TWI777681B - Vibration monitoring system for electrical machine - Google Patents
Vibration monitoring system for electrical machine Download PDFInfo
- Publication number
- TWI777681B TWI777681B TW110127024A TW110127024A TWI777681B TW I777681 B TWI777681 B TW I777681B TW 110127024 A TW110127024 A TW 110127024A TW 110127024 A TW110127024 A TW 110127024A TW I777681 B TWI777681 B TW I777681B
- Authority
- TW
- Taiwan
- Prior art keywords
- vibration
- data
- motor
- value
- monitoring system
- Prior art date
Links
Images
Landscapes
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
- Control Of Electric Motors In General (AREA)
Abstract
Description
本發明是有關一種用於電動機之振動監測系統，特別是一種能夠依據電動機之振動量測訊號，並將該振動量測訊號轉換為一電動機頻譜特徵資料，進行異常分析、剩餘壽命分析、健康度分析與故障分析，並能夠再發出通知與維修指引之系統。 The present invention relates to a vibration monitoring system for a motor, in particular to a vibration measurement signal of the motor, which can convert the vibration measurement signal into a motor spectrum characteristic data for abnormal analysis, remaining life analysis, and health status. A system that analyzes and analyzes failures, and can then issue notifications and maintenance instructions.
一般機械在運轉情況下會發生漸進式的故障，初期出現異常徵兆時，若未及時處理將有可能造成後續嚴重故障。 Generally, the machinery will have progressive failures during operation. When abnormal signs appear in the initial stage, if not dealt with in time, it may cause subsequent serious failures.
而傳統的維修方法是被動式維修，當機台發生異常，維修工程師才由機台狀態進行故障診斷。由於工業界維護技術的需求，維修的研究重點已逐步轉向狀態監測、預測性維修和故障早期診斷領域。 The traditional maintenance method is passive maintenance. When the machine is abnormal, the maintenance engineer can diagnose the fault based on the state of the machine. Due to the demand for maintenance technology in the industry, the research focus of maintenance has gradually shifted to the fields of condition monitoring, predictive maintenance and early fault diagnosis.
很多半導體製造業將向智慧化電子診斷的方向發展，從而實現即時監測和調整設備營運，這一技術的採用也影響整個工業界與半導體製造業，明顯可知，傳統的維修方法已不適用於半導體製造業等一類的產業了。 Many semiconductor manufacturing industries will develop in the direction of intelligent electronic diagnosis, so as to realize real-time monitoring and adjustment of equipment operations. The adoption of this technology also affects the entire industry and the semiconductor manufacturing industry. It is obvious that traditional maintenance methods are no longer suitable for semiconductors. industries such as manufacturing.
針對上述情況，本案能夠對電動機能夠透過對電動機的振動量測訊號進行收集與監控，並能夠進行異常分析、剩餘壽命分析、健康度分析與故障分析，以於發生嚴重問題前，則能夠發出警示通知，除此之外，更能夠針對所分 析之問題提出維修指引，如此將能夠避免因問題累積而導致嚴重故障的發生，因此本發明應為一最佳解決方案。 In view of the above situation, this case can collect and monitor the motor through the vibration measurement signal of the motor, and can carry out abnormal analysis, remaining life analysis, health analysis and failure analysis, so as to issue warnings before serious problems occur. Notifications, in addition to this, can be more Therefore, the present invention should be an optimal solution to provide maintenance guidelines based on the analyzed problems.
本發明用於電動機之振動監測系統，係應用於一個以上的電動機設施，而該用於電動機之振動監測系統係包含至少一個振動感測裝置，係與該電動機設施進行連接，用以偵測該電動機設施之振動量測訊號；至少一個網路裝置，用以接收資料，並以一網路傳輸方式傳送出去；至少一個訊號轉換裝置，係與該振動感測裝置及該網路裝置電性連接，用以接收該振動感測裝置所偵測之振動量測訊號，且將該振動量測訊號轉換為一電動機頻譜特徵資料，並再將該振動量測訊號之量測時間數據及該電動機頻譜特徵資料透過該網路裝置傳送出去；一伺服設備，係能夠接收該網路裝置所傳送之該量測時間數據及該電動機頻譜特徵資料，而該伺服設備係具有至少一個處理器及至少一個電腦可讀取記錄媒體，該等電腦可讀取記錄媒體儲存有至少一個監測分析應用程式、一正常振動數據資料及多個情境比對檔，其中該電腦可讀取記錄媒體更進一步儲存有電腦可讀取指令，當由該等處理器執行該等電腦可讀取指令時，致使該伺服設備進行下列程序：透過監測分析應用程式將所接收之電動機頻譜特徵資料與該正常振動數據資料進行比對，以輸出一判斷異常結果；用以將該頻段特徵區域資料進行持續儲存並建立出一趨勢模型，用以推估出一總振動值的時間趨勢，再依據該時間趨勢與該量測時間數據輸出一設備可用壽命數據；用以將接收之電動機頻譜特徵資料與不同的情境比對檔進行比對相近機率，並以最高機率的情境比對檔輸出為一故障分析判斷結果；用以能夠將該判斷異常結果、該設備可用壽命數據 或/及該故障分析判斷結果之內容發出一通知訊息。 The vibration monitoring system for an electric motor of the present invention is applied to more than one electric motor facility, and the vibration monitoring system for an electric motor comprises at least one vibration sensing device, which is connected with the electric motor facility to detect the The vibration measurement signal of the motor facility; at least one network device for receiving data and sending it out in a network transmission mode; at least one signal conversion device, which is electrically connected to the vibration sensing device and the network device , for receiving the vibration measurement signal detected by the vibration sensing device, and converting the vibration measurement signal into a motor spectrum characteristic data, and then the measurement time data of the vibration measurement signal and the motor spectrum The characteristic data is transmitted through the network device; a servo device can receive the measurement time data and the motor spectrum characteristic data transmitted by the network device, and the servo device has at least one processor and at least one computer A readable recording medium, the computer readable recording medium stores at least one monitoring and analysis application, a normal vibration data and a plurality of situation comparison files, wherein the computer readable recording medium further stores a computer readable recording medium. read instructions, which, when executed by the processors, cause the servo equipment to perform the following procedures: compare the received motor spectral characteristic data with the normal vibration data through a monitoring and analysis application , to output an abnormal judgment result; it is used to continuously store the characteristic area data of the frequency band and establish a trend model to estimate a time trend of the total vibration value, and then according to the time trend and the measurement time data Output a device usable life data; used to compare the received motor spectrum characteristic data with different situation comparison files to compare the similar probability, and output the situation comparison file with the highest probability as a fault analysis and judgment result; used to be able to The abnormal result of the judgment, the available life data of the equipment Or/and the content of the fault analysis and judgment result will send a notification message.
