TWI754879B - Method for operating fabric setting machine - Google Patents
Method for operating fabric setting machine Download PDFInfo
- Publication number
- TWI754879B TWI754879B TW109100502A TW109100502A TWI754879B TW I754879 B TWI754879 B TW I754879B TW 109100502 A TW109100502 A TW 109100502A TW 109100502 A TW109100502 A TW 109100502A TW I754879 B TWI754879 B TW I754879B
- Authority
- TW
- Taiwan
- Prior art keywords
- data
- partial discharge
- vibration
- setting machine
- normalized
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- D—TEXTILES; PAPER
- D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
- D06C—FINISHING, DRESSING, TENTERING OR STRETCHING TEXTILE FABRICS
- D06C7/00—Heating or cooling textile fabrics
- D06C7/02—Setting
Landscapes
- Engineering & Computer Science (AREA)
- Textile Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Tests Of Circuit Breakers, Generators, And Electric Motors (AREA)
Abstract
Description
本揭露是有關於一種織物定型機的操作方法,且特別是有關於一種織物定型機的馬達的故障預測方法。 The present disclosure is related to an operation method of a fabric setting machine, and more particularly, to a failure prediction method of a motor of the fabric setting machine.
隨著生活水準的提高,消費者對織物的功能有了新的要求,因此織物的需求亦與日俱增。在織物的大量生產過程中,作為織物原料的布材會經過定型處理以使織物的表面平整。由於一般的織物定型設備缺少故障檢測裝置,因此操作人員往往無法提前預知設備故障的發生並作出相對應的準備,且當設備發生故障時,往往須待維修人員進一步檢查方能找出故障的原因並進行修復,從而導致生產線停擺而造成嚴重的損失。 With the improvement of living standards, consumers have new requirements for the function of fabrics, so the demand for fabrics is also increasing. In the mass production process of fabrics, the cloth as the raw material of the fabric is subjected to a setting treatment to make the surface of the fabric flat. Due to the lack of fault detection devices in general fabric setting equipment, operators often cannot predict the occurrence of equipment failures in advance and make corresponding preparations, and when equipment fails, it is often necessary for maintenance personnel to further check to find out the cause of the failure. And repair it, resulting in a shutdown of the production line and causing serious losses.
本揭露內容提供一種具有馬達的織物定型機的操作方法。 The present disclosure provides a method of operating a fabric setting machine with a motor.
根據本揭露一實施方式,織物定型機的操作方法包括以下步驟。採集馬達的電流數據、振動數據、局部放電數 據以及故障類型。建立電流數據、振動數據以及局部放電數據對故障類型的關聯性。重複執行上述步驟,以建立資料庫;依據資料庫內的多筆電流數據、多筆振動數據以及多筆局部放電數據,建立迴歸方程式。在定型機的工作階段採集馬達的工作電流數據、工作振動數據以及工作局部放電數據,並透過關聯性及迴歸方程式分別獲得預計故障類型以及預計故障時間。 According to an embodiment of the present disclosure, an operating method of a fabric setting machine includes the following steps. Collect motor current data, vibration data, partial discharge data data and fault type. Correlate current data, vibration data, and partial discharge data to fault types. The above steps are repeatedly performed to establish a database; a regression equation is established according to a plurality of current data, a plurality of vibration data and a plurality of partial discharge data in the database. In the working stage of the setting machine, the working current data, working vibration data and working partial discharge data of the motor are collected, and the predicted failure type and predicted failure time are obtained respectively through correlation and regression equations.
在本揭露一實施方式中,建立資料庫的步驟包括:對多筆電流數據、多筆振動數據以及多筆局部放電數據進行正規化步驟,以分別得到多筆正規化電流數據、多筆正規化振動數據以及多筆正規化局部放電數據;以及依據多筆正規化電流數據、多筆正規化振動數據以及多筆正規化局部放電數據建立迴歸方程式。 In an embodiment of the present disclosure, the step of establishing a database includes: performing a normalization step on multiple pieces of current data, multiple pieces of vibration data, and multiple pieces of partial discharge data, so as to obtain multiple pieces of normalized current data and multiple pieces of normalized data, respectively. vibration data and multiple pieces of normalized partial discharge data; and establishing a regression equation according to multiple pieces of normalized current data, multiple pieces of normalized vibration data, and multiple pieces of normalized partial discharge data.
在本揭露一實施方式中,迴歸方程式為[預計故障時間=A×(正規化電流數據)-B×(正規化振動數據)-C×(正規化局部放電數據)+D×(正規化電流數據)×(正規化振動數據)+E×(正規化電流數據)1/2×(正規化局部放電數據)],其中A、B、C、D及E為常數,且7.2≦A≦8.8,18.3≦B≦22.3,1.4≦C≦1.8,1.1≦D≦1.3,2.2≦E≦2.7。 In an embodiment of the present disclosure, the regression equation is [expected failure time=A×(normalized current data)−B×(normalized vibration data)−C×(normalized partial discharge data)+D×(normalized current data) data)×(normalized vibration data)+E×(normalized current data) 1/2 ×(normalized partial discharge data)], where A, B, C, D and E are constants, and 7.2≦A≦8.8 , 18.3≦B≦22.3, 1.4≦C≦1.8, 1.1≦D≦1.3, 2.2≦E≦2.7.
