Rotational speed measuring device, rotational speed measuring system, and rotational speed measuring method

Abstract

Conventional blower rotation speed measuring devices have the problem of not being able to accurately read the frequency components that contribute to the rotation speed, resulting in reduced accuracy of rotation speed measurement. The objective is to provide a rotation speed measuring device, rotation speed measuring system, and rotation speed measuring method that can improve the accuracy of blower rotation speed measurement. [Solution] A rotational speed measuring device comprising a sensor unit that acquires the operating sound of a blower, and a calculation unit that converts the operating sound into a frequency spectrum, detects the peak frequency of the operating sound from the frequency spectrum, and calculates the rotational speed of the blower by dividing the peak frequency by the number of blades of the blower.

Description

Technical Field

[0001] The present disclosure relates to a rotational speed measuring device, a rotational speed measuring system, and a rotational speed measuring method for measuring the rotational speed of a blower.

Background Art

[0002] There is a rotational speed measuring device that measures the operating sound of a blower with a sensor and calculates the rotational speed. By measuring the rotational speed of the blower, it is possible to detect abnormalities and deterioration of the blower.

[0003] Patent Document 1 discloses a rotational speed measuring device that measures the wind discharged from a blower with a sensor and determines the rotational speed of the blower. In the rotational speed measuring device described in Patent Document 1, the rotational speed of the blower is measured by detecting the pulsation frequency of the wind measured in the wind tunnel section or the air flow path of the blower and dividing it by the number of blades.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, in the rotational speed measuring device of the blower described in Patent Document 1, when the flow in the flow path of the blower is not uniform, the pulsation frequency of the wind cannot be accurately detected. For this reason, the conventional rotational speed measuring device of the blower has a problem that the frequency components contributing to the rotational speed cannot be accurately read and the measurement accuracy of the rotational speed decreases.

[0006] The present disclosure has been made to solve such problems, and an object thereof is to provide a rotational speed measuring device, a rotational speed measuring system, and a rotational speed measuring method capable of improving the measurement accuracy of the rotational speed of a blower. [Means for solving the problem]

[0007] The rotational speed measuring device according to this disclosure comprises a sensor unit that acquires the operating sound of a blower, and a calculation unit that converts the operating sound into a frequency spectrum, detects the peak frequency of the operating sound from the frequency spectrum, and calculates the rotational speed of the blower by dividing the peak frequency by the number of blades of the blower.

[0008] The rotational speed measuring device according to this disclosure comprises a sensor unit that acquires the operating sound of a blower, a calculation unit that converts the operating sound into a frequency spectrum, a data acquisition unit that acquires the frequency spectrum from the calculation unit, and an inference unit that uses a trained model that infers a value obtained by multiplying the rotational speed of the blower by the number of blower blades from the frequency spectrum acquired by the data acquisition unit, and outputs a blade rotation peak frequency which is a value obtained by multiplying the rotational speed of the blower by the number of blower blades from the frequency spectrum acquired by the data acquisition unit, and the calculation unit calculates the rotational speed of the blower by dividing the blade rotation peak frequency by the number of blower blades.

[0009] The rotational speed measurement system according to this disclosure comprises a blower, a sensor unit that acquires the operating sound of the blower, and a calculation unit that converts the operating sound into a frequency spectrum, detects the peak frequency of the operating sound from the frequency spectrum, and calculates the rotational speed of the blower by dividing the peak frequency by the number of blades of the blower.

[0010] The rotational speed measurement method according to this disclosure comprises the steps of: a sensor unit acquiring the operating sound of a blower; a calculation unit converting the operating sound into a frequency spectrum; a calculation unit detecting the peak frequency of the operating sound from the waveform of the frequency spectrum; and a calculation unit calculating the rotational speed of the blower by dividing the frequency spectrum by the number of blades of the blower. [Effects of the Invention]

[0011] The rotational speed measuring device, rotational speed measuring system, and rotational speed measuring method described herein can improve the accuracy of measuring the rotational speed of a blower. [Brief explanation of the drawing]

