Mixed-flow pump fault early warning method, device, equipment, system and medium

Abstract

The invention relates to the technical field of fault early warning, in particular to a mixed-flow pump fault early warning method, device, equipment, system and medium, aiming at each preset acquisition position arranged on a mixed-flow pump, current data sets of the mixed-flow pump during load work are acquired, feature extraction is performed on each current data set in sequence, and the current data sets are acquired; the method comprises the following steps: acquiring vibration data of the mixed-flow pump, acquiring a fault data set of the mixed-flow pump, establishing a fault prediction model, inputting the fault data set into the fault prediction model, acquiring a fault prediction result of the mixed-flow pump, and performing fault early warning operation on the mixed-flow pump according to the fault prediction result, so that the method can perform vibration data acquisition on the mixed-flow pump during use; according to the method, the vibration data is collected, fault prediction is carried out according to the current data set composed of the collected vibration data, fault prediction operation is carried out on the mixed-flow pump through the fault prediction result obtained through prediction, fault prediction can be carried out on the mixed-flow pump, dependence on human experience is reduced, and fault prediction efficiency is improved. Fault prediction of the mixed-flow pump is not needed according to professional ability of analysis or prediction personnel.

Description

Technical Field

[0001] The present invention relates to the technical field of fault warning, and in particular to a mixed flow pump fault warning method, device, equipment, system and medium. Background Art

[0002] With the rapid development of industrial automation and intelligent manufacturing, mixed flow pump fault warning technology has become the key to ensure production continuity and improve efficiency. From the early simple vibration monitoring to the modern intelligent diagnosis system, the technology development path has undergone a transformation from mechanical and electrical to digital and intelligent. Early fault warning mainly depends on the operator's experience and regular maintenance inspections, while modern technology realizes real-time monitoring of the mixed flow pump status and fault warning through integrated sensors, data acquisition and analysis technology.

[0003] At present, the fault warning technology of mixed flow pump is mainly based on international standards such as "GB / T 6075.1-2012 Mechanical vibration - Measurement and evaluation of machine vibration on non-rotating parts" and "ISO10186 Mechanical vibration - Measurement and evaluation of mechanical vibration", and the working status is judged by monitoring the vibration intensity of the equipment. Vibration intensity, that is, the root mean square value of vibration velocity, is an important indicator for measuring the vibration energy of the unit. Although this method is simple to implement and can provide basic monitoring of equipment status, it has limitations in extracting fault information and cannot deeply analyze and predict potential faults. In addition, modern technology also relies on the collection of a large amount of equipment operation data, combined with signal processing technologies such as digital filtering, spectral analysis, and order analysis, and fault diagnosis is performed by professionals. Although this method can provide more detailed fault analysis, there are still some technical challenges.

[0004] The existing technology has a high reliance on human experience analysis results when performing fault analysis on mixed flow pumps, resulting in low fault identification efficiency. In addition, the accuracy is limited by the professional ability of the analyst, which affects the accuracy of fault identification. Summary of the invention

[0005] The main purpose of this application is to provide a mixed flow pump fault warning method, device, equipment, system and medium, aiming to solve the technical problem that when performing fault analysis on a mixed flow pump, the related technology has a high reliance on the results of human experience analysis, resulting in low fault identification efficiency, and the accuracy is limited by the professional ability of the analyst, affecting the accuracy of fault identification.

[0006] To achieve the above purpose, the present application proposes a mixed flow pump fault early warning method, comprising the following steps:

[0007] For each preset collection position set on the mixed flow pump, a current data set is collected when the mixed flow pump is working under load; wherein, the mixed flow pump is provided with a plurality of preset collection positions, and the current data set includes current vibration data corresponding to the preset collection positions at each working moment;

[0008] Extracting features from each of the current data sets in turn, and obtaining a fault data set of the mixed flow pump; wherein the fault data set includes the fault data of the corresponding preset acquisition position and the working time corresponding to the fault data;

[0009] A fault prediction model is established and the fault data set is input into the fault prediction model to obtain a fault prediction result of the mixed flow pump; wherein the fault prediction model is expressed using Formula 1, which is:

[0010]

[0011] L is the fault prediction result, N is the number of fault data sets, y i is the true label of the i-th sample, is the predicted probability of the i-th sample;

[0012] According to the fault prediction result, a fault warning operation is performed on the mixed flow pump.

