Abnormality diagnosis method for sintering machine ignition furnace and abnormality diagnosis device for sintering machine ignition furnace

Abstract

To provide an abnormality diagnostic method of a sintering machine ignition furnace and an abnormality diagnostic device of the sintering machine ignition furnace, capable of detecting abnormality of piping equipment of a burner by a simple prediction model, without installing a pressure gauge in respective branch pipes for supplying combustion gas to the burner.SOLUTION: An abnormality diagnosis method of a sintering machine ignition furnace includes an acquisition step of acquiring respective measurement values of an opening degree of a flow rate adjustment valve of each branch pipe for supplying combustion gas to each burner of an ignition furnace, a flow rate of each branch pipe, a flow rate of a main pipe connected to each branch pipe, and a pressure of the main pipe, an abnormality diagnosis step of extracting a candidate of abnormality of equipment including a pressure gauge, a flow meter, and a flow rate adjustment valve provided in the main pipe and each branch pipe using a combustion gas matching evaluation model for evaluating consistency of the flow rate of the main pipe and the flow rate of each branch pipe, and a flow rate adjustment valve opening degree prediction model for predicting the opening degree of the flow rate adjustment valve of each branch pipe based on the result of the abnormality diagnosis step.SELECTED DRAWING: Figure 5

Description

[Technical Field]

[0001] The present invention relates to an abnormality diagnosis method and an abnormality diagnosis device for an ignition furnace of a sintering machine. [Background technology]

[0002] Facilities within plants, including steelworks, include numerous piping systems that supply combustion gas (hereinafter referred to as "combustion gas") and air (hereinafter referred to as "combustion air") to combustion burners used in the heating equipment of continuous annealing furnaces, ignition burners for sintering raw materials in sintering manufacturing facilities, and the like.

[0003] For example, Patent Document 1 discloses a technology for determining the PQ characteristic value for each burner installed in a continuous annealing furnace for steel strips from the relationship between the burner inlet pressure P and flow rate Q of the combustion gas and combustion air, and determining that an abnormality has occurred if the emissivity ε and the PQ characteristic value exceed set values. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2004-091901 Summary of the Invention [Problem to be solved by the invention]

[0005] The technology of Patent Document 1 requires the measurement of the pressure in front of the burner using a pressure gauge in addition to the flow rate of the combustion gas from each burner. Therefore, there is an issue that it is difficult to apply in cases where individual pressure gauges cannot be installed due to factors such as manufacturing costs and maintainability.

[0006] The present invention has been made in consideration of the above, and aims to provide an abnormality diagnosis method and an abnormality diagnosis device for a sintering machine ignition furnace that can detect abnormalities in the piping equipment of a burner using a simple prediction model, without installing a pressure gauge in each branch pipe that supplies combustion gas to the burner. [Means for solving the problem]

[0007] In order to solve the above-mentioned problems and achieve the object, the abnormality diagnosis method for an ignition furnace of a sintering machine according to the present invention includes: an acquisition step of acquiring measured values ​​of the aperture of a flow control valve of each branch pipe that supplies combustion gas to each burner of the ignition furnace, the flow rate of each branch pipe, the flow rate of a main pipe connected to each branch pipe, and the pressure of the main pipe; an abnormality diagnosis step of extracting candidates for abnormality in equipment including a pressure gauge, a flow meter, and a flow control valve provided on the main pipe and each branch pipe using a combustion gas consistency evaluation model that evaluates the consistency of the flow rate of the main pipe and the flow rate of each branch pipe, and a flow control valve aperture prediction model that predicts the aperture of the flow control valve of each branch pipe based on the pressure of the main pipe and the flow rate of each branch pipe; and a presentation step of presenting the candidates for abnormality based on the results of the abnormality diagnosis step.

[0008] Furthermore, in the method for diagnosing an abnormality in an ignition furnace of a sintering machine according to the present invention, in the above invention, the combustion gas consistency evaluation model is a model for evaluating the balance between the flow rate of the main pipe and the flow rate of each of the branch pipes, and the flow control valve aperture prediction model is a model for predicting the aperture of the flow control valve of each of the branch pipes using a value obtained by dividing the square of the flow rate of each of the branch pipes by the pressure of the main pipe as an explanatory variable, and the abnormality diagnosis step uses the combustion gas consistency evaluation model to identify an abnormal flow meter and a normal flow meter based on the flow rate under normal conditions, and uses the flow control valve aperture prediction model to predict the aperture of the flow control valve of the branch pipe in which a normal flow meter is installed, and identifies an abnormality in the equipment or the branch pipe based on the magnitude of the prediction error in the aperture of the flow control valve.