在本揭露一實施方式中,織物定型機的操作方法更包括:依據工作電流數據、工作振動數據以及工作局部放電數據修改關聯性、資料庫以及迴歸方程式。 In an embodiment of the present disclosure, the operation method of the fabric setting machine further includes: modifying the correlation, the database and the regression equation according to the working current data, the working vibration data and the working partial discharge data.
在本揭露一實施方式中,電流數據、振動數據以及局部放電數據是分別透過三相電流軌跡圖、振動軌跡圖以及局部放電頻譜圖呈現。 In an embodiment of the present disclosure, the current data, the vibration data, and the partial discharge data are presented through a three-phase current trajectory graph, a vibration trajectory graph, and a partial discharge spectrum graph, respectively.
在本揭露一實施方式中,三相電流軌跡圖所呈現的軌跡形狀為三維橢圓,且電流數據=三維橢圓的長軸長度-三維橢圓的短軸長度。 In an embodiment of the present disclosure, the shape of the trajectory presented by the three-phase current trajectory graph is a three-dimensional ellipse, and the current data=the length of the long axis of the three-dimensional ellipse - the length of the short axis of the three-dimensional ellipse.
在本揭露一實施方式中,振動數據為馬達的軸承在振動軌跡圖中的位移量。 In an embodiment of the present disclosure, the vibration data is the displacement of the bearing of the motor in the vibration trajectory diagram.
在本揭露一實施方式中,故障類型包括定子故障、轉子故障、軸承故障以及對心故障。 In an embodiment of the present disclosure, the fault types include stator faults, rotor faults, bearing faults, and centering faults.
在本揭露一實施方式中,電流數據、振動數據以及局部放電數據分別透過第一感測器、第二感測器以及第三感測器測量,且第一感測器、第二感測器以及第三感測器設置於馬達的軸承上。 In an embodiment of the present disclosure, the current data, the vibration data, and the partial discharge data are measured by the first sensor, the second sensor, and the third sensor, respectively, and the first sensor, the second sensor and the third sensor is arranged on the bearing of the motor.
在本揭露一實施方式中,織物定型機的操作方法更包括:將預計故障類型及預計故障時間傳送至排程系統,以對織物定型機的工作階段進行重新排程。 In an embodiment of the present disclosure, the operation method of the fabric setting machine further includes: transmitting the expected failure type and the expected failure time to the scheduling system, so as to reschedule the working stage of the fabric setting machine.
根據本揭露上述實施方式,在織物定型機的操作方法中,採集馬達的電流數據、振動數據、局部放電數據以及故障類型,從而建立其關聯性以及迴歸方程式。織物定型機的控制系統可分別依據所建立的關聯性以及迴歸方程式預測馬達的故障類型以及故障時間,從而提前作出相對應的準備。此外,透過比對每一次的預測結果與實際故障狀況之間的差異,控制系統可逐步修正已建立好的關聯性以及迴歸方程式,從而提升所獲得的預計故障類型以及預計故障時間的準確性及可靠性。 According to the above-mentioned embodiments of the present disclosure, in the operation method of the fabric setting machine, the current data, vibration data, partial discharge data and fault type of the motor are collected to establish their correlation and regression equation. The control system of the fabric setting machine can predict the failure type and failure time of the motor according to the established correlation and regression equation, so as to make corresponding preparations in advance. In addition, by comparing the difference between each predicted result and the actual fault condition, the control system can gradually correct the established correlation and regression equation, thereby improving the accuracy and accuracy of the predicted fault type and predicted fault time obtained. reliability.
S10、S20、S30、S40、S50、S60、S70‧‧‧步驟 S10, S20, S30, S40, S50, S60, S70‧‧‧Steps
第1圖繪示根據本揭露一實施方式的織物定型機的操作方法的流程圖。 FIG. 1 is a flowchart illustrating an operation method of a fabric setting machine according to an embodiment of the present disclosure.
以下將以圖式揭露本揭露之複數個實施方式,為明確說明起見,許多實務上的細節將在以下敘述中一併說明。然而,應瞭解到,這些實務上的細節不應用以限制本揭露。也就是說,在本揭露部分實施方式中,這些實務上的細節是非必要的。此外,為簡化圖式起見,一些習知慣用的結構與元件在圖式中將以簡單示意的方式繪示之。 Several embodiments of the present disclosure will be disclosed in the following drawings, and for the sake of clarity, many practical details will be described together in the following description. It should be understood, however, that these practical details should not be used to limit the present disclosure. That is, in some embodiments of the present disclosure, these practical details are unnecessary. In addition, for the purpose of simplifying the drawings, some well-known structures and elements will be shown in a simple and schematic manner in the drawings.
本揭露提供一種織物定型機的操作方法,其可針對織物定型機的馬達進行故障類型及故障時間的預測,從而預知故障的發生以提前作出相對應的準備。例如,進行織物定型機工作階段的重新排程以及安排織物定型機的維修作業等。 The present disclosure provides an operating method of a fabric setting machine, which can predict the failure type and failure time of a motor of the fabric setting machine, so as to predict the occurrence of a failure and make corresponding preparations in advance. For example, rescheduling the working stage of the fabric setting machine and scheduling the maintenance work of the fabric setting machine, etc.
