TWI762089B - Machine condition detection system and machine condition detection method - Google Patents
Machine condition detection system and machine condition detection method Download PDFInfo
- Publication number
- TWI762089B TWI762089B TW109144684A TW109144684A TWI762089B TW I762089 B TWI762089 B TW I762089B TW 109144684 A TW109144684 A TW 109144684A TW 109144684 A TW109144684 A TW 109144684A TW I762089 B TWI762089 B TW I762089B
- Authority
- TW
- Taiwan
- Prior art keywords
- machine
- audio
- sound
- condition detection
- features
- Prior art date
Links
Images
Landscapes
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
Description
本發明是有關於一種機台狀況檢測系統以及機台狀況檢測方法,且特別是有關於一種藉由音頻訊號來判斷機台狀況的機台狀況檢測系統以及機台狀況檢測方法。The present invention relates to a machine condition detection system and a machine condition detection method, and more particularly, to a machine condition detection system and a machine condition detection method for judging the machine condition by audio signals.
每個機台是依據一操作程序來運行。一般來說,基於操作程序,機台通常會處於正常的運行狀況。然而,為了預防機台發生異常所衍生出的損失或工安意外,一種機台狀態的監控或檢測機制是被需要的。因此,如何實現精準判斷機台的運行狀況的監控或檢測機制,是本領域技術人員努力研究的課題之一。Each machine operates according to an operating program. Generally speaking, based on operating procedures, the machine is usually in a normal operating condition. However, in order to prevent losses or industrial safety accidents arising from machine abnormalities, a machine state monitoring or detection mechanism is required. Therefore, how to implement a monitoring or detection mechanism for accurately judging the running state of the machine is one of the subjects that those skilled in the art have been working on.
本發明提供一種能夠精準判斷機台的運行狀況的機台狀況檢測系統以及機台狀況檢測方法。The invention provides a machine condition detection system and a machine condition detection method capable of accurately judging the operation condition of the machine.
本發明的機台狀況檢測系統適用於檢測場域內的至少一機台的運行狀況。機台狀況檢測系統包括音頻感測模組以及處理模組。音頻感測模組經配置以持續地接收場域內的音頻訊號。處理模組耦接於音頻感測模組。處理模組經配置以將音頻訊號轉換為對應於單位時間區間的音頻頻譜圖,擷取音頻頻譜圖中的多個第一特徵,並且依據所述多個第一特徵以識別出該至少一機台處於多個運行狀況的其中之一。The machine condition detection system of the present invention is suitable for detecting the operation condition of at least one machine in the field. The machine condition detection system includes an audio sensing module and a processing module. The audio sensing module is configured to continuously receive audio signals within the field. The processing module is coupled to the audio sensing module. The processing module is configured to convert the audio signal into an audio spectrogram corresponding to a unit time interval, extract a plurality of first features in the audio spectrogram, and identify the at least one machine according to the plurality of first features The station is in one of several health states.
本發明的機台狀況檢測方法適用於檢測場域內的至少一機台的運行狀況。機台狀況檢測方法包括:持續地接收場域內的音頻訊號;將音頻訊號轉換為對應於單位時間區間的音頻頻譜圖;擷取音頻頻譜圖中的多個第一特徵;以及依據所述多個第一特徵以識別出所述至少一機台處於多個運行狀況的其中之一。The machine condition detection method of the present invention is suitable for detecting the operation condition of at least one machine in the field. The machine condition detection method includes: continuously receiving audio signals in the field; converting the audio signals into audio spectrograms corresponding to unit time intervals; extracting a plurality of first features in the audio spectrograms; and a first feature to identify that the at least one machine is in one of a plurality of operating conditions.
基於上述,本發明的機台狀況檢測系統以及機台狀況檢測方法依據關聯於音頻訊號的音頻頻譜圖以識別出機台處於多個運行狀況的其中之一。如此一來,機台狀況檢測系統以及機台狀況檢測方法能夠藉由音頻訊號來精準判斷出機台的運行狀況。Based on the above, the machine condition detection system and the machine condition detection method of the present invention identify that the machine is in one of a plurality of operating conditions according to the audio spectrogram associated with the audio signal. In this way, the machine state detection system and the machine state detection method can accurately determine the operation state of the machine by using the audio signal.
