Manhole pump diagnostic method and manhole pump diagnostic device

Abstract

To provide a method for diagnosing manhole pumps by which an abnormality can be accurately diagnosed even when a ratio of operation times for each manhole pump is selected as a diagnostic index.SOLUTION: A manhole pump diagnostic method includes: a diagnostic index calculation step of calculating a diagnostic index from operation information of manhole pumps collected during a diagnosis target period; and a diagnosis step of diagnosing conditions of the manhole pumps during the diagnosis target period based on the diagnostic index. At least the diagnostic index includes a ratio of the number of operation times of one manhole pump to the number of operation times of the other manhole pump during the diagnosis target period, and if a difference between the number of operation times of the one manhole pump and the number of operation times of the other manhole pump during the diagnosis period before calculating the ratio of the number of operation times is 1, the diagnostic index calculation step adds 1 to the number of operation times of a manhole pump with a smaller number of operation times or subtracts 1 from the number of operation times of a manhole pump with a larger number of operation times.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to a diagnostic method and diagnostic device for two manhole pumps that are installed in a manhole and are repeatedly started and stopped. [Background technology]

[0002] The manhole pump equipment includes a storage section that stores sewage that flows in from the inlet pipe, multiple pumps that drain the sewage stored in the storage section into the outlet pipe, a water level gauge that measures the level of the sewage stored in the storage section, and a control panel equipped with a control device that performs sewage transport control by starting one of the pumps to drain the sewage into the outlet pipe when the water level measured by the water level gauge reaches the pump start level, and stopping the pump when the water level reaches the pump stop level.

[0003] Such manhole pumping equipment is typically equipped with two pumps, and the control device is configured to operate the pumps alternately each time sewage is transported.

[0004] 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 specified time period divided by the operating time of each pump within the specified 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 predetermined drainage capacity range, and a means for issuing an alarm when the average drainage capacity of each of the multiple pumps exceeds the set drainage capacity range.

[0005] Patent document 2 discloses a control device for a submersible pump that includes a pressure control unit that activates an electromagnetic contactor to drive the submersible pump when the stored water level detected by a water level sensor reaches the pump startup level, and an abnormality determination unit that determines whether or not there is an abnormality based on the operating state of the electromagnetic contactor 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 contactor, and the stored water level, and the abnormality determination unit determines that there is an overheating abnormality in the electric motor with auto-cut activated if no current is detected by the current sensor while the electromagnetic contactor is operating and no drop in the stored water level is detected by the water level sensor.

[0006] The control device provided in the conventional manhole pump facility described above determines whether each pump is 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 exceed predetermined thresholds. Furthermore, it is necessary to perform measurement processing using various sensors to measure physical quantities appropriate for the type of abnormality anticipated, which creates a problem of being extremely cumbersome.

[0007] Furthermore, it was difficult to set a uniform threshold for determining an abnormality because it depended on the environment of the manhole the pump was installed in. For example, in areas where the amount of water entering per unit time was high and areas where it was low, there was a bias in the frequency of pump startup and operating time, making it difficult to make an accurate judgment if a fixed threshold was used.

[0008] In particular, in remote monitoring systems that have a communication device in the control panel of each manhole pump facility, a server that manages the pump operation data sent from each communication device, and allow administrators to access the server from their own terminals to monitor the operation status, a large number of physical quantities need to 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.

[0009] Therefore, Patent Document 3 proposes a manhole pump diagnostic method that can accurately diagnose abnormalities due to various causes even with a small physical quantity. This manhole pump diagnostic method is a method for diagnosing two manhole pumps installed in a manhole that repeatedly start and stop, and includes the following steps: a sampling step of sampling the operating time per start of each manhole pump within a predetermined diagnostic 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; and 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 ​​on the x-axis and the other on the y-axis, and using a machine learning device to perform 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 located. [Prior art documents] [Patent documents]

[0010] [Patent Document 1] Japanese Patent Application Laid-Open No. 2001-34338 [Patent Document 2] Japanese Patent Application Laid-Open No. 2010-236191 [Patent Document 3] Japanese Patent Publication No. 2020-107073 Summary of the Invention [Problem to be solved by the invention]

[0011] The manhole pump diagnostic method disclosed in Patent Document 3 is configured to plot normalized values ​​of the average operating time of each manhole pump during a specified diagnostic period as a pair of characteristic values ​​on a two-dimensional coordinate system in which boundary thresholds indicating a normal range are determined in advance by a machine learning device, and diagnose that the pair of characteristic values ​​are normal when they fall within the boundary thresholds, and that they are abnormal when they deviate from the boundary thresholds.

[0012] The boundary threshold determined by the machine learning device is a value obtained by learning the normal characteristic values ​​of many manhole pumps installed in various environments as training data.By normalizing the characteristic values ​​of the manhole pump to be diagnosed based on statistical data that is based only on the past characteristic values ​​of the manhole pump, it is possible to achieve appropriate diagnosis using a small number of characteristic values ​​while reducing the impact of differences in the installation environment, etc.

[0013] However, when the ratio between the number of times one manhole pump is operated and the number of times the other manhole pump is operated during the period to be diagnosed is used as the characteristic value to be applied to such a manhole pump diagnosis method, if the number of times the manhole pump is operated during the period to be diagnosed is small, there is a risk that large variations will occur in the characteristic value, leading to an erroneous diagnosis.

