Centrifugal pump fault online diagnosis method, device, storage medium and system

Abstract

The invention is suitable for the technical field of centrifugal pump fault detection, and provides a centrifugal pump fault online diagnosis method and device, a storage medium and a system. The method comprises the steps of obtaining a first vibration data set of the centrifugal pump system, obtaining a water inlet pressure data set and a second vibration data set of the centrifugal pump system, and obtaining a water outlet pressure data set of the centrifugal pump system and a current data set of centrifugal pump operation current, obtaining fault prediction probabilities of a plurality of different types of faults based on a data set comparison result; and when the fault prediction probability exceeds a fault threshold value, reporting the fault type exceeding the fault threshold value. Through the steps of data interval sampling, data processing, waveform matching, correlation analysis, result output and the like, the whole algorithm is closely combined with a centralized control / secret control system controller, the calculation complexity of a fault prediction algorithm is low, and the reliability of an existing detection system is remarkably improved under the condition that low hardware cost is maintained.

Description

Technical Field

[0001] The present invention belongs to the technical field of centrifugal pump fault detection, and in particular relates to a centrifugal pump fault online diagnosis method, device, storage medium and system. Background Art

[0002] The centrifugal pump system is a common fluid delivery system, usually used to transport liquid from one place to another. It is mainly composed of centrifugal pumps, pipelines and control valves. Its basic working principle is to use centrifugal force to suck liquid from the pump inlet, and then push the liquid to the pipeline system through the rotation of the pump, and finally send it to the required location.

[0003] The centrifugal pump system is the core mechanical equipment of the mine water supply and drainage system, which directly affects the underground drainage work. The electric gate valve, centrifugal pump and pipeline are the core equipment of the centrifugal pump system and are also the equipment most prone to failure. In actual use, failures are often procedural, but due to limited detection methods, failures are often not discovered in the first time, turning failures into accidents.

[0004] There are two mainstream fault detection methods at present. The first is to establish a vibration spectrum analysis model for the centrifugal pump system. This method generally requires the installation of special analysis equipment and special detection sensors. The detection spectrum needs to reach a certain response speed. At the same time, the system needs a special analysis system and a special analysis server. Although this method has high accuracy, it is expensive. The supervision of a centrifugal pump requires the operation of two systems, namely a centralized control / remote control system and a special prediction system. Few mines are willing to use this method. The other method is the traditional fault alarm method. This method will alarm when the equipment has a strong abnormal state, such as abnormal pressure and abnormal vibration. The alarm method has the system monitor the high and low limits in real time, and issue an alarm reminder when it exceeds the limit. The operation of the system is comprehensive and procedural. Once a limit alarm occurs, the system has exceeded the limit and a serious fault occurs.

[0005] Therefore, it can be seen that the existing detection methods are difficult to achieve high-precision fault detection with predictive capability without significantly increasing the detection cost. Summary of the invention

[0006] The purpose of the embodiments of the present application is to provide an online diagnosis method for centrifugal pump faults, aiming to solve the problem that existing detection methods are difficult to achieve high-precision fault detection with predictive capability without significantly increasing detection costs.

[0007] The embodiment of the present application is implemented by providing a centrifugal pump fault online diagnosis method, the method comprising the following steps:

[0008] Controlling the water inlet valve of the centrifugal pump system to open and start the vibration monitoring component; controlling the emptying pump of the centrifugal pump system to open and obtain a first vibration data set of the centrifugal pump system;

[0009] Acquire vacuum degree data of the centrifugal pump system, and when the vacuum degree reaches a vacuum threshold, control the drain pump to close and control the centrifugal pump to open; acquire a water inlet pressure data set and a second vibration data set of the centrifugal pump system;

[0010] Control the water outlet valve of the centrifugal pump system to open, and obtain a water outlet pressure data set of the centrifugal pump system and a current data set of the centrifugal pump operating current;

[0011] The first vibration data set, the second vibration data set, the water inlet pressure data set, the water outlet pressure data set and the current data set obtained based on real-time monitoring are compared with corresponding normal data sets in a historical database, and the fault prediction probabilities of several different types of faults are obtained based on the comparison results;

[0012] When the fault prediction probability exceeds a fault threshold, the fault type exceeding the fault threshold is reported.

