Anomaly detection apparatus

Abstract

An abnormality detection device of one embodiment detects an abnormality of a rolling system that rolls a raw material through a prescribed process, and includes: a pre-process specification determination unit that determines whether the raw material before the prescribed process satisfies a prescribed specification; a post-process specification determination unit that determines whether the raw material after the prescribed process satisfies the prescribed specification; an intervening operation amount extraction unit that extracts an operation amount in which an operator intervenes in the prescribed process; a determination unit that determines that there is an abnormality in the prescribed process at least when the post-process specification determination unit determines that the prescribed specification is satisfied and the operation amount extracted by the intervening operation amount extraction unit exceeds a predetermined operation amount; and an output unit that outputs a result of the determination by the determination unit.

Description

TECHNICAL FIELD

[0001] The present application relates to an abnormality detection device that detects an abnormality of a rolling system. BACKGROUND

[0002] For example, in a rolling process of rolling steel or the like, a rolling system or the like that has a hot rolling line and a cold rolling line and rolls a raw material (rolling material: material) in a plurality of lines or processes is used.

[0003] In addition, the rolling process sometimes has an abnormality due to the degradation of equipment over time or the like, and the quality of the rolled raw material is affected.

[0004] For example, if the coolant balance of a roll is broken due to a valve abnormality or the like, a shape abnormality such as bending or a travel abnormality such as eccentricity occurs on the raw material being rolled.

[0005] In addition, an operator monitors the state of the raw material and process data at the time of work, and in order to process the raw material into an appropriate quality precision, intervenes in control based on rolling conditions set in advance by a computer, and manually operates and adjusts the rolling conditions.

[0006] In this case, even if the quality precision of the raw material is maintained according to the skills and know-how of the operator, it cannot be known whether an abnormality has occurred in the rolling process. In general, in order to prevent equipment abnormalities that easily have a significant impact on work, early detection of abnormalities in the process is a technical problem for the entire equipment industry.

[0007] In addition, in a statistical process management method that is generally widely used, an abnormality is detected based on the precision of the raw material after rolling, the stability of rolling, or the like, and if there is an abnormality in the rolling result, it is determined that there is an abnormality in the rolling process including equipment abnormalities.

[0008] In addition, regarding abnormality diagnosis of the rolling process, a model-based method is disclosed in Patent Literature 1. A data utilization-based method is disclosed in, for example, Patent Literature 2.

[0009] In the abnormality diagnosis method disclosed in Patent Literature 1, a plurality of mathematical expression-based sub-models for predicting the state of a product in manufacturing are prepared using performance values of a plurality of variables in the manufacturing process at the time of normal work, and an abnormality cause is estimated using a scenario estimation list.

[0010] Here, for each device constituting the manufacturing process, a sub-model obtained by mathematically expressing the pre-manufacturing raw material performance correlation, the device setting correlation, the device performance correlation, the manual work intervention performance correlation, the intermediate product state performance correlation, and the post-manufacturing product performance correlation is created. In addition, a rule used when inferring the cause of the abnormal state occurring in the manufacturing process is defined as a causal inference list.

[0011] Then, for each sub-model, it is checked whether there is an abnormality, and the causal inference list is used to infer the cause of the abnormality in the post-manufacturing product.

[0012] For example, in a case where the primary factor (upstream side factor) of the abnormal state of the manufacturing process in the device i is "device performance" and the secondary factor (downstream side factor) of the abnormal state of the manufacturing process in the device k is "manual intervention performance", "a device abnormality occurred in the device i, and the operator operated the device k to compensate for the device abnormality but an error occurred" is inferred as the cause of the abnormal state of the manufacturing process.

[0013] However, this diagnosis method, when an abnormality occurs in the manufacturing performance, seeks a device, a setting, and a manual intervention that become the cause of the abnormality as a causal relationship. That is, in this diagnosis method, a case where it is checked whether there is an abnormality in the rolling process including the device regardless of whether there is an abnormality in the manufacturing performance is not included.

[0014] In addition, in Patent Literature 2, a diagnosis method and an apparatus for a device and a product process abnormal state in a rolling device or the like are disclosed, and an abnormality diagnosis method in which the causal relationship between the abnormality cause and the abnormality state is particularly clear is disclosed.