[0009] In order to solve the above-mentioned problems and achieve the object, the abnormality diagnosis device for a sintering machine ignition furnace according to the present invention comprises: an acquisition unit that acquires measured values ​​of the aperture of the flow control valve of each branch pipe that supplies combustion gas to each burner of the ignition furnace, the flow rate of each branch pipe, the flow rate of a main pipe connected to each branch pipe, and the pressure of the main pipe; an abnormality diagnosis unit that extracts candidates for abnormality in equipment including pressure gauges, flow meters, and flow control valves provided on the main pipe and each branch pipe using a combustion gas consistency evaluation model that evaluates the consistency of the flow rate of the main pipe and the flow rate of each branch pipe; and a flow control valve aperture prediction model that predicts the aperture of the flow control valve of each branch pipe based on the pressure of the main pipe and the flow rate of each branch pipe; and a presentation unit that presents the candidates for abnormality based on the results of the abnormality diagnosis unit. [Effects of the Invention]

[0010] According to the sintering machine ignition furnace abnormality diagnosis method and sintering machine ignition furnace abnormality diagnosis device of the present invention, abnormalities in piping equipment such as burner ignition equipment can be detected early using a simple prediction model. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram showing an outline of a manufacturing facility for sintered ore, which is a raw material to be charged into a blast furnace in a steelworks. [Figure 2] FIG. 2 is a diagram showing an outline of the piping and burners connected to the ignition furnace. [Figure 3] FIG. 3 is a diagram showing an outline of the piping for combustion gas and combustion air connected to the ignition furnace, and the instruments and valves provided in the piping routes. [Figure 4] FIG. 4 is a block diagram showing an example of the configuration of an abnormality diagnosis device for an ignition furnace of a sintering machine according to the embodiment. [Figure 5] FIG. 5 is a flowchart showing an example of the flow of an abnormality diagnosis method executed by the abnormality diagnosis device for an ignition furnace of a sintering machine according to the embodiment. [Figure 6] FIG. 6 is a graph showing the relationship between the flow rate of the main gas pipe and the sum of the flow rates of the branch gas pipes. [Figure 7]FIG. 7 is an example of the method for diagnosing an abnormality in an ignition furnace of a sintering machine according to the embodiment, and is a graph showing the relationship between the actual value (after normalization) of the flow regulation valve opening and “Qi 2 / P0” calculated from the actual value. DETAILED DESCRIPTION OF THE INVENTION

[0012] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS A method and an apparatus for diagnosing an abnormality in an ignition furnace of a sintering machine according to an embodiment of the present invention will be described with reference to the drawings.

[0013] (Sintered ore manufacturing equipment) An overview of a sintering facility to which an abnormality diagnosis device for a sintering machine ignition furnace according to an embodiment is applied will be described with reference to Figures 1 to 3. Figure 1 shows an overview of a manufacturing facility for sintered ore, which is a raw material to be charged into a blast furnace in a steelworks.

[0014] As shown in Fig. 1, the sintered ore manufacturing facility includes a blending tank 21, a drum mixer 22, a sintering machine 23, an ignition furnace 24, an electrostatic precipitator (EP) 25, a blower 26, a crusher 27, and a sieve 28. Sintered ore is a raw material for iron making that is produced by mixing powdered iron ore with auxiliary materials such as coke and limestone, then causing a sintering reaction in the sintering machine 23 to burn and harden the mixture, and then crushing it in the crusher 27. The sintered ore produced in the manufacturing facility is charged into a blast furnace 29.

[0015] The ignition furnace 24 in the sintering facility is a facility for igniting the coke in the raw materials sent out onto the pallet cart of the sintering machine 23. As shown in Fig. 2, inside the ignition furnace 24, a plurality of branch gas pipes 242 branching off from a main gas pipe 241 for combustion gas and a plurality of branch air pipes 244 branching off from a main air pipe 243 for combustion air are laid to the respective burners 245. The combustion gas here is, for example, C gas supplied from a coke plant.

