KR101829137B1 - Device abnormality early alarm method including decision for device improtance and alarm validation, and system using thereof - Google Patents

Abstract

The present invention provides a method and system for early warning of an abnormality of a device including device importance and alarm validity judgment. The early warning method of the device abnormality symptom is a first step of judging whether or not the device monitoring signal value exceeds the normal operation range by using a weight based on the importance data by monitoring variables previously analyzed by the operator in the early warning processing device A second step of generating an alarm when the device monitoring signal value exceeds the normal operation range in the early warning processing device and a second step of determining whether the generated alarm is a valid alarm to be analyzed and monitored, It includes three steps.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to an apparatus and method for early warning of an abnormality of apparatus including apparatus importance and determination of effectiveness of an alarm,

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an alarm apparatus abnormality alarm, and more particularly,

In the past, monitoring data such as temperature and pressure was acquired from a measuring device to determine an abnormality of a device at a power plant and an alarm was generated. The current value and the predicted value of the data were compared with each other to determine whether the device was abnormal. The current early warning system is implemented as a principle that represents the difference between the current value of the instrument monitoring variable and the predicted value calculated by the early warning program and generates an alarm if the residual is outside the normal operating range of the instrument monitoring variable.

1 is a configuration diagram of a conventional early warning system. Referring to FIG. 1, a conventional early warning system includes a meter 100 for measuring the state of power plant equipments, a monitoring signal (for example, pressure, temperature, flow rate, etc.) acquired from the meters 100 An early warning processing unit 120 for generating an early warning by analyzing the converted data, and an operator computer 120 for inquiring about the device status and early warning status, (130).

2 is a flowchart of a conventional early warning method. As shown in FIG. 2, the data processing apparatus 110 receives meter signals from the meters (S200).

Since the received meter signals are analog signals, the data processing unit 110 converts the digital signals into digital data (S210).

The data processing apparatus 110 then calculates current values of the instrument signals in real time (S220).

The early warning processor 120 receives the past instrument signal data of the predetermined period through the data processing step from the data processing apparatus 110 to generate a pattern learning model in advance (S230).

The calculated current values are transmitted to the early warning processor 120, and the early warning processor 120 calculates predicted values using the pattern learning model previously generated (S240).

The residuals (i.e., the current value - the predicted value |) are calculated using the current values and the predicted values (S250).

The residuals are compared with a normal operating range of each preset monitoring variable (e.g., pressure, temperature, flow rate, etc.) (S260). When the residual is out of the normal operating range, an alarm is generated (S270) and an alarm is not generated unless the residual is out of the normal operating range. At this time, the normal operation range for alarm generation can be adjusted by the operator.

Upon occurrence of an alarm, the early warning processor 120 transmits alarm status information to the operator computer 130 so that the operator can inquire the alarm status information (S280).

However, such an early warning system has the following problems.

There are hundreds of devices to be monitored at the power plant, and the monitoring variables range from 1,000 to 2,000 / unit. Therefore, when an alarm is generated in the above-described manner, an alarm occurs very frequently, and the operator takes much time to check and analyze the alarm.

In addition, since the importance of the devices is not considered, there is a problem that the operator has to judge the importance of the alarm every time the alarm occurs.

In addition, after the occurrence of an alarm, it is impossible to distinguish whether the alarm is an alarm caused by an abnormality of an actual apparatus or an alarm caused by a replacement operation of a previously planned apparatus, a test, or maintenance. Therefore, there is a problem that the operator must perform alarm analysis every time an alarm is generated to determine the validity of the alarm.

Therefore, it is necessary for the operator to efficiently operate the early warning system by causing an alarm only in the abnormal state of the actual equipment in advance.

An object of the present invention is to provide an apparatus and a method for adjusting the frequency of occurrence of an alarm according to the importance of the apparatus, Method and system.

According to an aspect of the present invention, there is provided an apparatus alarm early warning method including device importance and alarm effectiveness determination. The early warning method of the device abnormality symptom is a first step of judging whether or not the device monitoring signal value exceeds the normal operation range by using a weight based on the importance data by monitoring variables previously analyzed by the operator in the early warning processing device A second step of generating an alarm when the device monitoring signal value exceeds a normal operation range in the early warning processing device, and a second step of determining in the alarm determining device whether the generated alarm is a valid alarm, And a third step.