[0015] In addition, Patent Literature 2 discloses a method in which a linear multivariate analysis is performed to diagnose a product process abnormal state, and a method in which a neural network or a genetic algorithm is used to identify the causal relationship between the abnormality cause and the abnormality state, and a method in which an unnecessary explanatory variable that becomes an interference is discarded.

[0016] However, these diagnosis methods are all diagnosis methods for finding the cause of an abnormality found as a result of rolling as an abnormality of the rolling process including a device abnormality.

[0017] Prior Art Documents

[0018] Patent Literature

[0019] Patent Literature 1: Japanese Patent No. 6662222

[0020] Patent Literature 2: Japanese Patent No. 3892614 SUMMARY

[0021] Technical Problem to be Solved by the Invention

[0022] As described above, a method of finding a rolling process abnormality such as a device considered to be a cause when an abnormality occurs in a rolling result such as product quality, rolling stability, and the like has been conventionally proposed. However, in a case where an operator intervenes in control by manual operation to compensate for a rolling process abnormality so that a rolling result remains normal, an abnormality of a rolling process cannot be detected.

[0023] In an actual manufacturing process, an operator or the like intervenes to adjust a rolling process to obtain a desired rolling result.

[0024] The present application has been achieved in order to solve the above-described technical problem, and has an object to provide an abnormality detection device capable of detecting an abnormality occurring in a prescribed process even if a material after the prescribed process satisfies a prescribed specification.

[0025] Means for solving the technical problem

[0026] An abnormality detection device according to one embodiment of the present application detects an abnormality of a rolling system that rolls a material through a prescribed process, characterized by including: a pre-process specification determination unit that determines whether or not a material before the prescribed process satisfies a prescribed specification; a post-process specification determination unit that determines whether or not a material after the prescribed process satisfies a prescribed specification; an intervention operation amount extraction unit that extracts an operation amount by which an operator intervenes in the prescribed process; a determination unit that determines that there is an abnormality in the prescribed process at least in a case where the post-process specification determination unit determines that the prescribed specification is satisfied and the intervention operation amount extraction unit extracts an operation amount that exceeds a predetermined operation amount; and an output unit that outputs a result of the determination by the determination unit.

[0027] Further, the abnormality detection device according to one embodiment of the present application is characterized in that, preferably, the determination unit determines whether or not there is an abnormality on the basis of a specification of a material or a criterion that differs for each operator.

[0028] Further, the abnormality detection device according to one embodiment of the present application is characterized in that, preferably, the determination unit determines whether or not there is an abnormality using a non-statistical method.

[0029] Effects of the Invention

[0030] According to the present application, an abnormality occurring in a prescribed process can be detected even if a material after the prescribed process satisfies a prescribed specification. BRIEF DESCRIPTION OF DRAWINGS

[0031] Figure 1 is a diagram showing a configuration example of a process control system that includes a rolling system and an abnormality detection device that detects an abnormality of the rolling system.

[0032] Figure 2is a diagram showing a configuration example of an abnormality detection device of one embodiment.

[0033] Figure 3 is a flowchart showing an action example of an abnormality detection device of one embodiment.

[0034] Figure 4 is a diagram showing specific examples of a procedure in which an abnormality detection device detects an abnormality, equipment deterioration affected thereby, and an operator's manual intervention operation.

[0035] Figure 5 is a diagram showing specific examples of a procedure in which an abnormality detection device detects an abnormality, equipment deterioration affected thereby, and an operator's manual intervention operation. DETAILED DESCRIPTION

[0036] Hereinafter, one embodiment of an abnormality detection device that detects an abnormality of a rolling system will be described with reference to the drawings. Figure 1 is a diagram showing a configuration example of a process control system 1 provided with a rolling system and an abnormality detection device that detects an abnormality of the rolling system.

[0037] As shown in Figure 1 , the process control system 1 is configured by connecting, for example, two rolling systems, i.e., a hot rolling line 2 and a cold rolling line 3, to an abnormality detection device 4 via a control network 10, respectively, and rolling a raw material (rolling material) through a plurality of rolling processes in succession.

[0038] The control network 10 is, for example, a network such as a LAN (Local Area Network), and can be configured to include a control LAN and an information system LAN.

