Noise source estimation system and method

Abstract

To provide a noise source estimation system and method capable of estimating the source of vibration (noise) generated by life activities of residents in a housing complex.SOLUTION: A noise source estimation system 100 includes individual detection devices 50 installed in multiple dwelling units 1a, and a cloud device 60 capable of bidirectional communication with the multiple individual detection devices. Each of the individual detection device 50 includes an acceleration sensor 10 and a control unit 20. The acceleration sensor 10 detects vibration acceleration 4 generated in a floor slab 2. The control unit 20 estimates an estimated noise level B and, when the estimated noise level exceeds a determination value, transmits a noise generation notification D including the estimated noise level and the time of noise generation to the cloud device 60. The cloud device 60 estimates the source of the noise from one or more noise generation notifications.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a system for estimating a noise source in an apartment building and a method for estimating a noise source. [Background technology]

[0002] In apartment complexes and other multi-unit housing, everyday sounds such as walking noises transmitted from other dwelling units can be a problem. However, it is usually difficult to completely block these sounds using architectural techniques alone. Therefore, in order to maintain a good living environment, consideration must be given to the way residents live, and technologies to support this consideration have been proposed (for example, Patent Documents 1 and 2).

[0003] The "noise detection system" in Patent Document 1 includes a vibration detection sensor that detects vibrations on the floor above and outputs a voltage signal corresponding to the magnitude of the vibration, a noise conversion unit, a noise conversion condition setting unit, a vibration / noise conversion table, and a control unit. The noise conversion unit converts the voltage signal from the vibration detection sensor into a noise value on the floor below and outputs the converted noise value. If the converted noise value is greater than a threshold, the control unit outputs a warning output command to the warning unit.

[0004] The "noise monitoring system" of Patent Document 2 has an internet-based management server that includes a noise data collection unit, a noise level registration unit, and a noise level notification unit. The noise data collection unit sequentially stores the noise levels detected in each room of an apartment building or the like in a noise database. The noise level registration unit registers occupants of rooms whose noise levels are below the noise threshold on a whitelist, and occupants of rooms whose noise levels exceed the noise threshold on a blacklist. The noise level notification unit notifies occupants of rooms registered on the whitelist that they will receive useful services, and notifies occupants of rooms registered on the blacklist that they should be careful. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent No. 3751628 [Patent Document 2] Patent Publication No. 2021-76383 Summary of the Invention [Problem to be solved by the invention]

[0006] The system in Patent Document 1 uses a vibration detection sensor installed in the slab of one's own apartment to estimate the noise generated in the apartment on the floor below, and if the estimated value exceeds a threshold, it issues a warning to the apartment where the noise is generated.

[0007] The system of Patent Document 1 has the following problems. (1) A vibration detection sensor detects vibrations on the floor above and outputs a voltage signal corresponding to the magnitude of the vibration, and a noise conversion unit converts the voltage signal from the vibration detection sensor into a noise value on the floor below and outputs the converted value. Based on the obtained noise value, the noise generated in the apartment on the floor below is estimated. However, while this system can estimate the volume of noise generated in the apartment below (hereinafter referred to as noise level), it cannot identify the noise-generating behavior. (2) Because RC structures easily transmit vibrations, when vibrations occur on the floor of a certain dwelling unit, the vibrations propagate to surrounding dwelling units, albeit attenuated. As a result, if the vibrations from the source are strong, systems installed in the dwelling units around the source may mistakenly detect the vibrations (noise) as being generated by the dwelling unit itself.

[0008] Furthermore, the system of Patent Document 2 directly uses the noise level detected in each room of an apartment building or the like, and therefore cannot estimate the volume of noise occurring in the dwelling units on the floors below.

[0009] The present invention has been devised to solve the above-mentioned problems. That is, a first object of the present invention is to provide a noise source estimation system and method that can estimate the source of vibrations (noise) caused by the daily activities of residents in an apartment building. A second object of the present invention is to provide a noise source estimation system and method that can notify the residents of the noise source of the noise level and the noise-causing activity. [Means for solving the problem]

[0010] According to the present invention, there is provided a noise source estimation system for estimating a source of noise that is generated by daily life sounds from an upper floor dwelling unit in a lower floor dwelling unit in an apartment building where a plurality of dwelling units are adjacent to each other, comprising: The system comprises an individual detection device installed in each of the plurality of dwelling units, and a cloud device capable of bidirectional communication with the plurality of individual detection devices, The individual detection device includes an acceleration sensor fixed to a floor slab of each of the dwelling units and detecting vibration acceleration occurring in the floor slab; Estimating an estimated noise level of the noise propagating to the lower floor dwelling unit from acceleration data indicating a time change in the vibration acceleration; and a control unit that, when the estimated noise level exceeds a predetermined judgment value, transmits a noise occurrence notification to the cloud device, the notification including the estimated noise level and the time of occurrence of the noise; The cloud device is provided with a noise source estimation system that estimates the source of the noise from one or more of the noise occurrence notifications.

[0011] Furthermore, according to the present invention, the noise source estimation system is used to (A) a noise occurrence notification step of transmitting the noise occurrence notification to the cloud device when the estimated noise level from each of the control units exceeds a predetermined judgment value; (B) a similarity determination step of determining whether there are multiple similar acts occurring at the same time in multiple adjacent dwelling units; (C) a first identification step of identifying each of the dwelling units that sent the noise occurrence notification as a noise source when there are not multiple similar acts; (D) a source determination step in which, when there are multiple similar acts, the estimated noise levels in the multiple dwelling units are compared to determine whether a noise source can be identified whose estimated noise level exceeds a predetermined threshold value compared to an adjacent dwelling unit; (E) a second identification step of not identifying the dwelling units other than the noise source as the noise source when the noise source can be identified; (F) A noise source estimation method is provided, which includes a third identification step of identifying each of the dwelling units that transmitted the similar behavior as the noise source if the noise source cannot be identified. [Effects of the Invention]

[0012] The floor slab of the upper floor dwelling unit is less affected by the activities of the residents living in the lower floor, but is more likely to vibrate due to the activities of the residents living in the upper floor. In order to utilize this vibration characteristic, in the present invention, an acceleration sensor is fixed to the floor slab of the upper floor dwelling unit, so that the estimated noise level propagating to the lower floor dwelling unit can be estimated from the acceleration data generated on the floor slab.

