JP7498321B2 - Manhole pump diagnostic method and manhole pump diagnostic device - Google Patents

Description

The present invention relates to a diagnostic method and device for two manhole pumps that are installed in a manhole and are repeatedly started and stopped.

The manhole pump facility is equipped with a storage section that stores wastewater flowing in from an inlet pipe, multiple pumps that drain the wastewater stored in the storage section into an outlet pipe, a water level gauge that measures the level of the wastewater stored in the storage section, and a control panel equipped with a control device that executes wastewater transport control by starting one of the pumps to drain the wastewater into the outlet pipe when the water level measured by the water level gauge reaches the pump start water level and stopping the pump when the water level reaches the pump stop water level.

This type of manhole pump facility is usually equipped with two pumps, and the control system is configured to operate the pumps alternately each time sewage is transported.

Patent Document 1 proposes a pumping station monitoring system that includes a means for managing the cumulative inflow volume to be discharged by multiple pumps at a pumping station per given time period divided by the operating time of each pump within a given time period as the average drainage capacity of each pump as time-series data, a means for determining whether the average drainage capacity of each pump managed as time-series data has exceeded a preset drainage capacity range, and a means for issuing an alarm when the average drainage capacity of each of the multiple pumps exceeds the preset drainage capacity range.

Patent Document 2 discloses a control device for a submersible pump that includes a pressure control unit that operates an electromagnetic switch to drive the submersible pump when the stored water level detected by a water level sensor reaches a pump start water level, and an abnormality determination unit that determines the presence or absence of an abnormality based on the operating state of the electromagnetic switch that drives the electric motor, the detection state of a 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, and that determines that an overheating abnormality has occurred in the electric motor with auto-cut activated if no current is detected by the current sensor while the electromagnetic switch is operating and no drop in the stored water level is detected by the water level sensor.

JP 2001-34338 A JP 2010-236191 A

The control device installed in the conventional manhole pump equipment described above determined whether each pump was abnormal based on whether physical quantities such as the pump's drive current value, the pump's operating time from the start water level to the stop water level, and the pump's temperature exceeded predetermined thresholds. In order to measure physical quantities appropriate to the type of abnormality anticipated, it was necessary to perform measurement processing using various sensors, which was very cumbersome.

In addition, the threshold value for determining anomalies is also dependent on the environment of the manhole in which the pump is installed, making it difficult to set a uniform threshold value. For example, there is a bias in the frequency with which pumps are started and the length of time they are operated in areas with a high amount of water entering the area per unit time and areas with a low amount of water entering the area per unit time, making it difficult to make an accurate judgment when a fixed threshold value is used.

In particular, in a remote monitoring system that has a communication device in the control panel of each manhole pump facility, a server that manages the pump operation data transmitted from each communication device, and allows an administrator to access the server from a terminal they own to monitor the operation status, a very large number of physical quantities must be transmitted in order to individually determine various abnormalities in the pumps installed in each manhole pump facility, and while this increases the number of sensors and the volume of transmitted data, there is a problem in that it is difficult to set appropriate thresholds.

In view of the above-mentioned problems, the object of the present invention is to provide a method and device for diagnosing manhole pumps that can accurately diagnose abnormalities caused by various factors even with small physical quantities.

In order to achieve the above-mentioned object, a first characteristic configuration of a manhole pump diagnostic method according to the present invention is a method for diagnosing two manhole pumps that are installed in a manhole to be diagnosed and that repeatedly start and stop, comprising: a sampling step of sampling the operating time per start of each manhole pump within a specified diagnosis period and calculating the respective average operating times 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 on each characteristic value for a specified period immediately preceding the diagnosis period, which includes the diagnosis period; and a diagnosis step of plotting the pair of normalized characteristic values in 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 performing a primary diagnosis of the 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 is on; and 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, and each region is associated with one of the causes of abnormality, and the diagnostic step diagnoses the cause of the abnormality based on the region in which each characteristic value point is plotted on the diagnostic map.