[0039] The hot rolling line 2 is configured, for example, by a heating furnace (RF: Reheating Furnace) 20, a roughing mill (RM: Roughing mill) 21, a crop shear (CS: Crop Shear) 22, a finishing mill (FM: Finishing Mills) 23, a cooling device (ROT: Run Out Table) 24, and a down coiler (DC: Down Coiler) 25. In addition, the hot rolling line 2 is configured to be provided with, for example, sensors 26-1 to 26-4, and an operator operates a first operation panel 27, whereby a first control device 28 controls each part configuring the hot rolling line 2.

[0040] In the hot rolling line 2, the rough rolling machine 21 rough-rolls the billet output from the heating furnace 20, and the cut-off machine 22 cuts the rolled material after the cutting to deliver it to the finish rolling machine 23. Then, in the hot rolling line 2, the finish rolling machine 23 further rolls the rolled material after the rough rolling to a prescribed gauge, the cooling device 24 cools it, and the coiler 25 coils it. Thus, the hot rolling line 2 includes a plurality of processes to perform prescribed processing on the rolled material.

[0041] In addition, the sensor 26-1 is arranged, for example, at the output side of the rough rolling machine 21, detects the rolling performance data of the rolled material after the rolling by the rough rolling machine 21, and outputs it to the first control device 28. For example, the sensor 26-1 detects each performance value in the rolling process, so that the first control device 28 can acquire the length, thickness, width, and temperature of the rolled material at each of a plurality of positions different in the rolling direction (the advancing direction of the rolled material).

[0042] The sensor 26-2 is arranged at the input side of the finish rolling machine 23, detects the rolling performance data of the rolled material delivered to the finish rolling machine 23, and outputs it to the first control device 28. For example, the sensor 26-2 detects each performance value of the rolled material, so that the first control device 28 can acquire the length, thickness, width, and temperature of the rolled material at each of a plurality of positions different in the rolling direction.

[0043] The sensor 26-3 is arranged at the output side of the finish rolling machine 23, detects the rolling performance data of the rolled material after the rolling by the finish rolling machine 23, and outputs it to the first control device 28. For example, the sensor 26-3 detects each performance value in the rolling process, so that the first control device 28 can acquire the length, thickness, width, and temperature of the rolled material at each of a plurality of positions different in the rolling direction.

[0044] The sensor 26-4 is arranged at the output side of the cooling device 24, detects the rolling performance data of the rolled material after the cooling by the cooling device 24, and outputs it to the first control device 28. For example, the sensor 26-4 detects each performance value after the cooling process, so that the first control device 28 can acquire the length, thickness, width, and temperature of the rolled material at each of a plurality of positions different in the rolling direction.

[0045] Also, the first control device 28 transmits each rolling performance data detected by the sensors 26-1 to 26-4 to the abnormality detection device 4 via the control network 10. In addition, the hot rolling line 2 is provided with a plurality of other sensors not shown, which transmit various data detected by the sensors to the abnormality detection device 4, respectively.

[0046] The cold rolling line 3 has, for example, an uncoiler 30, an input side shearing machine 31, a welding machine 32, a loop former 33, a rolling mill 34, an output side shearing machine 35, a tension reel 36, a plurality of sensors 37, a second operation panel 38, and a second control device 39. Also, the cold rolling line 3 is configured so that the operator operates the second operation panel 38, whereby the second control device 39 controls each part constituting the cold rolling line 3.

[0047] The cold rolling line 3 further rolls the rolled material after the rolling by the hot rolling line 2, taking the tail end of the coiled material rolled by the coiler 25 of the hot rolling line 2 as the leading end.

[0048] More specifically, the uncoiler 30 takes the tail end of the coiled material rolled by the coiler 25 as the leading end, and feeds the rolled material to the input side shearing machine 31. The input side shearing machine 31 and the output side shearing machine 35 clip and pass the rolled material by means of front and rear pinch rollers (not shown) in order to arrange the leading end and the tail end of the rolled material, and cut the rolled material according to the control of the second control device 39.

[0049] The welding machine 32 has a function of connecting coiled materials by welding to enable continuous rolling of a plurality of coiled materials. The loop former 33 stores the rolled material, and supplies a certain amount of the rolled material to the rolling mill 34.

[0050] The rolling mill 34 further rolls the rolled material. The tension reel 36 winds the rolled material after the rolling by the rolling mill 34. In this way, the cold rolling line 3 includes a plurality of processes to perform prescribed processing of the rolled material.

