Rolling Equipment Deterioration Diagnosis Device

Abstract

This degradation diagnosis device for rolling equipment includes an input / output 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 monitoring parameter use determination unit has a category-specific monitoring parameter collection function of collecting monitoring parameters, calculated by the monitoring parameter calculation unit, for each category designated on the basis of the rolling conditions of a rolled material. The representative value calculation unit calculates a representative value for a set of monitoring parameters within a certain period for each category. The representative value storage unit accumulates, for each category, representative values in a learning period designated from the start of monitoring. The degradation diagnosis unit has a category-specific degradation determination function of determining the presence or absence of degradation for each category.

Description

Technical Field

[0001] The present disclosure 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 where a plurality of types of equipment are arranged, it is required to detect deterioration (response deterioration) of the equipment at an early stage, prompt an operator to perform maintenance and repair of the equipment, and achieve stable operation and quality improvement. Therefore, it has been studied to collect and accumulate operation data of equipment and utilize it for early detection of deterioration occurring in the equipment.

[0003] For example, Patent Document 1 below discloses a state abnormality determination device that monitors the state of a robot (equipment) and supports maintenance of the robot. In this device, a monitoring parameter obtained by directly comparing past normal time-series data (data in which current values flowing through a servo motor are arranged in time series) with current time-series data is aggregated every day to obtain a representative value. By comparing the obtained representative value with the distribution of the monitoring parameters during a specified learning period, deterioration of an actuator configured as a servo motor is determined.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] 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, when the equipment is a rolling reduction device (hydraulic cylinder), it is affected by the reaction force from the rolled material with respect to the rolling reduction force. In the rolling process, the monitoring parameters change due to changes in rolling conditions (steel type / thickness / width / target temperature, etc.) or changes in the rolling situation (rolling speed and rolling load of the rolled material set by the temperature distribution) even when the rolling conditions are the same. Therefore, it is difficult to accurately determine the presence or absence of deterioration of the equipment only by directly comparing time-series data as described in Patent Document 1.

[0006] The present disclosure has been made to solve the above-described problems. An object of the present disclosure is to provide a deterioration diagnosis device for rolling equipment that can accurately determine the presence or absence of deterioration of the equipment even when there is mutual interference that changes depending on rolling conditions or the like between the equipment and the rolled material.

Means for Solving the Problems

[0007] A first aspect of the present disclosure relates to a deterioration diagnosis device for a rolling facility that determines the presence or absence of deterioration of facility equipment installed in a rolling line. The deterioration diagnosis device includes an input / output 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 deterioration diagnosis unit. The input / output data acquisition unit acquires input / output data input to and output from the facility equipment during rolling each time a rolled material is rolled once in the rolling line. The model identification unit identifies a mathematical model from the input / output data acquired by the input / output data acquisition unit and obtains the parameters of the mathematical model. The monitoring parameter calculation unit calculates monitoring parameters from the parameters obtained by the model identification unit. The monitoring parameter use determination unit has a function of collecting the monitoring parameters calculated by the monitoring parameter calculation unit separately for each category specified by the rolling conditions of the rolled material. The representative value calculation unit calculates a representative value of a set of monitoring parameters within a certain period for each category obtained by the monitoring parameter use determination unit. The representative value storage unit accumulates the representative values obtained by the representative value calculation unit for each category during a specified learning period from the start of monitoring. The deterioration diagnosis unit has a normal value distribution parameter calculation function of calculating distribution parameters indicating the distribution of normal values from a set of representative values for each category accumulated in the representative value storage unit, and a function of collating the representative values obtained after the learning period by the representative value calculation unit with the distribution parameters obtained by the normal value distribution parameter calculation function to determine the presence or absence of deterioration for each category.

[0008] A second aspect further has the following features in addition to the first aspect. The deterioration diagnosis unit has an overall deterioration determination function of determining the presence or absence of deterioration of the facility equipment based on the determination results for each category obtained by the category-by-category deterioration determination function.