The normalization step normalizes the characteristic values, which are composed of the average operation times of each manhole pump calculated from the operation times per start of each manhole pump sampled in a time series manner in the sampling step, so that a pair of characteristic values, which are free from the influence of, for example, the inherent mechanical difference of the manhole pump and the influence of the installation environment, can be extracted as feature quantities, and the diagnosis step plots the characteristic value points representing the pair of characteristic values in a two-dimensional coordinate system, and a primary diagnosis is appropriately made as to whether the manhole pump is normal or abnormal using a preset boundary threshold as an index. The cause of the abnormality can be estimated depending on which region of the diagnosis map, which is divided outside the boundary threshold indicating the normal region, the characteristic value points represented by the normalized pair of characteristic values are located in. At this time, the normalization process is performed on the pair of characteristic values based on statistical data obtained from each characteristic value in the most recent predetermined period, so that the influence due to the passage of time, such as seasonal fluctuations, is eliminated, and a highly reliable diagnosis can be made.

The second characteristic configuration of the same is a diagnostic method for two manhole pumps that are installed in a manhole to be diagnosed and that repeatedly start and stop, comprising: a sampling step of sampling the operating time per start of each manhole pump within a specified period to be diagnosed, calculating the average operating time of each of the manhole pumps, and setting the average operating time of one of the pumps and the ratio of the average operating time of the one pump to the average operating time of the other pump 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 on each characteristic value of a specified period immediately preceding the period to be diagnosed, and a diagnostic step of plotting the pair of normalized characteristic values in a two-dimensional coordinate system with one of the pair of characteristic values as the x-axis and the other as the y-axis, and performing a primary diagnosis of whether each manhole pump is normal or abnormal based on which side of a boundary threshold value previously set in the two-dimensional coordinate system the plotted characteristic value point is on; and a diagnostic map in which the outside of the boundary threshold value set in the two-dimensional coordinate system is divided into a plurality of regions, and each region is associated with one of the causes of abnormality, and the diagnostic step diagnoses the cause of the abnormality based on the region in which each characteristic value point is plotted on the diagnostic map.

Among the average operation times calculated from the operation times per start of each manhole pump sampled in a time series manner in the sampling step, one average operation time and the ratio of the one average operation time to the other average operation time are set as a pair of characteristic values, and the pair of characteristic values are normalized in the normalization step, so that the pair of characteristic values, which are free from the influence of, for example, the inherent machine difference of the manhole pump and the influence of the installation environment, can be extracted as feature quantities, and the characteristic value points representing the pair of characteristic values are plotted in a two-dimensional coordinate system in the diagnosis step, and whether the manhole pump is normal or abnormal is appropriately diagnosed using a preset boundary threshold as an index. The cause of the abnormality can be estimated depending on which region of the diagnosis map, which is divided outside the boundary threshold indicating the normal region, the characteristic value point represented by the normalized pair of characteristic values is located in. At this time, the normalization process is performed on the pair of characteristic values based on statistical data obtained from each characteristic value in the most recent predetermined period, so that the influence due to the passage of time, such as seasonal fluctuations, is eliminated, and a highly reliable diagnosis can be made.

The third characteristic configuration, in addition to the first or second characteristic configuration described above , is that the diagnosis step automatically generates the boundary threshold value by a machine learning device based on the characteristic values input as learning data.

This eliminates the need for time-consuming preparations such as preparing training data that distinguishes between normal and abnormal conditions in advance and conducting machine learning. Instead, when multiple pairs of characteristic values when a manhole pump is operating properly are input into the machine learning device, a boundary threshold that distinguishes between normal and abnormal conditions 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 that are installed in a manhole to be diagnosed and that repeatedly start and stop, the diagnostic device comprising: a normalization processing unit that normalizes a pair of characteristic values constituted by each average operating time calculated from the operating time per start of each manhole pump sampled within a specified diagnostic period, based on statistical data calculated based on each characteristic value for a specified period immediately preceding the diagnostic period; and a diagnostic processing unit that plots the pair of normalized characteristic values in 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 performs a primary diagnosis of the normality or abnormality of each manhole pump based on on which side of a boundary threshold preset in the two-dimensional coordinate system the plotted characteristic value point is located, and the diagnostic processing unit has 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 is associated with one of the causes of abnormality, and the diagnostic processing unit diagnoses the cause of the abnormality based on the region in which each characteristic value point is plotted on the diagnostic map.

