TW202333890A - Turning tool collapse detection system and method thereof - Google Patents
Turning tool collapse detection system and method thereof Download PDFInfo
- Publication number
- TW202333890A TW202333890A TW111106647A TW111106647A TW202333890A TW 202333890 A TW202333890 A TW 202333890A TW 111106647 A TW111106647 A TW 111106647A TW 111106647 A TW111106647 A TW 111106647A TW 202333890 A TW202333890 A TW 202333890A
- Authority
- TW
- Taiwan
- Prior art keywords
- quantization error
- minimum quantization
- warning
- error value
- turning
- Prior art date
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000013139 quantization Methods 0.000 claims abstract description 90
- 238000003801 milling Methods 0.000 claims abstract description 22
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- 238000001228 spectrum Methods 0.000 claims description 33
- 238000006243 chemical reaction Methods 0.000 claims description 26
- 150000001875 compounds Chemical class 0.000 claims description 13
- 210000002569 neuron Anatomy 0.000 claims description 10
- 238000013507 mapping Methods 0.000 claims description 9
- 238000005259 measurement Methods 0.000 claims description 6
- 239000003086 colorant Substances 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 8
- 238000013473 artificial intelligence Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000007274 generation of a signal involved in cell-cell signaling Effects 0.000 description 4
- 238000013481 data capture Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 229910000952 Be alloy Inorganic materials 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000010791 quenching Methods 0.000 description 1
- 230000000171 quenching effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000005496 tempering Methods 0.000 description 1
Landscapes
- Numerical Control (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
Description
本發明是關於一種檢知系統及其方法，特別是關於一種車削崩刀檢知系統及其方法。The present invention relates to a detection system and a method thereof, in particular to a turning tool chipping detection system and a method thereof.
車削加工為傳統之加工方法，車床操作人員通常以車削時的卷屑、電流特徵、聲音或是目視刀具之經驗來判斷刀具是否已磨耗。然而，當操作人員察覺時，通常刀具已損壞，容易造成被加工之工件損傷。為了避免工件損壞，操作人員通常會提早更換刀具，可降低工件之損壞率，但卻增加停機更換的時間及刀具費用。由此可知，目前市場上缺乏一種可改進刀具更換時機的準確率之車削崩刀檢知系統及其方法，故相關業者均在尋求其解決之道。Turning is a traditional processing method. Lathe operators usually judge whether the tool has been worn based on the chip curling, current characteristics, sound or visual experience of the tool during turning. However, when the operator notices it, the tool is usually damaged, which can easily cause damage to the workpiece being processed. In order to avoid damage to the workpiece, operators usually replace the tool early, which can reduce the damage rate of the workpiece, but increases downtime for replacement and tool costs. It can be seen from this that there is currently a lack of a turning tool chipping detection system and method on the market that can improve the accuracy of tool replacement timing, so relevant industries are looking for solutions.
因此，本發明之目的在於提供一種車削崩刀檢知系統及其方法，其運用人工智慧於車削加工中切削狀態之崩刀檢知，可較準確地預知刀具即將崩毀，進而即時停機以更換刀具，不但能方便操作人員使用，還能確保加工中的工件不會因刀具崩壞而損傷，故可解決習知技術之人工判斷標準不一所造成的問題。Therefore, the object of the present invention is to provide a turning tool collapse detection system and a method thereof, which use artificial intelligence to detect tool collapse in the cutting state during turning processing, and can more accurately predict that the tool is about to collapse, and then shut down the machine immediately for replacement. The tool is not only convenient for the operator to use, but also ensures that the workpiece being processed will not be damaged due to tool breakage. Therefore, it can solve the problem caused by the different manual judgment standards in the conventional technology.
依據本發明的結構態樣之一實施方式提供一種車削崩刀檢知系統，其包含車銑複合機、三軸加速規以及運算處理器。車銑複合機包含一刀具。三軸加速規設置於車銑複合機且用以量測刀具而得到第一時域振動訊號與第二時域振動訊號。運算處理器電性連接三軸加速規，運算處理器接收第一時域振動訊號與第二時域振動訊號並經配置以實施包含以下步驟之操作：前處理步驟、模型建立步驟、振動預測步驟及崩刀檢知步驟。前處理步驟係將第一時域振動訊號轉換為複數第一頻帶能量。模型建立步驟係依據自組織映射網絡演算法與最小量化誤差法運算此些第一頻帶能量以建立一預測模型，並求得最佳預警最小量化誤差閥值組。振動預測步驟係將第二時域振動訊號轉換為複數第二頻帶能量，然後將此些第二頻帶能量輸入至預測模型而得到一預測最小量化誤差值。崩刀檢知步驟係比對預測最小量化誤差值與最佳預警最小量化誤差閥值組而得到一比對結果，並依據比對結果檢知刀具是否損壞。According to one embodiment of the structural aspect of the present invention, a turning tool chipping detection system is provided, which includes a turning-milling compound machine, a three-axis accelerometer, and a computing processor. The turn-mill machine contains a tool. The three-axis accelerometer is installed on the turn-milling machine and used to measure the tool to obtain the first time domain vibration signal and the second time domain vibration signal. The computing processor is electrically connected to the three-axis accelerometer. The computing processor receives the first time domain vibration signal and the second time domain vibration signal and is configured to perform operations including the following steps: a pre-processing step, a model building step, and a vibration prediction step. And the steps for detecting tool collapse. The pre-processing step is to convert the first time domain vibration signal into complex first frequency band energy. The model establishment step is based on the self-organizing mapping network algorithm and the minimum quantization error method to calculate the first frequency band energy to establish a prediction model and obtain the optimal early warning minimum quantization error threshold set. The vibration prediction step is to convert the second time domain vibration signal into complex second frequency band energy, and then input these second frequency band energies into the prediction model to obtain a predicted minimum quantization error value. The tool collapse detection step is to compare the predicted minimum quantized error value with the optimal early warning minimum quantized error threshold set to obtain a comparison result, and detect whether the tool is damaged based on the comparison result.
藉此，本發明之車削崩刀檢知系統運用人工智慧於車削加工中切削狀態之刀具檢測，可較準確地預知刀具即將崩毀，進而即時停機以更換刀具，不但能方便操作人員使用，還能確保加工中的工件不會因刀具崩壞而損傷。In this way, the turning tool collapse detection system of the present invention uses artificial intelligence to detect the cutting status of the tool during turning processing, and can more accurately predict that the tool is about to collapse, and then stop the machine immediately to replace the tool. This not only facilitates the use of the operator, but also It can ensure that the workpiece being processed will not be damaged due to tool breakage.
