JP7224176B2 - Diagnosis method for manhole pump and diagnosis device for manhole pump - Google Patents

Description

TECHNICAL FIELD The present invention relates to a diagnostic method and a diagnostic device for two manhole pumps installed in a manhole and repeatedly starting and stopping.

The manhole pump system consists of a reservoir that stores sewage that flows in from the inflow pipe, multiple pumps that discharge the sewage stored in the reservoir to the outflow pipe, and a water level that measures the water level of the sewage stored in the reservoir. When the water level measured by the water level gauge reaches the pump start water level, one of the pumps is started to discharge sewage to the outflow pipe, and when the water level reaches the pump stop water level, the pump is stopped. It has a control panel with running controls.

Two pumps are normally installed in such a manhole pump system, and a control device is configured to alternately operate the pumps each time sewage is conveyed.

In Patent Document 1, the value obtained by dividing the cumulative inflow amount to be discharged by a plurality of pumps at a pump station every predetermined time by the operation time of each pump within the predetermined time is defined as the average drainage capacity of each pump as time-series data. Means for managing, means for determining whether or not the average drainage capacity of each pump managed as time-series data exceeds a predetermined drainage capacity range, and setting the average drainage capacity of each of the plurality of pumps A pumping station monitoring system has been proposed with means for issuing an alarm when the drainage capacity range is exceeded.

In Patent Document 2, when the stored water level detected by the water level sensor reaches the pump starting water level, the pumping control unit that operates the electromagnetic switch to drive the submersible pump, the operating state of the electromagnetic switch that drives the electric motor, An abnormality determination unit that determines the presence or absence of an abnormality based on the detection state of the current sensor that detects the current in the power supply line connected to the armature winding via the electromagnetic switch and the stored water level. Disclosed is a control device for a submersible pump that determines an overheating abnormality of an electric motor in which an automatic cutoff is activated when no current is detected by a current sensor during operation of an electromagnetic switch and a decrease in the stored water level is not detected by a water level sensor. ing.

JP-A-2001-34338 JP 2010-236191 A

The control device provided in the conventional manhole pump equipment as described above has a physical quantity such as a pump drive current value, a pump operation time from the start water level to the stop water level, and the pump temperature exceeds a predetermined threshold. Whether or not each pump is abnormal is determined based on whether or not there is an abnormality. Then, in order to measure the physical quantity suitable for the type of assumed abnormality, it is necessary to perform measurement processing using various sensors, which causes a problem of being extremely complicated.

In addition, it is difficult to set a uniform threshold value for judging an abnormality because it depends on the environment of the manhole where the pump is installed. For example, in areas where the amount of water inflow per unit time is large and in areas where it is small, there is a difference in the start frequency and operation time of the pump, so there was a problem that it was difficult to make an accurate judgment if a fixed threshold was used.

In particular, a communication device is provided on the control panel of each manhole pump facility, a server is provided to manage pump operation data transmitted from each communication device, and the operating status is monitored by accessing the server from a terminal owned by the administrator. In a remote monitoring system capable of monitoring various manhole pumps, it is necessary to transmit a large number of physical quantities in order to individually determine various abnormalities in the pumps installed in each manhole pump facility. However, there is a problem that it is difficult to set an appropriate threshold value.

SUMMARY OF THE INVENTION An object of the present invention is to provide a diagnosis method and apparatus for a manhole pump capable of accurately diagnosing abnormality due to various causes even with a small physical quantity.

In order to achieve the above object, the first characteristic configuration of the manhole pump diagnosis method according to the present invention is a diagnosis method for two manhole pumps installed in a manhole to be diagnosed and repeatedly starting and stopping. a sampling step of sampling the operating time per start of each manhole pump within a predetermined diagnosis target period and calculating the respective average operating time as a pair of characteristic values; and a pair of characteristic values calculated in the sampling step. is normalized based on statistical data calculated based only on each characteristic value calculated in the most recent predetermined period including the diagnosis target period, and one of the pair of characteristic values is the x axis, and the other is A pair of normalized characteristic values are plotted on a two-dimensional coordinate system with the y-axis, and based on which side of the boundary threshold preset in the two-dimensional coordinate system the plotted characteristic value point exists a diagnostic step of primary diagnosing normality or abnormality of each manhole pump, wherein the boundary threshold value is each manhole pump installed in a plurality of manholes including each manhole pump installed in the manhole to be diagnosed. It is automatically generated by a machine learning device that learns using only normal characteristic values obtained from as teacher data, and indicates the boundary of the two-dimensional coordinate system that becomes a feature space containing normal characteristic values inside It is in.

By normalizing the characteristic value composed of each average operation time calculated from the operation time per start of each manhole pump sampled in time series in the sampling step in the normalization step, for example, the manhole pump It is possible to extract a pair of characteristic values excluding the influence of the unique machine difference and the influence of the installation environment as a feature amount. By using a preset boundary threshold value as an index, whether the manhole pump is normal or abnormal is appropriately primary diagnosed. By performing normalization processing on a pair of characteristic values based on statistical data obtained from each characteristic value in the most recent predetermined period, the effects caused by passage of time such as seasonal fluctuations are eliminated, resulting in high reliability. diagnosis becomes possible. The boundary threshold value is, for example, a group of measurement data obtained in a normal state in which manhole pumps installed in a plurality of manhole devices with different environments, including the manhole device in which the manhole pump to be diagnosed is installed, are properly operated. is automatically generated by a machine learning device using only as training data, an appropriate value that suppresses the influence of environmental differences can be obtained. No time-consuming preparation is required.

The second characteristic configuration is a method for diagnosing two manhole pumps that are installed in a manhole to be diagnosed and that are repeatedly started and stopped. a sampling step of sampling the operating times to calculate each average operating time, and setting one average operating time and a ratio of one average operating time to the other average operating time as a pair of characteristic values; A normalization step of normalizing the pair of characteristic values calculated in based on statistical data calculated only based on each characteristic value calculated in the most recent predetermined period including the diagnosis target period; and a pair of characteristic values A pair of normalized characteristic values is plotted on a two-dimensional coordinate system with one of the x-axis and the other y-axis, and the plotted characteristic value points are the boundary thresholds preset in the two-dimensional coordinate system. a diagnostic step of primary diagnosing whether each manhole pump is normal or abnormal based on which side it exists, wherein the boundary threshold is set to a plurality of manhole pumps including each manhole pump installed in the manhole to be diagnosed. It is automatically generated by a machine learning device that learns using only the normal characteristic values obtained from each manhole pump installed in the manhole as teacher data, and the normal characteristic values are included in the feature space. The point is that it indicates the boundary of the coordinate system.