[0013] The control unit also estimates the estimated noise level propagating to the lower floor dwelling unit from the acceleration data, and if the estimated noise level exceeds a predetermined judgment value, sends a noise occurrence notification to the cloud device.

[0014] Furthermore, the cloud device estimates the source of the noise from one or more noise occurrence notifications, and therefore can estimate the source of vibrations (noise) caused by the daily activities of the residents of the apartment building. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is an overall configuration diagram of a noise source estimation system according to the present invention; [Figure 2] FIG. 2 is an overall configuration diagram of a control unit. [Figure 3]10A and 10B are diagrams illustrating examples of changes in vibration acceleration over time in an impact system Y1, a drop system Y2, and a walking system Y3. [Figure 4] FIG. 10 is a diagram showing an example of time-dependent changes in vibration acceleration of the equipment system Y4 and the drag system Y5. [Figure 5] FIG. 1 is a configuration diagram of a noise estimation device. [Figure 6] 1 is an overall flow diagram of a noise source estimation method according to the present invention. [Figure 7] 1 is an explanatory diagram of a noise source estimation method according to the present invention; [Figure 8] This is a layout diagram of the experimental equipment simulating an upper floor dwelling unit. [Figure 9] FIG. 1 is a diagram showing the relationship between sampling frequency and F1-score. [Figure 10] This is an example of on-site measurement of vibration propagation within a reinforced concrete building. [Figure 11] This is an example of on-site measurement of vibration propagation in a reinforced concrete building due to the bounce of impact system Y1. [Figure 12] 11(B) is a comparison diagram of the amount of attenuation of (A) estimated noise level B and (B) estimated noise level B from the data of FIG. 11(B). [Figure 13] This is an example of on-site measurement of vibration propagation in a reinforced concrete building due to the impact of opening and closing a sliding door (impact system Y1). [Figure 14] 13(B) is a comparison diagram of the amount of attenuation of (A) estimated noise level B and (B) estimated noise level B from the data of FIG. 13(B). DETAILED DESCRIPTION OF THE INVENTION

[0016] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings. In addition, common parts in the drawings are given the same reference numerals, and duplicated explanations will be omitted.

[0017] FIG. 1 is a diagram showing the overall configuration of a noise source estimation system 100 according to the present invention. The noise source estimation system 100 is a system for estimating the source of noise that living sounds from upper floor dwellings affect on lower floor dwellings in an apartment building 1 where a plurality of individual dwelling units 1a are adjacent to each other.

[0018] In FIG. 1, (A) is a cross-sectional elevation view of an apartment building 1 consisting of 16 (=4×4) dwelling units 1a, and (B) is a cross-sectional elevation view of one of the units. The noise source estimation system 100 of the present invention includes a plurality of individual detection devices 50 installed in a plurality of dwelling units 1a, respectively, and a cloud device 60.

[0019] Each of the plurality of individual detection devices 50 includes an acceleration sensor 10 and a control unit 20 .

[0020] The acceleration sensor 10 is fixed to the floor slab 2 of the upper floor dwelling unit and detects the vibration acceleration 4 occurring in the floor slab 2. Acceleration sensor 10 is preferably a piezoelectric acceleration sensor, which detects accelerations of 5 μG to 10 kG in a frequency range of 0.5 to 20 kHz, for example. The acceleration sensor 10 is not limited to a piezoelectric acceleration sensor, but may be a strain gauge type, a capacitance type, a servo type, or the like.

[0021] The control unit 20 is preferably a computer (PC) and includes an input / output device, a storage device, and an arithmetic unit. The storage device is a RAM (Random Access Memory) and a ROM (Read Only Memory). The control unit 20 estimates an estimated noise level B propagating to the lower floor dwelling unit from acceleration data 5 that indicates a time change in vibration acceleration 4. Preferably, the control unit 20 further estimates a noise behavior Y of daily sounds from the acceleration data 5. Furthermore, when the estimated noise level B exceeds a predetermined judgment value, the control unit 20 transmits a noise occurrence notification D including the estimated noise level B and the noise occurrence time T to the cloud device 60. It is preferable that this noise occurrence notification D further includes a noisy behavior Y of daily sounds. Estimated noise level B is an estimate of the noise level propagating to the dwelling on the floor below. It should be noted that the control unit 20 may be connected to an internet line, and some of the functions of the control unit 20 may be performed by the cloud device 60 (cloud processing).

[0022] In FIG. 1, each of the plurality of individual detection devices 50 preferably further includes a noise notification device 30. The noise notification device 30 has a function of notifying its own resident of its own noise occurrence notification D when it receives a notification permission signal AS from the cloud device 60. This noise occurrence notification D includes the noise activity Y, the estimated noise level B, and the time T of occurrence of the noise activity Y, as described above. The noise notification device 30 is preferably a display device capable of audio output, or may be a portable device (for example, a smartphone). Furthermore, in this example, the individual detection device 50 has the control unit 20 and the noise notification device 30, but the control unit 20 and the noise notification device 30 may be integrated.

[0023] The cloud device 60 is, for example, a computer (PC) separate from the control unit 20, and is configured to be able to communicate bidirectionally with the plurality of individual detection devices 50 via, for example, an internet line. Note that the control unit 20 and a part or all of the cloud device 60 may be configured as the same cloud device 60.

[0024] The cloud device 60 estimates the source of the noise from one or more noise occurrence notifications D. Furthermore, the cloud device 60 preferably has a function of transmitting a notification permission signal AS to the noise notification device 30 of the noise source.