[0013] Preferably, the method of comparing the outlet pressure data set and the current data set obtained based on real-time monitoring with the corresponding normal data set in the historical database and obtaining the fault prediction probabilities of several different types of faults based on the comparison results includes:

[0014] Obtain the fluctuation correspondence between the outlet pressure historical data set and the current historical data set;

[0015] Based on the fluctuation correspondence, a two-dimensional relationship curve is obtained;

[0016] Fitting and comparing the outlet pressure data set and the current data set collected by real-time monitoring with the two-dimensional relationship curve to obtain a fitting deviation;

[0017] Based on the fitting deviation degree, a fault prediction probability of the first type of fault is obtained.

[0018] Preferably, the method of comparing the first vibration data set, the second vibration data set, and the water inlet pressure data set obtained based on real-time monitoring with the corresponding normal data sets in the historical database includes:

[0019] During the period from when the emptying pump is turned on to when the emptying pump is turned off and the centrifugal pump system is in a normal state, the vibration data of the centrifugal pump system on the X-axis, the Y-axis and the Z-axis are obtained once every first preset time to obtain a first historical vibration data set

[0020] Comparing the first vibration data set with the first historical vibration data set to obtain a first comparison result;

[0021] After the centrifugal pump is turned on and the centrifugal pump system is in a normal state, the vibration data of the centrifugal pump system on the X-axis, Y-axis and Z-axis are obtained once every second preset time to obtain a second historical vibration data set

[0022] Comparing the second vibration data set with the second historical vibration data set to obtain a second comparison result;

[0023] After the draining pump is turned on and the centrifugal pump system is in a normal state, the water inlet pressure data of the centrifugal pump system is obtained once at a third preset time interval to obtain a water inlet historical data set;

[0024] The water inlet historical data set is compared with the water inlet pressure data set to obtain a third comparison result.

[0025] Preferably, the method for obtaining the fault prediction probabilities of several different types of faults based on the comparison results includes:

[0026] Based on the first comparison result, a fault prediction probability of the second type of fault is obtained;

[0027] Based on the second comparison result, the fault prediction probability of the third type of fault is obtained;

[0028] Based on the third comparison result, the fault prediction probability of the fourth type of fault is obtained.

[0029] Preferably, the fault prediction probability of the fourth type of fault is calculated as follows:

[0030] Get the historical data set of the water inlet And the water inlet pressure data set collected in real time

[0031] The Euclidean metric of the water inlet historical data set and the water inlet pressure data set is calculated by an algorithm based on the following formula:

[0032]

[0033] The Euclidean metric is set to the fault prediction probability of the fourth type of fault.

[0034] Preferably, the method for obtaining the vibration data of the centrifugal pump system is:

[0035] A three-axis vibration sensor is arranged at the main motor of the centrifugal pump system, and data of the real-time vibration condition of the centrifugal pump system is collected based on the three-axis vibration sensor to obtain vibration data of the centrifugal pump system.

[0036] Preferably, when the fault prediction probability exceeds the fault threshold, the method for reporting the fault type exceeding the fault threshold is:

[0037] When the failure prediction probability of the first type of failure, the failure prediction probability of the second type of failure, the failure prediction probability of the third type of failure and the failure prediction probability of the fourth type of failure exceed their respective set warning thresholds, an alarm is issued for the failure result and the failure is reported.

[0038] Another object of the embodiment of the present application is to provide an online diagnosis device for centrifugal pump faults, the online diagnosis device for centrifugal pump faults comprising:

[0039] A first vibration data set acquisition module is used to control the water inlet valve of the centrifugal pump system to open and start the vibration monitoring component; control the emptying pump of the centrifugal pump system to open and acquire a first vibration data set of the centrifugal pump system;

[0040] A water inlet pressure data set and a second vibration data set acquisition module, used to acquire vacuum degree data of a centrifugal pump system, and when the vacuum degree reaches a vacuum threshold, control the emptying pump to be turned off and the centrifugal pump to be turned on; acquire a water inlet pressure data set and a second vibration data set of a centrifugal pump system;

[0041] The water outlet pressure data set and current data set acquisition module is used to control the opening of the water outlet valve of the centrifugal pump system, and acquire the water outlet pressure data set of the centrifugal pump system and the current data set of the centrifugal pump operating current;

[0042] A fault prediction probability acquisition module is used to compare the first vibration data set, the second vibration data set, the water inlet pressure data set, the water outlet pressure data set and the current data set acquired based on real-time monitoring with the corresponding normal data sets in the historical database, and obtain the fault prediction probabilities of several different types of faults based on the comparison results;

[0043] The fault type reporting module is used to report the fault type that exceeds the fault threshold when the fault prediction probability exceeds the fault threshold.