為讓本發明的上述特徵和優點能更明顯易懂,下文特舉實施例,並配合所附圖式作詳細說明如下。In order to make the above-mentioned features and advantages of the present invention more obvious and easy to understand, the following embodiments are given and described in detail with the accompanying drawings as follows.
本發明的部份實施例接下來將會配合附圖來詳細描述,以下的描述所引用的元件符號,當不同附圖出現相同的元件符號將視為相同或相似的元件。這些實施例只是本發明的一部份,並未揭示所有本發明的可實施方式。更確切的說,這些實施例只是本發明的專利申請範圍中的裝置與方法的範例。Some embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Element symbols quoted in the following description will be regarded as the same or similar elements when the same element symbols appear in different drawings. These examples are only a part of the invention and do not disclose all possible embodiments of the invention. Rather, these embodiments are merely exemplary of apparatus and methods within the scope of the present invention.
請參考圖1,圖1是依據本發明第一實施例所繪示的機台狀況檢測系統的示意圖。在本實施例中,機台狀況檢測系統100可適用於檢測場域F內的機台的運行狀況。為了便於說明,本實施例的場域F內以一個機台M為例。在一些實施例中,場域F內的機台的數量可以是多個。本發明並不以場域F內的機台數量為限。在本實施例中,場域F可以是任何室內空間的至少一部分。機台M可以是任何的製造設備或檢查設備。Please refer to FIG. 1 . FIG. 1 is a schematic diagram of a machine condition detection system according to a first embodiment of the present invention. In this embodiment, the machine
在本實施例中,機台狀況檢測系統100包括音頻感測模組110以及處理模組120。音頻感測模組110持續地接收場域F內的音頻訊號AS。在本實施例中,音頻感測模組110會持續地接收來自於場域F內的任一位置的音頻訊號AS。在本實施例中,音頻感測模組110可包括至少一個麥克風。為了能夠接收來自於機台M的音頻訊號AS,音頻感測模組110的至少一個麥克風可以被設置在接近於機台M的位置。在一些實施例中,音頻感測模組110的至少一個麥克風的至少一者也可以被設置在接近於機台M內。In this embodiment, the machine
在本實施例中,音頻訊號AS可以是符合MP3、WMA、WAV檔案格式的訊號。In this embodiment, the audio signal AS may be a signal conforming to MP3, WMA, and WAV file formats.
在本實施例中,處理模組120耦接於音頻感測模組110。處理模組120將音頻訊號AS轉換為音頻頻譜圖SP。在本實施例中,處理模組120可例如對音頻訊號AS進行傅立葉轉換(Fourier transform)以產生音頻頻譜圖SP。音頻頻譜圖SP對應於特定的單位時間區間。處理模組120可對音頻訊號AS進行短時距傅立葉轉換(short-time Fourier transform,STFT)以產生音頻頻譜圖SP。在本實施例中,處理模組120擷取音頻頻譜圖SP中的第一特徵F1並且依據第一特徵F1以識別出機台M處於多個運行狀況的其中之一。在本實施例中,處理模組120所擷取到的第一特徵F1的數量可以是一個或多個。In this embodiment, the
舉例來說,機台M的多個運行狀況包括正常運行狀況以及異常運行狀況。當處理模組120識別出第一特徵F1符合機台M的正常運行狀況的音頻特徵時,處理模組120會識別出機台M處於正常運行狀況。在另一方面,當處理模組120識別出第一特徵F1符合機台M的異常運行狀況的音頻特徵時(例如是不正常的碰撞聲或零件掉落聲),處理模組120則會識別出機台M處於異常運行狀況。在本實施例中,處理模組120藉由人工智慧(Artificial Intelligence,AI)方式識別出機台M的多個運行狀況的其中之一。For example, the multiple operating conditions of the machine M include normal operating conditions and abnormal operating conditions. When the
在此值得一提的是,處理模組120會依據關聯於音頻訊號AS的音頻頻譜圖SP以識別出機台M處於多個運行狀況的其中之一。如此一來,機台狀況檢測系統100能夠藉由音頻訊號AS來精準地且即時地判斷出機台M的運行狀況。It is worth mentioning here that the
在本實施例中,處理模組120例如是中央處理單元(Central Processing Unit,CPU),或是其他可程式化之一般用途或特殊用途的微處理器(Microprocessor)、數位訊號處理器(Digital Signal Processor,DSP)、可程式化控制器、特殊應用積體電路(Application Specific Integrated Circuits,ASIC)、可程式化邏輯裝置(Programmable Logic Device,PLD)或其他類似裝置或這些裝置的組合,其可載入並執行電腦程式。處理模組120可以是被設置伺服器、後台主機或電子裝置內。上述的伺服器、後台主機或電子裝置可以被設置在場域F的外部。在一些實施例中,上述的伺服器、後台主機或電子裝置可以被設置在場域F內。在一些實施例中,處理模組120可以與音頻感測模組110整合在同一設備中。In this embodiment, the
在本實施例中,音頻感測模組110的音頻敏感度為-50分貝(dB)至-44分貝,並且音頻感測模組110的取樣頻率大於20000赫茲。也就是說,音頻感測模組110的麥克風的音頻敏感度為-50分貝至-44分貝,並且麥克風的取樣頻率大於20000赫茲(Hz)。如此一來,本實施例能夠提高音頻頻譜圖SP的第一特徵解析度。In this embodiment, the audio sensitivity of the