[0014] Under normal conditions, the two manhole pumps are operated alternately, so the ratio of the number of times each manhole pump is operated converges to 1 as the number of times each manhole pump is operated during the period under diagnosis increases. However, if the number of times each manhole pump is operated is small, the ratio of the number of times each manhole pump is operated may be a value that is significantly deviated from 1.

[0015] For example, if the number of times each manhole pump was operated during the period under diagnosis was equal, the ratio of the number of times it was operated would be 1; whereas if one manhole pump was operated 1 time and the other 2 times during the period under diagnosis, the ratio of the number of times it was operated would be 0.5; and in the opposite case, the ratio of the number of times it was operated would be 2.

[0016] In view of the above-mentioned problems, an object of the present invention is to provide a manhole pump diagnostic method and diagnostic device that can accurately diagnose abnormalities even when the ratio of the number of times each manhole pump is operated is selected as a diagnostic index. [Means for solving the problem]

[0017] 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 manhole pump diagnostic method for diagnosing the status of two manhole pumps installed in a manhole and repeatedly starting and stopping, the method comprising: a diagnostic index calculation step of calculating a diagnostic index from operation information of the manhole pumps collected during a period to be diagnosed; and a diagnostic step of diagnosing the status of the manhole pumps during the period to be diagnosed based on the diagnostic index calculated in the diagnostic index calculation step, wherein the diagnostic index includes at least a ratio between the number of times one manhole pump is operated and the number of times the other manhole pump is operated during the period to be diagnosed; The diagnostic index calculation step is configured such that, before calculating the ratio of the number of times of operation, if the difference between the number of times one manhole pump is operated and the number of times the other manhole pump is operated during the diagnostic period is 1, 1 is added to the number of times the manhole pump is operated less frequently, or 1 is subtracted from the number of times the manhole pump is operated more frequently.

[0018] When the ratio between the number of times one manhole pump is operated and the number of times the other manhole pump is operated during the period to be diagnosed is used as the diagnostic index calculated in the diagnostic index calculation step, if the difference between the number of times one manhole pump is operated and the number of times the other manhole pump is operated is 1, it is assumed that both manhole pumps are being operated alternately appropriately, and by adding 1 to the number of times the manhole pump is operated less frequently or subtracting 1 from the number of times the manhole pump is operated more frequently, the ratio of the number of times the pump is operated is corrected to 1, thereby avoiding erroneous diagnosis even when the number of times the manhole pumps are operated during the period to be diagnosed is low.

[0019] In the second characteristic configuration, in addition to the first characteristic configuration described above, the diagnostic index further includes a ratio between the operation time of one manhole pump and the operation time of the other manhole pump during the diagnostic target period, and when adding 1 to the operation count of the manhole pump with a low operation count or subtracting 1 from the operation count of the manhole pump with a high operation count, the diagnostic index calculation step uses an average operation time per start during the diagnostic target period as the operation time per start of the manhole pump corresponding to the addition or subtraction. and add or subtract the average value The point is to

[0020] When using the ratio of the operating time of each manhole pump in addition to the ratio of the number of operations as a diagnostic index, it is necessary to maintain a balance with the corrected number of operations. To do this, it is necessary to increase or decrease the operating time of the manhole pump whose number of operations has been corrected, and in this case, by using the average value of the operating time per start during the period under diagnosis as the correction value for the operating time per start, an appropriate diagnosis can be performed.

[0021] The third characteristic configuration is, in addition to the first or second characteristic configuration described above, in that the diagnostic index calculation step includes a normalization step of normalizing the diagnostic index for the diagnostic period based on statistical data calculated only from each diagnostic index calculated for a predetermined period immediately preceding the diagnostic period, and the diagnosis step is configured to plot the normalized diagnostic index in a predetermined coordinate system and diagnose the normality or abnormality of the manhole pump based on which side of a boundary threshold preset in the coordinate system the plotted diagnostic index point is on, and the boundary threshold is automatically generated by a machine learning device that learns using as training data only diagnostic indexes in normal operating states obtained from a plurality of manhole pumps installed in a plurality of manholes including the manhole pump installed in the manhole to be diagnosed, and indicates the boundary of the coordinate system that becomes a feature space within which normal diagnostic indexes are included.

[0022] For example, even if the value of the diagnostic index varies greatly depending on the manhole installation environment, such as between areas with high and low inflow water volumes, the influence of external factors such as the installation environment can be eliminated by normalizing the diagnostic index for the period to be diagnosed based on statistical data calculated only from individual diagnostic indexes calculated for the most recent specified period including the period to be diagnosed. Furthermore, by plotting the normalized diagnostic index on a specified coordinate system and adopting a boundary threshold for diagnosing normality or abnormality through machine learning using as training data only diagnostic indexes during normal operation obtained from manhole pumps installed in multiple manholes with different installation environments, appropriate diagnosis that is not affected by the installation environment can be performed without the need to take the time to prepare diagnostic indexes for abnormalities in advance.

[0023] The fourth characteristic feature of the present invention is the above-mentioned or second In addition to the characteristic configuration of the above, the diagnostic index calculation step and the diagnosis step are configured to be repeated each time the diagnostic target period elapses, the diagnostic index calculation step calculates the diagnostic index only when the operating information of the manhole pump satisfies a predetermined condition, and the diagnosis step is configured to diagnose the condition of the manhole pump when the diagnostic index is calculated by the diagnostic index calculation step.

