JP2020181232A - Plant state monitoring system and plant state monitoring method - Google Patents

Abstract

To provide a plant state monitoring system that can efficiently store environmental data for detecting the change of state of a monitoring target facility regardless of a stationary or nonstationary state using operational data without a scheduling in advance.SOLUTION: A plant state monitoring system comprises: an environmental data measurement device for acquiring environmental data of a monitoring target facility; a monitoring controller for controlling the monitoring target facility, acquiring the operational data of the monitoring target facility, acquiring the environmental data acquired by the environmental data measurement device, and carrying out a preliminary treatment of the environmental data; and a data storage unit for storing the operational data acquired by the monitoring controller and the environmental data acquired by the environmental data measurement device while in association with both data.SELECTED DRAWING: Figure 1

Description

The present invention relates to a plant condition monitoring system and a plant condition monitoring method for monitoring the plant conditions of water and sewage plants, chemical plants and electric power plants.

Since 2011, water tariff income has been declining due to the effects of population decline and water conservation, and the financial situation is severe. In addition, the number of staff involved in water and sewage is decreasing. In particular, in recent years, skilled staff who have abundant know-how and skills have reached retirement age, and there is a shortage of staff, and passing on know-how and skills has become an issue. This tendency is not limited to the water supply industry, but the chemical industry and the electric power industry also have similar problems.

Skilled staff should detect changes in the state of the plant (equipment) by listening to the sounds emitted by pumps and motors, smelling faint chemical odors and ozone odors, and even looking at the facilities. Can be done. The detection of state changes based on such environmental data has a large sensory part and is difficult to leave in manuals.

However, if the number of skilled staff decreases, such know-how and technology may be lost, so systems and methods that replace these know-how and technology are needed.

As a background technique in this technical field, there is Japanese Patent Application Laid-Open No. 2002-014143 (Patent Document 1). In Patent Document 1, the acoustic signal acquired by the microphone is recorded in a data recorder, the acoustic signal is filtered by the filter device, and the frequency component of the sound emitted from at least one of the plurality of operating units is used. A method of diagnosing an abnormality in an operating unit that acquires one or more filtered signals in which one or more acoustic waveforms corresponding to the above clearly appear and determines the occurrence of an abnormality in each operating unit based on the acoustic waveform in a data analyzer. Is described (see summary).

JP-A-2002-041143

Patent Document 1 describes a method for diagnosing an abnormality in an operating unit, which can individually diagnose an abnormality in a plurality of operating units based on an acoustic signal. Further, Patent Document 1 describes that "the timing of sounds generated from each of a plurality of operating units on the time axis is specified in advance" (see 0010).

That is, in the method for diagnosing an abnormality of an operating unit described in Patent Document 1, the timing of the sound generated from each of the plurality of operating units is specified in advance to identify which operating unit the sound is generated from, and the sound is specified. It is described to diagnose the abnormality of the moving part where the sound is generated.

However, in the method for diagnosing an abnormality of an operating unit described in Patent Document 1, it is necessary to specify in advance the timing of sounds generated from each of a plurality of operating units, that is, prior scheduling of the operating unit is required, which is not possible. It may be difficult to obtain the sound at regular times.

Further, Patent Document 1 describes a case where it is necessary to acquire the sound timing and the sound at the steady state again when the moving parts are different, and the case where the moving parts are different. Absent.

Therefore, the present invention does not require prior scheduling, and uses operation data to efficiently obtain environmental data for detecting a state change of monitored equipment without distinguishing between steady time and non-steady time. It provides a plant condition monitoring system and a plant condition monitoring method that can be stored in.

In order to solve the above problems, the plant state monitoring system of the present invention controls an environmental data measuring device that acquires environmental data of the monitored equipment and the monitored equipment, acquires operation data of the monitored equipment, and obtains environmental data. A data storage unit that stores the monitoring control device that acquires the environmental data acquired by the measuring device and executes the preprocessing of the environmental data, and the environmental data acquired by the environmental data measuring device and the operation data acquired by the monitoring control device. And, characterized by having.

Further, the plant state monitoring method of the present invention acquires environmental data and operation data of the equipment to be monitored, executes a labeling process for assigning a label to the environmental data using the operation data, and executes the environmental data and operation. It is characterized by associating and storing data.

According to the present invention, environmental data for detecting a change of state of monitored equipment can be efficiently obtained by using operation data without requiring prior scheduling and without distinguishing between steady time and non-steady time. It is possible to provide a plant condition monitoring system and a plant condition monitoring method that can be stored in.

Issues, configurations and effects other than those described above will be clarified by the explanation of the following examples.