Among the average operating times calculated from the operating time per start of each manhole pump sampled in time series in the sampling step, the average operating time of one, the average operating time of one, and the average operating time of the other By normalizing the pair of characteristic values in the normalization step, for example, a pair of characteristic values that eliminates the effects of machine differences inherent to manhole pumps and the effects of the installation environment It can be extracted as a feature quantity, and the characteristic value points representing a pair of characteristic values are plotted on a two-dimensional coordinate system by the diagnostic step, and the manhole pump is normal or abnormal using a preset boundary threshold as an index. is properly primary diagnosed. By performing normalization processing on a pair of characteristic values based on statistical data obtained from each characteristic value in the most recent predetermined period, the effects caused by passage of time such as seasonal fluctuations are eliminated, resulting in high reliability. diagnosis becomes possible. The boundary threshold value is, for example, a group of measurement data obtained in a normal state in which manhole pumps installed in a plurality of manhole devices with different environments, including the manhole device in which the manhole pump to be diagnosed is installed, are properly operated. is automatically generated by a machine learning device using only as training data, an appropriate value that suppresses the influence of environmental differences can be obtained. No time-consuming preparation is required.

In the third feature configuration, in addition to the above-described first or second feature configuration, the normalization step includes the average value μ and the variance σ from each characteristic value obtained in the predetermined period ² is calculated as statistical data, and the formula (x−μ)/σ is applied to the feature amount x to normalize each characteristic value in the diagnosis target period.

Statistical data mean value μ and variance σ obtained based on the measurement data group for the most recent predetermined period ² By performing the normalization processing of the measurement data group based on, for example, influence due to passage of time such as seasonal variation is eliminated, and highly reliable diagnosis becomes possible.

In the fourth feature configuration, in addition to any one of the above-described first to third feature configurations, the diagnosis step includes a predetermined abnormality reference value each time a characteristic value point is primarily diagnosed as abnormal. is multiplied by a weighting factor based on the distance between the characteristic value point and the boundary threshold, and each time the characteristic value point is diagnosed as normal in the diagnosis step, a predetermined return-to-normal evaluation value is subtracted. The final diagnosis of normality or abnormality of the manhole pump is made based on the cumulative evaluation value obtained.

There are minor anomalies that are diagnosed as normal even if they are diagnosed as abnormal in the primary diagnosis, and there are also anomalies that are continuously diagnosed as abnormal and eventually lead to a serious failure. Even in such a case, each time an abnormality is diagnosed in the primary diagnosis, a value obtained by multiplying a predetermined abnormality reference value by a weighting factor based on the distance between the characteristic value point and the boundary threshold is added. A cumulative evaluation value obtained by subtracting a predetermined return-to-normal evaluation value is calculated, and a final diagnosis is made as to whether the manhole pump is normal or abnormal based on the cumulative evaluation value. It is possible to make a diagnosis considering the degree of abnormality such as

In the fifth feature configuration, in addition to any one of the first to fourth feature configurations described above, the outside of the boundary threshold set in the two-dimensional coordinate system is divided into a plurality of areas, and each division is A diagnosis map associated with any cause of abnormality is provided, and the diagnosis step consists in diagnosing the cause of abnormality based on the area where each characteristic value point is plotted.

The cause of the abnormality can be estimated by determining in which region of the diagnostic map partitioned outside the boundary threshold value indicating the normal region the characteristic value point indicated by the pair of normalized characteristic values is located.

The sixth characteristic configuration is a method for diagnosing two manhole pumps installed in a manhole to be diagnosed and repeatedly starting and stopping. a sampling step of sampling the driving time and calculating each average driving time as a pair of characteristic values; a normalization step of normalizing the pair of characteristic values calculated in the sampling step; A pair of normalized characteristic values are plotted on a two-dimensional coordinate system with the x-axis and the other y-axis, and the plotted characteristic value points exist on either side of a boundary threshold preset in the two-dimensional coordinate system. a diagnostic step of primary diagnosing whether each manhole pump is normal or abnormal based on whether the Accumulation obtained by multiplying and adding a weighting factor based on the distance between the characteristic value point and the boundary threshold, and subtracting a predetermined return-to-normal evaluation value each time the characteristic value point is diagnosed as normal in the diagnosis step The final diagnosis of normality or abnormality of the manhole pump is made based on the evaluation value.

The seventh characteristic configuration is a diagnostic method for two manhole pumps that are installed in a manhole to be diagnosed and that repeatedly start and stop. a sampling step of sampling the operating times to calculate each average operating time, and setting one average operating time and a ratio of one average operating time to the other average operating time as a pair of characteristic values; A normalization step for normalizing the pair of characteristic values calculated in , and plotting the normalized pair of characteristic values on a two-dimensional coordinate system with one of the pair of characteristic values on the x axis and the other on the y axis. , a diagnostic step of primarily diagnosing normality or abnormality of each manhole pump based on which side of a boundary threshold preset in the two-dimensional coordinate system the plotted characteristic value point exists, In the diagnosing step, each time a characteristic value point is primarily diagnosed as abnormal, a predetermined abnormality reference value is multiplied by a weighting factor based on the distance between the characteristic value point and the boundary threshold, and the characteristic value point Each time the manhole pump is diagnosed as normal in the diagnosing step, final diagnosis of normality or abnormality of the manhole pump is made based on an accumulated evaluation value obtained by subtracting a predetermined return-to-normal evaluation value.