[0009] A third aspect further has the following features in addition to the second aspect. The overall deterioration determination function calculates, for each certain period, the ratio of the number of categories determined to have deterioration among the number of categories for which the presence or absence of deterioration has been determined by the category-by-category deterioration determination function, and determines that the facility equipment has deterioration when the calculated ratio exceeds a threshold value.

[0010] In addition to the first aspect, the fourth aspect further has the following features. The model identification unit uses a first- or second-order ARX model as a mathematical model, and gives the parameters of the mathematical model by the coefficients of the ARX model. The monitoring parameter calculation unit uses a time constant or a decay coefficient as the monitoring parameter.

[0011] In addition to the first aspect, the fifth aspect further has the following features. The deterioration determination device further includes a data usage determination unit that determines that the input-output data of the corresponding rolled material is unusable when the standard deviation of the input data acquired by the input-output data acquisition unit is smaller than the threshold value.

[0012] In addition to the first aspect, the sixth aspect further has the following features. The deterioration determination device further includes a data usage determination unit that determines that the input-output data of the corresponding rolled material is unusable when the deviation between the average value of the input data and the average value of the output data acquired by the input-output data acquisition unit is greater than or equal to the threshold value.

[0013] In addition to the first aspect, the seventh aspect further has the following features. The monitoring parameter usage determination unit further has an outlier exclusion function that calculates the upper and lower limit values from the percentiles of the set of monitoring parameters within a certain period for each section obtained by the section-by-section monitoring parameter collection function, and excludes the monitoring parameters outside the range of the upper and lower limit values as outliers.

[0014] In addition to the seventh aspect, the eighth aspect further has the following features. The representative value calculation unit gives the median or average value of the set of parameters of the mathematical model within a certain period for each section after outlier exclusion as the representative value.

[0015] In addition to the first aspect, the ninth aspect further has the following features. The representative value calculation unit has a deterioration failure date estimation function that accumulates the calculated representative values, plots them daily, and calculates the date exceeding the threshold value from the intersection of the linearly approximated or polynomially approximated line and the set threshold value.

[0016] The tenth aspect further has the following features in addition to the first aspect. The classification is specified by 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 using a coil box, and by heating furnace.

[0017] The eleventh aspect further has the following features in addition to the first aspect. The normal value distribution parameter calculation function gives parameters indicating the distribution of normal values by the mean value and the standard deviation.

[0018] The twelfth aspect further has the following features in addition to the first aspect. The deterioration determination function by classification uses Hotelling's T 2 method, or Shewhart control chart, or both.

Advantages of the Invention

[0019] According to the present disclosure, by managing the monitoring parameters obtained within a certain period according to the classification specified by the rolling conditions and determining the presence or absence of deterioration of the equipment for each classification, even when there is an interaction that varies depending on the rolling conditions between the equipment and the rolled material, it is possible to provide a deterioration diagnosis device for rolling equipment that can accurately determine the presence or absence of deterioration of the equipment.

Brief Description of the Drawings

[0020]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Embodiments for Carrying Out the Invention

[0021] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In each figure, common or corresponding elements are denoted by the same reference numerals to simplify or omit the description.

[0022] FIG. 1 is a schematic diagram showing the configuration of a rolling line to which a deterioration diagnosis device for rolling equipment machines according to an embodiment is applied. The rolling line 1 shown in FIG. 1 uses steel or other metal materials as the rolling material M and hot-rolls the rolling material M into a plate shape. In the rolling line 1, as main equipment, a heating furnace 2, an edger 3, a rough rolling mill 4, a crop shear (not shown), a coil box (not shown), a finishing rolling mill 5, a cooling device 6, and a coiler 7 are installed.

[0023] The heating furnace 2 is configured to heat the slab, which is the rolling material M before rolling, to a predetermined temperature. The edger 3 is configured to form the rolling material M into a predetermined plate width.