[0025] In this example, the cloud device 60 specifically has the following functions. (1) Determine whether there are multiple similar acts with the same occurrence time T and noise act Y in multiple adjacent dwelling units 1a, and if there are no multiple similar acts, send a notification permission signal AS to the noise notification device 30 in each dwelling unit that sent the noise occurrence notification D. In this invention, the acceleration data is extracted for each fixed time interval, and noise level estimation and noisy behavior estimation are performed. Therefore, "occurrence time T is the same" specifically means that the events occur within the same time interval. Furthermore, since the time interval setting in the system under consideration is 1 second, "the same occurrence time T" means that the time difference between the occurrence times T is, for example, within 1 second. Furthermore, "the same noisy behavior Y" means that, for example, when the noisy behavior Y is divided into impact-based Y1, falling-based Y2, walking-based Y3, equipment-based Y4, and dragging-based Y5, any of Y1 to Y5 is the same. (2) When there are multiple similar acts, the estimated noise levels B in multiple dwelling units 1a are compared to determine whether a noise source can be identified whose estimated noise level B exceeds a predetermined threshold C compared to an adjacent dwelling unit 1a. From the examples described later, it is preferable that the threshold value C is 5 dB or more and 25 dB or less. (3) If the source of the noise can be identified, a notification permission signal AS is sent only to the noise notification device 30 of the dwelling unit 1a where the noise is generated, and if the source of the noise cannot be identified, a notification permission signal AS is sent to the noise notification device 30 of each dwelling unit 1a that transmitted similar behavior.

[0026] Living noises in apartment buildings can be broadly divided into (1) noise from household appliances, (2) noise from housing facilities and structures, (3) noise from audio equipment, and (4) other noises. "Noise from household appliances" refers to sounds from washing machines, refrigerators, air conditioners, outdoor units, vacuum cleaners, household heat pump water heaters, etc. "Noise from housing facilities and structures" refers to sounds such as doors opening and closing, furniture being moved, and water supply and drainage from the bathroom. "Noise from audio equipment" refers to sounds from televisions, audio equipment, alarm clocks, musical instruments such as pianos, drums, and guitars. "Other noises" include footsteps indoors and on stairs, talking, pets barking, etc. It should be noted that the living sounds that are the target of detection in this invention are limited to "sounds that are caused by the vibration of the dwelling floor due to living activities and are consequently transmitted to the dwelling units on the floor below," and do not include the sound of a television, the cries of pets, etc. There are various types of living sounds, but the one that is particularly likely to be a problem in apartment buildings is the sound that is caused by the vibration of the dwelling floor due to living activities and is consequently transmitted to the dwelling units on the floor below. The living sounds that are the subject of the present invention are such floor vibration sounds.

[0027] In the present invention, the noise behaviors Y of everyday sounds are classified into impact-related Y1, falling-related Y2, walking-related Y3, equipment-related Y4, and dragging-related Y5. Details of each noise behavior will be described later.

[0028] FIG. 2 is a diagram showing the overall configuration of the control unit 20. As shown in this figure, the control unit 20 includes a data storage device 22, a noise estimation device 24, an activity estimation device 26, and an occurrence notification device .

[0029] The data storage device 22 stores acceleration data 5 that indicates the change in vibration acceleration 4 over time. The data storage device 22 is preferably a magnetic disk (for example, HDD) or flash memory (for example, SSD, USB memory, SD card) connectable to a computer (PC). The data storage device 22 also stores the estimated value of the noise level propagating to the dwelling unit on the lower floor (estimated noise level B) and the estimated noise behavior Y of the daily sounds, together with the time T at which they occurred.

[0030] The noise estimation device 24 estimates an estimated noise level B propagating to the dwelling unit on the lower floor from acceleration data 5 that indicates the change over time of the vibration acceleration 4.

[0031] FIG. 3 is a diagram showing an example of the change over time of vibration acceleration 4 of the impact system Y1, the drop system Y2, and the walking system Y3, and FIG. 4 is a diagram showing an example of the change over time of vibration acceleration 4 of the equipment system Y4 and the drag system Y5. In Figures 3 and 4, the horizontal axis represents the elapsed time (seconds), and the vertical axis represents the magnitude of vibration acceleration 4 (m / s 2 ) In FIG. 3, (A) is an example of a jump in the impact type Y1, (B) is an example of a drop in the bathroom bucket in the drop type Y2, and (C) and (D) are examples of walking in slippers and jogging in slippers in the walking type Y3. In addition, in Figure 4, (A) and (B) are examples of the use of a kitchen food processor and the spin-drying operation of a drum washing machine, which are equipment type Y4, and (C) and (D) are examples of the dragging type Y5, such as dragging a chair and dragging a bathroom washbasin. In the examples of Figures 3 and 4, the time span on the horizontal axis is 1 second.

[0032] According to the performance standards for buildings and rooms by use set by the Architectural Institute of Japan, the preferred performance level (Class 1) recommended by the Architectural Institute for apartment buildings requires a noise level of 35 dB(A) or less. According to another source, internal noise from shared facilities in apartment buildings is considered "low sounding" at a noise level of 30 dB(A), "somewhat loud" at 40 dB(A), and "quite loud" at 50 dB(A). Therefore, the actual perception of noise in an apartment building needs to be judged based on the estimated noise level B rather than the maximum value X of the vibration acceleration 4 described above.

[0033] FIG. 5 is a diagram showing the configuration of the noise estimation device 24. In this figure, a noise estimation device 24 has a frequency analyzer 24a, a radiated sound calculator 24b, a band synthesis value calculator 24c, and a maximum level calculator 24d.

[0034] The frequency analyzer 24a passes the acceleration data 5 through an octave band filter and then through an effective value detection circuit with time weighting characteristics F to obtain a time waveform 6 for each octave band. This frequency analysis is similar to the frequency analysis function of a general noise system. The time weighting characteristic F is a process used in general sound level meters, and is usually used when evaluating impulsive sounds such as floor impact sounds. The frequency range should be the octave band with center frequencies of 31.5 Hz, 63 Hz, 125 Hz, 250 Hz, and 500 Hz, which is the target frequency range for measuring heavy floor impact sound insulation performance according to JIS A 1418-2. Furthermore, when obtaining an octave band waveform up to 500 Hz, the sampling frequency must cover the upper frequency limit of the 500 Hz band (= 500 × √2 ≒ 707 Hz).