[0016] FIG. 3 shows an outline of the piping for combustion gas and combustion air connected to the ignition furnace 24, and the instruments and valves provided in the piping routes.

[0017] The gas main 241 is connected to a plurality of branch gas pipes 242 and supplies combustion gas to each branch gas pipe 242. The gas main 241 is provided with a gas main pressure gauge 31, a gas main flow meter 32, a gas main diffusion valve 33, and a gas main shutoff valve 34.

[0018] The branch gas pipe 242 supplies combustion gas to the burner 245 of the ignition furnace 24. The branch gas pipe 242 is provided with a branch gas pipe shutoff valve 35, a branch gas pipe flow regulation valve (flow rate adjustment valve) 36, and a branch gas pipe flow meter 37. Note that, although four branch gas pipes 242 branch from the main gas pipe 241 in FIG. 3, the number of branch gas pipes 242 is not particularly limited. Furthermore, no pressure gauge is provided on the branch gas pipe 242.

[0019] The main air pipe 243 is connected to a plurality of branch air pipes 244, and supplies combustion air to each branch air pipe 244. The main air pipe 243 is provided with a main air flow meter 40.

[0020] The air branch pipe 244 supplies combustion air to the burner 245 of the ignition furnace 24. The air branch pipe 244 is provided with an air branch pipe flow meter 38 and an air branch pipe flow adjustment valve (flow rate control valve) 39. Note that, although four air branch pipes 244 are branched from the main air pipe 243 in FIG. 3, the number of air branch pipes 244 is not particularly limited.

[0021] (Abnormality diagnosis device) An abnormality diagnosis device for a sintering machine ignition furnace according to an embodiment (hereinafter simply referred to as "abnormality diagnosis device") will be described with reference to Fig. 4. The abnormality diagnosis device diagnoses abnormalities in equipment that branches combustion gas and combustion air from a main pipe to each burner and provides them through each branch pipe.

[0022] In this embodiment, a case will be described in which an abnormality is diagnosed in equipment that supplies combustion gas (such as a gas branch pipe 242, a gas main pressure meter 31, a gas branch pipe flow meter 37, and a gas branch pipe flow adjustment valve 36) for the ignition furnace 24 in a sintering facility. The abnormality diagnosis device is not limited to piping equipment that supplies combustion gas, but can also diagnose abnormalities in piping equipment that supplies combustion air (such as an air branch pipe 244, an air branch pipe flow meter 38, and an air branch pipe flow adjustment valve 39). In this case, similar to the gas main pipe 241, a pressure meter and a flow meter are also provided in the air main pipe 243, and abnormality diagnosis is performed.

[0023] The abnormality diagnosis device 1 is realized by an information processing device such as a general-purpose computer such as a workstation or a personal computer, or a server located on a cloud. As shown in FIG. 4, the abnormality diagnosis device 1 includes an acquisition unit 11, an abnormality diagnosis unit 12, and a presentation unit 13.

[0024] The acquisition unit 11 acquires information on the opening degree of the branch gas pipe flow adjustment valve 36 (hereinafter also referred to as "flow adjustment valve opening degree") from the branch gas pipe flow adjustment valve 36 provided in each branch gas pipe 242. The acquisition unit 11 also acquires a measurement value of the flow rate of the combustion gas flowing through the branch gas pipe 242 from the branch gas pipe flow meter 37 provided in each branch gas pipe 242. The acquisition unit 11 also acquires a measurement value of the flow rate of the combustion gas flowing through the main gas pipe 241 from the main gas pipe flow meter 32 provided in the main gas pipe 241. The acquisition unit 11 also acquires a measurement value of the pressure of the combustion gas flowing through the main gas pipe 241 from the main gas pipe pressure meter 31 provided in the main gas pipe 241.

[0025] The abnormality diagnosis unit 12 uses a combustion gas consistency evaluation model and a flow control valve opening prediction model to extract candidates for abnormality in equipment including, for example, a gas main pressure gauge 31, a gas main flow meter 32, a gas branch pipe flow control valve 36, a gas branch pipe flow meter 37, etc.