[0024] The rough rolling mill 4 has at least one, usually one to three rolling stands (hereinafter also referred to as "stands"), and is configured to perform multi-pass rolling of the rolling material M heated in the heating furnace 2 in the forward direction (the direction from the upstream side to the downstream side of the rolling line) and the reverse direction (the direction from the downstream side to the upstream side of the rolling line). A crop shear (not shown) is arranged on the downstream side of the rough rolling mill 4, and is configured to cut the defective shape portion existing at the tip or tail end of the rolling material M by the upper and lower blades based on the shape measured by the shape detector 81 described later. A coil box (not shown) is arranged between the rough rolling mill 4 and the finishing rolling mill 5, and is configured to temporarily wind the roughly rolled rolling material M into a coil shape. Note that the coil box may not be arranged in the rolling line 1.

[0025] The finishing rolling mill 5 is, for example, a hot tandem rolling mill. The finishing rolling mill 5 has a plurality (seven in this embodiment) of stands F1 to F7 arranged side by side in the conveying direction of the rolled material M. Each of the stands F1 to F7 is provided with two upper and lower work rolls 51, two upper and lower backup rolls 52, and an electric motor 53 for roll rotation. The backup roll 52 is provided with a rolling reduction device 54 such as a hydraulic cylinder, and the rolling reduction device 54 is configured to be able to adjust the roll gap between the upper and lower work rolls 51. The rolling load of each of the stands F1 to F7 is measured by a rolling load sensor 55. The rolling load sensor 55 is, for example, a load cell. Further, the roll gap of each of the rolling stands F1 to F7 is measured by a gap sensor such as a magnetic scale (not shown). A looper (not shown) is arranged between adjacent stands and is configured to control the tension of the rolled material M between the stands.

[0026] The cooling device 6 is configured to be able to cool the rolled material M by pouring water onto the rolled material M with a cooling bank. The cooled rolled material M is wound into a coil by a coiler 7.

[0027] Various sensors as various measuring instruments are installed at key points on the rolling line 1. The key points on the rolling line 1 are, for example, the outlet side of the heating furnace 2, the outlet side of the rough rolling mill 4 , the outlet side of the finishing rolling mill 5, and the inlet side of the coiler 7, etc. The various sensors may also be provided between the stands F1 to F7 of the finishing rolling 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 outlet side of the rough rolling mill 4 , a thermometer 82 for measuring the surface temperature of the rolled material M on the upstream side of the finishing rolling mill 5, a thickness gauge 83 for measuring the actual plate thickness of the rolled material M at the outlet side of the finishing rolling mill 5, the above-mentioned rolling load sensor 55 for measuring the rolling load at each of the stands F1 to F7, and the above-mentioned gap sensor for measuring the roll gap of each of the stands F1 to F7. The various sensors sequentially measure the state of the rolled material M and each equipment.

[0028] The rolling line 1 is operated (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. An interface screen 12, which is an operation screen by an operator, is connected to the process control computer 11 via a network. The operator can perform input operations of control conditions and the like on the interface screen 12. The interface screen 12 can also serve as a screen display device DP described later.

[0029] The process control computer 11 executes setting calculation and control of a control target in a series of rolling processes. Further, the process control computer 11 further has a function of correcting the roll gaps 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 heated by the heating furnace 2, and the steel type.

[0030] The process control computer 11 appropriately controls each facility based on the target information and control conditions given from the interface screen 12. The process control computer 11 is, for example, a controller. When the rolled material M is conveyed to a predetermined position on the rolling line 1, the process control computer 11 calculates the settings of each facility capable of achieving the target information, and based on those set values, operates actuators and electric motors (rotating machines) of each facility device such as the hydraulic cylinders constituting the rolling-down devices 54 of each stand F1 to F7.