更具體的說，所述振動量測訊號係為正弦振動波形或是衝擊波波形。 More specifically, the vibration measurement signal is a sinusoidal vibration waveform or a shock wave waveform.
更具體的說，所述該電動機頻譜特徵資料能夠依據不同的頻段分成為多個頻段特徵區域資料。 More specifically, the motor frequency spectrum characteristic data can be divided into a plurality of frequency band characteristic area data according to different frequency bands.
更具體的說，所述正常振動數據資料係為一或多個預設特徵警戒值，而該監測分析應用程式能夠依據該預設特徵警戒值，與電動機頻譜特徵資料進行比對，若達到該預設特徵警戒值，則輸出該判斷異常結果。 More specifically, the normal vibration data is one or more preset characteristic warning values, and the monitoring and analysis application can compare with the motor frequency spectrum characteristic data according to the preset characteristic warning values. If the characteristic warning value is preset, the abnormal judgment result is output.
更具體的說，所述正常振動數據資料係為收集長期正常運作下之資料，並依據該資料以機器學習方式訓練出一判斷模型，並以該判斷模型與該電動機頻譜特徵資料進行比對，若差異性過大，則輸出該判斷異常結果。 More specifically, the normal vibration data is collected from long-term normal operation data, and based on the data, a judgment model is trained by machine learning, and the judgment model is compared with the motor spectrum characteristic data, If the difference is too large, the abnormal judgment result is output.
更具體的說，所述監測分析應用程式能夠將該頻段特徵區域資料依據量測時間數據持續儲存為一總振動歷史數據，並依據該總振動歷史數據建立出該趨勢模型，並藉由該趨勢模型推估出該總振動值的時間趨勢，且再依據該設備機台設定一預設總振動上限值，並再以該預設總振動上限值及該總振動值的時間趨勢進行判斷出一設備可用上限時間數據，再藉由該設備可用上限時間數據與該量測時間數據輸出該設備可用壽命數據。 More specifically, the monitoring and analysis application program can continuously store the frequency band characteristic area data as a total vibration history data according to the measurement time data, establish the trend model according to the total vibration history data, and use the trend The model estimates the time trend of the total vibration value, and then sets a preset total vibration upper limit value according to the equipment machine, and then judges based on the preset total vibration upper limit value and the time trend of the total vibration value A device available upper limit time data is output, and then the device available life data is output through the device available upper limit time data and the measurement time data.
更具體的說，所述監測分析應用程式能夠依據該總振動歷史數據與該預設總振動上限值的比率做為一第一判斷值，並再依據該總振動值的時間趨勢配適一簡單線性回歸，以取得一穩定度，並依該穩定度做為一第二判斷值，之後再以該設備可用壽命數據與該設備可用上限時間數據的比率做為一第三判斷值，最後再將該第一判斷值、該第二判斷值及該第三判斷值以權重分配取得一 健康度數據。 More specifically, the monitoring and analysis application can use the ratio of the total vibration history data to the preset total vibration upper limit value as a first judgment value, and then adapt a value according to the time trend of the total vibration value. Simple linear regression to obtain a stability, and use the stability as a second judgment value, and then use the ratio of the equipment's usable life data to the equipment's usable upper limit time data as a third judgment value, and finally The first judgment value, the second judgment value and the third judgment value are obtained by weight distribution to obtain a health data.
更具體的說，所述監測分析應用程式能夠將接收之頻段特徵區域資料與不同的情境比對檔進行比對，並依據最高機率的情境比對檔輸出為該故障分析判斷結果，且若是判斷該接收之頻段特徵區域資料與每一個情境比對檔的相近機率低於一設定標準之下，則能夠將該接收之頻段特徵區域資料建立為一新的情境比對檔。 More specifically, the monitoring and analysis application can compare the received frequency band characteristic area data with different situation comparison files, and output the fault analysis judgment result according to the situation comparison file with the highest probability, and if the judgment is If the probability of the received frequency band characteristic area data and each situation comparison file is lower than a predetermined standard, the received frequency band characteristic area data can be established as a new situation comparison file.
更具體的說，所述監測分析應用程式能夠提供一回報介面，用以於該監測分析應用程式提供該故障分析判斷結果後，能夠透過該回報介面進行回報一判斷成功結果或是一判斷失效結果，而該監測分析應用程式能夠依據該判斷成功結果或是判斷失效結果進行回報，用以提高故障分析器的準確度。 More specifically, the monitoring and analysis application program can provide a report interface, which is used to report a judgment success result or a judgment failure result through the report interface after the monitoring and analysis application program provides the fault analysis judgment result. , and the monitoring and analysis application program can report according to the judging success result or the judging failure result, so as to improve the accuracy of the fault analyzer.
更具體的說，所述電腦可讀取記錄媒體內儲存有依據不同的情境比對檔所建立的維修指引檔，若是分析出該故障分析判斷結果，該監測分析應用程式能夠於該電腦可讀取記錄媒體找出對應之維修指引檔，以提供維修與零件檢查的排查順序。 More specifically, the computer-readable recording medium stores maintenance guide files established according to different situation comparison files. If the fault analysis and judgment result is analyzed, the monitoring and analysis application program can be read by the computer. Take the recording medium to find the corresponding maintenance guide file to provide the troubleshooting sequence for maintenance and parts inspection.
