TWI797716B - Method and system for detecting abnormal temperature rise - Google Patents
Method and system for detecting abnormal temperature rise Download PDFInfo
- Publication number
- TWI797716B TWI797716B TW110129917A TW110129917A TWI797716B TW I797716 B TWI797716 B TW I797716B TW 110129917 A TW110129917 A TW 110129917A TW 110129917 A TW110129917 A TW 110129917A TW I797716 B TWI797716 B TW I797716B
- Authority
- TW
- Taiwan
- Prior art keywords
- temperature
- fuzzy
- descriptions
- membership function
- value
- Prior art date
Links
Images
Landscapes
- Radiation Pyrometers (AREA)
- Protection Of Generators And Motors (AREA)
Abstract
Description
本揭露是有關於在煉鋼廠內的溫度檢測方法與系統。 The present disclosure relates to a temperature detection method and system in a steelmaking plant.
當要使用溫度感測器來判斷裝置或環境是否有異常升溫的狀況時,一種做法是判斷溫度是否超過一個臨界值一段時間,如果是的話就發出警告。但這樣的操作方式容易受到外部物件或雜訊的影響而誤判,例如在偵測範圍內出現一個高溫的物體,此物體並不是裝置異常導致所以會逐漸降溫,但依照上述的方式可能依然會發出警告。因此如何提出一種更適當的溫度檢測方法,為此領域技術人員所關心的議題。 When using a temperature sensor to determine whether there is an abnormal temperature rise in the device or the environment, one approach is to determine whether the temperature exceeds a critical value for a period of time, and if so, issue a warning. However, this method of operation is easily misjudged by the influence of external objects or noise. For example, a high-temperature object appears within the detection range. This object is not caused by an abnormal device, so it will gradually cool down. However, according to the above method, it may still send out warn. Therefore, how to propose a more appropriate temperature detection method is a topic concerned by those skilled in the art.
本揭露的實施例提出一種異常升溫的檢測方法,適用於電腦系統,此檢測方法包括:透過溫度感測器取得接鋼桶的溫度值並計算出溫度變化量;將溫度值輸入至第一 歸屬函數以取得多個第一模糊量值,並將溫度變化量輸入至第二歸屬函數以取得多個第二模糊量值,其中第一歸屬函數包含多個溫度描述,第一模糊量值屬於溫度描述,第二歸屬函數包含多個溫度變化描述,第二模糊量值屬於溫度變化描述;根據第一模糊量值所屬的溫度描述以及第二模糊量值所屬的溫度變化描述透過一模糊規則表進行模糊推論以得到異常狀態描述,此異常狀態描述屬於第三歸屬函數;根據第一模糊量值、第二模糊量值、異常狀態描述以及第三歸屬函數進行解模糊化以計算出異常分數;以及當異常分數大於一臨界值時,發出警告訊息。 The embodiment of this disclosure proposes a detection method for abnormal temperature rise, which is suitable for computer systems. The detection method includes: obtaining the temperature value of the steel drum through the temperature sensor and calculating the temperature change; inputting the temperature value into the first membership function to obtain a plurality of first fuzzy magnitudes, and input the temperature variation to a second membership function to obtain a plurality of second fuzzy magnitudes, wherein the first membership function contains a plurality of temperature descriptions, and the first fuzzy magnitude belongs to Temperature description, the second belonging function includes multiple temperature change descriptions, the second fuzzy value belongs to the temperature change description; according to the temperature description to which the first fuzzy value belongs and the temperature change description to which the second fuzzy value belongs, through a fuzzy rule table performing fuzzy inference to obtain an abnormal state description, which belongs to a third membership function; performing defuzzification according to the first fuzzy magnitude, the second fuzzy magnitude, the abnormal state description, and the third membership function to calculate an abnormality score; And when the abnormal score is greater than a critical value, a warning message is issued.
在一些實施例中,溫度描述的數量為3,溫度變化描述的數量為5,第一歸屬函數與第二歸屬函數是由多個三角形函數所組成。 In some embodiments, the number of temperature descriptions is 3, the number of temperature change descriptions is 5, and the first membership function and the second membership function are composed of a plurality of triangular functions.
在一些實施例中,異常狀態描述的數量為7,第三歸屬函數是由多個脈衝函數所組成。 In some embodiments, the number of abnormal state descriptions is 7, and the third membership function is composed of multiple impulse functions.