It is explanatory drawing explaining the plant condition monitoring system 10 in Example 1. FIG. It is explanatory drawing explaining the monitoring control apparatus 300 in Example 1. FIG. It is explanatory drawing explaining the work flow of the environment data preprocessing function 330 in Example 1. FIG. It is explanatory drawing explaining the label addition to the environmental data in Example 1. FIG. It is explanatory drawing explaining the plant condition monitoring system 10 in Example 2. FIG. It is explanatory drawing explaining the label addition to the environmental data in Example 2. FIG. It is explanatory drawing explaining the clustering (classification) of the environmental data in Example 2. It is explanatory drawing explaining the monitoring control apparatus 300 in Example 3. FIG. It is explanatory drawing explaining the relationship between the trouble which occurs around the pump in Example 3 and operation data or environmental data. It is explanatory drawing explaining the label addition to the environmental data in Example 4. FIG.

Hereinafter, examples will be described with reference to the drawings. In addition, substantially the same or similar configurations are designated by the same reference numerals, and when the explanations are duplicated, the explanations may be omitted.

First, the plant condition monitoring system 10 in the first embodiment will be described.

FIG. 1 is an explanatory diagram illustrating the plant condition monitoring system 10 according to the first embodiment.

The plant state monitoring system 10 described in this embodiment controls the environmental data measuring device 200 and the monitored equipment 100 that acquire the environmental data of the monitored equipment 100, acquires the operation data of the monitored equipment 100, and obtains the environmental data. The monitoring control device 300 that acquires the environmental data acquired by the measuring device 200 and executes the preprocessing of the environmental data, the environmental data acquired by the environmental data measuring device 200, and the operation data acquired by the monitoring control device 300 are stored in association with each other. It has a data storage unit 400 capable of deleting environmental data and operation data as needed, and a state change detecting means 500 for detecting a state change of the monitored equipment 100.

An environmental data measuring device 200 and a monitoring control device 300 are connected to the monitored equipment 100, and a data storage unit 400 and a state change detecting means 500 are connected to the monitoring control device 300. Further, the environment data measuring device 200 and the monitoring control device 300 are connected, and the data storage unit 400 and the state change detecting means 500 are connected.

A network is used for these connections. The network includes the Internet, WAN (Wide Area Network), LAN (Local Area Network), and the like.

The monitored equipment 100 is, for example, machinery such as a pump or a motor. The state of the monitored equipment 100 changes during operation and / or failure. This state change is a change in the operating state of the monitored equipment 100, and is a change (deviation) from the steady state.

The monitored equipment 100 is often installed in a plurality of systems in a plant, and in such a case, a plurality of the monitored equipment 100 are often installed in the same room (same space). Therefore, even when the monitored equipment 100 such as a plurality of pumps and motors are operating at the same time, it is necessary to appropriately detect the state change of the monitored equipment 100 such as the plurality of pumps and motors. is there.

In this embodiment, in particular, as the monitoring target equipment 100, one pump for injecting chemicals in a water supply plant will be described below. Further, in this embodiment, "sound generated by the pump" is used as the environmental data, and "on / off signal of the pump" is used as the operation data. In addition to the "sound generated by the pump", the environmental data includes electromagnetic waves emitted by the pump, and the operation data includes the pressure signal of the pump, the output signal of the pump, and the operation data in addition to the "On / Off signal of the pump". There are pump current signals, pump flow signals, etc.

The environmental data measuring device 200 is a device having a sound collecting function and a recording function for the sound (environmental data) emitted by the pump (monitoring target equipment 100). For example, it is a microphone (sound collecting device) and a data recorder (recording device) that records the sound acquired by the sound collecting device. Further, one or more environmental data measuring devices 200 are installed, and the operating sound and the failure sound of the pump are acquired as digital data (environmental data).

The monitoring control device 300 is a device that controls the operation of other equipment of the water supply plant, including the pump (monitored equipment 100). For example, a control panel. Further, the monitoring control device 300 acquires the On / Off signal (operation data) of the pump and executes preprocessing of the environmental data.

Then, the monitoring control device 300 acquires the operation data of the monitoring target equipment 100 and outputs a control signal to the monitoring target equipment 100.

The data storage unit 400 is a recording medium mounted on hardware such as a personal computer or a tablet, and stores environmental data and operation data.

The state change detecting means 500 is a program recorded on a recording medium, executes data analysis based on environmental data and / or operation data, and detects a state change of the monitored equipment 100. The state change detecting means 500 may be installed on the recording medium of the data storage unit 400, or may be installed on a recording medium different from the recording medium of the data storage unit 400.

Next, the monitoring control device 300 according to the first embodiment will be described.

FIG. 2 is an explanatory diagram illustrating the monitoring control device 300 according to the first embodiment.

The monitoring control device 300 described in this embodiment has an operation control function 310, a measurement data reception function 320, an environmental data preprocessing function 330, a data transmission function 340, and an alarm output function 350.

The operation control function 310 controls the operation of other equipment of the water supply plant, including the pump (monitored equipment 100). The operation control function 310 acquires the operation data of the monitored equipment 100 and outputs a control signal to the monitored equipment 100. For example, the operation control function 310 acquires the On / Off signal (operation data) of the pump and outputs the On / Off signal (control signal) to the pump.