進一步舉例說明音頻頻譜圖,請同時參考圖1以及圖2,圖2是依據本發明一實施例所繪示的音頻頻譜圖的示意圖。在本實施例中,圖2示例出對應於不同運行狀況的音頻頻譜圖SP1~SP7。音頻頻譜圖SP1是背景音的頻譜圖。背景音是機台M處於正常運行的聲音。音頻頻譜圖SP2是人類聲音的頻譜圖。音頻頻譜圖SP3是來自於機台M的塑膠摩擦所產生的聲音的頻譜圖。音頻頻譜圖SP4是來自於機台M的風扇聲的頻譜圖。音頻頻譜圖SP5來自於機台M的金屬撞擊所產生的聲音的頻譜圖。音頻頻譜圖SP6是來自於機台M的金屬掉落所產生的聲音的頻譜圖。音頻頻譜圖SP7是來自於機台M的晶片撞擊所產生的聲音的頻譜圖(機台M例如是半導體製程設備)。To further illustrate the audio spectrogram, please refer to FIG. 1 and FIG. 2 at the same time. FIG. 2 is a schematic diagram of an audio spectrogram according to an embodiment of the present invention. In this embodiment, FIG. 2 illustrates audio spectrograms SP1 to SP7 corresponding to different operating conditions. The audio spectrogram SP1 is the spectrogram of the background sound. The background sound is the sound when the machine M is in normal operation. The audio spectrogram SP2 is the spectrogram of the human voice. The audio spectrogram SP3 is the spectrogram of the sound produced by the plastic friction of the machine M. The audio spectrogram SP4 is a spectrogram of the fan sound from the machine M. The audio spectrogram SP5 comes from the spectrogram of the sound produced by the metal impact of the machine M. The audio spectrogram SP6 is a spectrogram of the sound produced by the metal falling from the machine M. The audio spectrogram SP7 is a spectrogram of the sound produced by the impact of the wafer from the machine M (the machine M is, for example, a semiconductor process equipment).
在本實施例中,音頻頻譜圖SP1~SP7的縱軸被表示為音頻頻率。音頻頻率可例如是由指數來表示(本發明並不以此為限)。音頻頻譜圖SP1~SP7的橫軸被表示為時間區間。時間區間是關聯於能夠代表上述所有運行狀況的一可識別時間來決定。舉例來說,時間區間可以是3秒(本發明並不以此為限)。也就是說,3秒內的音頻訊號AS足夠可反應出機台M的運行狀況。因此,音頻頻譜圖SP1~SP7例如是最近3秒內的強度窗格(window slot)。音頻頻譜圖SP1~SP7內的顏色或灰階則是對應於音頻以及時間點的強度。音頻頻譜圖SP1~SP7各包括對應於單位時間區間的多個時間點與多個頻率的音頻強度分佈。音頻頻譜圖SP1~SP7的音頻強度分佈就是對應於音頻頻譜圖SP1~SP7的特徵。In this embodiment, the vertical axes of the audio spectrograms SP1 to SP7 are represented as audio frequencies. The audio frequency can be represented by, for example, an index (the invention is not limited to this). The horizontal axis of the audio spectrograms SP1 to SP7 is represented as a time interval. The time interval is determined in relation to an identifiable time that can represent all of the above operating conditions. For example, the time interval may be 3 seconds (the invention is not limited to this). That is to say, the audio signal AS within 3 seconds is sufficient to reflect the operating status of the machine M. Therefore, the audio spectrograms SP1 to SP7 are, for example, intensity panes (window slots) in the last 3 seconds. The colors or grayscales in the audio spectrogram SP1~SP7 correspond to the intensity of the audio and time points. The audio spectrograms SP1 to SP7 each include audio intensity distributions corresponding to multiple time points and multiple frequencies in a unit time interval. The audio intensity distribution of the audio spectrograms SP1~SP7 is the feature corresponding to the audio spectrogram SP1~SP7.