[0026] Specifically, the abnormality diagnosis unit 12 uses a combustion gas consistency evaluation model to identify abnormal and normal branch gas pipe flow meters 37 among the multiple branch gas pipe flow meters 37, based on the combustion gas flow rate during normal operation. Furthermore, specifically, the abnormality diagnosis unit 12 uses a flow regulation valve opening prediction model to predict the opening of the branch gas pipe flow meter 37 of the branch gas pipe 242 in which a normal branch gas pipe flow meter 37 is installed, and identifies an abnormality in the equipment or the branch gas pipe 242 based on the magnitude of the prediction error in the opening of the branch gas pipe flow meter 37. Details of the combustion gas consistency evaluation model and the flow regulation valve opening prediction model will be described later.

[0027] The presentation unit 13 presents equipment that is a suspected abnormality based on the diagnosis results of the abnormality diagnosis unit 12, and the presentation unit 13 alerts operators, etc. by presenting the information on a display device such as an external display connected to the abnormality diagnosis device 1.

[0028] (Combustion gas consistency evaluation model) The combustion gas consistency evaluation model is a model that evaluates the consistency between the flow rate of the main gas pipe 241 and the flow rate of each branch gas pipe 242. Specifically, the combustion gas consistency evaluation model is a model that evaluates the balance between the flow rate of the main gas pipe 241 and the flow rate of each branch gas pipe 242.

[0029] The combustion gas matching evaluation model is a combustion gas flow rate balance evaluation formula that uses the conservation law between the flow rate of the main gas pipe 241 and the flow rate of each branch gas pipe 242, as shown in the following formula (1), for example.

[0030]

number

[0031] In the above equation (1), Eq is the flow rate prediction error, Q is the flow rate of the combustion gas in the gas main 241, and Q i is the flow rate of the combustion gas in the branch gas pipe 242, and i is a variable (natural number) corresponding to each branch gas pipe 242. The flow rate Q of the main gas pipe 241 is iTherefore, the flow rate prediction error Eq is defined as an equation for evaluating the balance of the flow rate of combustion gas, such as the above equation (1).

[0032] (Flow regulation valve opening prediction model) The flow regulation valve opening prediction model is a model that predicts the opening of the branch gas pipe flow regulation valve 36 based on the pressure of the main gas pipe 241 and the flow rate of each branch gas pipe 242. Specifically, the flow regulation valve opening prediction model is a model that predicts the opening of each branch gas pipe flow regulation valve 36 using the value obtained by dividing the square of the flow rate of each branch gas pipe 242 by the pressure of the main gas pipe 241 as an explanatory variable.

[0033] Differential pressure flow meters may be used as the main gas pipe flow meter 32 and the branch gas pipe flow meter 37. A differential pressure flow meter measures the flow rate by installing an orifice in a flow path to generate a pressure loss and detecting the pressure difference before and after the orifice. In this embodiment, combustion gas is supplied to multiple branch gas pipes 242 branching from a main gas pipe 241, and the combustion gas, whose flow rate is adjusted by branch gas pipe flow adjustment valves 36 installed in each branch gas pipe 242, is supplied to each burner 245.

[0034] Here, if it is considered that each gas branch pipe flow regulation valve 36 functions as a kind of orifice, the pressure difference ΔP between before and after the gas branch pipe flow regulation valve 36 of the gas branch pipe 242 is i If this is known, the flow rate Q of the gas branch pipe 242 on the burner 245 side can be calculated. i It is believed that this can be predicted by the following formula (2).

[0035]

number

[0036] In the above formula (2), Q i is the flow rate of the gas branch pipe 242 on the burner 245 side, C is the adjustment coefficient, A i is the opening area of ​​the gas branch pipe flow control valve 36, ΔP i is the pressure difference between the upstream and downstream of the branch gas pipe flow regulation valve 36 of the branch gas pipe 242. Also, in the above formula (2), P i 0is the pressure on the gas main 241 side of the gas branch pipe flow regulating valve 36, P i b is the pressure on the burner 245 side of the gas branch pipe flow regulating valve 36.

[0037] On the other hand, in the ignition furnace 24 of the sintering equipment, a pressure gauge is not installed in each gas branch pipe 242 from the viewpoint of manufacturing cost and maintainability. Therefore, the flow rate Q i It becomes difficult to estimate.