更具體的說，所述網路傳輸方式係為無線網路傳輸方式或是有線網路傳輸方式。 More specifically, the network transmission method is a wireless network transmission method or a wired network transmission method.
更具體的說，所述通知訊息係能夠透過mail、通訊軟體或是簡訊訊息的技術來發出。 More specifically, the notification message can be sent through mail, communication software, or SMS messaging technology.
1:電動機設施 1: Electric motor facilities
2:振動感測裝置 2: Vibration sensing device
3:訊號轉換裝置 3: Signal conversion device
31:連接線 31: connecting line
4:網路裝置 4: Network device
5:伺服設備 5: Servo equipment
51:處理器 51: Processor
52:電腦可讀取記錄媒體 52: Computer-readable recording medium
521:監測分析應用程式 521: Monitoring and Analysis Applications
5211:資料處理器 5211: Data Processor
5212:異常偵測器 5212: Anomaly Detector
5213:剩餘壽命判斷器 5213: Remaining life judger
5214:健康度判斷器 5214: Health Judger
5215:故障分析器 5215: Fault Analyzer
5216:警報通知器 5216: Alert Notifier
5217:使用介面器 5217: Using the interface
522:資料儲存單元 522: Data storage unit
53:資訊接收/傳輸器 53: Information receiver/transmitter
[第1A圖]係本發明用於電動機之振動監測系統之設備配置示意圖。 [Fig. 1A] is a schematic diagram of the equipment configuration of the vibration monitoring system for electric motors according to the present invention.
[第1B圖]係本發明用於電動機之振動監測系統之網路裝置與伺服設備之連接示意圖。 [FIG. 1B] is a schematic diagram of the connection between the network device and the servo equipment of the vibration monitoring system for the motor according to the present invention.
[第1C圖]係本發明用於電動機之振動監測系統之伺服設備之內部架構示意圖。 [Fig. 1C] is a schematic diagram of the internal structure of the servo equipment used in the vibration monitoring system of the motor according to the present invention.
[第1D圖]係本發明用於電動機之振動監測系統之監測分析應用程式之架構示意圖。 [FIG. 1D] is a schematic diagram of the structure of the monitoring and analysis application program of the vibration monitoring system for electric motors according to the present invention.
[第2A圖]係本發明用於電動機之振動監測系統之資料處理示意圖。 [Fig. 2A] is a schematic diagram of the data processing of the vibration monitoring system for electric motors according to the present invention.
[第2B圖]係本發明用於電動機之振動監測系統之資料處理示意圖。 [Fig. 2B] is a schematic diagram of the data processing of the vibration monitoring system for electric motors according to the present invention.
[第2C圖]係本發明用於電動機之振動監測系統之資料處理示意圖。 [Fig. 2C] is a schematic diagram of the data processing of the vibration monitoring system for electric motors according to the present invention.
[第3圖]係本發明用於電動機之振動監測系統之異常偵測分析流程圖。 [Fig. 3] is a flow chart of the abnormality detection and analysis of the vibration monitoring system of the motor according to the present invention.
[第4圖]係本發明用於電動機之振動監測系統之異常偵測分析之定量分析舉例示意圖。 [FIG. 4] is a schematic diagram of an example of quantitative analysis of abnormality detection and analysis of a vibration monitoring system for a motor according to the present invention.
[第5A圖]係本發明用於電動機之振動監測系統之異常偵測分析之定性分析舉例示意圖。 [FIG. 5A] is a schematic diagram of an example of qualitative analysis of the abnormality detection analysis of the vibration monitoring system for electric motors according to the present invention.
[第5B圖]係本發明用於電動機之振動監測系統之異常偵測分析之定性分析舉例示意圖。 [FIG. 5B] is a schematic diagram of an example of qualitative analysis of the abnormality detection and analysis of the vibration monitoring system for a motor according to the present invention.
[第5C圖]係本發明用於電動機之振動監測系統之異常偵測分析之定性分析舉例示意圖。 [FIG. 5C] is a schematic diagram of an example of qualitative analysis of the abnormality detection analysis of the vibration monitoring system for electric motors according to the present invention.
[第5D圖]係本發明用於電動機之振動監測系統之異常偵測分析之定性分析舉例示意圖。 [FIG. 5D] is a schematic diagram of an example of qualitative analysis of the abnormality detection analysis of the vibration monitoring system for electric motors according to the present invention.
[第6圖]係本發明用於電動機之振動監測系統之剩餘壽命與健康度分析流程圖。 [Fig. 6] is a flow chart of the remaining life and health analysis of the vibration monitoring system for electric motors according to the present invention.
[第7A圖]係本發明用於電動機之振動監測系統之健康度分析說明示意圖。 [Fig. 7A] is a schematic diagram illustrating the health degree analysis of the vibration monitoring system for electric motors according to the present invention.
[第7B圖]係本發明用於電動機之振動監測系統之健康度分析說明示意圖。 [FIG. 7B] is a schematic diagram illustrating the health analysis of the vibration monitoring system for electric motors according to the present invention.
[第7C圖]係本發明用於電動機之振動監測系統之健康度分析說明示意圖。 [Fig. 7C] is a schematic diagram illustrating the health analysis of the vibration monitoring system for electric motors according to the present invention.
[第8圖]係本發明用於電動機之振動監測系統之健康度分析舉例示意圖。 [Fig. 8] is a schematic diagram of an example of the health degree analysis of the vibration monitoring system for electric motors according to the present invention.
[第9圖]係本發明用於電動機之振動監測系統之故障分析流程圖。 [Fig. 9] is a flow chart of the failure analysis of the vibration monitoring system for the motor according to the present invention.
有關於本發明其他技術內容、特點與功效，在以下配合參考圖式之較佳實施例的詳細說明中，將可清楚的呈現。 Other technical contents, features and effects of the present invention will be clearly presented in the following detailed description of the preferred embodiments with reference to the drawings.