在本實施例中,處理模組120會持續地將最近3秒內的音頻訊號AS轉換為音頻頻譜圖SP,並依據音頻強度分佈擷取音頻頻譜圖SP中的第一特徵F1。舉例來說,當第一特徵F1被判斷出符合音頻頻譜圖SP1的特徵時,這意謂著在最近3秒內,場域F內僅有背景音。因此處理模組120會識別出機台M處於正常運行,並且提供機台M處於正常運行的相關訊息。另舉例來說,當第一特徵F1被判斷出符合音頻頻譜圖SP6的特徵時,處理模組120會判定機台M內發生了金屬撞擊,並且提供機台M內發生金屬撞擊的警示訊息。In this embodiment, the
舉例來說,在本實施例中,處理模組120擷取音頻頻譜圖SP中的多個音頻強度分佈的多個部分,並且將所述多個音頻強度分佈的多個部分進行轉換以產生多個第一特徵F1。處理模組120在擷取到所述多個音頻強度分佈之後,可例如藉由卷積神經網路(Convolutional Neural Networks,CNN)(本發明並不以此為限)模型來對所述多個音頻強度分佈進行轉換,從而獲得多個第一特徵F1。上述多個部分區域例如是音頻頻譜圖SP中已預設的多個感興趣區(regions of interest)或者是具有已預設的感興趣強度分佈的部分區域。因此,本實施例的第一特徵F1的數量可以被設定。For example, in this embodiment, the
請同時參考圖1以及圖3,圖3是依據本發明第一實施例所繪示的機台狀況檢測方法的流程圖。本實施例的機台狀況檢測方法可適用於機台狀況檢測系統100。在步驟S110中,持續地接收場域F內的音頻訊號AS。在本實施例中,步驟S110可以由音頻感測模組110來執行。在步驟S120中,將所接收到的音頻訊號AS轉換為音頻頻譜圖SP。在步驟S130中,擷取音頻頻譜圖SP中的第一特徵F1。在步驟S140中,依據第一特徵F1以識別出機台處於多個運行狀況的其中之一。在本實施例中,步驟S120~S140可以由處理模組120來執行。本實施例的步驟S110~S140的實施細節可以由圖1、圖2的多個實施例中獲得足夠的教示,因此恕不在此重述。Please refer to FIG. 1 and FIG. 3 at the same time. FIG. 3 is a flowchart of a method for detecting a machine condition according to a first embodiment of the present invention. The machine condition detection method of this embodiment can be applied to the machine
請同時參考圖2以及圖4,圖4是依據本發明第二實施例所繪示的機台狀況檢測系統的示意圖。在本實施例中,機台狀況檢測系統200包括音頻感測模組210、處理模組220以及學習模組230。本實施例的音頻感測模組210以及處理模組220的協同操作可以由圖1至圖3的多個實施例中獲得足夠的教示,因此恕不在此重述。在本實施例中,學習模組230耦接於處理模組220。學習模組230收集樣本音頻訊號SAS_1~SAS_7以及多個運行狀況。學習模組230擷取各樣本音頻訊號SAS_1~SAS_7中的第二特徵F2_1~F2_7。舉例來說,學習模組230會擷取樣本音頻訊號SAS_1中的第二特徵F2_1,擷取樣本音頻訊號SAS_2中的第二特徵F2_2,依此類推。Please refer to FIG. 2 and FIG. 4 at the same time. FIG. 4 is a schematic diagram of a machine condition detection system according to a second embodiment of the present invention. In this embodiment, the machine
在本實施例中,學習模組230進一步地將樣本音頻訊號SAS_1~SAS_7轉換為音頻頻譜圖。舉例來說,學習模組230將樣本音頻訊號SAS_1轉換為音頻頻譜圖SP1,將樣本音頻訊號SAS_2轉換為音頻頻譜圖SP2,依此類推。因此,學習模組230可依據音頻頻譜圖SP1的音頻強度分佈擷取第二特徵F2_1,將音頻頻譜圖SP2的音頻強度分佈擷取第二特徵F2_2,依此類推。舉例來說,學習模組230可將音頻頻譜圖SP1的音頻強度分佈的多個部份轉換為多個第二特徵F2_1,將音頻頻譜圖SP2的音頻強度分佈的多個部份轉換為多個第二特徵F2_2,依此類推。In this embodiment, the
在本實施例中,學習模組230還會依據各樣本音頻訊號SAS_1~SAS_7中的第二特徵F2_1~F2_7進行深度學習,使得各樣本音頻訊號SAS_1~SAS_7分別對應於所接收到的運行狀況的其中之一。在本實施例中,深度學習的學習模型可以是長短期記憶(Long Short-Term Memory,LSTM)模型、循環神經網路(Recurrent Neural Networks,RNN)模型、卷積神經網路模型、深度神經網路(Deep Neural Networks,DNN)模型、或區域卷積神經網路(Region-based Convolutional Neural Networks,R-CNN)模型。In this embodiment, the