The seventh characteristic configuration is, in addition to the fifth or sixth characteristic configuration described above, the statistical data necessary for the normalization process used in the normalization step is the diagnosis target period when the normalization process is executed. is calculated based on each characteristic value for the most recent predetermined period including

The eighth characteristic configuration, in addition to any one of the fifth to seventh characteristic configurations described above, is divided into a plurality of areas outside the boundary threshold value set in the two-dimensional coordinate system, and each division is A diagnosis map associated with any cause of abnormality is provided, and the diagnosis step consists in diagnosing the cause of abnormality based on the area where each characteristic value point is plotted.

The ninth feature configuration is, in addition to any one of the fifth to eighth feature configurations described above, in the diagnosis step, the boundary threshold value is determined by a machine learning device based on the characteristic value input as learning data. The point is that it is automatically generated.

A first characteristic configuration of the manhole pump diagnostic device according to the present invention is a diagnostic device for two manhole pumps installed in a manhole to be diagnosed and repeatedly starting and stopping. A pair of characteristic values composed of each average operation time calculated from the operation time per start of each sampled manhole pump is set to only each characteristic value calculated in the most recent predetermined period including the diagnosis target period. A pair of normalized characteristic values is plotted on a two-dimensional coordinate system in which one of the pair of characteristic values is on the x-axis and the other is on the y-axis. and a diagnosis processing unit that performs a primary diagnosis of normality or abnormality of each manhole pump based on which side of a boundary threshold preset in a two-dimensional coordinate system the plotted characteristic value point exists, The diagnosis processing unit performs machine learning using only normal characteristic values obtained from each manhole pump installed in a plurality of manholes, including each manhole pump installed in the manhole to be diagnosed, as teacher data. device, and the machine learning device generates the boundary threshold value of the two-dimensional coordinate system, which is a feature space in which normal characteristic values are included.

The second characteristic configuration is a diagnostic device for two manhole pumps installed in a manhole to be diagnosed and repeatedly starting and stopping. Of the average operating times calculated from the operating time per startup, a pair of characteristic values composed of one average operating time and the ratio of one average operating time to the other average operating time is selected as the diagnosis target. a normalization processing unit that normalizes based on statistical data calculated only based on each characteristic value calculated in the most recent predetermined period including the period; A pair of normalized characteristic values are plotted on a two-dimensional coordinate system, and each manhole is determined based on which side of a boundary threshold preset in the two-dimensional coordinate system the plotted characteristic value point exists. a diagnosis processing unit that performs a primary diagnosis of whether the pump is normal or abnormal, wherein the diagnosis processing unit is configured to detect each manhole pump installed in a plurality of manholes, including each manhole pump installed in the manhole to be diagnosed. A machine learning device that learns using only normal characteristic values obtained from as training data, and the machine learning device generates a boundary threshold value of the two-dimensional coordinate system that becomes a feature space containing normal characteristic values. It is in the point that it is done.

In the third feature configuration, in addition to the above-described first or second feature configuration, the diagnosis processing unit, each time a primary diagnosis is made that each characteristic value point is abnormal, Accumulation obtained by multiplying and adding a weighting factor based on the distance between each characteristic value point and the boundary threshold, and subtracting a predetermined abnormality reference value each time each characteristic value point is primary diagnosed as normal The final diagnosis is whether each manhole pump is normal or abnormal based on the evaluation value.

The fourth feature configuration is, in addition to any one of the first to third feature configurations described above, the outside of the boundary threshold set in the two-dimensional coordinate system is divided into a plurality of areas, and each section is abnormal A diagnosis map associated with any cause is provided, and the diagnosis processing unit diagnoses the cause of abnormality based on the area where each characteristic value point is plotted.

The fifth characteristic configuration is a diagnostic device for two manhole pumps that are installed in a manhole and repeatedly start and stop, and is calculated from the operating time per start of each manhole pump sampled within a predetermined period. A normalization processing unit that normalizes a pair of characteristic values composed of each average driving time, and a two-dimensional coordinate system in which one of the pair of characteristic values is the x axis and the other is the y axis. A diagnostic processing unit that plots a pair of characteristic values and performs a primary diagnosis of normality or abnormality of each manhole pump based on which side of a boundary threshold preset in a two-dimensional coordinate system the plotted characteristic value point exists. and the diagnosis processing unit multiplies a predetermined abnormality reference value by a weighting factor based on the distance between each characteristic value point and the boundary threshold each time each characteristic value point is primarily diagnosed as abnormal. In addition, each time when each characteristic value point is primary diagnosed as normal, the final diagnosis of normality or abnormality of each manhole pump is made based on the cumulative evaluation value obtained by subtracting the predetermined abnormality reference value. It is in.

The sixth characteristic configuration is a diagnostic device for two manhole pumps that are installed in a manhole and repeatedly start and stop, and is calculated from the operating time per start of each manhole pump sampled within a predetermined period. a normalization processing unit that normalizes a pair of characteristic values composed of one average driving time and the ratio of one average driving time and the other average driving time among the average driving times obtained; A pair of normalized characteristic values are plotted on a two-dimensional coordinate system in which one of the characteristic values is on the x-axis and the other is on the y-axis, and the plotted characteristic value points are boundaries set in advance in the two-dimensional coordinate system. a diagnostic processing unit that performs a primary diagnosis of normality or abnormality of each manhole pump based on which side of the threshold it exists, wherein the diagnostic processing unit performs a primary diagnosis that each characteristic value point is abnormal. Each time, a predetermined abnormality reference value is multiplied by a weighting factor based on the distance between each characteristic value point and the boundary threshold value, and each time the characteristic value point is primary diagnosed as normal, the predetermined abnormality reference value is added. The final diagnosis of whether each manhole pump is normal or abnormal is based on the accumulated evaluation value obtained by subtracting the reference value.

In the seventh characteristic configuration, in addition to the fifth or sixth characteristic configuration described above, the outside of the boundary threshold value set in the two-dimensional coordinate system is divided into a plurality of areas, and each division corresponds to any cause of abnormality. and the diagnostic processing unit diagnoses the cause of the abnormality based on the area where each characteristic value point is plotted.

The eighth feature configuration is, in addition to any one of the fifth to seventh feature configurations described above, the diagnostic processing unit automatically generating the boundary threshold value based on a pair of characteristic values input as learning data. It is equipped with a machine learning device that

As described above, according to the present invention, it is possible to provide a manhole pump diagnostic method and diagnostic apparatus capable of accurately diagnosing abnormalities due to various causes even with small physical quantities.

