An integrated pump station winding fault diagnosis method and fault diagnosis system

Abstract

The present invention provides an integrated pump station winding fault diagnosis method and fault diagnosis system, including a sensor assembly, a control system and an early warning system; the sensor assembly includes a flow sensor, a pressure sensor, a speed torque sensor and a vibration sensor; the flow sensor is used to detect the flow at the outlet of the sewage pump; the pressure sensor is used to detect the pressure at the inlet and outlet of the sewage pump; the speed torque sensor is used to detect the torque and speed output by the pump shaft; the vibration sensor is used to detect the vibration of the pump casing; the control system determines the fault type and the stage of the winding fault according to the signal collected by the sensor assembly. The early warning system sends different early warning signals according to the fault type and the stage of the winding fault. The present invention makes efficient and accurate judgments on the fault type, and at the same time diagnoses and monitors the development stage of the winding fault of the integrated pump station based on the characteristic data of different fault stages.

Description

Technical Field

[0001] The present invention relates to the technical field of hydraulic machinery fault diagnosis, and in particular to an integrated pump station winding fault diagnosis method and a fault diagnosis system. Background Art

[0002] With the continuous development of the modern pump industry, the research on the basic theory of water pumps, the improvement of water pump performance and the design of water pump solutions have been continuously improved. The corresponding level of intelligent monitoring technology for water pumps also needs to be continuously improved to meet the needs of the modern pump industry.

[0003] Pump monitoring mainly describes its characteristics through technical indicators such as flow, head, shaft power, efficiency, and speed. In view of the small footprint of the integrated pump station and the limited sensors used, the use of soft measurement technology can effectively save the internal space of the pump station. Using soft measurement technology to monitor pumps and pump stations can solve the problem that the quantity to be measured cannot be directly measured by sensors in some cases, and can effectively save costs.

[0004] Trash racks can intercept larger floating objects in sewage, but it is difficult to avoid smaller floating objects, especially flexible winding objects, entering the pump, and may entangle the pump shaft and cause failure. Pump winding failure will lead to reduced pump head, reduced speed and torque, and even cause the pump to get stuck. Therefore, monitoring pump winding failure can help detect the failure early and avoid more serious consequences.

[0005] At present, there are some existing monitoring and diagnosis methods for mechanical faults. The prior art discloses "a rotating machinery fault monitoring system", which includes a sensor, a judgment module, a data processing and display warning module, and can judge the state of the rotating machinery shaft by analyzing vibration and speed signals. However, this method can only judge whether the shaft is working properly and cannot judge the specific fault. The prior art discloses "a method for monitoring the fault of rotating engineering machinery", which uses a speed sensor and a pressure sensor to monitor the operating state of the main shaft and the eccentric wheel, and combines the mechanical vibration signal to judge whether the rotating machinery is faulty. It can perform real-time fault monitoring of the machinery, but this method needs to compare the data with the preset parameter data, which is inefficient.

[0006] Most of the currently applicable fault diagnosis methods are multi-signal acquisition and single signal comparison methods, and it is difficult to monitor specific faults. After the monitoring system recognizes the existence of a fault, it cannot inform the fault development stage, and the staff needs to participate again to manually identify the fault and give a maintenance strategy, which is inefficient. In addition, the fault identification of the existing technology cannot distinguish winding faults, and winding faults vary with the stage of the pump operation fault, which brings difficulties to identification. Summary of the invention

[0007] In view of the deficiencies in the prior art, the present invention provides an integrated pump station entanglement fault diagnosis method and fault diagnosis system, which monitors the torque, speed, pressure, and flow parameters of the integrated pump station and analyzes the evolution laws of each parameter to judge the entanglement fault and identify and distinguish the fault development stages.

[0008] The present invention achieves the above technical objectives through the following technical means.