[0031] FIG. 2 is a schematic diagram showing the configuration of a deterioration diagnosis device 9 for diagnosing (determining) the deterioration of facility devices (hereinafter also referred to as "rolling facility devices") installed on the rolling line 1. The rolling facility devices targeted by the deterioration diagnosis device 9 include hydraulic cylinders used for the edger 3, rough rolling mill 4, and finish rolling mill 5, and electric motors (rotating machines) used for the edger 3, rough rolling mill 4, finish rolling mill 5, and looper. In the present embodiment, the case where the hydraulic cylinder of the rolling-down device 54 of the finish rolling mill 5 among these rolling facility devices is targeted will be described as an example.

[0032] The deterioration diagnosis device 9 includes an input / output data acquisition unit 91, a data preprocessing unit 92, a data usage determination unit 93, a model identification unit 94, a model usage determination unit 95, a monitoring parameter calculation unit 96, a monitoring parameter usage determination unit 97, a representative value calculation unit 98, a representative value storage unit 99, and a deterioration diagnosis unit 100.

[0033] A data storage device DB and a screen display device DP are connected to the deterioration diagnosis device 9. The data storage device DB collects and stores data of a number of items from various sensors and devices such as the above-described process control computer (controller) 11 used in the rolling process. The data storage device DB is, for example, a database. The screen display device DP displays the deterioration diagnosis result (deterioration determination result) which is the output of the deterioration diagnosis device 9. Note that the data storage device DB and the screen display device DP may be provided inside the deterioration diagnosis device 9.

[0034] The input / output data acquisition unit 91 extracts and acquires input data and output data (hereinafter referred to as "input / output data") for the target equipment from the data of a number of items stored in the data storage device DB. In the present embodiment, the input / output data is a pair of a command value (input data) and an actual value (output data) regarding the position of the rolling reduction device (hydraulic cylinder) 54 during the rolling of each rolled material M. As shown in FIG. 3, the input / output data acquisition unit 91 extracts the input / output data of the rolling reduction device 54 from the data acquisition start time (the time when the rolled material M bites into the stand) to the data acquisition end time (the time when the rolled material M exits the stand). The input / output data extracted by the input / output data acquisition unit 91 in this way may also be referred to as "full-length data".

[0035] The data preprocessing unit 92 performs preprocessing on the overall length data of each facility equipment extracted by the input / output data acquisition unit 91. Specifically, among the overall length data shown in FIG. 3, data of unstable tip and tail parts in the transient state are excluded. Thereby, it is possible to prevent the data of the tip and tail parts from being used for deterioration diagnosis. When the input data after excluding the data of the tip and tail parts is x and the output data is y, the input data x and the output data y are defined by the following formulas (1) and (2).

Number

Number

[0036] The data usage determination unit 93 determines whether the input / output data preprocessed by the data preprocessing unit 92 is input data suitable for deterioration determination. For example, when the variation of the input data x preprocessed by the data preprocessing unit 92 is small, or when there is an offset between the input data x and the output data y, the data usage determination unit 93 determines that the input / output data of the rolled material M is not suitable for deterioration determination, and excludes the input / output data of the rolled material M from the diagnosis target.

[0037] Specifically, first, when the variation of the input data x is small, that is, when the standard deviation σ x of the input data x is smaller than a threshold value θ σx which is a predetermined reference value, it is determined that the input / output data of the corresponding rolled material M cannot be used, and the input / output data of the rolled material M is excluded from the diagnosis target. When the variation of the input / output data is small, the data usage determination unit 93 cannot accurately acquire the dynamic characteristics of the facility equipment, and there is a possibility of impairing the significance of the monitoring parameter described later which is an index of the degree of deterioration.

Number

[0038] Next, when there is an offset between the input data x and the output data y, the average value x of the input data x ave and the average value y of the output data y ave have a deviation that is a threshold value θ which is a predetermined reference value OFS or more, the data usage determination unit 93 determines that the input / output data of the corresponding rolled material M cannot be used, and excludes the input / output data of the rolled material M from the diagnosis target.