Explanatory drawing of manhole pump Explanatory drawing of manhole pump abnormality diagnosis device Explanatory drawing showing the procedure of the manhole pump abnormality diagnosis method (a) is an explanatory diagram of the measurement data, (b) is an enlarged explanatory diagram of the main part of the measurement data Explanatory diagram of normalization processing Illustration of primary diagnosis Explanatory diagram of cumulative evaluation value and final diagnosis Diagram of diagnostic map

The diagnostic method and diagnostic device for a manhole pump according to the present invention will be described below.

A manhole pump device 10 is shown in FIG. The manhole pump device 10 includes a manhole 12 as a water reservoir for storing sewage that has flowed in from an upstream sewage inflow pipe 11, and two pumps that pressure-feed the sewage stored in the manhole 12 to a downstream sewage outflow pipe 13. PA, PB and water level gauges 18 and 19 for measuring the water level of the sewage stored in the manhole 12 are provided.

A first pumping pipe 15b, a first curved pipe 15c, and a first horizontal pipe 15d are flange-connected to the discharge curved pipe 15a of the first pump PA. 13 is flanged. A check valve 15e is provided between the first pumping pipe 15b and the first curved pipe 15c.

A second pumping pipe 17b and a second curved pipe 17c are flange-connected to the discharge curved pipe 17a of the second pump PB, and the second curved pipe 17c is flange-connected to the sewage outflow pipe 13 via a header pipe 13a. there is A check valve 17e is provided between the second pumping pipe 17b and the second curved pipe 17c.

A immersion pressure or bubble type water gauge 18 is installed at the bottom of the manhole 12 . The water level of the sewage stored in the manhole 12 is continuously detected by the water level gauge 18 . Furthermore, a float-type water level gauge 19 is installed as a backup water level gauge for detecting an abnormally high water level HHWL.

In the vicinity of the manhole 12 is housed a control panel 20 including a control unit 21 for controlling the pumps PA and PB to carry out sewage transfer control for pumping the sewage collected in the manhole 12 to the sewage outflow pipe 13. 200 are installed.

The control panel 20 is provided with a control section 21 , a storage section 22 and a communication section 24 . The storage unit 22 stores control information from the control unit 21, water level information from the water level gauges 18 and 19, and the like. The communication unit 24 includes a transmission unit that transmits various information stored in the storage unit 22 to the remote monitoring device 40 and a reception unit that receives control commands from the monitoring device 40 .

A wireless communication medium such as a mobile phone network is preferably used as a communication medium for connecting the communication unit 24 and the monitoring device 40, and the monitoring device 40 and the communication unit 24 are connected to the Internet via such a communication medium. Further, the portable communication terminal 30 owned by the manager of the manhole pump device 10 and the monitoring device 40 are configured to be connectable to the Internet via a wireless communication medium.

The control panel 20 and the respective pumps PA and PB are connected by AC feeder lines L1 and L2, and the control panel 20 and the water level gauges 18 and 19 are connected by a signal line S.

When the control unit 21 detects that the water level measured by the water level gauge 18 has reached a predetermined pump activation water level HWL, the control unit 21 controls power supply from the power supply line L1 to activate one of the pumps PA and PB, When it is detected that the water level has reached the pump stop water level LWL which is lower than the pump start water level HWL, power supply is stopped to stop the one pump PA.

After that, when the control unit 21 detects that the water level has reached the pump start water level HWL again, it controls power supply from the power supply line L2 to start the other pump PB, and when it detects that the water level has reached the pump stop water level LWL, it starts power supply. Stop to stop the pump PB. That is, the controller 21 alternately controls the operation of the pumps PA and PB.

Furthermore, the control unit 21 detects an abnormally high water level when the pump starting water level HWL cannot be detected due to a failure of the water level gauge 18 or when a large amount of rainwater exceeding the drainage capacity of one pump flows into the manhole 12 due to torrential rain. When it is detected that the water level gauge 19 has reached HHWL, the two pumps PA and PB are operated simultaneously.

The control unit 21 samples the water level information detected by the water level gauges 18 and 19 at intervals of one minute, for example, in time series and stores it in the storage unit 22. Time-series operation information such as operation time from start to stop is stored in the storage unit 22 .

As shown in FIG. 2, the communication unit 24 provided in the control panel 20 of each manhole pump device 10 is configured to transmit the water level information and operation information stored in the storage unit 22 to the monitoring device 40 at predetermined intervals. ing.

The monitoring device 40 functions as a diagnostic device for the manhole pump device 10, and the communication unit 41 communicates with the communication unit 24 of each manhole pump device 10 and the manager's mobile communication terminal 30, and the communication unit 24 of each manhole pump device 10 A database DB that stores the transmitted water level information and operation information, a data processing unit 42 that exchanges data with the database DB, and each manhole pump device 10 is normal based on the water level information and operation information stored in the database DB. A diagnostic unit 44 is provided for diagnosing whether the system is operating normally.

The diagnosis section 44 includes a normalization processing section 46 and a diagnosis processing section 48 . The normalization processing unit 46 is configured to normalize a pair of characteristic values obtained from a predetermined period of operation time indicating the characteristic of each of the pumps PA and PB sampled in time series. The average operating time of each pump can be calculated as a pair of characteristic values, and the average operating time of one pump and the ratio of the average operating time of one pump to the average operating time of the other pump can be calculated as a pair of characteristic values. It can also be a characteristic value.

The diagnosis processing unit 48 includes a machine learning device that automatically generates a boundary threshold for diagnosing normality or abnormality based on a plurality of past data indicating a pair of characteristic values input as learning data. The machine learning device plots the pair of normalized characteristic values in a two-dimensional coordinate system in which one of the pair of characteristic values is the x-axis and the other is the y-axis, and the plotted characteristic value points are two-dimensional It is configured to perform a primary diagnosis of normality or abnormality of each manhole pump based on which side of the boundary threshold preset in the coordinate system exists. The machine learning device consists of a computer that executes a one-class support vector machine algorithm.

