TW202424168A - Method for predicting gas level of coke oven gas reservoir - Google Patents
Method for predicting gas level of coke oven gas reservoir Download PDFInfo
- Publication number
- TW202424168A TW202424168A TW111145834A TW111145834A TW202424168A TW 202424168 A TW202424168 A TW 202424168A TW 111145834 A TW111145834 A TW 111145834A TW 111145834 A TW111145834 A TW 111145834A TW 202424168 A TW202424168 A TW 202424168A
- Authority
- TW
- Taiwan
- Prior art keywords
- coke furnace
- furnace gas
- storage tank
- gas storage
- coke
- Prior art date
Links
- 239000000571 coke Substances 0.000 title claims abstract description 304
- 238000000034 method Methods 0.000 title claims abstract description 59
- 239000007789 gas Substances 0.000 claims abstract description 311
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 claims abstract description 160
- 239000003345 natural gas Substances 0.000 claims abstract description 80
- 238000003860 storage Methods 0.000 claims description 185
- 238000002347 injection Methods 0.000 claims description 53
- 239000007924 injection Substances 0.000 claims description 53
- 238000004519 manufacturing process Methods 0.000 claims description 29
- 238000004939 coking Methods 0.000 claims description 21
- 238000000611 regression analysis Methods 0.000 claims description 12
- 229910000831 Steel Inorganic materials 0.000 claims description 9
- 239000010959 steel Substances 0.000 claims description 9
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 6
- 230000007774 longterm Effects 0.000 claims description 6
- 238000005098 hot rolling Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 2
- 101100233916 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) KAR5 gene Proteins 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
Abstract
Description
本揭露是有關於一種預測儲槽槽位的方法，且特別是有關於一種預測焦爐氣儲槽槽位的方法。The present disclosure relates to a method for predicting the position of a storage tank, and in particular to a method for predicting the position of a coke furnace gas storage tank.
在石化工業中，煉焦製程所產生的焦爐氣可儲放於焦爐氣儲槽中，並在需要時用於供給至各生產工廠以作為發電能源。In the petrochemical industry, coke gas produced in the coking process can be stored in coke gas storage tanks and supplied to various production plants as an energy source for power generation when needed.
在普遍情況下，單一焦爐氣儲槽經常連接多個生產工廠，以藉由管網等連接設備供應能源。若是發生焦爐氣缺乏的情況，焦爐氣儲槽槽位以及管網壓力容易過低而造成運轉上的風險。具體而言，當管網壓力低於400mmH 2O時，各個工廠的廠內設備便有可能因為電力不足而有跳機的現象。此時常見的作法是將天然氣人為手動地注入，拉高焦爐氣儲槽槽位，以避免廠內設備跳機。但天然氣的注入量如何影響焦爐氣儲槽槽位實際上難以預測，人們往往只能依據經驗來調整天然氣的注入量。若是經驗不足的操作者，便有可能無法及時地調整天然氣注入量，而導致廠內設備跳機的憾事。故，如何準確預測焦爐氣儲槽槽位的變化，在焦爐製程中便成了至關重要的議題。 Generally, a single coke furnace gas storage tank is often connected to multiple production plants to supply energy through connecting equipment such as pipeline networks. If there is a shortage of coke furnace gas, the coke furnace gas storage tank position and the pipeline network pressure may be too low, causing operational risks. Specifically, when the pipeline network pressure is lower than 400mmH2O , the equipment in each plant may trip due to insufficient power. At this time, the common practice is to manually inject natural gas to raise the coke furnace gas storage tank position to avoid the plant equipment tripping. However, it is actually difficult to predict how the amount of natural gas injected will affect the coke furnace gas storage tank position, and people can often only adjust the amount of natural gas injected based on experience. If the operator is not experienced enough, he may not be able to adjust the natural gas injection volume in time, which may cause the equipment in the plant to trip. Therefore, how to accurately predict the changes in the coke furnace gas storage tank position has become a crucial issue in the coke furnace process.
因此，亟需一種可精準預測焦爐氣儲槽槽位的方法，能藉由焦爐氣儲槽的過往參數預測一定時間內的焦爐氣儲槽槽位變化，以供線上工作人員在瀏覽預測結果後即時注入天然氣，進而避免焦爐氣儲槽的槽位過低。Therefore, there is an urgent need for a method that can accurately predict the coke furnace gas storage tank position, which can predict the coke furnace gas storage tank position changes within a certain period of time based on the past parameters of the coke furnace gas storage tank, so that online workers can inject natural gas immediately after browsing the prediction results, thereby avoiding the coke furnace gas storage tank position being too low.
因此，本揭露之實施例之一目的是在於提供一種預測焦爐氣儲槽槽位的方法，其包含對焦爐氣壓力對焦爐氣儲槽槽位以及天然氣輸入量對焦爐氣儲槽槽位進行分析，並取得焦爐氣壓力與天然氣輸入量分別對焦爐氣儲槽槽位變化的關係式，且結合兩關係式以及其他參數對焦爐氣儲槽槽位進行預測，以精準掌握焦爐氣儲槽槽位的變化。Therefore, one purpose of the embodiments disclosed herein is to provide a method for predicting the position of a coke furnace gas storage tank, which includes analyzing the effect of coke furnace gas pressure on the position of the coke furnace gas storage tank and the effect of natural gas input on the position of the coke furnace gas storage tank, and obtaining a relationship between the coke furnace gas pressure and the natural gas input and the change of the coke furnace gas storage tank position, respectively, and combining the two relationships with other parameters to predict the position of the coke furnace gas storage tank, so as to accurately grasp the change of the coke furnace gas storage tank position.
