JP7156569B1 - Anomaly detector - Google Patents

Abstract

An abnormality detection device according to one aspect is an abnormality detection device that detects an abnormality in a rolling system that rolls a material in a predetermined process, and before the process of determining whether the material satisfies predetermined specifications before the predetermined process. A specification determination unit, a post-process specification determination unit that determines whether or not a material after a predetermined process satisfies a predetermined specification, and an intervention operation amount extractor that extracts an operation amount that an operator has intervened in a predetermined process. and at least the post-process specification determination unit determines that the predetermined specifications are satisfied, and when the operation amount extracted by the intervention operation amount extraction unit exceeds the predetermined operation amount, a predetermined process and an output unit for outputting the result determined by the determination unit.

Description

The present invention relates to an abnormality detection device for detecting an abnormality in a rolling system.

For example, a rolling process for rolling steel or the like uses a rolling system that includes a hot rolling line and a cold rolling line and rolls a raw material (rolled material: material) in a plurality of lines or processes.

In addition, in the rolling process, anomalies may occur due to deterioration of equipment over time, etc., which may affect the quality of the raw material to be rolled.

For example, if the coolant balance of the rolling rolls is disturbed due to a valve abnormality or the like, shape abnormalities such as bending and runnability abnormalities such as off-center occur in the rolled material.

In addition, the operator monitors the state of the material and process data during operation, intervenes in the control based on the rolling conditions set in advance by the computer, and manually manipulates the rolling conditions in order to finish the material to the appropriate quality accuracy. are adjusted accordingly.

In this case, even if the quality accuracy of the raw material is maintained by the operator's skill and know-how, it is not recognized whether or not an abnormality has occurred in the rolling process. In general, early detection of process anomalies is a challenge for the entire equipment industry in order to prevent equipment anomalies that can seriously affect operations.

In addition, in the widely used statistical process control method, anomalies are detected from the results of the rolling process, such as the accuracy of the material after rolling and the stability of the rolling. It is judged that there was an abnormality in the rolling process including.

In addition, Patent Literature 1 discloses a model-based method for diagnosing abnormalities in a rolling process. A method based on data utilization is disclosed in Patent Document 2, for example.

In the abnormality diagnosis method disclosed in Patent Document 1, a sub-model expressing a plurality of mathematical formulas for predicting the state of a product being manufactured is created using the actual values of a plurality of types of variables in the manufacturing process obtained during normal operation. Estimate the cause of the anomaly using the scenario estimation list.

Here, for each piece of equipment that constitutes the manufacturing process, the material results before manufacturing, the equipment settings, the equipment results, the manual intervention results, the intermediate product status results, and the product results after manufacturing Create a sub-model that expresses the formula. Also, the rules used when estimating the cause of an abnormal state that has occurred in the manufacturing process are defined as a scenario inference list.

Then, the presence or absence of abnormality is detected for each submodel, and the cause of the abnormality in the manufactured product is estimated using the scenario inference list.

For example, the main factor (upstream factor) of the abnormal state of the manufacturing process at facility i is "facilities performance", and the secondary factor (downstream factor) of the abnormal state of the manufacturing process at facility k is "manual intervention performance". In this case, it is presumed that the cause of the abnormal state of the manufacturing process is that "an equipment failure occurred in the equipment i, and the operator operated the equipment k to compensate for the equipment failure, but a mistake occurred".

However, this diagnostic method searches for the equipment, setting, and manual intervention that caused the abnormality as the causal relationship when an abnormality occurs in the manufacturing performance. In other words, this diagnosis method does not include detecting whether there is an abnormality in the rolling process including equipment, regardless of whether there is an abnormality in the manufacturing performance.

In addition, Patent Document 2 discloses an abnormality diagnosis method that can clarify the causal relationship between the cause of an abnormality and the abnormal state, for a method and apparatus for diagnosing an abnormal state of equipment and product processes in a data rolling facility. It is

In addition, Patent Document 2 describes a method for diagnosing product process abnormal states by performing linear multivariate analysis, and a method for identifying causal relationships between abnormal causes and abnormal states using neural networks and genetic algorithms. It discloses a method of discarding unnecessary explanatory variables.