[0012] [Figure 1] This is a schematic diagram showing the configuration of a rotational speed measuring device according to Embodiment 1 of the present disclosure. [Figure 2] This is a graph showing the frequency spectrum of the operating sound of a blower converted by the calculation unit of the rotational speed measuring device according to Embodiment 1 of this disclosure. [Figure 3] This is a flowchart showing the rotational speed measurement method according to Embodiment 1 of the present disclosure. [Figure 4] This is a schematic diagram showing the configuration of the rotational speed measurement system according to Embodiment 1 of the present disclosure. [Figure 5] This graph shows the frequency spectrum of the operating sound of a blower having a weather cover and shutter, converted by the calculation unit of the rotational speed measuring device according to Embodiment 2 of the present disclosure. [Figure 6] This is a schematic diagram showing the position of the sensor part of the rotational speed measuring device according to Embodiment 3 of the present disclosure. [Figure 7] This is a schematic diagram showing the configuration of a rotational speed measuring device according to Embodiment 4 of the present disclosure. [Figure 8] This is a schematic diagram showing a learning collection device for generating a learned model of a rotational speed measuring device according to Embodiment 4 of the present disclosure. [Figure 9] This is a schematic diagram showing a neural network used in a rotational speed measuring device according to Embodiment 4 of the present disclosure. [Modes for carrying out the invention]

[0013] The rotational speed measuring device, rotational speed measuring system, and rotational speed measuring method related to this disclosure will be described below with reference to the drawings.

[0014] Embodiment 1. FIG. 1 is a schematic diagram showing the configuration of a rotational speed measurement device according to Embodiment 1 of the present disclosure. As shown in FIG. 1, a rotational speed measurement device 100 according to Embodiment 1 of the present disclosure includes a sensor unit 1 and a calculation unit 2. The sensor unit 1 may be, for example, a microphone or the like as long as it can acquire the operating sound of the blower 3. The operating sound is the sound emitted by the blower 3 during operation. The blower 3 is, for example, an exhaust fan, a circulation fan, a fan for an air conditioner, or the like. The calculation unit 2 is, for example, a microcomputer or the like.

[0015] FIG. 2 is a graph showing the frequency spectrum of the operating sound of the blower converted by the calculation unit of the rotational speed measurement device according to Embodiment 1 of the present disclosure. In the graph shown in FIG. 2, the vertical axis represents the sound pressure level (SPL) [dB], which is the unit indicating the intensity of the spectrum, and the horizontal axis represents the frequency [Hz]. As shown in FIG. 2, the operating sound of the blower 3 becomes a graph having a plurality of peaks when converted into a frequency spectrum. The operating sound acquired by the blower 3 is converted into a frequency spectrum by the calculation unit 2 using the Fourier series formulas shown in the following formulas (1) to (4).

[0016]

Equation

[0017]

Equation

[0018]

Equation

[0019]

Equation

[0020] Equation (1) is the Fourier series expansion of a function with period 2T, and the operating sound acquired by the blower 3 corresponds to f(t) in equations (1) to (3). an and bn are the coefficients of the Fourier series expansion when the operating sound is treated as a function. Here, n is the order, and n = 0, 1, 2... cn is a number determined by an and bn, and represents the spectrum of the magnitude of the nth wave. In this way, the calculation unit 2 converts the operating sound acquired by the sensor unit 1 into a frequency spectrum.

[0021] If we use the frequency corresponding to the rotational speed of the blower 3 as a reference, then in the case of 3 blades, the noise caused by the blades will peak at a frequency obtained by multiplying the rotational speed of the blower 3 by the number of blades, which is 3. In other words, by dividing these frequencies by the number of blades, the rotational frequency of the blower 3 can be calculated inversely. These frequencies appear as peak frequencies, and methods for determining peak frequencies generally include using differentiation. For example, to determine the peak frequency using differentiation, the frequency spectrum plotted with n on the x-axis and the logarithm of Cn on the y-axis is differentiated with respect to n, and the frequency at the point where the derivative is zero is taken as the peak frequency.

[0022] The frequency spectrum of the operating sound converted by the calculation unit 2 has a peak frequency of a sound called the NZ sound, as shown in Figure 2. The NZ sound is a sound that depends on the rotational speed N and the number of blades Z of the blower 3, and is also called rotational sound. Its peak frequency appears around a frequency that is an integer multiple of the value obtained by multiplying the rotational speed of the blower 3 by the number of blades. By selecting a value of 1 multiplied by the value obtained by multiplying the rotational speed of the blower 3 by the number of blades, the user of the blower 3 can know in advance the frequency at which the NZ sound will be generated.

[0023] When a frequency spectrum like that shown in Figure 2 is obtained, the calculation unit 2 detects the peak frequency from the frequency spectrum and calculates the rotational speed of the blower by dividing the peak frequency by the number of blades of the blower 3.