[0009] An integrated pump station winding fault diagnosis method comprises the following steps:

[0010] Data collection: at least one sensor is used to collect the flow rate at the sewage pump outlet, the pressure at the sewage pump inlet and outlet, the torque and speed output by the pump shaft, the current of the motor and the vibration of the pump casing;

[0011] Data preprocessing: The processed data is used to establish the flow signal feature set {Q0, Q1} and the pressure signal feature set {P 01 , P 02 , P1, P2}, the torque signal feature set is {T0, T1}, the speed signal feature set is {n0, n1}, the current signal feature set is {I0, I1} and the vibration signal time domain signal feature set is {F0, F1};

[0012] Among them: {Q0} is the flow set in normal operation; {Q1} is the real-time monitoring flow set; {P 01 , P 02} are respectively the sewage pump inlet pressure set and the sewage pump outlet pressure set under normal operation; {P1, P2} are respectively the real-time monitoring sewage pump inlet pressure set and the real-time monitoring sewage pump outlet pressure set; {n0} is the speed set under normal operation; {n1} is the real-time monitoring speed set; {T0} is the torque set under normal operation; {T1} is the real-time monitoring torque set; {I0} is the current set under normal operation; {I1} is the real-time monitoring current set; {F0} is the vibration time domain set under normal operation; {F1} is the real-time monitoring vibration time domain set;

[0013] Fault diagnosis: Determine whether it is a winding fault, cavitation fault or blade fault based on the current signal feature set and the vibration signal time domain signal feature set. Specifically:

[0014] When 0 <T rmsi ≤0.005, the pump station is in normal operation; when 0.005 <T rmsi ≤0.01, the pump station is in winding fault; when 0.01 <T rmsi ≤0.1, the pump station is in blade failure; when 0.1 <T rmsi When ≤1, the pump station is in cavitation failure;

[0015] When 0 < T rmsF ≤ 0.3, the pumping station is in normal operation; when 0.3 < T rmsF ≤ 0.45, the pumping station is in a winding fault; when 0.45 < T rmsF ≤ 0.6, the pumping station is in a cavitation fault; when 0.6 < T rmsF ≤ 0.75, the pumping station is in a vane fault;

[0016] where T rmsi is the root mean square of the current within the sampling period; T rmsF is the root mean square of the vibration within the sampling period.

[0017] Furthermore, in the fault diagnosis, when the judgment results of the current signal feature set and the torque signal feature set conflict, if T rmsF < 0.55 and T rmsi < 0.025, the pumping station is in a winding fault; if 0.35 < T rmsF < 0.55 and 0.025 < T rmsi < 1, the pumping station is in a cavitation fault; if 0.55 < T rmsF < 0.75 and 0.006 < T rmsi < 1, the pumping station is in a vane fault.

[0018] Furthermore, when the fault diagnosis determines that it is in a winding fault, determine the stage of the winding fault according to the flow signal feature set, the pressure signal feature set, the torque signal feature set and the speed signal feature set, specifically:

[0019] When Q1 < Q0, and 0 < H1 < H0, and 0 < n1 < n0, and 0 < T1 < (0.75 - 1)T0, the winding fault is in stage I;

[0020] When Q1 < Q0, and H1 < 0, and 0 < n1 < n0, and 0 < T1 < T0, the winding fault is in stage II;

[0021] When Q1 < Q0, and H1 < 0, and 0 < n1 < n0, and T1 < 0, the winding fault is in stage III;

[0022] When Q1 < Q0, and H1 < 0, and n1 = 0, and T1 < 0, the winding fault is in stage IV, where H1 is the actual head of the sewage pump determined according to {P1, P2}; H0 is the head of the sewage pump under normal operation determined according to {P 01 , P02}.

[0023] Furthermore, the actual head H1 of the sewage pump determined according to {P1, P2} is specifically:

[0024]

[0025] Where:

[0026] H1—actual head of sewage pump, m;

[0027] P1—sewage pump inlet pressure, Pa;

[0028] P2—sewage pump outlet pressure, Pa;

[0029] c—pump inlet and outlet flow rates, m / s;

[0030] z out —Sewage pump outlet height, m;

[0031] z in —Sewage pump inlet height, m;

[0032] ρ—Liquid density, kg / m 3 ;

[0033] g—neutral acceleration, m / s 2 .

[0034] Furthermore, in the fault diagnosis, the current RMS T rmsi and the vibration root mean square T during the sampling period rmsF , specifically:

[0035]

[0036]

[0037] In the formula,

[0038] N—collection number;

[0039] x i-I —The current signal value collected at time i;

[0040] x i-F —The vibration signal value collected at time i.