[0044] Another object of an embodiment of the present application is to provide a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the processor executes the steps of the online diagnosis method for centrifugal pump faults as described above.

[0045] Another object of an embodiment of the present application is to provide an online diagnosis system for centrifugal pump faults, characterized in that when the system is running, it executes the steps of the online diagnosis method for centrifugal pump faults as described above.

[0046] The embodiment of the present application provides a centrifugal pump fault online diagnosis method, which has the outstanding effect that the present application can be operated with the hardware equipment of the existing centrifugal pump remote control / centralized control system without the need to add other hardware. By collecting information with the help of basic sensors and using information analysis methods, the detected information can be mined to complete fault prediction, and timely alarms can be issued when a fault occurs or signs of a fault appear, providing effective assistance for staff maintenance and troubleshooting. The overall solution uses steps such as data interval sampling, data processing, waveform matching, correlation analysis and result output, so that the entire algorithm is closely integrated with the centralized control / closed control system controller, and the fault prediction algorithm has low computational complexity. While maintaining a low hardware cost, the reliability of the existing detection system is significantly improved. In addition, the data comparison of the present application is determined based on the order in which the centrifugal pump is turned on. For example, when the emptying pump is turned on, the water inlet pressure comparison is started, and the segmented vibration comparison is performed, so that the comparison is more targeted, and the system's recognition accuracy for faults is further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A flow chart of a centrifugal pump fault online diagnosis method provided in an embodiment of the present application;

[0048] Figure 2 A schematic diagram of a centrifugal pump startup process provided in an embodiment of the present application;

[0049] Figure 3 A schematic diagram of a method for determining a fault type provided in an embodiment of the present application;

[0050] Figure 4 A structural block diagram of a centrifugal pump fault online diagnosis device provided in an embodiment of the present application;

[0051] Figure 5 FIG. 4 is a block diagram of the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0053] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, a first script may be referred to as a second script, and similarly, a second script may be referred to as a first script without departing from the scope of this application.

[0054] like Figure 1 As shown, in one embodiment, a centrifugal pump fault online diagnosis method is proposed. This embodiment is mainly illustrated by applying the method to a computer device. A centrifugal pump fault online diagnosis method may specifically include the following steps:

[0055] Step S10, controlling the water inlet valve of the centrifugal pump system to open and start the vibration monitoring component; controlling the emptying pump of the centrifugal pump system to open and obtain a first vibration data set of the centrifugal pump system;

[0056] Step S20, in the present application, obtains vacuum degree data of the centrifugal pump system, and when the vacuum degree reaches the vacuum threshold, controls the emptying pump to be turned off and controls the centrifugal pump to be turned on; obtains a water inlet pressure data set and a second vibration data set of the centrifugal pump system;

[0057] Step S30, controlling the water outlet valve of the centrifugal pump system to open, and obtaining a water outlet pressure data set of the centrifugal pump system and a current data set of the centrifugal pump operating current;

[0058] Step S40, comparing the first vibration data set, the second vibration data set, the water inlet pressure data set, the water outlet pressure data set and the current data set obtained based on real-time monitoring with the corresponding normal data sets in the historical database, and obtaining the fault prediction probabilities of several different types of faults based on the comparison results;

[0059] Step S50: When the fault prediction probability exceeds the fault threshold, the fault type exceeding the fault threshold is reported.