The measurement data receiving function 320 acquires the On / Off signal (operation data) of the pump acquired by the operation control function 310 and the sound (environmental data) emitted by the pump acquired by the environmental data measuring device 200 together with the time. The measurement data receiving function 320 is provided with operation data other than the sound emitted by the pump, for example, operation data such as a pump pressure signal, a pump current signal, a pump flow signal, and a pump output signal (the pump operates as a control signal). You may acquire the measurement data) which is the result of this.

The environmental data preprocessing function 330 executes preprocessing of the environmental data acquired by the measurement data receiving function 320. Then, the environmental data preprocessing function 330, together with the time, displays the On / Off signal (operation data) of the pump (monitoring target equipment 100) and the sound (sound information) (environmental data) emitted by the pump (monitoring target equipment 100). It is used to label the environmental data.

Here, the pretreatment is to decompose the sound (environmental data) emitted by the pump into frequency, sound pressure level, frequency component, etc., to give a label to the sound (environmental data) emitted by the pump, and to emit the pump. It includes removing noise from sound (environmental data), and may be referred to as "decomposition processing", "labeling processing", and "noise removal processing", respectively.

The data transmission function 340 transmits the environmental data and operation data acquired by the measurement data reception function 320, and the preprocessed environmental data for which the environmental data preprocessing function 330 has executed the preprocessing to the data storage unit 400. In particular, in this embodiment, the sound (environmental data) emitted by the pump acquired by the measurement data receiving function 320 is decomposed, and the on / off signal (operation data) of the pump is used to perform the labeling process. Then, the noise removal processing is executed, and the environment data after the preprocessing is transmitted to the data storage unit 400.

The alarm output function 350 receives the state change of the pump detected by the state change detecting means 500, and outputs an alarm as needed.

Next, the work flow of the environmental data preprocessing function 330 in the first embodiment will be described.

FIG. 3 is an explanatory diagram illustrating a work flow of the environmental data preprocessing function 330 in the first embodiment.

The environment data preprocessing function 330 executes preprocessing in the following step (S).

In S101, the time, the operation data of the target pump (on / off signal of the pump), and the environmental data of the target pump (sound emitted by the pump) are acquired from the measurement data receiving function 320.

In S102, acoustic analysis of environmental data (sound emitted by the pump) is executed. Specifically, the sound emitted by the pump is decomposed into sound information such as frequency, sound pressure level, and frequency component by using Fourier transform or the like. That is, the "disassembly process" is executed. Sound information such as the decomposed frequency (acoustic analysis was performed), sound pressure level, and frequency component is also environmental data.

In S103, the On / Off signal of the target pump is used to label the environmental data (for example, frequency) in which the decomposition process is executed. That is, the "labeling process" is executed.

In S104, steady-state noise (spatial noise, etc.) is removed by using the environmental data (for example, frequency) at the time of turning off of the target pump for which the labeling processing is executed. That is, the "noise removal process" is executed.

In S105, the preprocessed environmental data (for example, frequency) is transmitted to the data transmission function 340.

Here, in this embodiment, the environmental data (sound emitted by the pump) is decomposed into three types of sound information of frequency, sound pressure level, and frequency component, but decomposed into two types of sound information of frequency and sound pressure level. It may be decomposed into four or more kinds of sound information. Also, if it is possible to detect the state change of the target pump, such as narrowing down to sound information such as a specific (predetermined range) frequency, sound pressure level, frequency component, etc., which makes it easy to detect the state change of the target pump, acoustic analysis The method of is not particularly limited.

In this embodiment, the preprocessing is executed in the order of "decomposition processing", "labeling processing", and "noise removal processing", but the order is not necessarily limited to this. For example, the decomposition process may be executed, the noise removal process may be executed, and the labeling process may be executed, or the noise removal process, the decomposition process, and the labeling process may be executed.

As described above, the plant condition monitoring method described in this embodiment acquires the environmental data (sound emitted by the pump) and the operation data (on / off signal of the pump) of the monitored equipment (pump) 100, and uses the environmental data as the environmental data. , Execute the labeling process of assigning a label using the operation data.

Next, labeling of the environmental data in Example 1 will be described.

FIG. 4 is an explanatory diagram illustrating the labeling of the environmental data in the first embodiment.

The environmental data (sound emitted by the pump) acquired by the measurement data receiving function 320 is input to the environmental data preprocessing function 330 together with the time at regular intervals of about several minutes. Then, the environment data preprocessing function 330 continuously acquires the environment data.

In this embodiment, for example, a frequency is used as the environmental data for which the decomposition process is executed by the environmental data preprocessing function 330.

On the other hand, the operation data (Pump On / Off signal) of the target pump acquired by the operation control function 310 is also input to the environment data preprocessing function 330 together with the time.