[0041] A diagnostic system for an integrated pump station winding fault diagnostic method, comprising a sensor assembly, a control system and an early warning system;

[0042] The sensor assembly includes a flow sensor, a first pressure sensor, a second pressure sensor, a speed torque sensor and a vibration sensor; the flow sensor is used to detect the flow at the outlet of the sewage pump; the first pressure sensor is used to detect the pressure at the inlet of the sewage pump; the second pressure sensor is used to detect the pressure at the outlet of the sewage pump; the speed torque sensor is used to detect the torque and speed output by the pump shaft; the vibration sensor is used to detect the vibration of the pump housing;

[0043] The control system determines the fault type and the stage of the winding fault according to the signal collected by the sensor assembly.

[0044] The early warning system sends out different early warning signals according to the fault type and the stage of the winding fault.

[0045] The beneficial effects of the present invention are:

[0046] 1. The integrated pump station winding fault diagnosis method and fault diagnosis system described in the present invention can quickly and accurately identify winding faults by detecting two physical quantities, current and vibration, according to the relationship between various parameters during actual operation.

[0047] 2. The integrated pump station winding fault diagnosis method and fault diagnosis system described in the present invention detects flow, pressure, speed and torque, and according to the relationship between various parameters during actual operation, comprehensively judges the stage of fault development for different operating states. Maintenance personnel can give different response strategies for different stages.

[0048] 3. The integrated pump station winding fault diagnosis method and fault diagnosis system described in the present invention provide a solution when the judgment results of a single current signal feature set and a torque signal feature set conflict, thereby ensuring the accuracy of fault judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention 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. The drawings described below are some embodiments of the present invention. For ordinary technicians in this field, it is obvious that other drawings can be obtained based on these drawings without paying any creative work.

[0050] Figure 1 It is a schematic diagram of the integrated pump station winding fault diagnosis system described in the present invention.

[0051] Figure 2 The present invention is a flowchart of the integrated pump station winding fault diagnosis method.

[0052] Figure 3 is the RMS value of the real-time monitoring signal of the current, where a is the signal collected during winding fault; b is the signal collected during blade fault; c is the signal collected during cavitation fault;

[0053] Figure 4 is the root mean square value of the vibration real-time monitoring signal, where a is the signal collected during winding fault; b is the signal collected during cavitation fault; c is the signal collected during blade fault;

[0054] Figure 5Scatter plots of feature-level fusion for vibration and current signals;

[0055] Figure 6 It is a signal curve diagram at different winding stages.

[0056] In the figure:

[0057] 1-valve; 2-sewage pump inlet; 3-sewage pump outlet; 4-pump shaft; 5-motor; 6-pump housing; DETAILED DESCRIPTION

[0058] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0059] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "axial", "radial", "vertical", "horizontal", "inner", "outer" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0060] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0061] like Figure 1 As shown, the diagnostic system of the integrated pump station winding fault diagnostic method of the present invention includes a sensor component, a control system and an early warning system; the integrated pump station includes a sewage pump and an outlet valve 1;

[0062] The sensor assembly includes a flow sensor, a first pressure sensor, a second pressure sensor, a speed torque sensor and a vibration sensor; the flow sensor is used to detect the flow at the sewage pump outlet 3; the first pressure sensor is used to detect the pressure at the sewage pump inlet 2; the second pressure sensor is used to detect the pressure at the sewage pump outlet 3; the speed torque sensor is used to detect the torque and speed output by the pump shaft 4; the vibration sensor is used to detect the vibration of the pump housing 6; the control system determines the type of fault and the stage of the winding fault based on the signal collected by the sensor assembly; the early warning system sends different early warning signals according to the type of fault and the stage of the winding fault.

[0063] The control system can match the processing solutions in the historical data in the database according to different early warning signals, and the control system transmits the processing solutions to the system of the maintenance personnel.