[0013] In one embodiment, the step of establishing a fault prediction model and inputting the fault data set into the fault prediction model to obtain a fault prediction result of the mixed flow pump includes:

[0014] Establishing the fault prediction model;

[0015] The fault data set is input into the fault prediction model to perform fault prediction to obtain a fault prediction result of the mixed flow pump.

[0016] In one embodiment, the step of extracting features from each of the current data sets in sequence and obtaining the fault data set of the mixed flow pump includes:

[0017] Formula 2 is used to filter each of the current data sets in turn to extract features, and obtain the fault data set of the mixed flow pump; wherein the formula 2 is:

[0018]

[0019] P k|k =(Ik k H k ) k|k-1

[0020] K kis the Kalman gain, H k is the observation model, z k is the current dataset, is the predicted estimated value, is the updated estimate.

[0021] In one embodiment, the step of using Formula 2 to filter each of the current data sets in sequence to extract features and obtain the fault data set of the mixed flow pump includes:

[0022] Formula 2 is used to filter each of the current data sets in turn, and Formula 3 is used to perform abnormality detection on the current data set after feature extraction to obtain the fault data set of the mixed flow pump; wherein Formula 3 is:

[0023]

[0024] D is the fault data set, D i is the i-th current data set.

[0025] In one embodiment, the step of performing a fault warning operation on the mixed flow pump according to the fault prediction result includes:

[0026] According to the fault prediction result and the acquired fault type of the mixed flow pump, a fault warning operation is performed on the mixed flow pump; wherein the fault type includes an over-limit warning, an over-value warning of the change rate of each current data in the current data set corresponding to each preset collection position, and an over-value warning of the change trend of each current data in the current data set corresponding to each preset collection position.

[0027] In one embodiment, after the step of performing a fault warning operation on the mixed flow pump according to the fault prediction result and the acquired fault type of the mixed flow pump, the step further includes:

[0028] When any current data in the current data set exceeds a first preset value, the mixed flow pump is given an over-limit warning; wherein the first preset value is A, the vibration data corresponding to the mixed flow pump when performing initial load operation is B, and A≥1.5B;

[0029] When the difference between any two adjacent current data in the current data set is greater than a second preset value, the change rate over-value warning is issued to the mixed flow pump; wherein the second preset value is C, the target vibration data of any preset collection position corresponding to the mixed flow pump when performing initial load operation is D, the preset vibration data of the preset collection position corresponding to the mixed flow pump when performing no-load operation is E, and C=DE;

[0030] When the changing trend of all current data in the current data set at the working time does not meet the preset changing trend, the mixed flow pump will be given an over-value warning of the changing trend; wherein, the preset changing trend is the changing trend of the current data of each preset collection position corresponding to the mixed flow pump when the mixed flow pump is working at no load.

[0031] Based on the same technical concept, in a second aspect, the present invention also proposes a mixed flow pump fault warning device, comprising:

[0032] A data acquisition module, for acquiring a current data set of the mixed flow pump when the mixed flow pump is working under load for each preset acquisition position set on the mixed flow pump; wherein the mixed flow pump is provided with a plurality of preset acquisition positions, and the current data set includes current vibration data corresponding to the preset acquisition positions at each working moment;

[0033] A data processing module, used to extract features from each of the current data sets in turn, and obtain a fault data set of the mixed flow pump; wherein the fault data set includes the fault data of the corresponding preset acquisition position and the working time corresponding to the fault data;

[0034] A fault prediction module is used to establish a fault prediction model and input the fault data set into the fault prediction model to obtain a fault prediction result of the mixed flow pump; wherein the fault prediction model is expressed by formula 1, which is:

[0035]

[0036] L is the fault prediction result, N is the number of fault data sets, y i is the true label of the i-th sample, is the predicted probability of the i-th sample;

[0037] The early warning operation module is used to perform a fault early warning operation on the mixed flow pump according to the fault prediction result.