However, these diagnostic methods are also diagnostic methods for determining the cause of an abnormality that appears as a result of rolling from an abnormality in the rolling process, including an equipment abnormality.

Japanese Patent No. 6662222 Japanese Patent No. 3892614

As described above, conventionally, methods have been proposed for discovering a possible cause of an abnormality in the rolling process, such as equipment, when an abnormality occurs in a rolling result such as product quality or rolling stability. However, if the operator manually intervenes in the control to compensate for the rolling process abnormality and the rolling result is kept normal, the abnormality in the rolling process cannot be detected.

In the actual manufacturing process, an operator or the like often intervenes to adjust the rolling process so as to obtain the desired rolling result.

SUMMARY OF THE INVENTION The present invention is made to solve the above problems, and detects an abnormality occurring in a predetermined process even if the material after the predetermined process of processing the material satisfies a predetermined specification. It is an object of the present invention to provide an anomaly detection device capable of

An abnormality detection device according to one aspect of the present invention is an abnormality detection device that detects an abnormality in a rolling system that rolls a material in a predetermined process, and determines whether the material before the predetermined process satisfies predetermined specifications. a pre-process specification determination unit for determining whether or not a material after the predetermined process satisfies a predetermined specification; The intervention manipulated variable extracting unit for extraction and at least the post-process specification determining unit determine that the predetermined specifications are satisfied, and the manipulated variable extracted by the intervening manipulated variable extracting unit exceeds the predetermined manipulated variable. and an output unit for outputting the result determined by the determination unit.

Further, the abnormality detection device according to one aspect of the present invention is preferably characterized in that the determination unit determines whether or not there is an abnormality based on material specifications or criteria that differ from operator to operator.

Further, in the anomaly detection device according to one aspect of the present invention, the determination unit preferably determines whether or not there is an anomaly using a non-statistical method.

According to the present invention, it is possible to detect an abnormality occurring in a predetermined process even if the material after the predetermined process of processing the material satisfies the predetermined specifications.

1 is a diagram showing a configuration example of a rolling system and a process control system including an abnormality detection device that detects an abnormality in the rolling system; FIG. It is a figure which shows the structural example of the abnormality detection apparatus concerning one Embodiment. 4 is a flow chart showing an operation example of the abnormality detection device according to the embodiment; It is a figure which enumerates and shows the specific example of the process which an abnormality detection apparatus detects abnormality, the equipment deterioration which affects, and the operation which an operator intervenes manually. It is a figure which enumerates and shows the specific example of the process which an abnormality detection apparatus detects abnormality, the equipment deterioration which affects, and the operation which an operator intervenes manually.

An embodiment of an abnormality detection device for detecting an abnormality in a rolling system will be described below with reference to the drawings. FIG. 1 is a diagram showing a configuration example of a rolling system and a process control system 1 including an abnormality detection device for detecting an abnormality in the rolling system.

As shown in FIG. 1, a process control system 1 is configured by connecting two rolling systems, a hot rolling line 2 and a cold rolling line 3, to an abnormality detection device 4 via a control network 10, respectively. Then, the raw material (rolled material) is sequentially rolled by a plurality of rolling processes.

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

The hot rolling line 2 includes, for example, 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, It has a cooling device (ROT: Run Out Table) 24 and a winder (DC: Down Coiler) 25 . Further, the hot rolling line 2 is equipped with sensors 26-1 to 26-4, for example, and the operator operates the first control panel 27 so that the first controller 28 controls each part of the hot rolling line 2. configured to control.

In the hot rolling line 2 , a rough rolling mill 21 performs rough rolling on a slab output from a heating furnace 20 , and a crop shear 22 cuts the rolled material to a finishing mill 23 . In the hot rolling line 2 , the rough rolled material is further rolled to a predetermined specification by the finishing rolling mill 23 , cooled by the cooling device 24 , and then wound by the winder 25 . As described above, the hot rolling line 2 includes a plurality of steps to perform predetermined treatments on the rolled material.