請參閱第1A~1D圖，為本發明用於電動機之振動監測系統之設備配置示意圖、網路裝置與伺服設備之連接示意圖、伺服設備之內部架構示意圖及監測分析應用程式之架構示意圖，由圖中可知，該用於電動機之振動監測系統係應用於一廠房內的設備機台上的電動機設施1，該電動機設施1係與該振動感測裝置2進行連接，而連接方式不限於螺固於電動機上或是黏接於電動機表面上，主要是依據電動機設施1種類而有不同的連接方式(連接主要能夠接近電動機的振動源)，其中該電動機設施1能夠為振動電動機或是氣動電動機，而該振動電動機之振動量測訊號係為正弦振動波形，且該氣動電動機之振動量測訊號係為衝擊波波形。
Please refer to Figures 1A to 1D, which are the schematic diagram of the equipment configuration of the vibration monitoring system for electric motors, the schematic diagram of the connection between the network device and the servo equipment, the schematic diagram of the internal structure of the servo equipment, and the schematic diagram of the structure of the monitoring and analysis application program. It can be seen from the above that the vibration monitoring system for a motor is applied to a
該電動機設施1係能夠為恆壓泵浦、風扇馬達、壓縮機、感應電動機，而電動機設施1係不限於穩態&暫態之馬達。
The
而該振動感測裝置2另一端係與該訊號轉換裝置3進行連接，該訊號轉換裝置3用以接收該振動感測裝置2所偵測之振動量測訊號，且將該振動量
測訊號轉換為一電動機頻譜特徵資料，並再將該振動量測訊號之量測時間數據及該電動機頻譜特徵資料與該網路裝置4(網路裝置4是指具有網際網路傳輸功能的任何裝置，例如乙太網路閘道器或/及網路分享器)透過連接線31連接，並以網路傳輸方式(無線網路傳輸方式或是有線網路傳輸方式)傳送出去，如第2A圖所示，該振動感測裝置2取得振動量測訊號後，透過訊號轉換裝置3將一時域圖(Time Domain)轉為電動機頻譜特徵資料，如第2B圖所示，該電動機頻譜特徵資料為一頻域圖(Frequency Domain)，而時域圖轉換為頻域圖，能夠利用傅立葉轉換一類的運算法，將一個時域信號轉換成在不同頻率下對應的振幅及相位，其頻譜就是時域信號在頻域下的表現。
The other end of the
另外，該電動機頻譜特徵資料能夠依據不同的頻段進行頻譜特徵擷取出多個頻段特徵區域資料，而頻譜特徵擷取能夠由該訊號轉換裝置3或是該伺服設備5進行，如第2B及2C圖所示，則將電動機頻譜特徵資料以頻率區間區分成多個區段，其中第2C圖就是把每一個頻段區域的振幅值明確標示出來，而其中Band1的頻率範圍是參考iso規定的振動總量頻率範圍，而Band2~8的頻率範圍定義如下(以下不同頻率範圍定義僅是其中一種實施樣態的舉例，而實際執行，會依據不同設備而有不同Hz的定義範圍)：
In addition, the motor spectral characteristic data can be performed according to different frequency bands to extract a plurality of frequency band characteristic region data, and the spectral characteristic extraction can be performed by the
(1)Band2：55Hz~59Hz (1) Band2: 55Hz~59Hz
(2)Band3：115Hz~117Hz (2) Band3: 115Hz~117Hz
(3)Band4：170Hz~174Hz (3) Band4: 170Hz~174Hz
(4)Band5：227Hz~231Hz (4) Band5: 227Hz~231Hz
(5)Band6：285Hz~290Hz (5) Band6: 285Hz~290Hz
(6)Band7：300Hz~1000Hz (6) Band7: 300Hz~1000Hz
(7)Band8：100Hz~2000Hz (7) Band8: 100Hz~2000Hz
而該網路裝置4能夠與一伺服設備5進行連線，以使該訊號轉換裝置3能夠透過該網路裝置4將該量測時間數據及該電動機頻譜特徵資料傳送給該伺服設備5，該伺服設備5係具有一處理器51、一資訊接收/傳輸器53、一電腦可讀取記錄媒體52，其中該資訊接收/傳輸器53以網路傳輸方式接收該量測時間數據及該電動機頻譜特徵資料，而該電腦可讀取記錄媒體52內儲存有至少一個監測分析應用程式521及一資料儲存單元522，該資料儲存單元522內部係儲存有多種正常振動數據資料、多種情境比對檔、總振動歷史數據、多種維修指引檔(依據不同的情境比對檔所建立)；其中該監測分析應用程式521係包含有：
And the
(1)一資料處理器5211，用以接收該量測時間數據及該電動機頻譜特徵資料，並能夠將該電動機頻譜特徵資料以頻率區間區分成多個區段，以形成多個頻段特徵區域資料；
(1) A
(2)一異常偵測器5212，係與該資料處理器5211相連接，用以對該頻段特徵區域資料進行定量分析或是定性分析，如第3圖所述，說明與舉例如下：
(2) An
(a)定量分析： (a) Quantitative analysis:
(a1)將該電動機頻譜特徵資料301進行定量分析302，之後訂定該正常振動數據資料，而該正常振動數據資料係為一或多個預設特徵警戒值303，最後依據該預設特徵警戒值，與該電動機頻譜特徵資料之多個頻段特徵區域資進行比對，若達到該預設特徵警戒值，則輸出該判斷異常結果並發出警訊304；
(a1)
(a2)如第4圖所示，則是以某冰水泵電動機之總振動量為定量分析的 實施結果圖，過程如下： (a2) As shown in Figure 4, the quantitative analysis is based on the total vibration of an ice water pump motor. The implementation result diagram, the process is as follows:
A.紀錄總振動量實時資料(圖中的不規則振盪曲線)； A. Record the real-time data of the total vibration (the irregular oscillation curve in the figure);
B.以ISO-10816制定振動管制界限為依據(單位：mm/s)，其中振動值<=0.7則代表Good，若是0.7<振動值<=1.8則代表Acceptable，若是1.8<振動值<=4.5則代表Unsatisfactory，若是4.5<振動值則代表Unacceptable； B. Based on ISO-10816 to formulate vibration control limits (unit: mm/s), where vibration value <= 0.7 means Good, if 0.7 < vibration value <= 1.8 means Acceptable, if 1.8 < vibration value <= 4.5 It means Unsatisfactory, if 4.5<vibration value means Unacceptable;
C.圖中顯示振動值超過1.8mm/s共達52次(橫線上方區域)，這表示部分運作當下呈現振動較大，雖不常發生但應留意； C. The figure shows that the vibration value exceeds 1.8mm/s for a total of 52 times (the area above the horizontal line), which means that some operations have a large vibration at the moment, although it does not happen often, it should be paid attention to;
D.進行實時系統逐筆紀錄並警示相關人員介入確認； D. Make real-time system records one by one and alert relevant personnel to intervene for confirmation;
E.除用ISO為參考依據外，亦提供數種制定規範邏輯：平均值*n,n=1,2…；平均值+n*標準差，n=3,4...；中位數+n*IQR,n=1.5,3,…；或是自定義。 E. In addition to using ISO as a reference basis, several formulating normative logics are also provided: mean*n,n=1,2...; mean+n*standard deviation, n=3,4...; median +n*IQR,n=1.5,3,…; or custom.