[0038] Based on the same technical concept, in the third aspect, the present invention also proposes a mixed flow pump fault warning device, which includes a processor and a memory, and a mixed flow pump fault warning program is stored in the memory. When the mixed flow pump fault warning program is executed by the processor, the mixed flow pump fault warning method described in the first aspect is implemented.

[0039] Based on the same technical concept, in a fourth aspect, the present invention further proposes a mixed flow pump fault warning system, comprising:

[0040] The mixed flow pump early warning device according to the third aspect; and

[0041] A data acquisition device is installed on the mixed flow pump, and the mixed flow pump early warning device is communicatively connected to the data acquisition device, and the mixed flow pump early warning device can control the data acquisition device to collect vibration data at each preset collection position of the mixed flow pump.

[0042] Based on the same technical concept, in the fifth aspect, the present invention further proposes a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by one or more processors, the mixed flow pump fault warning method described in the first aspect is implemented.

[0043] One or more technical solutions proposed in this application have at least the following technical effects:

[0044] The technical solution of the present application collects the current data set of the mixed flow pump when it is working under load at each preset collection position set on the mixed flow pump, extracts features of each current data set in turn, obtains the fault data set of the mixed flow pump, establishes a fault prediction model, inputs the fault data set into the fault prediction model and obtains the fault prediction result of the mixed flow pump, and performs fault warning operation on the mixed flow pump according to the fault prediction result, so that the present invention can collect vibration data of the mixed flow pump when in use, and predict faults according to the current data set composed of the collected vibration data, and performs fault prediction operation on the mixed flow pump using the predicted fault prediction result, thereby enabling the present invention to predict faults of the mixed flow pump, reducing the dependence on human experience, and eliminating the need to predict faults of the mixed flow pump based on the professional ability of the analysis or prediction personnel, thereby ensuring the accuracy of fault identification and prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0047] Figure 1 This is a flow chart of the mixed flow pump fault warning method of this application;

[0048] Figure 2 This is a flowchart of step S300 of this application example;

[0049] Figure 3 This is a flowchart of step S400 of this application example;

[0050] Figure 4 This is a schematic diagram of the structure of the mixed flow pump fault warning device used as an example in this application.

[0051] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0052] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0053] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0054] The main solution of the embodiment of the present application is: for each preset collection position set on the mixed flow pump, the current data set of the mixed flow pump when it is working under load is collected, and features are extracted for each current data set in turn to obtain a fault data set of the mixed flow pump, a fault prediction model is established and the fault data set is input into the fault prediction model to obtain a fault prediction result of the mixed flow pump, and a fault warning operation is performed on the mixed flow pump according to the fault prediction result, so that the present invention can collect vibration data of the mixed flow pump when in use, and perform fault prediction based on the current data set composed of the collected vibration data, and perform fault prediction on the mixed flow pump using the predicted fault prediction result.

[0055] In the prior art, when performing fault analysis on a mixed flow pump, a vibration monitoring device is usually used to perform vibration monitoring and vibration data collection on structures such as the upper frame, lower frame, rotating bearing and connecting bearing on the mixed flow pump. After data collection, an artificial fault analysis is performed based on the collected vibration data. When performing artificial fault analysis, there is a high dependence on the results of artificial experience analysis, resulting in low fault identification efficiency, and the accuracy is limited by the professional ability of the analyst, affecting the fault identification efficiency.

[0056] The present application provides a solution, by collecting the current data set of the mixed flow pump when it is working under load at each preset collection position set on the mixed flow pump, extracting features of each current data set in turn, and obtaining a fault data set of the mixed flow pump, establishing a fault prediction model and inputting the fault data set into the fault prediction model to obtain a fault prediction result of the mixed flow pump, and performing a fault warning operation on the mixed flow pump according to the fault prediction result, so that the present invention can collect vibration data of the mixed flow pump when in use, and perform fault prediction based on the current data set composed of the collected vibration data, and perform a fault prediction operation on the mixed flow pump using the predicted fault prediction result, thereby enabling the present invention to perform fault prediction on the mixed flow pump, reducing dependence on human experience, and eliminating the need to predict faults of the mixed flow pump based on the professional ability of analysis or prediction personnel, thereby ensuring the accuracy of fault identification and prediction.

