Deterioration diagnostic device for rolling equipment

Abstract

The deterioration diagnosis device of the rolling equipment machine is provided with an input / output data acquisition part, a model identification part, a monitoring parameter calculation part, a monitoring parameter use judgment part, a representative value calculation part, a representative value storage part and a deterioration diagnosis part. The monitoring parameter usage determination unit has a category-by-category monitoring parameter collection function that collects the monitoring parameters calculated by the monitoring parameter calculation unit for each category specified according to the rolling conditions of the rolled material. The representative value calculation unit calculates a representative value of a set of monitoring parameters for each class in a certain period. The representative value storage unit accumulates, by category, representative values during a specified learning period from the start of monitoring. The deterioration diagnosis unit has a classification-by-classification deterioration determination function for determining the presence or absence of deterioration by classification.

Description

Technical Field

[0001] The present invention relates to a deterioration diagnosis device for rolling equipment that diagnoses deterioration of equipment installed in a rolling line. Background Art

[0002] In a rolling line equipped with various equipment and machines, it is required to detect the deterioration of the equipment and machines in advance (response degradation), prompt the operator to perform maintenance and repair of the equipment and machines, and achieve stabilization of operations and improvement of quality. Therefore, the operation data of the equipment and machines has been collected and accumulated, and research has been conducted on how to flexibly apply it to the early detection of the deterioration of the equipment and machines.

[0003] For example, the following patent document 1 discloses a state abnormality determination device that monitors the state of a robot (equipment machine) and supports the maintenance of the robot. Among them, the monitoring parameters obtained by directly comparing the past normal time series data (data in which the current value flowing in the servo motor is arranged in time series) with the current time series data are summarized on a daily basis and a representative value is obtained. The obtained representative value is compared with the distribution of the monitoring parameters during the specified learning period, thereby determining the degradation of the actuator constituting the servo motor.

[0004] Prior art literature

[0005] Patent Literature

[0006] Patent Document 1: International Publication No. 2022 / 024946 Summary of the invention

[0007] Problems to be solved by the invention

[0008] However, in the rolling process, there is mutual interference between the equipment and the rolled material, and the equipment is affected by the rolled material. For example, in the case where the equipment is a pressing device (hydraulic cylinder), it is affected by the reaction force from the rolled material relative to the pressing force. In the rolling process, the monitoring parameters change due to changes in rolling conditions (steel type / plate thickness / plate width / target temperature, etc.), and even if the rolling conditions are the same, they change due to changes in rolling conditions (plate speed of the rolled material set according to the temperature distribution, rolling load, etc.). Therefore, if the time series data are simply compared directly with each other as described in Patent Document 1, it is difficult to determine with high accuracy whether the equipment has deteriorated.

[0009] The present invention is made to solve the above-mentioned problems. The purpose of the present invention is to provide a deterioration diagnosis device for rolling equipment that can accurately determine whether the equipment is deteriorated even when there is mutual interference between the equipment and the rolled material that varies according to rolling conditions, etc.

[0010] Means for solving problems

[0011] The first aspect of the present invention relates to a degradation diagnosis device for rolling equipment and machinery, which determines whether the equipment and machinery installed in a point rolling line has degraded. The degradation diagnosis device includes a data acquisition unit, a model identification unit, a monitoring parameter calculation unit, a monitoring parameter use determination unit, a representative value calculation unit, a representative value storage unit, and a degradation diagnosis unit. The input-output data acquisition unit acquires input-output data relative to the input and output of the equipment and machinery during rolling each time the rolled material is rolled once through the rolling line. The model identification unit identifies a mathematical model from the input-output data acquired by the input-output data acquisition unit to obtain the parameters of the mathematical model. The monitoring parameter calculation unit calculates the monitoring parameters based on the parameters obtained by the model identification unit. The monitoring parameter use determination unit has a monitoring parameter collection function by category, which collects the monitoring parameters calculated by the monitoring parameter calculation unit according to the categories specified according to the rolling conditions of the rolled material. The representative value calculation unit calculates the representative value of the set of monitoring parameters within a certain period of each category obtained by the monitoring parameter use determination unit. The representative value storage unit accumulates representative values ​​obtained by the representative value calculation unit during a learning period specified from the start of monitoring, according to the category. The degradation diagnosis unit has: a normal value distribution parameter calculation function, which calculates a distribution parameter representing the distribution of normal values ​​based on a set of representative values ​​according to the category accumulated by the representative value storage unit; and a degradation determination function according to the category, which compares the representative value obtained by the representative value calculation unit after the learning period with the distribution parameter obtained by the normal value distribution parameter calculation function, and determines the presence or absence of degradation according to each category.