Number

[0039] The model identification unit 94 identifies an ARX model from the input / output data of the rolled material M not excluded by the data usage determination unit 93. The order of the ARX model includes the first order and the second order, and can be selected for each facility and equipment to be diagnosed. It is preferable to determine in advance the order of the ARX model suitable for the target facility and equipment through experiments or simulations.

[0040] The first-order ARX model is represented by the following formula (5).

Number

[0041] The model coefficients a 1_1 , b 1_1 to be identified are determined by the following formula (6) so that the sum of the squared errors between the output data y and the calculated values of the ARX model is minimized.

Number

[0042] Also, the second-order ARX model is represented by the following formula (7).

Number

[0043] The model coefficient a to be identified 1_1 , a 2_2 , b 1_2 is determined such that the sum of the squared errors between the output data and the calculated values of the ARX model is minimized.

Number

[0044] The model usage determination unit 95 determines whether the ARX model obtained by the model identification unit 94 can be used for response degradation diagnosis based on the signs of the coefficients of the ARX model. Specifically, in the case of a first-order ARX model, when Equation (9) is satisfied, and in the case of a second-order ARX model, when Equation (10) is satisfied, the monitoring parameter cannot be calculated using Equation (11) or (12) described later. Therefore, the model identification result of the rolled material M is excluded from the diagnosis target.

Number

Number

[0045] The monitoring parameter calculation unit 96 calculates the monitoring parameter using the model coefficients of the rolled material M that were not excluded by the model usage determination unit 95. As the monitoring parameter, the time constant τ is adopted for the first-order ARX model, and the damping coefficient ζ is adopted for the second-order ARX model.

[0046] In the case of a first-order ARX model, the time constant τ is calculated using the following Equation (11) and the model coefficient a 1_1 is used.

Number

[0047] In the case of a second-order ARX model, the model coefficient a 1_1, a 2_2 is used to calculate the damping coefficient ζ. First, according to the following formula (12), a 2_2 is used to calculate the product of the damping coefficient ζ and the natural angular frequency ω n . [Number] Here, T s represents the sampling pitch.

[0048] Next, according to the following formula (14), the product ζω n is used to calculate the natural angular frequency ω n . At this time, the calculation formula is switched with reference to the θ ζ calculated by the following formula (13). [Number] [Number]

[0049] Finally, according to the following formula (15), the damping coefficient ζ is calculated using the natural angular frequency ω n . [Number]

[0050] Figure 4 is a schematic diagram showing the functions of the monitoring parameter usage determination unit 97. With reference to the flow shown in Figure 4, the operation of the monitoring parameter usage determination unit 97 will be described. The monitoring parameter usage determination unit 97 has a classified monitoring parameter collection function 971 and an outlier exclusion function 972.

[0051] The classification monitoring parameter collection function 971 collects the monitoring parameters obtained by the monitoring parameter calculation unit 96 according to the classification specified by the rolling conditions (also referred to as "layer classification"), for example, on a daily basis. Here, the classification is specified by at least one rolling condition selected from steel grade, target plate thickness, target plate width, target coiling temperature, presence or absence of using a coil box, and by heating furnace. By managing the monitoring parameters in this way according to the classification specified by the rolling conditions, it is possible to prevent the monitoring parameters from being affected by the rolled material (material) M.

[0052] The outlier exclusion function 972 excludes the monitoring parameters that are outliers from the monitoring parameters for one day collected by the classification monitoring parameter collection function 971. Among the set of monitoring parameters x for one day for each classification, the monitoring parameter x that does not satisfy the following formula (16) is regarded as an outlier. An outlier is a sudden value or a value affected by manual intervention by the operator of the rolling line 1. Since such outliers cause a decrease in the deterioration determination accuracy, they are excluded by the outlier exclusion function 972.

Equation

[0053] Here, P 75 is the 75th percentile of the monitoring parameters for one day, P 25 is the 25th percentile of the monitoring parameters for one day, and α is an arbitrary magnification factor.