第1圖繪示根據本揭露一實施方式的織物定型機的操作方法的流程圖。織物定型機的操作方法包含步驟S10、S20、S30、S40、S50、S60及S70。在步驟S10中,採集馬達的電流數據、振動數據、局部放電數據以及故障類型。在步驟S20中,建立電流數據、振動數據以及局部放電數據對故障類型的關聯性。在步驟S30中,重複執行步驟S10及S20,以建立資料庫。在步驟S40中,依據資料庫內的多筆電流數據、多筆振動數據以及多筆局部放電數據,建立迴歸方程式。在步驟 S50中,在織物定型機的工作階段採集馬達的工作電流數據、工作振動數據以及工作局部放電數據。在步驟S60中,透過關聯性及迴歸方程式分別獲得預計故障類型以及預計故障時間。在步驟S70中,依據工作電流數據、工作振動數據以及工作局部放電數據修改關聯性、資料庫及迴歸方程式。在以下敘述中,將進一步說明上述各步驟。 FIG. 1 is a flowchart illustrating an operation method of a fabric setting machine according to an embodiment of the present disclosure. The operation method of the fabric setting machine includes steps S10, S20, S30, S40, S50, S60 and S70. In step S10, current data, vibration data, partial discharge data and fault type of the motor are collected. In step S20, the correlation of the current data, the vibration data and the partial discharge data to the fault type is established. In step S30, steps S10 and S20 are repeatedly executed to create a database. In step S40, a regression equation is established according to a plurality of current data, a plurality of vibration data and a plurality of partial discharge data in the database. in step In S50, the working current data, working vibration data and working partial discharge data of the motor are collected during the working stage of the fabric setting machine. In step S60, the predicted failure type and the predicted failure time are obtained respectively through the correlation and the regression equation. In step S70, the correlation, the database and the regression equation are modified according to the working current data, the working vibration data and the working partial discharge data. In the following description, the above-mentioned steps will be further explained.
在一些實施方式中,可於織物定型機的馬達的軸承上安裝感測器。感測器可包括第一感測器、第二感測器以及第三感測器,其中第一感測器配置以測量馬達的電流數值,第二感測器配置以測量馬達的振動數值,而第三感測器配置以測量馬達的局部放電數值。詳細來說,第一感測器、第二感測器以及第三感測器可於織物定型機的工作階段分別測量馬達的電流數值、振動數值以及局部放電數值,並將各數值傳輸至織物定型機的控制系統以進一步轉換為電流數據、振動數據以及局部放電數據。 In some embodiments, sensors may be mounted on the bearings of the motors of the fabric setting machine. The sensors may include a first sensor, a second sensor and a third sensor, wherein the first sensor is configured to measure the current value of the motor, the second sensor is configured to measure the vibration value of the motor, The third sensor is configured to measure the partial discharge value of the motor. In detail, the first sensor, the second sensor and the third sensor can respectively measure the current value, vibration value and partial discharge value of the motor during the working stage of the fabric setting machine, and transmit the values to the fabric The control system of the sizing machine is further converted into current data, vibration data and partial discharge data.
在步驟S10中,採集馬達的故障類型,並分別透過第一感測器、第二感測器以及第三感測器測量馬達的電流數值、振動數值以及局部放電數值。故障類型的採集以及電流數值、振動數值及局部放電數值的測量是在織物定型機的工作階段進行。接著,透過織物定型機的控制系統進一步將所測量到的電流數值、振動數值以及局部放電數值分別轉換為電流數據、振動數據以及局部放電數據。 In step S10, the fault type of the motor is collected, and the current value, vibration value and partial discharge value of the motor are measured through the first sensor, the second sensor and the third sensor respectively. The collection of fault types and the measurement of current value, vibration value and partial discharge value are carried out in the working phase of the fabric setting machine. Then, the measured current value, vibration value and partial discharge value are further converted into current data, vibration data and partial discharge data respectively through the control system of the fabric setting machine.
在一些實施方式中,馬達的故障類型包括定子故障、轉子故障、軸承故障以及對心故障。詳細來說,定子故障 包括定子繞組故障、內部放電、槽放電、繞組端部放電或導電粒子故障;轉子故障包括轉子斷條;軸承故障包括軸承斷條、支承部件鬆動或軸承彎曲;對心故障包括動靜態偏心、轉子不對心、轉子不平衡或動靜件摩擦。上述13種故障類型為馬達常見的故障類型,且本揭露的織物定型機的操作方法可針對上述13種故障類型進行故障特徵的採集。 In some embodiments, the types of faults of the motor include stator faults, rotor faults, bearing faults, and centring faults. In detail, the stator fault Including stator winding failure, internal discharge, slot discharge, winding end discharge or conductive particle failure; rotor failure includes broken rotor bar; bearing failure includes broken bearing bar, loose supporting parts or bearing bending; centering failure includes dynamic and static eccentricity, rotor Misalignment, rotor imbalance or friction between moving and static parts. The above 13 fault types are common fault types of motors, and the operation method of the fabric setting machine of the present disclosure can collect fault characteristics for the above 13 fault types.
在一些實施方式中,電流數值可以是馬達的定子的三相電流數值,且三相電流數值可透過三相電流軌跡圖呈現。具體來說,三相電流軌跡圖是透過將三相電流數值的三個振幅分別轉換為三維電流軌跡而獲得的。應瞭解到,在正常的馬達的三相電流軌跡圖中,三相電流數值所呈現的三維電流軌跡形狀分別為三個三維圓形;反之,在故障的馬達的三相電流軌跡圖中,三相電流數值所呈現的三維電流軌跡形狀分別為三個三維橢圓形。 In some embodiments, the current value may be a three-phase current value of a stator of the motor, and the three-phase current value may be represented by a three-phase current trace graph. Specifically, the three-phase current trace map is obtained by converting the three amplitudes of the three-phase current values into three-dimensional current traces, respectively. It should be understood that in the three-phase current trace diagram of a normal motor, the three-dimensional current trace shapes presented by the three-phase current values are three three-dimensional circles; on the contrary, in the three-phase current trace diagram of the faulty motor, the three The three-dimensional current trace shapes presented by the phase current values are three three-dimensional ellipses.