The first step includes a step of analog-to-digital conversion of the monitoring signals received from the measuring devices and a calculation of the current value of the monitoring signals in the data processing device, and the current value is transmitted to the early warning processing device and the importance classifying device at predetermined time intervals Step < / RTI >

The first step may further include searching, in the importance classification apparatus, the importance level and the weight of the monitored variable corresponding to the received current value from the importance database and transmitting the search result to the early warning processing apparatus.

The first step may further include a step of calculating a residual using the current value and the weight and the pattern learning model constructed in advance in the early warning processor.

The first step may further include the step of determining whether the early alarm processing apparatus is out of a normal operation range preset by an operator using the residual.

In the third step, when the alarm is generated, the alarm determination device may include a step of receiving the alert status information and classifying the alarm status into a predicted alert and an analysis target alert.

The anticipated alarm may correspond to at least one of a generator main alarm occurrence alarm, an occurrence alarm caused by the device replacement operation, and an alarm generated by a pre-planned test or maintenance.

If the alarm is the alarm to be analyzed, if the alarm is analyzed by the integration center operator and it is determined that the monitoring of the power plant is necessary as a result of the trace, the alarm determination device notifies the occurrence of the alarm to at least one of the power plant operator computer and the power station operator personal radio communication device .

According to another aspect of the present invention, there is provided an apparatus abnormality early warning system including device importance and alarm validity determination. The device early warning system uses the weight based on the importance data of each monitoring variable analyzed by the operator to determine whether the device monitoring signal value exceeds the normal operation range, And an alarm determination device for determining whether the generated alarm is a valid alarm to be analyzed and tracked.

The device abnormality early warning system includes a data processing unit for analog-to-digital converting the monitoring signals received from the measuring devices, calculating a current value of the monitoring signals, and transmitting the calculated values to the priority alarm processing device and the importance classification device at predetermined time intervals As shown in FIG.

The apparatus abnormality warning early warning system may further include the importance classifying apparatus for searching the importance database for the importance level and the weight of the monitored variables corresponding to the current value transmitted thereto and transmitting the retrieved importance level database to the early warning processing apparatus.

The early warning processor can calculate a residual using the received current value, the weight, and a pre-built pattern learning model.

The early warning processor can determine whether the operator is out of the normal operating range set in advance by using the residual.

When the alarm is generated, the alarm determination device may receive the current status information of the alarm and classify the alarm as the predicted alarm and the analysis target alarm.

The anticipated alarm may correspond to at least one of a generator main alarm occurrence alarm, an occurrence alarm caused by the device replacement operation, and an alarm generated by a pre-planned test or maintenance.

If the alarm is the alarm to be analyzed, if the alarm is analyzed by the integration center operator and it is determined that the monitoring of the power plant is necessary as a result of the trace, the alarm determination device notifies the occurrence of the alarm to at least one of the power plant operator computer and the power station operator personal radio communication device .

The apparatus and method of early warning of abnormality of the apparatus including the apparatus importance and alarm validity determination of the present invention can minimize the labor requirement for early alarm analysis by reducing the occurrence frequency of alarms with low importance, Can also be used effectively to prevent equipment and power station shutdown by quickly detecting and generating alarms.

Also, by separating the generated alarms into alarms that need to be traced and analyzed and unnecessary alarms, it is possible to efficiently operate an early warning system of multiple units with a small number of personnel.

1 is a configuration diagram of a conventional early warning system.
2 is a flowchart of a conventional early warning method.
3 is a block diagram of an early warning system according to an embodiment of the present invention.
4 is a flowchart of an early warning method according to an embodiment of the present invention.

While the invention is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and will herein be described in detail. It is to be understood, however, that the invention is not to be limited to the specific embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention.

The terms including the first, second, etc. may be used to describe various elements, but the elements are not limited to these terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component. The term " and / or " includes any combination of a plurality of related entry items or any of a plurality of related entry items.

When an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, but other elements may be present in between. On the other hand, when an element is referred to as being "directly connected" or "directly connected" to another element, it should be understood that there are no other elements in between.