[0054] The representative value calculation unit 98 calculates the representative value of the set of monitoring parameters within a certain period for each section that was not excluded by the monitoring parameter usage determination unit 97. Specifically, the representative value calculation unit 98 calculates the average value or the median value of the set of monitoring parameters for a certain period of each section, and gives the calculated average value or median value as the representative value. At this time, when the outlier is excluded by the monitoring parameter usage determination unit 97 and the number of rolled products M in each section per day decreases, the distribution of the monitoring parameters may be biased, and there is a possibility of misdiagnosing as deterioration. In such a case, it may be possible not to calculate the representative value for the corresponding day. Further, the obtained representative values are plotted daily, and a deterioration failure date estimation function for calculating the days exceeding the threshold value from the intersection of the linearly approximated or polynomially approximated line and the set threshold value and predicting the days when deterioration occurs may be added to the representative value calculation unit 98.

[0055] The representative part storage unit 99 accumulates the representative values obtained by the representative value calculation unit 98 for each section, with the number of days specified in advance from the start date of monitoring as the learning period. At this time, the number of accumulated representative values may be counted for each section, and the period until the representative values for the specified number of days are accumulated may be used as the learning period.

[0056] FIG. 5 is a schematic diagram showing the functions of the deterioration diagnosis unit 100. With reference to the flow shown in FIG. 5, the operation of the deterioration diagnosis unit 100 will be described.

[0057] The deterioration diagnosis unit 100 has a normal value distribution parameter calculation function 101, a section-by-section deterioration determination function 102, and an overall deterioration determination function 103.

[0058] The normal value distribution parameter calculation function 101 obtains the set of daily representative values for each section in the learning period (for example, from X month X day to Y month Y day) accumulated in the representative part storage unit 99. The normal value distribution parameter calculation function 101 calculates, as the distribution parameters indicating the distribution of normal values, for example, the average value and the standard deviation of the daily representative values in the learning period from the set of daily representative values for each section obtained from the representative part storage unit 99.

[0059] The discrimination deterioration determination function 102 determines the presence or absence of deterioration for each category by comparing (collating) the representative value obtained by the representative value calculation unit 98 after the learning period with the distribution parameters obtained by the normal value distribution parameter calculation function 101. Although there are many such determination methods, the discrimination deterioration determination function 102 can use, for example, Hotelling's T 2 method, or a Shewhart control chart, or both, to make the determination.

[0060] First, the Hotelling's T 2 method will be explained. Assuming that the monitoring parameter serving as the population follows a normal distribution, the abnormality degree H for the j-th day (for example, the Z-th day of the Y-th month) is calculated using the representative value x rep (j) on the j-th day, the average value x rep,ave of the representative values for each day during the learning period, and the standard deviation σ x_rep .

Equation

[0061] An arbitrary threshold is set for the abnormality degree H, and when the threshold is exceeded, it is determined as deterioration. It has been theoretically proven that the abnormality degree H follows a chi-square distribution with 1 degree of freedom, and the probability that H takes a certain value can be obtained. For example, the probability that H = 3.84 is approximately 5%, the probability that H = 6.63 is approximately 1%, and the probability that H = 10.8 is approximately 0.1%. Referring to the relationship between the abnormal value H and the probability, the threshold for determining deterioration can be set.

[0062] Next, the determination method using a Shewhart control chart will be explained. Using the average value x rep,ave of the representative values for each day during the learning period as a reference, a constant multiple of the standard deviation σ x_rep in the positive and negative directions is used as the threshold, and when the representative value x rep (j) on the j-th day (for example, the Z-th day of the Y-th month) is outside the range of the threshold, it is determined as deterioration.

[0063] As another determination method used in the classification-based deterioration determination function 102, there is a method of using a constant multiple of the average value of the representative values for each day during the learning period as a threshold value and determining deterioration when the representative value exceeds the threshold value. Also, multiple threshold values may be prepared for one determination method, and the degree of deterioration may be determined step by step.