在進行深度學習之後,學習模組230會將第二特徵F2_1對應到背景音。學習模組230會將第二特徵F2_2對應到人類聲音。學習模組230會將第二特徵F2_3對應到來自於機台(如圖1所示的機台M)的塑膠摩擦所產生的聲音。學習模組230會將第二特徵F2_4對應到來自於機台的風扇聲。學習模組230會將第二特徵F2_5對應到來自於機台的金屬撞擊所產生的聲音。學習模組230會將第二特徵F2_6對應到來自於機台的金屬掉落所產生的聲音。此外,學習模組230還會將第二特徵F2_7對應到來自於機台的晶片撞擊所產生的聲音。因此,第二特徵F2_1~F2_7分別對應於不同的運行狀況。After deep learning is performed, the
在本實施例中,學習模組230會將第二特徵F2_1~F2_7提供至處理模組220。此外,舉例來說,依據實際的使用需求,第二特徵F2_1、F2_3、F2_4可以被設定為機台的正常運行狀況。第二特徵F2_5~F2_7可以被設定為機台的異常運行狀況。In this embodiment, the
在此值得一提的是,依據實際的使用需求,樣本音頻訊號SAS_1~SAS_7以及多個運行狀況可以被提供到學習模組230。如此一來,學習模組230能夠將使用者所提供的樣本音頻訊號SAS_1~SAS_7的第二特徵F2_1~F2_7分別對應到機台的不同運行狀況,藉以實現第二特徵F2_1~F2_7的客製化設定。It is worth mentioning here that, according to actual usage requirements, the sample audio signals SAS_1 to SAS_7 and a plurality of operating conditions can be provided to the
在本實施例中,處理模組220還會對第一特徵F1與所接收到的第二特徵F2_1~F2_7進行比對,以判斷音頻訊號AS的類別是否符合樣本音頻訊號SAS_1~SAS_7的其中之一的類別。舉例來說,當處理模組220判斷出第一特徵F1相似或等於第二特徵F2_1時,處理模組220會判斷音頻訊號AS符合樣本音頻訊號SAS_1,並且識別出機台處於正常運行狀況,並提供機台處於正常運行狀況的訊息。另舉例來說明,當處理模組220判斷出第一特徵F1相似或等於第二特徵F2_7時,處理模組220會判斷音頻訊號AS符合樣本音頻訊號SAS_7,並且判定機台發生晶片撞擊,並提供對應於機台內發生晶片撞擊的警示訊息。在本實施例中,警示訊息可以包括警示光、警示聲以及警示文字的至少其中之一。In this embodiment, the
請同時參考圖4以及圖5,圖5是依據本發明第二實施例所繪示的機台狀況檢測方法的流程圖。本實施例的機台狀況檢測方法可適用於機台狀況檢測系統200。在步驟S210中,收集樣本音頻訊號SAS_1~SAS_7。在步驟S220中,擷取各樣本音頻訊號SAS_1~SAS_7中的第二特徵F2_1~F2_7。在步驟S230中,依據第二特徵F2_1~F2_7進行深度學習,使得樣本音頻訊號SAS_1~SAS_7分別對應於所述多個運行狀況的其中之一。在本實施例中,步驟S210~S230可以由學習模組230來執行。在步驟S240中,持續地接收場域(如,圖1所示的場域F)內的音頻訊號AS。在本實施例中,步驟S210~S230可以由音頻感測模組210來執行。在步驟S250中,將所接收到的音頻訊號AS轉換為音頻頻譜圖SP。在步驟S260中,擷取音頻頻譜圖SP中的第一特徵F1。在本實施例中,步驟S250、S260可以由處理模組220來執行。在步驟S270中,依據第一特徵F1以識別出機台處於多個運行狀況的其中之一。進一步地,在本實施例中,處理模組220會對第一特徵F1與所接收到的第二特徵F2_1~F2_7進行比對,以判斷音頻訊號AS的類別是否符合樣本音頻訊號SAS_1~SAS_7的其中之一的類別,進而識別出機台的運行狀況。在步驟S280中,當機台被識別出處於異常狀況時,處理模組220會提供對應於異常狀況的警示訊息。Please refer to FIG. 4 and FIG. 5 at the same time. FIG. 5 is a flowchart of a machine condition detection method according to a second embodiment of the present invention. The machine condition detection method of this embodiment can be applied to the machine
在本實施例中,步驟S230可以在步驟S240之前被執行。步驟S230也可以在步驟S270之前被執行。In this embodiment, step S230 may be performed before step S240. Step S230 may also be performed before step S270.