前述實施方式之其他實施例如下：前述前處理步驟可包含第一轉換步驟與第二轉換步驟。第一轉換步驟係依據一傅立葉轉換將第一時域振動訊號轉換為一頻域振動訊號。第二轉換步驟係將頻域振動訊號分成複數區段頻譜訊號，並依據一方均根轉換將此些區段頻譜訊號轉換為此些第一頻帶能量。Other examples of the foregoing implementation are as follows: the foregoing preprocessing step may include a first conversion step and a second conversion step. The first conversion step is to convert the first time domain vibration signal into a frequency domain vibration signal based on a Fourier transform. The second conversion step is to divide the frequency domain vibration signal into complex segment spectrum signals, and convert these segment spectrum signals into the first frequency band energy according to a square root mean transformation.
前述實施方式之其他實施例如下：在前述第二轉換步驟中，此些區段頻譜訊號之數量可為13，此些區段頻譜訊號之至少一者之一頻譜範圍為1000 Hz，此些區段頻譜訊號具有複數特徵點，且此些特徵點之數量為39。此外，在模型建立步驟中，運算處理器調整自組織映射網絡演算法以找出一優勝神經元，然後依據優勝神經元與最小量化誤差法運算此些第一頻帶能量以建立預測模型，並求得最佳預警最小量化誤差閥值組。Other examples of the aforementioned implementation are as follows: in the aforementioned second conversion step, the number of these segment spectrum signals may be 13, and the spectrum range of at least one of these segment spectrum signals is 1000 Hz. The segment spectrum signal has a complex number of feature points, and the number of these feature points is 39. In addition, in the model building step, the computing processor adjusts the self-organizing mapping network algorithm to find a winning neuron, and then calculates the first frequency band energy according to the winning neuron and the minimum quantization error method to establish a prediction model, and obtains Obtain the best early warning minimum quantization error threshold group.
前述實施方式之其他實施例如下：前述車銑複合機可更包含警示燈與可程式化邏輯控制器。可程式化邏輯控制器電性連接運算處理器與警示燈，運算處理器依據比對結果決定是否產生一預警訊號，可程式化邏輯控制器依據預警訊號控制警示燈。最佳預警最小量化誤差閥值組包含第一預警閥值與第二預警閥值，第一預警閥值小於第二預警閥值。當比對結果為預測最小量化誤差值小於等於第一預警閥值時，運算處理器決定不產生預警訊號，警示燈亮綠燈。當比對結果為預測最小量化誤差值大於第一預警閥值且小於等於第二預警閥值時，運算處理器決定產生預警訊號並將預警訊號傳送至可程式化邏輯控制器，警示燈亮黃燈。當比對結果為預測最小量化誤差值大於第二預警閥值時，運算處理器決定產生預警訊號並將預警訊號傳送至可程式化邏輯控制器，警示燈亮紅燈且停止刀具作動。Other examples of the foregoing embodiments are as follows: the foregoing turning-milling compound machine may further include a warning light and a programmable logic controller. The programmable logic controller is electrically connected to the computing processor and the warning light. The computing processor determines whether to generate an early warning signal based on the comparison result, and the programmable logic controller controls the warning light based on the early warning signal. The optimal early warning minimum quantization error threshold group includes a first early warning threshold and a second early warning threshold, and the first early warning threshold is smaller than the second early warning threshold. When the comparison result is that the predicted minimum quantization error value is less than or equal to the first warning threshold, the computing processor decides not to generate a warning signal, and the warning light turns green. When the comparison result is that the predicted minimum quantization error value is greater than the first warning threshold and less than or equal to the second warning threshold, the computing processor decides to generate a warning signal and transmits the warning signal to the programmable logic controller, and the warning light turns yellow. . When the comparison result is that the predicted minimum quantization error value is greater than the second warning threshold, the computing processor decides to generate a warning signal and transmits the warning signal to the programmable logic controller. The warning light turns red and the tool stops.
前述實施方式之其他實施例如下：前述車削崩刀檢知系統可更包含一圖形使用者介面，其電性連接運算處理器並接收此些第二頻帶能量及預測最小量化誤差值，圖形使用者介面於第一區域顯示此些第二頻帶能量之總量，並於第二區域顯示預測最小量化誤差值。第二區域包含第一子區域、第二子區域及第三子區域，第一子區域、第二子區域及第三子區域的顏色分別呈綠色、黃色及紅色。當比對結果為預測最小量化誤差值小於等於第一預警閥值時，預測最小量化誤差值顯示於第一子區域。當比對結果為預測最小量化誤差值大於第一預警閥值且小於等於第二預警閥值時，預測最小量化誤差值顯示於第二子區域。當比對結果為預測最小量化誤差值大於第二預警閥值時，預測最小量化誤差值顯示於第三子區域。Other examples of the aforementioned implementation are as follows: the aforementioned turning tool chipping detection system may further include a graphical user interface that is electrically connected to the computing processor and receives the second frequency band energy and the predicted minimum quantization error value. The graphical user interface The interface displays the total amount of the second frequency band energy in the first area, and displays the predicted minimum quantization error value in the second area. The second area includes a first sub-area, a second sub-area and a third sub-area. The colors of the first sub-area, the second sub-area and the third sub-area are green, yellow and red respectively. When the comparison result is that the predicted minimum quantization error value is less than or equal to the first warning threshold, the predicted minimum quantization error value is displayed in the first sub-region. When the comparison result is that the predicted minimum quantization error value is greater than the first warning threshold and less than or equal to the second warning threshold, the predicted minimum quantization error value is displayed in the second sub-region. When the comparison result is that the predicted minimum quantization error value is greater than the second warning threshold, the predicted minimum quantization error value is displayed in the third sub-region.