(b)定性分析： (b) Qualitative analysis:
(b1)將該電動機頻譜特徵資料301進行定性分析305，其中該正常振動數據資料係為收集長期正常運作條件下之資料306，並依據該資料以機器學習方式訓練出一判斷模型307，並能夠提供使用者以介面選擇敏感度(高、標準、低)308後，則能夠將該判斷模型與新的電動機頻譜特徵資料進行比對309，若差異性過大(超過模型決策邊界)，則判斷為異常310並輸出並紀錄該判斷異常結果與發出警訊311，反之，若是比對結果於模型決策邊界內，則判斷為無異常312；
(b1)
(b2)而定性分析所使用的方法為Isolation Forest，該方法簡述如下： (b2) The method used in qualitative analysis is Isolation Forest, which is briefly described as follows:
A.容易被孤立的即為離群點；分佈稀疏且距離高密度較遠之資料即為離群； A. Those that are easily isolated are outliers; data that are sparsely distributed and far away from high density are outliers;
B.將資料集連續且隨機對資料進行切割，直到每個子空間剩1個點； B. Continuously and randomly cut the data set until there is one point left in each subspace;
C.重複上述資料切割行為多次； C. Repeat the above data cutting behavior for many times;
D.多次隨機切割後，計算異常得分，若是愈接近1，愈有可能為異常點，若所有得分皆在0.5左右，則可解釋為可能資料中不具有異常點； D. After multiple random cuts, calculate the abnormal score. If it is closer to 1, it is more likely to be an abnormal point. If all the scores are around 0.5, it can be interpreted that there is no abnormal point in the possible data;
(b3)如第5A~5D圖所示，則是以某冰水泵電動機之總振動量為定性分析的實施結果圖，過程如下： (b3) As shown in Figures 5A to 5D, it is a diagram of the implementation result of qualitative analysis based on the total vibration of a certain ice pump motor. The process is as follows:
A.以冰水泵電動機之葉輪振動資料為例，並收集兩種資料集分別為Normal Set(為正常狀態下之運轉資料，如第5A圖所示)與Testing Set(為葉輪異常狀態下資料，指葉輪不平衡、負載的資料，如第5C圖所示)； A. Take the vibration data of the impeller of the ice pump motor as an example, and collect two data sets: Normal Set (for the operation data in normal state, as shown in Figure 5A) and Testing Set (for the data in the abnormal state of the impeller, Refers to the impeller imbalance, load data, as shown in Figure 5C);
B.其中以Training Set並搭配Isolation Forest機器學習方法獲得模型，並計算其Anomaly Score(為葉輪正常狀態下資料，如第5B圖所示)，從Anomaly Score選擇臨界值，此案例為0.7236，紀錄模型； B. The model is obtained with Training Set and Isolation Forest machine learning method, and its Anomaly Score is calculated (the data under the normal state of the impeller, as shown in Figure 5B), and the critical value is selected from the Anomaly Score. In this case, it is 0.7236, and the record is Model;
C.將模型套用至Testing Set並計算Anomaly Score(如下表一)
D.以0.7236為閥值，Testing Set之Anomaly Score大於0.7236則為異常資料點(如第5D圖中的位於上方區域的資料點)，反之，小於0.7236則為正常點； D. Taking 0.7236 as the threshold, if the Anomaly Score of the Testing Set is greater than 0.7236, it is an abnormal data point (such as the data point in the upper area in Figure 5D), otherwise, if it is less than 0.7236, it is a normal point;
E.將異常資料點紀錄於資料庫，通知相關工程單位查詢； E. Record the abnormal data points in the database and notify the relevant engineering units to inquire;
F.此例顯示異常資料點若持續出現，應注意葉輪是否有異常狀況導致與原正常資料差異變大。 F. This example shows that if abnormal data points continue to appear, you should pay attention to whether there is abnormal condition of the impeller, which causes the difference from the original normal data to become larger.