Since the environmental data (for example, frequency) is decomposed, there is a slight time delay with respect to the operation data (pump On / Off signal), but the time of the acquired operation data and the time Based on the time of the environment data, these times are matched and the labeling process is executed.

In this embodiment, three types of labels are prepared. The first is the label when the target pump is operating and stopped (no symbol), the second is the label when the target pump is on / off (La + number), and the third. Is a label (Lb + number) when the target pump is stopped when the target pump is On / Off.

In this embodiment, when the target pump is On / Off, a label of La or Lb is given to the environmental data for several tens of seconds before and after the On / Off signal of the target pump. That is, in this embodiment, labels (La or Lb) are added to the environmental data before and after the input of the operation data (the input of the On signal or the input of the Off signal of the target pump).

For example, the label La1 and the label Lb1 are assigned to the environmental data for several tens of seconds before and after the signal of Off (1). That is, the label La1 is given for several tens of seconds before the signal of Off (1), and the label Lb1 is given for several tens of seconds after the signal of Off (1).

Further, the label La2 and the label Lb2 are attached to the environmental data for several tens of seconds before and after the signal of On (1). That is, the label Lb2 is given for several tens of seconds before the signal of On (1), and the label La2 is given for several tens of seconds after the signal of On (1).

Further, before and after the signal of Off (2) and before and after the signal of On (2), the label La3 and the label Lb3, and the label La4 and the label Lb4 are similarly attached.

This is because the state of the target pump is likely to change when the target pump is turned on / off in this way.

It is preferable that such labeling processing is executed in a timely manner at any time, but environmental data (for example, frequency) and operation data (pump On / Off signal) are temporarily preprocessed for environmental data. It is possible to store in the function 330, match these times based on the time of the operation data and the time of the environmental data, and execute the labeling process retroactively.

Further, in this embodiment, environmental data (for example, frequency) and operation data (pump On / Off signal) of the labeled portion are stored. That is, if necessary, the environmental data and operation data other than this part are deleted. As a result, environmental data and operation data can be efficiently stored.

Then, in particular, in this embodiment, the environmental data (for example, frequency) of the label portion when the target pump is stopped (Off), that is, the environmental data of any portion of Lb1, Lb2, Lb3, Lb4 (for example, for example). Frequency) is used to perform the noise removal process.

That is, in this embodiment, from the environmental data in which the label is given before (meaning "before" before and after the On / Off signal of the target pump), after ("after" before and after the On / Off signal of the target pump). The environmental data labeled after (meaning) is removed, or before (on / of the target pump) from the environmental data labeled after (meaning "after" before and after the On / Off signal of the target pump). Environmental data labeled (meaning "before" before and after the Off signal) is removed, and noise removal processing is executed.

As a result, since noise is removed, it is not necessary to acquire the sound of the target pump again, and the noise removal process can be efficiently executed.

Further, in this embodiment, the noise removal process is executed by using the environmental data (for example, frequency) of the label portion at the time of the latest stop (Off) of the target pump. As a result, the noise removal process can be executed with high accuracy.

As described above, in this embodiment, for the On / Off signal of the target pump, two types of labels, a label at the time of operation and a label at the time of stop (two types of labels before and after the On / Off signal of the pump). By preparing the above, the noise removal process can be executed efficiently and accurately.

Further, according to this embodiment, environmental data for detecting a state change of the monitored equipment 100 without requiring prior scheduling and using operation data to distinguish between steady time and non-steady time. Can be stored efficiently.

In this embodiment, the On / Off signal of the target pump is used as the operation data, but for example, the output signal (UP / DOWN signal) of the target pump can be used as the operation data. Two types of labels are attached before and after the UP / DOWN signal of the target pump in the same manner as the On / Off signal of the target pump. As a result, the environment data and the operation data can be efficiently stored and the noise removal processing can be efficiently and accurately executed as in the case of using the On / Off signal of the target pump as the operation data. Can be done.

In addition, even during steady operation of the target pump (a state of steady operation other than during On / Off and UP / DOWN), it is possible to periodically label and store environmental data for maintenance purposes. preferable.

The data storage unit 400 includes environmental data (such as the sound emitted by the pump) of the target pump measured by the environmental data measuring device 200, for example, a pump pressure signal, a pump current signal, a pump flow signal, a pump output signal, and the like. This is a database that stores the measurement data of the target pump and the operation data of the target pump (on / off signal of the pump, etc.) in association with the time. That is, the data storage unit 400 stores the environment data and the operation data in association with each other.

The data storage unit 400 periodically deletes these data to secure the recording capacity of the data storage unit 400. In this embodiment, for example, when one month has passed since the environmental data and the operation data were acquired, the data with the label (no symbol) at the time of the steady operation or the long-term stop of the target pump was deleted. The recording capacity of the data storage unit 400 is secured.