[0060] In this embodiment, the above scheme disclosed in the present application can automatically diagnose the faults of multi-stage centrifugal pumps for mining, and is used to solve the problem that the existing automatic fault diagnosis method of multi-stage centrifugal pumps cannot predict and infer according to the maintenance degree of the centrifugal pump, and cannot reasonably assign the faults to the corresponding maintenance personnel for maintenance according to the fault type and fault degree of the centrifugal pump. This method collects the centrifugal pump information of the multi-stage centrifugal pump for mining through a data acquisition module, and by distinguishing different maintenance types, the multi-stage centrifugal pump for mining is first allocated and then processed, so as to facilitate the allocation of corresponding maintenance personnel to repair and maintain the multi-stage centrifugal pump for mining. By calculating the maintenance matching value of the maintenance personnel, it is convenient to reasonably select the corresponding maintenance personnel for maintenance and processing. When the maintenance personnel perform fault repair on the centrifugal pump to be processed, the maintenance information of the centrifugal pump to be processed can be uploaded after the repair is completed, and the server receives the maintenance information and stores it.

[0061] like Figure 2As shown, it is a startup sequence diagram of each module in a system provided by the present application. The present application can acquire data through the existing three-axis vibration sensor installed at the centrifugal pump motor, the inlet negative pressure sensor installed at the water inlet valve, and the outlet positive pressure sensor installed outside the water outlet valve. The three-axis vibration, negative pressure and positive pressure conditions of the centrifugal pump system can be collected in real time during the first operation of the system, and during the startup and operation of the equipment to build a historical database.

[0062] The embodiment of the present application provides a centrifugal pump fault online diagnosis method, which has the outstanding effect that the present application can be operated with the hardware equipment of the existing centrifugal pump remote control / centralized control system without the need to add other hardware. By collecting information with the help of basic sensors and using information analysis methods, the detected information can be mined to complete fault prediction, and timely alarms can be issued when a fault occurs or signs of a fault appear, providing effective assistance for staff maintenance and troubleshooting. The overall solution uses steps such as data interval sampling, data processing, waveform matching, correlation analysis and result output, so that the entire algorithm is closely integrated with the centralized control / closed control system controller, and the fault prediction algorithm has low computational complexity. While maintaining a low hardware cost, the reliability of the existing detection system is significantly improved. In addition, the data comparison of the present application is determined based on the order in which the centrifugal pump is turned on. For example, when the emptying pump is turned on, the water inlet pressure comparison is started, and the segmented vibration comparison is performed, so that the comparison is more targeted, and the system's recognition accuracy for faults is further improved.

[0063] In a preferred embodiment, the method of comparing the outlet pressure data set and the current data set obtained based on real-time monitoring with the corresponding normal data set in the historical database and obtaining the fault prediction probabilities of several different types of faults based on the comparison results includes:

[0064] Obtain the fluctuation correspondence between the outlet pressure historical data set and the current historical data set;

[0065] Based on the fluctuation correspondence, a two-dimensional relationship curve is obtained;

[0066] Fitting and comparing the outlet pressure data set and the current data set collected by real-time monitoring with the two-dimensional relationship curve to obtain a fitting deviation;

[0067] Based on the fitting deviation degree, a fault prediction probability of the first type of fault is obtained.

[0068] In the embodiment of the present application, for the outlet pressure data set and the current data set, the comparison result is the fitting deviation, which is used to characterize the offset of the two-dimensional relationship curve between the real-time detection data and the normal state with the outlet pressure and the centrifugal pump working current as the horizontal and vertical coordinates. When the degree of offset is high, it is considered that a fault has occurred. Based on the numerical value of the degree of deviation, the numerical value of the fault prediction probability can be defined and obtained according to the actual situation.

[0069] This embodiment avoids the problem of inaccurate fault prediction caused by the analysis of single data. Since the magnitude of the current when the water pump is working is often correlated with the water flow rate, the accuracy of fault prediction is significantly improved by analyzing the correlated quantity.