[0012] The second aspect has the following features in addition to the first aspect: The degradation diagnosis unit has a comprehensive degradation determination function for determining whether or not the equipment device is degraded based on the determination results for each category obtained by the degradation determination function for each category.

[0013] The third viewpoint has the following features in addition to the second viewpoint: The comprehensive degradation judgment function is to calculate the ratio of the number of categories judged to be degraded to the number of categories judged to be degraded by the degradation judgment function for each category for a certain period, and judge that the equipment is degraded when the calculated ratio exceeds a threshold.

[0014] The fourth aspect has the following features in addition to the first aspect: the model identification unit uses a first-order or second-order ARX model as a mathematical model and assigns parameters of the mathematical model using coefficients of the ARX model. The monitoring parameter calculation unit sets the monitoring parameter as a time constant or a decay coefficient.

[0015] The fifth aspect has the following features in addition to the first aspect: The degradation diagnosis device further includes a data use determination unit that determines that the input / output data of the rolled material is unusable when a standard deviation of the input data acquired by the input / output data acquisition unit is smaller than a threshold value.

[0016] The sixth aspect is characterized in that, in addition to the first aspect, the degradation diagnosis device further includes a data use determination unit that determines that the input and output data of the corresponding rolled material are unusable when a deviation between an average value of input data acquired by the input and output data acquisition unit and an average value of output data exceeds a threshold.

[0017] The seventh viewpoint has the following features in addition to the first viewpoint. The monitoring parameter use determination unit also has the following outlier value exclusion function: the upper and lower limit values ​​of the set of monitoring parameters within a certain period of each category obtained by the monitoring parameter collection function by category are calculated based on the percentage of the set of monitoring parameters within a certain period of each category, and the monitoring parameters outside the range of the upper and lower limit values ​​are excluded as outlier values.

[0018] The eighth aspect has the following features in addition to the seventh aspect: The representative value calculation unit assigns a median or average value of a set of parameters of the mathematical model within a certain period of time for each category after excluding outliers as the representative value.

[0019] The ninth aspect is characterized in that, in addition to the first aspect, the representative value calculation unit has the following degradation failure day estimation function: the calculated representative values ​​are accumulated, plotted on a daily basis, and the date exceeding the threshold is calculated based on the intersection of the line obtained by linear approximation or polynomial approximation and the set threshold.

[0020] The tenth aspect has the following characteristics in addition to the first aspect: The category is specified based on at least one rolling condition selected from the steel type of the rolled material, the target plate thickness, the target plate width, the target coiling temperature, the use of a hot coil box, and the heating furnace.

[0021] The eleventh aspect has the following features in addition to the first aspect: The normal value distribution parameter calculation function assigns a parameter representing the distribution of normal values ​​based on the mean value and the standard deviation.

[0022] The twelfth aspect has the following features in addition to the first aspect. The degradation judgment function for each category uses Hotelling's T 2 Act, Shewhart Management Chart, or both.

[0023] Effects of the Invention

[0024] According to the present invention, a degradation diagnosis device for rolling equipment can be provided, which manages monitoring parameters obtained within a certain period according to categories specified according to rolling conditions, and determines whether the equipment has degraded according to the categories. Thus, even when there is mutual interference between the equipment and the rolled material that varies according to the rolling conditions, it is possible to determine with high accuracy whether the equipment has degraded. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 This is a schematic diagram showing the configuration of a rolling line to which the deterioration diagnosis device for rolling mill equipment according to the embodiment is applied.

[0026] Figure 2 It is a schematic diagram showing the configuration of a deterioration diagnosis device for rolling mill equipment according to an embodiment.

[0027] Figure 3 It means by Figure 2 The input / output data acquired by the input / output data acquisition unit shown is a schematic diagram of the full-length data.

[0028] Figure 4 Yes means Figure 2 The diagram shows a schematic diagram of the functions of the monitoring parameter use determination unit.

[0029] Figure 5 Yes means Figure 2 The diagram schematically shows the functions of the degradation diagnosis unit shown.

[0030] Figure 6 This is a conceptual diagram showing an example of the hardware configuration of a processing circuit included in the deterioration diagnosis device for rolling mill equipment. DETAILED DESCRIPTION

[0031] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In each of the drawings, common or corresponding elements are denoted by the same reference numerals, and descriptions thereof will be simplified or omitted.