在一些實施例中,上述的解模糊化是根據離散式重心計算法所執行。 In some embodiments, the above-mentioned defuzzification is performed according to a discrete centroid calculation method.
在一些實施例中,上述的溫度感測器為熱像儀。 In some embodiments, the aforementioned temperature sensor is a thermal imager.
以另一個角度來說,本揭露提出一種檢測系統,包括接鋼桶、溫度感測器以及電腦系統。接鋼桶用以容納鋼液。溫度感測器用以取得關於接鋼桶的溫度值。電腦系統通訊連接至溫度感測器,用以接收來自溫度感測器的溫度值並計算出溫度變化量。電腦系統將溫度值輸入至第一歸屬函數以取得第一模糊量值,並將溫度變化量輸入至第二 歸屬函數以取得第二模糊量值。第一歸屬函數包含多個溫度描述,第一模糊量值屬於溫度描述。第二歸屬函數包含多個溫度變化描述,第二模糊量值屬於溫度變化描述。電腦系統還用以根據第一模糊量值所屬的溫度描述以及第二模糊量值所屬的溫度變化描述透過一模糊規則表進行模糊推論以得到異常狀態描述,此異常狀態描述屬於第三歸屬函數。電腦系統還用以根據第一模糊量值、第二模糊量值、異常狀態描述以及第三歸屬函數進行解模糊化以計算出異常分數。當異常分數大於一臨界值時,電腦系統用以發出警告訊息。 From another point of view, the present disclosure proposes a detection system including a steel drum, a temperature sensor and a computer system. The steel drum is used to hold the molten steel. The temperature sensor is used to obtain the temperature value of the steel drum. The computer system is communicatively connected to the temperature sensor for receiving the temperature value from the temperature sensor and calculating the temperature variation. The computer system inputs the temperature value into the first membership function to obtain the first fuzzy value, and inputs the temperature change into the second membership function to obtain the second fuzzy magnitude. The first membership function contains a plurality of temperature descriptions, and the first fuzzy magnitude belongs to the temperature descriptions. The second membership function includes a plurality of temperature change descriptions, and the second fuzzy magnitude belongs to the temperature change descriptions. The computer system is also used to perform fuzzy inference through a fuzzy rule table according to the temperature description to which the first fuzzy magnitude belongs and the temperature change description to which the second fuzzy magnitude belongs to obtain the abnormal state description, and the abnormal state description belongs to the third membership function. The computer system is also used to perform defuzzification according to the first fuzzy value, the second fuzzy value, the abnormal state description and the third belonging function to calculate the abnormal score. When the abnormal score is greater than a critical value, the computer system is used to issue a warning message.
100:檢測系統 100: Detection system
110:接鋼桶 110: Connect steel drum
120:溫度感測器 120: temperature sensor
130:電腦系統 130: Computer system
501~505:步驟 501~505: steps
為讓本發明的上述特徵和優點能更明顯易懂,下文特舉實施例,並配合所附圖式作詳細說明如下。 In order to make the above-mentioned features and advantages of the present invention more comprehensible, the following specific embodiments are described in detail together with the accompanying drawings.
圖1是根據一實施例繪示檢測系統的示意圖。 FIG. 1 is a schematic diagram illustrating a detection system according to an embodiment.
圖2是根據一實施例繪示溫度值的歸屬函數。 FIG. 2 is a diagram illustrating a membership function of temperature values according to an embodiment.
圖3是根據一實施例繪示溫度變化量的歸屬函數。 FIG. 3 is a graph illustrating a membership function of temperature variation according to an embodiment.
圖4是根據一實施例繪示狀態值的歸屬函數。 FIG. 4 is a diagram illustrating membership functions of state values according to an embodiment.
圖5是根據一實施例繪示異常升溫的檢測方法的流程圖。 FIG. 5 is a flowchart illustrating a method for detecting abnormal temperature rise according to an embodiment.
關於本文中所使用之「第一」、「第二」等,並非特別指次序或順位的意思,其僅為了區別以相同技術用語描述的元件或操作。 The terms "first", "second" and the like used herein do not specifically refer to a sequence or sequence, but are only used to distinguish elements or operations described with the same technical terms.