在故障的馬達的三相電流軌跡圖中,馬達的故障相與三維橢圓形的長軸方向一致,也就是說,可根據三維橢圓形的長軸方向判斷馬達的故障相。此外,在故障的馬達的三相電流軌跡圖中,三維橢圓形的長軸的長度與馬達在特定故障相的嚴重程度呈正相關。舉例來說,當馬達於同一負載電流下發生短路的線圈匝數越多,三維橢圓形的長軸的長度越長。在一些實施方式中,織物定型機的控制系統進一步將所測量到的電流數值轉換為電流數據(亦稱作嚴重性因子),且透過電流數據可判斷馬達故障的嚴重程度,其中電流數據=三維橢圓形的長軸長度-三維橢圓形的短軸長度。當電流數據的絕對值越大, 代表馬達在特定故障相的故障程度越大。在一些實施方式中,上述電流數據的範圍可介於-4單位長度至4單位長度之間,亦即,三維橢圓形的長軸減去短軸的長度差的範圍可介於-4單位長度至4單位長度之間。 In the three-phase current trace diagram of the faulty motor, the faulty phase of the motor is consistent with the long axis direction of the three-dimensional ellipse, that is, the faulty phase of the motor can be judged according to the long axis direction of the three-dimensional ellipse. Furthermore, in the three-phase current trace diagram of a faulted motor, the length of the long axis of the three-dimensional ellipse is positively correlated with the severity of the motor in a particular faulty phase. For example, when the number of coil turns of the motor short-circuited under the same load current, the length of the long axis of the three-dimensional ellipse is longer. In some embodiments, the control system of the fabric setting machine further converts the measured current value into current data (also called a severity factor), and the current data can be used to determine the severity of the motor failure, where current data = three-dimensional Ellipse's Major Axis Length - The minor axis length of a 3D ellipse. When the absolute value of the current data is larger, Represents the greater the degree of failure of the motor in the particular faulty phase. In some embodiments, the range of the above current data may be between -4 unit lengths to 4 unit lengths, that is, the range of the length difference between the major axis minus the minor axis of the three-dimensional ellipse may be between -4 unit lengths to 4 units in length.
在一些實施方式中,振動數值可以是馬達的軸承在特定方向(例如,水平的x方向或垂直的y方向)上的位移量,例如,振動數值可包括水平振動數值(x)以及垂直振動數值(y)。振動數值可透過振動軌跡圖以振動數據的形式呈現,且振動數據可以是馬達的軸承於工作階段在二維平面上相對於靜止階段的位移量。舉例來說,在振動軌跡圖中,當靜止階段的馬達的軸承的座標位置為(0,0),且工作階段的馬達的軸承的座標位置為(x,y)時,振動數據可表示為[(x2+y2)1/2]。透過振動軌跡圖中馬達的軸承的位移方向以及振動數據的大小,可判斷馬達於工作階段的偏移方向以及故障程度。在一些實施方式中,振動數據的範圍可介於0微米至300微米之間。 In some embodiments, the vibration value may be the amount of displacement of the bearing of the motor in a specific direction (eg, the horizontal x-direction or the vertical y-direction). For example, the vibration value may include a horizontal vibration value (x) and a vertical vibration value (y). The vibration value can be presented in the form of vibration data through the vibration trajectory graph, and the vibration data can be the displacement of the motor bearing in the working stage relative to the static stage on a two-dimensional plane. For example, in the vibration trajectory diagram, when the coordinate position of the bearing of the motor in the stationary phase is (0, 0), and the coordinate position of the bearing of the motor in the working phase is (x, y), the vibration data can be expressed as [(x 2 +y 2 ) 1/2 ]. Through the displacement direction of the motor's bearing and the magnitude of the vibration data in the vibration trace diagram, the deviation direction and the failure degree of the motor during the working stage can be judged. In some embodiments, the vibration data may range from 0 microns to 300 microns.
在一些實施方式中,局部放電數值可以是馬達內部的三相電流的局部放電數值。局部放電數值可透過局部放電頻譜圖以局部放電數據的形式呈現。在一些實施方式中,局部放電數據可反映馬達的定子繞組的絕緣狀況,也就是說,可根據局部放電數據的大小判斷馬達的定子繞組是否達到其應有的絕緣效果。具體來說,局部放電數據的大小與馬達的定子繞組的絕緣狀況之間的關係如表一所示。在一些實施方式中,局部放電數據具有三個區段的範圍,分別為小於10000pC、介於10000pC至30000pC之間以及大於30000pC。 In some embodiments, the partial discharge value may be the partial discharge value of the three-phase current inside the motor. The partial discharge value can be presented in the form of partial discharge data through the partial discharge spectrogram. In some embodiments, the partial discharge data can reflect the insulation condition of the stator winding of the motor, that is, it can be judged whether the stator winding of the motor achieves its proper insulation effect according to the magnitude of the partial discharge data. Specifically, the relationship between the magnitude of the partial discharge data and the insulation condition of the stator windings of the motor is shown in Table 1. In some embodiments, the partial discharge data has a range of three segments, less than 10000 pC, between 10000 pC to 30000 pC, and greater than 30000 pC, respectively.