[0032] Figure 1 It is a schematic diagram showing the configuration of a rolling line to which the deterioration diagnosis device for equipment in a rolling mill according to the embodiment is applied. Figure 1 The rolling mill 1 shown uses iron steel or other metal materials as a rolling material M and hot-rolls the rolling material M into a plate shape. The rolling mill 1 is provided with a heating furnace 2, a trimming machine 3, a roughing mill 4, a head cutting machine (not shown), a hot coil box (not shown), a finishing mill 5, a cooling device 6, and a coiler 7 as main equipment.

[0033] The heating furnace 2 is configured to heat the slab, which is the rolled material M before rolling, to a predetermined temperature. The trimmer 3 is configured to shape the rolled material M into a predetermined plate width.

[0034] The rough rolling mill 4 is configured to have at least one, usually one to three, rolling stands (hereinafter also referred to as "stands"), and to roll the rolled material M heated by the heating furnace 2 in a forward direction (direction from the upstream side of the rolling line to the downstream side) and a reverse direction (direction from the downstream side of the rolling line to the upstream side) for a plurality of passes. In addition, it is configured to have a head trimmer (not shown) arranged on the downstream side of the rough rolling mill 4, and to cut off the shape defective portion existing at the front end or the tail end of the rolled material M by upper and lower blades based on the shape measured by the shape detector 81 described later. In addition, it is configured to have a hot coil box (not shown) arranged between the rough rolling mill 4 and the finishing rolling mill 5, and to temporarily coil the rolled material M after rough rolling into a spiral shape. In addition, the hot coil box may not be arranged on the rolling line 1.

[0035] The finishing mill 5 is, for example, a tandem hot rolling mill. The finishing mill 5 has a plurality of (seven in this embodiment) stands F1 to F7 arranged in parallel in the conveying direction of the rolled material M. Each of the stands F1 to F7 is provided with two upper and lower working rolls 51, two upper and lower support rolls 52, and a motor 53 for rotating the rolls. The support rolls 52 are provided with a pressing device 54 such as a hydraulic cylinder, and the roll gap between the upper and lower working rolls 51 can be adjusted by the pressing device 54. The rolling load of each stand F1 to F7 is measured by a rolling load sensor 55. The rolling load sensor 55 is, for example, a load sensor. In addition, the roll gap of each rolling stand F1 to F7 is measured by a gap sensor such as a magnetic scale not shown in the figure. In addition, a ring top (not shown in the figure) is arranged between adjacent stands to control the tension of the rolled material M between the stands.

[0036] The cooling device 6 is configured to cool the rolled material M by pouring water into the rolled material M via a cooling bed. The rolled material M after being cooled is coiled in a spiral shape by a coiler 7 .

[0037] Various sensors as various measuring devices are provided at important locations of the rolling line 1. For example, the important locations of the rolling line 1 are the exit side of the heating furnace 2, the exit side of the roughing mill 3, the exit side of the finishing mill 5, and the entry side of the coiler 7. Various sensors can also be provided between the stands F1 to F7 of the finishing mill 5. The various sensors include: a shape detector 81 capable of measuring the shape (including the plate width) of the rolled material M at the exit side of the roughing mill 3, a thermometer 82 capable of measuring the surface temperature of the rolled material M at the upstream side of the finishing mill 5, a plate thickness gauge 83 capable of measuring the actual plate thickness of the rolled material M at the exit side of the finishing mill 5, the above-mentioned rolling load sensor 55 for measuring the rolling load in each stand F1 to F7, and the above-mentioned gap sensor for measuring the roll gap of each stand F1 to F7. The various sensors measure the state of the rolled material M and each equipment machine in sequence.

[0038] The rolling line 1 is operated by a control system using a computer. The computer includes a host computer 10 and a process control computer 11 connected to each other via a network. The process control computer 11 is connected to an operation screen of an operator, i.e., an interface screen 12 via a network. The operator can perform input operations of control conditions on the interface screen 12. The interface screen 12 can also serve as a screen display device DP described later.

[0039] The process control computer 11 performs setting calculation and control of the control object in a series of rolling processes. In addition, the process control computer 11 also has the function of correcting the roll gap of each stand F1 to F7. Product information is input to the process control computer 11 from the host computer 10. The product information includes target information (product target) such as the target plate thickness (product plate thickness) and target plate width of the rolled material M after being heated by the heating furnace 2, and the steel type.

[0040] The process control computer 11 appropriately controls each device based on the target information, the control conditions given from the interface screen 12, etc. The process control computer 11 is, for example, a controller. When the rolled material M is conveyed to a predetermined position of the rolling line 1, the process control computer 11 calculates the settings of each device that can realize the target information, and based on these setting values, operates the actuators and motors (rotating machines) of each device machine such as the hydraulic cylinder of the press-down device 54 constituting each frame F1 to F7.