The terminology used in this application is used only to describe a specific embodiment and is not intended to limit the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In the present application, the terms "comprises" or "having" and the like are used to specify that there is a feature, a number, a step, an operation, an element, a component or a combination thereof described in the specification, Should not be construed to preclude the presence or addition of one or more other features, integers, steps, operations, elements, parts, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the contextual meaning of the related art and are to be interpreted as either ideal or overly formal in the sense of the present application Do not.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Reference will now be made in detail to the preferred embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the like elements throughout. The description will be omitted.

3 is a block diagram of an early warning system according to an embodiment of the present invention. 3, the early warning system of the present invention includes an instrument 100 for measuring the state of power plant equipment, monitoring signals (for example, pressure, temperature, flow data, etc.) acquired from the instruments 100, An early warning processing unit 120 for analyzing the converted data and generating an early warning based on the importance of each monitored signal, An importance classifying unit 140 for classifying the collected surveillance signals according to the degree of importance, an alarm determining unit 150 for determining the validity of the alarm when the alarm is generated, An integration center operator computer 130 for receiving and inquiring an alarm status, a power plant operator computer 160 for receiving an alarm status only in the case of a valid alarm, Line communication device 170. [

The meter 100 is installed at or around the power plant equipment to measure the state (e.g., pressure, temperature, flow rate, etc.) of the devices and transmits the monitoring data to the data processing device 110 by wire. The transmission interval can be transmitted at a time interval specified by the operator (for example, at intervals of 1 second).

The data processing apparatus 110 includes an analog-to-digital converter to convert the analog monitoring data received from the meter 100 into digital monitoring data. The digital surveillance data is transmitted through the wired communication link to the early warning processing device 120 and the importance classifying device 140.

The early warning processing device 120 generates a pattern learning model using past transmitted monitoring data (for example, 18 months). Also, the transmitted monitoring data value is compared with the predicted value of the pattern learning model generated beforehand to determine whether or not the operation is normal, and an alarm is generated. When the current monitoring data value is compared with the predicted value, it is determined whether the normal operation is performed by applying the importance of each monitoring variable stored in the importance classification device.

The importance classifying apparatus 140 includes an importance database.

The importance database includes all the monitoring variables of the devices operating at the nuclear power plant, and information that classifies the importance of each monitored variable according to the importance classifying criteria predetermined by the operator is stored.

For example, variables affecting plant shutdown (grade A) by monitoring variables, variables that have no effect on plant shutdown but affect single plant shutdown (class B), and variables that do not affect shutdown ) Can be classified into three types can be stored.

For example, the feed pump bearing temperature can be classified as Class B, which can cause feed pump shutdown in case of a sudden rise, and the turbine bearing vibration can be classified as Class A, .

In addition, the importance database stores the weight for each grade designated by the operator to be used for calculating the predicted value. For example, the weight for each grade can be set to 1.2 to 1.5 for the A grade, 1.1 to 0.9 for the B grade, and 0.8 to 0.6 for the C grade.

)가 더욱 커지는 효과가 있어 작은 변화에도 경보가 발생한다. 따라서, 중요한 감시변수의 경우 미세한 변화도 감지할 수 있다. When the weights are determined as described above, in the case of the monitoring variables having the high importance degree,

) Is increased, and an alarm is generated even in a small change. Thus, in the case of important monitoring variables, even minute changes can be detected.

In the case of low importance monitoring variables, the effect of reducing residuals is reduced, so that alarms are generated only when the variation is very large, which can greatly reduce alarm frequency.

The importance level and the weight for each grade can be determined by the operator based on the contents described in the various operating procedures of the nuclear power plant and the operation experience of the operator.

The importance classifying apparatus 140 judges to which importance the monitoring data transmitted from the data processing apparatus 110 corresponds to the importance information stored in the importance database.

The alarm determination device 150 automatically sends the alarm status to the power plant operator computer 160 and the power station operator personal wireless communication device 170 when it is determined that the generated alarm is a valid alarm requiring notification and action to the power plant. The valid alarm determination may be made, for example, in the case where the same alarm occurs in the power main control room (MCR) (i.e., when the monitoring data value reaches a preset value and an alarm is generated) Whether it is an alarm generated by a pre-planned test or maintenance, and judges that only those alarms not corresponding to this case are valid alarms.