(3)一剩餘壽命判斷器5213，係與該資料處理器5211相連接，能夠將該頻段特徵區域資料依據量測時間數據持續儲存為一總振動歷史數據，並依據該總振動歷史數據建立出該趨勢模型，並藉由該趨勢模型推估出該總振動值的時間趨勢，且再依據該設備機台設定一預設總振動上限值，並再以該預設總振動上限值及該總振動值的時間趨勢進行判斷出一設備可用上限時間數據，再藉由該設備可用上限時間數據與該量測時間數據輸出該設備可用壽命數據，說明如下：
(3) A remaining
(a)本案以振幅值為依據，從歷史數據配適最佳趨勢模型(線性or非線性模型)。建立振動OA值和時間數列關係，將量測數據轉換成為預測的時間數列資訊，作為預測機台性能退化基礎； (a) In this case, based on the amplitude value, the best trend model (linear or nonlinear model) is fitted from the historical data. Establish the relationship between the vibration OA value and the time series, convert the measurement data into the predicted time series information, and use it as the basis for predicting the performance degradation of the machine;
(b)而運作條件舉例如下： (b) and the operating conditions are as follows:
(b1)需定義警戒值：總振動量以ISO上限值為參考，其他振動量可由場域自訂，而場域定義如下： (b1) The warning value needs to be defined: the total vibration amount is based on the ISO upper limit value, and other vibration amounts can be customized by the field, and the field is defined as follows:
(b11)振幅最大值(Max)*n,n=2,3,...； (b11) Amplitude maximum value (Max)*n, n=2,3,...;
(b12)振幅平均值*n,n=2,3,...； (b12) Average value of amplitude*n,n=2,3,...;
(b13)或是自定義 (b13) or custom
(b2)長時間資料建模較穩健； (b2) Long-term data modeling is more robust;
(c)而運作方式如下(以下運作範例僅是其中一種實施樣態的舉例，而實際執行，會依據不同設備而有不同非線性算法)： (c) The operation method is as follows (the following operation example is only an example of one of the implementation modes, and the actual implementation will have different nonlinear algorithms according to different devices):
(c1)以線性與非線性方式配飾出一趨勢模型 (c1) Fitting a trend model in linear and non-linear ways
(c11)線性：glm (c11) Linear: glm
y=α+βx y = α + βx
(c12)非線性：Exponential Model衰退成指數分配 (c12) Nonlinear: Exponential Model decays into exponential distribution
y=α+e βx y = α + e βx
(c2)以建模模型估算達到上限值之時間，此時間即為End Time(TEnd)。 (c2) Use the modeling model to estimate the time when the upper limit value is reached, and this time is the End Time (TEnd).
(c3)RUL(剩餘壽命)=TFail-Tnow (c3) RUL (Remaining Life) = TFail-Tnow
(4)一健康度判斷器5214，係與該資料處理器5211及該剩餘壽命判斷器5213相連接，能夠依據該總振動歷史數據與該預設總振動上限值的比
率做為一第一判斷值，並再依據該總振動值的時間趨勢配適一簡單線性回歸，以取得一穩定度，並依該穩定度做為一第二判斷值，之後再以該設備可用壽命數據與該設備可用上限時間數據的比率做為一第三判斷值，最後再將該第一判斷值、該第二判斷值及該第三判斷值以權重分配取得一健康度數據，說明如下：
(4) A
(a)本案以設備總振度/部件振動值，模型預估與ISO規範計算健康度，如第6圖所示，先記錄電動機設備歷史總振動量與開始運作日期601後，再進行資料更新602(若有新的資料進來，則將舊資料與新資料合併)，之後進行資料清洗603(用來排除停機狀態資料與排除人為造成異常資料)，最後進行模型配適，估算健康度、剩餘壽命604；
(a) In this case, the health degree is calculated based on the total vibration of the equipment/components, model estimation and ISO specifications. As shown in Figure 6, the historical total vibration of the motor equipment and the start date of
(b)第一判斷值(H1)：以總振動值為參考依據 (b) The first judgment value (H1): take the total vibration value as the reference basis
(b1)ISO規範總振動值上限為(ex：calss 1,<15kw,4.8mm/s)
(b1) The upper limit of the total vibration value of the ISO specification is (ex:
(b2)健康度：
(c)第二判斷值(H2)：以Model R^2解釋穩定度 (c) The second judgment value (H2): explain the stability with Model R^2
(c1)定義振動總量上限值 (c1) Define the upper limit of the total amount of vibration
(c2)採振幅vs.時間配適一簡單線性回歸，並以R^2值轉換表示相依時間之穩定度，以第7A圖為例，量測曲線所配適出的配適線之R2為0.0316，而H2=96.4%，再以第7B圖為例，剛開始為穩定，而一定時間後，曲線往上走則表示為不穩定，量測曲線所配適出的配適線之R2為0.8484，而H2=15.1%， (c2) A simple linear regression is used for amplitude vs. time adaptation, and the R^2 value is converted to represent the stability of time-dependent time. Taking Figure 7A as an example, the R 2 of the fitting line fitted by the measurement curve is measured. It is 0.0316, and H2=96.4%. Taking Figure 7B as an example, it is stable at the beginning, but after a certain period of time, the curve goes up, which means it is unstable. Measure the R of the fitting line fitted by the curve. 2 is 0.8484, and H2=15.1%,
(c3)簡單線性回歸(Y=α+βX+ε)說明如下：樣本資料：(y i ,x i ),i=1...n (c3) Simple linear regression (Y=α+βX+ε) is explained as follows: Sample data: ( y i ,x i ) ,i =1... n
誤差：
最小平方法求誤差最小值，計算
而輸出運算範例如下：lm(formula = Value ~ time2value_1, data = VMS) The output operation example is as follows: lm(formula = Value ~ time2value_1, data = VMS)
Residuals: Min 1Q Median 3Q Max Residuals: Min 1Q Median 3Q Max
-0.47368 -0.14947 -0.00553 0.13945 1.51415 -0.47368 -0.14947 -0.00553 0.13945 1.51415
Coefficients: Estimate Std. Error t value Pr(>|t|) Coefficients: Estimate Std. Error t value Pr(>|t|)
(Intercept) 1.768e+00 5.545e-03 318.89 <2e-16 *** (Intercept) 1.768e+00 5.545e-03 318.89 <2e-16 ***
time2value_1 4.953e-07 5.922e-09 83.63 <2e-16 *** time2value_1 4.953e-07 5.922e-09 83.63 <2e-16 ***