[0041] Figure 2 This is a schematic diagram showing the structure of a degradation diagnosis device 9 for diagnosing (determining) degradation of equipment and machinery installed in a rolling line 1 (hereinafter, also referred to as "rolling equipment and machinery"). The rolling equipment and machinery that the degradation diagnosis device 9 targets include hydraulic cylinders used in the trimming machine 3, the roughing mill 4, and the finishing mill 5, and motors (rotating machines) used in the trimming machine 3, the roughing mill 4, the finishing mill 5, and the ring top. In this embodiment, the case where the hydraulic cylinder that is the pressing device 54 of the finishing mill 5 is used as the target is described as an example.

[0042] The degradation diagnosis device 9 has an input / output data acquisition unit 91, a data pre-processing unit 92, a data use determination unit 93, a model identification unit 94, a model use determination unit 95, a monitoring parameter calculation unit 96, a monitoring parameter use determination unit 97, a representative value calculation unit 98, a representative value storage unit 99 and a degradation diagnosis unit 100.

[0043] The degradation diagnosis device 9 is connected to a data storage device DB and a screen display device DP. The data storage device DB collects and stores data of multiple items from the various sensors and process control computers (controllers) 11 and other machines used in the rolling process. The data storage device DB is, for example, a database. The screen display device DP displays the output of the degradation diagnosis device 9, i.e., the degradation diagnosis result (degradation determination result). In addition, the data storage device DB and the screen display device DP may also be provided inside the degradation diagnosis device 9.

[0044] The input / output data acquisition unit 91 extracts the input data and output data (hereinafter referred to as "input / output data") for the target equipment from the data of multiple items accumulated in the data accumulation device DB. In this embodiment, the input / output data is a pair of command values ​​(input data) and actual values ​​(output data) related to the position of the pressing device (hydraulic cylinder) 54 during the rolling of each rolled material M. Figure 3 As shown, the input / output data acquisition unit 91 extracts the input / output data of the press device 54 from the data acquisition start time (the time when the rolled material M is bitten by the stand) to the data acquisition end time (the time when the rolled material M is discharged from the stand). The input / output data thus extracted by the input / output data acquisition unit 91 is sometimes referred to as "full-length data".

[0045] The data preprocessing unit 92 performs preprocessing on the full-length data of each device extracted by the input / output data acquisition unit 91. Figure 3 The data of the unstable front end and tail end in the transition state are excluded from the full-length data shown. Thus, the data of the front end and tail end can be prevented from being used for degradation diagnosis. When the input data after excluding the data of the front end and tail end is set to x and the output data is set to y, the input data x and the output data y are defined by the following equations (1) and (2).

[0046]

Number 1

[0047] x=[x(0) x(1) x(2) … x(n)]…(1)

[0048]

Number 2

[0049] y=[y(0) y(1) y(2) … y(n)]…(2)

[0050] Here, n is Figure 3 The number of data shown.

[0051] The data use determination unit 93 determines whether the input / output data pre-processed by the data pre-processing unit 92 is input data suitable for degradation determination. For example, when the variation of the input data x pre-processed by the data pre-processing unit 92 is small or when there is a deviation between the input data x and the output data y, the data use determination unit 93 determines that the input / output data of the rolled material M is not suitable for degradation determination, and excludes the input / output data of the rolled material M from the diagnosis object.

[0052] Specifically, first, when the variation of the input data x is small, that is, the standard deviation σ of the input data x is x The threshold value θ is greater than the predetermined reference value. σx When the change in input / output data is small, it is determined that the input / output data of the rolled material M is unusable, and the input / output data of the rolled material M is excluded from the diagnosis object. When the change in input / output data is small, the data use determination unit 93 cannot accurately obtain the dynamic characteristics of the equipment and machinery, which may damage the effectiveness of the monitoring parameters described later as indicators of the degree of deterioration.

[0053]

Number 3

[0054] σ x <θ σ_x …(3)

[0055] Next, in the case where there is an offset between the input data x and the output data y, the average value x of the input data x is ave The average value y of the output data y ave The deviation is the threshold value θ as the specified reference value. OFS In the above case, the data use determination unit 93 determines that the input / output data of the rolled material M is not usable, and excludes the input / output data of the rolled material M from the diagnosis target.

[0056]

Number 4

[0057] |x ave -y ave |<θ OFS …(4)

[0058] The model identification unit 94 identifies the ARX model from the input and output data of the rolled material M that has not been excluded by the data use determination unit 93. The ARX model has a degree of 1 and a degree of 2, which can be selected according to each equipment machine of the diagnosis object. It is preferable to determine the degree of the ARX model suitable for the equipment machine of the object in advance through experiments and simulations.