[0024] Figure 3 is a flowchart illustrating a rotational speed measurement method according to Embodiment 1 of the present disclosure. As shown in Figure 1, the rotational speed measurement method according to Embodiment 1 of the present disclosure first involves the sensor unit 1 acquiring the operating sound of the blower 3 in step S1. In step S2, the calculation unit 2 converts the operating sound into a frequency spectrum. In step S3, the calculation unit detects the peak frequency of the operating sound from the waveform of the frequency spectrum. In step S4, the calculation unit calculates the rotational speed of the blower 3 by dividing the frequency spectrum by the number of blades of the blower 3. In this way, the rotational speed measurement method according to Embodiment 1 of the present disclosure measures the rotational speed of the blower 3.

[0025] Figure 4 is a schematic diagram showing the configuration of a rotational speed measurement system according to Embodiment 1 of the present disclosure. As shown in Figure 4, the rotational speed measurement system according to Embodiment 1 of the present disclosure comprises a blower 3 and a rotational speed measuring device 100.

[0026] As described above, according to the rotational speed measuring device 100, rotational speed measuring method, and rotational speed measuring system 200 of Embodiment 1 of this disclosure, the calculation unit 2 converts the operating sound of the blower 3 into a frequency spectrum to detect the peak frequency of the operating sound, and calculates the rotational speed of the blower 3 by dividing the peak frequency by the number of blades of the blower 3. Because the rotational speed measuring device 100, rotational speed measuring method, and rotational speed measuring system 200 of Embodiment 1 of this disclosure use the peak frequency of the operating sound, the measurement accuracy of the rotational speed of the blower 3 can be improved.

[0027] Furthermore, the rotational speed measuring device 100 according to Embodiment 1 of this disclosure may also include a notification unit that compares the rotational speed calculated by the calculation unit with the rotational speed input to the blower 3 and notifies when a difference in rotational speed occurs. A threshold value that can be set by the user of the blower 3 may be set for the difference in rotational speed. For example, a notification of deterioration may be given when the difference between the measured rotational speed and the rotational speed input to the blower 3 is 10% or more. The difference in rotational speed may also be the difference from the initial rotational speed when the blower 3 was installed on site. By notifying when the rotational speed changes from the initially set rotational speed, clogging of the filter and other issues can be detected early. The initial rotational speed may be automatically input to the calculation unit 2 when it is set. The notification unit 9 notifies of the deterioration of the blower 3 by an alert sound, output of a message to a monitor or mobile terminal, illumination of an LED, etc.

[0028] The rotational speed measuring device 100 according to Embodiment 1 of this disclosure is equipped with a notification unit 9, which allows the rotational speed measuring device 100 according to Embodiment 1 of this disclosure to quickly detect deterioration of the blower 3, thereby enabling efficient maintenance of the blower 3.

[0029] Embodiment 2. In Embodiment 2, the same reference numerals are used for the same components as in Embodiment 1 of this disclosure, and descriptions of the same or corresponding parts are omitted. In Embodiment 2, the method of calculating the rotational speed in the calculation unit 2 differs mainly from that of Embodiment 1. The rotational speed measuring device 101 according to Embodiment 2 will be described below with reference to the drawings.

[0030] Figure 5 is a graph showing the frequency spectrum of the operating sound of a blower having a weather cover and shutter, converted by the calculation unit 2 of the rotational speed measuring device according to Embodiment 2 of this disclosure. As shown in Figure 3, when a weather cover and shutter are provided on the blower 3, the number and intensity of the peaks in the frequency spectrum of the operating sound change compared to Figure 2. In such cases, the spectrum at frequencies twice or more than one times the frequency of the NZ sound may have a stronger intensity than the spectrum at one times the frequency of the NZ sound. Therefore, it was difficult for the calculation unit 2 to identify the peak frequency of the operating sound of the blower 3.

[0031] In the second embodiment of the present disclosure, the rotational speed measuring device 101, when multiple peak frequencies are detected by the calculation unit 2, calculates the rotational speed using the lowest peak frequency among frequency spectra having a predetermined intensity. Here, a frequency spectrum having a predetermined intensity is, for example, an intensity of more than half that of the frequency spectrum with the highest intensity. By setting a threshold for the intensity of the frequency spectrum in this way, the frequency spectrum of the NZ sound can be identified even when the spectrum at a frequency more than twice that of the NZ sound has a stronger intensity than the spectrum at a frequency one times that of the NZ sound, as shown in Figure 5. The second embodiment of the present disclosure makes it easier to identify the peak frequency of the blower 3, and therefore the measurement accuracy of the rotational speed of the blower 3 can be improved.