Further, the sensor 26-1 is arranged, for example, on the delivery side of the roughing mill 21, detects the rolling performance data of the rolled material rolled by the roughing mill 21, and outputs it to the first control device 28. . For example, the sensor 26-1 is configured so that the first control device 28 can acquire the length, thickness, width, temperature, etc. of the rolled material at each of a plurality of different positions in the rolling direction (advancing direction of the rolled material). Detect each actual value in the rolling process.

The sensor 26 - 2 is arranged on the entry side of the finishing mill 23 , detects rolling performance data of the rolled material sent to the finishing mill 23 , and outputs the data to the first controller 28 . For example, the sensor 26-2 obtains actual values for the rolled material so that the first controller 28 can acquire the length, thickness, width, temperature, etc. of the rolled material at each of a plurality of different positions in the rolling direction. To detect.

The sensor 26 - 3 is arranged on the delivery side of the finishing mill 23 , detects rolling performance data of the rolled material rolled by the finishing mill 23 , and outputs it to the first controller 28 . For example, the sensor 26-3 collects each actual value in the rolling process so that the first controller 28 can acquire the length, thickness, width, temperature, etc. of the rolled material at each of a plurality of different positions in the rolling direction. To detect.

The sensor 26 - 4 is arranged on the output side of the cooling device 24 , detects rolling performance data of the rolled material cooled by the cooling device 24 , and outputs the data to the first control device 28 . For example, the sensor 26-4 may be used for each actual value after the cooling process so that the first control device 28 can acquire the length, thickness, width, temperature, etc. of the rolled material at each of a plurality of different positions in the rolling direction. to detect

Then, the first control device 28 transmits each rolling result data detected by the sensors 26-1 to 26-4 to the abnormality detection device 4 via the control network 10. FIG. The hot rolling line 2 is also provided with many other sensors (not shown), and transmits various data detected by the sensors to the abnormality detection device 4 .

The cold rolling line 3 includes, for example, a payoff reel 30, an entry-side shear 31, a welding machine 32, a looper 33, a rolling mill 34, an exit-side shear 35, a tension reel 36, a plurality of sensors 37, a second operation panel 38, and a 2 controller 39 . The cold rolling line 3 is configured such that the second control device 39 controls each part of the cold rolling line 3 by operating the second operation panel 38 by the operator.

The cold rolling line 3 further rolls the rolled material rolled by the hot rolling line 2 with the tail end of the coil of the rolled material wound by the winder 25 of the hot rolling line 2 as the leading end.

More specifically, the payoff reel 30 pays out the rolled material toward the entry side shear 31 with the tail end of the coil wound by the winder 25 as the leading end. The entry-side shear 31 and the exit-side shear 35 sandwich the material between front and rear pinch rolls (not shown) in order to straighten the leading end and trailing end of the rolled material. Cut the rolled material.

The welder 32 has a function of joining coils together by welding and making it possible to continuously perform a rolling process for a plurality of coils. The looper 33 stores the rolled material and supplies the rolled material to the rolling mill 34 at a constant rate.

The rolling mill 34 further rolls the rolled material. The tension reel 36 winds up the rolled material rolled by the rolling mill 34 . In this manner, the cold rolling line 3 includes a plurality of steps to perform predetermined treatments on the rolled material.

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

Then, the second control device 39 transmits each rolling performance data detected by each sensor 37 and the like to the abnormality detection device 4 via the control network 10 . The cold rolling line 3 is also provided with many other sensors (not shown), and transmits various data detected by the sensors to the abnormality detection device 4 .