[0059] The first-order ARX model is represented by the following equation (5).

[0060]

Number 5

[0061] y(m)=a 1_1 y(m-1)+b 11 x(m-1)…(5)

[0062] Here, a 11 represents the model coefficient of the output data, b 11 represents the model coefficient of the input data, and m represents an arbitrary data point.

[0063] The model coefficient a to be identified 11 , b 11 It is determined by the following formula (6) so that the sum of square errors between the output data y and the calculated value of the ARX model is minimized.

[0064]

Number 6

[0065]

[0066] In addition, the secondary ARX model is expressed by the following formula (7).

[0067]

Number 7

[0068] y(m)=a 1，2 y(m-1)+a 2_2 y(m-2)+b 1，2 x(m-1)…(7)

[0069] Here, a 11 、a 22 represents the model coefficient of the output data y, b 12 represents the model coefficient of the input data x, and m represents an arbitrary data point.

[0070] The model coefficient a to be identified 11 、a 22 , b 12 It is determined so that the sum of square errors between the output data and the calculated value of the ARX model is minimized.

[0071]

Number 8

[0072]

[0073] The model use determination unit 95 determines whether the model can be used for response degradation diagnosis based on the sign of the coefficient of the ARX model obtained by the model identification unit 94. Specifically, when the first-order ARX model satisfies equation (9) and the second-order ARX model satisfies equation (10), the monitoring parameter cannot be calculated using equation (11) or (12) described later, so the model identification result of the rolled material M is excluded from the diagnosis object.

[0074]

Number 9

[0075] a1_1 <0…(9)

[0076]

Number 10

[0077] a 2_2 >0…(10)

[0078] The monitoring parameter calculation unit 96 calculates monitoring parameters using the model coefficients of the rolled material M not excluded by the model use determination unit 95. As monitoring parameters, the time constant τ is used in the first-order ARX model, and the attenuation coefficient ζ is used in the second-order ARX model.

[0079] In the case of the first-order ARX model, the model coefficient a is used by the following formula (11): 11 To calculate the time constant τ.

[0080]

Number 11

[0081]

[0082] Here, T s Indicates the sampling interval.

[0083] In the case of a quadratic ARX model, the model coefficient a is used 11 、a 22 To calculate the attenuation coefficient ζ. First, use the following formula (12) to use a 22 To calculate the product of the attenuation coefficient ζ and the natural angular frequency ωn.

[0084]

Number 12

[0085]

[0086] Here, T s Indicates the sampling interval.

[0087] Next, using the product ζω, we can use the following formula (14): n To calculate the natural angular frequency ω n At this time, the calculation formula refers to θ calculated based on the following formula (13): ζ to switch.

[0088]

Number 13

[0089]

[0090]

Number 14

[0091]

[0092] Finally, using the natural angular frequency ω, n To calculate the attenuation coefficient ζ.

[0093]

Number 15

[0094]

[0095] Figure 4 2 is a schematic diagram showing the functions of the monitoring parameter use determination unit 97. Figure 4 The flowchart shown here explains the operation of the monitoring parameter use determination unit 97. The monitoring parameter use determination unit 97 has a monitoring parameter collection function 971 for each type and a deviating value exclusion function 972.

[0096] The monitoring parameter collection function 971 by category is to collect the monitoring parameters obtained by the monitoring parameter calculation unit 96, for example, daily, according to different categories (also called "different categories for different layers") specified according to rolling conditions. Here, the category is specified according to at least one rolling condition selected from steel type, target plate thickness, target plate width, target coiling temperature, whether or not a hot coil box is used, and a heating furnace. In this way, by managing the monitoring parameters according to the categories specified according to the rolling conditions, it is possible to prevent the monitoring parameters from being affected by the rolled material (material) M.

[0097] The deviated value exclusion function 972 excludes the monitoring parameters that become deviated values ​​from the monitoring parameters of one day collected by the monitoring parameter collection function 971 by category. The monitoring parameters x that do not satisfy the following formula (16) in the set of monitoring parameters x of one day according to each category are set as deviated values. The deviated value refers to a sudden value or a value affected by the manual intervention of the operator of the rolling line 1. Such a deviated value will cause a decrease in the accuracy of the degradation judgment, and is therefore excluded by the deviated value exclusion function 972.