圖1是根據一實施例繪示檢測系統的示意圖。請參照圖1,檢測系統100包括接鋼桶110、溫度感測器120與電腦系統130。接鋼桶110是設置在煉鋼廠內,例如用以接收來自於轉爐的鋼液。溫度感測器120例如是熱像儀或是紅外線溫度感測器,用以感測接鋼桶110的溫度值。電腦系統130可以是個人電腦、伺服器、中央控制台或任意有計算能力的電子裝置。電腦系統130可以透過任意有線或無線的通訊手段來通訊連接至溫度感測器120並取得關於接鋼桶110的溫度值。當接鋼桶110上有破損導致鋼液漏出時溫度會急速上升,電腦系統130會執行一個檢測方法來判斷接鋼桶110的溫度是否異常。在此會將接鋼桶110劃分為多個區域,在此所提到的溫度值可以是關於其中任何一個區域。特別的是,在此是採用模糊狀態描述法(Fuzzy status description)來判斷溫度是否異常。
FIG. 1 is a schematic diagram illustrating a detection system according to an embodiment. Please refer to FIG. 1 , the
首先,電腦系統130會取得接鋼桶110的溫度值,並且計算出溫度變化量(將目前的溫度值減去之前感測的溫度值)。接著,對於溫度值以及溫度變化量分別設計兩個歸屬函數(membership function)。圖2是根據一實施例繪示溫度值的歸屬函數。請參照圖2,溫度的歸屬函數包含了3個溫度描述,其中“Z”表示“Zero”,“PS”表示“Positive Small”,而“PB”表示“Positive Big”。在此是用三角形函數來組成歸屬函數,溫度描述“PB”的峰值發生在溫度值為20時,溫度描述“PS”的峰值發生在溫度值為10時,溫度描述“Z”的峰值發生在溫度值為0時,也
就是說溫度值越高越有可能是異常。在其他實施例中也可以用多項式函數、指數函數等各類型的函數來形成歸屬函數,本揭露並不在此限。圖2的橫軸為溫度值,縱軸為歸屬函數的輸出,值得注意的是圖2的溫度值已經經過正規化或是量化,因此並不代表實際上的溫度(並不代表攝氏或華氏)。當把溫度值輸入至此歸屬函數時,可以得到每個溫度描述的模糊量值,舉例來說,當溫度為8時,溫度描述“Z”所對應的模糊量值為0.2,溫度描述“PS”所對應的模糊量值為0.8,而溫度描述“PB”所對應的模糊量值為0。
Firstly, the
圖3是根據一實施例繪示溫度變化量的歸屬函數。請參照圖3,溫度變化量的歸屬函數包含了5個溫度變化描述,其中“NB”表示“Negative Big”,“NS”表示“Negative Small”,其他描述則如同溫度描述,在此不贅述。圖3是用三角形函數來組成歸屬函數,溫度變化描述“NB”的峰值發生在溫度變化量為-20時,溫度描述“NS”的峰值發生在溫度變化量為-10時,溫度變化描述“Z”的峰值發生在溫度變化量為0時,溫度變化描述“PS”的峰值發生在溫度變化量為10時,溫度變化描述“PB”的峰值發生在溫度變化量為20時,也就是說溫度變化量越大越有可能是異常。同樣的,在其他實施例中也可以多項式函數、指數函數或各類型的函數來組成歸屬函數,本揭露並不在此限。類似於圖2,在此溫度變化量已經經過了正規化或是量化,因此並不是攝氏或華氏的差。當把溫度變化量輸入至此歸屬函數時,可以得到每個溫度變化描述的模糊量 值,舉例來說,當溫度變化量為17時,溫度變化描述“NB”所對應的模糊量值為0,溫度變化描述“NS”所對應的模糊量值為0,溫度變化描述“Z”所對應的模糊量值為0,溫度變化描述“PS”所對應的模糊量值為0.3,而溫度變化描述“PB”所對應的模糊量值為0.7。 FIG. 3 is a graph illustrating a membership function of temperature variation according to an embodiment. Please refer to Figure 3, the attribute function of temperature change includes 5 temperature change descriptions, among which "NB" means "Negative Big", "NS" means "Negative Small", and other descriptions are the same as temperature descriptions, which will not be repeated here. Figure 3 uses a triangular function to form the membership function. The peak of the temperature change description "NB" occurs when the temperature change is -20, the peak value of the temperature description "NS" occurs when the temperature change is -10, and the temperature change description " The peak of Z" occurs when the temperature change is 0, the peak of the temperature change description "PS" occurs when the temperature change is 10, and the peak of the temperature change description "PB" occurs when the temperature change is 20, that is to say The larger the amount of temperature change, the more likely it is abnormal. Likewise, in other embodiments, polynomial functions, exponential functions, or various types of functions may also be used to form the membership function, and the present disclosure is not limited thereto. Similar to Figure 2, here the temperature change has been normalized or quantized, so it is not a difference in Celsius or Fahrenheit. When the temperature change is input to this membership function, the fuzzy quantity described by each temperature change can be obtained Value, for example, when the temperature change is 17, the fuzzy value corresponding to the temperature change description "NB" is 0, the fuzzy value corresponding to the temperature change description "NS" is 0, and the temperature change description "Z" The corresponding fuzzy value is 0, the temperature change description "PS" corresponds to a fuzzy value of 0.3, and the temperature change description "PB" corresponds to a fuzzy value of 0.7.