[0064] like Figure 2 As shown, the integrated pump station winding fault diagnosis method of the present invention comprises the following steps:

[0065] Data collection: The flow rate of the sewage pump outlet 3, the pressure of the sewage pump inlet 2 and the sewage pump outlet 3, the torque and speed output by the pump shaft 4, the current of the motor 5 and the vibration of the pump housing 6 are collected respectively by at least one sensor;

[0066] Data preprocessing: The processed data is used to establish the flow signal feature set {Q0, Q1} and the pressure signal feature set {P 01 , P 02 , P1, P2}, the torque signal feature set is {T0, T1}, the speed signal feature set is {n0, n1}, the current signal feature set is {I0, I1} and the vibration signal time domain signal feature set is {F0, F1};

[0067] Among them: {Q0} is the flow set in normal operation; {Q1} is the real-time monitoring flow set; {P 01 , P 02} are respectively the pressure set of sewage pump inlet 2 and the pressure set of sewage pump outlet 3 under normal operation; {P1, P2} are respectively the real-time monitoring pressure set of sewage pump inlet 2 and the real-time monitoring pressure set of sewage pump outlet 3; {n0} is the speed set under normal operation; {n1} is the real-time monitoring speed set; {T0} is the torque set under normal operation; {T1} is the real-time monitoring torque set; {I0} is the current set under normal operation; {I1} is the real-time monitoring current set; {F0} is the vibration time domain set under normal operation; {F1} is the real-time monitoring vibration time domain set;

[0068] The average value of the data collected during the normal operation of the integrated pump station is taken as Q0, T0, n0, H0

[0069] Fault diagnosis: Determine whether it is a winding fault, cavitation fault or blade fault based on the current signal feature set and the vibration signal time domain signal feature set. Specifically:

[0070] The vibration signal and current signal are used as key signals for discrimination: when a winding fault occurs, the shaft power increases while the flow rate and head decrease, and the pressure fluctuation is small; when a cavitation fault occurs, the vibration signal is instantly enhanced, causing the change of the vibration signal peak value, and the pressure pulsation will increase accordingly, and the hydraulic load torque with the blade passing frequency as the base frequency will also increase; when a blade fault occurs, the energy intensity of the vibration signal changes significantly. At this time, the occurrence of the fault causes different forces at each position, so there are certain differences in the vibration signal intensity measured at different positions.

[0071] Therefore, for the current signal, when 0 <T rmsi ≤0.005, the pump station is in normal operation; when 0.005 <T rmsi ≤0.01, the pump station is in winding fault; when 0.01 <T rmsi ≤0.1, the pump station is in blade failure; when 0.1 <T rmsi When ≤1, the pump station is in cavitation failure;

[0072] For vibration signal, when 0 <T rmsF ≤0.3, the pump station is in normal operation; when 0.3 <T rmsF ≤0.45, the pump station is in winding fault; when 0.45 <T rmsF ≤0.6, the pump station is in cavitation failure; when 0.6 <T rmsF When ≤0.75, the pump station is in blade failure;

[0073] Where T rmsi is the RMS current during the sampling period; T rmsF is the root mean square of vibration during the sampling period, specifically:

[0074]

[0075]

[0076] In the formula,

[0077] N—collection number;

[0078] x i-I —The current signal value collected at time i;

[0079] x i-F —The vibration signal value collected at time i.

[0080] Issue a warning for the same type of fault only when the current signal and the vibration signal are judged to be the same type of fault. For example, when both the current signal and the vibration are winding faults, issue a winding fault warning.

[0081] When the judgment results of the current signal and the vibration signal conflict, especially when the signal is near the judgment boundary, use the regional boundary judgment, that is, use the root mean square eigenvalue T of the vibration signal rmsF as the abscissa, and use the root mean square eigenvalue T of the current signal rmsi as the ordinate to make a scatter plot, and judge the fault state of the device according to the result area. When the judgment results of the current signal feature set and the torque signal feature set conflict, if T rmsF <0.55 and T rmsi <0.025, the pumping station is in a winding fault; if 0.35 < T rmsF <0.55 and 0.025 < T rmsi <1, the pumping station is in a cavitation fault; if 0.55 < T rmsF <0.75 and 0.006 < T rmsi <1, the pumping station is in a blade fault.

[0082] When the fault diagnosis determines a winding fault, determine the stage of the winding fault according to the flow signal feature set, the pressure signal feature set, the torque signal feature set and the speed signal feature set. Specifically:

[0083] When Q1 < Q0, and 0 < H1 < H0, and 0 < n1 < n0, and 0 < T1 < (0.75 - 1)T0, the winding fault is in stage I; within this stage, the head, flow rate, and torque are no longer fluctuating near the normal level due to the fault and show an obvious downward trend.

