagnosis data generation unit 41 of the first embodiment, and therefore a description thereof will be omitted.

[0070] The first processing unit 52 outputs a first diagnosis result indicating whether the electric motor 62 is abnormal or not based on the first index. Specifically, the first processing unit 52 outputs the first diagnosis result by comparing the first index with a predetermined first threshold. In this embodiment, the first processing unit 52 diagnoses the electric motor 62 as normal when the correlation coefficient is greater than the first threshold, and diagnoses the electric motor 62 as abnormal in other cases. For example, 0.6 can be used as the first threshold.

[0071] In this embodiment, the first diagnostic result is set to 1 if normal, and set to 0 if not normal. The same applies to the second and third diagnostic results described below.

[0072] The second processing unit 53 outputs a second diagnosis result indicating whether or not the electric motor 62 is abnormal based on the second index. Specifically, the second processing unit 53 outputs the second diagnosis result by comparing the second index with a predetermined second threshold. In this embodiment, the second processing unit 53 diagnoses that the electric motor 62 is normal when the Q statistics is smaller than the predetermined second threshold, and diagnoses that the electric motor 62 is abnormal in other cases. The second threshold is, for example, 1.0×10 4 can be used.

[0073] The third processing unit 54 outputs a third diagnosis result indicating whether or not the electric motor 62 is abnormal based on the third index. Specifically, the third processing unit 54 outputs the third diagnosis result by comparing the third index with a predetermined third threshold. In this embodiment, the third processing unit 54 diagnoses the electric motor 62 as normal when the ratio (A / a) between the average value A of the diagnostic data described in the first embodiment and the average value a of the third model M3 is within a predetermined range, and diagnoses the electric motor 62 as abnormal in other cases. The predetermined range can be, for example, 0.5 to 2.0.

[0074] The diagnostic unit 55 outputs a fourth diagnostic result indicating whether or not the electric motor 62 is abnormal, based on the first to third diagnostic results. The diagnostic unit 55 may output the fourth diagnostic result based on a value obtained by adding the first diagnostic result, the second diagnostic result, and the third diagnostic result. As described above, the first to third diagnostic results are 0 (abnormal) or 1 (normal). Therefore, the value obtained by adding the first to third diagnostic results is equal to or greater than 0 and equal to or less than 3. The diagnostic unit 55 may diagnose the motor 62 as normal if the added value is, for example, 2 or 3.

[0075] Alternatively, the diagnostic unit 55 may output the fourth diagnostic result based on the results obtained by weighting each of the first diagnostic result, the second diagnostic result, and the third diagnostic result according to the number of normal data.

[0076] As a specific example, assume that the first, second, and third diagnostic results are 0 (abnormal), 1 (normal), and 1 (normal), respectively. Then, the weights for the first, second, and third diagnostic results are w α , w β and w γ In this case, the weighted quantity W is W = 0 × w α +1×w β +1×w γ =w β +w γ Then, based on this weighted amount W, it is diagnosed whether or not the electric motor 62 is abnormal.

[0077] Here, the weight w α , w β and w γ As a method for determining the above and a method for diagnosing an abnormality, the methods described in the first embodiment can be used.

[0078] <Abnormality diagnosis processing> An example of the process executed by each functional block will be described below with reference to Fig. 11 etc. Fig. 11 is a flowchart showing an example of the process executed by the abnormality check device 3.

[0079] In the flowchart shown in FIG. 11, S22, S24, and S26 are similar to S12, S13, and S14, respectively, described with reference to FIG. 9 in the first embodiment, and therefore detailed description thereof will be omitted.

[0080] After calculating the first index in S22, the first processing unit 52 outputs a first diagnosis result indicating whether or not the electric motor 62 is abnormal, based on the first index (S23).

[0081] Next, after calculating the second index in S24, the second processing unit 53 outputs a second diagnosis result indicating whether or not the electric motor 62 is abnormal, based on the second index (S25).

[0082] Next, the third processing unit 54 calculates the third index in S26, and then outputs a third diagnosis result indicating whether or not the electric motor 62 is abnormal, based on the third index (S27).

[0083] Next, the diagnosis unit 55 outputs a fourth diagnosis result indicating whether or not the electric motor 62 is abnormal based on the first to third diagnosis results (S28). The diagnosis unit 55 may output the fourth diagnosis result based on a result obtained by weighting each of the first diagnosis result, the second diagnosis result, and the third diagnosis result according to the number of normal data.