根據本揭露之上述目的，提出一種預測焦爐氣儲槽槽位的方法，包含進行焦爐氣壓力對焦爐氣儲槽槽位分析，以取得焦爐氣壓力對焦爐氣儲槽槽位變化關係；進行天然氣輸入量對焦爐氣儲槽槽位分析，以取得天然氣輸入量對焦爐氣儲槽槽位變化關係；以及依據焦爐氣壓力對焦爐氣儲槽槽位變化關係、天然氣輸入量對焦爐氣儲槽槽位變化關係、天然氣輸入量、預設時間區段前之焦爐氣壓力、當前焦爐氣儲槽槽位，進行天然氣注入後焦爐氣儲槽槽位變化預測分析，並預測下一分鐘之焦爐氣儲槽槽位。According to the above-mentioned purpose of the present disclosure, a method for predicting the slot position of a coke furnace gas storage tank is proposed, comprising: performing a coke furnace gas pressure analysis on the slot position of the coke furnace gas storage tank to obtain the relationship between the coke furnace gas pressure and the slot position of the coke furnace gas storage tank; performing a natural gas input amount analysis on the slot position of the coke furnace gas storage tank to obtain the relationship between the natural gas input amount and the slot position of the coke furnace gas storage tank; And based on the relationship between coke furnace gas pressure and coke furnace gas storage tank position change, the relationship between natural gas input and coke furnace gas storage tank position change, natural gas input, coke furnace gas pressure before the preset time period, and current coke furnace gas storage tank position, the coke furnace gas storage tank position change prediction analysis after natural gas injection is performed, and the coke furnace gas storage tank position in the next minute is predicted.
根據本揭露之一些實施例，上述之焦爐氣壓力對焦爐氣儲槽槽位分析包含分別對數個焦爐氣儲槽進行數個焦爐氣壓力偵測，以取得焦爐氣儲槽的數個焦爐氣壓力；分別對焦爐氣儲槽進行數個焦爐氣儲槽槽位偵測，以取得焦爐氣儲槽的數個焦爐氣儲槽槽位變化；以及對焦爐氣壓力以及焦爐氣儲槽槽位進行第一迴歸分析處理，以取得焦爐氣壓力對焦爐氣儲槽槽位變化關係式。According to some embodiments of the present disclosure, the above-mentioned coke furnace gas pressure versus coke furnace gas storage tank position analysis includes performing a plurality of coke furnace gas pressure detections on a plurality of coke furnace gas storage tanks to obtain a plurality of coke furnace gas pressures of the coke furnace gas storage tanks; performing a plurality of coke furnace gas storage tank position detections on the coke furnace gas storage tanks to obtain a plurality of coke furnace gas storage tank position changes of the coke furnace gas storage tanks; and performing a first regression analysis process on the coke furnace gas pressure and the coke furnace gas storage tank position to obtain a relationship between the coke furnace gas pressure and the coke furnace gas storage tank position change.
根據本揭露之一些實施例，上述之焦爐氣壓力對焦爐氣儲槽槽位變化關係式是： Y1=(0.021297X1-21.55493)， 其中Y1是每分鐘之焦爐氣儲槽槽位變化百分比，X1是每分鐘之平均焦爐氣槽壓力。 According to some embodiments of the present disclosure, the above-mentioned relationship between the coke furnace gas pressure and the coke furnace gas storage tank position change is: Y1 = (0.021297X1-21.55493), where Y1 is the coke furnace gas storage tank position change percentage per minute, and X1 is the average coke furnace gas tank pressure per minute.
根據本揭露之一些實施例，上述之天然氣輸入量對焦爐氣儲槽槽位分析包含依據數個煉焦製程記錄，計算每小時之煉焦製程供應焦爐氣儲槽的焦爐氣氣體提供量；依據數個生產製程記錄，計算每小時之焦爐氣儲槽的焦爐氣氣體消耗量；依據焦爐氣氣體提供量以及焦爐氣氣體消耗量，計算焦爐氣儲槽之每小時的焦爐氣注入量；對天然氣注入量以及焦爐氣注入量進行第二迴歸分析處理，以取得天然氣注入量對焦爐氣注入量關係式；以及依據天然氣注入量對焦爐氣注入量關係式求得天然氣輸入量對焦爐氣儲槽槽位變化關係式。According to some embodiments of the present disclosure, the above-mentioned natural gas input amount to coke furnace gas storage tank slot analysis includes calculating the coke furnace gas supply amount of the coke furnace gas storage tank supplied by the coke furnace process per hour based on a plurality of coke process records; calculating the coke furnace gas consumption of the coke furnace gas storage tank per hour based on a plurality of production process records; and calculating the coke furnace gas supply amount and the coke furnace gas consumption of the coke furnace gas storage tank according to the coke furnace gas supply amount and the coke furnace gas consumption. The coke furnace gas consumption is calculated to calculate the coke furnace gas injection amount per hour of the coke furnace gas storage tank; the natural gas injection amount and the coke furnace gas injection amount are processed by the second regression analysis to obtain the relationship between the natural gas injection amount and the coke furnace gas injection amount; and the relationship between the natural gas input amount and the coke furnace gas storage tank position change is obtained based on the relationship between the natural gas injection amount and the coke furnace gas injection amount.
根據本揭露之一些實施例，上述之天然氣注入量對焦爐氣注入量關係式是： 1.836822X2=X3， 其中X2是每分鐘之天然氣注入量，X3是每分鐘之焦爐氣注入量。 According to some embodiments of the present disclosure, the above-mentioned relationship between the natural gas injection amount and the coke furnace gas injection amount is: 1.836822X2=X3, where X2 is the natural gas injection amount per minute, and X3 is the coke furnace gas injection amount per minute.