Further, the diagnosis processing unit 48 multiplies and adds a predetermined abnormality reference value by a weighting factor based on the distance between the characteristic value point and the boundary threshold, and adds the characteristic value Each time a point is diagnosed as normal in the primary diagnosis, a final diagnosis of normality or abnormality of the manhole pump is made based on an accumulated evaluation value obtained by subtracting a predetermined return-to-normal evaluation value.

The outside of the boundary threshold set in the two-dimensional coordinate system is divided into a plurality of areas, each section is provided with a diagnostic map associated with one of the causes of abnormality, and the diagnostic processing unit 48 plots each characteristic value point It is configured to diagnose the anomaly cause based on the area.

FIG. 3 shows a flow of a series of diagnostic processes executed by the monitoring device 40. As shown in FIG. When the measurement data for one day is received from each manhole pump device 10 and stored in the database DB (SA1), the measurement data of the pumps PA and PB are used as the measurement data for each pump of each manhole pump device 10 to determine abnormality. The operating hours are extracted, and the average operating hours of the pumps PA and PB are calculated by dividing the total operating hours of the pumps in one day by the number of times of operation (SA2). As the feature quantity, a pair of characteristic values may be selected from the average operating time of each pump, or the ratio of the average operating time of one pump to the average operating time of one pump to the average operating time of the other pump. and may be selected as a pair of characteristic values. Statistical amounts required for normalization processing, that is, average values and variance values, are calculated from the average driving time within the most recent predetermined period stored in the database DB, and the feature values of the day to be judged are normalized. (SA3).

The normalized feature amount is input to the machine learning device and primary judgment is performed based on the set boundary threshold (SA5). SA6), and if it is determined to be normal, the cumulative evaluation value is subtracted (SA7).

A final abnormality determination is made as to whether or not the cumulative evaluation value calculated by repeating such processing daily exceeds a preset cumulative abnormality threshold (SA8). The cause of the abnormality is specified based on the diagnostic map showing the correlation with the cause (SA9), and the cause of the abnormality and an alarm to the effect that there is an abnormality are transmitted to a mobile terminal or the like owned by the administrator (SA10). The warning notification is sent as an e-mail via a mailer provided in the communication section 41 .

The diagnostic unit 44 will be described in detail below.
FIG. 4(a) shows operation data of the manhole pump device for 24 hours from 00:00 am to 00:00 the next day. The water level fluctuations, the operation timing and operation time of the pumps PA and PB, the current value of the pump PA, and the current value of the pump PB are shown in order from the top.

FIG. 4(b) is an enlarged display for facilitating understanding of the relationship between the water level fluctuations, the operation timings of the pumps PA and PB, and the operation time shown in FIG. 4(a). When the manhole water level reaches HWL, the pump PA is started and stopped when the water level drops to LWL. Next, when the water level reaches HWL, the pump PB is started and stopped when the water level drops to LWL. Any pump is activated until the water level drops from HWL to LWL. The operating time of the pump becomes longer when the pump's conveying amount is low or when the amount of sewage flowing into the manhole is large.

Such water level information and operation information stored in the storage unit 22 of each manhole pump device 10 are transmitted to the monitoring device 40 via the communication unit 24 and stored in the database DB via the data processing unit 42 .

From such data, the data processing unit 42 extracts the "total value of pump operating time" and the "number of times of operation" when each pump PA, PB is started, and extracts the "total value of pump operating time". ” divided by the “number of times of operation”, the average operating time of each pump is set as a pair of characteristic values, or the average operating time of one pump and the average operating time of one pump The ratio of the average operating time of one pump and the average operating time of the other pump is calculated as a pair of characteristic values and transferred to the normalization processing unit 46 .

As shown in FIG. 5, the normalization processing unit 46 calculates the average value μ and the variance σ ² for data normalization using the feature values accumulated in the database DB in the last three months as a population. Then, each average operating time, which is a feature quantity, is normalized by the formula (x−μ)/σ for the feature quantity x.

Although not limited to the most recent three months, the statistical data (average value, variance value) required for normalization processing is calculated based on the measurement data group for the most recent predetermined period when normalization processing is executed. It is preferred that the effects due to the lapse of time, such as seasonal variations, are eliminated, and a highly reliable diagnosis is possible.

A pair of characteristic values composed of the feature value "average operating time of each pump" normalized by the normalization processing unit 46 or "average operating time of one pump, average operating time of one pump and average operating time of the other pump" When a pair of characteristic values constituted by the ratio of the average operating time of the pump is input to the diagnosis processing unit 48, the normal plotting a pair of characteristic values, and primary diagnosis of normality or abnormality of each manhole pump based on which side of the boundary threshold value preset in the two-dimensional coordinate system the plotted characteristic value point exists. do.

By normalizing the characteristic values calculated based on the measured values sampled in chronological order in the sampling step in the normalization step, characteristic values excluding the influence of machine differences of manhole pumps and the influence of the installation environment, etc. can be extracted as feature values, and the feature values, that is, the points representing the two types of measurement data groups are plotted in a two-dimensional coordinate system as a plurality of time-series points in the diagnosis step, and a preset boundary threshold is used as an index to properly perform primary diagnosis as to whether the manhole pump device is normal or abnormal.

In FIG. 6, the vertical axis (y-axis) is the ratio of the average operating time of each pump (T(PA)/T(PB)), and the horizontal axis (x-axis) is the average operating time of the pump PB (T(PB) ) of the two-dimensional coordinate system (the average value of each value). It shows how it is determined to be normal and abnormal when the plotted characteristic value points are located outside the boundary threshold. The characteristic value points may be plotted on a two-dimensional coordinate system in which the vertical axis (y-axis) is the average operating time of one pump and the horizontal axis (x-axis) is the average operating time of the other pump PB.

The diagnostic processing unit 48 includes a machine learning device that automatically generates the above-described boundary threshold value based on the measurement data group input as learning data. As the machine learning device, a computer that executes algorithms such as a one-class support vector machine, LOF (local outlier factor) method, IF (Isolation Forest) method, RC (Robust Covariance) method, or the like can be used.

By performing machine learning, in the mapping space (feature space) shown in FIG. 6, a normal data space in which normal measurement data (training data) are mapped, that is, an inner space of boundary thresholds is generated. In the example of FIG. 6, the result of learning as learning data a pair of characteristic values for one year obtained from 100 manhole pump devices with two pumps installed is shown.