In this manner, the process control system 1 rolls the rolled material by the hot rolling line 2 and the cold rolling line 3, and the abnormality detection device 4 receives actual time-series data and the like in each rolling process. Further, the abnormality detection device 4 receives information indicating operations performed on the first operation panel 27 and the second operation panel 38 by the operator. In other words, the abnormality detection device 4 collects the amount of operation performed by the operator on the hot rolling line 2 and the cold rolling line 3 .

Next, a configuration example of the abnormality detection device 4 will be described in detail. FIG. 2 is a diagram showing a configuration example of the abnormality detection device 4 according to one embodiment. The abnormality detection device 4 is, for example, a computer having a CPU, and includes a production information storage unit 40, a performance storage unit 41, an operation amount storage unit 42, a coincidence determination unit 43, a pre-process specification determination unit 44, and a post-process specification determination unit. 45 , an intervention operation amount extraction unit 46 , a determination unit 47 , and an output unit 48 .

The production information storage unit 40 pre-stores production information (production conditions, etc.) of the rolled material in the hot rolling line 2 and the cold rolling line 3 . The production information is, for example, computer data set in advance including the steel type of the raw material to be fed to the hot rolling line 2 and the cold rolling line 3, the product size, and the like.

The performance storage unit 41 stores performance time-series data transmitted by the hot rolling line 2 and the cold rolling line 3 . The actual time-series data is the result of each sensor detecting the rolled material processed in each process of the hot rolling line 2 and the cold rolling line 3 . For example, the actual time-series data is data relating to quality accuracy of rolled material, stability of rolling phenomena, quality problems other than accuracy, and the like.

The operation amount storage unit 42 stores information (time-series data) indicating operations (lever operation, gain adjustment, etc.) manually performed on the first operation panel 27 and the second operation panel 38 by the operator at his or her own discretion. do. In other words, the abnormality detection device 4 can collect the amount of operation performed by the operator on the hot rolling line 2 and the cold rolling line 3 .

The coincidence determination unit 43 acquires information indicating a process start operation to 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 stores the production information. The production information stored by the unit 40 is read. Also, the coincidence determination unit 43 determines whether the process executed in each process by the hot rolling line 2 or the cold rolling line 3 matches the read production information.

Next, the coincidence determination unit 43 identifies a process to be executed by the hot rolling line 2 or the cold rolling line 3 from among the plurality of production conditions stored in the production information storage unit 40 . Then, the coincidence determination unit 43 outputs the standard specifications that should exist before a predetermined process to the pre-process specification determination unit 44 . Also, the coincidence determination unit 43 outputs the standard specifications that should exist after a predetermined process to the post-process specification determination unit 45 . In addition, the coincidence determination unit 43 outputs to the determination unit 47 an operation amount (a reference operation amount: for example, a threshold) that an operator can normally intervene in a predetermined process.

The pre-process specification determination unit 44 compares the predetermined pre-process reference specification input from the coincidence determination unit 43 with the performance time-series data of the predetermined pre-process read out from the performance storage unit 41, and determines the pre-process specification. It is determined whether or not the rolled material in satisfies the predetermined specifications. In other words, the pre-process specification determining unit 44 quantifies the precision of the rolled material before a predetermined process and monitors changes. Then, the pre-process specification determination unit 44 outputs the determination result to the determination unit 47 .

The post-process specification determination unit 45 compares the standard specifications after the predetermined process input from the coincidence determination unit 43 with the performance time-series data after the predetermined process read from the performance storage unit 41, and determines the post-process specifications. It is determined whether or not the rolled material in satisfies the predetermined specifications. That is, the post-process specification determination unit 45 quantifies the accuracy of the rolled material after a predetermined process and monitors changes. Then, the post-process specification determination section 45 outputs the determination result to the determination section 47 .

The intervention operation amount extraction unit 46 reads information (time-series data) indicating the operations manually performed on the first operation panel 27 and the second operation panel 38 by the operator at his/her own judgment from the operation amount storage unit 42 . , the intervention operation amount indicating the operation amount manually intervened by the operator for each predetermined process in the hot rolling line 2 and the cold rolling line 3 , and output to the determination unit 47 . In other words, the intervention operation amount extraction unit 46 extracts the operator's operation amount, quantifies it, and monitors the change.