The state change detecting means 500 executes data analysis on the environmental data (for example, frequency) stored in the data storage unit 400, and detects the state change of the target pump.

As a method for detecting a state change, there are a physical model, an FTA (Fault Tree Analysis), a statistical model, and the like. In particular, a statistical model includes an adaptive resonance theory (ART) which is a kind of clustering. Using this ART, the occurrence pattern of the state change of the target pump is extracted, and the state change of the target pump is detected. In this embodiment, the environmental data for detecting the state change of the target pump is efficiently stored. Therefore, the description of the state change detection method will be omitted.

The state change detection method is not limited to these, and any other detection method may be used as long as the state change of the target pump can be detected.

Then, if the state change is detected as a result of the data analysis, the state change detecting means 500 outputs the state change detection signal to the alarm output function 350, and the alarm output function 350 outputs an alarm. Here, the alarm is to output characters or sound an alarm sound on the monitor of the monitoring screen.

In this embodiment, the sound generated by the pump is used as the environmental data, but the environmental data is not limited to the sound generated by the pump. For example, electromagnetic waves, light, odors, and the like can be handled in the same manner. For example, since the pump generates electromagnetic waves, an electromagnetic wave measuring device that measures electromagnetic waves can be used as the environmental data measuring device 200, and can be treated in the same manner as the sound emitted by the pump.

Further, in the present embodiment, the pump is used as the monitored equipment 100, but the monitored equipment 100 is not limited to such a pump. For example, an emergency generator used in the event of a power failure can be handled in the same manner. The combustion state of the emergency generator is measured by using an optical device such as a camera as an environmental data measuring device 200. Then, using the light (environmental data) emitted by the emergency generator, the environmental data preprocessing function 330 decomposes this light into optical information such as brightness and wavelength (executes decomposition processing), and is appropriate. Labeling (performing labeling processing) using various operation data.

As a result, the environmental data and the operation data can be efficiently stored and the noise removal processing can be efficiently and accurately executed as in the case of using the pump as the monitored equipment 100.

As described above, the plant state monitoring system 10 described in the present embodiment at least controls the environmental data measuring device 200 for acquiring the environmental data of the monitored equipment 100 and the monitored equipment 100, and operates the monitored equipment 100. The monitoring control device 300 that acquires the data, acquires the environmental data acquired by the environmental data measuring device 200, and executes the preprocessing of the environmental data, and the environmental data and the monitoring control device 300 acquired by the environmental data measuring device 200. It has a data storage unit 400 that stores the operation data to be used and can delete the environment data and the operation data as needed.

According to this embodiment, the environmental data for detecting the state change of the monitored equipment 100 by using the operation data without the need for prior scheduling without distinguishing between the steady state and the non-steady state, It can be saved efficiently, selectively.

Then, since the environmental data for detecting the state change of the monitored equipment 100 can be selectively stored, even if the state change is detected by the environmental data having a large sensory part, the points are narrowed down. , The quality can be improved and the plant condition can be monitored.

Further, by supporting the monitoring of the plant state in this way, even when the number of skilled staff is reduced, the system can be unmanned (labor saving) and the shortage of human resources can be solved.

First, the plant condition monitoring system 10 in the second embodiment will be described.

FIG. 5 is an explanatory diagram illustrating the plant condition monitoring system 10 according to the second embodiment.

Compared with the plant condition monitoring system 10 described in the first embodiment, the plant condition monitoring system 10 described in this embodiment has a plurality of monitored equipments (monitored equipment A101, monitored equipment B102, monitored equipment C103). Is different in that the operation data and the environmental data of a plurality of monitored equipments (monitored equipment A101, monitored equipment B102, monitored equipment C103) are acquired.

That is, the plant state monitoring system 10 described in this embodiment includes an environmental data measuring device 200 and a plurality of environmental data measuring devices 200 that acquire environmental data of a plurality of monitored equipments (monitored equipment A101, monitored equipment B102, monitored equipment C103). Controls the monitored equipment (monitored equipment A101, monitored equipment B102, monitored equipment C103), and acquires operation data of multiple monitored equipment (monitored equipment A101, monitored equipment B102, monitored equipment C103). , The monitoring control device 300 that acquires the environmental data acquired by the environmental data measuring device 200 and executes the preprocessing of the environmental data, stores the environmental data acquired by the environmental data measuring device 200 and the operation data acquired by the monitoring control device 300. It also has a data storage unit 400 that can delete environmental data and operation data as needed, and a state change detecting means 500 that detects a state change of the monitored equipment 100.

Further, the monitoring control device 300 described in this embodiment has an operation control function 310, a measurement data receiving function 320, an environmental data preprocessing function 330, a data transmission function 340, and an alarm output function 350.

The environmental data preprocessing function 330 described in this embodiment takes into consideration that it handles a plurality of monitored equipments (monitored equipment A101, monitored equipment B102, monitored equipment C103), and measures data receiving function 320. Performs preprocessing of the environment data acquired by.