根據本揭露之一些實施例，上述之天然氣輸入量對焦爐氣儲槽槽位變化關係式是： Y1=0.000051X2， 其中Y1是每分鐘之焦爐氣儲槽槽位變化百分比，X2是每分鐘之天然氣注入量。 According to some embodiments of the present disclosure, the above-mentioned relationship between the natural gas input amount and the coke furnace gas storage tank position change is: Y1 = 0.000051X2, where Y1 is the coke furnace gas storage tank position change percentage per minute, and X2 is the natural gas injection amount per minute.
根據本揭露之一些實施例，上述之天然氣輸入量對焦爐氣儲槽槽位分析更包含進行資料清洗作業，去除煉焦製程記錄以及生產製程記錄中的數個無效資料或複數個低關聯性資料。According to some embodiments of the present disclosure, the above-mentioned natural gas input volume and coke furnace gas storage tank position analysis further includes performing a data cleaning operation to remove several invalid data or multiple low-correlation data in the coking process records and the production process records.
根據本揭露之一些實施例，上述之煉焦製程記錄包含各階煉焦的煉焦製程參數。According to some embodiments of the present disclosure, the above-mentioned coking process record includes coking process parameters of each stage of coking.
根據本揭露之一些實施例，上述之生產製程記錄包含數個熱軋製程記錄、數個鋼板生產製程記錄、數個鋼胚生產製程記錄、數個條鋼生產製程記錄、數個線材生產製程記錄、焦爐氣儲槽變化量記錄、以及數個焦爐氣使用記錄。According to some embodiments of the present disclosure, the above-mentioned production process records include a plurality of hot rolling process records, a plurality of steel plate production process records, a plurality of steel billet production process records, a plurality of steel strip production process records, a plurality of wire rod production process records, a coke furnace gas storage tank variation record, and a plurality of coke furnace gas usage records.
根據本揭露之一些實施例，上述之預測焦爐氣儲槽槽位的方法更包含重複進行天然氣注入後焦爐氣儲槽槽位變化預測分析，以預測當前焦爐氣儲槽槽位的長期變化。According to some embodiments of the present disclosure, the above-mentioned method for predicting the coke furnace gas storage tank position further includes repeatedly performing a prediction analysis of the coke furnace gas storage tank position change after natural gas injection to predict the long-term change of the current coke furnace gas storage tank position.
由上述本揭露實施方式可知，本揭露主要是透過迴歸分析分別取得焦爐氣壓力對焦爐氣儲槽槽位變化關係式以及天然氣輸入量對焦爐氣儲槽槽位變化關係式，再結合焦爐氣壓力對焦爐氣儲槽槽位變化關係式以及天然氣輸入量對焦爐氣儲槽槽位變化關係式，來預測天然氣注入後焦爐氣儲槽槽位的長期變化。本揭露之預測焦爐氣儲槽槽位的方法在預測上具有高度的準確性，且能即時呈現預測結果給線上工作人員，故可有效避免焦爐氣儲槽槽位過低而發生各工廠設備跳機的情況。另外，天然氣輸入量對焦爐氣儲槽槽位分析還包含資料清洗作業，以移除無效資料以及低關聯性資料，進而提升分析的準確性。As can be seen from the above-mentioned implementation method of the present disclosure, the present disclosure mainly obtains the relationship between the coke furnace gas pressure and the coke furnace gas storage tank position change relationship and the natural gas input and the coke furnace gas storage tank position change relationship through regression analysis, and then combines the relationship between the coke furnace gas pressure and the coke furnace gas storage tank position change relationship and the natural gas input and the coke furnace gas storage tank position change relationship to predict the long-term change of the coke furnace gas storage tank position after natural gas injection. The method for predicting the coke furnace gas storage tank position disclosed in the present disclosure has a high degree of accuracy in prediction, and can present the prediction results to the online staff in real time, so it can effectively avoid the situation where the coke furnace gas storage tank position is too low and the equipment of each factory trips. In addition, the analysis of natural gas input on coke furnace gas storage tank locations also includes data cleaning operations to remove invalid data and low-relevance data, thereby improving the accuracy of the analysis.
以下仔細討論本揭露的實施例。然而，可以理解的是，實施例提供許多可應用的概念，其可實施於各式各樣的特定內容中。所討論與揭示之實施例僅供說明，並非用以限定本揭露之範圍。The following is a detailed discussion of embodiments of the present disclosure. However, it is understood that the embodiments provide many applicable concepts that can be implemented in a variety of specific contexts. The embodiments discussed and disclosed are for illustration only and are not intended to limit the scope of the present disclosure.
請參照圖1，圖1係繪示依照本揭露之一些實施方式之預測焦爐氣儲槽槽位的方法的流程圖。在一些實施方式中，方法100包含步驟200、步驟300、步驟400、以及步驟500。須注意的是，方法100僅是例示，且非用以將本揭露限制在清楚揭示的專利保護範圍之內。在方法100之前、期間、與之後可提供額外的步驟，且對於方法100的額外實施方式，可移動、移除、取代、或刪減所述的這些步驟的一些。Please refer to FIG. 1, which is a flow chart of a method for predicting the position of a coke gas storage tank according to some embodiments of the present disclosure. In some embodiments, method 100 includes step 200, step 300, step 400, and step 500. It should be noted that method 100 is merely an example and is not intended to limit the present disclosure to the patent protection scope clearly disclosed. Additional steps may be provided before, during, and after method 100, and some of the steps described may be moved, removed, replaced, or deleted for additional embodiments of method 100.