[0035] The indoor sound pressure level Lp due to radiation from a vibrating floor slab can theoretically be calculated using equation (1). Here, Lp is the indoor sound pressure level, La is the vibration acceleration level of the floor slab, ΔLa is the vibration acceleration level amplification amount (assumed ceiling effect), f is the frequency, k is the radiation coefficient, S is the radiation area, and A is the indoor equivalent sound absorption area (room surface area x indoor average sound absorption coefficient).

[0036]

number

[0037] The radiated sound calculator 24b calculates the room average sound pressure level 7 due to radiation of each octave band from the time waveform 6 of each octave band. In this calculation, the radiation efficiency k is a value determined by the physical properties of the floor and the frequency, and in the example described below, a value was used assuming a concrete slab thickness of 200 mm, which is a typical floor for a reinforced concrete apartment building. The radiation area S and the room equivalent sound absorption area A are set to approximate values. In the example described below, we assume a room the size of a bedroom, with a floor area of ​​10 m. 2 , room surface area 50m 2 The average indoor sound absorption coefficient was set to be the general measurement value for a residential room.

[0038] The band synthesis value calculator 24c synthesizes the energy of the room average sound pressure levels 7 of the respective octave bands to calculate the sum of the amounts of energy 8. That is, the synthesized level is calculated by taking the sum of the amounts of energy 8 of the time waveforms of the respective octave bands. When synthesizing energy, by taking into account the A-weighting correction value for each band, corrections can be made that correspond to human hearing, and a value equivalent to the estimated noise level B, which is an index of sound loudness, can be calculated.

[0039] The maximum level calculator 24d estimates an estimated noise level B, which is the maximum level within the target time period, for the combined sum 9 of the energy amounts.

[0040] The behavior estimation device 26 in Figure 2 uses, for example, a discrimination program that uses multiple acceleration data 5 indicating the time change in vibration acceleration 4 of noise behavior Y of daily sounds divided into multiple categories, and performs machine learning on some of the data as learning data and the rest as evaluation data.

[0041] The noise occurrence notification device 28 in FIG. 2 transmits a noise occurrence notification D to the cloud device 60 when the estimated noise level B exceeds a predetermined judgment value. The noise occurrence notification D includes the above-mentioned noisy behavior Y, estimated noise level B, and occurrence time T of the noisy behavior Y.

[0042] FIG. 6 is an overall flow diagram of the noise source estimation method according to the present invention. The noise source estimation method of the present invention uses the noise source estimation system 100 described above and includes steps S1 to S8.

[0043] In step S1, when noise occurs in each dwelling unit 1a, it is determined whether or not the estimated noise level B exceeds a predetermined judgment value. As mentioned above, in an apartment building, a noise level of 30 dB(A) is considered "low," 40 dB(A) is "slightly loud," and 50 dB(A) is "quite loud." The judgment value is set to, for example, 30 dB(A), and noises below the judgment value are ignored here as they are not noises that would cause dissatisfaction to residents.

[0044] In the noise occurrence notification step S2, in each dwelling unit 1a, a noise occurrence notification D is transmitted to the cloud device 60 when the estimated noise level B exceeds a predetermined judgment value.

[0045] In the similarity determination step S3, the cloud device 60 determines whether there are multiple similar acts with the same occurrence time T and noisy act Y in multiple adjacent dwelling units 1a. If there are no multiple similar acts (NO) in the similarity determination step S3, each dwelling unit that has transmitted the noise occurrence notification D is identified as a noise source in the first identification step S4. In this example, in the first specifying step S4, a notification permission signal AS (first notification permission signal AS1) is transmitted to the noise notification device 30 of each dwelling unit that has transmitted the noise occurrence notification D.

[0046] If there are multiple similar behaviors in the similarity determination step S3 (YES), the estimated noise levels B in the multiple dwelling units 1a are compared in the noise source determination step S5 to determine whether the noise source can be identified. Specifically, in the source determination step S5, it is determined whether a noise source can be identified whose estimated noise level B exceeds a predetermined threshold C compared to the adjacent dwelling unit 1a. The threshold C is preferably 5 dB or more and 25 dB or less.

[0047] If the noise source can be identified in the noise source determination step S5, only the noise notification device 30 in the dwelling unit that is the noise source is identified as the noise source in the second identification step S6. Also in this example, in the second identification step S6, dwelling units other than the noise source are not identified as noise sources, and a notification permission signal AS (second notification permission signal AS2) is transmitted only to the noise notification device 30 of the dwelling unit that is the noise source.

[0048] If the noise source cannot be identified in the source determination step S5, each dwelling unit that transmitted the similar behavior is identified as the noise source in the third identification step S7. In this example, in the third identification step S7, a notification permission signal AS (third notification permission signal AS3) is transmitted to the noise notification device 30 of each dwelling unit that has transmitted the similar behavior.

[0049] In this example, in the individual occurrence notification step S8, if a notification permission signal AS is transmitted in steps S4, S6, or S7 and received, the dwelling unit 1a that received the signal notifies its resident of a noise occurrence notification D. The notification permission signal AS in this case is the first notification permission signal AS1, the second notification permission signal AS2, or the third notification permission signal AS3.

[0050] As described above, in this invention, the "evaluation target dwelling unit (own dwelling unit)" and the "adjacent dwelling units" surrounding it diagonally above, below, left, right, and diagonally are set, and then a determination is made as to whether the vibrations detected in the "evaluation target dwelling unit" are "originating from the own dwelling unit" or "originating from another dwelling unit" based on the situation of the "adjacent dwelling units." Then, by carrying out the above determination in sequence for each dwelling unit in the building as the "dwelling unit to be evaluated," it is possible to avoid erroneous notifications throughout the entire building.

[0051] 7 is an explanatory diagram of the noise source estimation method of the present invention, in which (A) shows a case where the own dwelling unit is determined to be the noise source, and (B) shows a case where another dwelling unit is determined to be the noise source.