[0051] The plurality of sensors 37 are arranged around a plurality of stands provided in the rolling mill 34, and detect, for example, the thickness of the rolled material, and the like, and output to the second control device 39. Also, the sensors 37 can detect each actual value in the rolling process, so that the second control device 39 can acquire the length, width, and temperature of the rolled material at each of a plurality of positions different in the rolling direction.

[0052] Then, the second control device 39 transmits each rolling actual value data detected by each sensor 37 or the like to the abnormality detection device 4 via the control network 10. Also, a plurality of other sensors not shown are provided in the cold rolling line 3, and each of the various data detected by the sensors is transmitted to the abnormality detection device 4.

[0053] Thus, the process control system 1 rolls the rolling material by the hot rolling line 2 and the cold rolling line 3, respectively, and the abnormality detection device 4 receives the actual performance time series data and the like in each rolling process. In addition, the abnormality detection device 4 receives information indicating operations performed by the operator on the first operation panel 27 and the second operation panel 38. That is, the abnormality detection device 4 collects the operation amounts of the operator who operates the hot rolling line 2 and the cold rolling line 3.

[0054] Next, a configuration example of the abnormality detection device 4 will be described in detail. Figure 2 is a diagram indicating a configuration example of the abnormality detection device 4 according to an embodiment. The abnormality detection device 4 is, for example, a computer or the like provided with a CPU, and has a production information storage section 40, an actual performance storage section 41, an operation amount storage section 42, a coincidence determination section 43, a pre-process specification determination section 44, a post-process specification determination section 45, an intervening operation amount extraction section 46, a determination section 47, and an output section 48.

[0055] The production information storage section 40 stores production information (production conditions and the like) of the rolling material in the hot rolling line 2 and the cold rolling line 3 in advance. The production information is, for example, computer data set in advance including a steel type of a raw material to be fed to the hot rolling line 2 and the cold rolling line 3, a product size, and the like.

[0056] The actual performance storage section 41 stores the actual performance time series data transmitted from the hot rolling line 2 and the cold rolling line 3. The actual performance time series data is a result and the like obtained by each sensor detecting the rolling material processed in each process by the hot rolling line 2 and the cold rolling line 3. For example, the actual performance time series data is data related to a quality accuracy of the rolling material, a stability of a rolling phenomenon, a quality problem other than accuracy, and the like.

[0057] The operation amount storage section 42 stores information (time series data) indicating operations (lever operations, gain adjustments, and the like) manually performed by the operator on the first operation panel 27 and the second operation panel 38 based on his or her own judgment. That is, the abnormality detection device 4 can collect each operation amount of the operator who operates the hot rolling line 2 and the cold rolling line 3.

[0058] The coincidence determination section 43 acquires information indicating a process start operation of the hot rolling line 2 or the cold rolling line 3 input by the operator via the first operation panel 27 or the second operation panel 38, and reads out the production information stored by the production information storage section 40. In addition, the coincidence determination section 43 determines coincidence of a process performed in each process by the hot rolling line 2 or the cold rolling line 3 with the read-out production information.

[0059] Next, the conformity determination section 43 determines the process performed in each process by the hot rolling line 2 or the cold rolling line 3 from among the plurality of production conditions stored by the production information storage section 40. Then, the conformity determination section 43 outputs the prescribed pre-process reference specification to the pre-process specification determination section 44. In addition, the conformity determination section 43 outputs the prescribed post-process reference specification to the post-process specification determination section 45. In addition, the conformity determination section 43 outputs the amount of operation (reference operation amount: for example, threshold value, etc.) in which the operator can normally intervene in the prescribed process to the determination section 47.

[0060] The pre-process specification determination section 44 compares the reference specification of the prescribed pre-process input from the conformity determination section 43 and the actual performance time series data of the prescribed pre-process read out from the actual performance storage section 41, and determines whether the rolling material of the prescribed pre-process satisfies the prescribed specification. That is, the pre-process specification determination section 44 quantifies the accuracy of the rolling material of the prescribed pre-process and monitors the change. Then, the pre-process specification determination section 44 outputs the determination result to the determination section 47.

[0061] The post-process specification determination section 45 compares the reference specification of the prescribed post-process input from the conformity determination section 43 and the actual performance time series data of the prescribed post-process read out from the actual performance storage section 41, and determines whether the rolling material of the prescribed post-process satisfies the prescribed specification. That is, the post-process specification determination section 45 quantifies the accuracy of the rolling material of the prescribed post-process and monitors the change. Then, the post-process specification determination section 45 outputs the determination result to the determination section 47.