進行預測焦爐氣儲槽槽位的方法100時，可先進行步驟200，以進行焦爐氣壓力對焦爐氣儲槽槽位分析，來取得焦爐氣壓力對焦爐氣儲槽槽位變化關係。請一併參照圖2，其係繪示依照本揭露之一些實施方式之焦爐氣壓力對焦爐氣儲槽槽位分析的流程圖。在一些實施例中，進行焦爐氣壓力對焦爐氣儲槽槽位分析包含步驟210、步驟220、以及步驟230。同樣地，步驟200僅是例示，且非用以將本揭露限制在清楚揭示的專利保護範圍之內。在步驟200之前、期間、與之後可提供額外的步驟，且對於步驟200的額外實施方式，可移動、移除、取代、或刪減所述的這些步驟的一些。When performing the method 100 for predicting the position of the coke furnace gas storage tank, step 200 may be performed first to perform a coke furnace gas pressure versus coke furnace gas storage tank position analysis to obtain the relationship between the coke furnace gas pressure and the coke furnace gas storage tank position change. Please refer to FIG. 2 , which is a flow chart of the coke furnace gas pressure versus coke furnace gas storage tank position analysis according to some embodiments of the present disclosure. In some embodiments, performing the coke furnace gas pressure versus coke furnace gas storage tank position analysis includes step 210, step 220, and step 230. Similarly, step 200 is merely an example and is not intended to limit the present disclosure to the patent protection scope clearly disclosed. Additional steps may be provided before, during, and after step 200, and some of the steps described may be moved, removed, substituted, or deleted for additional implementations of step 200.
進行焦爐氣壓力對焦爐氣儲槽槽位分析時，可先進行步驟210，以分別對數個焦爐氣儲槽進行數個焦爐氣壓力偵測，來取得焦爐氣儲槽的數個焦爐氣壓力。具體而言，在一些實施方式中，線上工作人員可透過預先連接至各焦爐氣儲槽之焦爐氣壓力偵測器測量各焦爐氣儲槽內之焦爐氣壓力，並在連續紀錄後求得每特定時間間隔(例如，但不限於，15分鐘)內的平均焦爐氣壓力。在一些例子中，焦爐氣壓力偵測器可以是，但不限於指針型壓力計、數位接點式壓力計、或是隔膜式壓力計等等。焦爐氣壓力偵測器不受限於壓力計的種類，惟只須能精準量測各焦爐氣儲槽內之焦爐氣壓力即可。When performing the coke gas pressure analysis on the coke gas storage tank position, step 210 may be performed first to perform a plurality of coke gas pressure detections on a plurality of coke gas storage tanks respectively to obtain a plurality of coke gas pressures of the coke gas storage tanks. Specifically, in some embodiments, the online staff may measure the coke gas pressure in each coke gas storage tank through a coke gas pressure detector pre-connected to each coke gas storage tank, and obtain the average coke gas pressure in each specific time interval (for example, but not limited to, 15 minutes) after continuous recording. In some examples, the coke furnace gas pressure detector may be, but is not limited to, a pointer type pressure gauge, a digital contact type pressure gauge, or a diaphragm type pressure gauge, etc. The coke furnace gas pressure detector is not limited to the type of pressure gauge, but only needs to be able to accurately measure the coke furnace gas pressure in each coke furnace gas storage tank.
焦爐氣壓力對焦爐氣儲槽槽位分析時接下來可進行步驟220，以分別對焦爐氣儲槽進行數個焦爐氣儲槽槽位偵測，來取得焦爐氣儲槽的數個焦爐氣儲槽槽位變化。具體而言，在一些實施方式中，線上操作者可透過預先連接至各焦爐氣儲槽之焦爐氣槽位偵測器測量各焦爐氣儲槽內之料位，並在連續紀錄後求得每特定時間間隔(例如，但不限於，15分鐘)內的平均焦爐氣槽的槽位變化。在一些例子中，焦爐氣槽位偵測器可以是，但不限於電容式料位計、超音波式料位計、或是雷達波式料位計等等。焦爐氣槽位偵測器不受限於料位計的種類，惟只須能精準量測各焦爐氣槽內之料位即可。When analyzing the effect of coke gas pressure on the position of coke gas storage tanks, step 220 may be performed to perform multiple coke gas storage tank position detections on the coke gas storage tanks to obtain multiple coke gas storage tank position changes of the coke gas storage tanks. Specifically, in some embodiments, an online operator may measure the material level in each coke gas storage tank through a coke gas tank position detector pre-connected to each coke gas storage tank, and obtain the average coke gas tank position change in each specific time interval (for example, but not limited to, 15 minutes) after continuous recording. In some examples, the coke furnace gas tank level detector may be, but is not limited to, a capacitive level meter, an ultrasonic level meter, or a radar wave level meter, etc. The coke furnace gas tank level detector is not limited to the type of level meter, but only needs to be able to accurately measure the material level in each coke furnace gas tank.