The second characteristic configuration of the same is a diagnostic device for two manhole pumps that are installed in a manhole to be diagnosed and that repeatedly start and stop, the diagnostic device comprising: a normalization processing unit that normalizes a pair of characteristic values, each composed of one average operating time and the ratio of the one average operating time to the other average operating time, among the average operating times calculated from the operating times per start of each manhole pump sampled within a specified diagnostic period, based on statistical data calculated based on each characteristic value for a specified period immediately preceding the diagnostic period; and a diagnostic processing unit that plots the pair of normalized characteristic values 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 performs a primary diagnosis of the normality or abnormality of each manhole pump based on which side of a boundary threshold value preset in the two-dimensional coordinate system the plotted characteristic value point is on. The diagnostic device also comprises a diagnostic map in which the outside of the boundary threshold value set in the two-dimensional coordinate system is divided into a plurality of regions, each region is associated with one of the causes of abnormality, and the cause of the abnormality is diagnosed based on the region in which each characteristic value point is plotted on the diagnostic map.

The third characteristic configuration is that, in addition to the first or second characteristic configuration described above, the diagnostic processing unit is equipped with a machine learning device that automatically generates the boundary threshold value based on a pair of characteristic values input as learning data.

As explained above, the present invention provides a method and device for diagnosing manhole pumps that can accurately diagnose abnormalities caused by various factors even with a small number of physical quantities.

Illustration of a manhole pump Illustration of manhole pump abnormality diagnosis device An explanatory diagram showing the procedure for diagnosing an abnormality in a manhole pump FIG. 1A is an explanatory diagram of measurement data, and FIG. 1B is an enlarged explanatory diagram of a main part of the measurement data. Normalization process diagram Illustration of primary diagnosis Cumulative evaluation score and final diagnosis Diagram of diagnostic map

The following describes the manhole pump diagnostic method and diagnostic device according to the present invention.

Figure 1 shows a manhole pump device 10. The manhole pump device 10 includes a manhole 12 as a water storage section for storing wastewater flowing in from an upstream wastewater inlet pipe 11, two pumps PA and PB for pumping the wastewater stored in the manhole 12 to a downstream wastewater outlet pipe 13, and water level gauges 18 and 19 for measuring the water level of the wastewater stored in the manhole 12.

The first pump PA's discharge bend 15a is flange-connected to the first lift pipe 15b, the first bend 15c, and the first horizontal pipe 15d, and the first horizontal pipe 15d is flange-connected to the sewage outflow pipe 13 via the header pipe 13a. A check valve 15e is provided between the first lift pipe 15b and the first bend 15c.

The second pump PB has a discharge bend 17a to which a second lift pipe 17b and a second bend 17c are flange-connected, and the second bend 17c is flange-connected to the wastewater outflow pipe 13 via the header pipe 13a. A check valve 17e is provided between the second lift pipe 17b and the second bend 17c.

A water level gauge 18 of the plunge pressure type or air bubble type is installed at the bottom of the manhole 12. The water level gauge 18 continuously detects the water level of the wastewater stored in the manhole 12. In addition, a float type water level gauge 19 is installed as a backup water level gauge to detect the abnormally high water level HHWL.

A control panel device 200 is installed near the manhole 12, and includes a control panel 20 including a control unit 21 that controls the pumps PA and PB to perform sewage transport control, which pressure-feeds the sewage that has accumulated in the manhole 12 to the sewage outflow pipe 13.

The control panel 20 is provided with a control unit 21, a memory unit 22, and a communication unit 24. The memory 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 the various information stored in the memory unit 22 to a 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 the communication medium 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. Furthermore, the mobile communication terminal 30 owned by the manager of the manhole pump device 10 and the monitoring device 40 are configured to be able to connect to the Internet via the wireless communication medium.

The control panel 20 and each pump PA, PB are connected by AC power supply lines L1, L2, and the control panel 20 and water level gauges 18, 19 are connected by signal lines S.

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

When the control unit 21 detects that the water level has again reached the pump start water level HWL, it controls the 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 stops the power supply and stops the pump PB. In other words, the control unit 21 controls the operation of the pumps PA and PB alternately.

Furthermore, if the control unit 21 cannot detect the pump start water level HWL due to a malfunction of the water level gauge 18, or if it detects that a large amount of rainwater that exceeds the drainage capacity of a single pump has flowed into the manhole 12 due to heavy rain and reached the abnormally high water level HHWL as measured by the water level gauge 19, it will operate the two pumps PA and PB simultaneously.

The control unit 21 samples the water level information detected by the water level gauges 18 and 19 in chronological order, for example at one-minute intervals, and stores the information in the memory unit 22. The control unit 21 also stores in the memory unit 22 chronological operation information, such as the start and stop times of each pump PA and PB, and the operating time from start to stop.