[0062] The intervention operation amount extraction section 46 reads out information (time series data) indicating the operation manually performed by the operator on the first operation panel 27 and the second operation panel 38 according to his or her own judgment from the operation amount storage section 42, extracts the intervention operation amount indicating the amount of operation in which the operator manually intervenes in each prescribed process in the hot rolling line 2 and the cold rolling line 3, and outputs it to the determination section 47. That is, the intervention operation amount extraction section 46 extracts the amount of operation by the operator, quantifies it, and monitors the change.

[0063] The determination section 47 determines that there is an abnormality in the prescribed process at least in the case where the post-process specification determination section 45 determines that the prescribed specification is satisfied and the amount of operation (intervention operation amount) extracted by the intervention operation amount extraction section 46 exceeds the amount of operation (reference operation amount: for example, threshold value) determined in advance. Then, the determination section 47 outputs the result of the determination to the output section 48.

[0064] Further, the determination unit 47 can determine whether there is an abnormality based on, for example, the gauge of the rolled material input via the first operation panel 27 or the second operation panel 38, or a criterion (for example, a specific condition) that differs for each operator. This is because the amount of intervention in the operation differs depending on the gauge of the rolled material or each operator. Further, the determination unit 47 can determine whether there is an abnormality using a non-statistical method such as clustering.

[0065] In this way, the determination unit 47 determines whether the operation of the operator contributes to maintaining the accuracy of the rolled material based on the amount of operation of the operator, with reference to the correlation between the amount of operation of the operator and the accuracy of the rolled material after the prescribed process, by logic and a threshold value, or the like.

[0066] The output unit 48 outputs the determination result input from the determination unit 47. For example, the output unit 48 can output by displaying the determination result or the process change input from the determination unit 47 on a display or the like, or can output by sound or light, or the like.

[0067] That is, even if the production conditions are the same, and the accuracy of the raw material after the process (the accuracy of the rolled material) satisfies the prescribed gauge, in a case where the amount of operation of the operator in the process deviates from past data or the like as a criterion, the abnormality detection device 4 determines that there is an abnormality in the process.

[0068] Figure 3 is a flowchart showing an example of the operation of the abnormality detection device 4 according to one embodiment. As shown in Figure 3 The determination unit 47 determines whether there is an abnormality in the process performed by the hot rolling line 2 or the cold rolling line 3 in each process based on the amount of operation of the operator, with reference to the correlation between the amount of operation of the operator and the accuracy of the rolled material after the prescribed process, by logic and a threshold value, or the like.

[0069] In step 102 (S102), the pre-process gauge determination unit 44 compares the prescribed pre-process reference gauge input from the agreement determination unit 43 and the pre-process actual time series data read out from the actual performance storage unit 41, and determines whether the rolled material before the prescribed process satisfies the prescribed gauge.

[0070] In step 104 (S104), the post-process gauge determination unit 45 compares the prescribed post-process reference gauge input from the agreement determination unit 43 and the post-process actual time series data read out from the actual performance storage unit 41, and determines whether the rolled material after the prescribed process satisfies the prescribed gauge.

[0071] In step 106 (S106), the intervention operation amount extraction section 46 reads out information (time series data) indicating operations manually performed by the operator on the first operation panel 27 and the second operation panel 38 based on his own judgment from the operation amount storage section 42, and extracts intervention operation amounts indicating operation amounts manually intervened by the operator in each prescribed process in the hot rolling line 2 and the cold rolling line 3, respectively.

[0072] In step 108 (S108), the determination section 47 determines that there is an abnormality in the prescribed process in a case where the process after-specification determination section 45 determines that the prescribed specification is satisfied and the operation amount (intervention operation amount) extracted by the intervention operation amount extraction section 46 exceeds a predetermined operation amount (reference operation amount: for example, a threshold value).

[0073] In step 110 (S110), the output section 48 outputs the determination result input from the determination section 47.

[0074] Next, a specific example of the operation of the abnormality detection device 4 will be described taking the bending of the material of the hot rolling line 2 at the time of rolling as an example.

[0075] First, the coincidence determination section 43 determines the layer number for the material using the steel grade number, the plate thickness classification number, the plate width classification number, and the like as input data from a computer not shown, as production information (steel grade, product size, and the like). At this time, all the materials are determined the layer number, and the same layer number is regarded as the same production condition.