Further, also in this embodiment, as in the case of the first embodiment, as a plurality of monitored equipments (monitored equipment A101, monitored equipment B102, monitored equipment C103), a pump for injecting chemicals in a water supply plant is targeted. , The following will be explained. Then, it is assumed that one pump is installed in each monitored equipment. Further, also in this embodiment, "sound generated by the pump" is used as environmental data, and "on / off signal of pump" is used as operation data.

In this embodiment as well, the pretreatment is "decomposition processing", "labeling processing", and "noise removal processing" as in the first embodiment. In other words, the sound emitted by the pump (environmental data) is decomposed into frequencies, sound pressure levels, frequency components, etc. (decomposition processing), and the sound emitted by the pump (environmental data) is labeled (labeling processing). Includes removing noise from the sound (environmental data) emitted by the pump (noise removal processing).

Next, labeling of the environmental data in Example 2 will be described.

FIG. 6 is an explanatory diagram illustrating the labeling of the environmental data in the second embodiment.

In this embodiment as well, as in the first embodiment, the environmental data (sound emitted by the pump) acquired by the measurement data receiving function 320 is sent to the environmental data preprocessing function 330 at regular intervals of about several minutes together with the time. Is entered. Then, the environment data preprocessing function 330 continuously acquires the environment data.

In this embodiment as well, for example, a frequency is used as the environmental data for which the decomposition process is executed by the environmental data preprocessing function 330, as in the first embodiment.

On the other hand, in this embodiment, the plurality of monitored equipment (pumps) are turned on / off while the monitored equipment B102 is operating while the monitored equipment B102 is operating, while the monitored equipment B102 is operating. , It is assumed that the monitored equipment C103 is turned on.

In addition, three types of labels are prepared as in Example 1. The first is the label when the target pump is operating and stopped (no symbol), the second is the label when the target pump is on / off (La + number), and the third. Is a label (Lb + number) when the target pump is stopped when the target pump is On / Off.

In this embodiment, for example, the label La5 and the label Lb5 are assigned to the environmental data for several tens of seconds before and after the signal of On (3). That is, the label Lb5 is given for several tens of seconds before the signal of On (3), and the label La5 is given for several tens of seconds after the signal of On (1).

Further, the label La6 and the label Lb6 are assigned to the environmental data for several tens of seconds before and after the signal of On (4). That is, the label Lb6 is given for several tens of seconds before the signal of On (4), and the label La6 is given for several tens of seconds after the signal of On (4).

Further, the label La7 and the label Lb7 are assigned to the environmental data for several tens of seconds before and after the signal of Off (3). That is, the label La7 is given for several tens of seconds before the signal of Off (3), and the label Lb7 is given for several tens of seconds after the signal of Off (3).

In this embodiment, the monitored equipment B102 is operated (On) while the monitored equipment A101 is operating.

At this time, the acquired environmental data overlaps the environmental data (sound information (for example, frequency)) of the monitored equipment A101 and the monitored equipment B102, and the environmental data of the monitored equipment A101 and the monitored target. It is difficult to acquire the environmental data of the equipment B102 for each, and it is difficult to detect which of the monitored equipments has a state change.

Therefore, using the environmental data of the label (Lb5) part given at the time of operation (On) of the monitored equipment B102, the environmental data of the label (Lb5) part is converted from the environmental data of the label (La5) part. By removing, the environmental data of the monitored equipment B102 can be acquired.

Similarly, using the environmental data of the label (Lb6) part given at the time of operation (On) of the monitored equipment C103, from the environmental data of the label (La6) part, the environment of the label (Lb6) part. By removing the data, the environmental data of the monitored equipment C103 can be acquired.

Similarly, using the environmental data of the label (Lb7) part given when the monitored equipment B102 is stopped (Off), the environment of the label (Lb7) part is obtained from the environmental data of the label (La7) part. By removing the data, the environmental data of the monitored equipment B102 can be acquired.

That is, in this embodiment, the environment data to be labeled "after" is removed from the environment data to be labeled "before", or the environment data to be labeled "after" is "before". The environmental data labeled with "" is removed, and noise removal processing is executed.

This is because there is a high possibility that the state of the monitored equipment will change when the monitored equipment is turned on / off, and thereby, the state change of each of the plurality of monitored equipment in such a case is detected. can do.

Then, also in this embodiment, as in the first embodiment, the environmental data and the operation data (pump On / Off signal) of the labeled portion are stored in the data storage unit 400 in association with each other.

Next, clustering (classification) of environmental data in Example 2 will be described.

FIG. 7 is an explanatory diagram illustrating clustering (classification) of environmental data in the second embodiment.

In this embodiment, the On / Off signals of the respective monitored equipment can be used to classify into seven classes.