表一
在步驟S20中,針對於步驟S10中所採集的電流數據、振動數據、局部放電數據以及故障類型進行歸納及關聯性分析,以建立電流數據、振動數據以及局部放電數據對故障類型的關聯性。透過關聯性的建立,當織物定型機於下次工作階段產生相近(或相同)的工作電流數據、工作振動數據以及工作局部放電數據時,控制系統便可藉由上述關聯性預測馬達可能發生的故障類型。 In step S20, the current data, vibration data, partial discharge data, and fault types collected in step S10 are summarized and correlated, so as to establish the correlation of current data, vibration data, and partial discharge data to fault types. Through the establishment of the correlation, when the fabric setting machine generates similar (or the same) working current data, working vibration data and working partial discharge data in the next working stage, the control system can predict the possible occurrence of the motor based on the above correlation. Fault type.
當完成上述階段後,可視為完整地進行一次電流數據、振動數據、局部放電數據以及故障類型的採集與關聯性的建立。對於單次數據及類型的採集與關聯性建立而言,可將一些參數輸出以作為建立資料庫的試驗數據。此些參數包括電流數據、振動數據、局部放電數據以及故障類型。換句話說,在進行一次數據及類型的採集與關聯性建立後,可得到一筆試驗數據,此試驗數據包括一筆電流數據、一筆振動數據、一筆局部放電數據以及一筆故障類型。在重複進行多次數據及類型的採集與關聯性的建立後,可得到多筆試驗數據。接著,收集多筆試驗數據,從而在步驟S30中透過多筆試驗數據建立出資料庫。 When the above-mentioned stages are completed, the collection and correlation establishment of primary current data, vibration data, partial discharge data and fault types can be regarded as complete. For the collection and correlation establishment of single data and types, some parameters can be output as experimental data for establishing a database. These parameters include current data, vibration data, partial discharge data, and fault type. In other words, after one data and type collection and correlation establishment, a piece of test data can be obtained, and the test data includes a piece of current data, a piece of vibration data, a piece of partial discharge data, and a piece of fault type. After repeated collection of data and types and establishment of correlation, multiple test data can be obtained. Next, a plurality of test data are collected, so that a database is established through the plurality of test data in step S30.
在步驟S40中,透過資料庫中的多筆試驗數據,建立出馬達的故障時間預測模型。馬達的故障時間預測模型的表示方式可以是「預計故障時間對於電流數據、振動數據以及局部放電數據的迴歸方程式」,在本文中以「迴歸方程式」表示。在迴歸方程式中,預計故障時間是應變數,而電流數據、振動數據以及局部放電數據是自變數。透過迴歸方程式的建立,控制系統可藉由採集工作階段的馬達的工作電流數據、工作振動數據以及工作局部放電數據而預測馬達預計發生故障的時間。 In step S40 , a prediction model of motor failure time is established through multiple test data in the database. The representation of the failure time prediction model of the motor can be "the regression equation of the predicted failure time on the current data, vibration data and partial discharge data", which is represented by the "regression equation" in this paper. In the regression equation, the expected failure time is the strain number, and the current data, vibration data, and partial discharge data are the independent variables. Through the establishment of the regression equation, the control system can predict the time when the motor is expected to fail by collecting the working current data, working vibration data and working partial discharge data of the motor in the working stage.
在一些實施方式中,為了降低不同的織物定型機於操作時的差異,可於建立馬達的故障時間預測模型之前進行正規化(或標準化)步驟。具體來說,在將每一筆試驗數據儲存至資料庫前,可先針對每一筆試驗數據中的每一筆電流數據、每一筆振動數據以及每一筆局部放電數據進行正規化步驟。在一些實施方式中,電流數據、振動數據以及局部放電數據是分別透過不同的正規化計算式進行正規化步驟,且電流數據、振動數據以及局部放電數據分別具有不同的正規化範圍。舉例來說,電流數據的正規化計算式為:正規化電流數據=電流數據+4,且其正規化電流數據的範圍為介於0至8之間;振動數據的正規化計算式為:正規化振動數據=振動數據/1000,且其正規化振動數據的範圍為介於0至0.3之間;局部放電數據的正規化計算式為:正規化局部放電數據=局部放電數據/10000,且正規化局部放電數據的範圍為介於0至3之間。 In some embodiments, a normalization (or normalization) step may be performed prior to building a motor failure time prediction model in order to reduce variability in the operation of different fabric setting machines. Specifically, before storing each piece of test data in the database, a normalization step may be performed for each piece of current data, each piece of vibration data, and each piece of partial discharge data in each piece of test data. In some embodiments, the current data, the vibration data, and the partial discharge data are normalized through different normalization formulas, respectively, and the current data, the vibration data, and the partial discharge data have different normalization ranges. For example, the normalized calculation formula of current data is: normalized current data=current data+4, and the range of the normalized current data is between 0 and 8; the normalized calculation formula of vibration data is: normalized current data Normalized vibration data=vibration data/1000, and the range of normalized vibration data is between 0 and 0.3; the normalized calculation formula of partial discharge data is: normalized partial discharge data=partial discharge data/10000, and normalized partial discharge data The range of the partial discharge data is between 0 and 3.