[0032] Furthermore, in the rotational speed measuring device 101 according to Embodiment 2 of this disclosure, when multiple peak frequencies are detected, the calculation unit 2 calculates candidate rotational speeds of the blower 3 by dividing the peak frequency of the frequency spectrum having a predetermined intensity by the number of blades of the blower 3, and the rotational speed of the blower 3 among the candidate rotational speeds is lower than the synchronous rotational speed of the blower 3.

[0033] The rotational speed measuring device 101 according to Embodiment 2 of this disclosure can reflect the operating conditions of the blower 3 in the calculation of the rotational speed by using a rotational speed lower than the synchronous rotational speed of the blower 3 as the rotational speed. Therefore, the rotational speed measuring device 101 according to Embodiment 2 of this disclosure can improve the accuracy of rotational speed measurement.

[0034] Furthermore, the rotational speed measuring device 101 according to Embodiment 2 of this disclosure may also be subjected to A-correction of the frequency spectrum. A-correction is a frequency weighting characteristic used when measuring noise levels, and is a frequency characteristic that mimics human hearing. Human hearing is most sensitive to sound in a specific frequency band, but low-frequency and high-frequency sounds are perceived as quieter even at the same sound pressure level. Therefore, A-correction takes this perception into account and adjusts the sound pressure level to produce a value close to the "loudness" that humans actually perceive. If A-correction is not performed, the intensity of the low-frequency side of the frequency spectrum of the operating sound of the blower 3 may become too high. As a result, the frequency spectrum of the NZ sound may be buried, and the measurement accuracy will decrease. A-correction is an effective measurement method in such cases, and by performing A-correction, the rotational speed measuring device 101 according to Embodiment 2 of this disclosure can improve the measurement accuracy of the rotational speed of the blower 3.

[0035] Furthermore, the rotational speed measuring device 101 according to Embodiment 2 of this disclosure may detect a frequency spectrum whose peak frequency is an integer multiple of the lowest peak frequency in the frequency spectrum and calculate the rotational speed using the lowest peak frequency. In this method of calculating rotational speed, for example, when a frequency spectrum is detected, the calculation unit 2 checks whether a frequency spectrum exists near frequencies such as 2, 3, or 4 times the lowest peak frequency. An integer multiple refers to 2, 3, or 4 times, and does not need to be strictly integer multiples; it can be approximately an integer multiple. If a peak in the frequency spectrum is detected near an integer multiple frequency, the calculation unit 2 calculates the rotational speed using the frequency that is 1 times that frequency, i.e., the lowest frequency, as the peak frequency. By calculating the rotational speed using the lowest peak frequency among frequency spectra with integer multiple peaks in this way, the rotational speed measuring device 101 according to Embodiment 2 of this disclosure can improve the measurement accuracy of the rotational speed of the blower 3.

[0036] Embodiment 3. In Embodiment 3, the same reference numerals are used for the same components as in Embodiment 1 of this disclosure, and descriptions of the same or corresponding parts are omitted. In Embodiment 3, the location where the sensor is provided is mainly different from Embodiments 1 and 2. The rotational speed measuring device 102 according to Embodiment 2 will now be described with reference to the drawings.

[0037] Figure 6 is a schematic diagram showing the position of the sensor unit of the rotational speed measuring device according to Embodiment 3 of the present disclosure. Figure 6(a) is a front view of the blower 3, which has blades 10 and a frame 11. Here, the front in Embodiment 3 of the present disclosure refers to the surface from which air is discharged from the blades 10 of the blower 3. As shown in Figure 6(a), in the rotational speed measuring device 102 according to Embodiment 3 of the present disclosure, the sensor unit 1a is provided on the frame 11 of the blower 3. By providing the sensor unit 1a in this position, the sensor unit 1a is not directly affected by the wind discharged from the blower 3, and therefore the operating sound of the blower 3 can be acquired with high accuracy. For this reason, the rotational speed measuring device 102 according to Embodiment 3 of the present disclosure can improve the accuracy of rotational speed measurement.