[0076] The process before-specification determination section 44 quantifies the bending amount of the material on the rough rolling output side using the performance time series data of the material before the process (quality accuracy, instability of rolling phenomenon, quality problems other than accuracy, and the like) as input data, and monitors the change in the bending amount of the material on the rough rolling output side. The process before-specification determination section 44 uses, as a monitoring method, a method of determining data exceeding a threshold value of 1σ based on, for example, an X-s control chart as an abnormality.

[0077] The process after-specification determination section 45 quantifies the bending amount of the material on the finish rolling output side using the performance time series data of the material after the process (quality accuracy, instability of rolling phenomenon, quality problems other than accuracy, and the like) as input data, and monitors the change in the bending amount of the material on the finish rolling output side. The process after-specification determination section 45 uses, as a monitoring method, a method of determining data exceeding a threshold value of 1σ based on, for example, an X-s control chart as an abnormality.

[0078] The intervention operation quantity extraction unit 46 takes the time series data of the operator's operation quantity (lever, gain, etc.) as input data, extracts and quantifies the operator's operation quantity for gap adjustment in the finishing rolling process, and monitors changes in the operation quantity. As a monitoring method, the intervention operation quantity extraction unit 46 uses a method based on, for example, an X-s management chart to determine data exceeding a 2σ threshold as abnormal.

[0079] The determination unit 47 determines, for example, the process variations in finishing or roughing and whether there are any abnormalities in the process, as described below. Process variations include left-right imbalances in the gap caused by the rolls and left-right imbalances in the gap caused by the pressing device.

[0080] Then, the determination unit 47 uses logic and thresholds to determine the correlation between the operator's operation volume and the accuracy of the raw materials after the process, and detects changes in the process.

[0081] For example, the determination unit 47 may determine that the operation has absorbed the process change if the bending amount of the raw material on the roughing output side has not changed and is of normal accuracy, the bending amount of the raw material on the finishing output side has not changed and is of normal accuracy, and the operator's operation amount has changed significantly.

[0082] In addition, the determination unit 47 can also determine that the process of the process has changed in either the process of the roughing mill output side or the process of the previous process, and that the operation has absorbed the process change, if the bending amount of the raw material on the roughing mill output side changes, the bending amount of the raw material on the finishing mill output side does not change and is normal, and the operator's operation amount changes significantly.

[0083] Specifically, the determination unit 47 determines that the finishing rolling process of the coil may have a process abnormality, for example, if the operator's operation volume exceeds the threshold of 2σ and the accuracy of the raw material after the process is within 1σ.

[0084] The result determined by the determination unit 47 is displayed by the output unit 48 on a screen, such as a display.

[0085] Next, specific examples will be given of the process (controlled object) in which the anomaly detection device 4 detects anomalies and the operation (intervention method) in which the operator manually intervenes. Figure 4 , Figure 5 This diagram illustrates specific examples of the abnormality detection device 4 detecting abnormalities in the process (controlled object), the resulting equipment deterioration, and the operator's manual intervention (intervention method).

[0086] In the strip straightening machine's cross-grid section (cold rolling / process), the operator increases the amount of cross-grid when the straightening machine's pushing pressure changes.

[0087] Further, the operator manually performs an intervention operation of a bender / leveler of shape control off in the shape control of a cold-rolled steel sheet <cold rolling> or a target shape change in the case where roughness of a roll is changed.

[0088] Further, the operator performs an operation of increasing a speed lead ratio or delaying a winding completion time in the case where there is a deterioration (roughness reduction) of a wear coefficient of a mandrel in the winding completion determination for a tension reel <cold rolling / process>.

[0089] Further, the operator performs an operation of increasing a tension setting to make the motor generate a torque in order to make a belt / gear not slack in the case where there is a GD2 change (an influence caused by deterioration / insufficiency of lubricant) of the belt / gear in the tension control (tension meterless) <cold rolling / process>.

[0090] Further, the operator performs an operation of switching to a fixed piece setting or making a valve delay speed setting consistent with an actual state in the case where there is an opening / closing speed deterioration of a jet valve in the hot rolling CTC control <hot rolling>.

[0091] Further, the operator performs a fine adjustment operation by a fine operation in the case where a hydraulic source is reduced and a friction coefficient of a guide rail is changed and a stop at a prescribed position is not possible in the coil moving car position control <cold rolling / process>.