[0064] The comprehensive deterioration determination function 103 comprehensively determines (makes a final determination) the presence or absence of deterioration of the facility equipment from the deterioration diagnosis results (determination results) of each section obtained by the classification-based deterioration determination function 102. Specifically, every day, the ratio of the number of sections determined to have deterioration among the sections for which the presence or absence of deterioration was determined by the above classification-based deterioration determination function 102 on that date is calculated, and when it exceeds the threshold value, the equipment is determined to have deteriorated. By having the comprehensive deterioration determination function 103 in this way, even when the number of sections is large, deterioration can be determined accurately.

[0065] Note that the determination results of each section by the classification-based deterioration determination function 102 may be comprehensively determined with equal weighting, or may be comprehensively determined with different weightings for the determination results of each section. For example, for the determination results of sections of steel grades with a large number of rolling passes or for the determination results of steel grades that must be judged severely, the weight can be increased and comprehensively determined, and thereby, deterioration can be determined even more accurately.

[0066] As described above, according to the present embodiment, the monitoring parameters obtained by the data monitoring parameter calculation unit 96 are managed by the monitoring parameter use determination unit 97 for each specified section according to the rolling conditions at regular intervals, and the deterioration diagnosis unit 100 determines the presence or absence of deterioration of the facility equipment for each section. Thus, even when there is an interference that changes depending on the rolling conditions or the like between the facility equipment and the rolled material M, it is possible to provide the deterioration diagnosis device 9 that can accurately determine the presence or absence of deterioration of the facility equipment. Further, by comprehensively determining using the determination results of each section by the comprehensive deterioration determination function 103, even when the number of sections is large, accurate determination can be made. Also, by selecting input / output data suitable for deterioration determination by the data use determination unit 93 and excluding outliers from the set of monitoring parameters for each section by the outlier exclusion function 972, more accurate determination can be made.

[0067] Next, the specific structure of the deterioration diagnosis device 9 will be described. Although there is no limitation to the specific structure of the deterioration diagnosis device 9, it may be the following as an example. FIG. 6 is a conceptual diagram showing a hardware configuration example of a processing circuit included in the deterioration diagnosis device 9. Each part and each function constituting the deterioration diagnosis device 9 are realized 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.

[0068] When the processing circuit includes the processor 90a and the memory 90b, each function of the deterioration diagnosis device 9 is realized by software, firmware, or a combination of software and firmware. At least one of the software and the firmware is described as a program. At least one of the software and the 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, or 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, or an EEPROM, a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, a DVD, or the like.

[0069] When the processing circuit includes 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 combination thereof. For example, each function is realized by the processing circuit respectively. For example, each function is realized by the processing circuit collectively. Also, for each function, a part may be realized by dedicated hardware 90c and the other part may be realized by software or firmware. Thus, the processing circuit realizes each function by hardware 90c, software, firmware, or a combination thereof.

[0070] Although the embodiments of the present disclosure have been described above, the present disclosure is not limited to the above-described embodiments, and can be implemented with various modifications without departing from the spirit of the present disclosure. For example, in the above embodiment, as the target control device, the hydraulic cylinder constituting the rolling-down device 54 of the finishing rolling mill 5 has been described as an example, but it is not limited thereto, and it may be installed in a hot rolling line.

[0071] Also, when referring to numbers such as the number, quantity, amount, range, etc. of each element in the above embodiments, the present disclosure is not limited to the recited number, except when specifically stated or clearly specified by the principle. Further, the structures and the like described in the above embodiments are not necessarily essential to the present invention, except when specifically stated or clearly specified by the principle.