4 is a flowchart of an early warning method according to an embodiment of the present invention. Referring to FIG. 4, the data processing apparatus 110 receives meter signals from the meters (S400).

Since the received meter signals are analog signals, the data processing apparatus 110 performs an analog-digital conversion step of converting the digital data into digital data (S410). The converted digital data is transmitted to the early warning processing device 120.

The data processing apparatus 110 then calculates the current value of the instrument signals at predetermined time intervals (for example, 1 second intervals) (S520), and calculates the current values of the instrument signals by using the early warning processing apparatus 120 and the importance classification apparatus 140 send.

The importance classification apparatus 140 determines the importance of the current value received from the data processing apparatus 110 (S460). The importance determination is performed by searching a value stored in the importance database of the importance classifier 140 for the importance level and the weight of the monitored variable corresponding to the transmitted current value. For example, if the current value received is the feed pump bearing temperature data, the importance level of the feed pump bearing temperature stored in the importance database and the weight of the corresponding grade are retrieved.

The early warning processing device 120 generates a pattern learning model using the past monitoring data of a predetermined period (for example, 18 months) through the analog-digital conversion step (S410) transmitted from the data processing apparatus 110 (S430).

The early warning processor 120 calculates predicted values using the received current values and a previously generated pattern learning model (S440). That is, the present value is compared with the learning value of the pattern learning model at a predetermined time interval (for example, at intervals of 1 second), and a similar pattern is found to calculate a predicted value.

)을 계산한다(S450).Then, using the current values and the predicted values, the residual a (i.e.,

(S450).

)을 계산한다(S470). 조기경보처리장치(120)에는 잔차a를 실시간으로 계산하면서 중요도분류장치(140)로부터 동일 감시변수의 가중치를 찾아내는 기능이 포함되어 실시간으로 잔차b가 계산될 수 있다. Using the calculated residuals a and the weights corresponding to the importance of the monitoring variables determined in the importance classifying apparatus 140,

(S470). The early warning processing device 120 includes a function of finding the weight of the same monitoring variable from the importance classifying apparatus 140 while calculating the residual a in real time and the residual b can be calculated in real time.

The calculated residuals b are compared with the normal operating range of each preset monitoring variable (S480).

When the residual b is out of the normal operating range, an alarm is generated (S490). If the residual b does not exceed the normal operating range, no alarm is generated.

At this time, the normal operation range for alarm generation can be adjusted by the operator. For example, the normal operation range of the feed pump is 45 (minimum) to 55 (maximum), and the deviation between the minimum value and the maximum value is 10. If the residual is programmed to generate an alarm when it exceeds 30% (± 3) of the [maximum-minimum] deviation (10) of the normal operating range, the residual is 8 if the current value entered is 60 and the calculated predicted value is 52 And an alarm occurs in excess of 30% of the deviation. Conversely, if the current value is 43 and the predicted value is 45, the residual is 2 and no alarm is generated.

Upon occurrence of an alarm, the early warning processor 120 transmits alarm status information to the integration center operator computer 130, which monitors all power plants, so that the operator can inquire the alarm status information (S500). At the same time, the alarm status information is transmitted to the alarm determination device 150.

The alarm determination device 150 receives the alarm status information and performs an alarm validity determination process.

First, the alarm determination device 150 classifies the types of alarms received and determines an analysis target (S510).

For example, in the alarm determination device 150, whether the alarm generated is the same alarm in the power main control room (MCR), alarm generated by the device replacement operation, And if any of them is applicable, it is stored in the alert list, and all of the alarms are stored in the analysis target alarm list.

The alarms stored in the alarm list to be analyzed are subjected to alarm tracking / analysis by the integration center operator (S520). As a result, when it is determined that the power plant is required to be inspected, the alarm is notified to the power plant operator computer 160 and the personal wireless communication apparatus 170 of the power plant operator (or the person in charge of the apparatus). If it is determined that a power plant inspection is unnecessary, monitor the trends continuously and perform additional analysis if necessary.