[0038] Figure 6(b) is a view of the blower 3 from the back side of the surface from which air is discharged. As shown in Figure 6(b), in the rotational speed measuring device 102 according to Embodiment 3 of the present disclosure, the sensor unit 1a may be provided on the back side of the surface from which air is discharged from the blades of the blower 3. By providing the sensor unit 1a in such a position, the sensor unit 1a is not directly affected by the wind discharged from the blower 3, and the operating sound of the blower 3 can be acquired with high accuracy. For this reason, the rotational speed measuring device 102 according to Embodiment 3 of the present disclosure can improve the accuracy of rotational speed measurement. Furthermore, by providing the sensor unit 1a on the back side, the rotational speed measuring device 102 according to Embodiment 3 of the present disclosure can be placed not only in the corners of the frame 11 but also in the frame 11 near the central motor, thus improving the flexibility of placement of the sensor unit 1a. Note that Figure 6(b) shows an example in which the sensor 1a is provided in both the corners of the frame 11 on the back side of the blower 3 and in the frame 11 near the central motor, but it may be provided in only one side, or in the four corners, etc.

[0039] Furthermore, although Figures 6(a) and (b) show one example of the sensor unit 1a, there may be multiple sensor units 1a, and they may be provided on both the front and back sides of the blower 3. By arranging the sensor units 1a in this way, the rotational speed measuring device 102 according to Embodiment 3 of this disclosure can accurately acquire the operating sound of the blower 3.

[0040] Embodiment 4. In Embodiment 4, the same reference numerals are used for the same components as in Embodiment 1 of this disclosure, and descriptions of the same or corresponding parts are omitted. Embodiment 4 differs from Embodiments 1 to 3 in that it calculates the rotational speed using machine learning. The rotational speed measuring device 103 according to Embodiment 2 will now be described with reference to the drawings.

[0041] Figure 7 is a schematic diagram showing the configuration of a rotational speed measuring device according to Embodiment 4 of the present disclosure. As shown in Figure 7, the rotational speed measuring device 103 according to Embodiment 4 of the present disclosure comprises a sensor unit 1b, a calculation unit 2a, a data acquisition unit 4, and an inference unit 5. The sensor unit 1b acquires the operating sound of the blower 3, and the calculation unit 2a converts the operating sound of the blower 3 into a frequency spectrum. The data acquisition unit 4 acquires the frequency spectrum from the calculation unit 2a. The inference unit 5 uses a trained model that infers a value including the rotational speed of the blower 3 and the number of blades 10 of the blower 3 from the frequency spectrum acquired by the data acquisition unit 4, and outputs the blade rotation peak frequency, which is the value obtained by multiplying the rotational speed of the blower 3 by the number of blades 10 of the blower 3, from the frequency spectrum acquired by the data acquisition unit 4. The calculation unit 2a calculates the rotational speed of the blower 3 by dividing the blade rotation peak frequency by the number of blades of the blower 3. In other words, the inference unit 5 infers from the frequency spectrum a value equivalent to the number of blades of the blower 3 multiplied by the rotational speed of the blower 3.

[0042] Figure 8 is a schematic diagram showing a learning device for generating a trained model of a rotational speed measuring device according to Embodiment 4 of the present disclosure. The learning device 8 comprises a data acquisition unit 4a and a model generation unit 7. The data acquisition unit 4a acquires the frequency spectrum and the blade rotation peak frequency. The model generation unit 7 creates training data for the blade rotation peak frequency based on the combination of the frequency spectrum and the blade rotation peak frequency output from the data acquisition unit 4a. In other words, the rotational speed measuring device 103 according to Embodiment 4 of the present disclosure generates a trained model storage unit 6 that infers the blade rotation peak frequency from the frequency spectrum. The data acquisition unit 1 and the inference unit 2 are, for example, RAM, and the trained model storage unit 3 is, for example, ROM.

[0043] Figure 9 is a schematic diagram showing a neural network used in a rotation speed measuring device according to Embodiment 4 of this disclosure. The model generation unit 7 learns the blade rotation peak frequency by so-called supervised learning according to a neural network model, for example. Here, supervised learning is a method that learns features in the learning data by providing a learning device with pairs of input and result (label) data, and infers the result from the input.

[0044] A neural network consists of an input layer made up of multiple neurons, an intermediate layer (hidden layer) made up of multiple neurons, and an output layer made up of multiple neurons. The intermediate layer can be one or more layers.