依據本發明的方法態樣之一實施方式提供一種車削崩刀檢知方法，包含以下步驟：振動量測步驟、前處理步驟、模型建立步驟、振動預測步驟以及崩刀檢知步驟。振動量測步驟係驅動三軸加速規量測車銑複合機之刀具而得到第一時域振動訊號。前處理步驟係驅動運算處理器將第一時域振動訊號轉換為複數第一頻帶能量。模型建立步驟係驅動運算處理器依據自組織映射網絡演算法與最小量化誤差法運算此些第一頻帶能量以建立預測模型，並求得最佳預警最小量化誤差閥值組。振動預測步驟係驅動三軸加速規量測刀具而得到第二時域振動訊號，並驅動運算處理器將第二時域振動訊號轉換為複數第二頻帶能量，然後驅動運算處理器將此些第二頻帶能量輸入至預測模型而得到預測最小量化誤差值。崩刀檢知步驟係驅動運算處理器比對預測最小量化誤差值與最佳預警最小量化誤差閥值組而得到一比對結果，並依據比對結果檢知刀具是否損壞。According to one embodiment of the method aspect of the present invention, a turning tool chipping detection method is provided, which includes the following steps: a vibration measurement step, a preprocessing step, a model establishing step, a vibration prediction step, and a chipping detection step. The vibration measurement step is to drive a three-axis acceleration gauge to measure the tool of the turn-milling machine to obtain the first time domain vibration signal. The pre-processing step is to drive the computing processor to convert the first time domain vibration signal into complex first frequency band energy. The model building step drives the computing processor to calculate the first frequency band energy according to the self-organizing mapping network algorithm and the minimum quantization error method to establish a prediction model and obtain the optimal early warning minimum quantization error threshold set. The vibration prediction step is to drive the three-axis accelerometer to measure the tool to obtain the second time domain vibration signal, and drive the arithmetic processor to convert the second time domain vibration signal into complex second frequency band energy, and then drive the arithmetic processor to convert these second time domain vibration signals. The two-band energy is input to the prediction model to obtain the predicted minimum quantization error value. The tool collapse detection step drives the computing processor to compare the predicted minimum quantized error value with the optimal early warning minimum quantized error threshold set to obtain a comparison result, and detect whether the tool is damaged based on the comparison result.
藉此，本發明之車削崩刀檢知方法利用人工智慧於車削加工中切削狀態之刀具檢測，可較準確地預知刀具即將崩毀，進而即時停機以更換刀具，不但能方便操作人員使用，還能確保加工中的工件不會因刀具崩壞而損傷，故可解決習知技術之人工判斷標準不一所造成的問題。In this way, the turning tool collapse detection method of the present invention uses artificial intelligence to detect the cutting status of the tool in the turning process, and can more accurately predict that the tool is about to collapse, and then stop the machine immediately to replace the tool. This not only facilitates the use of the operator, but also It can ensure that the workpiece being processed will not be damaged due to tool breakage, so it can solve the problem caused by the different manual judgment standards of the conventional technology.
前述實施方式之其他實施例如下：前述前處理步驟可包含第一轉換步驟與第二轉換步驟。第一轉換步驟係依據傅立葉轉換將第一時域振動訊號轉換為頻域振動訊號。第二轉換步驟係將頻域振動訊號分成複數區段頻譜訊號，並依據方均根轉換將此些區段頻譜訊號轉換為此些第一頻帶能量。Other examples of the foregoing implementation are as follows: the foregoing preprocessing step may include a first conversion step and a second conversion step. The first conversion step is to convert the first time domain vibration signal into a frequency domain vibration signal based on Fourier transform. The second conversion step is to divide the frequency domain vibration signal into complex segment spectrum signals, and convert these segment spectrum signals into the first frequency band energy according to the root mean square transformation.
前述實施方式之其他實施例如下：在前述第二轉換步驟中，此些區段頻譜訊號之數量可為13，此些區段頻譜訊號之至少一者之頻譜範圍為1000 Hz，此些區段頻譜訊號具有複數特徵點，且此些特徵點之數量為39。在模型建立步驟中，運算處理器調整自組織映射網絡演算法以找出優勝神經元，然後依據優勝神經元與最小量化誤差法運算此些第一頻帶能量以建立預測模型，並求得最佳預警最小量化誤差閥值組。Other examples of the aforementioned implementation are as follows: in the aforementioned second conversion step, the number of these segment spectrum signals may be 13, and the spectrum range of at least one of these segment spectrum signals is 1000 Hz. The spectrum signal has a complex number of feature points, and the number of these feature points is 39. In the model building step, the computing processor adjusts the self-organizing mapping network algorithm to find the winning neuron, and then calculates these first frequency band energies based on the winning neuron and the minimum quantization error method to establish a prediction model and obtain the best Early warning minimum quantization error threshold group.
前述實施方式之其他實施例如下：前述車削崩刀檢知方法可更包含預警訊號產生步驟與警示步驟。預警訊號產生步驟係驅動運算處理器依據比對結果決定是否產生預警訊號。警示步驟係驅動車銑複合機之可程式化邏輯控制器依據預警訊號控制車銑複合機之警示燈。最佳預警最小量化誤差閥值組包含第一預警閥值與第二預警閥值，第一預警閥值小於第二預警閥值。當比對結果為預測最小量化誤差值小於等於第一預警閥值時，運算處理器決定不產生預警訊號，警示燈亮綠燈。當比對結果為預測最小量化誤差值大於第一預警閥值且小於等於第二預警閥值時，運算處理器決定產生預警訊號並將預警訊號傳送至可程式化邏輯控制器，警示燈亮黃燈。當比對結果為預測最小量化誤差值大於第二預警閥值時，運算處理器決定產生預警訊號並將預警訊號傳送至可程式化邏輯控制器，警示燈亮紅燈且停止刀具作動。Other examples of the aforementioned implementation are as follows: the aforementioned turning tool chipping detection method may further include an early warning signal generating step and a warning step. The early warning signal generating step drives the computing processor to decide whether to generate an early warning signal based on the comparison result. The warning step is to drive the programmable logic controller of the turn-mill compound machine to control the warning light of the turn-mill compound machine based on the early warning signal. The optimal early warning minimum quantization error threshold group includes a first early warning threshold and a second early warning threshold, and the first early warning threshold is smaller than the second early warning threshold. When the comparison result is that the predicted minimum quantization error value is less than or equal to the first warning threshold, the computing processor decides not to generate a warning signal, and the warning light turns green. When the comparison result is that the predicted minimum quantization error value is greater than the first warning threshold and less than or equal to the second warning threshold, the computing processor decides to generate a warning signal and transmits the warning signal to the programmable logic controller, and the warning light turns yellow. . When the comparison result is that the predicted minimum quantization error value is greater than the second warning threshold, the computing processor decides to generate a warning signal and transmits the warning signal to the programmable logic controller. The warning light turns red and the tool stops.