[0070] In a preferred embodiment, the method of comparing the first vibration data set, the second vibration data set, and the water inlet pressure data set obtained based on real-time monitoring with the corresponding normal data sets in the historical database includes:

[0071] During the period from when the emptying pump is turned on to when the emptying pump is turned off and the centrifugal pump system is in a normal state, the vibration data of the centrifugal pump system on the X-axis, the Y-axis and the Z-axis are obtained once every first preset time to obtain a first historical vibration data set

[0072] Comparing the first vibration data set with the first historical vibration data set to obtain a first comparison result;

[0073] After the centrifugal pump is turned on and the centrifugal pump system is in a normal state, the vibration data of the centrifugal pump system on the X-axis, Y-axis and Z-axis are obtained once every second preset time to obtain a second historical vibration data set

[0074] Comparing the second vibration data set with the second historical vibration data set to obtain a second comparison result;

[0075] After the draining pump is turned on and the centrifugal pump system is in a normal state, the water inlet pressure data of the centrifugal pump system is obtained once at a third preset time interval to obtain a water inlet historical data set;

[0076] The water inlet historical data set is compared with the water inlet pressure data set to obtain a third comparison result.

[0077] In the embodiment of the present application, the interval time can be determined according to the actual situation. For example, within 60 seconds after the pump is turned on, the X-axis vibration, Y-axis vibration, and Z-axis vibration are collected every 0.5 seconds and once every second to form a corresponding prediction set.

[0078] In a preferred embodiment, the method for obtaining the fault prediction probabilities of several different types of faults based on the comparison results includes:

[0079] Based on the first comparison result, a fault prediction probability of the second type of fault is obtained;

[0080] Based on the second comparison result, the fault prediction probability of the third type of fault is obtained;

[0081] Based on the third comparison result, the fault prediction probability of the fourth type of fault is obtained.

[0082] In the embodiment of the present application, different fault type probabilities represent different types of faults that may have occurred. Figure 3 As shown, in one embodiment, a schematic diagram for predicting a fault type is provided. Through this method, corresponding fault analysis results can be obtained based on different fault types. For example, if the emptying system is running and the vibration spectrum is abnormal, it can be determined that there is a problem with the pump body seal; if the emptying system is running and the negative pressure is abnormal, it can be determined that there is a leak in the pipeline; if the vibration spectrum is abnormal when the pump is turned on, it can be determined that there is mechanical looseness such as the anchor bolts and screws; if the outlet pressure is abnormal after the water outlet valve is started, it can be determined that there is a fault in the water outlet valve.

[0083] In a preferred embodiment, the fault prediction probability of the fourth type of fault is calculated as follows:

[0084] Get the historical data set of the water inlet And the water inlet pressure data set collected in real time

[0085] The Euclidean metric of the water inlet historical data set and the water inlet pressure data set is calculated by an algorithm based on the following formula:

[0086]

[0087] The Euclidean metric is set to the fault prediction probability of the fourth type of fault.

[0088] In the embodiment of the present application, only the failure probability is obtained by using the water inlet historical data set as an example. The probability of other types of failures can also be obtained by referring to this method.

[0089] In a preferred embodiment, the method for obtaining vibration data of a centrifugal pump system is:

[0090] A three-axis vibration sensor is arranged at the main motor of the centrifugal pump system, and data of the real-time vibration condition of the centrifugal pump system is collected based on the three-axis vibration sensor to obtain vibration data of the centrifugal pump system.

[0091] In an embodiment of the present application, a method for obtaining vibration data is provided, wherein it can be understood that vibration can utilize sensors arranged at different positions to obtain multiple groups of data, and each group of data can be compared separately.

[0092] In a preferred embodiment, when the fault prediction probability exceeds the fault threshold, the method for reporting the fault type exceeding the fault threshold is:

[0093] When the failure prediction probability of the first type of failure, the failure prediction probability of the second type of failure, the failure prediction probability of the third type of failure and the failure prediction probability of the fourth type of failure exceed their respective set warning thresholds, an alarm is issued for the failure result and the failure is reported.

[0094] In the embodiment of the present application, the alarm may refer to sound and light alarm, information alarm, etc. Different thresholds may be set, and different alarm strategies may be adopted under different fault probabilities.

[0095] like Figure 4 As shown, in one embodiment, a centrifugal pump fault online diagnosis device is provided, which can be integrated into the above-mentioned computer device 120, and specifically can include a first vibration data set acquisition module 510, an inlet pressure data set and a second vibration data set acquisition module 520, an outlet pressure data set and a current data set acquisition module 530, a fault prediction probability acquisition module 540 and a fault type reporting module 550.