[0038] Here, the pressure P i 0 ,P i b However, the opening degree of the gas branch pipe flow regulation valve 36 provided in each gas branch pipe 242 (flow regulation valve opening degree d i ) can be obtained. Therefore, the inventors have used a flow regulation valve opening prediction model to obtain the pressure P i 0 ,P i b We thought that by predicting the flow regulation valve opening from other measured values ​​and evaluating the prediction error between the predicted value and the actual measured value, it would be possible to detect blockages in the pipes or malfunctions in the flow regulation valve itself.

[0039] Opening area A of gas branch pipe flow control valve 36 i is the total opening area A0 of the gas branch pipe flow regulation valve 36 and the flow regulation valve opening d i Using "A i =d i A0”. Therefore, the above formula (2) can be transformed into the following formulas (3) to (5).

[0040]

number

number

number

[0041] Here, in the above formula (5), "ρ / (2C 2 A0 2 ) is a constant, so d i 2 and "Q i 2 / P i 2 " is assumed to have a correlation. i 0 is the pressure on the gas main 241 side of the gas branch pipe flow regulating valve 36, so if the pressure of the gas main 241 is P0, then P i 0 and P0 are correlated. Therefore, d i 2 and "Q i / P0" is thought to be correlated with this.

[0042] In addition, "1 / 1-(P i b / P i 0 )" item, the supply of combustion gas is sufficient, and the pressure on the burner 245 side of each gas branch pipe 242 is close to atmospheric pressure, and "P i b ≪P i 0 " is used in the situation, so it is considered to be essentially 1. Therefore, "1 / 1-(P i b / P i 0 )" and d i 2 The correlation with

[0043] Furthermore, the flow regulation valve opening d i It is considered that the flow regulation valve operates at an opening of Δd relative to the opening d0 during normal operation. i = d0 + Δd, and d i 2 If it can be approximated by the following equation (6), the correlation shown in the following equation (7) can be expected in the operation around steady operation.

[0044]

number

number

[0045] Also, the flow control valve opening d i to "Q i 2 Considering the modeling of estimating the flow regulation valve opening using a linear equation of " / P0", the predicted value of i When expressed as ^, the flow regulation valve opening prediction model can be expressed as in the following equation (8): In the following equation (8), a and b are coefficients.

[0046]

number

[0047] Although the above equation (8) is approximated by a linear equation, the flow control valve opening prediction model may be constructed as shown in the following equation (9) by using other polynomial models or machine learning models and providing an appropriate function F(·).

[0048]

number

[0049] A flow control valve aperture prediction model is constructed and prepared in advance for each gas branch pipe 242. Furthermore, it is preferable to train the flow control valve aperture prediction model using operational data that includes not only the steady-state production speed of the sinter machine 23 in a normal state, but also the production speeds during increased and decreased production. It is believed that the production speed during increased and decreased production varies by approximately ±20% of the steady-state production speed. Therefore, it is preferable to determine the range of flow control valve aperture during steady-state operation from the past performance of the flow control valve aperture corresponding to changes in production speed, and then determine the range of data to be used for training the flow control valve aperture prediction model by determining the range that includes this range and where linearity is established. The verification results of the operational data used for training the flow control valve aperture prediction model will be described later (see Figure 7).

[0050] (Abnormality diagnosis method) Details of the abnormality diagnosis method executed by the abnormality diagnosis device for a sintering machine ignition furnace according to the embodiment will be described with reference to Figures 5 and 6. The abnormality diagnosis method includes an acquisition step (step S1), an abnormality diagnosis step (steps S2 to S8), and a presentation step (step S9).

[0051] First, the acquisition unit 11 acquires the measurement values ​​of the opening of each branch gas pipe flow regulating valve 36, the flow rate of each branch gas pipe 242, the flow rate of the main gas pipe 241, and the pressure of the main gas pipe 241 (step S1). Next, the abnormality diagnosis unit 12 evaluates the balance of the flow rates of the main gas pipe 241 and each branch gas pipe 242 using the combustion gas consistency evaluation model shown in the above formula (1) (step S2), and determines whether or not there is an abnormality in the main gas pipe flow meter 32 or the branch gas pipe flow meter 37 (step S3).