[0045] For example, in a three-layer neural network as shown in Figure 9, when multiple inputs are input to the input layer (X1-X3), these values ​​are multiplied by weights W1 (w11-w16) and input to the hidden layer (Y1-Y2). The result is then further multiplied by weights W2 (w21-w26) and output from the output layer (Z1-Z3). This output varies depending on the values ​​of weights W1 and W2.

[0046] In this disclosure, the neural network learns the blade rotation peak frequency by so-called supervised learning, according to training data created based on a combination of the frequency spectrum acquired by the data acquisition unit 4a and the blade rotation peak frequency.

[0047] In other words, the neural network learns by inputting a frequency spectrum into the input layer and adjusting the weights W1 and W2 so that the result output from the output layer approaches the peak frequency of blade rotation. The model generation unit generates and outputs a trained model by performing the above learning process. The trained model storage unit 6 stores the trained model output from the model generation unit 7.

[0048] As described above, the rotational speed measuring device 103 according to Embodiment 4 of the present disclosure comprises a sensor unit 1b that acquires the operating sound of a blower, a calculation unit 2a that converts the operating sound into a frequency spectrum, a data acquisition unit 4 that acquires the frequency spectrum from the calculation unit 2a, and an inference unit 5 that uses a trained model that infers from the frequency spectrum acquired by the data acquisition unit 4 a value obtained by multiplying the rotational speed of the blower 3 by the number of blades 10 of the blower 3, and outputs a blade rotation peak frequency which is the value obtained by multiplying the rotational speed of the blower 3 by the number of blades of the blower 3 from the frequency spectrum acquired by the data acquisition unit 4, and the calculation unit 2a calculates the rotational speed of the blower 3 by dividing the blade rotation peak frequency by the number of blades of the blower 3.

[0049] Therefore, the rotational speed measuring device 103 according to Embodiment 4 of this disclosure has the effect of being able to determine the rotational speed of the blower 3 by inference, in addition to the effects of Embodiment 1, even when there is little measurement data of the operating sound of the blower 3. Furthermore, the rotational speed measuring device 103 according to Embodiment 4 of this disclosure can improve the accuracy of rotational speed measurement by increasing the amount of data used in the learned model storage unit 6.

[0050] The configurations shown in the embodiments described above are merely examples of the content of this disclosure and can be combined with other known technologies. Furthermore, it is possible to omit or modify parts of the configuration without departing from the gist of this disclosure.

[0051] The various aspects of this disclosure are summarized below as an appendix. (Note 1) A sensor unit that acquires the operating sound of the blower, A rotational speed measuring device comprising: a calculation unit that converts the aforementioned operating sound into a frequency spectrum, detects the peak frequency of the operating sound from the frequency spectrum, and calculates the rotational speed of the blower by dividing the peak frequency by the number of blades of the blower. (Note 2) The rotational speed measuring device according to Appendix 1, further comprising a notification unit that compares the rotational speed calculated by the calculation unit with the rotational speed input to the blower and notifies the user if a difference in rotational speed occurs. (Note 3) The rotational speed measuring device according to Appendix 1 or 2, wherein, when multiple peak frequencies are detected, the calculation unit calculates the rotational speed using the lowest peak frequency among the frequency spectra having predetermined intensities. (Note 4) The rotational speed measuring device according to Appendix 1 or 2, wherein, when multiple peak frequencies are detected, the calculation unit calculates candidate rotational speeds of the blower by dividing the peak frequencies of the frequency spectrum having a predetermined intensity by the number of blades of the blower, and sets the rotational speed lower than the synchronous rotational speed of the blower among the candidate rotational speeds as the rotational speed. (Note 5) The calculation unit is a rotational speed measuring device according to any one of the appendices 1 to 4, which applies A correction to the frequency spectrum. (Note 6) The rotational speed measuring device according to any one of the appendices 1 to 5, wherein the calculation unit detects the frequency spectrum in which the peak frequency is an integer multiple of the lowest peak frequency in the frequency spectrum, and calculates the rotational speed using the lowest peak frequency. (Note 7) The sensor unit is a rotational speed measuring device according to any one of the appendices 1 to 6, which is provided on the frame of the blower. (Note 8) The sensor unit is a rotational speed measuring device according to any one of the appendices 1 to 7, provided on the back surface of the surface from which air is discharged from the blades of the blower. (Note 9) A sensor unit that acquires the operating sound of the blower, A calculation unit that converts the aforementioned operating sound into a frequency spectrum, A data acquisition unit that acquires the frequency spectrum from the calculation unit, The system includes an inference unit that uses a trained model to infer a value obtained by multiplying the rotation speed of the blower by the number of blades of the blower from the frequency spectrum acquired by the data acquisition unit, and outputs a blade rotation peak frequency which is a value obtained by multiplying the rotation speed of the blower by the number of blades of the blower from the frequency spectrum acquired by the data acquisition unit, The aforementioned calculation unit is a rotational speed measuring device that calculates the rotational speed of the blower by dividing the blade rotation peak frequency by the number of blades of the blower. (Note 10) A blower and A rotational speed measuring system comprising a rotational speed measuring device as described in any one of the appendices 1 to 9. (Note 11) The sensor unit acquires the operating sound of the blower, The calculation unit converts the operating sound into a frequency spectrum, The calculation unit performs the step of detecting the peak frequency of the operating sound from the waveform of the frequency spectrum, A rotational speed measurement method comprising the step of the calculation unit calculating the rotational speed of the blower by dividing the frequency spectrum by the number of blades of the blower. [Explanation of Symbols]