[0057] The present embodiment and the following embodiments are described below by taking a computer device capable of running the mixed flow pump fault warning method of the present invention as an example of an execution subject.

[0058] Based on this, see Figures 1 to 4 The present application proposes a mixed flow pump fault warning method of the first embodiment, comprising the following steps:

[0059] S100. For each preset collection position set on the mixed flow pump, collect a current data set of the mixed flow pump when it is working under load; wherein, the mixed flow pump is provided with a plurality of preset collection positions, and the current data set includes current vibration data corresponding to the preset collection positions at each working moment.

[0060] In this embodiment, when it is specifically implemented, it is first necessary to set multiple preset collection positions on the mixed flow pump. When setting the preset collection positions, the specific positions of the upper frame, the lower frame, the water guide bearing and the coupling in the mixed flow pump can be determined first, and then at least one preset collection position is set on the upper frame, the lower frame, the water guide bearing and the coupling respectively, and then a vibration data collection device is set at each preset collection position, and the vibration data collection device is used to collect vibration data.

[0061] In this embodiment, the vibration data acquisition device of the example is preferably a three-way temperature vibration sensor, and the preset acquisition position of the example is the best acquisition position when collecting vibration data of the upper frame, lower frame, water-guide bearing and coupling in the mixed flow pump. More specifically, the best acquisition position of the example refers to the position for collecting data on the upper frame, lower frame, water-guide bearing and coupling in the mixed flow pump. More specifically, the best acquisition position on the upper frame is the outer edge position of the upper frame, the best acquisition position on the lower frame is the outer edge position of the lower frame, the best acquisition position on the water-guide bearing is the outer edge position of the water-guide bearing, and the best acquisition position on the coupling is the outer periphery of the shaft of the coupling. In this embodiment, the acquisition process of the current data set of the example is:

[0062] When the mixed flow pump is working under load, the vibration data collection device is used to collect vibration data, and the vibration data collection device collects vibration data at each working moment, and the collected vibration data is sorted according to the data collection time to form a current data set.

[0063] S200, extracting features from each of the current data sets in turn, and obtaining a fault data set of the mixed flow pump; wherein the fault data set includes the fault data of the corresponding preset acquisition position and the working time corresponding to the fault data;

[0064] In this embodiment, when extracting features from each current data set, firstly, Formula 2 is used to extract features from the collected current data set to obtain a fault data set of the mixed flow pump. The exemplary Formula 2 is:

[0065]

[0066] P k|k =(Ik k H k ) k|k-1

[0067] K k is the Kalman gain, H k is the observation model, z k is the current dataset, is the predicted estimated value, is the updated estimate.

[0068] Furthermore, when extracting fault features, Formula 3 is used to perform abnormal detection on the fault features to achieve the function of fault detection. The example Formula 3 is:

[0069]

[0070] D is the fault data set, D iis the i-th current data set.

[0071] In this embodiment, by performing feature extraction on the current data set to obtain a corresponding fault data set, the present invention can determine the fault data set.

[0072] S300, establishing a fault prediction model and inputting the fault data set into the fault prediction model to obtain a fault prediction result of the mixed flow pump; wherein the fault prediction model is expressed by Formula 1, which is:

[0073]

[0074] L is the fault prediction result, N is the number of fault data sets, y i is the true label of the i-th sample, is the predicted probability of the i-th sample;

[0075] In this embodiment, when performing fault prediction, the fault data set is input into Formula 1 to achieve the function of fault prediction.

[0076] S400: Perform a fault warning operation on the mixed flow pump according to the fault prediction result.