前述實施方式之其他實施例如下：前述車削崩刀檢知方法可更包含一介面顯示步驟，其係驅動圖形使用者介面於第一區域顯示此些第二頻帶能量之總量，並於第二區域顯示預測最小量化誤差值。第二區域包含第一子區域、第二子區域及第三子區域，第一子區域、第二子區域及第三子區域的顏色分別呈綠色、黃色及紅色。當比對結果為預測最小量化誤差值小於等於第一預警閥值時，預測最小量化誤差值顯示於第一子區域。當比對結果為預測最小量化誤差值大於第一預警閥值且小於等於第二預警閥值時，預測最小量化誤差值顯示於第二子區域。當比對結果為預測最小量化誤差值大於第二預警閥值時，預測最小量化誤差值顯示於第三子區域。Other examples of the aforementioned implementation are as follows: the aforementioned turning tool chipping detection method may further include an interface display step, which drives the graphical user interface to display the total amount of the second frequency band energy in the first area, and displays the total amount of the second frequency band energy in the second area. The area shows the predicted minimum quantization error value. The second area includes a first sub-area, a second sub-area and a third sub-area. The colors of the first sub-area, the second sub-area and the third sub-area are green, yellow and red respectively. When the comparison result is that the predicted minimum quantization error value is less than or equal to the first warning threshold, the predicted minimum quantization error value is displayed in the first sub-region. When the comparison result is that the predicted minimum quantization error value is greater than the first warning threshold and less than or equal to the second warning threshold, the predicted minimum quantization error value is displayed in the second sub-region. When the comparison result is that the predicted minimum quantization error value is greater than the second warning threshold, the predicted minimum quantization error value is displayed in the third sub-region.
以下將參照圖式說明本發明之複數個實施例。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發明。也就是說，在本發明部分實施例中，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；並且重複之元件將可能使用相同的編號表示之。Several embodiments of the present invention will be described below with reference to the drawings. For the sake of clarity, many practical details will be explained together in the following narrative. However, it will be understood that these practical details should not limit the invention. That is to say, in some embodiments of the present invention, these practical details are not necessary. In addition, in order to simplify the drawings, some commonly used structures and components will be illustrated in a simple schematic manner in the drawings; and repeated components may be represented by the same numbers.
此外，本文中當某一元件(或單元或模組等)「連接」於另一元件，可指所述元件是直接連接於另一元件，亦可指某一元件是間接連接於另一元件，意即，有其他元件介於所述元件及另一元件之間。而當有明示某一元件是「直接連接」於另一元件時，才表示沒有其他元件介於所述元件及另一元件之間。而第一、第二、第三等用語只是用來描述不同元件，而對元件本身並無限制，因此，第一元件亦可改稱為第二元件。且本文中之元件/單元/電路之組合非此領域中之一般周知、常規或習知之組合，不能以元件/單元/電路本身是否為習知，來判定其組合關係是否容易被技術領域中之通常知識者輕易完成。In addition, when a certain component (or unit or module, etc.) is "connected" to another component in this article, it may mean that the component is directly connected to the other component, or it may mean that one component is indirectly connected to the other component. , meaning that there are other elements between the said element and another element. When it is stated that an element is "directly connected" to another element, it means that no other elements are interposed between the element and the other element. Terms such as first, second, third, etc. are only used to describe different components without limiting the components themselves. Therefore, the first component can also be renamed the second component. Moreover, the combination of components/units/circuit in this article is not a combination that is generally known, conventional or customary in this field. Whether the component/unit/circuit itself is common knowledge cannot be used to determine whether its combination relationship is easily understood by those in the technical field. Usually it is easily accomplished by the knowledgeable.
請一併參閱第1圖與第2圖，其中第1圖係繪示本發明之第一實施例之車削崩刀檢知系統100的示意圖；以及第2圖係繪示本發明之第二實施例之車削崩刀檢知方法700的流程示意圖。車削崩刀檢知系統100經配置以實施車削崩刀檢知方法700且包含車銑複合機200、三軸加速規300、運算處理器400、圖形使用者介面500及數據擷取卡600。Please refer to Figures 1 and 2 together. Figure 1 is a schematic diagram of the turning tool chipping detection system 100 according to the first embodiment of the present invention; and Figure 2 is a schematic diagram of the second embodiment of the present invention. An example is a flow chart of the tool chipping detection method 700 in turning. The turning tool chipping detection system 100 is configured to implement the turning tool chipping detection method 700 and includes a turning-milling machine 200 , a three-axis accelerometer 300 , an arithmetic processor 400 , a graphical user interface 500 and a data capture card 600 .
車銑複合機200包含刀具210、可程式化邏輯控制器220(Programmable Logic Controller；PLC)及警示燈230。刀具210用以車銑工件。可程式化邏輯控制器220電性連接運算處理器400與警示燈230，可程式化邏輯控制器220結合警示燈230所產生之亮燈警示用以監控機台當前的加工狀態。三軸加速規300設置於車銑複合機200且電性連接數據擷取卡600，三軸加速規300用以量測刀具210並透過數據擷取卡600擷取而得到第一時域振動訊號與第二時域振動訊號。第一時域振動訊號與第二時域振動訊號之任一者包含X軸向訊號、Y軸向訊號及Z軸向訊號。運算處理器400透過數據擷取卡600電性連接三軸加速規300，並接收第一時域振動訊號與第二時域振動訊號，運算處理器400用以運算分析各種數據。圖形使用者介面500電性連接運算處理器400並用以將數據可視化呈現。藉此，本發明之車削崩刀檢知系統100運用人工智慧於車削加工中切削狀態之刀具210檢測，可較準確地預知刀具210即將崩毀，進而即時停機以更換刀具210，不但能方便操作人員使用，還能確保加工中的工件不會因刀具210崩壞而損傷，故可解決習知技術之人工判斷標準不一所造成的問題。The turning-milling machine 200 includes a tool 210 , a programmable logic controller 220 (Programmable Logic Controller; PLC), and a warning light 230 . The tool 210 is used for turning and milling the workpiece. The programmable logic controller 220 is electrically connected to the computing processor 400 and the warning light 230. The programmable logic controller 220 combines the light warning generated by the warning light 230 to monitor the current processing status of the machine. The three-axis accelerometer 300 is installed on the turning-milling compound machine 200 and is electrically connected to the data acquisition card 600. The three-axis accelerometer 300 is used to measure the tool 210 and acquire the first time domain vibration signal through the data acquisition card 600. and the second time domain vibration signal. Either one of the first time domain vibration signal and the second time domain vibration signal includes an X-axis signal, a Y-axis signal, and a Z-axis signal. The computing processor 400 is electrically connected to the three-axis accelerometer 300 through the data acquisition card 600, and receives the first time domain vibration signal and the second time domain vibration signal. The computing processor 400 is used to calculate and analyze various data. The graphical user interface 500 is electrically connected to the computing processor 400 and used to visually present data. Thereby, the turning tool collapse detection system 100 of the present invention uses artificial intelligence to detect the cutting status of the tool 210 during the turning process, and can more accurately predict that the tool 210 is about to collapse, and then stop the machine immediately to replace the tool 210, which not only facilitates operation When used by personnel, it can also ensure that the workpiece being processed will not be damaged due to the collapse of the tool 210, so it can solve the problem caused by the different manual judgment standards in the conventional technology.