[0052] In this example, the apartment building 1 is a four-story building (1F to 4F), and dwelling units 1a numbered 1 to 4 are located adjacent to each other on each floor. Note that this apartment building 1 is merely an example, and other apartment buildings 1 may also be used. In this example, the individual's residence is Unit 1a, No. 3 on the 3rd floor (hereinafter referred to as "Unit 3-3"). The shaded areas in the figure represent dwelling units 1a where impact vibrations (noise where the estimated noise level B exceeds a predetermined threshold) were detected, and the number XX dB in each dwelling unit represents the estimated noise level B where the time T of the detected impact vibration coincides with the noise behavior Y. In this example, the predetermined threshold C is 5 dB.

[0053] In Figure 7(A), the estimated noise level B of the dwelling unit (3-3 dwelling unit) is 50 dB, while the estimated noise values ​​(estimated noise levels B) of the adjacent dwelling units adjacent to the dwelling unit above, below, left, right, and diagonally are 40 to 43 dB. In other words, the estimated noise values ​​of the neighboring dwellings are all lower than that of the dwelling unit itself, and in this case, the source of the noise is determined (estimated) to be the dwelling unit itself (dwelling unit 3-3).

[0054] In FIG. 7(B), the estimated noise level B of the residence (3-3 residence) is 43 dB, while the maximum estimated noise level B of the neighboring residences is 50 dB. In other words, if the neighboring dwelling unit that detected the impact vibration is another dwelling unit that is up to 7 dB louder than the dwelling unit itself, exceeding threshold C (5 dB), then the source of the vibration is determined to be the other dwelling unit (dwelling unit 3-2).

[0055] In Figures 7(A) and (B), if the time T at which the impact vibration occurred or the noisy behavior Y in each dwelling unit 1a is different, it is clear that the sources of the vibrations are different. In this case, in the first identification step S4 described above, a notification permission signal AS is transmitted to the noise notification device 30 of each dwelling unit 1a that has transmitted the noise occurrence notification D. Next, in the individual occurrence notification step S8, the noise occurrence notification D is transmitted to the resident in each dwelling unit 1a that has received the notification permission signal AS.

[0056] Furthermore, in Figure 7(A), when threshold C is set to 8 dB, the estimated noise level of the dwelling unit where multiple similar behaviors occurred does not exceed threshold C (8 dB) compared to the estimated noise level of the adjacent dwelling unit. Therefore, in this case, it is considered that multiple similar behaviors occurred simultaneously in multiple rooms, and the source of the noise is determined to be each of the dwelling units where the multiple similar behaviors occurred. In this case, in the third identification step S7 described above, a notification permission signal AS is transmitted to each of the dwelling units 1a (5 dwelling units 2-3, 3-2, 3-3, 3-4, and 4-3) that transmitted the similar behavior. Next, in the individual occurrence notification step S8, a noise occurrence notification D is transmitted to the residents of the dwelling units 1a that transmitted the notification permission signal AS.

[0057] Similarly, in Figure 7(B), when threshold C is set to 8 dB, in none of the dwelling units where multiple similar acts occurred did the estimated noise level of the dwelling unit itself exceed threshold C (8 dB) compared to the estimated noise level of the adjacent dwelling unit. Therefore, in this case as well, in the third identification step S7, a notification permission signal is sent to each of the dwelling units 1a (4 dwelling units 2-2, 3-2, 3-3, and 4-2) that have been notified of similar behavior. Next, in the individual occurrence notification step S8, a noise occurrence notification D is sent to the residents of the dwelling units 1a that have sent the notification permission signal. [Example]

[0058] An example in which a time-series data analysis tool is used as a machine learning discrimination program will be described below.

[0059] (Validation data) Figure 8 shows the layout of the experimental equipment simulating the upper floor dwelling units. (A) Dwelling unit 1 is constructed using a large slab method without small beams, and (B) Dwelling unit 2 is constructed using a small beam frame, both of which are common slab construction methods for reinforced concrete apartment buildings. The floor slabs of the upper floor units are 200mm thick prestressed reinforced concrete (PRC) for unit 1 and 120mm to 180mm thick reinforced concrete (RC) for unit 2. In the test, acceleration sensors 10 were fixed at two and four locations indicated by ▼ marks in the figure. The acceleration sensors 10 were piezoelectric acceleration sensors, and the data sampling frequency was 12.8 kHz for dwelling unit 1 and 2.56 kHz for dwelling unit 2.

[0060] (Recorded acceleration data 5) Noisy behaviors Y of everyday sounds were recorded and divided into four patterns: impact type Y1, falling type Y2, walking type Y3, and dragging type Y5. Equipment type Y4 was excluded from the study due to the lack of data. Impact patterns for Y1 include jumping, opening and closing a door, dropping a washbasin, dropping a bucket, and opening and closing a sliding door. The drop type Y2 patterns include a washbasin drop, a bucket drop, etc. The walking pattern for Y3 is slipper walking, walking, and slipper jogging. Dragging patterns for Y5 include dragging a chair, dragging a bath stool, opening and closing sliding doors, etc. The length of each data is 1 second. The number of recorded injuries is approximately 1,300 for impact type Y1, approximately 900 for fall type Y2, approximately 3,000 for walking type Y3, and approximately 1,500 for dragging type Y5.

[0061] (Analysis method) The analysis was carried out according to the following procedure. (1) Classify noise behavior Y of daily life sounds and record all acceleration data 5. (2) All acceleration data 5 from dwelling unit 1 and dwelling unit 2 are randomly divided into training and evaluation data in a ratio of 7:3. (3) A feature is extracted from the learning acceleration data 5 according to the feature extraction logic. The feature extraction logic is, for example, the logic shown in FIG. (4) The learning acceleration data 5 is input into a time series data analysis tool for machine learning, and a discrimination program is created that estimates the behavior of daily sounds from the acceleration data 5. (5) The acceleration data 5 for evaluation is input into the discrimination program, an estimation result is obtained, and the estimation performance is evaluated. During the analysis, the data sampling frequency was unified to 2.56 kHz by downsampling.