[0052] Here, Eq in the above formula (1) represents the flow rate prediction error. Therefore, in step S3, if the absolute value of this flow rate prediction error Eq exceeds a predetermined threshold, it is determined that there is an abnormality in the main gas pipe flow meter 32 or one of the branch gas pipe flow meters 37. The above threshold is determined to be an appropriate value from a threshold such as 2σ or 3σ by calculating the standard deviation σ of the flow rate prediction error Eq using, for example, the actual flow rates of the main gas pipe 241 and each branch gas pipe 242 under normal conditions.

[0053] Fig. 6 is a scatter diagram illustrating the above relationship, with the vertical axis representing the flow rate (actual value) of the main gas pipe 241 and the horizontal axis representing the sum (actual value) of the flow rates of the branch gas pipes 242. The area surrounded by the dashed line in Fig. 6 is the normal detection range. In step S3, the presence or absence of an abnormality may be determined based on the flow rate prediction error Eq of the above equation (1), or the presence or absence of an abnormality may be determined based on the distance d illustrated in Fig. 6.

[0054] If it is determined in step S3 that an abnormality exists (Yes in step S3), the abnormality diagnosis unit 12 identifies the abnormal main gas flow meter 32 or branch gas flow meter 37 (step S4). Identifying the abnormality in step S4 can be performed, for example, by focusing on the values ​​of the main gas flow meter 32 and branch gas flow meter 37 that significantly deviate from the normal flow rates of the main gas pipe 241 and branch gas pipe 242. In this case, for example, the main gas flow meter 32 or branch gas flow meter 37 that significantly deviates from the normal flow rate value can be identified as the abnormal location. Alternatively, the deviation amount of the flow rate prediction error Eq may be evaluated using an average value over a predetermined period, and compared with the average value of the prediction error for each branch gas pipe 242 over the same predetermined period. If there is a prediction error for the branch gas pipe 242 that shows a similar value, the branch gas flow meter 37 showing that value may be identified as the abnormal location. Next, the abnormality diagnosis unit 12 identifies the flow meters other than the flow meter identified as having an abnormality in step S4 as normal flow meters (step S5).

[0055] Next, the abnormality diagnosis unit 12 uses the flow control valve opening prediction model shown in the above equation (8) or (9) to evaluate the prediction error of the flow control valve opening of each gas branch pipe 242 (step S6) and determines whether there is an abnormality in the equipment or the gas branch pipe 242 (step S7).

[0056] Here, if it is determined in step S3 that there is no abnormality in the flow rate of all the branch gas pipes 242 (No in step S3), the processing from step S6 onwards is performed on all the branch gas pipes 242. Furthermore, if it is determined in step S3 that there is an abnormality in the flow rate of any of the branch gas pipes 242 (Yes in step S3), the processing from step S6 onwards is also performed on the branch gas pipe 242 corresponding to the branch gas pipe flowmeter 37 identified as a normal flowmeter in step S5.

[0057] As described above, the flow control valve opening degree d of each gas branch pipe 242 i can be obtained from the gas branch pipe flow regulation valve 36. Therefore, in step S4, the flow regulation valve opening degree d i The prediction error err_d is the difference between the actual value and the estimated value of the flow regulation valve opening calculated by the flow regulation valve opening prediction model.i In the following formula (10), the above formula (8) is used as the flow regulation valve opening prediction model, but the above formula (9) may also be used.

[0058]

number

[0059] This prediction error err_d i If the value of the flow rate prediction falls outside the normal range, there is a possibility that an abnormality has occurred somewhere in the relationship between the flow rate prediction and the flow regulation valve opening. In this case, the abnormality diagnosis unit 12 determines that an abnormality has occurred in the equipment or the gas branch pipe 242 (Yes in step S7), and extracts abnormality candidates (step S8).