接下來,根據非零的模糊量值所對應的溫度描述以及溫度變化描述可透過一模糊規則表進行模糊推論,此模糊規則表如以下表1。 Next, according to the temperature description and the temperature change description corresponding to the non-zero fuzzy value, a fuzzy inference can be performed through a fuzzy rule table. The fuzzy rule table is shown in Table 1 below.
在表1中,第2至第4行的欄位(T)表示溫度描述,而第2至第6列的欄位(△T)表示溫度變化描述,根據表1可以決定要輸出哪一個異常狀態描述,在此共有7個異常狀態描述,分別是“NB”、“NS2”、“NS1”、“Z”、“PS1”、“PS2”、“PB”。舉例來說,當溫度描述為第二行的“Z”且溫度變化描述為第五列的“PS”,則輸出的異常狀態描述為第二行第五列的“PS1”,以此類推。在上述例子中,溫度描述“Z”、“PS”所對應的模糊量值不為0,另外溫度變 化描述“PS”、“PB”所對應的模糊量值不為0,因此共會輸出2個異常狀態描述,分別是“PS1”以及“PS2”,這兩個異常狀態描述都會輸出2次,以下稱4次推論。 In Table 1, the column (T) of the 2nd to 4th row indicates the temperature description, and the column (△T) of the 2nd to 6th column indicates the description of the temperature change. According to Table 1, it can be determined which abnormality to output State description, there are 7 abnormal state descriptions here, namely "NB", "NS2", "NS1", "Z", "PS1", "PS2", and "PB". For example, when the temperature is described as "Z" in the second row and the temperature change is described as "PS" in the fifth column, then the abnormal state of the output is described as "PS1" in the second row and fifth column, and so on. In the above example, the fuzzy value corresponding to the temperature description "Z" and "PS" is not 0, and the temperature changes The fuzzy values corresponding to the simplified descriptions "PS" and "PB" are not 0, so two abnormal state descriptions will be output, namely "PS1" and "PS2", and these two abnormal state descriptions will be output twice. Hereinafter referred to as 4 inferences.
圖4是根據一實施例繪示狀態值的歸屬函數。請參照圖4,在此是以脈衝函數來組成歸屬函數,此歸屬函數是用以將上述的異常狀態描述轉換為狀態值。每個異常狀態描述都對應至一個狀態值,在此實施例中,異常狀態描述“NB”所對應的狀態值為-4,異常狀態描述“NS2”所對應的狀態值為-3,異常狀態描述“NS1”所對應的狀態值為-2,異常狀態描述“Z”所對應的狀態值為0,異常狀態描述“PS1”所對應的狀態值為1,異常狀態描述“PS2”所對應的狀態值為2,異常狀態描述“PB”所對應的狀態值為3。狀態值的大小代表發生異常的可能性,數值越大表示越有可能是異常。 FIG. 4 is a diagram illustrating membership functions of state values according to an embodiment. Please refer to FIG. 4 , where the impulsive function is used to form the membership function, and the membership function is used to convert the above abnormal state description into a state value. Each abnormal state description corresponds to a state value. In this embodiment, the state value corresponding to the abnormal state description "NB" is -4, the state value corresponding to the abnormal state description "NS2" is -3, and the abnormal state The state value corresponding to the description "NS1" is -2, the state value corresponding to the abnormal state description "Z" is 0, the state value corresponding to the abnormal state description "PS1" is 1, and the state value corresponding to the abnormal state description "PS2" is The state value is 2, and the state value corresponding to the abnormal state description "PB" is 3. The size of the status value represents the possibility of abnormality, and the larger the value, the more likely it is abnormal.