The determination unit 47 determines that at least the post-process specification determination unit 45 satisfies the predetermined specifications, and the operation amount (intervention operation amount) extracted by the intervention operation amount extraction unit 46 is a predetermined operation amount ( If it exceeds a reference manipulated variable (for example, a threshold value), it is determined that there is an abnormality in the predetermined process. Then, the determination unit 47 outputs the determined result to the output unit 48 .

The determination unit 47 determines whether there is an abnormality based on the specification of the rolled material input via the first operation panel 27 or the second operation panel 38, or a standard (for example, a specific condition) that differs for each operator. You may This is because it is conceivable that the operation amount to be intervened differs depending on the specification of the rolled material or each operator. Moreover, the determination unit 47 may determine whether or not there is an abnormality using a non-statistical method such as clustering.

In this way, based on the operation amount of the operator, the determination unit 47 determines whether or not the operator's operation is useful for maintaining the accuracy of the rolled material. is determined by logic and threshold.

The output unit 48 outputs the determination result input from the determination unit 47 . For example, the output unit 48 may output the determination results and process changes input from the determination unit 47 by displaying them on a display or the like, or output them by sound, light, or the like.

In other words, even if the production conditions are the same and the material accuracy (rolled material accuracy) after the process satisfies a predetermined specification, the abnormality detection device 4 detects the past data, etc., based on the operation amount of the operator in the process. , it is determined that the process is abnormal.

FIG. 3 is a flowchart showing an operation example of the abnormality detection device 4 according to one embodiment. As shown in FIG. 3, in step 100 (S100) of the abnormality detection device 4, the coincidence determination unit 43 selects the hot rolling line 2 or the cold rolling line 2 from among a plurality of production conditions stored in the production information storage unit 40 A process that the intermediate rolling line 3 performs in each step is specified.

In step 102 (S102), the pre-process specification determination unit 44 selects the predetermined pre-process reference specification input from the coincidence determination unit 43 and the predetermined pre-process performance time-series data read from the performance storage unit 41. By comparison, it is determined whether or not the rolled material before a predetermined process satisfies predetermined specifications.

In step 104 (S104), the post-process specification determination unit 45 selects the standard specification after the predetermined process input from the coincidence determination unit 43 and the performance time-series data after the predetermined process read from the performance storage unit 41. By comparing, it is determined whether or not the rolled material after the predetermined process satisfies the predetermined specifications.

In step 106 (S106), the intervention operation amount extraction unit 46 manipulates information (time-series data) indicating the operations manually performed on the first operation panel 27 and the second operation panel 38 by the operator's own judgment. It reads out from the quantity storage unit 42 and extracts each intervention operation amount indicating the operation amount manually intervened by the operator for each predetermined process in the hot rolling line 2 and the cold rolling line 3 .

In step 108 (S108), the determination unit 47 determines that at least the post-process specification determination unit 45 satisfies the predetermined specifications, and the operation amount (intervention operation amount) extracted by the intervention operation amount extraction unit 46 is If it exceeds a predetermined manipulated variable (reference manipulated variable: for example, threshold value), it is determined that there is an abnormality in the predetermined process.

At step 110 ( S<b>110 ), the output unit 48 outputs the determination result input from the determination unit 47 .

Next, a specific example of the operation of the abnormality detection device 4 will be described, taking bending of the material during rolling by the hot rolling line 2 as an example.

First, the match determination unit 43 uses the steel grade number, thickness division number, width division number, etc. of the material as input data from a computer (not shown) of production information (steel grade, product size, etc.) Decide on a different number. At this time, all materials are assigned a layer number, and the same layer number is regarded as the same production condition.