接著進行步驟230，以對焦爐氣壓力以及焦爐氣儲槽槽位進行第一迴歸分析處理，來取得焦爐氣壓力對焦爐氣儲槽槽位變化關係式。舉例而言，在測得每15分鐘內之各焦爐氣儲槽的平均焦爐氣壓力以及平均焦爐氣槽的槽位變化後，操作者可利用各種分析程式語言或軟體，例如，但不限於，R語言、Python、Excel、以及SAS來進行迴歸分析，以取得焦爐氣壓力對焦爐氣儲槽槽位變化關係式。在一些例子中，焦爐氣壓力對焦爐氣儲槽槽位變化關係式是： Y1=(0.021297X1-21.55493)， 其中Y1是每分鐘之焦爐氣儲槽槽位變化百分比，X1是每分鐘之平均焦爐氣槽壓力。 Then, step 230 is performed to perform a first regression analysis on the coke furnace gas pressure and the coke furnace gas storage tank position to obtain a relationship between the coke furnace gas pressure and the coke furnace gas storage tank position change. For example, after measuring the average coke furnace gas pressure of each coke furnace gas storage tank and the average coke furnace gas tank position change every 15 minutes, the operator can use various analysis programming languages or software, such as, but not limited to, R language, Python, Excel, and SAS to perform regression analysis to obtain a relationship between the coke furnace gas pressure and the coke furnace gas storage tank position change. In some examples, the relationship between coke furnace gas pressure and coke furnace gas storage tank position change is: Y1 = (0.021297X1-21.55493), where Y1 is the coke furnace gas storage tank position change percentage per minute, and X1 is the average coke furnace gas tank pressure per minute.
預測焦爐氣儲槽槽位的方法接著進行步驟300。請同時參照圖1以及圖3，圖3係繪示依照本揭露之一些實施方式之天然氣輸入量對焦爐氣儲槽槽位分析的流程圖。進行步驟300時，可先進行天然氣輸入量對焦爐氣儲槽槽位分析，以取得天然氣輸入量對焦爐氣儲槽槽位變化關係。天然氣輸入量對焦爐氣儲槽槽位分析可包含步驟310、步驟320、步驟330、步驟340、步驟350、以及步驟360。須強調的是，步驟300僅是例示，且非用以將本揭露限制在清楚揭示的範圍之內。在步驟300之前、期間、與之後可提供額外的步驟，且對於步驟300的額外實施方式，可移動、移除、取代、或刪減所述的這些步驟的一些。The method for predicting the position of the coke furnace gas storage tank then proceeds to step 300. Please refer to Figure 1 and Figure 3 at the same time. Figure 3 is a flow chart showing the analysis of the natural gas input amount and the coke furnace gas storage tank position according to some embodiments of the present disclosure. When performing step 300, the natural gas input amount and the coke furnace gas storage tank position analysis can be performed first to obtain the relationship between the natural gas input amount and the coke furnace gas storage tank position change. The natural gas input amount and the coke furnace gas storage tank position analysis can include step 310, step 320, step 330, step 340, step 350, and step 360. It should be emphasized that step 300 is only an example and is not used to limit the present disclosure to the scope of the clear disclosure. Additional steps may be provided before, during, and after step 300, and some of the steps described may be moved, removed, substituted, or deleted for additional implementations of step 300.
請參照圖3，進行天然氣輸入量對焦爐氣儲槽槽位分析時，可先進行步驟310，依據數個煉焦製程記錄，來計算每小時之煉焦製程供應焦爐氣儲槽的焦爐氣氣體提供量。具體而言，在一些例子中，煉焦製程記錄包含各階煉焦的煉焦製程參數，故在進行煉焦製程時，工作人員會記錄各煉焦製程中每小時所產生的焦爐氣產量，並記錄在對應各煉焦製程的煉焦製程記錄中。在一些例子中，數個煉焦製程記錄可以用數位資料的形式儲存於關聯式資料庫(例如，MySQL、SQL Server、以及Oracle)或非關聯式資料庫(例如，MongoDB)裡頭，故工作人員可運用SQL或Python等程式語言即時查詢或更動資料庫裡的內容。Please refer to FIG3 . When analyzing the input of natural gas to the coke furnace gas storage tank position, step 310 may be performed first to calculate the coke furnace gas supply of the coke furnace gas storage tank per hour according to a plurality of coking process records. Specifically, in some examples, the coking process record includes coking process parameters of each stage of coking, so when the coking process is performed, the staff will record the coke furnace gas output generated per hour in each coking process and record it in the coking process record corresponding to each coking process. In some examples, several coking process records can be stored in a relational database (e.g., MySQL, SQL Server, and Oracle) or a non-relational database (e.g., MongoDB) in the form of digital data, so that staff can use programming languages such as SQL or Python to query or modify the contents of the database in real time.
天然氣輸入量對焦爐氣儲槽槽位分析時接下來可進行步驟320，依據數個生產製程記錄，來計算每小時之焦爐氣儲槽的焦爐氣氣體消耗量。具體而言，在進行各生產製程時，焦爐器可做為電力能源供各生產製程使用，線上工作人員可記錄各生產製程中每小時所消耗的焦爐氣氣體消耗量，並製作出對應的生產製程記錄。在一些例子中，生產製程記錄包含，但不限於，數個熱軋製程記錄、數個鋼板生產製程記錄、數個鋼胚生產製程記錄、數個條鋼生產製程記錄、數個線材生產製程記錄、焦爐氣儲槽變化量記錄、以及數個焦爐氣使用記錄。在一些例子中，數個生產製程記錄可以用數位資料的形式儲存於關聯式資料庫(例如，MySQL、SQL Server、以及Oracle)或非關聯式資料庫(例如，MongoDB)裡頭，故工作人員可運用SQL或Python等程式語言即時查詢或更動資料庫裡的內容。When the natural gas input is analyzed for the coke furnace gas storage tank position, step 320 can be performed to calculate the coke furnace gas consumption of the coke furnace gas storage tank per hour based on a number of production process records. Specifically, when each production process is carried out, the coke furnace can be used as an electrical energy source for each production process. The online staff can record the coke furnace gas consumption consumed per hour in each production process and make a corresponding production process record. In some examples, the production process records include, but are not limited to, a plurality of hot rolling process records, a plurality of steel plate production process records, a plurality of steel billet production process records, a plurality of steel strip production process records, a plurality of wire rod production process records, coke furnace gas storage tank variation records, and a plurality of coke furnace gas usage records. In some examples, the plurality of production process records may be stored in a relational database (e.g., MySQL, SQL Server, and Oracle) or a non-relational database (e.g., MongoDB) in the form of digital data, so that staff can use programming languages such as SQL or Python to query or modify the contents of the database in real time.