接下來,根據上述溫度描述的模糊量值、溫度變化描述的模糊量值、上述表1所輸出的異常狀態描述以及圖4的歸屬函數可以進行解模糊化,在此實施例中是採用離散式重心計算法來進行解模糊化。具體來說,可將溫度描述的模糊量值乘上溫度變化描述的模糊量值以及對應異常狀態描述的狀態值,最後再加總起來。舉例來說,溫度描述“PS”所對應的模糊量值為0.8,溫度變化描述“PS”所對應的模糊量值為0.3,依照表1所輸出的是異常狀態描述“PS1”,其狀態值為1,因此對應的計算為0.8×0.3×1。以此類推,把4次推論的結果加總起來會得到0.8×0.3×1+0.8× 0.7×2+0.2×0.3×1+0.2×0.7×2=1.7,此計算結果亦稱為異常分數,當此異常分數大於一臨界值(例如為2或任意的數值)時則發出警告訊號。此警告訊息可以包含文字、數字或任意的符號,用以傳送到煉鋼廠的相關負責人員。 Next, defuzzification can be performed according to the fuzzy magnitude described by the above-mentioned temperature, the fuzzy magnitude described by the temperature change, the abnormal state description output in the above-mentioned Table 1, and the membership function in Figure 4. In this embodiment, the discrete Center of gravity calculation method for defuzzification. Specifically, the fuzzy value described by the temperature can be multiplied by the fuzzy value described by the temperature change and the state value described by the corresponding abnormal state, and finally summed up. For example, the fuzzy value corresponding to the temperature description "PS" is 0.8, and the fuzzy value corresponding to the temperature change description "PS" is 0.3. According to Table 1, the abnormal state description "PS1" is output, and its state value is 1, so the corresponding calculation is 0.8×0.3×1. By analogy, adding up the results of the 4 inferences will result in 0.8×0.3×1+0.8× 0.7×2+0.2×0.3×1+0.2×0.7×2=1.7, this calculation result is also called abnormal score, when the abnormal score is greater than a critical value (such as 2 or any value), a warning signal will be issued. This warning message can contain text, numbers or arbitrary symbols to be sent to the relevant responsible personnel in the steelmaking plant.
值得注意的是,當溫度變化描述為“NB”與“NS”時,表1輸出的異常狀態描述可能是“NB”、“NS2”、“NS1”等,因為所對應的狀態值都是負的(分別是-4、-3以及-2),因此上述計算出的異常分數會變小。這表示如果溫度變化量是負的,則比較不會發出警告訊息,在實務上鋼液可能會濺出而推積在接鋼桶上,鋼液的溫度基本上都在1200度以上,而接鋼桶的安全溫度範圍是在450度以下,因此如果發生大量噴濺可能會因為溫度暫時的升高而誤判為接鋼桶已損壞。然而,由於濺出的鋼液會逐漸的降溫,透過上述的方法,在降溫時會減少異常分數,藉此可以避免假警報。 It is worth noting that when the temperature change is described as "NB" and "NS", the abnormal state description output in Table 1 may be "NB", "NS2", "NS1", etc., because the corresponding state values are all negative (-4, -3, and -2 respectively), so the anomaly scores calculated above will be smaller. This means that if the temperature change is negative, the warning message will not be issued. In practice, the molten steel may splash and accumulate on the steel drum. The temperature of the molten steel is basically above 1200 degrees, while The safe temperature range of the steel drum is below 450 degrees, so if a large amount of splashing occurs, it may be misjudged that the steel drum is damaged due to the temporary increase in temperature. However, since the splashed molten steel will gradually cool down, through the above method, the abnormal score will be reduced during the cooling down, thereby avoiding false alarms.