[0024] Each time a diagnostic period (set as appropriate, for example, 24 hours) elapses, a diagnostic index is calculated in a diagnostic index calculation step from the operating information collected during that period, and a series of operations is repeated to diagnose the condition of the manhole pump during the diagnostic period in a diagnostic step. However, if a diagnosis is made in an unsteady state, such as when one of the manhole pumps is set to operate alone for maintenance, or when there is no inflow water and the manhole pump is not operating, a misdiagnosis may occur. Even in such cases, if a predetermined condition is set for the collected operating information of the manhole pump and the system is configured to calculate a diagnostic index only when the predetermined condition is met, it is possible to avoid inadvertent misdiagnosis.

[0025] A first characteristic configuration of the manhole pump diagnostic device according to the present invention is a manhole pump diagnostic device that diagnoses the condition of two manhole pumps that are installed in a manhole and that repeatedly start and stop, and that includes a diagnostic index calculation processing unit that calculates a diagnostic index from operation information of the manhole pumps collected during a period to be diagnosed, and a diagnostic processing unit that diagnoses the condition of the manhole pumps during the period to be diagnosed based on the diagnostic index calculated by the diagnostic index calculation processing unit, wherein the diagnostic index includes at least a ratio between the number of times one manhole pump is operated and the number of times the other manhole pump is operated during the period to be diagnosed, and the diagnostic index calculation processing unit is configured, before calculating the ratio of the number of times the one manhole pump is operated and the other manhole pump, to add 1 to the number of times the manhole pump is operated less frequently or subtract 1 from the number of times the manhole pump is operated more frequently if the difference between the number of times the one manhole pump is operated and the other manhole pump during the period to be diagnosed is 1.

[0026] In the second characteristic configuration, in addition to the first characteristic configuration described above, the diagnostic index further includes a ratio between the operation time of one manhole pump and the operation time of the other manhole pump during the diagnostic target period, and when adding 1 to the operation count of a manhole pump with a low operation count or subtracting 1 from the operation count of a manhole pump with a high operation count, the diagnostic index calculation processing unit uses an average value of the operation time per start during the diagnostic target period as the operation time per start of the manhole pump corresponding to the addition or subtraction. and add or subtract the average value The point is to

[0027] The third characteristic configuration is, in addition to the first or second characteristic configuration described above, that the diagnostic index calculation processing unit includes a normalization processing unit that normalizes the diagnostic index for the diagnostic period based on statistical data calculated only from each diagnostic index calculated for a predetermined period immediately preceding the diagnostic period, and the diagnostic processing unit is configured to plot the normalized diagnostic index in a predetermined coordinate system and diagnose the normality or abnormality of the manhole pump based on which side of a boundary threshold preset in the coordinate system the plotted diagnostic index point is on, and the boundary threshold is automatically generated by a machine learning device that learns using as training data only diagnostic indexes in normal operating states obtained from a plurality of manhole pumps installed in a plurality of manholes including the manhole pump installed in the manhole to be diagnosed, and indicates the boundary of the coordinate system that becomes a feature space within which normal diagnostic indexes are included.

[0028] The fourth characteristic configuration is the above-mentioned first or second In addition to the characteristic configuration described above, the diagnostic index calculation processing unit and the diagnostic processing unit are configured to be repeatedly executed each time the diagnostic target period elapses, the diagnostic index calculation processing unit calculates the diagnostic index only when the operating information of the manhole pump satisfies a predetermined condition, and the diagnostic processing unit is configured to diagnose the condition of the manhole pump when the diagnostic index is calculated by the diagnostic index calculation processing unit. [Effects of the Invention]

[0029] As described above, according to the present invention, it is possible to provide a manhole pump diagnostic method and diagnostic device that can accurately diagnose abnormalities even when the ratio of the number of times each manhole pump is operated is selected as a diagnostic index. [Brief explanation of the drawings]

[0030] [Figure 1] Manhole pump illustration [Figure 2] Diagram of manhole pump diagnostic device [Figure 3]An explanatory diagram showing the procedure for diagnosing a manhole pump [Figure 4] (a) is an explanatory diagram of the measurement data, and (b) is an enlarged explanatory diagram of the main part of the measurement data. [Figure 5] Normalization process diagram [Figure 6] (a) is an explanatory diagram of the primary diagnosis, and (b) is an explanatory diagram showing the values ​​of the diagnostic index before and after the correction process when the difference in the number of operations is 1. [Figure 7] Illustrative diagram of cumulative evaluation value and final diagnosis [Figure 8] Diagnostic map illustration DETAILED DESCRIPTION OF THE INVENTION

[0031] The manhole pump diagnostic method and diagnostic device according to the present invention will be described below.

[0032] Figure 1 shows a manhole pumping device 10. The manhole pumping device 10 includes a manhole 12 as a water storage unit that stores sewage that flows in from an upstream sewage inlet pipe 11, two pumps PA and PB that pump the sewage stored in the manhole 12 to a downstream sewage outlet pipe 13, and water level gauges 18 and 19 that measure the level of the sewage stored in the manhole 12.

[0033] A first lifting pipe 15b, a first curved pipe 15c, and a first horizontal pipe 15d are each flange-connected to the discharge curved pipe 15a of the first pump PA, and the first horizontal pipe 15d is flange-connected to the sewage outflow pipe 13 via a header pipe 13a. A check valve 15e is provided between the first lifting pipe 15b and the first curved pipe 15c.