Each time the diagnostic processing unit 48 makes a primary diagnosis that the characteristic value point is abnormal, the weighting factor based on the distance between the position of each characteristic value point and the boundary threshold is added to the predetermined abnormality reference value Vnb based on the following formula: W is multiplied and added, and each time each characteristic value point is diagnosed as normal in the primary diagnosis, a predetermined return-to-normal evaluation value Vpb is subtracted to calculate a cumulative evaluation value V, and based on the cumulative evaluation value Final diagnosis of normality or abnormality of manhole pump equipment. The distance between the position of the characteristic value point and the boundary threshold refers to the length of the normal line from the boundary threshold that passes through the characteristic value point.
V=Vnb×W−Vpb
In this embodiment, Vnb=1 and Vnb<Vpb<Wmax×Vnb are set.

There are minor anomalies that are diagnosed as normal even if they are diagnosed as abnormal in the primary diagnosis, and there are also anomalies that are continuously diagnosed as abnormal and eventually lead to a serious failure. Even in such a case, each time an abnormality is diagnosed in the primary diagnosis, a value obtained by multiplying a predetermined abnormality reference value by a weighting factor based on the distance between the characteristic value point and the boundary threshold is added. A cumulative evaluation value obtained by subtracting a predetermined return-to-normal evaluation value is calculated, and a final diagnosis of normality or abnormality of the mechanical equipment is made based on the cumulative evaluation value, thereby detecting abnormalities that require maintenance in the near future, for example. It is possible to make a diagnosis considering the degree of abnormality such as

FIG. 7 shows changes in cumulative evaluation values. The cumulative evaluation value is subjected to a primary evaluation every predetermined period in which the characteristic value points are plotted. When it is determined to be abnormal, the value of Vnb×W is added to the initial value 0, and when it is determined to be normal, the value of Vpb is subtracted. be. When the cumulative evaluation value exceeds a predetermined threshold value, which is "10" in this example, a final determination of abnormality is made, and a notification to that effect is sent to a mobile terminal or the like owned by the administrator. It should be noted that the primary determination and the final determination are continuously made even after the abnormality is determined.

A diagnostic map is illustrated in FIG. The area outside the boundary threshold shown in the feature space shown in FIG. 6 is divided into 8 regions, and each region is associated with one of the causes of abnormality. The diagnosis processing unit 48 diagnoses the cause of abnormality based on the area where each feature data is plotted.

For example, in the example of FIG. 8, when the characteristic value points are plotted in region 2, only the pump PA that operates for a long time is abnormal, in region 4, the external environment is abnormal such as a water level gauge abnormality, and in region 5, both are for a long time. Abnormalities in both pumps that are in operation, an increase in the inflow of sewage, abnormalities in the external environment such as clogging of the confluence of the discharge pipes, and in region 8, only the pump PB that has been operating for a long time is diagnosed as abnormal.

In the above example, the average operating time of each pump or the ratio of the average operating time of one pump to the average operating time of the other pump is used as a pair of characteristic values. Not limited to data, the operating time per operation of each pump, the ratio of the operating time per operation of one pump and the operating time per operation of the other pump, Fig. 4 ( Needless to say, the current value during operation of each pump shown in a), the average current value, the ratio of the average current values of both pumps, and the like can be appropriately set.

As described above, the method for diagnosing manhole pumps according to the present invention is a method for diagnosing two manhole pumps installed in a manhole and repeatedly starting and stopping. A sampling step of sampling the driving time of each and calculating each average driving time as a pair of characteristic values, a normalization step of normalizing the pair of characteristic values calculated in the sampling step, and one of the pair of characteristic values A pair of normalized characteristic values are plotted on a two-dimensional coordinate system with the x-axis and the other y-axis, and the plotted characteristic value points exist on either side of a boundary threshold preset in the two-dimensional coordinate system. a diagnostic step of primary diagnosing whether each manhole pump is normal or abnormal based on whether the manhole pump is normal or abnormal.

In addition, the operating time per start of each manhole pump within a predetermined period is sampled to calculate the average operating time of each, and the average operating time of one and the ratio of the average operating time of one to the average operating time of the other a pair of characteristic values, a normalization step of normalizing the pair of characteristic values calculated in the sampling step, and a two-dimensional coordinate system in which one of the pair of characteristic values is the x-axis and the other is the y-axis , plot a pair of normalized characteristic values, and determine whether each manhole pump is normal or abnormal based on which side of the boundary threshold the plotted characteristic value point lies on, which is preset in a two-dimensional coordinate system. and a diagnostic step of primarily diagnosing the

Statistical data necessary for the normalization process used in the normalization step is calculated based on each characteristic value in a predetermined period immediately before the execution of the normalization process.

In the diagnosis step, each time the characteristic value point is primarily diagnosed as abnormal, a predetermined abnormality reference value is multiplied by a weighting factor based on the distance between the characteristic value point and the boundary threshold, and the A final diagnosis of normality or abnormality of the manhole pump is made based on an accumulated evaluation value obtained by subtracting a predetermined return-to-normal evaluation value every time the manhole pump is diagnosed as normal.

A diagnosis map is provided in which the outside of a boundary threshold set in a two-dimensional coordinate system is divided into a plurality of areas, and each division is associated with one of the causes of anomalies, and the diagnosis step includes: It is configured to diagnose the cause of the abnormality based on.

Preferably, the diagnosis step automatically generates a boundary threshold value using a machine learning device based on characteristic values input as learning data.

In the above-described embodiments, the entire diagnosis step is performed by the machine learning device, but only the generation of the boundary thresholds may be performed by the machine learning device, and even the default boundary thresholds may be calculated without using the machine learning device. A diagnostic step may be performed using

Each of the above-described embodiments is an example of the present invention, and the technical scope of the present invention is not limited by the description. It is needless to say that the threshold value to be set to can be appropriately changed and designed as long as the effects of the present invention are exhibited.