在一實施例中，車銑複合機200可為數值控制(Computer Numerical Control；CNC)車銑複合機；運算處理器400可為工業電腦；工件可為調質前的合金鋼SCM440，但本發明不以此為限。In one embodiment, the turn-milling machine 200 can be a Computer Numerical Control (CNC) turning-milling machine; the computing processor 400 can be an industrial computer; and the workpiece can be alloy steel SCM440 before quenching and tempering. However, the present invention Not limited to this.
由第1圖與第2圖可知，車削崩刀檢知方法700包含振動量測步驟S02、前處理步驟S04、模型建立步驟S06、振動預測步驟S08及崩刀檢知步驟S10。振動量測步驟S02係驅動三軸加速規300量測車銑複合機200之刀具210而得到第一時域振動訊號。前處理步驟S04係驅動運算處理器400將第一時域振動訊號轉換為複數第一頻帶能量。模型建立步驟S06係驅動運算處理器400依據自組織映射網絡演算法(Self-Organizing Map；SOM)與最小量化誤差法(Minimum Quantization Error；MQE)運算此些第一頻帶能量以建立一預測模型，並求得最佳預警最小量化誤差閥值組。振動預測步驟S08係驅動三軸加速規300量測刀具210而得到第二時域振動訊號，並驅動運算處理器400將第二時域振動訊號轉換為複數第二頻帶能量，然後驅動運算處理器400將此些第二頻帶能量輸入至預測模型而得到預測最小量化誤差值。崩刀檢知步驟S10係驅動運算處理器400比對預測最小量化誤差值與最佳預警最小量化誤差閥值組而得到一比對結果，並依據比對結果檢知刀具210是否損壞。藉此，本發明之車削崩刀檢知方法700運用人工智慧(如SOM與MQE)於車削加工中切削狀態之刀具210檢測，可較準確地預知刀具210即將崩毀，進而即時停機以更換刀具210，不但能方便操作人員使用，還能確保加工中的工件不會因刀具210崩壞而損傷，故可解決習知技術之人工判斷標準不一所造成的問題。以下為詳細的實施例來說明上述各步驟之細節。As can be seen from Figures 1 and 2, the turning tool chipping detection method 700 includes a vibration measurement step S02, a pre-processing step S04, a model building step S06, a vibration prediction step S08, and a tool chipping detection step S10. The vibration measurement step S02 is to drive the three-axis accelerometer 300 to measure the tool 210 of the turn-milling compound machine 200 to obtain the first time domain vibration signal. The preprocessing step S04 is to drive the arithmetic processor 400 to convert the first time domain vibration signal into a complex first frequency band energy. The model building step S06 is to drive the computing processor 400 to calculate the first frequency band energy according to the self-organizing map network algorithm (Self-Organizing Map; SOM) and the minimum quantization error method (Minimum Quantization Error; MQE) to establish a prediction model. And obtain the best early warning minimum quantization error threshold group. The vibration prediction step S08 is to drive the three-axis accelerometer 300 to measure the tool 210 to obtain a second time domain vibration signal, and drive the arithmetic processor 400 to convert the second time domain vibration signal into a complex second frequency band energy, and then drive the arithmetic processor 400 400 Input these second frequency band energies to the prediction model to obtain the predicted minimum quantization error value. The tool collapse detection step S10 drives the arithmetic processor 400 to compare the predicted minimum quantized error value with the optimal early warning minimum quantized error threshold set to obtain a comparison result, and detect whether the tool 210 is damaged based on the comparison result. Thereby, the turning tool collapse detection method 700 of the present invention uses artificial intelligence (such as SOM and MQE) to detect the cutting status of the tool 210 during the turning process, and can more accurately predict that the tool 210 is about to collapse, and then stop the machine immediately to replace the tool. 210 is not only convenient for the operator to use, but also ensures that the workpiece being processed will not be damaged due to the collapse of the tool 210. Therefore, it can solve the problem caused by the different manual judgment standards in the conventional technology. The following are detailed examples to illustrate the details of each of the above steps.