[0084] When Q1 < Q0, and H1 < 0, and 0 < n1 < n0, and 0 < T1 < T0, the winding fault is in stage II; within this stage, the winding fault causes the pump head to cross zero.

[0085] When Q1 < Q0, and H1 < 0, and 0 < n1 < n0, and T1 < 0, the winding fault is in stage III; within this stage, the torque of the winding fault pump crosses zero.

[0086] When Q1 < Q0, and H1 < 0, and n1 = 0, and T1 < 0, the winding fault is in stage IV, where H1 is the actual head of the sewage pump determined according to {P1, P2}; H0 is the head of the sewage pump under normal operating conditions determined according to {P 01 , P02}. Stage IV of the winding fault is the most serious situation of the fault development, that is, the pump is completely stuck and the speed is zero.

[0087] The actual head H1 of the sewage pump determined according to {P1, P2} is specifically as follows:

[0088]

[0089] In the formula:

[0090] H1—the actual head of the sewage pump, m;

[0091] P1—the pressure at the inlet (2) of the sewage pump, Pa;

[0092] P2—the pressure at the outlet (3) of the sewage pump, Pa;

[0093] c—the flow velocity at the inlet and outlet of the pump, m / s;

[0094] z out —the height of the sewage pump outlet, m;

[0095] z in —the height of the sewage pump inlet, m;

[0096] ρ—the liquid density, kg / m 3 ;

[0097] g—the gravitational acceleration, m / s 2 .

[0098] Embodiment

[0099] For a certain integrated pumping station, winding fault diagnosis is carried out, and single-signal analysis is performed on the current, vibration signals and their mean square values. Figure 3 is the relationship between the mean square value of the current signal and time, Figure 3 a, Figure 3 b and Figure 3 c are winding, blade, and cavitation faults respectively. For different faults, according to the root mean square analysis of the current, Figure 3 In a, 0.017 < T rmsi < 0.045, which is a winding fault; Figure 3 In b, 0.02 < T rmsi < 0.3, which is a blade fault; Figure 3 In c, 0.65 < T rmsi < 1.8, which is a cavitation fault; Figure 4 is the relationship between the mean square value of the vibration signal and time, Figure 4 a, Figure 4 b and Figure 4 c are winding, cavitation, and blade faults respectively. For different faults, according to the root mean square analysis of the vibration, it is calculated that Figure 4 In a, T rmsF = 0.4, which is a winding fault; Figure 4 In a, T rmsF = 0.5, which is a cavitation fault; Figure 4 In a, TrmsF = 0.65, indicating a blade fault.

[0100] For a certain integrated pump station, winding fault diagnosis is carried out, and current, vibration signals and their mean square values are used for feature-level fusion analysis. The results are as Figure 5 . In the figure, Y1 is the winding fault signal, Y2 is the cavitation fault signal, and Y3 is the blade fault signal. Feature point 1T rmsi = 0.024, T rmsF = 0.3. When judging according to T rmsi , this fault is a blade fault. When judging according to T rmsF , this fault is a winding fault, which conflicts with each other. Then the region discrimination method is used. This point is located in the winding area, and a winding fault warning should be given; Feature point 2T rmsi = 0.007, T rmsF = 0.47. When judging according to T rmsi , this fault is a winding fault. When judging according to T rmsF , this fault is a cavitation fault, which conflicts with each other. Then the region discrimination method is used. This point is located in the winding area, and a winding fault warning should be given.

[0101] For a certain integrated pump station, the development stage analysis of winding faults is carried out. The flow rate, rotational speed, head and torque are mainly analyzed, and the collected data is processed. The development process of the test monitoring data is as Figure 6 shown in the figure. In the test results, the time when the fault occurs is recorded as the time zero point, that is, when the fault stage I starts, t = 0s; The data during normal operation is used as the reference 1, and the changes of each data in the winding accident are compared.