[0084] It should be noted that S23, S25, and S27 may be executed after S22, S24, and S26, respectively, and the order of S22 to S26 is not limited to that in this example.

[0085] ===Summary=== As described above, the abnormality diagnosis device 3 of the first and second embodiments includes a first processing unit 42 that calculates a first index indicating the similarity between diagnostic data indicating the frequency spectrum of vibration of the target device and a first model constructed based on normal data indicating the frequency spectrum of vibration of the target device when the target device is normal, a second processing unit 43 that calculates a second index indicating the degree of abnormality of the target device based on the normal data and abnormal data indicating the frequency spectrum of vibration of the target device when the target device is abnormal, and the diagnostic data, and a diagnosis unit 45 that diagnoses whether the target device is abnormal or not based on the first index and the second index.

[0086] This makes it possible to suppress erroneous diagnosis that occurs regardless of the number of normal data samples, and also to suppress deterioration of discrimination performance due to an insufficient number of normal data samples.

[0087] In the above-mentioned abnormality diagnosis device 3, the first processing unit 42 calculates a correlation coefficient indicating the similarity between the diagnosis data and the first model as a first index. By taking the correlation coefficient into consideration, it is possible to obtain reliable diagnosis results even when the number of normal data used is insufficient.

[0088] In the above-mentioned abnormality diagnosis device 3, the second processing unit 43 calculates the second index using a second model constructed by multivariate statistical process control. By using multivariate statistical process control, the reliability of the diagnosis result is improved as the number of normal data used increases.

[0089] The abnormality diagnosis device 3 further includes a third processing unit 44 that calculates a third index indicating the degree of similarity between the statistics of the diagnosis data and the statistics of a third model constructed based on normal data, and a diagnosis unit 45 diagnoses whether the target device is abnormal or not based on the first to third indexes. This allows for an intuitive and easy-to-understand diagnosis method to be adopted.

[0090] In the above-described abnormality diagnosis device, the statistics include at least one of an average value, a maximum value, and a standard deviation, thereby making it possible to adopt a more intuitive and easy-to-understand diagnosis method.

[0091] Furthermore, in the abnormality diagnosis device 3 of the first embodiment, the diagnosis unit 45 diagnoses whether or not the target device is abnormal based on the results obtained by weighting the normalized values ​​of each of the first index, the second index, and the third index according to the number of normal data. This makes it possible to obtain a reliable diagnosis result overall by reducing the contribution of reliable indexes due to a lack of the required number of normal data when constructing any of the models.

[0092] In the abnormality diagnosis device 3 of the second embodiment, the first processing unit 42 outputs a first diagnostic result indicating whether or not the target device is abnormal based on the first index, the second processing unit 43 outputs a second diagnostic result indicating whether or not the target device is abnormal based on the second index, the third processing unit 44 outputs a third diagnostic result indicating whether or not the target device is abnormal based on the third index, and the diagnosis unit 45 outputs a fourth diagnostic result indicating whether or not the target device is abnormal based on the first to third diagnostic results. Since the diagnosis results by each diagnosis method can be confirmed, if the fourth diagnostic result is abnormal, it becomes easier to identify the cause of the diagnosis of abnormality.

[0093] Moreover, in the abnormality diagnosis device of the second embodiment, the diagnosis unit 45 outputs a fourth diagnosis result based on the results obtained by weighting each of the first diagnosis result, the second diagnosis result, and the third diagnosis result according to the number of normal data. This makes it possible to obtain a reliable diagnosis result overall by reducing the contribution of reliable indicators due to a shortage of the number of necessary normal data when constructing any of the models.

[0094] In the above-mentioned abnormality diagnosis device 3, the target device has a switching circuit that operates at a predetermined switching frequency, and the diagnosis data is data that indicates the frequency spectrum of the vibration of the target device, and in which the frequency spectrum of the frequency band corresponding to the predetermined switching frequency is suppressed. This makes it possible to suppress erroneous diagnosis caused by switching noise even if switching noise is included in the vibration data.

[0095] The present invention also includes a processing unit that calculates an index indicating the degree of similarity between the diagnostic data indicating the frequency spectrum of the vibration of the target device and the model constructed based on normal data indicating the frequency spectrum of the vibration of the target device when the target device is normal, and a diagnosis unit that diagnoses whether the target device is abnormal based on the index. This makes it possible to suppress deterioration of discrimination performance due to a shortage of samples of normal data.