[0034] A second lifting 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 the header pipe 13a. A check valve 17e is provided between the second lifting pipe 17b and the second curved pipe 17c.

[0035] 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 an abnormally high water level HHWL.

[0036] A control panel device 200 is installed near the manhole 12, and contains 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 accumulated in the manhole 12 into the sewage outflow pipe 13.

[0037] 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 transmitter that transmits the various types of information stored in the memory unit 22 to a remote monitoring device 40, and a receiver that receives control commands from the monitoring device 40.

[0038] 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, and further, 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.

[0039] The control panel 20 and the pumps PA and PB are connected by AC power feed lines L1 and L2, and the control panel 20 and the water level gauges 18 and 19 are connected by a signal line S.

[0040] When the control unit 21 detects that the water level measured by the water level gauge 18 has reached a predetermined pump start-up water level HWL, it controls the power supply from the power supply line L1 to start one of the pumps PA, PB, pump PA, and when it detects that the water level has reached a pump stop water level LWL, which is lower than the pump start-up water level HWL, it stops the power supply and stops the one of the pumps PA.

[0041] 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.

[0042] Furthermore, if the control unit 21 cannot detect the pump start-up water level HWL due to a malfunction of the water level gauge 18, or if it detects that a large amount of rainwater has flowed into the manhole 12 due to heavy rain, exceeding the drainage capacity of a single pump, and the water level gauge 19 measures that the water level has reached an abnormally high water level HHWL, it will operate the two pumps PA and PB simultaneously.

[0043] The control unit 21 samples the water level information detected by the water level gauges 18, 19 in chronological order, for example at one-minute intervals, and stores it in the memory unit 22, and also stores in the memory unit 22 chronological operating information such as the start and stop times of each pump PA, PB and the operating time from start to stop.

[0044] As shown in Figure 2, the communication unit 24 provided on the control panel 20 of each manhole pump device 10 is configured to transmit water level information and operating information stored in the memory unit 22 to the monitoring device 40 at predetermined intervals.

[0045] The monitoring device 40 functions as a diagnostic device for multiple manhole pump devices 10, and can be configured as, for example, a server computer. The monitoring device 40 includes a communication unit 41 that communicates with the communication unit 24 of each manhole pump device 10 and the manager's mobile communication terminal 30, a database DB that stores water level information and operation 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 / or operation information stored in the database DB.

[0046] The diagnosis unit 44 includes a diagnostic index calculation processing unit 46 and a diagnostic processing unit 48. The diagnostic index calculation processing unit 46 calculates diagnostic indexes from the operation information of the manhole pumps PA, PB collected during the period to be diagnosed for each manhole pump device 10. The diagnostic processing unit 48 diagnoses the conditions of the manhole pumps PA, PB during the period to be diagnosed based on the diagnostic indexes calculated by the diagnostic index calculation processing unit 46.

[0047] The diagnostic indicators used are the ratio n1 / n2 between the number of times n1 one manhole pump PA is operated during the diagnostic period and the number of times n2 the other manhole pump PB is operated, and the ratio t1 / t2 between the operating time t1 of one manhole pump PA and the operating time t2 of the other manhole pump PB during the diagnostic period.

[0048] Before calculating the ratio of the number of operations n1 / n2, if the difference between the number of operations n1 of one manhole pump PA and the number of operations n2 of the other manhole pump PB during the period to be diagnosed is 1, the diagnostic index calculation processing unit 46 adds 1 to the number of operations of the manhole pump with the fewer number of operations, or subtracts 1 from the number of operations of the manhole pump with the more number of operations.

[0049] Under normal conditions, the two manhole pumps PA and PB are operated alternately, so the ratio of the number of times each manhole pump PA and PB is operated during the period under diagnosis increases, and the ratio of the number of times they are operated, n1 / n2, converges to 1. However, if the number of times each manhole pump PA and PB is operated during the period under diagnosis is small, the ratio of the number of times they are operated, n1 / n2, will be a value that is significantly deviated from 1, which may lead to an incorrect diagnosis.

[0050] Therefore, if the difference between the number of times n1 one manhole pump PA operates and the number of times n2 the other manhole pump PB operates is 1, it is assumed that both manhole pumps PA and PB are being operated alternately appropriately, and 1 is added to the number of times the manhole pump that operates less frequently, or 1 is subtracted from the number of times the manhole pump that operates more frequently, thereby correcting the ratio of the number of times of operation to 1. This correction makes it possible to avoid erroneous diagnosis even if the number of times the manhole pumps PA and PB operate during the period to be diagnosed is small.

[0051] When the diagnostic index calculation processing unit 46 adds 1 to the number of times a manhole pump is operated infrequently or subtracts 1 from the number of times a manhole pump is operated in frequent intervals, it uses the average value of the operating time per start-up during the diagnostic period as the operating time per start-up of the manhole pump corresponding to the addition or subtraction.

[0052] Since it is necessary to maintain a balance with the corrected number of operations, the operating time per start of the manhole pump whose number of operations has been corrected is increased or decreased, and by using the average value of the operating time per start during the period to be diagnosed as the correction value, it becomes possible to perform an appropriate diagnosis.

[0053] Furthermore, the diagnostic index calculation processing unit 46 is equipped with a normalization processing unit that normalizes the diagnostic indexes for the diagnostic period based on statistical data calculated only from each diagnostic index calculated for the most recent specified period including the diagnostic period.