另一種情境是,如果接鋼桶因為破損導致鋼液流出,這會讓溫度快速上升,但習知技術中是要在溫度超過一臨界值一段時間以後才會發出警告訊息,這無法及時的反應出接鋼桶的破損。然而,透過上述的方法,當溫度變化量快速上升時,溫度變化描述可能為“PB”,這會使得表1輸出的異常狀態描述為“PS2”或是“PB”,這都會增加異常分數,藉此與習知技術相比可以更及時的發出警告訊息。 Another situation is that if the molten steel flows out due to damage to the steel drum, the temperature will rise rapidly. However, in the conventional technology, a warning message is issued only after the temperature exceeds a critical value for a period of time, which cannot be reflected in time. Damage to the steel drum. However, through the above method, when the temperature change increases rapidly, the temperature change description may be "PB", which will make the abnormal state output in Table 1 be described as "PS2" or "PB", which will increase the abnormal score. Compared with the prior art, the warning message can be issued more timely.
此外,當鋼液濺出時接鋼桶的溫度會上升,但與接鋼桶破損導致的溫度上升來說,鋼液濺出時的溫度上升速 度比較慢。在習知技術中只要溫度超過一臨界值一段時間就會發出警報,但根據上述的做法由於同時考慮溫度值與溫度變化量,當溫度緩慢上升時溫度變化量比較小,這會抑制警告訊息,但溫度持續上升時依然保有預警機制,這同樣可以減少假警報的次數或時間。 In addition, when the molten steel is splashed, the temperature of the steel drum will rise, but compared with the temperature rise caused by the damage of the steel drum, the temperature rise rate when the molten steel is splashed The speed is relatively slow. In the conventional technology, an alarm will be issued as long as the temperature exceeds a critical value for a period of time. However, according to the above method, the temperature value and the temperature variation are considered at the same time. When the temperature rises slowly, the temperature variation is relatively small, which will suppress the warning message, but When the temperature continues to rise, there is still an early warning mechanism, which can also reduce the number or time of false alarms.
換言之,上述表1中的異常狀態描述“NB”、“NS2”、“NS1”可以剃除有降溫趨勢時的假警報,而異常狀態描述“PS2”、“PS1”、“PB”可以判斷溫度上升的趨勢,藉此提早發出警報或抑制假警報。因此,本揭露提出的方法可以減少假警報(false positive)與沒有正確發出警報(false negative)的次數或時間。 In other words, the abnormal state descriptions "NB", "NS2", and "NS1" in Table 1 above can eliminate false alarms when there is a cooling trend, while the abnormal state descriptions "PS2", "PS1", and "PB" can judge the temperature Uptrends, thereby sounding early warnings or suppressing false alarms. Therefore, the method proposed in this disclosure can reduce the number or time of false positives and false negatives.
圖5是根據一實施例繪示異常升溫的檢測方法的流程圖。請參照圖5,在步驟501,透過溫度感測器取得接鋼桶的溫度值並計算出溫度變化量。在步驟502,將溫度值輸入至第一歸屬函數以取得多個第一模糊量值,並將溫度變化量輸入至第二歸屬函數以取得多個第二模糊量值。在步驟503,根據第一模糊量值所屬的溫度描述以及第二模糊量值所屬的溫度變化描述透過一模糊規則表進行模糊推論以得到異常狀態描述,此異常狀態描述屬於第三歸屬函數。在步驟504,根據第一模糊量值、第二模糊量值、異常狀態描述以及第三歸屬函數進行解模糊化以計算出異常分數。在步驟505,當異常分數大於一臨界值時,發出警告訊息。然而,圖5中各步驟已詳細說明如上,在此便不再贅述。值得注意的是,圖5中各步驟可以實作為多個
程式碼或是電路,本發明並不在此限。此外,圖5的方法可以搭配以上實施例使用,也可以單獨使用。換言之,圖5的各步驟之間也可以加入其他的步驟。
FIG. 5 is a flowchart illustrating a method for detecting abnormal temperature rise according to an embodiment. Please refer to FIG. 5 , in
雖然本發明已以實施例揭露如上,然其並非用以限定本發明,任何所屬技術領域中具有通常知識者,在不脫離本發明的精神和範圍內,當可作些許的更動與潤飾,故本發明的保護範圍當視後附的申請專利範圍所界定者為準。 Although the present invention has been disclosed above with the embodiments, it is not intended to limit the present invention. Anyone with ordinary knowledge in the technical field may make some changes and modifications without departing from the spirit and scope of the present invention. The scope of protection of the present invention should be defined by the scope of the appended patent application.