[0098]

Number 16

[0099] P 25 -α(P 75 -P 25 )<χ <P 75 +α(P 75 -P 25 )…(16)

[0100] Here, P 75 It is 75% of the daily monitoring parameter, P 25 It is 25 percent of the daily monitoring parameter, and α is an arbitrary multiplication factor.

[0101] The representative value calculation unit 98 calculates the representative value of the set of monitoring parameters within a certain period of each category that is not excluded by the monitoring parameter use determination unit 97. Specifically, the representative value calculation unit 98 calculates the average value or median value of the set of monitoring parameters within a certain period of each category, and assigns the calculated average value or median value as the representative value. At this time, if the number of rolled roots of each category of rolled material M on a day decreases due to the exclusion of the deviating value by the monitoring parameter use determination unit 97, the distribution of the monitoring parameters may be biased, and it may be misdiagnosed as degradation. In this case, the representative value of the day may not be calculated. In addition, the following degradation fault day inference function may be added to the representative value calculation unit 98: the obtained representative value is plotted on a daily basis, and the day exceeding the threshold is calculated based on the intersection of the line obtained by linear approximation or polynomial approximation and the set threshold, and the day when degradation occurs is predicted.

[0102] The representative unit storage unit 99 uses the number of days specified in advance from the monitoring start date as a learning period, and accumulates the representative values ​​obtained by the representative value calculation unit 98 according to the category. At this time, the number of accumulated representative values ​​may be counted according to the category, and the period until the representative values ​​of the specified number of days are accumulated may be used as the learning period.

[0103] Figure 5 2 is a schematic diagram showing the functions of the degradation diagnosis unit 100. Figure 5 The illustrated flow explains the operation of degradation diagnosis unit 100 .

[0104] The degradation diagnosis unit 100 includes a normal value distribution parameter calculation function 101 , a type-specific degradation determination function 102 , and a comprehensive degradation determination function 103 .

[0105] The normal value distribution parameter calculation function 101 obtains a set of representative values ​​of each day during the learning period (e.g., X-month X-day to Y-month Y-day) for each category stored in the representative unit storage unit 99. The normal value distribution parameter calculation function 101 calculates, for example, the average value and standard deviation of the representative values ​​of each day during the learning period as distribution parameters representing the distribution of normal values ​​based on the set of representative values ​​of each day during the learning period obtained from the representative unit storage unit 99.

[0106] The degradation determination function 102 for each category compares the representative value obtained by the representative value calculation unit 98 after the learning period with the distribution parameter obtained by the normal value distribution parameter calculation function 101, and determines the presence or absence of degradation for each category. There are many methods for such determination, but the degradation determination function 102 for each category can use Hotelling's T 2 The judgment is made based on the Shewhart management diagram, or both.

[0107] First, Hotelling's T 2 Assume that the monitoring parameter of the parent group follows a normal distribution and use the representative value x on day j rep (j) The average value of the representative value of each day during the learning period x rep、ave , standard deviation σ x_rep , calculate the abnormality H of the jth day (for example, Y month Z day).

[0108]

Number 17

[0109]

[0110] An arbitrary threshold is set for the abnormality H, and when it exceeds the threshold, it is judged as degradation. In addition, it is theoretically proved that the abnormality H conforms to the chi-square distribution with 1 degree of freedom, and the probability of H taking a certain value can be calculated. For example, the probability of H = 3.84 is about 5%, the probability of H = 6.63 is about 1%, and the probability of H = 10.8 is about 0.1%. The relationship between the abnormal value H and the probability can be used as a reference to set the threshold for judging degradation.

[0111] Next, the determination method based on the Shewhart management chart is described. rep，ave As a benchmark, the standard deviation σ in the positive and negative directions x_rep The threshold value is set as a constant multiple of x on the jth day (for example, Y month Z day). rep (j) When it is outside the threshold range, it is determined to be degraded.

[0112] As another determination method used by the degradation determination function 102 by category, the following method can be cited: a constant multiple of the average value of the representative value of each day during the learning period is set as a threshold value, and when the representative value exceeds the threshold value, it is determined to be degradation. In addition, multiple threshold values ​​can be prepared for one determination method to determine the degree of degradation in stages.

[0113] The comprehensive degradation judgment function 103 makes a comprehensive judgment (final judgment) on whether the equipment equipment has degraded based on the degradation diagnosis results (judgment results) of each category obtained by the degradation judgment function 102 by category. Specifically, for each day, the ratio of the number of categories judged to be degraded among the categories judged to be degraded by the above-mentioned degradation judgment function 102 by category on that day is calculated, and when it exceeds a threshold, the equipment is judged to be degraded. By having the comprehensive degradation judgment function 103 in this way, even when the number of categories is large, it is possible to judge degradation with high accuracy.