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

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

The diagnosis unit 44 includes a normalization processing unit 46 and a diagnosis processing unit 48. The normalization processing unit 46 is configured to normalize a pair of characteristic values obtained from the operating times of a predetermined period of time that indicate the characteristics of each pump PA, PB sampled in a time series manner. The average operating times 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 also be calculated as a pair of characteristic values.

The diagnostic processing unit 48 is configured with a machine learning device that automatically generates a boundary threshold for diagnosing whether a pump is normal or abnormal based on multiple past data indicating a pair of characteristic values input as learning data, and the machine learning device is configured to plot the normalized pair of characteristic values in 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 to perform a primary diagnosis of whether each manhole pump is normal or abnormal based on on which side of a boundary threshold preset in the two-dimensional coordinate system the plotted characteristic value point is located. The machine learning device is configured as a computer that executes a one-class support vector machine algorithm.

Furthermore, the diagnostic processing unit 48 is configured to multiply a predetermined abnormality reference value by a weighting coefficient based on the distance between the characteristic value point and the boundary threshold value and add the result each time the characteristic value point is diagnosed as abnormal in the primary diagnosis, and to make a final diagnosis of whether the manhole pump is normal or abnormal based on a cumulative evaluation value obtained by subtracting a predetermined normal return evaluation value each time the characteristic value point is diagnosed as normal in the primary diagnosis.

The area outside the boundary threshold set in the two-dimensional coordinate system is divided into a number of regions, and a diagnostic map is provided in which each region is associated with one of the causes of anomaly, and the diagnostic processing unit 48 is configured to diagnose the cause of anomaly based on the region in which each characteristic value point is plotted.

Figure 3 shows a flow of a series of diagnostic processes executed by the monitoring device 40. After receiving one day's worth of measurement data from each manhole pump device 10 and storing it in the database DB (SA1), the operation time of each pump PA, PB is extracted as measurement data used for abnormality judgment for each pump of each manhole pump device 10, and the average operation time for each pump PA, PB is calculated by dividing the total operation time of the pump in one day by the number of operations (SA2). As a feature, the average operation time of each pump may be selected as a pair of characteristic values, or the average operation time of one pump and the ratio of the average operation time of one pump to the average operation time of the other pump may be selected as a pair of characteristic values. The statistics required for normalization processing, that is, the average value and variance value, are calculated from the average operation time within the most recent specified period stored in the database DB, and the feature value for the day to be judged is normalized (SA3).

The normalized features are input into a machine learning device and a primary judgment is made based on a set boundary threshold (SA5). If an abnormality is detected, the cumulative evaluation value is increased taking into account the degree of abnormality (SA6). If a normality is detected, the cumulative evaluation value is decreased (SA7).

This process is repeated daily to determine whether the calculated cumulative evaluation value exceeds a preset cumulative abnormality threshold value (SA8). If the cumulative abnormality threshold value is exceeded, the cause of the abnormality is identified based on a diagnostic map that indicates a correlation with the cause of the abnormality (SA9), and an alarm indicating an abnormal state along with the cause of the abnormality is sent to a mobile terminal or the like owned by the manager (SA10). The alarm notification is sent as an e-mail via a mailer provided in the communication unit 41.

The diagnosis unit 44 will be described in detail below.
4A shows operation data for the manhole pump device for 24 hours from 0:00 a.m. to 0:00 the next day. From the top to bottom, the data shows fluctuations in water level, operation timing and operation time of pumps PA and PB, current value of pump PA, and current value of pump PB.

Figure 4(b) is an enlarged view to make it easier to understand the relationship between the fluctuations in water level shown in Figure 4(a) and the operation timing and operation time of pumps PA and PB. Pump PA is started when the water level in the manhole reaches HWL and is stopped when the water level drops to LWL. Pump PB is started when the water level in the manhole next reaches HWL and is stopped when the water level drops to LWL. One of the pumps is running until the water level drops from HWL to LWL. The pump operation time will be longer if the pump's transport rate is reduced or if there is a large amount of sewage flowing into the manhole.

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

The data processing unit 42 extracts from such data the "total pump operation time" and the "number of operations" of each pump PA, PB when they are started, and calculates the average operation time of each pump as a pair of characteristic values based on the average daily operation time obtained by dividing the "total pump operation time" by the "number of operations", or calculates the average operation time of one pump and the ratio of the average operation time of one pump to the average operation time of the other pump as a pair of characteristic values, and passes them to the normalization processing unit 46.