請一併參閱第1圖至第5圖，其中第3圖係繪示第2圖之車削崩刀檢知方法700之前處理步驟S04的示意圖；第4圖係繪示第2圖之車削崩刀檢知方法700之介面顯示步驟S16顯示第二頻帶能量之三軸頻帶能量總量Acc-X、Acc-Y、Acc-Z與時間的關係圖；以及第5圖係繪示第2圖之車削崩刀檢知方法700之介面顯示步驟S16顯示預測最小量化誤差值與時間的關係圖。前處理步驟S04包含第一轉換步驟S042與第二轉換步驟S044。第一轉換步驟S042係依據一傅立葉轉換將第一時域振動訊號110轉換為一頻域振動訊號120。第二轉換步驟S044係將頻域振動訊號120分成複數區段頻譜訊號，並依據一方均根轉換(Root Mean Square；RMS)將此些區段頻譜訊號轉換為此些第一頻帶能量130。在第二轉換步驟S044中，此些區段頻譜訊號之數量為13，此些區段頻譜訊號之至少一者之一頻譜範圍為1000 Hz。此些區段頻譜訊號具有複數特徵點，且此些特徵點之數量為39。在模型建立步驟S06中，運算處理器400調整自組織映射網絡演算法以找出一優勝神經元(Best Matching Unit；BMU)，然後依據優勝神經元與最小量化誤差法運算此些第一頻帶能量130以建立預測模型，並求得最佳預警最小量化誤差閥值組。在一實施例中，第一時域振動訊號110與第二時域振動訊號均於每秒蒐集76800取樣點，第一時域振動訊號110之振幅(g)介於-15 g至15 g之間；傅立葉轉換可為快速傅立葉轉換(Fast Fourier Transform；FFT)；頻域振動訊號120的頻率(Hz)範圍可為0 Hz至12800 Hz，其強度(g-rms)介於0 g-rms至0.15 g-rms之間；此些區段頻譜訊號之前十二個區段之頻譜範圍均為1000 Hz，而最後一個區段(12000 Hz至12800 Hz)之頻譜範圍為800 Hz，但本發明不以此為限。第一頻帶能量130係用頻帶(Hz)與能量(mg-rms)表示。另外值得一提的是，本發明透過第二轉換步驟S044將特徵點之數量由原本之38400個降至39個，可達到降維的效果。Please refer to Figures 1 to 5 together. Figure 3 is a schematic diagram illustrating the processing step S04 before the turning tool chipping detection method 700 in Figure 2; Figure 4 is a schematic diagram showing the turning chipping detection method 700 in Figure 2. The interface display step S16 of the detection method 700 displays the relationship between the total amount of the three-axis frequency band energy Acc-X, Acc-Y, and Acc-Z of the second frequency band energy and time; and Figure 5 shows the turning of Figure 2 The interface display step S16 of the tool chip detection method 700 displays a graph of the predicted minimum quantization error value versus time. The preprocessing step S04 includes a first conversion step S042 and a second conversion step S044. The first conversion step S042 is to convert the first time domain vibration signal 110 into a frequency domain vibration signal 120 based on a Fourier transform. The second conversion step S044 is to divide the frequency domain vibration signal 120 into complex segment spectrum signals, and convert these segment spectrum signals into the first frequency band energies 130 according to Root Mean Square (RMS) transformation. In the second conversion step S044, the number of the segment spectrum signals is 13, and the spectrum range of at least one of the segment spectrum signals is 1000 Hz. These segment spectrum signals have a plurality of feature points, and the number of these feature points is 39. In the model building step S06, the computing processor 400 adjusts the self-organizing mapping network algorithm to find a winning neuron (Best Matching Unit; BMU), and then calculates the first frequency band energy according to the winning neuron and the minimum quantization error method. 130 to establish a prediction model and obtain the best early warning minimum quantization error threshold group. In one embodiment, the first time domain vibration signal 110 and the second time domain vibration signal are both collected at 76800 sampling points per second, and the amplitude (g) of the first time domain vibration signal 110 is between -15 g and 15 g. time; the Fourier transform can be a Fast Fourier Transform (FFT); the frequency (Hz) range of the frequency domain vibration signal 120 can be from 0 Hz to 12800 Hz, and its intensity (g-rms) ranges from 0 g-rms to Between 0.15 g-rms; the spectrum range of the first twelve sections of these section spectrum signals are all 1000 Hz, and the spectrum range of the last section (12000 Hz to 12800 Hz) is 800 Hz, but the present invention does not This is the limit. The first frequency band energy 130 is expressed in terms of frequency band (Hz) and energy (mg-rms). It is also worth mentioning that the present invention reduces the number of feature points from the original 38,400 to 39 through the second conversion step S044, thereby achieving a dimensionality reduction effect.
由第2圖可知，車削崩刀檢知方法700更包含預警訊號產生步驟S12、警示步驟S14及介面顯示步驟S16。其中預警訊號產生步驟S12係驅動運算處理器400依據比對結果決定是否產生一預警訊號。警示步驟S14係驅動車銑複合機200之可程式化邏輯控制器220依據預警訊號控制車銑複合機200之警示燈230。最佳預警最小量化誤差閥值組包含第一預警閥值MQEV1與第二預警閥值MQEV2，第一預警閥值MQEV1小於第二預警閥值MQEV2。當比對結果為預測最小量化誤差值小於等於第一預警閥值MQEV1時，運算處理器400決定不產生預警訊號，警示燈230亮綠燈。當比對結果為預測最小量化誤差值大於第一預警閥值MQEV1且小於等於第二預警閥值MQEV2時，運算處理器400決定產生預警訊號並將預警訊號傳送至可程式化邏輯控制器220，警示燈230亮黃燈。當比對結果為預測最小量化誤差值大於第二預警閥值MQEV2時，運算處理器400決定產生預警訊號並將預警訊號傳送至可程式化邏輯控制器220，警示燈230亮紅燈且停止刀具210作動。再者，介面顯示步驟S16係驅動圖形使用者介面500於第一區域510顯示此些第二頻帶能量於三軸各自的頻帶能量總量Acc-X、Acc-Y、Acc-Z，並於第二區域520顯示預測最小量化誤差值。「Acc-X」、「Acc-Y」、「Acc-Z」分別代表X軸頻帶能量總量、Y軸頻帶能量總量、Z軸頻帶能量總量。第二區域520包含第一子區域522、第二子區域524及第三子區域526，第一子區域522、第二子區域524及第三子區域526的顏色分別呈綠色、黃色及紅色，且分別代表正常(Good)、預警(Worn)及停車(Bad)。當比對結果為預測最小量化誤差值小於等於第一預警閥值MQEV1時，預測最小量化誤差值顯示於第一子區域522；當比對結果為預測最小量化誤差值大於第一預警閥值MQEV1且小於等於第二預警閥值MQEV2時，預測最小量化誤差值顯示於第二子區域524；當比對結果為預測最小量化誤差值大於第二預警閥值MQEV2時，預測最小量化誤差值顯示於第三子區域526。藉此，本發明之車削崩刀檢知方法700利用預警訊號產生步驟S12、警示步驟S14及介面顯示步驟S16方便使用者透過將數據可視化呈現來監控機台當前加工狀態之預測最小量化誤差值，既可確保刀具210狀態可控，亦可確保三軸加速規300異常(損壞)時能即時被發現而不影響工件品質。