[0114] In addition, the degradation determination function 102 for each category may be weighted equally and comprehensively determined, or may be weighted differently and comprehensively determined. For example, for the determination results of the category of steel types with a large number of rollings or the determination results of steel types that must be strictly determined, it is possible to increase the weight and comprehensively determine, thereby making it possible to determine degradation with higher accuracy.

[0115] As described above, according to the present embodiment, the following configuration is adopted: the monitoring parameters obtained by the data monitoring parameter calculation unit 96 are managed in the monitoring parameter use determination unit 97 according to different categories specified according to rolling conditions for each certain period, and the degradation diagnosis unit 100 determines whether the equipment and machinery are degraded according to the categories. Thus, a degradation diagnosis device 9 can be provided, which can accurately determine whether the equipment and machinery are degraded even when there is mutual interference between the equipment and machinery and the rolled material M that varies according to rolling conditions, etc. Moreover, the determination results of each category are used in the comprehensive degradation determination function 103 for comprehensive determination, thereby enabling high-precision determination even when the number of categories is large. In addition, the input and output data suitable for degradation determination are screened by the data use determination unit 93, and the deviated values ​​are excluded from the set of monitoring parameters of each category by the deviated value exclusion function 972, thereby enabling further high-precision determination.

[0116] Next, a description will be given of a specific structure of the degradation diagnosis device 9. The specific structure of the degradation diagnosis device 9 is not limited, but the following structure may be used as an example. Figure 6 1 is a conceptual diagram showing an example of the hardware configuration of the processing circuit of the degradation diagnosis device 9. Each unit and each function constituting the degradation diagnosis device 9 is implemented by the processing circuit. For example, the processing circuit includes at least one processor 90a and at least one memory 90b. For example, the processing circuit includes at least one dedicated hardware 90c. As a specific example, the processing circuit is a personal computer (PC) or the like.

[0117] When the processing circuit has a processor 90a and a memory 90b, the functions of the degradation diagnosis device 9 are implemented by software, firmware, or a combination of software and firmware. At least one of the software and firmware is described as a program. At least one of the software and firmware is stored in the memory 402. The processor 90a realizes each function by reading and executing the program stored in the memory 90b. The processor 401 is also called a CPU (Central Processing Unit), a central processing unit, a processing unit, an arithmetic unit, a microprocessor, a microcomputer, and a DSP. For example, the memory 402 is a non-volatile or volatile semiconductor memory such as a RAM, a ROM, a flash memory, an EPROM, an EEPROM, a magnetic disk, a floppy disk, an optical disk, a CD, a microdisk, a DVD, etc.

[0118] In the case where the processing circuit has dedicated hardware 90c, the processing circuit is, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC, an FPGA, or a circuit formed by combining these. For example, each function is implemented by a processing circuit separately. For example, each function is implemented by a processing circuit in a centralized manner. In addition, each function may be partially implemented by dedicated hardware 90c, and the other part may be implemented by software or firmware. In this way, the processing circuit implements each function through hardware 90c, software, firmware, or a combination of these.

[0119] The embodiments of the present invention are described above, but the present invention is not limited to the above embodiments, and various modifications can be made without departing from the scope of the present invention. For example, in the above embodiments, as the object control machine, the hydraulic cylinder constituting the pressing device 54 of the finishing mill 5 is described as an example, but it is not limited to this, and it can also be a control machine set in the hot rolling line.

[0120] In addition, when the numerical values ​​of the number, quantity, amount, range, etc. of each element are mentioned in the above-mentioned embodiments, the present invention is not limited to the numerical values ​​mentioned, except for the cases where the numerical values ​​are specifically stated or clearly determined in principle. In addition, the structures and the like described in the above-mentioned embodiments are not essential to the present invention, except for the cases where the numerical values ​​are specifically stated or clearly determined in principle.

[0121] Explanation of symbols

[0122] 1: rolling line, M: rolled material, 5: finishing mill, F1~F6: rolling stands, 54: pressing device, 9: degradation diagnosis device, 91: input / output data acquisition unit, 92: data pre-processing unit, 93: data usage determination unit, 94: model identification unit, 95: model usage determination unit, 96: monitoring parameter calculation unit, 97: monitoring parameter usage determination unit, 971: monitoring parameter collection function by category, 972: outlier value exclusion function, 98: representative value calculation unit, 99: representative unit storage unit, 100: degradation diagnosis unit, 101: normal value distribution parameter calculation function, 102: degradation determination function by category, 103: comprehensive degradation determination function.