[0052] 1 1a 1b Sensor unit, 2 2a Calculation unit, 3 Blower, 4 4a Data acquisition unit, 5 Inference unit, 6 Trained model storage unit, 7 Model generation unit, 8 Learning device, 9 Notification unit, 10 Blade, 11 Frame, 100 101 102 103 Rotation speed measuring device, 200 Rotation speed measuring system

Claims

1. A sensor unit that acquires the operating sound of the blower, A rotational speed measuring device comprising: a calculation unit that converts the aforementioned operating sound into a frequency spectrum, detects the peak frequency of the operating sound from the frequency spectrum, and calculates the rotational speed of the blower by dividing the peak frequency by the number of blades of the blower.

2. The rotational speed measuring device according to claim 1, further comprising a notification unit that compares the rotational speed calculated by the calculation unit with the rotational speed input to the blower and notifies when a difference in rotational speed occurs.

3. The rotational speed measuring device according to claim 1 or 2, wherein when multiple peak frequencies are detected, the calculation unit calculates the rotational speed using the lowest peak frequency among the frequency spectra having predetermined intensities.

4. The rotational speed measuring device according to claim 1 or 2, wherein, when multiple peak frequencies are detected, the calculation unit calculates candidate rotational speeds of the blower by dividing the peak frequencies of the frequency spectrum having a predetermined intensity by the number of blades of the blower, and sets the rotational speed of the candidate rotational speed that is lower than the synchronous rotational speed of the blower.

5. The rotational speed measuring device according to claim 1 or 2, wherein the calculation unit performs A correction on the frequency spectrum.

6. The rotational speed measuring device according to claim 1 or 2, wherein the calculation unit detects the frequency spectrum in which the peak frequency is an integer multiple of the lowest peak frequency among the frequency spectrum, and calculates the rotational speed using the lowest peak frequency.

7. The rotational speed measuring device according to claim 1 or 2, wherein the sensor unit is provided on the frame of the blower.

8. The rotational speed measuring device according to claim 1 or 2, wherein the sensor unit is provided on the back surface of the surface from which air is discharged from the blades of the blower.

9. A sensor unit that acquires the operating sound of the blower, A calculation unit that converts the aforementioned operating sound into a frequency spectrum, A data acquisition unit that acquires the frequency spectrum from the calculation unit, The system includes an inference unit that uses a trained model to infer a value obtained by multiplying the rotation speed of the blower by the number of blades of the blower from the frequency spectrum acquired by the data acquisition unit, and outputs a blade rotation peak frequency which is a value obtained by multiplying the rotation speed of the blower by the number of blades of the blower from the frequency spectrum acquired by the data acquisition unit, The aforementioned calculation unit is a rotational speed measuring device that calculates the rotational speed of the blower by dividing the blade rotation peak frequency by the number of blades of the blower.

10. The aforementioned blower and, A rotational speed measuring system comprising a rotational speed measuring device according to claim 1 or 2.

11. The sensor unit acquires the operating sound of the blower, The calculation unit converts the operating sound into a frequency spectrum, The calculation unit performs the step of detecting the peak frequency of the operating sound from the waveform of the frequency spectrum, A rotational speed measurement method comprising the step of the calculation unit calculating the rotational speed of the blower by dividing the frequency spectrum by the number of blades of the blower.

Images