[0062] (estimated performance) Table 1 shows the estimation results of four patterns (Y1, Y2, Y3, Y5) of living sounds based on the acceleration sensor 10 placed near the center of the slab.

[0063] [Table 1]

[0064] In Table 1, Precision (hereinafter referred to as Pr) means TP / (TP+FP), where TP is the case when the predicted result is positive and the true result is also positive, and FP is the case when the predicted result is positive and the true result is negative. Furthermore, Recall (hereinafter referred to as Re) means TP / (TP+FN), where FN is the case where the predicted result is negative and the true result is positive. Furthermore, F1-score means 2(Re×Pr) / (Re+Pr) and corresponds to the accuracy rate of estimation.

[0065] From the above-mentioned examples, an average F1-score of 0.74 was obtained, and it was confirmed that a general-purpose discrimination program can be constructed by learning using data from various floor construction methods. [Example]

[0066] FIG. 9 is a diagram showing the relationship between the sampling frequency and the F1-score. In this figure, the horizontal axis is the sampling frequency and the vertical axis is the average F1-score. Note that this figure examines the effect of sampling frequency on analysis accuracy under the condition that only data from dwelling unit 1 was used for learning and evaluation.

[0067] From Figure 9, we can see that classification can be performed with an accuracy of about 80% even when the data sampling frequency is reduced to about 300 Hz by downsampling. For example, there is no particular problem even if the sampling frequency is lowered to 2.56 kHz. On the other hand, as mentioned above, when determining octave band waveforms up to a frequency of 500 Hz in frequency analysis, the sampling frequency must cover at least twice the upper limit frequency of 500 Hz (= 500 × √2 ≒ 707 Hz). Therefore, by setting the sampling frequency of the acceleration data 5 to be higher than twice the upper limit frequency of 500 Hz and lower than the target frequency of the acceleration sensor, the load of data analysis can be reduced as much as possible. [Example]

[0068] Figure 10 shows an example of on-site measurements of vibration propagation in a reinforced concrete building. In this figure, (A) is the elevation cross-section of the reinforced concrete building, and (B) is the experimental results.

[0069] In Figure 10(A), a room in a reinforced concrete building (in this example, the center right side) is set as the sound source unit, and the floor slab of the sound source unit is excited with an excitation source (standard lightweight impact source of JIS A 1417-1), and floor slab vibrations are measured in the units adjacent to the sound source unit, directly above it, and diagonally above it. The circles in the figure indicate the excitation sources, and the ▼ marks indicate the measurement points.

[0070] In Figure 10(B), the horizontal axis is the octave band center frequency [Hz], and the vertical axis is the vibration acceleration level attenuation [dB]. Also, the circles, triangles, and squares in the figure represent the attenuation [dB] of the vibration source for the dwelling units next to, directly above, and diagonally above, respectively.

[0071] The following became clear from FIG. 10(B). (1) The attenuation varies depending on the propagation direction and frequency, but is generally more than 5 dB, with an average of about 13 dB. (2) Therefore, if the difference in floor slab vibration (or noise estimate based on vibration) between adjacent dwelling units is 5 dB or more, it can be interpreted that vibration generated in one dwelling unit is propagating to the other. (3) Conversely, if the difference is less than 5 dB, it is possible that vibrations are occurring simultaneously in each dwelling unit. Another possibility is that the difference is small because vibrations are propagating from a source further away than adjacent dwelling units. In this case, however, the vibrations are significantly attenuated, making it unlikely that the estimated noise level will exceed the specified threshold. (4) In the above example, the predetermined threshold C was set to 5 dB, but in practice it is preferable to adjust the value of threshold C to tune the extent to which notifications about vibrations that may be originating from other dwelling units are eliminated. In addition, optimizing the value of threshold C based on a survey of the propagation characteristics of daily vibrations within the building can also improve the accuracy of noise source estimation. [Example]

[0072] Figure 11 shows an example of on-site measurements of vibration propagation in a reinforced concrete building due to the bounce of impact system Y1. In this figure, (A) is the elevation cross-section of the reinforced concrete building, and (B) is the experimental results.

[0073] In Figure 11(A), in a reinforced concrete building, rooms 104, 204, 304, 404, and 504 are located vertically from the bottom up, with room 304 being the sound source room and noisy behavior Y being jumping. Figure 11(B) shows the vibration measurement results for rooms 204, 304, 404, and 504. In each figure, the horizontal axis represents the octave band center frequency [Hz], and the vertical axis represents the vibration acceleration level [dB]. The broken lines in each figure represent multiple measurement values.

[0074] FIG. 12 is a comparison diagram of the amount of attenuation of (A) estimated noise level B and (B) estimated noise level B from the data in FIG. 11(B). In FIG. 12(A), the horizontal axis represents each room corresponding to FIG. 11(A), and the vertical axis represents the estimated noise level [dB]. In FIG. 12(B), the vertical axis represents the attenuation [dB] of the estimated noise level B from the sound source room (Room 304, 3rd floor).

[0075] 12(A) and 12(B), in the above-mentioned source determination step S5 (see FIG. 6), it is possible to identify the noise source (in this example, the third floor) whose estimated noise level B exceeds the predetermined threshold C compared to the adjacent dwelling units (in this example, the fourth and second floors). In this example, it is preferable to set the threshold C to less than 10 dB. Therefore, in this example, in the second identification step S6 described above, only the noise notification device 30 in the dwelling unit (room 304) of the noise source (on the third floor in this example) can be identified as the noise source. [Example]

[0076] Figure 13 shows an example of on-site measurements of vibration propagation in a reinforced concrete building due to the impact of a sliding door opening and closing (impact system Y1). In this figure, (A) shows the elevation cross-section of the reinforced concrete building, and (B) shows the experimental results.