綜上所述,本發明的機台狀況檢測系統以及機台狀況檢測方法依據關聯於音頻訊號的音頻頻譜圖以識別出機台處於多個運行狀況的其中之一。如此一來,機台狀況檢測系統以及機台狀況檢測方法能夠藉由音頻訊號來精準判斷出機台的運行狀況。此外,本發明能夠將使用者所提供的多個樣本音頻訊號的多個第二特徵分別對應到機台的不同運行狀況,從而實現客製化的設定。To sum up, the machine condition detection system and the machine condition detection method of the present invention identify that the machine is in one of a plurality of operating conditions according to the audio spectrogram associated with the audio signal. In this way, the machine state detection system and the machine state detection method can accurately determine the operation state of the machine by using the audio signal. In addition, the present invention can respectively correspond to a plurality of second features of a plurality of sample audio signals provided by a user to different operating conditions of the machine, thereby realizing customized settings.
雖然本發明已以實施例揭露如上,然其並非用以限定本發明,任何所屬技術領域中具有通常知識者,在不脫離本發明的精神和範圍內,當可作些許的更動與潤飾,故本發明的保護範圍當視後附的申請專利範圍所界定者為準。Although the present invention has been disclosed above by the embodiments, it is not intended to limit the present invention. Anyone with ordinary knowledge in the technical field can make some changes and modifications without departing from the spirit and scope of the present invention. Therefore, The protection scope of the present invention shall be determined by the scope of the appended patent application.
100、200:機台狀況檢測系統100, 200: Machine condition detection system
110、210:音頻感測模組110, 210: Audio sensing module
120、220:處理模組120, 220: Processing module
230:學習模組230: Learning Mods
AS:音頻訊號AS: audio signal
F:場域F: Field
F1:第一特徵F1: First feature
F2_1~F2_7:第二特徵F2_1~F2_7: Second feature
M:機台M: machine
S110~S140:步驟S110~S140: Steps
S210~S280:步驟S210~S280: Steps
SAS_1~SAS_7:樣本音頻訊號SAS_1~SAS_7: Sample audio signal
SP、SP1~SP7:音頻頻譜圖SP, SP1~SP7: Audio Spectrogram
圖1是依據本發明第一實施例所繪示的機台狀況檢測系統的示意圖。 圖2是依據本發明一實施例所繪示的音頻頻譜圖的示意圖。 圖3是依據本發明第一實施例所繪示的機台狀況檢測方法的流程圖。 圖4是依據本發明第二實施例所繪示的機台狀況檢測系統的示意圖。 圖5是依據本發明第二實施例所繪示的機台狀況檢測方法的流程圖。 FIG. 1 is a schematic diagram of a machine condition detection system according to a first embodiment of the present invention. FIG. 2 is a schematic diagram of an audio spectrogram according to an embodiment of the present invention. FIG. 3 is a flowchart of a method for detecting a machine condition according to the first embodiment of the present invention. FIG. 4 is a schematic diagram of a machine condition detection system according to a second embodiment of the present invention. FIG. 5 is a flowchart of a method for detecting a machine condition according to a second embodiment of the present invention.