As shown in FIG. 5, the normalization processing unit 46 calculates the mean value μ and variance σ ² for normalizing the data using the feature values accumulated in the database DB during the most recent past three months as a population, and normalizes the average driving time, which is the feature value, for the feature value x using the formula (x-μ)/σ.

Although not limited to the most recent three months, the statistical data (average value, variance) required for normalization processing is preferably calculated based on a group of measurement data from a specified period immediately preceding the time the normalization processing is performed, which eliminates the effects of time-related factors such as seasonal fluctuations, enabling more reliable diagnosis.

When a pair of characteristic values consisting of the feature quantity "average operating time of each pump" normalized by the normalization processing unit 46 or a pair of characteristic values consisting of "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" is input to the diagnosis processing unit 48, the normalized pair of characteristic values are plotted in a two-dimensional coordinate system with one of the pair of characteristic values on the x-axis and the other on the y-axis, and a primary diagnosis of the normality or abnormality of each manhole pump is made based on which side of a boundary threshold preset in the two-dimensional coordinate system the plotted characteristic value point is on.

By normalizing the characteristic values calculated based on the measurement values sampled in a time series in the sampling step in the normalization step, it is possible to extract the characteristic values as feature quantities, eliminating the effects of, for example, mechanical differences in the manhole pump and the effects of the installation environment, and in the diagnosis step, these feature quantities, i.e., points representing the two types of measurement data groups, are plotted as multiple points in a time series in a two-dimensional coordinate system, and an appropriate initial diagnosis is made as to whether the manhole pump device is normal or abnormal, using a preset boundary threshold as an index.

Figure 6 shows how a nearly circular closed curve (shown by a thick line) with the origin (average value of each value) of a two-dimensional coordinate system, with the vertical axis (y-axis) representing the ratio of the average operating times of each pump (T(PA)/T(PB)) and the horizontal axis (x-axis) representing the average operating time of pump PB (T(PB)), is used as the boundary threshold, and how plotted characteristic value points are judged to be normal when they are inside the boundary threshold, and abnormal when they are outside the boundary threshold. Note that characteristic value points may also be plotted in a two-dimensional coordinate system with the vertical axis (y-axis) representing the average operating time of one pump and the horizontal axis (x-axis) representing the average operating time of the other pump PB.

The diagnostic processing unit 48 includes a machine learning device that automatically generates the above-mentioned boundary threshold value based on a group of measurement data input as learning data. The machine learning device can be a computer that executes algorithms such as a one-class support vector machine, a local outlier factor (LOF) method, an isolation forest (IF) method, or a robust covariance (RC) method.

By performing machine learning, a normal data space is generated in which normal measurement data (training data) is mapped into the mapping space (feature space) shown in Figure 6, that is, the internal space of the boundary threshold. The example in Figure 6 shows the results of learning one year's worth of pairs of characteristic values obtained from 100 manhole pump devices with two pumps installed as learning data.

Each time the diagnostic processing unit 48 makes a primary diagnosis that a characteristic value point is abnormal, it multiplies a predetermined abnormality reference value Vnb by a weighting coefficient W based on the distance between the position of each characteristic value point and the boundary threshold value based on the following formula, and adds the result, and each time each characteristic value point is diagnosed as normal in the primary diagnosis, it calculates a cumulative evaluation value V by subtracting a predetermined normal return evaluation value Vpb, and makes a final diagnosis of the normality or abnormality of the manhole pump apparatus based on the cumulative evaluation value. The distance between the position of the characteristic value point and the boundary threshold value refers to the length of a normal line from the boundary threshold value that passes through the characteristic value point.
V=Vnb×W−Vpb
In this embodiment, the settings are Vnb=1 and Vnb<Vpb<Wmax×Vnb.

Some abnormalities are minor, but are later diagnosed as normal even if they are diagnosed as abnormal in the primary diagnosis, while other abnormalities continue to be diagnosed as abnormal and eventually lead to a serious breakdown. Even in such cases, a cumulative evaluation value is calculated by adding a value obtained by multiplying a predetermined abnormality reference value by a weighting coefficient based on the distance between the characteristic value point and the boundary threshold each time an abnormality is diagnosed in the primary diagnosis, and subtracting a predetermined normal return evaluation value each time a normality is diagnosed, and a final diagnosis of whether the mechanical equipment is normal or abnormal is made based on this cumulative evaluation value, making it possible to make a diagnosis that takes into account the degree of abnormality, such as an abnormality that will require maintenance in the near future.