接著進行步驟330，以依據焦爐氣氣體提供量以及焦爐氣氣體消耗量，來計算焦爐氣儲槽之每小時的焦爐氣注入量。Then, step 330 is performed to calculate the hourly coke gas injection rate of the coke gas storage tank according to the coke gas supply rate and the coke gas consumption rate.
天然氣輸入量對焦爐氣儲槽槽位分析時接著執行步驟340，進行資料清洗作業，以去除煉焦製程記錄以及生產製程記錄中的數個無效資料或數個低關聯性資料。具體而言，在一些例子中，煉焦製程記錄以及生產製程記錄中可能包含數個儲存資訊錯誤或沒有資訊的欄位。這些資料在未來進行迴歸分析時容易導致分析結果失準，或甚至造成無法進行分析的情形。故，線上工作人員可進行資料清洗(Data Cleansing)的動作，將資料庫中不完整、不準確、無效，或低關聯性的資料移除，以提升未來進行迴歸分析時結果的準確性。When analyzing the natural gas input volume for the coke furnace gas storage tank slot position, step 340 is then executed to perform data cleaning operations to remove several invalid data or several low-relevance data in the coking process records and the production process records. Specifically, in some examples, the coking process records and the production process records may contain several fields that store incorrect information or no information. These data may easily lead to inaccurate analysis results or even make it impossible to perform analysis when performing regression analysis in the future. Therefore, online staff can perform data cleaning operations to remove incomplete, inaccurate, invalid, or low-relevance data in the database to improve the accuracy of the results of future regression analysis.
天然氣輸入量對焦爐氣儲槽槽位分析時，在完成步驟340後，接著進行步驟350，以對天然氣注入量以及焦爐氣注入量進行第二迴歸分析處理，來取得天然氣注入量對焦爐氣注入量關係式。具體而言，在求得焦爐氣儲槽之每小時的焦爐氣注入量後，線上工作人員可從原先儲存的歷史數據中提取出每小時注入焦爐氣儲槽的天然氣注入量，並利用各種分析軟體或程式語言對焦爐氣注入量以及天然氣注入量進行迴歸分析。在一些例子中，天然氣注入量對焦爐氣注入量關係式是： 1.836822X2=X3， 其中X2是每分鐘之天然氣注入量，X3是每分鐘之焦爐氣注入量。 When analyzing the input amount of natural gas to the position of the coke gas storage tank, after completing step 340, step 350 is then performed to perform a second regression analysis on the natural gas injection amount and the coke gas injection amount to obtain a relationship between the natural gas injection amount and the coke gas injection amount. Specifically, after obtaining the hourly coke gas injection amount of the coke gas storage tank, the online staff can extract the hourly natural gas injection amount injected into the coke gas storage tank from the previously stored historical data, and use various analysis software or programming languages to perform regression analysis on the coke gas injection amount and the natural gas injection amount. In some examples, the relationship between natural gas injection rate and coke furnace gas injection rate is: 1.836822X2=X3, where X2 is the natural gas injection rate per minute, and X3 is the coke furnace gas injection rate per minute.
天然氣輸入量對焦爐氣儲槽槽位分析時最後進行步驟360，以依據天然氣注入量對焦爐氣注入量關係式，來求得天然氣輸入量對焦爐氣儲槽槽位變化關係式。具體而言，在已知焦爐氣儲槽在滿槽時的容量為60000NM3的前提下，線上工作人員可量測每小時注入焦爐氣儲槽的焦爐氣體積，來推測每分鐘焦爐氣儲槽因焦爐氣注入而產生的槽位變化，故藉由天然氣注入量對焦爐氣注入量關係式，可輕易求出天然氣注入量對焦爐氣儲槽槽位變化關係式。在一些例子中，天然氣輸入量對焦爐氣儲槽槽位變化關係式是： Y1=0.000051X2， 其中Y1是每分鐘之焦爐氣儲槽槽位變化百分比，X2是每分鐘之天然氣注入量。 When analyzing the natural gas input amount and the coke furnace gas storage tank slot position, the last step is to perform step 360, so as to obtain the natural gas input amount and the coke furnace gas storage tank slot position change relationship based on the natural gas injection amount and the coke furnace gas injection amount relationship. Specifically, under the premise that the capacity of the coke furnace gas storage tank is known to be 60000NM3 when the tank is full, the online staff can measure the volume of coke furnace gas injected into the coke furnace gas storage tank per hour to estimate the slot position change of the coke furnace gas storage tank caused by the coke furnace gas injection per minute. Therefore, through the natural gas injection amount and the coke furnace gas injection amount relationship, the natural gas injection amount and the coke furnace gas storage tank slot position change relationship can be easily obtained. In some examples, the relationship between natural gas input and coke furnace gas storage tank position change is: Y1 = 0.000051X2, where Y1 is the coke furnace gas storage tank position change percentage per minute, and X2 is the natural gas injection volume per minute.