501~505:步驟501~505: steps
Claims (10)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW110129917A TWI797716B (en) | 2021-08-13 | 2021-08-13 | Method and system for detecting abnormal temperature rise |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW110129917A TWI797716B (en) | 2021-08-13 | 2021-08-13 | Method and system for detecting abnormal temperature rise |
Publications (2)
Publication Number | Publication Date |
---|---|
TW202307408A TW202307408A (en) | 2023-02-16 |
TWI797716B true TWI797716B (en) | 2023-04-01 |
Family
ID=86661155
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW110129917A TWI797716B (en) | 2021-08-13 | 2021-08-13 | Method and system for detecting abnormal temperature rise |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWI797716B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107764412A (en) * | 2017-11-27 | 2018-03-06 | 国网河南省电力公司电力科学研究院 | A kind of environment temperature object of reference Sign Board applied to power system infrared detection |
TWI628285B (en) * | 2016-08-12 | 2018-07-01 | 中國鋼鐵股份有限公司 | Quality evaluation system and method for rolling metal billet |
JP2018172715A (en) * | 2017-03-31 | 2018-11-08 | 住友金属鉱山株式会社 | Device and method for preventing leakage of molten steel |
CN212363432U (en) * | 2020-04-30 | 2021-01-15 | 宁波海泰汽车电子有限公司 | Infrared thermometer |
-
2021
- 2021-08-13 TW TW110129917A patent/TWI797716B/en active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI628285B (en) * | 2016-08-12 | 2018-07-01 | 中國鋼鐵股份有限公司 | Quality evaluation system and method for rolling metal billet |
JP2018172715A (en) * | 2017-03-31 | 2018-11-08 | 住友金属鉱山株式会社 | Device and method for preventing leakage of molten steel |
CN107764412A (en) * | 2017-11-27 | 2018-03-06 | 国网河南省电力公司电力科学研究院 | A kind of environment temperature object of reference Sign Board applied to power system infrared detection |
CN212363432U (en) * | 2020-04-30 | 2021-01-15 | 宁波海泰汽车电子有限公司 | Infrared thermometer |
Also Published As
Publication number | Publication date |
---|---|
TW202307408A (en) | 2023-02-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2015176439A1 (en) | Method, system and apparatus for detecting blockage of dust filter | |
CN107766533A (en) | Telephone traffic abnormal automatic testing method and system, storage medium, electronic equipment | |
JP5474415B2 (en) | Temperature difference rise alarm generation method | |
TWI797716B (en) | Method and system for detecting abnormal temperature rise | |
KR20150131841A (en) | Intelligent fire detection system using fuzzy logic | |
WO2016127490A1 (en) | Fault diagnosis and treatment method and system for thermocouples in heat treatment apparatus | |
US20140169936A1 (en) | Method for detecting heat-dissipating air flow and electronic device using the same | |
US20070204452A1 (en) | Methods for detecting water induction in steam turbines | |
CN114046456A (en) | Corrosion assessment method and system integrating fuzzy inference and neural network | |
JP4515939B2 (en) | Plant monitoring method | |
CN115163825B (en) | Overheat protection method and device for wet double-clutch automatic transmission and electronic equipment | |
Zhou et al. | Fault-alarm-threshold optimization method based on interval evidence reasoning | |
JP5426608B2 (en) | Abnormality detection apparatus and abnormality detection method | |
CN113945290B (en) | Temperature alarm method, device and medium | |
CN111998066B (en) | Early warning method and device applied to power take-off system | |
Lv et al. | General log‐linear Weibull model combining vibration and temperature characteristics for remaining useful life prediction of rolling element bearings | |
JP5159288B2 (en) | Condition monitoring device | |
US20200371890A1 (en) | Learning method for the detection of anomalies implemented on a microcontroller and associated method for detecting anomalies | |
JP2006277247A (en) | Plant abnormality monitoring system and plant abnormality monitoring method | |
JP6459345B2 (en) | Fluctuation data management system and its specificity detection method | |
JPS58172701A (en) | Operation guidance method of plant | |
CN116814874B (en) | Control method, device, equipment and medium for blast furnace top pressure | |
EP3109806A1 (en) | Method for generating prognostic alerts and a human machine interface (hmi) device therefor | |
Xie et al. | Computer-aided statistical monitoring of automated manufacturing processes | |
JPWO2015040683A1 (en) | Sensor soundness determination method and sensor soundness determination device |