Figure 7 shows the evolution of the cumulative evaluation value. A primary evaluation is performed on the cumulative evaluation value for each specified period during which the characteristic value points are plotted, and if an abnormality is determined, the value of Vnb x W is added to the initial value of 0, and if a normality is determined, the value of Vpb is subtracted. When the cumulative evaluation value exceeds a specified threshold, in this example "10", a final abnormality determination is made, and a message to that effect is sent to the administrator's mobile device or the like. Note that the primary and final determinations continue to be performed even after an abnormality has been determined.

Figure 8 shows an example of a diagnostic map. The area outside the boundary threshold shown in the feature space shown in Figure 6 is divided into eight regions, and each region is associated with one of the causes of anomaly. The diagnostic processing unit 48 diagnoses the cause of anomaly based on the region in which each feature data is plotted.

For example, in the example of Figure 8, when characteristic value points are plotted in region 2, only pump PA, which has been operating for a long time, is diagnosed as abnormal; in region 4, there is an abnormality in the external environment, such as an abnormality in the water level gauge; in region 5, there is an abnormality in both pumps, which have been operating for a long time, an increase in the amount of wastewater inflow, and an abnormality in the external environment, such as a blockage at the junction of the discharge pipe; and in region 8, only pump PB, which 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. However, the pair of characteristic values is not limited to these data, and can be set appropriately to the operating time per operation of each pump, the ratio of the operating time per operation of one pump to the operating time per operation of the other pump, the current value during operation of each pump shown in Figure 4 (a), the average current value, or the ratio of the average current values of both pumps.

As described above, the manhole pump diagnostic method according to the present invention is a method for diagnosing two manhole pumps that are installed in a manhole and are repeatedly started and stopped, and includes a sampling step for sampling the operating time per start of each manhole pump within a predetermined period and calculating the respective average operating times as a pair of characteristic values, a normalization step for normalizing the pair of characteristic values calculated in the sampling step, and a diagnostic step for plotting the pair of normalized characteristic values in a two-dimensional coordinate system with one of the pair of characteristic values on the x-axis and the other on the y-axis, and performing a primary diagnosis of the normality or abnormality of each manhole pump based on on which side of a boundary threshold preset in the two-dimensional coordinate system the plotted characteristic value point is located.

The method also includes a sampling step in which the operating time per start of each manhole pump within a specified 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 are taken as a pair of characteristic values; a normalization step in which the pair of characteristic values calculated in the sampling step are normalized; and a diagnosis step in which the normalized pair of characteristic values are plotted in a two-dimensional coordinate system with one of the pair of characteristic values on the x-axis and the other on the y-axis, and a primary diagnosis of the normality or abnormality of each manhole pump is made based on which side of a boundary threshold preset in the two-dimensional coordinate system the plotted characteristic value point is on.

The statistical data required for the normalization process used in the normalization step is configured to be calculated based on each characteristic value for a specified period immediately preceding the time the normalization process is performed.

The diagnosis step is configured to multiply a predetermined abnormality reference value by a weighting coefficient based on the distance between the characteristic value point and the boundary threshold value and add the result each time the characteristic value point is initially diagnosed as abnormal, and to make a final diagnosis of whether the manhole pump is normal or abnormal based on an accumulated evaluation value obtained by subtracting a predetermined normal return evaluation value each time the characteristic value point is diagnosed as normal in the diagnosis step.

The area outside the boundary threshold set in the two-dimensional coordinate system is divided into a plurality of regions, and each region is provided with a diagnostic map associated with one of the causes of anomaly, and the diagnostic step is configured to diagnose the cause of anomaly based on the region in which each characteristic value point is plotted.

In the diagnosis step, it is preferable that a boundary threshold be automatically generated by a machine learning device based on characteristic values input as learning data.

In the above-described embodiment, the entire diagnostic step is performed by the machine learning device, but only the generation of the boundary threshold may be performed by the machine learning device, or the diagnostic step may be performed using a default boundary threshold without using the machine learning device.