10: Manhole pump equipment PA, PB: Pumps 18, 19: Water level gauge 21: Control unit 22: Storage unit 24: Communication unit 30: Mobile terminal 40: Monitoring device 41: Communication unit 42: Data processing unit 44: Diagnosis unit 46 : Normalization processing unit 48: Diagnosis processing unit

Claims (18)

A diagnostic method for two manhole pumps installed in a manhole to be diagnosed and repeatedly starting and stopping,
a sampling step of sampling the operating time per start of each manhole pump within a predetermined diagnosis target period and calculating the average operating time of each as a pair of characteristic values;
A normalization step of normalizing the pair of characteristic values calculated in the sampling step based on statistical data calculated based only on each characteristic value calculated in the most recent predetermined period including the diagnosis target period;
A pair of normalized characteristic values are plotted on a two-dimensional coordinate system in which one of the pair of characteristic values is the x-axis and the other is the y-axis, and the plotted characteristic value points are a boundary preset in the two-dimensional coordinate system. a diagnostic step of primary diagnosing whether each manhole pump is normal or abnormal based on which side of the threshold it exists;
with
The boundary threshold is learned using only normal characteristic values obtained from each manhole pump installed in a plurality of manholes, including each manhole pump installed in the manhole to be diagnosed, as teacher data. A method for diagnosing a manhole pump, wherein the boundary of the two-dimensional coordinate system is automatically generated by the apparatus and is a feature space containing normal characteristic values. A diagnostic method for two manhole pumps installed in a manhole to be diagnosed and repeatedly starting and stopping,
Sampling the operating time per start of each manhole pump within a predetermined diagnosis target period, calculating each average operating time, and calculating the average operating time of one and the ratio of the average operating time of one to the average operating time of the other a sampling step with and as a pair of characteristic values;
a normalization step of normalizing the pair of characteristic values calculated in the sampling step based on statistical data calculated based only on each characteristic value calculated in the most recent predetermined period including the diagnosis target period;
A pair of normalized characteristic values are plotted on a two-dimensional coordinate system in which one of the pair of characteristic values is the x-axis and the other is the y-axis, and the plotted characteristic value points are preset in the two-dimensional coordinate system. a diagnostic step of primary diagnosing whether each manhole pump is normal or abnormal based on which side of the boundary threshold value is present;
with
The boundary threshold is learned using only normal characteristic values obtained from each manhole pump installed in a plurality of manholes, including each manhole pump installed in the manhole to be diagnosed, as teacher data. A method for diagnosing a manhole pump, wherein the boundary of the two-dimensional coordinate system is automatically generated by the apparatus and is a feature space containing normal characteristic values. In the normalization step, the average value μ and variance σ ² are calculated as statistical data from each characteristic value obtained in the predetermined period, and the formula (x−μ)/σ is applied to the feature amount x. 3. The method of diagnosing a manhole pump according to claim 1, wherein each characteristic value in said diagnosis target period is normalized. In the diagnosis step, each time a characteristic value point is primarily diagnosed as abnormal, a predetermined abnormality reference value is multiplied by a weighting factor based on the distance between the characteristic value point and the boundary threshold, and the characteristic value 4. A final diagnosis of normality or abnormality of said manhole pump is made based on an accumulated evaluation value obtained by subtracting a predetermined return-to-normal evaluation value every time a point is diagnosed as normal in said diagnosing step. The method for diagnosing a manhole pump as described above. A diagnostic map in which the outside of the boundary threshold set in the two-dimensional coordinate system is divided into a plurality of regions, each region being associated with one of the causes of abnormality;
5. The method of diagnosing a manhole pump according to any one of claims 1 to 4, wherein said diagnosing step diagnoses the cause of abnormality based on the area where each characteristic value point is plotted. A diagnostic device for two manhole pumps installed in a manhole to be diagnosed and repeatedly starting and stopping,
A pair of characteristic values composed of each average operating time calculated from the operating time per start of each manhole pump sampled within a predetermined diagnostic period is calculated for the most recent predetermined period including the diagnostic target period. a normalization processing unit that normalizes based on statistical data calculated based only on each characteristic value;
A pair of normalized characteristic values is plotted on a two-dimensional coordinate system in which one of the pair of characteristic values is the x-axis and the other is the y-axis, and the plotted characteristic value points are preset boundaries in the two-dimensional coordinate system. a diagnosis processing unit that performs a primary diagnosis of normality or abnormality of each manhole pump based on which side of the threshold it exists;
with
The diagnosis processing unit is a machine that learns using only normal characteristic values obtained from each manhole pump installed in a plurality of manholes, including each manhole pump installed in the manhole to be diagnosed, as teacher data. A diagnosis device for a manhole pump, comprising a learning device, wherein the boundary threshold value of the two-dimensional coordinate system, which is a feature space containing normal characteristic values, is generated by the machine learning device. A diagnostic device for two manhole pumps installed in a manhole to be diagnosed and repeatedly starting and stopping,
Among the average operating times calculated from the operating time per start of each manhole pump sampled within a predetermined diagnostic period, the average operating time of one, the average operating time of one, and the average operating time of the other A normalization processing unit that normalizes a pair of characteristic values composed of a ratio based on statistical data calculated based only on each characteristic value calculated in the most recent predetermined period including the diagnosis target period;
A pair of normalized characteristic values are plotted on a two-dimensional coordinate system in which one of the pair of characteristic values is the x-axis and the other is the y-axis, and the plotted characteristic value points are preset in the two-dimensional coordinate system. a diagnostic processing unit that performs a primary diagnosis of normality or abnormality of each manhole pump based on which side of the boundary threshold value is present;
with
The diagnosis processing unit is a machine that learns using only normal characteristic values obtained from each manhole pump installed in a plurality of manholes, including each manhole pump installed in the manhole to be diagnosed, as teacher data. A diagnosis device for a manhole pump, comprising a learning device, wherein the boundary threshold value of the two-dimensional coordinate system, which is a feature space containing normal characteristic values, is generated by the machine learning device. The diagnosis processing unit multiplies and adds a predetermined abnormality reference value by a weighting factor based on the distance between each characteristic value point and the boundary threshold each time a primary diagnosis is made that each characteristic value point is abnormal, 8. A final diagnosis of normality or abnormality of each manhole pump is made based on an accumulated evaluation value obtained by subtracting a predetermined abnormality reference value every time each characteristic value point is primarily diagnosed as being normal. diagnostic equipment for manhole pumps. a diagnostic map in which the outside of the boundary threshold set in a two-dimensional coordinate system is segmented into a plurality of regions, each segment being associated with one of the causes of anomalies;