[0096] The present invention also includes a processing unit that calculates an index indicating the degree of abnormality of the target device based on a model constructed based on normal data indicating the frequency spectrum of the vibration of the target device when the target device is normal and abnormal data indicating the frequency spectrum of the vibration of the target device when the target device is abnormal, and diagnostic data indicating the frequency spectrum of the vibration of the target device, and a diagnostic unit that diagnoses whether the target device is abnormal based on the index. This makes it possible to take into account the shape of the frequency spectrum when diagnosing an abnormality, thereby suppressing erroneous diagnosis that occurs regardless of the number of samples of normal data.

[0097] Moreover, the abnormality diagnosis system 1 of the first embodiment and the second embodiment includes the abnormality diagnosis device 3 of the first embodiment or the abnormality diagnosis device 3 of the second embodiment, which further includes an acquisition unit 40 that acquires vibration data output by the vibration sensor 2 provided in the target device and a diagnostic data generation unit 41 that generates diagnostic data based on the vibration data, and the vibration sensor 2 provided in the target device. This makes it possible to suppress erroneous diagnosis that occurs regardless of the number of normal data samples, and to suppress deterioration of discrimination performance due to an insufficient number of normal data samples.

[0098] The above-mentioned embodiment is for the purpose of facilitating understanding of the present invention, and is not intended to limit the present invention. Furthermore, the present invention can be modified or improved without departing from the spirit of the present invention, and it goes without saying that the present invention includes equivalents thereof. [Explanation of symbols]

[0099] 1: Abnormality diagnosis system 2: Vibration sensor 3: Abnormality diagnosis device 30: CPU 31: Memory 32: Storage device 33: Input device 34:Display device 35:Communication equipment 40: Acquisition Department 41: Diagnostic data generation unit 42: First processing section 43: Second processing section 44: Third processing section 45: Diagnostics Department 50: Acquisition section 51: Diagnostic data generation unit 52: First processing section 53: Second processing section 54: Third processing section 55: Diagnostics Department 6: Drive unit 60:Power equipment 61: Inverter 62: Electric motor

Claims

1. Diagnostic data showing a frequency spectrum of vibration of a target device and the target device when the target device is normal a first processing unit that calculates a first index indicating a similarity between the first model and a first model constructed based on normal data indicating a frequency spectrum of a vibration of the target device; a second processing unit that calculates a second index indicating an abnormality degree of the target device based on the normal data and abnormality data indicating a frequency spectrum of vibration of the target device when the target device is abnormal, and the diagnosis data; a third processing unit that calculates a third index indicating a similarity between statistics of the diagnostic data and statistics of a third model constructed based on the normal data; a diagnosis unit that diagnoses whether or not the target device is abnormal based on a result obtained by weighting the normalized values ​​of each of the first index, the second index, and the third index in accordance with the number of normal data; An abnormality diagnosis device comprising:

2. The first processing unit is A correlation coefficient indicating a degree of similarity between the diagnostic data and the first model is calculated as the first index. The abnormality diagnosis device according to claim 1 .

3. The second processing unit is Calculating the second indicator using the second model constructed by multivariate statistical process control. The abnormality diagnosis device according to claim 1 or 2.

4. The abnormality diagnosis device as described in claim 1, characterized in that the statistical quantities include at least one of an average value, a maximum value, and a standard deviation.

5. The first processing unit outputs a first diagnosis result indicating whether or not the target device is abnormal based on the first indicator; The second processing unit outputs a second diagnosis result indicating whether or not the target device is abnormal based on the second indicator; and The third processing unit outputs a third diagnosis result indicating whether or not the target device is abnormal based on the third indicator; and The diagnostic unit outputs a fourth diagnostic result indicating whether or not the target device is abnormal based on the first to third diagnostic results. The abnormality diagnosis device according to claim 1 .

6. The abnormality diagnosis device described in Claim 5, wherein the diagnostic unit outputs the fourth diagnostic result based on the results obtained by weighting each of the first diagnostic result, the second diagnostic result, and the third diagnostic result in accordance with the number of normal data.

7. The target device has a switching circuit that operates at a predetermined switching frequency, The diagnostic data is data in which a frequency spectrum of a frequency band corresponding to the predetermined switching frequency is suppressed among data indicating a frequency spectrum of vibration of the target device. The abnormality diagnosis device according to any one of claims 1 to 6.

8. An acquisition unit that acquires vibration data output by a vibration sensor provided in the target device; The abnormality diagnosis device according to any one of claims 1 to 7, further comprising: a diagnostic data generation unit that generates the diagnostic data based on the vibration data; The vibration sensor is provided in the target device.

Images