[0054] For example, even if the value of the diagnostic index varies greatly depending on the installation environment of the manhole pump device 10, such as areas with high and low inflow water volumes, the influence of external factors such as the installation environment can be eliminated by normalizing the diagnostic index for the period under diagnosis based on statistical data calculated only from individual diagnostic indexes calculated for the most recent specified period including the period under diagnosis.

[0055] The diagnostic processing unit 48 plots the normalized diagnostic index in a predetermined coordinate system, which in this embodiment is a two-dimensional coordinate system of x and y, and diagnoses whether the manhole pumps PA and PB are normal or abnormal based on which side of a boundary threshold preset in the two-dimensional coordinate system the plotted diagnostic index point is on.

[0056] The boundary threshold is automatically generated by a machine learning device that learns using as training data only diagnostic indicators in normal operating states obtained from multiple manhole pumps PA, PB installed in multiple manholes 12, including the manhole pumps PA, PB installed in the manhole 12 to be diagnosed, and indicates the boundary of a three-dimensional coordinate system that serves as a feature space containing normal diagnostic indicators. The machine learning device is constructed in the diagnostic processing unit 48 and is composed of a functional block that executes a one-class support vector machine algorithm.

[0057] By plotting the normalized diagnostic index on a specified coordinate system and adopting the boundary threshold for diagnosing normality or abnormality as a value obtained by machine learning using only diagnostic indexes during normal operation obtained from manhole pumps installed in multiple manholes with different installation environments as training data, it becomes possible to make appropriate diagnoses that are not affected by the installation environment, etc., without having to take the time to prepare diagnostic indexes for abnormalities in advance.

[0058] 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 the 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.

[0059] 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 abnormality, and the diagnostic processing unit 48 is configured to diagnose the cause of abnormality based on the region in which each characteristic value point is plotted.

[0060] 3 shows the flow of a series of diagnostic processes executed by monitoring device 40. When data processing unit 42 has received measurement data, which is operation information for one day set as the diagnostic target period, from each manhole pump apparatus 10 and stored the data in database DB (SA1), diagnostic index calculation processing unit 46 extracts the operation counts n1 and n2 of pumps PA and PB as measurement data for calculating diagnostic indexes used to determine abnormalities for each pump of each manhole pump apparatus 10, extracts total operation times t1 and t2 of the pumps for one day, and calculates the ratio of operation counts n1 / n2 and the ratio of operation times t1 / t2 as diagnostic indexes (SA2).

[0061] In step SA2, before calculating the ratio of the number of operations n1 / n2, if the difference between the number of operations n1 of one manhole pump and the number of operations n2 of the other manhole pump during the period to be diagnosed is 1, a process is executed to add 1 to the number of operations of the manhole pump with the fewer number of operations, or subtract 1 from the number of operations of the manhole pump with the greater number of operations. Note that if the difference between the number of operations n1 and the number of operations n2 is other than 1, that is, if they are the same value or 2 or greater, this correction process is not executed.

[0062] Furthermore, when adding 1 to the number of times a manhole pump that is operated less frequently or subtracting 1 from the number of times a manhole pump that is operated more frequently, the average operating time per start-up during the period under diagnosis is calculated, and the average operating time per start-up of the manhole pump corresponding to the addition or subtraction is added or subtracted.

[0063] The diagnostic index calculation processing unit 46 normalizes the diagnostic index for the diagnostic period (1 day) based on statistical data calculated only from each diagnostic index of the manhole pump device 10 calculated during the most recent predetermined period including the diagnostic period (1 day) stored in the database DB, for example, several months (3 months in this embodiment) (SA3).

[0064] The diagnostic processing unit 48 inputs the normalized diagnostic index calculated by the diagnostic index calculation processing unit 46 into the machine learning device and performs a primary judgment based on a preset boundary threshold (SA5).If an abnormality is judged, the cumulative evaluation value is increased taking into account the degree of abnormality (SA6), and if a normality is judged, the cumulative evaluation value is decreased (SA7).

[0065] This process is repeated every day to determine whether the calculated cumulative evaluation value exceeds a preset cumulative abnormality threshold (SA8), and if it does, the cause of the abnormality is identified based on a diagnostic map that indicates the 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 administrator (SA10). The alarm notification is sent as an email via a mailer provided in the communication unit 41.

[0066] The diagnosis unit 44 will be described in detail below. 4(a) shows the operation data of the manhole pumping device 10 for 24 hours from midnight to midnight, which is the period to be diagnosed. From the top to bottom, the data shows the fluctuations in the water level, the operation timing and operation time of pumps PA and PB, the current value of pump PA, and the current value of pump PB.

[0067] Figure 4(b) is an enlarged view to make it easier to understand the relationship between the fluctuations in the water level shown in Figure 4(a) and the operation timing and operation time of pumps PA and PB. When the water level in the manhole reaches HWL, pump PA is started, and when the water level drops to LWL, it is stopped. Next, when the water level in the manhole reaches HWL, pump PB is started, and when the water level drops to LWL, it is stopped. One of the pumps is running until the water level drops from HWL to LWL. If the pump's transport rate is low or if there is a large amount of sewage flowing into the manhole, the pump's operation time will be longer.

[0068] Such 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.

[0069] The data processing unit 42 passes such operating information for the period to be diagnosed to the diagnostic index calculation processing unit 46, and the diagnostic index calculation processing unit 46 calculates the "number of operating times n1, n2" and "total pump operating times t1, t2" of each pump PA, PB from the operating information passed to it as diagnostic indexes.