The above-mentioned embodiments are merely examples of the present invention, and the technical scope of the present invention is not limited by the above description. It goes without saying that the specific configuration of each part, including the pump and water level gauge, and the threshold values set for abnormality determination can be appropriately modified and designed within the scope of the effects of the present invention.

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

Claims (6)

A method for diagnosing two manhole pumps that are installed in a manhole to be diagnosed and that repeatedly start and stop, comprising the steps of:
A sampling step of sampling the operation time per start of each manhole pump within a predetermined diagnosis period and calculating the respective average operation times 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 on each characteristic value for a most recent predetermined period including the diagnosis target period ;
a diagnostic step of plotting the pair of normalized characteristic values on a two-dimensional coordinate system with one of the pair of characteristic values as the x-axis and the other as the y-axis, and performing a primary diagnosis of whether each manhole pump is normal or abnormal based on whether the plotted characteristic value point is on either side of a boundary threshold preset in the two-dimensional coordinate system;
In addition to providing
a diagnostic map in which an area outside the boundary threshold set in the two-dimensional coordinate system is divided into a plurality of regions, and each of the regions is associated with one of the causes of an abnormality;
The diagnosis method for a manhole pump includes diagnosing a cause of an abnormality based on an area in which each characteristic value point is plotted on the diagnostic map. A method for diagnosing two manhole pumps that are installed in a manhole to be diagnosed and that repeatedly start and stop, comprising the steps of:
a sampling step of sampling the operation time per start of each manhole pump within a predetermined diagnosis period, calculating the average operation time of each, and setting one average operation time and a ratio of the one average operation time to the other average operation time 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 on each characteristic value for a most recent predetermined period including the diagnosis target period ;
a diagnostic step of plotting the pair of normalized characteristic values on a two-dimensional coordinate system with one of the pair of characteristic values as the x-axis and the other as the y-axis, and performing a primary diagnosis of whether each manhole pump is normal or abnormal based on on which side of a boundary threshold preset in the two-dimensional coordinate system the plotted characteristic value point is located;
In addition to providing
a diagnostic map in which an area outside the boundary threshold set in the two-dimensional coordinate system is divided into a plurality of regions, and each of the regions is associated with one of the causes of an abnormality;
The diagnosis method for a manhole pump includes diagnosing a cause of an abnormality based on an area in which each characteristic value point is plotted on the diagnostic map. The manhole pump diagnosis method according to claim 1 or 2 , wherein the diagnosis step automatically generates the boundary threshold value by a machine learning device based on the characteristic values input as learning data. A diagnostic device for two manhole pumps that are installed in a manhole to be diagnosed and that repeatedly start and stop,
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 diagnosis period , based on statistical data calculated based on each characteristic value for a most recent predetermined period including the diagnosis period ;
a diagnostic processing unit that plots the pair of normalized characteristic values on a two-dimensional coordinate system with one of the pair of characteristic values as the x-axis and the other as the y-axis, and performs a primary diagnosis of whether each manhole pump is normal or abnormal based on on which side of a boundary threshold preset in the two-dimensional coordinate system the plotted characteristic value point is located;
In addition to providing
The diagnostic processing unit is provided with 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, with each region being associated with one of the causes of anomaly, and the manhole pump diagnostic device diagnoses the cause of anomaly based on the region in which each characteristic value point is plotted on the diagnostic map. A diagnostic device for two manhole pumps that are installed in a manhole to be diagnosed and that repeatedly start and stop,
a normalization processing unit that normalizes a pair of characteristic values, each of which is composed of one average operation time and a ratio of the one average operation time to the other average operation time, among the respective average operation times calculated from the operation time per start of each manhole pump sampled within a predetermined diagnosis period, based on statistical data calculated based on each characteristic value for a most recent predetermined period including the diagnosis period ;
a diagnostic processing unit that plots the pair of normalized characteristic values on a two-dimensional coordinate system with one of the pair of characteristic values as the x-axis and the other as the y-axis, and performs a primary diagnosis of whether each manhole pump is normal or abnormal based on on which side of a boundary threshold value preset in the two-dimensional coordinate system the plotted characteristic value point is located;
In addition to providing
The manhole pump diagnostic device includes 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 anomaly, and the device diagnoses the cause of anomaly based on the region in which each characteristic value point is plotted on the diagnostic map. The manhole pump diagnostic device according to claim 4 or 5 , wherein the diagnostic processing unit includes a machine learning device that automatically generates the boundary threshold value based on a pair of characteristic values input as learning data.

Images