As can be seen from Figure 2, the turning tool chipping detection method 700 further includes an early warning signal generation step S12, a warning step S14 and an interface display step S16. The early warning signal generating step S12 drives the arithmetic processor 400 to determine whether to generate an early warning signal based on the comparison result. The warning step S14 is to drive the programmable logic controller 220 of the turn-mill compound machine 200 to control the warning light 230 of the turn-mill compound machine 200 based on the early warning signal. The optimal early warning minimum quantization error threshold group includes a first early warning threshold MQEV1 and a second early warning threshold MQEV2, and the first early warning threshold MQEV1 is smaller than the second early warning threshold MQEV2. When the comparison result is that the predicted minimum quantization error value is less than or equal to the first warning threshold MQEV1, the computing processor 400 decides not to generate a warning signal, and the warning light 230 turns green. When the comparison result is that the predicted minimum quantization error value is greater than the first warning threshold MQEV1 and less than or equal to the second warning threshold MQEV2, the operation processor 400 decides to generate a warning signal and transmits the warning signal to the programmable logic controller 220, Warning light 230 lights up yellow. When the comparison result is that the predicted minimum quantization error value is greater than the second warning threshold MQEV2, the computing processor 400 decides to generate a warning signal and transmits the warning signal to the programmable logic controller 220. The warning light 230 lights up in red and stops the tool. 210 action. Furthermore, the interface display step S16 drives the graphical user interface 500 to display the total amount of the second frequency band energy in the three axes of the respective frequency band energy Acc-X, Acc-Y, and Acc-Z in the first area 510, and in the third The second area 520 displays the predicted minimum quantization error value. "Acc-X", "Acc-Y", and "Acc-Z" respectively represent the total amount of X-axis frequency band energy, the total amount of Y-axis frequency band energy, and the total amount of Z-axis frequency band energy. The second area 520 includes a first sub-area 522, a second sub-area 524, and a third sub-area 526. The colors of the first sub-area 522, the second sub-area 524, and the third sub-area 526 are green, yellow, and red respectively. And respectively represent normal (Good), warning (Worn) and parking (Bad). When the comparison result is that the predicted minimum quantization error value is less than or equal to the first warning threshold MQEV1, the predicted minimum quantization error value is displayed in the first sub-area 522; when the comparison result is that the predicted minimum quantization error value is greater than the first warning threshold MQEV1 and is less than or equal to the second early warning threshold MQEV2, the predicted minimum quantization error value is displayed in the second sub-area 524; when the comparison result is that the predicted minimum quantization error value is greater than the second early warning threshold MQEV2, the predicted minimum quantization error value is displayed in Third sub-area 526. Thus, the turning tool chipping detection method 700 of the present invention utilizes the early warning signal generation step S12, the warning step S14, and the interface display step S16 to facilitate the user to monitor the predicted minimum quantified error value of the current processing status of the machine by visually presenting the data. It can not only ensure that the status of the tool 210 is controllable, but also ensure that the abnormality (damage) of the three-axis accelerometer 300 can be detected immediately without affecting the quality of the workpiece.
在其他實施例中，運算處理器400可電性連接網路卡，用以將數據傳輸至網路或雲端，進而實現物聯網或大數據分析。In other embodiments, the computing processor 400 can be electrically connected to a network card to transmit data to the network or cloud, thereby realizing the Internet of Things or big data analysis.
由上述實施方式可知，本發明具有下列優點：其一，運用人工智慧於車削加工中切削狀態之刀具檢測，可較準確地預知刀具即將崩毀，進而即時停機以更換刀具，不但能方便操作人員使用，還能確保加工中的工件不會因刀具崩壞而損傷，故可解決習知技術之人工判斷標準不一所造成的問題。其二，透過第二轉換步驟可將特徵點之數量由原本之38400個降至39個，進而達到降維的效果。其三，利用警示燈、可程式化邏輯控制器、圖形使用者介面、預警訊號產生步驟、警示步驟及介面顯示步驟方便使用者透過將數據可視化呈現來監控機台當前加工狀態之預測最小量化誤差值，既可確保刀具狀態可控，亦可確保三軸加速規異常(損壞)時能即時被發現而不影響工件品質。It can be seen from the above embodiments that the present invention has the following advantages: First, the use of artificial intelligence to detect the cutting status of the tool in turning processing can more accurately predict that the tool is about to collapse, and then stop the machine immediately to replace the tool, which not only facilitates the operator The use can also ensure that the workpiece being processed will not be damaged due to tool breakage, so it can solve the problems caused by the different manual judgment standards of the conventional technology. Secondly, through the second conversion step, the number of feature points can be reduced from the original 38,400 to 39, thereby achieving the effect of dimensionality reduction. Third, the use of warning lights, programmable logic controllers, graphical user interfaces, early warning signal generation steps, warning steps and interface display steps facilitates users to monitor the predicted minimum quantified error of the current processing status of the machine through visual presentation of data. value, which not only ensures that the tool status is controllable, but also ensures that abnormality (damage) of the three-axis accelerometer can be detected immediately without affecting the quality of the workpiece.
雖然本發明已以實施方式揭露如上，然其並非用以限定本發明，任何熟習此技藝者，在不脫離本發明之精神和範圍內，當可作各種之更動與潤飾，因此本發明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 invention has been disclosed in the above embodiments, it is not intended to limit the present invention. Anyone skilled in the art can make various modifications and modifications without departing from the spirit and scope of the present invention. Therefore, the protection of the present invention is The scope shall be determined by the appended patent application scope.