[0070] As shown in FIG. 5, the diagnostic index calculation processing unit 46 calculates the mean value μ and variance σ for normalizing the data using the past diagnostic indexes obtained from the driving information accumulated in the database DB for the most recent three months as a population. 2 The average driving time of each feature is normalized using the formula (x-μ) / σ for the feature x.

[0071] Although not limited to the most recent three months, the statistical data (average value, variance) required for the normalization process is preferably calculated based on pump operation information including diagnostic indicators for the most recent specified period, including the period to be diagnosed when the normalization process is performed, thereby eliminating the influence of the passage of time, such as seasonal fluctuations, and enabling a more reliable diagnosis.

[0072] When a pair of characteristic values ​​consisting of the diagnostic indexes "ratio of the number of operations n1 / n2" and "ratio of the total value of pump operating time t1 / t2" normalized by the diagnostic index calculation processing unit 46 is input to the diagnostic processing unit 48, one of the pair of characteristic values ​​is plotted in correspondence with a two-dimensional coordinate system with the x-axis and the other being the y-axis, and a primary diagnosis of whether each manhole pump is normal or abnormal is made based on which side of a boundary threshold preset in the two-dimensional coordinate system the plotted characteristic value point is on.

[0073] Figure 6(a) shows how the boundary threshold is an approximately 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 total pump operating times t1 / t2" and the horizontal axis (x-axis) representing the "ratio of operating times n1 / n2." When the plotted characteristic value points are located inside the boundary threshold, they are judged to be normal, and when the plotted characteristic value points are located outside the boundary threshold, they are judged to be abnormal.

[0074] As described above, the machine learning device provided in the diagnostic processing unit 48 automatically generates a boundary threshold by learning using as training data only diagnostic indices in normal operating states obtained from multiple manhole pumps installed in multiple manhole pump devices 10, including the manhole pump installed in the manhole pump device 10 to be diagnosed. The generated boundary threshold indicates the boundary of a coordinate system that is a feature space containing normal diagnostic indices. The learning algorithm executed by the machine learning device can be a one-class support vector machine, a local outlier factor (LOF) method, an isolation forest (IF) method, a robust covariance (RC) method, or the like.

[0075] By performing machine learning, a normal data space in which normal measurement data (training data) is mapped in the mapping space (feature space) shown in Fig. 6(a), that is, an internal space of boundary thresholds, is generated. The example in Fig. 6 shows the results of learning using one year's worth of pairs of characteristic values ​​in normal conditions obtained from 100 manhole pump devices 10 each equipped with two pumps as learning data.

[0076] 6(b) shows an example of pre-correction data in which uncorrected diagnostic indices are plotted, and post-correction data in which corrected diagnostic indices are plotted, when the difference between the operation count n1 and operation count n2 of each pump PA, PB is 1. The uncorrected diagnostic indices deviate from the boundary threshold and are diagnosed as abnormal, but the corrected diagnostic indices lie within the boundary threshold and are diagnosed as normal.

[0077] Each time the diagnostic processing unit 48 makes a primary diagnosis that a characteristic value point is abnormal, based on the following formula, it adds the product of a predetermined abnormal reference value Vnb and a weight coefficient W based on the distance between the position of each characteristic value point and the boundary threshold value, and subtracts a predetermined normal recovery evaluation value Vpb each time each characteristic value point is diagnosed as normal in the primary diagnosis, thereby calculating a cumulative evaluation value V, and finally diagnoses whether the manhole pump device is normal or abnormal 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 the normal line from the boundary threshold value passing through the characteristic value point. V = Vnb × W - Vpb In this embodiment, Vnb = 1, and it is set that Vnb < Vpb < Wmax × Vnb.

[0078] Even if it is diagnosed as abnormal in the primary diagnosis, there are mild abnormalities that will be diagnosed as normal later, and there are also abnormalities that will continue to be diagnosed as abnormal and eventually lead to serious failures. Even in such cases, each time it is diagnosed as abnormal in the primary diagnosis, a value obtained by multiplying a predetermined abnormal reference value by a weight coefficient based on the distance between the characteristic value point and the boundary threshold value is added, and a predetermined normal recovery evaluation value is subtracted each time it is diagnosed as normal, thereby calculating a cumulative evaluation value, and finally diagnosing whether the mechanical equipment is normal or abnormal based on the cumulative evaluation value, so that it is possible to make a diagnosis taking into account the degree of abnormality, such as an abnormality that requires maintenance in the near future.

[0079] FIG. 7 shows the transition of the cumulative evaluation value. The cumulative evaluation value is subjected to a primary evaluation every predetermined period during which the characteristic value points are plotted. When an abnormality is determined, the value of Vnb × W is added to the initial value 0, and when a normal determination is made, the value of Vpb is subtracted. When the cumulative evaluation value exceeds a predetermined threshold value, in this example, "10", a final abnormality determination is made, and this fact is transmitted to a mobile terminal or the like owned by the administrator. Note that the primary determination and the final determination are continuously performed even after an abnormality is determined.

[0080] An example of a diagnostic map is shown in Fig. 8. The area outside the boundary threshold shown in the feature space shown in Fig. 6 is divided into eight regions, and each region is associated with one of the causes of an abnormality. The diagnostic processing unit 48 diagnoses the cause of an abnormality based on the region in which each feature data is plotted.