[0092] Further, the operator performs an operation of adding an offset to a target sheet thickness or adding an offset to a sheet thickness variation target (usually 0) of AGC control in the case where a sheet thickness gauge line source is reduced and there is an X-ray axis deviation in the sheet thickness gauge measurement <hot rolling / cold rolling>.

[0093] Further, the operator performs an operation of performing work avoiding a resonance speed region or changing a schedule of a steel sheet generated in the case where there is a change in a resonance frequency caused by deterioration of a mill housing, a roll, a gear, and a motor in the speed control of a rolling mill <hot rolling / cold rolling>.

[0094] Further, the operator performs an operation of setting a synchronous position on a short end side and setting the ring car not to travel toward a long end in the case where there is a tilt of a ring car housing and a failure (a snake or a large vibration of a sheet) of a swing mechanism in the ring car position control <cold rolling / process>.

[0095] Further, the operator performs an operation of increasing a pressing amount of a wiping roll in the case where there is surface deterioration of a wiping roll (a rubber roll) in the wiping roll control <cold rolling / process>.

[0096] Further, the operator performs an operation of adding a set offset amount to make the actual performance a desired tension in straightness (snaking) of the slab in the furnace on the process line in a case where the characteristics of the furnace or the heating device are deteriorated / changed.

[0097] Further, the operator performs an operation of changing the target value of the SPM load by setting in a case where the rigidity of the skin pass mill, the press-down system is deteriorated / changed, and L2 (a prescribed level 2) does not reach the set target load in the SPM elongation.

[0098] As described above, the abnormality detection device 4 determines that there is an abnormality in the prescribed process in a case where the process after process specification determination section 45 determines that the prescribed specification is satisfied and the operation amount extracted by the intervening operation amount extraction section 46 exceeds the predetermined operation amount, and thus can detect an abnormality occurring in the prescribed process even if the prescribed process of the raw material satisfies the prescribed specification.

[0099] Further, a part or all of each of the functions of the abnormality detection device 4 can be respectively constituted by a hardware such as a PLD (Programmable Logic Device) or an FPGA (Field Programmable Gate Array), or can be constituted by a program executed by a processor such as a CPU.

[0100] Explanation of Reference Numerals

[0101] 1 • • • process control system; 2 • • • hot rolling production line (rolling system); 3 • • • cold rolling production line (rolling system); 4 • • • abnormality detection device; 10 • • • control network; 20 • • • heating furnace; 21 • • • rough rolling mill; 22 • • • crop shear; 23 • • • finish rolling mill; 24 • • • cooling device; 25 • • • coiling machine; 26-1 to 26-4 • • • sensor; 27 • • • first operation panel; 28 • • • first control device; 30 • • • uncoiler; 31 • • • input side shear; 32 • • • welding machine; 33 • • • looping machine; 34 • • • rolling mill; 35 • • • output side shear; 36 • • • tension reel; 37 • • • sensor; 38 • • • second operation panel; 39 • • • second control device; 40 • • • production information storage section; 41 • • • actual performance storage section; 42 • • • operation amount storage section; 43 • • • coincidence determination section; 44 • • • process before process specification determination section; 45 • • • process after process specification determination section; 46 • • • intervening operation amount extraction section; 47 • • • determination section; 48 • • • output section.

Claims

1. An anomaly detection device for detecting anomalies in a rolling system that rolls raw materials through a prescribed process, characterized in that, having: a pre-process specification judgment unit that judges whether or not a raw material before the prescribed process satisfies a prescribed specification; a post-process specification judgment unit that judges whether or not a raw material after the prescribed process satisfies a prescribed specification; an intervention operation amount extraction unit that extracts an operation amount by which an operator intervenes in the prescribed process; a judgment unit that judges that there is an abnormality in the prescribed process at least when the post-process specification judgment unit judges that the prescribed specification is satisfied and the operation amount extracted by the intervention operation amount extraction unit exceeds a predetermined operation amount; and an output unit that outputs a result of the judgment by the judgment unit.

2. The abnormality detection device according to claim 1, wherein the judgment unit judges whether or not there is an abnormality based on a specification of a raw material or a criterion that differs for each operator.

3. The abnormality detection device according to claim 1, wherein the judgment unit judges whether or not there is an abnormality using a non-statistical method. ​ ​ ​

Images