9. The manhole pump diagnosis device according to claim 6, wherein the diagnosis processing unit diagnoses the cause of abnormality based on the area where each characteristic value point is plotted. A diagnostic method for two manhole pumps installed in a manhole to be diagnosed and repeatedly starting and stopping,
a sampling step of sampling the operating time per start of each manhole pump within a predetermined diagnosis target period and calculating the average operating time of each as a pair of characteristic values;
a normalization step of normalizing the pair of characteristic values calculated in the sampling step;
A pair of normalized characteristic values is plotted on a two-dimensional coordinate system in which one of the pair of characteristic values is the x-axis and the other is the y-axis, and the plotted characteristic value points are preset boundaries in the two-dimensional coordinate system. a diagnostic step of primary diagnosing whether each manhole pump is normal or abnormal based on which side of the threshold it exists;
with
In the diagnosis step, each time a characteristic value point is primarily diagnosed as abnormal, a predetermined abnormality reference value is multiplied by a weighting factor based on the distance between the characteristic value point and the boundary threshold, and the characteristic value A manhole pump diagnosing method for final diagnosing whether the manhole pump is normal or abnormal based on an accumulated evaluation value obtained by subtracting a predetermined return-to-normal evaluation value each time a point is diagnosed as normal in the diagnosing step. A diagnostic method for two manhole pumps installed in a manhole to be diagnosed and repeatedly starting and stopping,
Sampling the operating time per start of each manhole pump within a predetermined diagnosis target period, calculating each average operating time, and calculating the average operating time of one and the ratio of the average operating time of one to the average operating time of the other a sampling step with and as a pair of characteristic values;
a normalization step of normalizing the pair of characteristic values calculated in the sampling step;
A pair of normalized characteristic values are plotted on a two-dimensional coordinate system in which one of the pair of characteristic values is the x-axis and the other is the y-axis, and the plotted characteristic value points are preset in the two-dimensional coordinate system. a diagnostic step of primary diagnosing whether each manhole pump is normal or abnormal based on which side of the boundary threshold value is present;
with
In the diagnosis step, each time a characteristic value point is primarily diagnosed as abnormal, a predetermined abnormality reference value is multiplied by a weighting factor based on the distance between the characteristic value point and the boundary threshold, and the characteristic value A manhole pump diagnosing method for final diagnosing whether the manhole pump is normal or abnormal based on an accumulated evaluation value obtained by subtracting a predetermined return-to-normal evaluation value each time a point is diagnosed as normal in the diagnosing step. 12. The statistical data required for the normalization process used in the normalization step is calculated based on each characteristic value of the most recent predetermined period including the diagnosis target period when the normalization process is executed. diagnostic method for manhole pumps. A diagnostic map in which the outside of the boundary threshold set in the two-dimensional coordinate system is divided into a plurality of regions, each region being associated with one of the causes of abnormality;
13. The method of diagnosing a manhole pump according to any one of claims 10 to 12, wherein said diagnosing step diagnoses the cause of abnormality based on the area where each characteristic value point is plotted. 14. The method of diagnosing a manhole pump according to any one of claims 10 to 13, wherein, in said diagnosing step, a machine learning device automatically generates said boundary threshold based on said characteristic value input as learning data. A diagnostic device for two manhole pumps installed in a manhole and repeatedly starting and stopping,
a normalization processing unit that normalizes a pair of characteristic values composed of each average operation time calculated from the operation time per start of each manhole pump sampled within a predetermined period;
A pair of normalized characteristic values is plotted on a two-dimensional coordinate system in which one of the pair of characteristic values is the x-axis and the other is the y-axis, and the plotted characteristic value points are preset boundaries in the two-dimensional coordinate system. a diagnosis processing unit that performs a primary diagnosis of normality or abnormality of each manhole pump based on which side of the threshold it exists;
with
The diagnosis processing unit multiplies and adds a predetermined abnormality reference value by a weighting factor based on the distance between each characteristic value point and the boundary threshold each time a primary diagnosis is made that each characteristic value point is abnormal, A diagnosis device for manhole pumps that makes a final diagnosis of normality or abnormality of each manhole pump based on a cumulative evaluation value obtained by subtracting a predetermined abnormality reference value every time each characteristic value point is primary diagnosed as normal. A diagnostic device for two manhole pumps installed in a manhole and repeatedly starting and stopping,
Among the average operating times calculated from the operating time per start of each manhole pump sampled within a predetermined period, the average operating time of one and the ratio of the average operating time of one to the average operating time of the other a normalization processing unit that normalizes the pair of configured characteristic values;
A pair of normalized characteristic values are plotted on a two-dimensional coordinate system in which one of the pair of characteristic values is the x-axis and the other is the y-axis, and the plotted characteristic value points are preset in the two-dimensional coordinate system. a diagnostic processing unit that performs a primary diagnosis of normality or abnormality of each manhole pump based on which side of the boundary threshold value is present;
with
The diagnosis processing unit multiplies and adds a predetermined abnormality reference value by a weighting factor based on the distance between each characteristic value point and the boundary threshold each time a primary diagnosis is made that each characteristic value point is abnormal, A diagnosis device for manhole pumps that makes a final diagnosis of normality or abnormality of each manhole pump based on a cumulative evaluation value obtained by subtracting a predetermined abnormality reference value every time each characteristic value point is primary diagnosed as normal. a diagnostic map in which the outside of the boundary threshold set in a two-dimensional coordinate system is segmented into a plurality of regions, each segment being associated with one of the causes of anomalies;
17. The diagnosis device for a manhole pump according to claim 15, wherein said diagnosis processing unit diagnoses the cause of abnormality based on the area where each characteristic value point is plotted. 18. The manhole pump diagnostic device according to claim 15, wherein said diagnostic processing unit comprises a machine learning device for automatically generating said boundary threshold based on a pair of characteristic values input as learning data.

Images