For example, in class 1, when all of the monitored equipment A101, the monitored equipment B102, and the monitored equipment C103 are Off, in the class 2, the monitored equipment A101 is On, the monitored equipment B102, and the monitored equipment C103 are Off. In the case of class 3, when the monitored equipment B102 is On and the monitored equipment A101 and the monitored equipment C103 are Off, in the class 4, the monitored equipment C103 is On, the monitored equipment A101 and the monitored equipment B102 are Off. In the case of, in class 5, the monitored equipment A101 and the monitored equipment B102 are On, and the monitored equipment C103 is Off. In the class 6, the monitored equipment B102, the monitored equipment C103 is On, and the monitored equipment A101 is Off. In the case of, the class 7 is the case where the monitored equipment A101, the monitored equipment C103 is On, and the monitored equipment B102 is Off.

That is, in this embodiment, the On / Off signals (operation data) of a plurality of monitored equipments (monitored equipment A101, monitored equipment B102, monitored equipment C103) are used, classified into classes, and noise removal processing is performed. Select the environment data to run.

In this way, by using the classified classes based on the On / Off signals of each monitored equipment, it is possible to acquire the environmental data of each monitored equipment. In addition, noise removal processing can be executed.

In this embodiment, the pump On / Off signals are used to classify the classes. For example, since the sound information of a pump is likely to change depending on the output, the output signal of each pump (pump current signal). , Pressure signal, flow rate signal, etc.) are also preferably classified together.

Then, in this embodiment, the data storage unit 400 has such a clustering function (classification function), and the environmental data after labeling is subjected to noise removal processing and equipment identification processing for specifying the equipment to be monitored (this processing is also broadly defined). Store to perform the noise removal process).

In addition, in waterworks plants (water purification plants), the operation of monitored equipment may change depending on the weather. For this reason, it is preferable to classify weather information (sunny, rain, etc.) as a whole. As a result, noise removal processing and equipment identification processing can be executed with higher accuracy.

As described above, according to the present embodiment, in order to detect a state change of a plurality of monitored equipments by using operation data without distinguishing between steady time and non-steady time and without requiring prior scheduling. Environmental data can be saved efficiently and selectively.

Further, according to this embodiment, the noise removal processing and the equipment identification processing are executed more accurately by clustering (classifying) and storing the environmental data for executing the noise removal processing and the equipment identification processing. It is possible to detect changes in the state of the monitored equipment more accurately.

In particular, in this embodiment, since the sound information is used as the environmental data, the information in the space can be collectively acquired, and the state change of a plurality of monitored equipment can be detected at the same time.

First, the monitoring control device 300 according to the third embodiment will be described.

FIG. 8 is an explanatory diagram illustrating the monitoring control device 300 according to the third embodiment.

In this embodiment, operation data other than the pump On / Off signal is used to give a new label to the environment data, and when a change of state of the pump is detected, the environment data and the operation data are respectively. To identify the cause of the change of state of the pump by using the presence or absence of the change of the pump.

The monitoring control device 300 described in this embodiment has an operation control function 310, a measurement data reception function 320, an environmental data preprocessing function 330, a data transmission function 340, and an alarm output function 350, as in the first embodiment.

In this embodiment, in particular, the state change of the pump detected by the state change detecting means 500 is fed back to the environmental data preprocessing function 330, and a new label is given to the environmental data.

Specifically, the environment data pre-processing function 330 stores the pre-processed environment data analyzed by the state change detecting means 500. That is, the environment data preprocessing function 330 stores the environment data after the preprocessing has already been executed and the state change detecting means 500 has detected the state change of the pump.

That is, the state change detecting means 500 has operation data such as "the pressure signal of the pump exceeds the upper and lower limit values" and "the current signal of the pump is out of the threshold value" (result of detecting the state change of the pump). Is clustered (classified).

Then, when the state change of the pump is detected, the state change detecting means 500 outputs the state change detection signal to the alarm output function 350 as in the first embodiment.

On the other hand, the state change detecting means 500 simultaneously outputs a state change detection signal to the environment data preprocessing function 330.

Then, the environmental data preprocessing function 330 adds a new label (Lc + number) to the environmental data based on the operation data when the state change is detected based on the input state change detection signal. That is, this new label is given when a change of state of the pump is detected.

In this way, the environment data with the new label is overwritten and stored in the data storage unit 400.

As a result, the operation data in which the state change of the pump is detected and the environmental data after the pretreatment can be appropriately and selectively stored. Further, when the change of state of the pump is detected, the cause of the change of state of the pump can be identified by combining the environmental data after the pretreatment and the operation data.

Next, the relationship between the defect occurring around the pump in the third embodiment and the operation data or the environmental data will be described. FIG. 9 explains the relationship between the defect occurring around the pump in the third embodiment and the operation data or the environmental data. It is explanatory drawing to do.