[0096] The first vibration data set acquisition module is used to control the water inlet valve of the centrifugal pump system to open and start the vibration monitoring component; control the emptying pump of the centrifugal pump system to open and acquire the first vibration data set of the centrifugal pump system;

[0097] A water inlet pressure data set and a second vibration data set acquisition module, used to acquire vacuum degree data of a centrifugal pump system, and when the vacuum degree reaches a vacuum threshold, control the emptying pump to be turned off and the centrifugal pump to be turned on; acquire a water inlet pressure data set and a second vibration data set of a centrifugal pump system;

[0098] The water outlet pressure data set and current data set acquisition module is used to control the opening of the water outlet valve of the centrifugal pump system, and acquire the water outlet pressure data set of the centrifugal pump system and the current data set of the centrifugal pump operating current;

[0099] A fault prediction probability acquisition module is used to compare the first vibration data set, the second vibration data set, the water inlet pressure data set, the water outlet pressure data set and the current data set acquired based on real-time monitoring with the corresponding normal data sets in the historical database, and obtain the fault prediction probabilities of several different types of faults based on the comparison results;

[0100] The fault type reporting module is used to report the fault type that exceeds the fault threshold when the fault prediction probability exceeds the fault threshold.

[0101] In the embodiment of the present application, the explanation and description of the above-mentioned centrifugal pump fault online diagnosis device can refer to the explanation and description of the above-mentioned corresponding method. For the description of the above-mentioned centrifugal pump fault online diagnosis method, please refer to the above, which will not be repeated here.

[0102] The embodiment of the present application provides an online diagnosis device for centrifugal pump faults, and the outstanding effect is that the present application can be operated with the hardware equipment of the existing centrifugal pump remote control / centralized control system without the need to add other hardware. By collecting information with the help of basic sensors and using information analysis methods, the detected information can be mined to complete fault prediction, and a timely alarm can be issued when a fault occurs or a sign of a fault appears, providing effective assistance for staff to inspect and troubleshoot. The overall solution is through data interval sampling, data processing, waveform matching, correlation analysis and result output, so that the entire algorithm is closely integrated with the centralized control / closed control system controller, and the fault prediction algorithm has low computational complexity. While maintaining a low hardware cost, the reliability of the existing detection system is significantly improved. In addition, the data comparison of the present application is determined based on the order of opening the centrifugal pump. For example, when the emptying pump is turned on, the water inlet pressure comparison is started, and the segmented vibration comparison is performed, so that the comparison is more targeted, and the system's recognition accuracy for faults is further improved.

[0103] Figure 5 FIG. 1 shows an internal structure diagram of a computer device in an embodiment. The computer device may specifically be a carrier for the operation of the above method. Figure 5 As shown, the computer device includes a processor, a memory, a network interface, an input device and a display screen connected through a system bus. Among them, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor can implement an online diagnosis method for centrifugal pump faults. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor can execute an online diagnosis method for centrifugal pump faults. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen. The input device of the computer device may be a touch layer covered on the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc., which can be used to control the centrifugal pump system.

[0104] Those skilled in the art will understand that Figure 5The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0105] In one embodiment, the centrifugal pump fault online diagnosis device provided by the present application can be implemented in the form of a computer program. The computer program can be Figure 5 The computer device shown in the figure is run. The memory of the computer device can store various program modules constituting the centrifugal pump fault online diagnosis device, for example, Figure 4 The computer program composed of the modules 510, 520 and 530 enables the processor to execute the steps of the centrifugal pump fault online diagnosis method of each embodiment of the present application described in this specification.

[0106] For example, Figure 5 The computer device shown can be Figure 4 The module 510 in the centrifugal pump fault online diagnosis device shown in the figure executes step S10. The computer device can execute step S20 through the module 520. And so on.

[0107] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the processor executes the steps of the centrifugal pump fault online diagnosis method as described above.

[0108] In the embodiment of the present application, for the description of the above-mentioned centrifugal pump fault online diagnosis method, please refer to the above text and will not be repeated here.