--- ---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1 Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Residual standard error: 0.1837 on 10358 degrees of freedom Residual standard error: 0.1837 on 10358 degrees of freedom
Multiple R-squared: 0.403, Adjusted R-squared: 0.403 Multiple R-squared: 0.403, Adjusted R-squared: 0.403
F-statistic: 6993 on 1 and 10358 DF, p-value: <2.2e-16 F-statistic: 6993 on 1 and 10358 DF, p-value: <2.2e-16
(c4)R^2：值介於0~1之間： (c4)R^2: The value is between 0 and 1:
0：表示穩定，與時間無關，故效能穩定 0: means stable, independent of time, so the performance is stable
1：表示不穩定，與時間相依，故效能不穩定 1: Indicates instability, dependent on time, so the performance is unstable
(d)第三判斷值(H3)：以剩餘壽命估計，如第7C圖所示，其量測資料為不規則的量測曲線，而另一趨勢曲線為弧線向上，並於碰觸到上限值之時間設為TEnd，而T0為開始使用時間，T1為當下量測時間，而估計公式如下：
(e)結合H1 & H2 & H3，並由業主設定權重比例 (e) Combine H1 & H2 & H3, and set the weight ratio by the owner
Healthy=a×H1+b×H2+c×H3,a+b+c=1
Healthy = a ×
(f)實例舉例如第8圖所示，說明如下： (f) An example is shown in Figure 8, and the description is as follows:
(f1)以某半導體廠機台實例，其中總振動量上限值為6，而圖中y軸是表示實際振動資料點，x軸是時間，而橫線則是本例配適之線性趨勢線(y=2.228+3.505x10-7x)，數據顯示此設備振動趨於穩定，預估209天後達警戒上限； (f1) Take an example of a semiconductor factory, where the upper limit of the total vibration amount is 6, and the y-axis in the figure represents the actual vibration data point, the x-axis is time, and the horizontal line is the linear trend of this example. Line (y=2.228+3.505x10 -7 x), the data shows that the vibration of this equipment tends to be stable, and it is estimated that the upper limit of warning will be reached after 209 days;
(f2)而健康度計算如下，H1=52.3%，H2=99.2%，H3=93.7%，採平均計算後，整體健康度估計為81.8%； (f2) The health degree is calculated as follows, H1=52.3%, H2=99.2%, H3=93.7%, after the average calculation, the overall health degree is estimated to be 81.8%;
(f3)而本例的模型配適運算如下：lm(formula = Value ~ time2value_1, data = VMS) (f3) The model fitting operation of this example is as follows: lm(formula = Value ~ time2value_1, data = VMS)
Residuals: Min 1Q Median 3Q Max Residuals: Min 1Q Median 3Q Max
-0.5818 -0.3820 -0.2258 0.2087 3.3649 -0.5818 -0.3820 -0.2258 0.2087 3.3649
Coefficients: Estimate Std. Error t value Pr(>|t|) Coefficients: Estimate Std. Error t value Pr(>|t|)
(Intercept) 2.228e+00 3.909e-02 57.003 <2e-16 *** (Intercept) 2.228e+00 3.909e-02 57.003 <2e-16***
time2value_ 1 3.505e-07 1.420e-07 2.469 0.0138 *
--- ---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1 Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Residual standard error: 0.5703 on 763 degrees of freedom Residual standard error: 0.5703 on 763 degrees of freedom
Multiple R-squared: 0.007927, Adjusted R-squared: 0.006627 Multiple R-squared: 0.007927, Adjusted R-squared: 0.006627
F-statistic:6.097 on 1 and 763 DF, p-value:0.01376 F-statistic: 6.097 on 1 and 763 DF, p-value: 0.01376
(5)一故障分析器5215，係與該資料處理器5211相連接，能夠將接收之頻段特徵區域資料與不同的情境比對檔進行比對，並依據最高機率的情境比對檔輸出為該故障分析判斷結果，且若是判斷該接收之頻段特徵區域資料與每一個情境比對檔的相近機率低於一設定標準之下，則能夠將該接收之頻段特徵區域資料建立為一新的情境比對檔，說明如下：
(5) A
(a)而本案故障分析程序，如第9圖所示，進行電動機設備振動資料模擬901，建立多個情境檔902，再進行資料清洗、標籤化、標準化等處理903之後，進行神經網路訓練、建模、更新904，最後再將模型輸出905，並將模型套用分析906；
(a) The fault analysis program in this case, as shown in Figure 9, simulates the vibration data of the
(b)而當電動機設備新資料輸入907，之後則透過該模型進行故障分析預測908；
(b) When the new data of the electric motor equipment is
(c)而當預測失誤後，系統能夠提供失效預測進行更新模組909，之後則能夠於該資料儲存單元522內的情境庫910內進行更新情境911，用以提高故障分析器的準確度。
(c) When the prediction is wrong, the system can provide failure prediction to update the
(6)一警報通知器5216，係與異常偵測器5212、剩餘壽命判斷器5213、健康度判斷器5214、故障分析器5215相連接，用以當判斷有異常情況時，則能夠透過該資訊接收/傳輸器53以mail、通訊軟體或是簡訊訊息等技術發出通知訊息或是直接顯示於回報介面上。
(6) An
(7)一使用介面器5217，係與異常偵測器5212、剩餘壽命判斷器5213、健康度判斷器5214、故障分析器5215及警報通知器5216相連接，該使用介面器5217能夠提供一回報介面，用以提供該故障分析判斷結果後，能夠透
過該回報介面進行回報一判斷成功結果或是一判斷失效結果，而該監測分析應用程式能夠依據該判斷成功結果或是判斷失效結果進行回報，用以提高故障分析的準確度。
(7) A
另外該電腦可讀取記錄媒體52之資料儲存單元522內儲存有依據不同的情境比對檔所建立的維修指引檔，若是分析出該故障分析判斷結果，該監測分析應用程式521能夠於該電腦可讀取記錄媒體找出對應之維修指引檔，以提供維修與零件檢查的排查順序。
In addition, the
本發明所提供之用於電動機之振動監測系統，與其他習用技術相互比較時，其優點如下： The advantages of the vibration monitoring system for electric motors provided by the present invention are as follows when compared with other conventional technologies:
(1)本發明能夠對電動機能夠透過對電動機的振動量測訊號進行收集與監控，並能夠進行異常分析、剩餘壽命分析、健康度分析與故障分析，以於發生嚴重問題前，則能夠發出警示通知。 (1) The present invention can collect and monitor the motor through the vibration measurement signal of the motor, and can carry out abnormal analysis, remaining life analysis, health analysis and failure analysis, so that a warning can be issued before serious problems occur. Notice.