For example, using the environmental data with a new label, the operation data at that time, and the cause of the pump state change found after that, as shown in FIG. 9, the cause of the pump state change (occurs around the pump). It is possible to summarize the relationship between the sound pressure (environmental data) and the operation data (pressure, current).

When the state change detecting means 500 detects a state change of the pump, if there is a change in sound pressure, a change in pressure, and no change in current, "pump drive unit failure" is the cause of the state change of the pump. Is identified as likely to be.

In this way, by combining the operation data related to the pump and the environmental data after the pretreatment, the cause of the change of state of the pump can be identified.

In this embodiment, the pump is used as the monitored equipment, but the monitored equipment is not limited to such a pump. For example, motors and other machinery can be handled in the same way.

Further, as the operation data, although the pressure and the current have been described, other operation data such as output and flow rate may be used. Further, as the environmental data, although the sound pressure of the sound information has been described, other sound information, other environmental data such as electromagnetic waves and odors may be used.

According to this embodiment, operation data other than the pump's On / Off signal can be used to add a new label to the environmental data, and the environmental data and the operation data can be appropriately and selectively stored. Can be done. In addition, when a change of state of the pump is detected, the cause of the change of state of the pump can be identified by combining the operation data and the environmental data.

First, labeling of the environmental data in Example 4 will be described.

FIG. 10 is an explanatory diagram illustrating the labeling of the environmental data in the fourth embodiment.

In this embodiment, it will be described that the environmental data is labeled in consideration of the inspection schedule of the worker (staff) in addition to the On / Off signal of the pump.

In this embodiment, the inspection schedule of the worker is recorded in advance, and when the worker works in the room where the target pump is installed, the time (time in between) may not be labeled. That is, the label Lb8 and the label La8, and the label La9 and the label Lb9 are given.

As a result, it is possible to acquire only the environmental data necessary for detecting the state change of the monitored equipment, excluding the environmental data that is not involved in the state change of the monitored equipment such as the work sound emitted when the worker works.

The present invention is not limited to the above-mentioned examples, and includes various modifications. For example, the above-described embodiment is described in detail and concretely in order to explain the present invention in an easy-to-understand manner, and is not necessarily limited to the one having all the components described. It is also possible to replace some of the components of one embodiment with some of the components of another embodiment. It is also possible to add the constituent requirements of another embodiment to the constituent requirements of one embodiment. It is also possible to add, delete, or replace some of the other components with respect to some of the components of each embodiment.

10 Plant condition monitoring system 100 Monitoring target equipment 101 Monitoring target equipment A
102 Monitored equipment B
103 Monitored equipment C
200 Environmental data measurement device 300 Monitoring control device 310 Operation control function 320 Measurement data reception function 330 Environmental data preprocessing function 340 Data transmission function 350 Alarm output function 400 Data storage unit 500 State change detection means

Claims (11)

The environment data measuring device that acquires the environmental data of the monitored equipment, controls the monitored equipment, acquires the operation data of the monitored equipment, acquires the environmental data acquired by the environmental data measuring device, and obtains the environment. A plant characterized by having a monitoring control device that executes preprocessing of data, and a data storage unit that stores environmental data acquired by the environmental data measuring device and operation data acquired by the monitoring control device in association with each other. Status monitoring system. The plant state monitoring system according to claim 1, further comprising a state change detecting means for detecting a state change of the monitored equipment. The monitoring control device has an environment data preprocessing function that executes preprocessing of the environment data, and uses the operation data of the monitoring target equipment and the environment data of the monitoring target equipment together with the time to use the environment. The plant state monitoring system according to claim 1, wherein the data is labeled. The plant condition monitoring system according to claim 3, wherein the operation data is an On / Off signal of the monitored equipment, and the environmental data is sound information of the monitored equipment. The plant condition monitoring system according to claim 4, wherein the sound information is a frequency, a sound pressure level, or a frequency component obtained by acoustic analysis. The plant state monitoring system according to claim 2, wherein the state change detecting means uses an adaptive resonance theory when detecting a state change of the equipment to be monitored. The plant condition monitoring system according to claim 3, wherein labels are attached to the environmental data before and after the input of the operation data. Remove the environment data that is labeled later from the environment data that is labeled earlier, or remove the environment data that is labeled earlier from the environment data that is labeled later, and execute the noise removal process. The plant state monitoring system according to claim 7, wherein the plant state monitoring system is used. The plant condition monitoring system according to claim 1, wherein the operation data of the monitored equipment is used, classified into classes, and environmental data for executing noise removal processing is selected. The plant condition monitoring system according to claim 1, wherein the environmental data and the operation data are combined to identify the cause of the state change of the monitored equipment. The environmental data and operation data of the equipment to be monitored are acquired, and the operation data is used for the environmental data to execute a labeling process for assigning a label.
A plant condition monitoring method, characterized in that the environmental data and the operation data are stored in association with each other.

Images