請再參照圖1，進行預測焦爐氣儲槽槽位的方法100時，接著可進行步驟400，以依據焦爐氣壓力對焦爐氣儲槽槽位變化關係、天然氣輸入量對焦爐氣儲槽槽位變化關係、天然氣輸入量、預設時間區段前之焦爐氣壓力、當前焦爐氣儲槽槽位，來進行天然氣注入後焦爐氣儲槽槽位變化預測分析，並預測下一分鐘之焦爐氣儲槽槽位。具體而言，在得到焦爐氣壓力對焦爐氣儲槽槽位變化關係式以及天然氣輸入量對焦爐氣儲槽槽位變化關係式後，線上工作人員可透過機器學習等方式，依據焦爐氣壓力對焦爐氣儲槽槽位變化關係式以及天然氣輸入量對焦爐氣儲槽槽位變化關係式建置預測模型，並將天然氣輸入量、預設時間區段(例如，3分鐘)前之焦爐氣壓力、當前焦爐氣儲槽槽位輸入建置好的模型中，以預測下一分鐘之焦爐氣儲槽槽位變化，進而求得下一分鐘之焦爐氣儲槽槽位。Please refer to FIG. 1 again. When the method 100 for predicting the position of the coke furnace gas storage tank is performed, step 400 may be performed next to predict and analyze the position change of the coke furnace gas storage tank after natural gas injection based on the relationship between the coke furnace gas pressure and the position of the coke furnace gas storage tank, the relationship between the natural gas input and the position of the coke furnace gas storage tank, the natural gas input, the coke furnace gas pressure before a preset time period, and the current position of the coke furnace gas storage tank, and predict the position of the coke furnace gas storage tank in the next minute. Specifically, after obtaining the relationship between the coke furnace gas pressure and the coke furnace gas storage tank position change relationship and the natural gas input amount and the coke furnace gas storage tank position change relationship, online workers can use machine learning and other methods to build a prediction model based on the relationship between the coke furnace gas pressure and the coke furnace gas storage tank position change relationship and the natural gas input amount and the coke furnace gas storage tank position change relationship, and input the natural gas input amount, the coke furnace gas pressure before a preset time period (for example, 3 minutes), and the current coke furnace gas storage tank position into the built model to predict the coke furnace gas storage tank position change in the next minute, and then obtain the coke furnace gas storage tank position in the next minute.
進行預測焦爐氣儲槽槽位的方法100時，在完成步驟400後，接下來可步驟500，重複進行天然氣注入後焦爐氣儲槽槽位變化預測分析，來預測當前焦爐氣儲槽槽位的長期變化。具體而言，在利用步驟400取得下一分鐘之焦爐氣儲槽槽位後，線上工作人員可將下一分鐘之焦爐氣儲槽槽位以及其他參數再度代入模型中，以求出2分鐘後的焦爐氣儲槽槽位。以此類推，即可預測當前焦爐氣儲槽槽位的長期(例如，1小時)變化。When performing the method 100 for predicting the position of the coke furnace gas storage tank, after completing step 400, the next step may be step 500 to repeat the prediction analysis of the position change of the coke furnace gas storage tank after natural gas injection to predict the long-term change of the current coke furnace gas storage tank position. Specifically, after obtaining the position of the coke furnace gas storage tank in the next minute by using step 400, the online staff can substitute the position of the coke furnace gas storage tank in the next minute and other parameters into the model again to obtain the position of the coke furnace gas storage tank in 2 minutes. By analogy, the long-term (for example, 1 hour) change of the current coke furnace gas storage tank position can be predicted.
由上述本揭露實施方式可知，本揭露主要是透過迴歸分析分別取得焦爐氣壓力對焦爐氣儲槽槽位變化關係式以及天然氣輸入量對焦爐氣儲槽槽位變化關係式，再結合焦爐氣壓力對焦爐氣儲槽槽位變化關係式以及天然氣輸入量對焦爐氣儲槽槽位變化關係式，來預測天然氣注入後焦爐氣儲槽槽位的長期變化。本揭露之預測焦爐氣儲槽槽位的方法在預測上具有高度的準確性，且能即時呈現預測結果給線上工作人員，故可有效避免焦爐氣儲槽槽位過低而發生各工廠設備跳機的情況。另外，天然氣輸入量對焦爐氣儲槽槽位分析還包含資料清洗作業，以移除無效資料以及低關聯性資料，進而提升分析的準確性。As can be seen from the above-mentioned implementation method of the present disclosure, the present disclosure mainly obtains the relationship between the coke furnace gas pressure and the coke furnace gas storage tank position change relationship and the natural gas input and the coke furnace gas storage tank position change relationship through regression analysis, and then combines the relationship between the coke furnace gas pressure and the coke furnace gas storage tank position change relationship and the natural gas input and the coke furnace gas storage tank position change relationship to predict the long-term change of the coke furnace gas storage tank position after natural gas injection. The method for predicting the coke furnace gas storage tank position disclosed in the present disclosure has a high degree of accuracy in prediction, and can present the prediction results to the online staff in real time, so it can effectively avoid the situation where the coke furnace gas storage tank position is too low and the equipment of each factory trips. In addition, the analysis of natural gas input on coke furnace gas storage tank locations also includes data cleaning operations to remove invalid data and low-relevance data, thereby improving the accuracy of the analysis.
雖然本揭露已以實施例揭露如上，然其並非用以限定本揭露，任何所屬技術領域中具有通常知識者，在不脫離本揭露的精神和範圍內，當可作些許的更動與潤飾，故本揭露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 disclosure has been disclosed as above by way of embodiments, it is not intended to limit the present disclosure. Any person having ordinary knowledge in the relevant technical field may make some changes and modifications without departing from the spirit and scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the definition of the attached patent application scope.