[0081] For example, in the example of Figure 8, if characteristic value points are plotted in areas 1, 2, and 4, pump PA, which will be operating for a long time, is diagnosed as having an abnormality in the form of a decrease in drainage capacity; if characteristic value points are plotted in areas 5, 7, and 8, pump PB, which will be operating for a long time, is diagnosed as having an abnormality in the form of a decrease in drainage capacity; and if characteristic value points are plotted in areas 3 and 6, the pump operating time and number of times are biased to one side, and therefore it is diagnosed as having an abnormality in the circuit components installed in control panel 20.

[0082] In the above example, the ratio n1 / n2 of the number of pump operations and the ratio t1 / t2 of the operation time are used as diagnostic indices, but in the present invention, it is necessary to include at least the ratio n1 / n2 of the number of pump operations, and other indices such as the ratio of the average operation time required for one start-up may be used instead of the ratio t1 / t2 of the operation time. Also, only the ratio n1 / n2 of the number of pump operations may be used as a diagnostic indices.

[0083] The diagnostic index calculation processing unit 46 and the diagnostic processing unit 48 are configured to be repeatedly executed each time the diagnostic target period elapses, the diagnostic index calculation processing unit calculates a diagnostic index only when the operating information of the manhole pump satisfies predetermined conditions, and the diagnostic processing unit is configured to diagnose the condition of the manhole pump when the diagnostic index is calculated by the diagnostic index calculation processing unit.

[0084] The specified conditions are that either manhole pump is stopped for maintenance, that both are in an operable state but the number of times or operating time of either during the period to be diagnosed is zero, or that the manhole pump has been replaced and no diagnostic indicators for normalization have been accumulated.

[0085] By setting predetermined conditions for the collected operating information of the manhole pump and configuring the system so that diagnostic indicators are calculated only when the predetermined conditions are met, it is possible to avoid inadvertent misdiagnosis.

[0086] As described above, the manhole pump diagnostic method according to the present invention is a manhole pump diagnostic method for diagnosing the conditions of two manhole pumps that are installed in a manhole and repeatedly start and stop, and is executed by the diagnostic device described above. That is, the manhole pump diagnostic method comprises a diagnostic index calculation step of calculating a diagnostic index from operation information of the manhole pump collected during a period to be diagnosed, and a diagnostic step of diagnosing the state of the manhole pump during the period to be diagnosed based on the diagnostic index calculated in the diagnostic index calculation step, wherein the diagnostic index includes at least a ratio between the number of times one manhole pump is operated and the number of times the other manhole pump is operated during the period to be diagnosed, and the diagnostic index calculation step is configured to, before calculating the ratio of the number of times of operation, add 1 to the number of times the manhole pump is operated less frequently or subtract 1 from the number of times the manhole pump is operated more frequently if the difference between the number of times the one manhole pump is operated and the number of times the other manhole pump is operated during the period to be diagnosed is 1.

[0087] The diagnostic index further includes a ratio between the operating time of one manhole pump and the operating time of the other manhole pump during the period to be diagnosed, and when the diagnostic index calculation step adds 1 to the operating count of a manhole pump that is operated less frequently or subtracts 1 from the operating count of a manhole pump that is operated more frequently, the diagnostic index calculation step uses the average operating time per start-up during the period to be diagnosed as the operating time per start-up of the manhole pump that corresponds to the addition or subtraction.

[0088] The diagnostic index calculation step includes a normalization step of normalizing the diagnostic indexes for the period to be diagnosed based on statistical data calculated only from each diagnostic index calculated for a specified period immediately preceding the period to be diagnosed, and the diagnosis step is configured to plot the normalized diagnostic indexes in a specified coordinate system and diagnose whether the manhole pump is normal or abnormal based on which side of a boundary threshold preset in the coordinate system the plotted diagnostic index point is on, and the boundary threshold is automatically generated by a machine learning device that learns using as training data only diagnostic indexes in normal operating states obtained from a plurality of manhole pumps installed in a plurality of manholes including the manhole pump installed in the manhole to be diagnosed, and indicates the boundary of the coordinate system that becomes a feature space within which normal diagnostic indexes are included.

[0089] The diagnostic index calculation step and the diagnosis step are configured to be repeated each time the diagnostic target period elapses, the diagnostic index calculation step calculates the diagnostic index only when the operating information of the manhole pump satisfies a predetermined condition, and the diagnosis step is configured to diagnose the condition of the manhole pump when the diagnostic index is calculated by the diagnostic index calculation step.

[0090] The above-described embodiment shows one example of the present invention, and the technical scope of the present invention is not limited by this description. It goes without saying that the specific configuration of each part, including the pump and water level meter, the threshold value set for abnormality determination, the diagnostic target period, the predetermined period during which the diagnostic indexes used in the normalization process are accumulated, the sampling period for the diagnostic indexes used in the learning process, the number of manhole pump devices, etc. can be appropriately modified and designed within the scope in which the effects of the present invention are achieved. [Explanation of symbols]

[0091] 10: Manhole pump equipment PA,PB: Pump 18,19: Water level gauge 21: Control unit 22: Storage part 24: Communications Department 30: Mobile devices 40: Monitoring device 41: Communications Department 42: Data processing section 44: Diagnostic Department 46: Diagnostic index calculation processing unit 48: Diagnostic processing unit