在進行正規化步驟後,便可得到多筆正規化電流 數據、多筆正規化振動數據以及多筆正規化局部放電數據。在一些實施方式中,迴歸方程式是依據多筆正規化後的數據所建立。舉例來說,迴歸方程式可表示為:[預計故障時間=A×(正規化電流數據)-B×(正規化振動數據)-C×(正規化局部放電數據)+D×(正規化電流數據)×(正規化振動數據)+E×(正規化電流數據)1/2×(正規化局部放電數據)],其中A、B、C、D及E為常數,且7.2≦A≦8.8,18.3≦B≦22.3,1.4≦C≦1.8,1.1≦D≦1.3,2.2≦E≦2.7。 After the normalization step is performed, multiple pieces of normalized current data, multiple pieces of normalized vibration data, and multiple pieces of normalized partial discharge data can be obtained. In some embodiments, the regression equation is established based on multiple pieces of normalized data. For example, the regression equation can be expressed as: [Expected time to failure=A×(normalized current data)−B×(normalized vibration data)−C×(normalized partial discharge data)+D×(normalized current data) )×(normalized vibration data)+E×(normalized current data) 1/2 ×(normalized partial discharge data)], where A, B, C, D and E are constants, and 7.2≦A≦8.8, 18.3≦B≦22.3, 1.4≦C≦1.8, 1.1≦D≦1.3, 2.2≦E≦2.7.
在步驟S50中,採集馬達的工作電流數據、工作振動數據以及工作局部放電數據。工作電流數據、工作振動數據以及工作局部放電數據的採集是在織物定型機的工作階段進行。在一些實施方式中,工作電流數據、工作振動數據以及工作局部放電數據的採集是分別透過以第一感測器、第二感測器以及第三感測器測量工作電流數值、工作振動數值以及工作局部放電數值,並將各數值經由控制系統轉換而得。 In step S50, the working current data, the working vibration data and the working partial discharge data of the motor are collected. The collection of working current data, working vibration data and working partial discharge data is carried out in the working stage of the fabric setting machine. In some embodiments, the working current data, the working vibration data and the working partial discharge data are collected by measuring the working current value, the working vibration value and the The working partial discharge value is obtained by converting each value through the control system.
在步驟S60中,透過於步驟S50中所採集的工作電流數據、工作振動數據與工作局部放電數據以及於步驟S20中所建立的電流數據、振動數據以及局部放電數據對故障類型的關聯性,可預測織物定型機的馬達於下次發生故障的類型(即預計故障類型)以及此預計故障類型發生的機率,且預計故障類型可以是於步驟S10中所採集的13種故障類型中的任一者。此外,透過於步驟S50中所採集的工作電流數據、工作振動數據與工作局部放電數據以及於步驟S40中所建立的故障時間預測模型(即迴歸方程式),可預測織物定型機的馬達於下 次發生故障的時間(即預計故障時間)。表二為透過上述關聯性以及故障時間預測模型來分別獲得預計故障類型以及預計故障時間的實施例1至實施例15。 In step S60, through the working current data, the working vibration data and the working partial discharge data collected in step S50, and the correlation between the current data, vibration data and partial discharge data established in step S20 to the fault type, it is possible to Predict the type of failure of the motor of the fabric setting machine next time (ie, the predicted failure type) and the probability of the predicted failure type, and the predicted failure type can be any one of the 13 failure types collected in step S10 . In addition, through the working current data, working vibration data and working partial discharge data collected in step S50 and the failure time prediction model (ie regression equation) established in step S40, it can be predicted that the motor of the fabric setting machine will be in the following The time at which the next failure occurs (ie, the expected failure time). Table 2 shows Examples 1 to 15 in which the predicted failure type and the predicted failure time are obtained respectively through the above correlation and failure time prediction model.
表二
在一些實施方式中,可將於步驟S60中所預測的故障類型以及故障時間傳送至織物定型機的排程系統,從而對 織物定型機的工作階段進行重新排程。具體來說,排程系統可根據預計故障類型以及預計故障時間重新安排後續的製程順序(例如,將交期較早的訂單提前安排至織物定型機故障前執行)以及製程產量。此外,排程系統亦可根據預計故障類型以及預計故障時間提前安排維修作業,以減少織物定型機因故障而無法運作的時間。 In some embodiments, the failure type and failure time predicted in step S60 may be transmitted to the scheduling system of the fabric setting machine, so that the The work phases of the fabric setting machine are rescheduled. Specifically, the scheduling system can rearrange the subsequent process sequence according to the expected failure type and expected failure time (for example, scheduling an order with an earlier delivery date to be executed before the fabric setting machine fails) and the process output. In addition, the scheduling system can also arrange maintenance operations in advance according to the expected failure type and expected failure time, so as to reduce the time when the fabric setting machine cannot be operated due to failure.
在步驟S70中,當織物定型機發生故障後,透過比對預計故障類型及時間與實際故障類型及時間之間的差異,控制系統可修正資料庫中的各數據以及已建立好的關聯性與迴歸方程式,從而提升所獲得的預計故障類型以及預計故障時間的準確性及可靠性。 In step S70, when the fabric setting machine fails, by comparing the difference between the predicted failure type and time and the actual failure type and time, the control system can correct the data in the database and the established correlation with the The regression equation improves the accuracy and reliability of the predicted failure type and predicted failure time obtained.