[0102] In the example test, in order to observe the occurrence and evolution of the fault, the actual fault process is magnified, that is, in the experiment, the fault develops rapidly in a short time, while in reality, the winding fault will accumulate for a long time. The whole process of the fault stage developing from I to IV can be clearly observed in the test, and at the same time, the phenomenon of extremely short development time due to the nature of the test can be seen.

[0103] Before t = 0s, the pump operates normally, and the normal operation data {Q0, T0, n0, H0} is recorded at the same time;

[0104] When t = 0s, it is monitored that each monitoring data starts to decrease, that is, Q1 < Q0, H1 < H0, n1 < n0, T1 < T0. Near t = 0.08s, T1 < 0.75T0, exceeding the fluctuation threshold, and the winding fault is in stage I, and a warning for fault stage I is issued;

[0105] When t = 0.325s, Q1 < Q0, H1 < 0, n1 < n0, 0 < T1 < T0, and at the same time, it is monitored that H1 < 0, and the winding fault is in stage II, and a warning for fault stage II is issued;

[0106] When t = 0.355 s, the fault continues to develop, Q1 < Q0, H1 < 0, n1 < n0, and at the same time, it is monitored that T1 < 0. The winding fault is in stage III, and a warning for fault stage III is issued.

[0107] The fault continues to develop over time. At t = 5 s, Q1 < Q0, H1 < 0, n1 = 0, T1 < 0, the pump has stopped rotating, the winding fault is in stage IV, and a warning for fault stage IV is issued.

[0108] Statistically analyze the detailed records, fault records, and maintenance plans of the winding faults that have occurred in the integrated pumping station equipment, and establish an equipment information management database. The control system can match the processing solutions in the historical data in the equipment information management database according to different warning signals, and the control system transmits the processing solutions to the system of the maintenance personnel.

[0109] When a warning for fault stage I is issued, the running pump should be continuously monitored.

[0110] When a warning for fault stage II is issued, monitor the temperature rise of the pump casing and the pressure output by the pump. If necessary, the pump should be stopped for cleaning, and generally, it can be repaired during the night rest.

[0111] When a warning for fault stage III is issued, the running pump should be maintained in a timely manner, the pump should be stopped to clean the winding objects and continuously monitored.

[0112] When a warning for fault stage IV is issued, the pump should be stopped for timely maintenance, the winding objects should be cleaned, and it should be detected whether other components are damaged. Conduct no-load commissioning and continuous monitoring. If the pump runs normally, it can continue to be used; otherwise, it needs to be repaired.

[0113] It should be understood that although this specification is described according to various embodiments, not every embodiment only contains an independent technical solution. This narrative way of the specification is only for clarity. Those skilled in the art should regard the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

[0114] The series of detailed descriptions listed above are only specific descriptions of the feasible embodiments of the present invention, and they are not intended to limit the protection scope of the present invention. Any equivalent embodiments or changes made without departing from the technical spirit of the present invention should be included within the protection scope of the present invention.

Claims

1. An integrated pump station winding fault diagnosis method, characterized in that: It includes the following steps: Data acquisition: The flow rate at the outlet (3) of the sewage pump, the pressures at the inlet (2) and outlet (3) of the sewage pump, the torque and rotational speed output by the pump shaft (4), the current of the motor (5), and the vibration of the pump casing (6) are respectively acquired through at least one sensor. Data preprocessing: The processed data is used to establish the flow signal feature set {Q0, Q1} and the pressure signal feature set {P 01 , P 02 , P1, P2}, the torque signal feature set is {T0, T1}, the speed signal feature set is {n0, n1}, the current signal feature set is {I0, I1} and the vibration signal time domain signal feature set is {F0, F1}; Among them: {Q0} is the flow set in normal operation; {Q1} is the real-time monitoring flow set; {P 01 , P 02 } are respectively the pressure set of the sewage pump inlet (2) and the pressure set of the sewage pump outlet (3) under normal operation; {P1, P2} are respectively the real-time monitoring pressure set of the sewage pump inlet (2) and the real-time monitoring pressure set of the sewage pump outlet (3); {n0} is the speed set under normal operation; {n1} is the real-time monitoring speed set; {T0} is the torque set under normal operation; {T1} is the real-time monitoring torque set; {I0} is the current set under normal operation; {I1} is the real-time monitoring current set; {F0} is the vibration time domain set under normal operation; {F1} is the real-time monitoring vibration time domain set; Fault diagnosis: Determine whether it belongs to winding fault, cavitation fault, and vane fault according to the current signal feature set and the time-domain signal feature set of the vibration signal. Specifically: When 0 <T rmsi ≤0.005, the pump station is in normal operation; when 0.005 <T rmsi ≤0.01, the pump station is in winding fault; when 0.01 <T rmsi ≤0.1, the pump station is in blade failure; when 0.1 <T rmsi When ≤1, the pump station is in cavitation failure; When 0 <T rmsF ≤0.3, the pump station is in normal operation; when 0.3 <T rmsF ≤0.45, the pump station is in winding fault; when 0.45 <T rmsF ≤0.6, the pump station is in cavitation failure; when 0.6 <T rmsF When ≤0.75, the pump station is in blade failure; Where T rmsi is the RMS current during the sampling period; T rmsF is the root mean square of vibration during the sampling period.