100:方法 200:步驟 210:步驟 220:步驟 230:步驟 300:步驟 310:步驟 320:步驟 330:步驟 340:步驟 350:步驟 360:步驟 400:步驟 500:步驟 100:Method 200:Step 210:Step 220:Step 230:Step 300:Step 310:Step 320:Step 330:Step 340:Step 350:Step 360:Step 400:Step 500:Step
為讓本發明之上述和其他目的、特徵、優點與實施例能更明顯易懂，所附圖式之詳細說明如下： 圖1係繪示依照本揭露之一些實施方式之預測焦爐氣儲槽槽位的方法的流程圖； 圖2係繪示依照本揭露之一些實施方式之焦爐氣壓力對焦爐氣儲槽槽位分析的流程圖；以及 圖3係繪示依照本揭露之一些實施方式之天然氣輸入量對焦爐氣儲槽槽位分析的流程圖。 In order to make the above and other purposes, features, advantages and embodiments of the present invention more clearly understandable, the attached figures are described in detail as follows: FIG. 1 is a flow chart showing a method for predicting the position of a coke furnace gas storage tank according to some embodiments of the present disclosure; FIG. 2 is a flow chart showing the analysis of the position of a coke furnace gas storage tank by coke furnace gas pressure according to some embodiments of the present disclosure; and FIG. 3 is a flow chart showing the analysis of the position of a coke furnace gas storage tank by natural gas input according to some embodiments of the present disclosure.
國內寄存資訊(請依寄存機構、日期、號碼順序註記) 無 國外寄存資訊(請依寄存國家、機構、日期、號碼順序註記) 無 Domestic storage information (please note in the order of storage institution, date, and number) None Foreign storage information (please note in the order of storage country, institution, date, and number) None
100:方法 100:Methods
200:步驟 200: Steps
300:步驟 300: Steps
400:步驟 400:Steps
500:步驟 500: Steps
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW111145834A TWI819911B (en) | 2022-11-30 | 2022-11-30 | Method for predicting gas level of coke oven gas reservoir |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW111145834A TWI819911B (en) | 2022-11-30 | 2022-11-30 | Method for predicting gas level of coke oven gas reservoir |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| TWI819911B TWI819911B (en) | 2023-10-21 |
| TW202424168A true TW202424168A (en) | 2024-06-16 |
Family
ID=89858070
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| TW111145834A TWI819911B (en) | 2022-11-30 | 2022-11-30 | Method for predicting gas level of coke oven gas reservoir |
Country Status (1)
| Country | Link |
|---|---|
| TW (1) | TWI819911B (en) |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4357484B2 (en) * | 2003-10-30 | 2009-11-04 | カウンシル オブ サイエンティフィク アンド インダストリアル リサーチ | A method for predicting the amount of gas produced during coal gasification. |
| CN102566436A (en) * | 2010-12-10 | 2012-07-11 | 沈阳中科博微自动化技术有限公司 | Control system special for gasification furnace |
| TWI737993B (en) * | 2019-05-14 | 2021-09-01 | 中國鋼鐵股份有限公司 | Prediction method of converter gas output |
-
2022
- 2022-11-30 TW TW111145834A patent/TWI819911B/en active
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109214601A (en) | Household electric appliances big data Method for Sales Forecast method | |
| US10090678B2 (en) | Production energy management system and computer program | |
| CN104036357B (en) | The analysis method of user power utilization electricity stealing pattern | |
| Garratt et al. | Real-time representations of the output gap | |
| JP7053152B2 (en) | Systems and methods for optimizing recommended inspection intervals | |
| CN102968529B (en) | Method for quantifying computed result non-determinacy interval of water supply pipe network model | |
| CN105205570A (en) | Power grid power sale quantity prediction method based on season time sequence analysis | |
| JP2017151980A5 (en) | ||
| CN112131685B (en) | Uncertainty evaluation method for overall thermodynamic performance test of combined cycle unit | |
| CN101673096B (en) | Soft-measuring method for density in concentration process of salvia miltiorrhiza injection production | |
| JP2015090641A (en) | Pipe line renewal planning support system and pipe line renewal planning support method | |
| Oberoi et al. | SPC (statistical process control): a quality control technique for confirmation to ability of process | |
| CN115147012A (en) | Carbon emission accounting method and device based on neural network model | |
| TWI819911B (en) | Method for predicting gas level of coke oven gas reservoir | |
| TW202424168A (en) | Method for predicting gas level of coke oven gas reservoir | |
| CN103177392A (en) | Correlation method in steel coil length process | |
| CN117591679A (en) | Intelligent analysis system and method for carbon footprint of building block type product based on knowledge graph | |
| JP2013250958A (en) | Operational status diagnosis device for diagnosing operational status of apparatus and equipment, operational status diagnosis method, and operational status diagnosis program | |
| KR102124168B1 (en) | method for selecting optimal location of water pressure gauge for leakage detection in water supply networks | |
| CN111444478A (en) | Comprehensive plant power consumption rate statistical method | |
| Jalilov et al. | Development of energy characteristics of electric drives of technological equipment and normalization of electric consumption of fat-and-oil enterprise | |
| CN106651462A (en) | Evaluation method for second-hand device | |
| CN107798209A (en) | Method and device for calculating pump detection period reference value of oil pumping unit well | |
| CN112926821A (en) | Method for predicting wafer yield based on process capability index | |
| Xia et al. | Reliability evaluation for the running state of the manufacturing system based on poor information |