本揭露提供一種織物定型機的操作方法,其可針對織物定型機的馬達進行故障類型及故障時間的預測。在織物定型機的操作方法中,採集馬達的電流數據、振動數據、局部放電數據以及故障類型,從而建立其關聯性以及迴歸方程式。織物定型機的控制系統可分別依據所建立的關聯性以及迴歸方程式預測馬達的故障類型以及故障時間,從而提前做出相對應的準備。此外,透過比對每一次的預測結果與實際故障狀況之間的差異,控制系統可逐步修正已建立好的關聯性以及迴歸方程式,從而提升所獲得的預計故障類型以及預計故障時間的準確性及可靠性。 The present disclosure provides an operation method of a fabric setting machine, which can predict the failure type and failure time of a motor of the fabric setting machine. In the operation method of the fabric setting machine, the current data, vibration data, partial discharge data and fault type of the motor are collected to establish their correlation and regression equation. The control system of the fabric setting machine can predict the failure type and failure time of the motor according to the established correlation and regression equation, so as to make corresponding preparations in advance. In addition, by comparing the difference between each predicted result and the actual fault condition, the control system can gradually correct the established correlation and regression equation, thereby improving the accuracy and accuracy of the predicted fault type and predicted fault time obtained. reliability.
雖然本揭露已以實施方式揭露如上,然其並非用以限定本揭露,任何熟習此技藝者,在不脫離本揭露之精神和範圍內,當可作各種之更動與潤飾,因此本揭露之保護範圍當 視後附之申請專利範圍所界定者為準。 Although the present disclosure has been disclosed as above in embodiments, it is not intended to limit the present disclosure. Anyone skilled in the art can make various changes and modifications without departing from the spirit and scope of the present disclosure. Therefore, the present disclosure protects range when The scope of the patent application attached shall prevail.
S10、S20、S30、S40、S50、S60、S70‧‧‧步驟 S10, S20, S30, S40, S50, S60, S70‧‧‧Steps
Claims (9)
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911222921.1A CN112903001A (en) | 2019-12-03 | 2019-12-03 | Operation method of fabric setting machine |
CN201911222921.1 | 2019-12-03 |
Publications (2)
Publication Number | Publication Date |
---|---|
TW202122939A TW202122939A (en) | 2021-06-16 |
TWI754879B true TWI754879B (en) | 2022-02-11 |
Family
ID=76104666
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW109100502A TWI754879B (en) | 2019-12-03 | 2020-01-07 | Method for operating fabric setting machine |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN112903001A (en) |
TW (1) | TWI754879B (en) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TW201023061A (en) * | 2008-12-03 | 2010-06-16 | Ind Tech Res Inst | System and method of prognostic analysis and resource planning for apparatu |
CN102466566A (en) * | 2010-11-03 | 2012-05-23 | 财团法人工业技术研究院 | Power equipment abnormality detection device and detection method thereof |
TW201333188A (en) * | 2011-09-25 | 2013-08-16 | Theranos Inc | Systems and methods for multi-analysis |
CN103429876A (en) * | 2011-03-14 | 2013-12-04 | 通用电气公司 | Condition monitoring of mechanical drive train coupled with electrical machine |
CN104160269A (en) * | 2012-01-09 | 2014-11-19 | Isis创新有限公司 | Monitoring engine components |
CN104380126A (en) * | 2012-06-14 | 2015-02-25 | 三菱电机株式会社 | Apparatus for detecting deterioration of power module |
US20160350671A1 (en) * | 2015-05-28 | 2016-12-01 | Predikto, Inc | Dynamically updated predictive modeling of systems and processes |
TW201842428A (en) * | 2017-04-05 | 2018-12-01 | 日商荏原製作所股份有限公司 | Semiconductor manufacturing apparatus, failure prediction method for semiconductor manufacturing apparatus, and failure prediction program for semiconductor manufacturing apparatus |
US10430719B2 (en) * | 2014-11-25 | 2019-10-01 | Stream Mosaic, Inc. | Process control techniques for semiconductor manufacturing processes |
WO2019216975A1 (en) * | 2018-05-07 | 2019-11-14 | Strong Force Iot Portfolio 2016, Llc | Methods and systems for data collection, learning, and streaming of machine signals for analytics and maintenance using the industrial internet of things |
Family Cites Families (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103024761B (en) * | 2011-09-26 | 2016-03-02 | 艾默生网络能源有限公司 | Base station energy consumption method for establishing model, energy consumption Forecasting Methodology and device |
CN103176128A (en) * | 2013-03-28 | 2013-06-26 | 华南理工大学 | Method and system for forcasting state of wind generating set and diagnosing intelligent fault |
CN203278198U (en) * | 2013-05-08 | 2013-11-06 | 青岛数能电气工程有限公司 | Motor fault predetermination protective device |
CN107194053B (en) * | 2017-05-16 | 2020-10-20 | 歌拉瑞电梯股份有限公司 | Intelligent elevator control system operation fault prediction method |
CN107247230B (en) * | 2017-07-03 | 2020-02-07 | 浙江大学 | Rotary motor state monitoring method based on support vector machine and data driving |
CN107657335A (en) * | 2017-09-06 | 2018-02-02 | 武汉科技大学 | A kind of spatial and temporal distributions Forecasting Methodology of airport traffic |
CN107742168B (en) * | 2017-10-20 | 2021-04-02 | 西北工业大学 | Production workshop dynamic bottleneck prediction method based on Internet of things technology |
CN107679634A (en) * | 2017-10-27 | 2018-02-09 | 国网陕西省电力公司西安供电公司 | A kind of method that power supply trouble based on data visualization reports analysis and prediction for repairment |