100:機台狀況檢測系統 100: Machine condition detection system
110:音頻感測模組 110: Audio sensing module
120:處理模組 120: Processing modules
AS:音頻訊號 AS: audio signal
F:場域 F: Field
F1:第一特徵 F1: First feature
M:機台 M: machine
SP:音頻頻譜圖 SP: Audio Spectrogram
Claims (14)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW109144684A TWI762089B (en) | 2020-12-17 | 2020-12-17 | Machine condition detection system and machine condition detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW109144684A TWI762089B (en) | 2020-12-17 | 2020-12-17 | Machine condition detection system and machine condition detection method |
Publications (2)
Publication Number | Publication Date |
---|---|
TWI762089B true TWI762089B (en) | 2022-04-21 |
TW202225950A TW202225950A (en) | 2022-07-01 |
Family
ID=82198908
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW109144684A TWI762089B (en) | 2020-12-17 | 2020-12-17 | Machine condition detection system and machine condition detection method |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWI762089B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109443525A (en) * | 2018-11-02 | 2019-03-08 | 四川长虹电器股份有限公司 | A kind of equipment abnormal sound detection system and detection method |
TW201942899A (en) * | 2018-03-30 | 2019-11-01 | 維呈顧問股份有限公司 | Detecting system and method of movable noise source |
US20200202869A1 (en) * | 2018-12-24 | 2020-06-25 | Google Llc | Targeted voice separation by speaker conditioned on spectrogram masking |
-
2020
- 2020-12-17 TW TW109144684A patent/TWI762089B/en active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TW201942899A (en) * | 2018-03-30 | 2019-11-01 | 維呈顧問股份有限公司 | Detecting system and method of movable noise source |
CN109443525A (en) * | 2018-11-02 | 2019-03-08 | 四川长虹电器股份有限公司 | A kind of equipment abnormal sound detection system and detection method |
US20200202869A1 (en) * | 2018-12-24 | 2020-06-25 | Google Llc | Targeted voice separation by speaker conditioned on spectrogram masking |
Also Published As
Publication number | Publication date |
---|---|
TW202225950A (en) | 2022-07-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112201260B (en) | Transformer running state online detection method based on voiceprint recognition | |
CN111436944B (en) | Falling detection method based on intelligent mobile terminal | |
CN110837011A (en) | Abnormal data processing method and device, intelligent projector and storage medium | |
CN109300483B (en) | Intelligent audio abnormal sound detection method | |
KR102270347B1 (en) | Apparatus for detecting abnormal situation using deep learning ensemble model and method thereof | |
TW201807413A (en) | Tool status detection system and method thereof | |
CN111964909A (en) | Rolling bearing operation state detection method, fault diagnosis method and system | |
JP2019067197A (en) | Method for detecting trouble sign | |
CN110988137A (en) | Abnormal sound detection system and method based on time-frequency domain characteristics | |
CN116778964A (en) | Power transformation equipment fault monitoring system and method based on voiceprint recognition | |
TWI762089B (en) | Machine condition detection system and machine condition detection method | |
JP3594477B2 (en) | Abnormal noise inspection device | |
CN113053412B (en) | Transformer fault identification method based on sound | |
CN110456769A (en) | Car fault diagnosis method and system | |
CN107644651A (en) | Circuit and method for speech recognition | |
CN116907029A (en) | Method for detecting abnormality of fan in outdoor unit, control device and air conditioner outdoor unit | |
CN116364108A (en) | Transformer voiceprint detection method and device, electronic equipment and storage medium | |
CN116206625A (en) | Self-supervision abnormal sound detection method based on combination of frequency spectrum and time information | |
WO2023053024A1 (en) | Method for identifying and characterizing, by using artificial intelligence, noises generated by a vehicle braking system | |
WO2022142213A1 (en) | Blade fault diagnosis method, apparatus and system, and storage medium | |
CN113703401B (en) | Configuration method and device of anomaly detection algorithm, electronic equipment and storage medium | |
JP3012449B2 (en) | Method and apparatus for identifying acoustic signal | |
CN114997207A (en) | Device state detection method, device, equipment and storage medium | |
TWI453389B (en) | Surveillance method of rotary machine apparatus and surveillance system using the same | |
JP2012177653A (en) | Acoustic diagnosis method, program, and device |