In the foregoing, a number of embodiments of the present invention have been described. Nevertheless, it should be understood that the foregoing description is intended to be illustrative and not restrictive of the scope of the invention, which is defined by the scope of the following claims. Accordingly, other embodiments are also within the scope of the following claims. For example, various modifications may be made without departing from the scope of the present invention. Additionally, some of the steps described above may be performed in a different order than described, since they are order independent.

100: Meter 110: Data processing device
120: early warning processing device 130: integration center operator computer
140: Priority classifying device 150: Alarm judging device
160: Power station operator computer 170: Power station operator Personal wireless communication device

Claims (16)

A device alarm early warning method comprising device importance and alert validity determination,
Storing, in an importance database, information classified in importance according to monitoring variables previously analyzed according to an importance classification standard previously designated by an operator in an importance classification apparatus;
Calculating a current value of the monitoring signals received from the measuring device, searching the importance database for the importance value and the weight of the monitored variable corresponding to the calculated current value, and transmitting the detected value to the early warning processor;
Determining whether the device monitoring signal value exceeds a normal operation range by using a weight based on the information classified by the preliminarily analyzed monitoring variables stored in the importance database in the early warning processing device;
Generating an alarm in the early warning processing device when the device monitoring signal value exceeds a normal operation range; And
And a step of determining, in the alarm determination device, whether the generated alarm is a valid alarm requiring notification and action.
delete delete The method according to claim 1,
Further comprising the step of calculating a residual in the early warning processing apparatus using the received current value and the weight and a pre-built pattern learning model. 5. The method of claim 4,
Further comprising the step of determining whether the early alarm processing apparatus is out of a normal operating range set in advance by the operator using the residual. The method according to claim 1,
Wherein the step of determining whether the generated alert is a valid alarm requiring notification and action includes receiving alert status information from the alert determination device and classifying the alert information into a predicted alert and an analyzed alert, Indication of equipment malfunction Early warning method. 7. The method of claim 6,
An early warning method for equipment malfunction indication, which corresponds to at least one of occurrence alarm of power plant main room, occurrence alarm by device replacement operation, and occurrence alarm by preplanned test or maintenance. The method according to claim 6,
If the alarm is the alarm to be analyzed, if the alarm is analyzed by the integration center operator and it is determined that the monitoring of the power plant is necessary as a result of tracking, the alarm determination device notifies the occurrence of an alarm to at least one of the power plant operator computer and the power plant operator's personal radio communication device Indication of equipment malfunction Early warning method. An apparatus abnormality early warning system comprising device importance and alarm validity determination,
The information classifying importance of each monitored variable analyzed in advance according to the importance classifying standard previously designated by the operator is stored in the importance database and the current value of the monitoring signals received from the measuring device is calculated and the calculated value An importance classifying unit for searching for the importance level and the weight of the monitoring variable from the importance database and transmitting the importance class;
Wherein the information classifier classifies the importance of each monitored variable stored in the importance database by the importance classifier and receives a device monitoring signal using the weight based on the information classified by the pre- An early alarm processing unit for determining whether the value of the device monitoring signal exceeds a normal operation range and generating an alarm when the device monitoring signal value exceeds a normal operation range; And
And an alarm judging device for judging whether the generated alarm is a valid alarm requiring notification and action.
delete delete 10. The method of claim 9,
Wherein the early warning processor calculates a residual using the current value, the weight, and a pattern learning model that is constructed in advance. 13. The method of claim 12,
Wherein the early alarm processing device uses the residual to determine whether the operator is out of a predetermined normal operating range. 10. The method of claim 9,
Wherein the alarm determination apparatus receives the alert status information when the alert is generated, and classifies the alert information into an alert and an analysis target alert. 15. The method of claim 14,
An early warning system for equipment malfunction indication, which corresponds to at least one of an occurrence alarm of the plant main engine room, an occurrence alarm by the device replacement operation, and a pre-planned test or maintenance alarm. 15. The method of claim 14,
When the alarm is the alarm to be analyzed, if the alert center analyzes the alarm and it is determined that the monitoring of the power plant is necessary as a result of the tracking, the alarm determination device notifies the occurrence of the alarm to at least one of the power plant operator's computer and the power station operator's personal radio communication device Characterized in that the instrument is indicative of an early warning system.

Images