[0077] In this embodiment, by collecting the current data set of the mixed flow pump when it is working under load at each preset collection position set on the mixed flow pump, feature extraction is performed on each current data set in turn, and a fault data set of the mixed flow pump is obtained, a fault prediction model is established, and the fault data set is input into the fault prediction model to obtain a fault prediction result of the mixed flow pump, and a fault warning operation is performed on the mixed flow pump according to the fault prediction result, so that the present invention can collect vibration data of the mixed flow pump when in use, and perform fault prediction based on the current data set composed of the collected vibration data, and perform fault prediction on the mixed flow pump using the predicted fault prediction result, thereby enabling the present invention to perform fault prediction on the mixed flow pump, reducing dependence on human experience, and eliminating the need to predict faults of the mixed flow pump based on the professional ability of analysis or prediction personnel, thereby ensuring the accuracy of fault identification and prediction.

[0078] In one embodiment, step S300 includes:

[0079] S310, establishing the fault prediction model;

[0080] S320: Input the fault data set into the fault prediction model to perform fault prediction to obtain a fault prediction result of the mixed flow pump.

[0081] In this embodiment, a fault prediction model is established and a fault data set is input into the fault prediction model to obtain a fault prediction result of the mixed flow pump, so that the present invention can realize the function of fault prediction when used.

[0082] In one embodiment, step S200 includes:

[0083] Formula 2 is used to filter each of the current data sets in turn to extract features, and obtain the fault data set of the mixed flow pump; wherein the formula 2 is:

[0084]

[0085] P k|k =(Ik k H k ) k|k-1

[0086] K k is the Kalman gain, H k is the observation model, z k is the current dataset, is the predicted estimated value, is the updated estimate.

[0087] In one embodiment, the step of using Formula 2 to filter each of the current data sets in turn to extract features and obtain the fault data set of the mixed flow pump includes:

[0088] Formula 2 is used to filter each of the current data sets in turn, and Formula 3 is used to perform abnormality detection on the current data set after feature extraction to obtain the fault data set of the mixed flow pump; wherein Formula 3 is:

[0089]

[0090] D is the fault data set, D i is the i-th current data set.

[0091] In this embodiment, each current data set is filtered and Formula 3 is detected for anomalies, thereby being able to filter out fault data from the current data set, thereby ensuring the efficiency and accuracy of filtering out fault data from the current data set.

[0092] It should be noted that, in this embodiment, when performing abnormality detection, a standard data is first set, and then each data in the current data set is compared with the standard data, and it is determined whether the compared data is higher than the standard data. If it is higher than the standard data, the corresponding data is used as fault data.

[0093] It can be further clarified that, in this embodiment, the exemplary process of obtaining standard data is: when the mixed flow pump is operating at no-load, vibration data collection is performed for each preset collection position, and the collected vibration data is used as standard data.

[0094] In one embodiment, step S400 includes:

[0095] S410. Perform fault warning operation on the mixed flow pump according to the fault prediction result and the acquired fault type of the mixed flow pump; wherein the fault type includes over-limit warning, over-value warning of the change rate of each current data in the current data set corresponding to each preset collection position, and over-value warning of the change trend of each current data in the current data set corresponding to each preset collection position.

[0096] In this embodiment, when performing a fault warning operation on the mixed flow pump, it can be determined whether the vibration data is greater than the standard data, or whether the change value of any two adjacent current data in the current data set meets the preset change value, or whether the difference between any two adjacent current data in the current data set is greater than the preset difference. When the corresponding judgment conditions are met, the corresponding fault warning operation is performed.

[0097] It should be particularly and clearly stated that, in this embodiment, the process of obtaining the preset change value is as follows:

[0098] When the mixed flow pump is in no-load operation, vibration data is collected for each preset collection position to obtain preset vibration data; then when the mixed flow pump is in initial load operation, vibration data is collected for each preset collection position to obtain corresponding initial vibration data, and the collected initial vibration data is subtracted from the preset vibration data to obtain a preset difference. At the same time, the initial vibration data and the preset vibration data are sorted to obtain the corresponding preset change value.

[0099] In one embodiment, after step S410, the method further includes:

[0100] S420. When any current data in the current data set exceeds a first preset value, the mixed flow pump is given an over-limit warning; wherein the first preset value is A, and the vibration data corresponding to the mixed flow pump when performing initial load operation is B, and A≥1.5B.