The pre-process specification determination unit 44 uses as input data actual time-series data of the material before the process (quality accuracy, instability of rolling phenomena, quality problems other than accuracy, etc.), and determines the amount of bending of the material on the delivery side of rough rolling. Quantify and monitor changes in the amount of bending of the material on the delivery side of rough rolling. As a monitoring method, the pre-process specification determination unit 44 uses, for example, a method of determining data exceeding a threshold value of 1σ based on an Xs control chart as abnormal.

The post-process specification judging section 45 uses actual time-series data of the material after the process (quality accuracy, instability of rolling phenomena, quality problems other than accuracy, etc.) as input data, and determines the amount of bending of the material on the delivery side of the finishing rolling. Quantify and monitor changes in the amount of bending of the material on the delivery side of the finishing rolling. As a monitoring method, the post-process specification determination unit 45 uses, for example, a method of determining data exceeding a threshold value of 1σ based on an Xs control chart as being abnormal.

The intervention operation amount extracting unit 46 uses the time-series data of the operator's operation amount (lever, gain, etc.) as input data, extracts and quantifies the operation amount of the gap leveling by the operator for the finish rolling process, and monitors the change in the operation amount. do. As a monitoring method, the intervention manipulated variable extracting unit 46 uses, for example, a method of judging data exceeding a threshold value of 2σ based on an Xs control chart as abnormal.

For example, the determination unit 47 determines the presence or absence of an abnormality in the process change and process of finish rolling or rough rolling as follows. The process changes include left-right imbalance of the gap caused by the rolls, left-right imbalance of the gap caused by the screw down device, and the like.

Then, the determination unit 47 determines the correlation between the operation amount of the operator and the post-process material accuracy using logic and a threshold value, and detects changes in the process.

For example, the determination unit 47 determines that the amount of bending of the material on the rough output side is normal with no change, and that the amount of bending of the material on the finishing output side is normal with no change, and that the operator's If the manipulated variable changes significantly, it may be determined that the operation has absorbed the process change.

In addition, the determination unit 47 determines that there is a change in the amount of bending of the material on the rough output side, there is no change in the amount of bending of the material on the finishing output side, and the accuracy is normal, and the operation amount of the operator changes greatly. If so, it may be determined that a change has occurred in both the current process and the previous process, or either one of them, and that the operation has absorbed the process change.

Specifically, for example, when the operation amount of the operator exceeds a threshold value of 2σ and the accuracy of the material after the process is within 1σ, the determination unit 47 performs the finish rolling process in which the coil is rolled. It is determined that there is a possibility of process abnormality.

The result determined by the determination unit 47 is displayed by the output unit 48 on, for example, a display.

Next, specific examples of the process (controlled object) in which the abnormality detection device 4 detects an abnormality and the operation (intervention method) in which the operator manually intervenes will be described. 4 and 5 are diagrams listing specific examples of the process (controlled object) in which the abnormality detection device 4 detects an abnormality, the equipment deterioration that affects it, and the operation (intervention method) that the operator manually intervenes. .

In the strip leveler intermesh <cold rolling/process>, the operator increases the amount of intermesh when the leveler pressing pressure changes.

In addition, in the shape control <cold rolling> of the cold-rolled steel sheet, when the roughness of the roll changes, the operator manually performs an intervening operation of bender/leveling by turning off the shape control or changes the target shape.

In addition, in the tension reel winding completion determination <cold rolling/process>, if the wear coefficient of the mandrel has deteriorated (roughness drop), the operator increases the speed lead rate or delays the winding completion timing.

In addition, in the bridle tension control (without tension meter) <cold rolling/process>, if there is a GD2 change in the bridle/gear (influenced by deterioration/insufficient grease), the operator should Then, the tension setting is increased to force the motor to generate torque.

Also, in the hot rolling CTC control <hot rolling>, if the on/off speed of the spray valve deteriorates, the operator switches to the fixed bank setting or adjusts the valve delay speed setting to the actual situation.

In addition, in the incoming/outgoing coil car position control <cold rolling/process>, if there is a drop in oil pressure or a change in the friction coefficient of the rail, the operator cannot stop at a predetermined position. I do.