[0060] Examples of abnormality candidates extracted in step S8 include the following: (1) Abnormality of gas main pressure gauge 31 For example, if all of the prediction errors of the flow control valve opening shown in the above equation (10) are judged to be abnormal, it is highly likely that the value (P0) of the main pipe pressure gauge 31, which is a common input of equation (10), is abnormal. (2) Abnormality in the gas main flow meter 32 or the gas branch flow meter 37 As described above, in steps S3 and S4, there may be a case where it is possible to determine that there is an abnormality in the balance between the flow rate of the main gas pipe 241 and the flow rate of each branch gas pipe 242, and that there is an abnormality in one of the flow meters. (3) Abnormal opening of the gas branch pipe flow control valve 36, or clogging or leakage of the gas branch pipe 242 If the prediction error of the above formula (10) for a specific flow regulation valve greatly exceeds the threshold, it means that there is an abnormality in either the target flow regulation valve opening or the predicted value. In this case, it is assumed that there is no abnormality in the target flow meter and no abnormality in the pressure of the gas main 241, so it is estimated that the flow regulation valve opening is showing an abnormal value, or that due to a leak or blockage in the piping, the flow meter measurement value is correct but the prediction of the flow regulation valve opening is incorrect.

[0061] Next, the presentation unit 13 presents equipment that is a candidate for an abnormality to the operator or the like via a display device or the like based on the diagnosis result of the abnormality diagnosis unit 12 (step S9). Also, in step S9, the main gas pipe flow meter 32 or branch gas pipe flow meter 37 identified as an abnormal flow meter in step S4 is also presented to the operator or the like via a display device or the like. This completes the present flow.

[0062] In addition, in step S7, if it is determined that there is no abnormality in the equipment or the gas branch pipe 242 (No in step S7), the abnormality diagnosis unit 12 completes this flow. In the abnormality diagnosis method for a sinter machine ignition furnace according to the embodiment, the series of processes shown in Fig. 5 are performed periodically or irregularly during operation of the sinter ore manufacturing equipment to diagnose abnormalities in the ignition furnace 24.

[0063] According to the sintering machine ignition furnace abnormality diagnosis method and sintering machine ignition furnace abnormality diagnosis device of the embodiment described above, abnormalities in piping equipment such as burner ignition equipment (see (1) to (3) above) can be detected early using a simple prediction model.

[0064] Furthermore, conventional abnormality diagnosis techniques have not been able to distinguish between abnormalities in the flow meter and abnormalities such as abnormal flow control valve opening or clogged piping. On the other hand, the abnormality diagnosis method and abnormality diagnosis device for a sintering machine ignition furnace according to the embodiment first detects whether or not there is an abnormality in the branch gas pipe flow meter 37 (see steps S2 to S5 in FIG. 5), and then predicts the flow control valve opening for the branch gas pipe 242 that is determined to be normal. This makes it possible to distinguish between abnormalities in the branch gas pipe flow meter 37 and abnormalities such as abnormal flow control valve opening or clogged piping in the branch gas pipe 242. Therefore, the abnormality diagnosis method and abnormality diagnosis device for a sintering machine ignition furnace according to the embodiment can perform more detailed abnormality diagnosis than conventional methods.

[0065] (Example) An example of the method for diagnosing an abnormality in an ignition furnace of a sintering machine according to the embodiment will be described with reference to FIG. 7. In this example, operational data used for learning the flow regulation valve opening prediction model was verified. In FIG. 7, the vertical axis represents the actual value of the flow regulation valve opening (flow regulation valve opening d i ) and the horizontal axis is Q i "Q" calculated from the actual values ​​of (flow rate on the burner 245 side of the gas branch pipe 242) and P0 (pressure of the gas main pipe 241) i 2 The values ​​on the vertical and horizontal axes are expanded and normalized using the upper limit of each range, and evaluated as a percentage of that upper limit.

[0066] In the range shown in part A of Figure 7, the flow control valve opening d i " and "Q i 2 It can be seen that a nearly linear relationship is obtained between the valve opening and the flow rate. Figure 7 shows that there is a lot of data in the vicinity of 55-78% valve opening, especially at 65-75%, which indicates that this is the normal operating range. This figure shows that even when the valve opening is increased and fuel supply is increased during increased sinter production, abnormality diagnosis is possible based on a certain degree of linear relationship. Furthermore, it is believed that the above judgments can be made more accurately by changing the method for determining the threshold value depending on the flow regulation valve opening state. Furthermore, even when the valve opening is reduced to the extent that combustion is stopped, a linear relationship can be predicted up to about 30% valve opening, indicating that this model can be used sufficiently as a predictive model within the normal operating range.