Description of Reference Numerals

[0072] 1…Rolling line, M…Rolled material, 5…Finishing rolling mill, F1 to F6…Rolling stands, 54…Gauge control device, 9……Deterioration diagnosis device, 91…Input / output data acquisition unit, 92…Data preprocessing 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…Function for collecting monitoring parameters by classification, 972…Function for excluding outliers, 98…Representative value calculation unit, 99…Representative part storage unit, 100…Deterioration diagnosis unit, 101…Function for calculating normal value distribution parameters, 102…Function for classifying and determining deterioration, 103…Function for comprehensively determining deterioration

Claims

1. A deterioration diagnosis device for rolling equipment that determines the presence or absence of deterioration of equipment installed on a rolling line, comprising: an input / output data acquisition unit that acquires input / output data input to and output from the equipment during rolling each time a rolled material is rolled once on 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 that calculates monitoring parameters from the parameters obtained by the model identification unit; a monitoring parameter usage determination unit having a function of collecting the monitoring parameters calculated by the monitoring parameter calculation unit separately for each category specified by the rolling conditions of the rolled material; a representative value calculation unit that calculates a representative value of a set of the monitoring parameters within a certain period for each category obtained by the monitoring parameter usage determination unit; a storage unit that accumulates the representative values obtained by the representative value calculation unit for each category during a specified learning period from the start of monitoring; a normal value distribution parameter calculation function that obtains distribution parameters indicating the distribution of normal values from a set of the representative values for each category accumulated in the storage unit, and a per-category deterioration determination function that collates the representative values obtained after the learning period by the representative value calculation unit and the distribution parameters obtained by the normal value distribution parameter calculation function to determine the presence or absence of deterioration for each category; A deterioration diagnosis device for rolling equipment.

2. The deterioration diagnosis device for rolling equipment according to claim 1, wherein the deterioration diagnosis unit has an overall deterioration determination function of determining the presence or absence of deterioration of the equipment based on the determination results for each category obtained by the per-category deterioration determination function.

3. The deterioration diagnosis device for rolling equipment according to claim 2, wherein the overall deterioration determination function calculates, for each of the certain periods, the ratio of the number of categories determined to have deterioration among the number of categories for which the presence or absence of deterioration is determined by the per-category deterioration determination function, and determines that the equipment has deterioration when the ratio exceeds a threshold value.

4. The model identification unit uses a first-order or second-order ARX model as the mathematical model, and gives the parameters of the mathematical model as the coefficients of the ARX model. The monitoring parameter calculation unit uses the monitoring parameter as a time constant or a damping coefficient. The deterioration diagnosis device for rolling equipment according to claim 1.

5. The deterioration diagnosis device for rolling equipment according to claim 1, further comprising a data usage determination unit that determines that the input / output data of the corresponding rolled material is unusable when the 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 equipment according to claim 1, further comprising a data usage determination unit that determines that the input / output data of the corresponding rolled material is unusable when the deviation between the average value of the input data and the average value of the output data acquired by the input / output data acquisition unit exceeds a threshold value.

7. The monitoring parameter usage determination unit further has an outlier exclusion function that calculates upper and lower limit values from percentiles of the set of monitoring parameters within a certain period for each section obtained by the section-by-section monitoring parameter collection function, and excludes monitoring parameters outside the range of the upper and lower limit values as outliers. The deterioration diagnosis device for rolling equipment according to claim 1.

8. The representative value calculation unit gives the median or average value of the set of parameters of the mathematical model within a certain period for each section after excluding the outliers as the representative value. The deterioration diagnosis device for rolling equipment according to claim 7.

9. The representative value calculation unit accumulates the calculated representative values, plots them daily, and has a deterioration failure date estimation function that calculates the date exceeding the threshold value from the intersection of the linearly approximated or polynomially approximated line and the set threshold value. The deterioration diagnosis device for rolling equipment according to claim 1.

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

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

12. The discrimination deterioration determination function is Hotelling's T ２ he method, or a Shewhart control chart, or both, is used in the deterioration diagnosis device for rolling equipment according to claim 1.

Images