[0077] In FIG. 13(A), rooms 104, 204, 304, 404, and 504 are located vertically in the reinforced concrete building from the bottom up, the sound source room is room 304, and the noisy behavior Y is the opening and closing of a sliding door. Figure 13(B) shows the vibration measurement results for rooms 204, 304, 404, and 504. In each figure, the horizontal axis represents the octave band center frequency [Hz], and the vertical axis represents the vibration acceleration level. The broken lines in each figure represent multiple measurement values.

[0078] FIG. 14 is a comparison diagram of the amount of attenuation of (A) estimated noise level B and (B) estimated noise level B from the data in FIG. 13(B). In FIG. 14(A), the horizontal axis represents each room corresponding to FIG. 13(A), and the vertical axis represents the estimated noise level B. In FIG. 14(B), the vertical axis represents the attenuation [dB] of the estimated noise level B from the sound source room (Room 304, 3rd floor).

[0079] From Figure 14(A)(B), it can be seen that it is difficult to apply this method to impacts transmitted to the floor slab through a partition wall, such as when a sliding door is opened and closed, because the slabs on the upper and lower floors of the residential unit vibrate to the same extent. That is, in the above-mentioned source determination step S5 (see FIG. 6), it is not possible to identify a noise source (in this example, the third floor) whose estimated noise level B exceeds a predetermined threshold C (e.g., 5 dB) more than that of an adjacent dwelling unit (in this example, the fourth floor). Therefore, in this example, in the third identification step S7 described above, a notification permission signal AS (third notification permission signal AS3) is transmitted to the noise notification devices 30 in each of the dwelling units (rooms 304 and 404) that transmitted the similar behavior.

[0080] However, from the results of Figures 13 and 14, in the case of the impact of the sliding door opening and closing of impact system Y1, it is thought that the noise occurs in a room away from the floor and is propagated equally to the floor of that room and the floor of the room directly above. Therefore, in the above-mentioned third identification step S7, if the noise behavior Y is of the same impact type Y1 and the dwelling unit transmitting similar behavior is adjacent above or below, it is preferable to send a third notification permission signal AS3 to the dwelling unit on the upper floor along with a message that the dwelling unit is "unlikely to be the noise source." In this case, only the third notification permission signal AS3, or the third notification permission signal AS3 and a message indicating that "there is a high possibility that the noise source is present," may be transmitted to the dwelling units on the lower floors.

[0081] As described above, the floor slab 2 of the upper dwelling unit is less susceptible to the influence of the living activities of the dwelling unit on the lower floor, but is more likely to vibrate due to the living activities of the dwelling unit on the upper floor. In order to utilize this vibration characteristic, in the present invention, an acceleration sensor 10 is fixed to the floor slab 2 of the upper floor dwelling unit, so that the estimated noise level B propagating to the lower floor dwelling unit can be estimated from the acceleration data 5 generated on the floor slab 2.

[0082] In addition, the control unit 20 estimates the estimated noise level B propagating to the lower floor dwelling unit and preferably the noise behavior Y of daily life sounds from the acceleration data 5, and if the estimated noise level B exceeds a predetermined judgment value, a noise occurrence notification D is sent to the cloud device 60.

[0083] Furthermore, the cloud device 60 estimates the source of the noise from one or more noise occurrence notifications D, and preferably transmits a notification permission signal AS to the noise notification device 30 of the noise source. As a result, the noise notification device 30 that receives the notification permission signal AS can notify its own resident of its own noise occurrence notification D.

[0084] Specifically, if there are no similar acts with the same occurrence time T and noise act Y in multiple adjacent dwelling units 1a, the cloud device 60 identifies each dwelling unit that sent the noise occurrence notification D as the noise source, and preferably transmits a first notification permission signal AS1 to the noise notification device 30 in each dwelling unit. As a result, each dwelling unit that has received the first notification permission signal AS1 can notify its own resident of its own noise occurrence notification D.

[0085] Furthermore, if there are multiple similar behaviors, the estimated noise levels B in the multiple dwelling units 1a are compared. If this comparison identifies a noise source whose estimated noise level B exceeds the predetermined threshold C compared to an adjacent dwelling unit 1a, only the noise notification device 30 in the dwelling unit from which the noise is generated is identified as the noise source, and preferably a second notification permission signal AS2 is transmitted. As a result, only the dwelling unit 1a that is the noise source notifies its own resident of its own noise occurrence notification D, thereby preventing erroneous notification to adjacent dwelling units 1a.

[0086] Furthermore, if the noise source cannot be identified, each dwelling unit that transmitted the similar behavior is identified as the noise source, and preferably a third notification permission signal AS3 is transmitted to the noise notification device 30 of each dwelling unit. As a result, in a plurality of dwelling units 1a where similar noises have occurred at the same time, each noise occurrence notice D can be sent to its own resident.

[0087] Therefore, according to the present invention, it is possible to estimate the source of vibrations (noise) caused by the daily activities of residents of an apartment building, and notify the resident of the source of the estimated noise level B and the noise-causing activity Y.

[0088] The scope of the present invention is not limited to the above-described embodiments, but is indicated by the claims, and further includes all modifications within the meaning and scope equivalent to the claims. [Explanation of symbols]

[0089] AS, AS1, AS2, AS3: Notification permission signal, B: Estimated noise level, C: Threshold, D: Noise occurrence notification, T: Occurrence time, X: Maximum value, Y: Noisy behavior, Y1: Impact behavior, Y2: Falling behavior, Y3: Walking behavior, Y4: Equipment behavior, Y5: Dragging behavior, 1: Apartment building, 1a: Dwelling unit, 2: Floor slab, 4: Vibration acceleration, 5: Acceleration data, 6: Octave band time waveform, 7: Indoor average sound pressure level, 8: Sum of energy, 10: Acceleration sensor, 22: Data storage device, 24: Noise estimation device, 24a: Frequency analyzer, 24b: Radiated sound calculator, 24c: Band composite value calculator, 24d: Maximum level calculator, 26: Behavior estimation device, 28: Occurrence notification device, 30: Noise notification device, 50: Individual detection device, 60: Cloud device, 100: Noise source estimation system

Claims

1. A noise source estimation system for estimating the source of noise that is generated by the daily life sounds of an upper floor dwelling unit in a housing complex where multiple dwelling units are adjacent to each other, comprising: The system comprises an individual detection device installed in each of the plurality of dwelling units, and a cloud device capable of bidirectional communication with the plurality of individual detection devices, The individual detection device includes an acceleration sensor fixed to a floor slab of each of the dwelling units and detecting vibration acceleration occurring in the floor slab; Estimating an estimated noise level of the noise propagating to the lower floor dwelling unit from acceleration data indicating a time change in the vibration acceleration; and a control unit that, when the estimated noise level exceeds a predetermined judgment value, transmits a noise occurrence notification to the cloud device, the notification including the estimated noise level and the time of occurrence of the noise; The cloud device estimates the source of the noise from one or more of the noise occurrence notifications.