Claims

1. A manhole pump diagnostic method for diagnosing the status of two manhole pumps that are installed in a manhole and repeatedly start and stop, comprising: a diagnostic index calculation step of calculating a diagnostic index from the operation information of the manhole pump collected during a diagnostic target period; a diagnosis step of diagnosing a state of the manhole pump during the diagnosis target period based on the diagnostic index calculated in the diagnostic index calculation step; Equipped with The diagnostic index includes at least a ratio between the number of times one manhole pump is operated and the number of times the other manhole pump is operated during the diagnostic target period, The manhole pump diagnostic method is configured such that, before calculating the ratio of the number of times of operation, if the difference between the number of times one manhole pump is operated and the number of times the other manhole pump is operated during the diagnostic period is 1, 1 is added to the number of times the manhole pump is operated less frequently, or 1 is subtracted from the number of times the manhole pump is operated more frequently.

2. The diagnostic index further includes a ratio between the operation time of one manhole pump and the operation time of the other manhole pump during the diagnostic target period, 2. A manhole pump diagnostic method according to claim 1, wherein the diagnostic index calculation step, when adding 1 to the number of times a manhole pump is operated infrequently or subtracting 1 from the number of times a manhole pump is operated in frequent intervals, employs an average value of the operating time per start-up during the diagnostic period as the operating time per start-up of the manhole pump corresponding to the addition or subtraction, and adds or subtracts this average value.

3. the diagnostic index calculation step includes a normalization step of normalizing the diagnostic index for the diagnostic period based on statistical data calculated only from diagnostic indexes calculated for a predetermined period immediately preceding the diagnostic period, the normalization step including the diagnostic period; The diagnosis step is configured to plot the normalized diagnostic index in a predetermined coordinate system, and diagnose whether the manhole pump is normal or abnormal based on whether the plotted diagnostic index point is on either side of a boundary threshold value preset in the coordinate system, The manhole pump diagnostic method according to claim 1 or 2, wherein the boundary threshold is automatically generated by a machine learning device that learns using as training data only diagnostic indicators in normal operating conditions obtained from multiple manhole pumps installed in multiple manholes, including the manhole pump installed in the manhole to be diagnosed, and indicates the boundary of the coordinate system that is a feature space that includes normal diagnostic indicators.

4. 3. A manhole pump diagnostic method according to claim 1 or 2, wherein the diagnostic index calculation step and the diagnosis step are configured to be repeated each time the diagnostic target period elapses, the diagnostic index calculation step calculates the diagnostic index only when operating information of the manhole pump satisfies a predetermined condition, and the diagnosis step is configured to diagnose the condition of the manhole pump when the diagnostic index is calculated by the diagnostic index calculation step.

5. A manhole pump diagnostic device that diagnoses the status of two manhole pumps that are installed in a manhole and repeatedly start and stop, a diagnostic index calculation processing unit that calculates a diagnostic index from the operation information of the manhole pump collected during a diagnostic target period; a diagnostic processing unit that diagnoses the state of the manhole pump during the diagnostic target period based on the diagnostic index calculated by the diagnostic index calculation processing unit; Equipped with The diagnostic index includes at least a ratio between the number of times one manhole pump is operated and the number of times the other manhole pump is operated during the diagnostic target period, The diagnostic index calculation processing unit is configured to add 1 to the number of times the manhole pump is operated less frequently or subtract 1 from the number of times the manhole pump is operated more frequently if the difference between the number of times the one manhole pump is operated and the number of times the other manhole pump is operated during the diagnostic period is 1 before calculating the ratio of the number of times the pump is operated.

6. The diagnostic index further includes a ratio between the operation time of one manhole pump and the operation time of the other manhole pump during the diagnostic target period, 6. A manhole pump diagnostic device as described in claim 5, wherein when the diagnostic index calculation processing unit adds 1 to the number of times a manhole pump is operated infrequently or subtracts 1 from the number of times a manhole pump is operated in frequent intervals, the diagnostic index calculation processing unit uses the average value of the operating time per start-up during the diagnostic period as the operating time per start-up of the manhole pump corresponding to the addition or subtraction, and adds or subtracts this average value.

7. the diagnostic index calculation processing unit includes a normalization processing unit that normalizes the diagnostic indexes for the diagnostic target period based on statistical data calculated only from the diagnostic indexes calculated for a predetermined period immediately preceding the diagnostic target period, and the diagnostic processing unit is configured to plot the normalized diagnostic index in a predetermined coordinate system, and diagnose whether the manhole pump is normal or abnormal based on whether the plotted diagnostic index point is on either side of a boundary threshold value that is preset in the coordinate system; The manhole pump diagnostic device according to claim 5 or 6, wherein the boundary threshold is automatically generated by a machine learning device that learns using as training data only diagnostic indicators in normal operating states obtained from multiple manhole pumps installed in multiple manholes including the manhole pump installed in the manhole to be diagnosed, and indicates the boundary of the coordinate system that is a feature space that includes normal diagnostic indicators.

8. 7. A manhole pump diagnostic device according to claim 5 or 6, wherein the diagnostic index calculation processing unit and the diagnostic processing unit are configured to be repeatedly executed each time the diagnostic target period elapses, the diagnostic index calculation processing unit calculates the diagnostic index only when operating information of the manhole pump satisfies a predetermined condition, and the diagnostic processing unit is configured to diagnose the condition of the manhole pump when the diagnostic index is calculated by the diagnostic index calculation processing unit.

Images