[0109] In the embodiment of the present application, the program run by the method stored in the storage medium of the embodiment of the present application has the outstanding effect that it can be run with the hardware equipment of the existing centrifugal pump remote control / centralized control system without adding other hardware. By collecting information with the help of basic sensors and using information analysis methods, the detected information can be mined to complete fault prediction, and timely alarms can be issued when a fault occurs or signs of a fault appear, providing effective assistance for staff maintenance and troubleshooting. The overall solution is through data interval sampling, data processing, waveform matching, correlation analysis and result output steps, so that the entire algorithm is closely integrated with the centralized control / closed control system controller, the fault prediction algorithm has low computational complexity, and the reliability of the existing detection system is significantly improved while maintaining a low hardware cost. In addition, the data comparison of the present application is determined based on the order of opening the centrifugal pump. For example, when the emptying pump is turned on, the water inlet pressure comparison is started, and the segmented vibration comparison is performed, so that the comparison is more targeted, and the system's recognition accuracy for faults is further improved.

[0110] In one embodiment, a centrifugal pump fault online diagnosis system is provided. When the system is running, the steps of the centrifugal pump fault online diagnosis method as described above are executed.

[0111] In the embodiment of the present application, the system can be a computer software or program system, which runs in the hardware containing the processing device, and when the above system is running, the corresponding method is executed. For the description of the above centrifugal pump fault online diagnosis method, please refer to the above text, which will not be repeated here.

[0112] In the embodiment of the present application, based on this system, it can be operated with the help of the hardware equipment of the existing centrifugal pump remote control / centralized control system, without the need to add other hardware. By collecting information with the help of basic sensors and using information analysis methods, the detected information can be mined to complete fault prediction, and timely alarms can be issued when a fault occurs or signs of a fault appear, providing effective assistance for staff to inspect and troubleshoot. The overall solution uses steps such as data interval sampling, data processing, waveform matching, correlation analysis and result output, so that the entire algorithm is closely integrated with the centralized control / closed control system controller, and the fault prediction algorithm has low computational complexity. While maintaining a low hardware cost, the reliability of the existing detection system is significantly improved. In addition, the data comparison of the present application is determined based on the order in which the centrifugal pump is turned on. For example, when the emptying pump is turned on, the water inlet pressure comparison is started, and the segmented vibration comparison is performed, so that the comparison is more targeted, further improving the system's accuracy in identifying faults.

[0113] It should be understood that, although each step in the flow chart of each embodiment of the present application is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is clear explanation in this article, the execution of these steps does not have strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0114] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0115] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0116] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A centrifugal pump fault online diagnosis method, characterized in that: The method comprises the following steps: Controlling the water inlet valve of the centrifugal pump system to open and start the vibration monitoring component; controlling the emptying pump of the centrifugal pump system to open and obtain a first vibration data set of the centrifugal pump system; Acquire vacuum degree data of the centrifugal pump system, and when the vacuum degree reaches a vacuum threshold, control the drain pump to close and control the centrifugal pump to open; acquire a water inlet pressure data set and a second vibration data set of the centrifugal pump system; Control the water outlet valve of the centrifugal pump system to open, and obtain a water outlet pressure data set of the centrifugal pump system and a current data set of the centrifugal pump operating current; The first vibration data set, the second vibration data set, the water inlet pressure data set, the water outlet pressure data set and the current data set obtained based on real-time monitoring are compared with corresponding normal data sets in a historical database, and the fault prediction probabilities of several different types of faults are obtained based on the comparison results; When the fault prediction probability exceeds a fault threshold, the fault type exceeding the fault threshold is reported.

2. A centrifugal pump fault online diagnosis method according to claim 1, characterized in that: The method of comparing the outlet pressure data set and the current data set obtained based on real-time monitoring with the corresponding normal data set in the historical database and obtaining the fault prediction probabilities of several different types of faults based on the comparison results includes: Obtain the fluctuation correspondence between the outlet pressure historical data set and the current historical data set; Based on the fluctuation correspondence, a two-dimensional relationship curve is obtained; Fitting and comparing the outlet pressure data set and the current data set collected by real-time monitoring with the two-dimensional relationship curve to obtain a fitting deviation; Based on the fitting deviation degree, a fault prediction probability of the first type of fault is obtained.