(2)本發明能夠針對所分析之問題提出維修指引，如此將能夠避免因問題累積而導致嚴重故障的發生。 (2) The present invention can provide maintenance guidelines for the analyzed problems, so that serious failures caused by accumulation of problems can be avoided.
本發明已透過上述之實施例揭露如上，然其並非用以限定本發明，任何熟悉此一技術領域具有通常知識者，在瞭解本發明前述的技術特徵及實施例，並在不脫離本發明之精神和範圍內，當可作些許之更動與潤飾，因此本發明之專利保護範圍須視本說明書所附之請求項所界定者為準。 The present invention has been disclosed above through the above-mentioned embodiments, but it is not intended to limit the present invention. Anyone familiar with this technical field with ordinary knowledge can understand the aforementioned technical features and embodiments of the present invention without departing from the present invention. Within the spirit and scope, some changes and modifications can be made, so the scope of patent protection of the present invention shall be determined by the claims attached to this specification.
1:電動機設施 1: Electric motor facilities
2:振動感測裝置 2: Vibration sensing device
3:訊號轉換裝置 3: Signal conversion device
31:連接線 31: connecting line
4:網路裝置 4: Network device
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW110127024A TWI777681B (en) | 2021-07-22 | 2021-07-22 | Vibration monitoring system for electrical machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW110127024A TWI777681B (en) | 2021-07-22 | 2021-07-22 | Vibration monitoring system for electrical machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| TWI777681B true TWI777681B (en) | 2022-09-11 |
| TW202305339A TW202305339A (en) | 2023-02-01 |
Family
ID=84958100
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| TW110127024A TWI777681B (en) | 2021-07-22 | 2021-07-22 | Vibration monitoring system for electrical machine |
Country Status (1)
| Country | Link |
|---|---|
| TW (1) | TWI777681B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW200600765A (en) * | 2004-03-31 | 2006-01-01 | Chugoku Electric Power | Method and apparatus for assessing remaining life of rolling bearing |
| WO2007099730A1 (en) * | 2006-02-28 | 2007-09-07 | Thk Co., Ltd. | State detection device, state detection method, state detection program, and information recording medium |
| TW201118361A (en) * | 2009-11-25 | 2011-06-01 | China Steel Corp | Method of monitoring and inspecting equipment |
| TW201329427A (en) * | 2011-10-13 | 2013-07-16 | Moventas Gears Oy | A method and a system for the purpose of condition monitoring of gearboxes |
| TWI460416B (en) * | 2011-03-28 | 2014-11-11 | Univ Nat Taiwan | Method and apparatus for judging status of mechanic system |
| TWM603957U (en) * | 2020-07-13 | 2020-11-11 | 財團法人精密機械研究發展中心 | Diagnosis mechanism of harmonic reducer |
-
2021
- 2021-07-22 TW TW110127024A patent/TWI777681B/en active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW200600765A (en) * | 2004-03-31 | 2006-01-01 | Chugoku Electric Power | Method and apparatus for assessing remaining life of rolling bearing |
| WO2007099730A1 (en) * | 2006-02-28 | 2007-09-07 | Thk Co., Ltd. | State detection device, state detection method, state detection program, and information recording medium |
| TW201118361A (en) * | 2009-11-25 | 2011-06-01 | China Steel Corp | Method of monitoring and inspecting equipment |
| TWI460416B (en) * | 2011-03-28 | 2014-11-11 | Univ Nat Taiwan | Method and apparatus for judging status of mechanic system |
| TW201329427A (en) * | 2011-10-13 | 2013-07-16 | Moventas Gears Oy | A method and a system for the purpose of condition monitoring of gearboxes |
| TWM603957U (en) * | 2020-07-13 | 2020-11-11 | 財團法人精密機械研究發展中心 | Diagnosis mechanism of harmonic reducer |
Also Published As
| Publication number | Publication date |
|---|---|
| TW202305339A (en) | 2023-02-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6285119B2 (en) | System and method for monitoring pump cavitation | |
| CA2545695C (en) | Method and system for predicting remaining life for motors featuring on-line insulation condition monitor | |
| RU2756731C2 (en) | Methods and devices for monitoring the structure condition | |
| JP2000259222A (en) | Device monitoring and preventive maintenance system | |
| EP2051086A2 (en) | Method and system for remotely predicting the remaining life of an AC motor system | |
| JP2013516674A (en) | Method and apparatus for monitoring plant equipment performance and predicting failures | |
| EP2581753A1 (en) | Systems and methods for monitoring electrical contacts | |
| JP2017010263A (en) | Preprocessor of abnormality sign diagnosis device and processing method of the preprocessor | |
| KR102102346B1 (en) | System and method for condition based maintenance support of naval ship equipment | |
| WO2002003158A1 (en) | System for diagnosing facility apparatus, managing apparatus and diagnostic apparatus | |
| KR20090010430A (en) | Apparatus for detecting mechanical trouble | |
| US20120303321A1 (en) | Monitoring for invalid data from field instruments | |
| JP2004240642A (en) | Maintenance support device for plant equipment | |
| JP2002073154A (en) | Equipment diagnostic system | |
| US9249794B2 (en) | Condition-based and predictive maintenance of compressor systems | |
| CN117212055A (en) | Wind power generation system and abnormality identification and early warning method for generator winding | |
| CN117171366B (en) | Knowledge graph construction method and system for power grid dispatching operation situation | |
| TWI777681B (en) | Vibration monitoring system for electrical machine | |
| RU2687848C1 (en) | Method and system of vibration monitoring of industrial safety of dynamic equipment of hazardous production facilities | |
| CN117289745B (en) | Operation monitoring method for digital power distribution room | |
| TWM621425U (en) | Vibration monitoring system for electrical machine | |
| CN115146895A (en) | Health assessment of mechanical systems | |
| US11467214B2 (en) | Anomaly detection system and method for electric drives | |
| CN115931112A (en) | Vibration monitoring system for electric motor | |
| KR20160053977A (en) | Apparatus and method for model adaptation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GD4A | Issue of patent certificate for granted invention patent |