2. The device further includes a noise notification device that notifies its resident of the noise occurrence notification when a notification permission signal is received from the cloud device, The noise source estimation system according to claim 1 , wherein the cloud device transmits the notification permission signal to the noise notification device of the noise source.

3. The control unit further estimates the noise behavior of the living sounds from the acceleration data, the noise occurrence notification includes the noise activity; The cloud device (A) determining whether there are multiple similar acts with the same occurrence time and noise act in multiple adjacent dwelling units, and if there are no multiple similar acts, transmitting the notification permission signal to the noise notification device in each of the dwelling units that sent the noise occurrence notification; (B) if there are multiple similar acts, compare the estimated noise levels in the multiple dwelling units to determine whether a noise source can be identified whose estimated noise level exceeds a predetermined threshold value compared to an adjacent dwelling unit; (C) A noise source estimation system as described in claim 2, which transmits the notification permission signal only to the noise notification device of the dwelling unit where the noise source can be identified, and transmits the notification permission signal to the noise notification device of each dwelling unit that transmitted the similar behavior when the noise source cannot be identified.

4. The noise source estimation system according to claim 3 , wherein the threshold value is equal to or greater than 5 dB and equal to or less than 25 dB.

5. The control unit a noise estimation device that estimates the estimated noise level from the acceleration data; an activity estimation device that estimates the noisy activity from the acceleration data; The noise source estimation system according to claim 3 , further comprising: an occurrence notification device that transmits the noise occurrence notification to the cloud device.

6. The noise estimation device comprises: a frequency analyzer that passes the acceleration data through octave band filters with center frequencies of 31.5 Hz, 63 Hz, 125 Hz, 250 Hz, and 500 Hz to obtain a time waveform for each octave band; a radiation sound calculator that calculates an average indoor sound pressure level due to radiation of each of the octave bands from the time waveform; a band synthesis value calculator that synthesizes the energy of the room average sound pressure levels of the respective octave bands to calculate a total energy amount; 6. The noise source estimation system according to claim 5, further comprising: a maximum level calculator that estimates the estimated noise level, which is the maximum level within a target time period, by taking into account a time weighting characteristic of the sum of the combined energy amounts.

7. The noise behavior of the living sounds is an impact-related, a falling-related, a walking-related, a machine-related, and a dragging-related. The noise source estimation system described in claim 5, wherein the activity estimation device uses a discrimination program that is machine-learned using some of the multiple acceleration data classified as the noisy activities as learning data and the rest as evaluation data.

8. the control unit includes a data storage device that stores the acceleration data; 4. The noise source estimation system according to claim 3, wherein the data storage device stores the estimated noise level and the noise behavior of the daily sounds together with the time of occurrence.

9. Using the noise source estimation system according to claim 1, (A) a noise occurrence notification step of transmitting the noise occurrence notification from each of the control units to the cloud device when the estimated noise level exceeds a predetermined judgment value; (B) a similarity determination step of determining whether there are multiple similar acts occurring at the same time in multiple adjacent dwelling units; (C) a first identification step of identifying each of the dwelling units that sent the noise occurrence notification as a noise source when there are not multiple similar acts; (D) a source determination step for, when there are multiple similar acts, comparing the estimated noise levels in the multiple dwelling units to determine whether a noise source can be identified whose estimated noise level exceeds a predetermined threshold value compared to an adjacent dwelling unit; (E) a second identification step of not identifying any of the dwelling units other than the noise source as the noise source when the noise source can be identified; (F) A noise source estimation method comprising a third identification step of identifying each of the dwelling units that transmitted the similar behavior as the noise source if the noise source cannot be identified.

10. The device further includes a noise notification device that notifies its resident of the noise occurrence notification when a notification permission signal is received from the cloud device, In the first identification step, a first notification permission signal is transmitted to the noise notification device of each of the dwelling units that has transmitted the noise occurrence notification; In the second identifying step, a second notification permission signal is transmitted only to the noise notification device of the dwelling unit of the noise source; In the third identification step, a third notification permission signal is transmitted to the noise notification device of each of the dwelling units that transmitted the similar behavior; and (G) A noise source estimation method as described in claim 9, further comprising an individual occurrence notification step of notifying the resident of the noise occurrence notification of the resident when the first notification permission signal, the second notification permission signal, or the third notification permission signal is received.

11. The noise occurrence notification includes the noise behavior of the daily sounds, The noise source estimating method according to claim 9 or 10, wherein the similar behavior is a behavior in which the occurrence time and the noisy behavior are the same.

12. The noise behavior of the living sounds is an impact-related, a falling-related, a walking-related, a machine-related, and a dragging-related. A noise source estimation method as described in claim 11, which uses a discrimination program that has been machine-learned using some of the multiple acceleration data classified as the noisy behavior as learning data and the rest as evaluation data.

13. A noise source estimation method as described in claim 12, wherein in the third identification step, if the noise behavior is of the same impact type and the dwelling unit transmitting the similar behavior is adjacent above or below, a message is sent to the dwelling unit on the upper floor that it is unlikely to be the noise source.

14. 12. The noise source estimating method according to claim 11, wherein the sampling frequency of the acceleration data is set in a range higher than twice the upper limit frequency of an octave band of 500 Hz and lower than a target frequency of the acceleration sensor.

Images