[0067] In this way, the actual value of the flow regulation valve opening and "Q i 2 / P0" has a correlation with Q i By using the operational data of the actual values ​​of P0 and P1, it is possible to construct a flow control valve opening prediction model.

[0068] The sintering machine ignition furnace abnormality diagnosis method and sintering machine ignition furnace abnormality diagnosis device according to the present invention have been specifically described above using the preferred embodiment and examples, but the gist of the present invention is not limited to these descriptions and should be broadly interpreted based on the claims. Furthermore, it goes without saying that various changes and modifications based on these descriptions are also included in the gist of the present invention. [Explanation of symbols]

[0069] 1. Abnormality diagnosis device 11 Acquisition Department 12 Abnormality diagnosis section 13 Presentation part 21 Blending tank 22 Drum Mixer 23 Sintering machine 24 Ignition Furnace 241 Gas Main 242 Gas branch pipe 243 Air Main 244 Air Bronchial Pipe 245 Burner 25 Electrostatic Precipitator (EP) 26 Blower 27 Crusher 28 Sieve 29 Blast Furnace 31 Gas main pressure gauge 32 Gas main flow meter 33 Gas main release valve 34 Gas main shutoff valve 35 Gas branch pipe shutoff valve 36 Gas branch pipe flow control valve 37 Gas branch flowmeter 38 Air branch flow meter 39 Air bronchial flow control valve 40 Air main flow meter

Claims

1. A method for diagnosing an abnormality in an ignition furnace of a sintering machine, which is performed by an abnormality diagnosis device for an ignition furnace of a sintering machine, comprising: an acquisition step of acquiring measurement values ​​of the opening degree of a flow control valve of each branch pipe supplying combustion gas to each burner of the ignition furnace, the flow rate of each branch pipe, the flow rate of a main pipe connected to each branch pipe, and the pressure of the main pipe; an abnormality diagnosis step of extracting candidates for abnormality in equipment including pressure gauges, flow meters, and flow control valves provided in the main pipe and each of the branch pipes, using a combustion gas consistency evaluation model that evaluates the consistency of the flow rate of the main pipe and the flow rate of each of the branch pipes, and a flow control valve opening prediction model that predicts the opening of the flow control valve of each of the branch pipes based on the pressure of the main pipe and the flow rate of each of the branch pipes; a presentation step of presenting the abnormality candidate based on a result of the abnormality diagnosis step; A method for diagnosing abnormalities in an ignition furnace of a sintering machine, comprising:

2. the combustion gas matching evaluation model is a model for evaluating a balance between a flow rate of the main pipe and a flow rate of each of the branch pipes, the flow regulation valve opening prediction model is a model that predicts the opening of the flow regulation valve of each of the branch pipes using a value obtained by dividing the square of the flow rate of each of the branch pipes by the pressure of the main pipe as an explanatory variable, The abnormality diagnosis step includes: Using the combustion gas matching evaluation model, an abnormal flow meter and a normal flow meter are identified based on a flow rate under normal conditions; using the flow regulation valve opening prediction model to predict the opening of a flow regulation valve of a branch pipe in which a normal flow meter is installed, and identifying an abnormality in the facility or the branch pipe based on the magnitude of a prediction error in the opening of the flow regulation valve; The method for diagnosing an abnormality in an ignition furnace of a sintering machine according to claim 1.

3. an acquisition unit that acquires measurement values ​​of the opening degree of a flow control valve of each branch pipe that supplies combustion gas to each burner of the ignition furnace, the flow rate of each branch pipe, the flow rate of a main pipe connected to each branch pipe, and the pressure of the main pipe; an abnormality diagnosis unit that extracts candidates for abnormality in equipment including pressure gauges, flow meters, and flow control valves provided in the main pipe and each of the branch pipes, using a combustion gas consistency evaluation model that evaluates the consistency of the flow rate of the main pipe and the flow rate of each of the branch pipes, and a flow control valve opening prediction model that predicts the opening of the flow control valve of each of the branch pipes based on the pressure of the main pipe and the flow rate of each of the branch pipes; a presentation unit that presents the abnormality candidates based on the results of the abnormality diagnosis unit; An abnormality diagnosis device for a sintering machine ignition furnace.

Images