3. A centrifugal pump fault online diagnosis method according to claim 2, characterized in that: The method of comparing the first vibration data set, the second vibration data set, and the water inlet pressure data set obtained based on real-time monitoring with the corresponding normal data sets in the historical database includes: During the period from when the emptying pump is turned on to when the emptying pump is turned off and the centrifugal pump system is in a normal state, the vibration data of the centrifugal pump system on the X-axis, the Y-axis and the Z-axis are obtained once every first preset time to obtain a first historical vibration data set Comparing the first vibration data set with the first historical vibration data set to obtain a first comparison result; After the centrifugal pump is turned on and the centrifugal pump system is in a normal state, the vibration data of the centrifugal pump system on the X-axis, Y-axis and Z-axis are obtained once every second preset time to obtain a second historical vibration data set Comparing the second vibration data set with the second historical vibration data set to obtain a second comparison result; After the draining pump is turned on and the centrifugal pump system is in a normal state, the water inlet pressure data of the centrifugal pump system is obtained once at a third preset time interval to obtain a water inlet historical data set; The water inlet historical data set is compared with the water inlet pressure data set to obtain a third comparison result.

4. A centrifugal pump fault online diagnosis method according to claim 3, characterized in that: Methods for obtaining the failure prediction probabilities of several different types of failures based on the comparison results include: Based on the first comparison result, a fault prediction probability of the second type of fault is obtained; Based on the second comparison result, the fault prediction probability of the third type of fault is obtained; Based on the third comparison result, the fault prediction probability of the fourth type of fault is obtained.

5. A centrifugal pump fault online diagnosis method according to claim 4, characterized in that: The calculation method of the failure prediction probability of the fourth type of failure is: Get the historical data set of the water inlet And the water inlet pressure data set collected in real time The Euclidean metric of the water inlet historical data set and the water inlet pressure data set is calculated by an algorithm based on the following formula: The Euclidean metric is set to the fault prediction probability of the fourth type of fault.

6. A centrifugal pump fault online diagnosis method according to claim 1, characterized in that: The method to obtain the vibration data of the centrifugal pump system is: A three-axis vibration sensor is arranged at the main motor of the centrifugal pump system, and data of the real-time vibration condition of the centrifugal pump system is collected based on the three-axis vibration sensor to obtain vibration data of the centrifugal pump system.

7. A centrifugal pump fault online diagnosis method according to claim 4, characterized in that: When the fault prediction probability exceeds the fault threshold, the method for reporting the fault type exceeding the fault threshold is: When the failure prediction probability of the first type of failure, the failure prediction probability of the second type of failure, the failure prediction probability of the third type of failure and the failure prediction probability of the fourth type of failure exceed their respective set warning thresholds, an alarm is issued for the failure result and the failure is reported.

8. An online diagnosis device for centrifugal pump faults, characterized in that: The centrifugal pump fault online diagnosis device comprises: A first vibration data set acquisition module is used to control the water inlet valve of the centrifugal pump system to open and start the vibration monitoring component; control the emptying pump of the centrifugal pump system to open and acquire a first vibration data set of the centrifugal pump system; A water inlet pressure data set and a second vibration data set acquisition module, used to acquire vacuum degree data of a centrifugal pump system, and when the vacuum degree reaches a vacuum threshold, control the emptying pump to be turned off and the centrifugal pump to be turned on; acquire a water inlet pressure data set and a second vibration data set of a centrifugal pump system; The water outlet pressure data set and current data set acquisition module is used to control the opening of the water outlet valve of the centrifugal pump system, and acquire the water outlet pressure data set of the centrifugal pump system and the current data set of the centrifugal pump operating current; A fault prediction probability acquisition module is used to compare the first vibration data set, the second vibration data set, the water inlet pressure data set, the water outlet pressure data set and the current data set acquired based on real-time monitoring with the corresponding normal data sets in the historical database, and obtain the fault prediction probabilities of several different types of faults based on the comparison results; The fault type reporting module is used to report the fault type that exceeds the fault threshold when the fault prediction probability exceeds the fault threshold.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the steps of the centrifugal pump fault online diagnosis method according to any one of claims 1 to 7.

10. A centrifugal pump fault online diagnosis system, characterized in that: When the system is running, the steps of the centrifugal pump fault online diagnosis method according to any one of claims 1 to 7 are executed.

Images