In addition, in the thickness measurement <hot rolling/cold rolling> using a thickness gauge, if there is a decrease in the thickness gauge radiation source or an X-ray axis deviation, the operator adds an offset to the target thickness or performs AGC control. An operation is performed to add an offset to the thickness variation target (normally 0).

In addition, in the rolling mill speed control <hot rolling/cold rolling>, if there is a change in the resonance frequency due to deterioration of the rolling mill housing, rolls, gears, and motors, the operator should avoid the resonance speed range. Take action to change the schedule of steel plates to be performed or to occur.

Also, in the loop car position control <cold rolling/process>, if the loop car housing tilts or the swing mechanism fails (meandering or plate vibration increases), the operator should move the synchronous position to the short end side. Perform the operation to set so that the loop car does not go to the long end side.

Also, in the wiper roll control <cold rolling/process>, if the surface of the wiper roll (rubber roll) is deteriorated, the operator increases the pressing amount of the wiper roll.

In addition, in the straightness (meandering) of the plate in the furnace in the process line, if the characteristics of the furnace or the heating device deteriorate or change, the operator can additionally set the offset amount so that the actual result becomes the desired tension. to perform the operation.

In addition, in the SPM (skin pass mill) elongation rate, if the rigidity and reduction system of the skin pass mill deteriorate or change and the target load set by L2 (predetermined level 2) is not reached, the target value of the SPM load to change the settings.

As described above, the abnormality detection device 4 determines that at least the post-process specification determination unit 45 satisfies the predetermined specification, and the operation amount extracted by the intervention operation amount extraction unit 46 is a predetermined operation. Since it is determined that there is an abnormality in the predetermined process when the amount exceeds the amount, even if the material after the predetermined process of processing the material satisfies the predetermined specifications, an abnormality occurring in the predetermined process is detected. can do.

Each function of the abnormality detection device 4 may be configured partially or wholly by hardware such as a PLD (Programmable Logic Device) or FPGA (Field Programmable Gate Array), or may be executed by a processor such as a CPU. It may be configured as a program to

DESCRIPTION OF SYMBOLS 1... Process control system, 2... Hot rolling line (rolling system), 3... Cold rolling line (rolling system), 4... Abnormality detection device, 10... Control network, 20 ... heating furnace, 21 ... rough rolling mill, 22 ... crop shear, 23 ... finishing rolling mill, 24 ... cooling device, 25 ... winding machine, 26-1 to 26- 4... Sensor, 27... First operation panel, 28... First control device, 30... Payoff reel, 31... Entrance side shear, 32... Welding machine, 33... Looper 34... Rolling mill 35... Delivery side shear 36... Tension reel 37... Sensor 38... Second operation panel 39... Second controller 40. Production information storage unit 41 Result storage unit 42 Manipulated amount storage unit 43 Coincidence determination unit 44 Pre-process specification determination unit 45 Post-process specification determination Part, 46... Intervention operation amount extraction part, 47... Judgment part, 48... Output part

Claims (3)

In an abnormality detection device that detects an abnormality in a rolling system that rolls a material in a predetermined process,
a pre-process specification determination unit that determines whether the material before the predetermined process satisfies predetermined specifications;
a post-process specification determination unit that determines whether the material after the predetermined process satisfies predetermined specifications;
an intervention operation amount extraction unit that extracts an operation amount that an operator has intervened with respect to the predetermined process;
When at least the post-process specification determination unit determines that the predetermined specification is satisfied and the operation amount extracted by the intervention operation amount extraction unit exceeds a predetermined operation amount, the predetermined process A determination unit that determines that there was an abnormality in
and an output unit for outputting the result determined by the determination unit. The determination unit is
2. The abnormality detection device according to claim 1, wherein whether or not there is an abnormality is determined based on material specifications or criteria that differ from operator to operator. The determination unit is
3. The abnormality detection device according to claim 1, wherein whether or not there is an abnormality is determined using a non-statistical method.

Images