Claims

1. A deterioration diagnosis device for rolling equipment, which determines whether equipment installed in a rolling line has deteriorated, and comprises: an input / output data acquisition unit that acquires input / output data of input / output to the equipment and machine during rolling, each time the rolled material is rolled once in the rolling line; a model identification unit that identifies a mathematical model from the input-output data acquired by the input-output data acquisition unit and obtains parameters of the mathematical model; a monitoring parameter calculation unit, which calculates monitoring parameters based on the parameters obtained by the model identification unit; a monitoring parameter use determination unit having a monitoring parameter collection function by category, wherein the monitoring parameter collection function by category is to collect the monitoring parameter calculated by the monitoring parameter calculation unit according to a category specified according to a rolling condition of the rolled material; a representative value calculation unit that calculates a representative value of a set of the monitoring parameters for each category within a certain period of time obtained by the monitoring parameter use determination unit; a storage unit that accumulates the representative values ​​obtained by the representative value calculation unit in a designated learning period from the start of monitoring, according to the category; as well as The degradation diagnosis unit has a normal value distribution parameter calculation function and a degradation judgment function by category. The normal value distribution parameter calculation function is to obtain distribution parameters representing the distribution of normal values ​​based on the set of representative values ​​of each category accumulated by the storage unit. The degradation judgment function by category is to compare the representative value obtained by the representative value calculation unit after a learning period with the distribution parameter obtained by the normal value distribution parameter calculation function, and judge whether there is degradation by category.

2. The deterioration diagnosis device for rolling mill machinery according to claim 1, wherein: The degradation diagnosis unit has a comprehensive degradation determination function for determining whether or not the equipment device has degraded based on determination results for each category obtained by the category-based degradation determination function.

3. The deterioration diagnosis device for rolling mill machinery according to claim 2, wherein: The comprehensive degradation determination function calculates, for each of the predetermined periods, a ratio of the number of categories determined to be degraded to the number of categories determined to be degraded by the degradation determination function for each category, and determines that the equipment device is degraded when the ratio exceeds a threshold.

4. The deterioration diagnosis device for rolling mill equipment according to claim 1, wherein: The model identification unit uses a first-order or second-order ARX model as the mathematical model, and assigns parameters of the mathematical model through coefficients of the ARX model. The monitoring parameter calculation unit sets the monitoring parameter as a time constant or an attenuation coefficient.

5. The deterioration diagnosis device for rolling mill machinery according to claim 1, wherein: The degradation diagnosis device further includes a data use determination unit configured to determine that the input / output data of the corresponding rolled material is unusable when a standard deviation of the input data acquired by the input / output data acquisition unit is smaller than a threshold value.

6. The deterioration diagnosis device for rolling mill machinery according to claim 1, wherein: The degradation diagnosis device further includes a data use determination unit that determines that the input and output data of the corresponding rolled material is unusable when a deviation between an average value of input data and an average value of output data acquired by the input and output data acquisition unit exceeds a threshold value.

7. The deterioration diagnosis device for rolling mill equipment according to claim 1, wherein: The monitoring parameter usage determination unit also has a deviating value exclusion function, which is to calculate the upper and lower limit values ​​of the set of monitoring parameters within a certain period of each category obtained by the monitoring parameter collection function by category based on the percentage of the set of monitoring parameters within a certain period of each category, and exclude the monitoring parameters outside the range of the upper and lower limit values ​​as deviating values.

8. The deterioration diagnosis device for rolling mill equipment according to claim 7, wherein: The representative value calculation unit assigns a median or an average value of a set of parameters of the mathematical model within a certain period of each category excluding the outlier value as the representative value.

9. The deterioration diagnosis device for rolling mill machinery according to claim 1, wherein: The representative value calculation unit has a degradation failure day estimation function, which accumulates the calculated representative values, plots them on a daily basis, and calculates a date exceeding a threshold value based on an intersection of a line obtained by linear approximation or polynomial approximation and a set threshold value.

10. The deterioration diagnosis device for rolling mill equipment according to claim 1, wherein: The category is specified based on at least one rolling condition selected from the steel type of the rolled material, the target plate thickness, the target plate width, the target coiling temperature, the presence or absence of use of a hot coil box, and the heating furnace.

11. The deterioration diagnosis device for rolling mill equipment according to claim 1, wherein: The normal value distribution parameter calculation function calculates the mean value and the standard deviation as the distribution parameters.

12. The deterioration diagnosis device for rolling mill equipment according to claim 1, wherein: The degradation determination function for each category uses Hotelling's T 2 Act, or Shewhart Management Chart, or both.

Images