CN109616201B (en) * | 2018-11-09 | 2023-10-31 | 深圳职业技术大学 | Fatigue early warning method based on small data dynamic prediction model |
CN109739213A (en) * | 2019-01-07 | 2019-05-10 | 东莞百宏实业有限公司 | A kind of failure prediction system and prediction technique |
CN110136014A (en) * | 2019-05-23 | 2019-08-16 | 王为光 | A kind of medical insurance data analysing method based on big data |
CN110276416B (en) * | 2019-07-02 | 2023-04-28 | 广东省智能机器人研究院 | Rolling bearing fault prediction method |
CN110257577B (en) * | 2019-07-16 | 2020-04-24 | 中南大学 | Burning process control method and system for ball type hot blast stove |
CN110376522B (en) * | 2019-09-03 | 2021-07-16 | 宁夏西北骏马电机制造股份有限公司 | Motor fault diagnosis method of data fusion deep learning network |
-
2019
- 2019-12-03 CN CN201911222921.1A patent/CN112903001A/en active Pending
-
2020
- 2020-01-07 TW TW109100502A patent/TWI754879B/en active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TW201023061A (en) * | 2008-12-03 | 2010-06-16 | Ind Tech Res Inst | System and method of prognostic analysis and resource planning for apparatu |
CN102466566A (en) * | 2010-11-03 | 2012-05-23 | 财团法人工业技术研究院 | Power equipment abnormality detection device and detection method thereof |
CN103429876A (en) * | 2011-03-14 | 2013-12-04 | 通用电气公司 | Condition monitoring of mechanical drive train coupled with electrical machine |
TW201333188A (en) * | 2011-09-25 | 2013-08-16 | Theranos Inc | Systems and methods for multi-analysis |
CN104160269A (en) * | 2012-01-09 | 2014-11-19 | Isis创新有限公司 | Monitoring engine components |
CN104380126A (en) * | 2012-06-14 | 2015-02-25 | 三菱电机株式会社 | Apparatus for detecting deterioration of power module |
US10430719B2 (en) * | 2014-11-25 | 2019-10-01 | Stream Mosaic, Inc. | Process control techniques for semiconductor manufacturing processes |
US20160350671A1 (en) * | 2015-05-28 | 2016-12-01 | Predikto, Inc | Dynamically updated predictive modeling of systems and processes |
TW201842428A (en) * | 2017-04-05 | 2018-12-01 | 日商荏原製作所股份有限公司 | Semiconductor manufacturing apparatus, failure prediction method for semiconductor manufacturing apparatus, and failure prediction program for semiconductor manufacturing apparatus |
WO2019216975A1 (en) * | 2018-05-07 | 2019-11-14 | Strong Force Iot Portfolio 2016, Llc | Methods and systems for data collection, learning, and streaming of machine signals for analytics and maintenance using the industrial internet of things |
Also Published As
Publication number | Publication date |
---|---|
CN112903001A (en) | 2021-06-04 |
TW202122939A (en) | 2021-06-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111758036B (en) | System and method for monitoring an operating state of an operating electrical device | |
CN103823150B (en) | Turbo generator rotor interturn short circuit fault diagnosis method of multi sensor joint | |
CN104655977B (en) | Generator excitation Winding Short Fault Diagnosis method based on torque comparison principle | |
KR102676587B1 (en) | On-line fault diagnosis method for motor of machine tool | |
Fenger et al. | Development of a tool to detect faults in induction motors via current signature analysis | |
CN113748326A (en) | Method for estimating severity of bearing failure for induction motor | |
US11411521B2 (en) | Method for static eccentricity fault detection of induction motors | |
JP2022552683A (en) | Fault detection in synchronous machines | |
US10430038B2 (en) | Automated data overlay in industrial monitoring systems | |
KR20150058928A (en) | Plant defect diagnostic system using vibration characteristics | |
Ferracuti et al. | Induction motor fault detection and diagnosis using KDE and Kullback-Leibler divergence | |
CN103674545A (en) | Mechanical fault detecting method | |
TWI754879B (en) | Method for operating fabric setting machine | |
Leonidovich et al. | The development and use of diagnostic systems and estimation of residual life in industrial electrical equipment | |
CN106989879B (en) | Modal testing method for steam turbine generator base | |
Osornio-Rios et al. | Data fusion system for electric motors condition monitoring: an innovative solution | |
CN104391220A (en) | Improved turbo-generator excitation winding short-circuit fault on-line detection method | |
CN112285562B (en) | Asynchronous motor fault detection method based on electromagnetic field and thermal field multi-signal fusion | |
US9836817B2 (en) | Synchronized zooming across multiple plots | |
Serna et al. | Detection of rotor faults in field oriented controlled induction machines | |
V Sri Ram Prasad et al. | Experimental modal analysis of induction machine stator end windings of driving end and non-driving end to predict the looseness | |
Galar et al. | Application of dynamic benchmarking of rotating machinery for e-maintenance | |
Zhang et al. | Detection of Ending Winding Wear Regulation Acting by Electromagnetic Force in Synchronous Generators under both SISC and SAGE Conditions | |
KR101472768B1 (en) | Method for checking of facility status with the number of vibrations of rotary machine | |
Dlamini et al. | An improved motor replacement strategy using non-intrusive motor efficiency estimation |