2. The integrated pump station winding fault diagnosis method according to claim 1 is characterized in that: In the fault diagnosis, when the judgment results of the current signal feature set and the torque signal feature set conflict, if T rmsF <0.55 and T rmsi <0.025, the pump station is in a winding fault; if 0.35 <T rmsF <0.55 and 0.025 <T rmsi <1, the pump station is in cavitation failure; if 0.55 <T rmsF <0.75 and 0.006 <T rmsi <1, the pump station is in blade failure.

3. The integrated pump station winding fault diagnosis method according to claim 1 is characterized in that: When the fault diagnosis determines that it is in the winding fault, determine the stage of the winding fault according to the flow signal feature set, the pressure signal feature set, the torque signal feature set, and the rotational speed signal feature set. Specifically: When Q1 < Q0, and 0 < H1 < H0, and 0 < n1 < n0, and 0 < T1 < (0.75 - 1)T0, the winding fault is in stage I; When Q1 < Q0, and H1 < 0, and 0 < n1 < n0, and 0 < T1 < T0, the winding fault is in stage II; When Q1 < Q0, and H1 < 0, and 0 < n1 < n0, and T1 < 0, the winding fault is in stage III; When Q1 < Q0, H1 < 0, n1 = 0, and T1 < 0, the winding fault is in Stage IV, where H1 is the actual head of the sewage pump determined according to {P1, P2}; H0 is the head of the sewage pump under normal operating conditions determined according to {P 01 , P 02}.

4. The integrated pump station winding fault diagnosis method according to claim 3 is characterized in that: The actual lift H1 of the sewage pump determined according to {P1, P2}, specifically: In the formula: H1—the actual lift of the sewage pump, m; P1—the pressure at the inlet (2) of the sewage pump, Pa; P2—the pressure at the outlet (3) of the sewage pump, Pa; z out —Sewage pump outlet height, m; z in —Sewage pump inlet height, m; ρ—Liquid density, kg / m 3 ; g—neutral acceleration, m / s 2 .

5. The integrated pump station winding fault diagnosis method according to claim 1 is characterized in that: In the fault diagnosis, the current RMS T rmsi and the vibration root mean square T during the sampling period rmsF , specifically: In the formula, N—the number of acquisitions; x i-I —The current signal value collected at time i; x i-F —The vibration signal value collected at time i.

6. A diagnostic system for the integrated pump station winding fault diagnosis method according to any one of claims 1 to 5, characterized in that: It includes a sensor assembly, a control system, and an early warning system; The sensor assembly includes a flow sensor, a first pressure sensor, a second pressure sensor, a rotational speed and torque sensor, and a vibration sensor; the flow sensor is used to detect the flow rate at the outlet (3) of the sewage pump; the first pressure sensor is used to detect the pressure at the inlet (2) of the sewage pump; the second pressure sensor is used to detect the pressure at the outlet (3) of the sewage pump; the rotational speed and torque sensor is used to detect the torque and rotational speed output by the pump shaft (4); the vibration sensor is used to detect the vibration of the pump casing (6); The control system judges the type of fault and the stage of the winding fault according to the signals collected by the sensor assembly; The early warning system issues different early warning signals according to the type of fault and the stage of the winding fault.

Images