100:車削崩刀檢知系統 110:第一時域振動訊號 120:頻域振動訊號 130:第一頻帶能量 200:車銑複合機 210:刀具 220:可程式化邏輯控制器 230:警示燈 300:三軸加速規 400:運算處理器 500:圖形使用者介面 510:第一區域 520:第二區域 522:第一子區域 524:第二子區域 526:第三子區域 600:數據擷取卡 700:車削崩刀檢知方法 S02:振動量測步驟 S04:前處理步驟 S042:第一轉換步驟 S044:第二轉換步驟 S06:模型建立步驟 S08:振動預測步驟 S10:崩刀檢知步驟 S12:預警訊號產生步驟 S14:警示步驟 S16:介面顯示步驟 Acc-X,Acc-Y,Acc-Z:頻帶能量總量 FFT:快速傅立葉轉換 MQEV1:第一預警閥值 MQEV2:第二預警閥值 RMS:方均根轉換 100: Turning tool chipping detection system 110: First time domain vibration signal 120: Frequency domain vibration signal 130: First frequency band energy 200: Turning and milling compound machine 210: Knives 220: Programmable Logic Controller 230:Warning light 300:Three-axis accelerometer 400:Arithmetic processor 500: Graphical user interface 510:First area 520:Second area 522: First sub-area 524: Second sub-area 526: The third sub-area 600:Data capture card 700: Method for detecting chipping in turning S02: Vibration measurement steps S04: Pre-processing steps S042: First conversion step S044: Second conversion step S06: Model establishment steps S08: Vibration prediction step S10: Tool collapse detection steps S12: Early warning signal generation steps S14: Warning Steps S16: Interface display steps Acc-X,Acc-Y,Acc-Z: Total energy of frequency band FFT: Fast Fourier Transform MQEV1: first warning threshold MQEV2: Second warning threshold RMS: root mean square conversion
第1圖係繪示本發明之第一實施例之車削崩刀檢知系統的示意圖； 第2圖係繪示本發明之第二實施例之車削崩刀檢知方法的流程示意圖； 第3圖係繪示第2圖之車削崩刀檢知方法之前處理步驟的示意圖； 第4圖係繪示第2圖之車削崩刀檢知方法之介面顯示步驟顯示第二頻帶能量之三軸頻帶能量總量與時間的關係圖；以及 第5圖係繪示第2圖之車削崩刀檢知方法之介面顯示步驟顯示預測最小量化誤差值與時間的關係圖。 Figure 1 is a schematic diagram of a turning tool chipping detection system according to the first embodiment of the present invention; Figure 2 is a schematic flow chart illustrating a method for detecting chipping in turning according to the second embodiment of the present invention; Figure 3 is a schematic diagram showing the processing steps before the turning tool chipping detection method in Figure 2; Figure 4 is a diagram illustrating the relationship between the total amount of three-axis frequency band energy and time of the second frequency band energy in the interface display steps of the turning tool chip detection method in Figure 2; and Figure 5 is a diagram illustrating the relationship between the predicted minimum quantization error value and time in the interface display steps of the turning tool chipping detection method in Figure 2.
100:車削崩刀檢知系統 100: Turning tool chipping detection system
200:車銑複合機 200: Turning and milling machine
210:刀具 210: Knives
220:可程式化邏輯控制器 220: Programmable Logic Controller
230:警示燈 230:Warning light
300:三軸加速規 300:Three-axis accelerometer
400:運算處理器 400:Arithmetic processor
500:圖形使用者介面 500: Graphical user interface
600:數據擷取卡 600:Data capture card
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW111106647A TWI794027B (en) | 2022-02-23 | 2022-02-23 | Turning tool collapse detection system and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW111106647A TWI794027B (en) | 2022-02-23 | 2022-02-23 | Turning tool collapse detection system and method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| TWI794027B TWI794027B (en) | 2023-02-21 |
| TW202333890A true TW202333890A (en) | 2023-09-01 |
Family
ID=86689440
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| TW111106647A TWI794027B (en) | 2022-02-23 | 2022-02-23 | Turning tool collapse detection system and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| TW (1) | TWI794027B (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201334911A (en) * | 2012-02-24 | 2013-09-01 | Optica Tech Co Ltd | Method and apparatus for detecting the break of the cutter of the machine tool automatically |
| TWI637169B (en) * | 2016-08-18 | 2018-10-01 | 王智中 | Tool status detection system and method thereof |
| TWI649152B (en) * | 2017-11-28 | 2019-02-01 | 先馳精密儀器股份有限公司 | Tool state detection system and method |
| SE543978C2 (en) * | 2018-02-21 | 2021-10-12 | Lantern Holdings Llc | High-precision abnormal motion detection for power tools |
| CN113305644A (en) * | 2021-05-20 | 2021-08-27 | 华中科技大学 | Cutter state monitoring and early warning method and system based on part measurement data |
| CN215547228U (en) * | 2021-06-04 | 2022-01-18 | 四川旭博精密科技有限公司 | CNC numerically controlled fraise machine cutter detecting system |
-
2022
- 2022-02-23 TW TW111106647A patent/TWI794027B/en active
Also Published As
| Publication number | Publication date |
|---|---|
| TWI794027B (en) | 2023-02-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Khorasani et al. | Development of a dynamic surface roughness monitoring system based on artificial neural networks (ANN) in milling operation | |
| JP6450738B2 (en) | Machine learning device, CNC device, and machine learning method for detecting sign of occurrence of tool vibration in machine tool | |
| CN109766334B (en) | Processing method and system for online monitoring abnormal data of power equipment | |
| US20150371134A1 (en) | Predicting circuit reliability and yield using neural networks | |
| JP6752866B2 (en) | Cutting tool condition inspection system and method | |
| Guh | Simultaneous process mean and variance monitoring using artificial neural networks | |
| WO2016004749A1 (en) | Method for recognizing tool abrasion degree of large numerical control milling machine | |
| TWM575368U (en) | Cloud computing system for intelligent machine tools | |
| JP5062496B2 (en) | Operating state analysis system and operating state analysis method | |
| CN111390647A (en) | Tool life prediction system and method | |
| JP2016200451A (en) | Signal processing method, signal processing device, and cutting work abnormality detection device | |
| US11977372B2 (en) | Integrity index detecting method for device by means of control output signal | |
| CN114986258A (en) | Cutter state monitoring method and device, computer equipment and system | |
| CN108363822A (en) | Cutter rigid predictions are used to inhibit the device and method of cutting-vibration | |
| TW202333890A (en) | Turning tool collapse detection system and method thereof | |
| CN114055249B (en) | Bore hole surface roughness monitoring method and system and storage medium | |
| TWM627935U (en) | Turning tool collapse detection system | |
| TWI676873B (en) | Tools monitoring system and monitoring method thereof | |
| CN112114578B (en) | Steady method for multi-process multivariable process online monitoring and abnormal source diagnosis | |
| Chen et al. | A multiple-regression model for monitoring tool wear with a dynamometer in milling operations | |
| JP7368189B2 (en) | Analysis equipment | |
| JPH06274778A (en) | Plant monitoring/diagnosing device and its fault sign detecting method | |
| Jiao et al. | Fault characteristics analysis of industrial robot based on fault tree | |
| JP2021076597A (en) | Detecting rotor anomalies by determining vibration trends during transient speed operation | |
| CN112968525A (en) | Converter valve submodule on-site operation and maintenance system and method |