[0101] S430. When the difference between any two adjacent current data in the current data set is greater than a second preset value, the mixed flow pump is given an over-value warning of the rate of change; wherein the second preset value is C, the target vibration data of any preset collection position corresponding to the mixed flow pump when it is performing initial load operation, the target vibration data is D, the preset vibration data of the preset collection position corresponding to the mixed flow pump when it is performing no-load operation, the preset vibration data is E, and C=DE.

[0102] S440. When the changing trend of all current data in the current data set at the working time does not meet the preset changing trend, an over-value warning of the changing trend is issued to the mixed flow pump; wherein, the preset changing trend is the changing trend of the current data of each preset collection position corresponding to the mixed flow pump when the mixed flow pump is working at no load.

[0103] Based on the same technical concept, in a second aspect, the present invention also proposes a mixed flow pump fault warning device, comprising:

[0104] A data acquisition module, for acquiring a current data set of the mixed flow pump when the mixed flow pump is working under load for each preset acquisition position set on the mixed flow pump; wherein the mixed flow pump is provided with a plurality of preset acquisition positions, and the current data set includes current vibration data corresponding to the preset acquisition positions at each working moment;

[0105] A data processing module, used to extract features from each of the current data sets in turn, and obtain a fault data set of the mixed flow pump; wherein the fault data set includes the fault data of the corresponding preset acquisition position and the working time corresponding to the fault data;

[0106] A fault prediction module is used to establish a fault prediction model and input the fault data set into the fault prediction model to obtain a fault prediction result of the mixed flow pump; wherein the fault prediction model is expressed by formula 1, which is:

[0107]

[0108] L is the fault prediction result, N is the number of fault data sets, y i is the true label of the i-th sample, is the predicted probability of the i-th sample;

[0109] The early warning operation module is used to perform a fault early warning operation on the mixed flow pump according to the fault prediction result.

[0110] The mixed flow pump fault warning device provided by the present application adopts the mixed flow pump fault warning method in the above embodiment, which can solve the technical problem that when performing fault analysis on the mixed flow pump, there is a high reliance on the results of human experience analysis, resulting in low fault identification efficiency, and the accuracy is limited by the professional ability of the analyst, which affects the accuracy of fault identification. Compared with the prior art, the beneficial effects of the mixed flow pump fault warning device provided by the present application are the same as the beneficial effects of the mixed flow pump fault warning method provided by the above embodiment, and the other technical features in the mixed flow pump fault warning device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0111] Based on the same technical concept, in the third aspect, the present invention also proposes a mixed flow pump fault warning device, which includes a processor and a memory, and a mixed flow pump fault warning program is stored in the memory. When the mixed flow pump fault warning program is executed by the processor, the mixed flow pump fault warning method described in the first aspect is implemented.

[0112] The mixed flow pump fault warning device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. The mixed flow pump fault warning device shown in the present invention is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0113] The mixed flow pump fault warning device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. Various programs and data required for the operation of the mixed flow pump fault warning device are also stored in the RAM 1004. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the mixed flow pump fault warning device to communicate wirelessly or wired with other devices to exchange data. Although the mixed flow pump fault warning device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0114] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0115] The mixed flow pump fault warning device provided by the present application adopts the mixed flow pump fault warning method in the above embodiment, which can solve the technical problem that when performing fault analysis on the mixed flow pump, there is a high reliance on the results of human experience analysis, resulting in low fault identification efficiency, and the accuracy is limited by the professional ability of the analyst, which affects the accuracy of fault identification. Compared with the prior art, the beneficial effects of the mixed flow pump fault warning device provided by the present application are the same as the beneficial effects of the mixed flow pump fault warning method provided by the above embodiment, and the other technical features in the mixed flow pump fault warning device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0116] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0117] In addition, the mixed flow pump fault warning device provided in the embodiment of the present application can solve the technical problem that when performing fault analysis on the mixed flow pump, there is a high reliance on the results of human experience analysis, resulting in low fault identification efficiency, and the accuracy is limited by the professional ability of the analyst, which affects the accuracy of fault identification. Compared with the prior art, the beneficial effects of the mixed flow pump fault warning device provided in the embodiment of the present application are the same as the beneficial effects of the mixed flow pump fault warning method provided in the above embodiment, and other technical features in the engineering machinery are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0118] Based on the same technical concept, in a fourth aspect, the present invention further proposes a mixed flow pump fault warning system, comprising:

[0119] The mixed flow pump early warning device according to the third aspect; and

[0120] A data acquisition device is installed on the mixed flow pump, and the mixed flow pump early warning device is communicatively connected to the data acquisition device, and the mixed flow pump early warning device can control the data acquisition device to collect vibration data at each preset collection position of the mixed flow pump.

[0121] The mixed flow pump fault warning system provided by the present application adopts the mixed flow pump fault warning method in the above embodiment, which can solve the technical problem that when performing fault analysis on the mixed flow pump, there is a high reliance on the results of human experience analysis, resulting in low fault identification efficiency, and the accuracy is limited by the professional ability of the analyst, which affects the accuracy of fault identification. Compared with the prior art, the beneficial effects of the mixed flow pump fault warning system provided by the present application are the same as the beneficial effects of the mixed flow pump fault warning method provided by the above embodiment, and the other technical features in the mixed flow pump fault warning device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0122] Based on the same technical concept, in the fifth aspect, the present invention further proposes a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by one or more processors, the mixed flow pump fault warning method described in the first aspect is implemented.

[0123] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0124] The computer-readable storage medium may be included in the mixed flow pump fault warning device; or may exist independently without being assembled into the mixed flow pump fault warning device.

[0125] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the mixed flow pump fault warning device, the mixed flow pump fault warning device can implement the mixed flow pump fault warning method described above.

[0126] The computer program code for performing the operation of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0127] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0128] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0129] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned mixed flow pump fault warning method, and can solve the technical problems that when performing fault analysis on the mixed flow pump, there is a high dependence on the results of human experience analysis, resulting in low fault identification efficiency, and the accuracy is limited by the professional ability of the analyst, which affects the accuracy of fault identification. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the mixed flow pump fault warning method provided by the above-mentioned embodiment, which will not be repeated here.

[0130] The present application also provides a computer program product, including a computer program, which implements the steps of the mixed flow pump fault warning method as described above when the computer program is executed by a processor.

[0131] The computer program product provided by the present application can solve the technical problems that when performing fault analysis on a mixed flow pump, there is a high reliance on the results of human experience analysis, resulting in low fault identification efficiency, and the accuracy is limited by the professional ability of the analyst, which affects the accuracy of fault identification. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the mixed flow pump fault warning method provided by the above embodiment, and will not be elaborated here.

[0132] The above are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A mixed flow pump fault early warning method, characterized in that: The steps include: For each preset collection position set on the mixed flow pump, a current data set is collected when the mixed flow pump is working under load; wherein, the mixed flow pump is provided with a plurality of preset collection positions, and the current data set includes current vibration data corresponding to the preset collection positions at each working moment; Extracting features from each of the current data sets in turn, and obtaining a fault data set of the mixed flow pump; wherein the fault data set includes the fault data of the corresponding preset acquisition position and the working time corresponding to the fault data; A fault prediction model is established and the fault data set is input into the fault prediction model to obtain a fault prediction result of the mixed flow pump; wherein the fault prediction model is expressed using Formula 1, which is: L is the fault prediction result, N is the number of fault data sets, y i is the true label of the i-th sample, is the predicted probability of the i-th sample; According to the fault prediction result, a fault warning operation is performed on the mixed flow pump.

2. The mixed flow pump fault early warning method according to claim 1, characterized in that: The step of establishing a fault prediction model and inputting the fault data set into the fault prediction model to obtain a fault prediction result of the mixed flow pump comprises: Establishing the fault prediction model; The fault data set is input into the fault prediction model to perform fault prediction to obtain a fault prediction result of the mixed flow pump.

3. The mixed flow pump fault early warning method according to claim 2, characterized in that: The step of extracting features from each of the current data sets in sequence and obtaining the fault data set of the mixed flow pump comprises: Formula 2 is used to filter each of the current data sets in turn to extract features, and obtain the fault data set of the mixed flow pump; wherein the formula 2 is: P k|k =(I-k k H k )P k|k-1 K k is the Kalman gain, H k is the observation model, z k is the current dataset, is the predicted estimated value, is the updated estimate.

4. The mixed flow pump fault early warning method according to claim 3, characterized in that: The step of using Formula 2 to filter each of the current data sets in turn to extract features and obtain the fault data set of the mixed flow pump includes: Formula 2 is used to filter each of the current data sets in turn, and Formula 3 is used to perform abnormality detection on the current data set after feature extraction to obtain the fault data set of the mixed flow pump; wherein Formula 3 is: D is the fault data set, D i is the i-th current data set.

5. The mixed flow pump fault early warning method according to any one of claims 1 to 4, characterized in that: The step of performing a fault warning operation on the mixed flow pump according to the fault prediction result comprises: According to the fault prediction result and the acquired fault type of the mixed flow pump, a fault warning operation is performed on the mixed flow pump; wherein the fault type includes an over-limit warning, an over-value warning of the change rate of each current data in the current data set corresponding to each preset collection position, and an over-value warning of the change trend of each current data in the current data set corresponding to each preset collection position.

6. The mixed flow pump fault early warning method according to claim 5, characterized in that: After the step of performing a fault warning operation on the mixed flow pump according to the fault prediction result and the acquired fault type of the mixed flow pump, the method further includes: When any current data in the current data set exceeds a first preset value, the mixed flow pump is given an over-limit warning; wherein the first preset value is A, the vibration data corresponding to the mixed flow pump when performing initial load operation is B, and A≥1.5B; When the difference between any two adjacent current data in the current data set is greater than a second preset value, the change rate over-value warning is issued to the mixed flow pump; wherein the second preset value is C, the target vibration data of any preset collection position corresponding to the mixed flow pump when performing initial load operation is D, the preset vibration data of the preset collection position corresponding to the mixed flow pump when performing no-load operation is E, and C=DE; When the changing trend of all current data in the current data set at the working time does not meet the preset changing trend, the mixed flow pump will be given an over-value warning of the changing trend; wherein, the preset changing trend is the changing trend of the current data of each preset collection position corresponding to the mixed flow pump when the mixed flow pump is working at no load.

7. A mixed flow pump fault warning device, characterized in that: include: A data acquisition module, for acquiring a current data set of the mixed flow pump when the mixed flow pump is working under load for each preset acquisition position set on the mixed flow pump; wherein the mixed flow pump is provided with a plurality of preset acquisition positions, and the current data set includes current vibration data corresponding to the preset acquisition positions at each working moment; A data processing module, used to extract features from each of the current data sets in turn, and obtain a fault data set of the mixed flow pump; wherein the fault data set includes the fault data of the corresponding preset acquisition position and the working time corresponding to the fault data; A fault prediction module is used to establish a fault prediction model and input the fault data set into the fault prediction model to obtain a fault prediction result of the mixed flow pump; wherein the fault prediction model is expressed by formula 1, which is: L is the fault prediction result, N is the number of fault data sets, y i is the true label of the i-th sample, is the predicted probability of the i-th sample; The early warning operation module is used to perform a fault early warning operation on the mixed flow pump according to the fault prediction result.

8. A mixed flow pump fault warning device, characterized in that: The mixed flow pump fault warning device includes a processor and a memory, wherein a mixed flow pump fault warning program is stored in the memory, and when the mixed flow pump fault warning program is executed by the processor, the mixed flow pump fault warning method according to any one of claims 1 to 6 is implemented.

9. A mixed flow pump fault warning system, characterized in that: include: The mixed flow pump early warning device according to claim 8; as well as, A data acquisition device is installed on the mixed flow pump, and the mixed flow pump early warning device is communicatively connected to the data acquisition device, and the mixed flow pump early warning device can control the data acquisition device to collect vibration data at each preset collection position of the mixed flow pump.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by one or more processors, the mixed flow pump fault warning method according to any one of claims 1 to 6 is implemented.

Images