Method and system for controlling shutdown check of motor

Abstract

The invention provides a method and a system for controlling shutdown check of a motor. The method comprises the following steps: determining a vibration measuring point, a temperature measuring point and a sound measuring point on the motor; acquiring a vibration value at the vibration measuring point, a temperature value at the temperature measuring point and a noise value at the sound measuring point; based on the vibration value, the temperature value and the noise value, whether shutdown inspection needs to be carried out on the motor or not is judged; shutdown control is carried out on the motor according to the current measured value of the motor and the preset threshold value of the motor, the problem that abnormity of the motor cannot be found in time is solved, and safe and stable operation of equipment is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of motor fault detection, and in particular to a method and system for controlling motor shutdown inspection. Background Art

[0002] An electric motor is a device that converts electrical energy into mechanical energy and is widely used in industries, transportation, and homes. It is an indispensable power source in modern society. Engines and generators are both types of electric motors. The main parts of an electric motor include a stator and a rotor. The stator is enclosed in the motor housing and is usually composed of an iron core and a coil to generate a magnetic field. The rotor is located inside the stator and is composed of a magnet and an armature, which generates mechanical motion when it rotates. During the operation of the motor, the generator may have various faults, which may cause the motor's performance to deteriorate or even fail to work properly; motor fault types include insulation faults, cable faults, and bearing faults, but existing motors only have current protection functions, and no protection functions for vibration, temperature, abnormal noise, etc. However, motor failures are closely related to vibration, temperature, abnormal noise, etc. Vibration, temperature, and abnormal noise can be used to detect faults in a timely manner to prevent the motor coil from burning out.

[0003] In view of this, the present invention provides a method and system for controlling the shutdown inspection of a motor, which performs shutdown control on the motor according to the current measured value of the motor and the preset threshold of the motor, thereby solving the problem of failure to detect motor abnormalities in time and ensuring safe and stable operation of the equipment. Summary of the invention

[0004] The object of the present invention is to provide a method for controlling a motor shutdown inspection, comprising: determining a vibration measuring point, a temperature measuring point and a sound measuring point on the motor; obtaining a vibration value at the vibration measuring point, a temperature value at the temperature measuring point and a noise value at the sound measuring point; and judging whether the motor needs to be shut down for inspection based on the vibration value, the temperature value and the noise value.

[0005] Furthermore, the vibration measuring points include the bearings, front cover, rear cover, fan and base of the motor.

[0006] Furthermore, the temperature measurement points include the air inlet and outlet, bearings, windings and casing of the motor.

[0007] Furthermore, the sound measurement points include the windings, bearings, base and casing of the motor.

[0008] Further, whether the motor needs to be shut down for inspection is determined as follows: when the vibration value is not within a preset vibration threshold, the temperature value is not within a preset temperature threshold, or the noise value is not within a preset noise threshold, it is determined that the motor needs to be shut down for inspection.

[0009] Furthermore, determining whether it is necessary to perform a shutdown inspection on the motor comprises: constructing an initial shutdown judgment model; acquiring historical data; the historical data comprises historical fault data and historical non-fault data; the historical fault data and the historical non-fault data comprise at least historical vibration values, historical temperature values ​​and historical noise values; inputting the historical data into the initial shutdown judgment model, and the model determines whether the motor is faulty; constructing a loss function based on the result of the initial shutdown judgment model and the type of the historical data; updating the parameters of the initial shutdown judgment model based on the loss function to obtain a trained shutdown judgment model; inputting the vibration value, the temperature value and the noise value into the shutdown judgment model, and the shutdown judgment model outputs whether the motor is faulty; if so, performing a shutdown inspection on the motor.

[0010] Further, the shutdown judgment model includes a temperature value sorting model, a vibration value sorting model, a noise value sorting model and a fault determination model; the initial shutdown judgment model includes an initial temperature value sorting model, an initial vibration value sorting model, an initial noise value sorting model and an initial fault determination model; the initial temperature value sorting model is a CatBoost model; the temperature values ​​at multiple temperature measurement points are input into the temperature value sorting model, and the model outputs the importance of the temperature values; the initial vibration value sorting model is a CatBoost model; the temperature values ​​at multiple vibration measurement points are input into the vibration value sorting model, and the model outputs the importance of the vibration values; the initial noise value sorting model is a CatBoost model; the noise values ​​at multiple sound measurement points are input into the noise value sorting model, and the model outputs the importance of the noise values; the initial fault determination model is an LSTM model; the temperature value, the importance of the temperature value, the vibration value, the importance of the vibration value, the noise value and the importance of the noise value are input into the fault determination model, and the model outputs the probability of whether the motor is faulty; when the probability of fault is greater than a preset fault threshold, it is determined that the motor is faulty.

[0011] Furthermore, the temperature values ​​include inlet temperature value, outlet temperature value, bearing temperature value, winding temperature value and casing temperature value; the vibration values ​​include bearing vibration value, front cover vibration value, rear cover vibration value, fan vibration value and base vibration value; the noise values ​​include winding noise value, bearing noise value, base noise value and casing noise value.

[0012] Furthermore, the input of the initial temperature value sorting model includes the air inlet temperature value, the air outlet temperature value, the bearing temperature value, the winding temperature value, the casing temperature value, whether the generator is faulty or not, and the classification characteristics of each temperature value; the classification characteristics of each temperature value are the ratio of the number of samples of each temperature value within the normal temperature value range to the total number of samples; the input of the initial vibration value sorting model includes the bearing vibration value, the front cover vibration value, the rear cover vibration value, the fan vibration value and the base vibration value, whether the generator is faulty or not, and the classification characteristics of each vibration value; the classification characteristics of each vibration value are the ratio of the number of samples of each vibration value within the normal vibration value range to the total number of samples; the input of the initial noise value sorting model includes the winding noise value, the bearing noise value, the base noise value and the casing noise value, whether the generator is faulty or not, and the classification characteristics of each noise value; the classification characteristics of each noise value are the ratio of the number of samples of each noise value within the normal noise value range to the total number of samples.

[0013] The object of the present invention is to provide a system for controlling the shutdown inspection of an electric motor, characterized in that it includes a determination module, an acquisition module and a judgment module; the determination module is used to determine the vibration measurement point, the temperature measurement point and the sound measurement point on the motor; the acquisition module is used to obtain the vibration value at the vibration measurement point, the temperature value at the temperature measurement point and the noise value at the sound measurement point; the judgment module is used to judge whether the motor needs to be shut down for inspection based on the vibration value, the temperature value and the noise value.

[0014] The technical solution of the embodiment of the present invention has at least the following advantages and beneficial effects:

[0015] Some embodiments of the present invention perform shutdown control on the motor according to the current measurement value of the motor and the preset threshold value of the motor, thereby solving the problem of failure to timely discover the abnormality of the motor and ensuring the safe and stable operation of the equipment.

[0016] Some embodiments of the present invention use the CatBoost model to sort the temperature values, vibration values ​​and noise values, and obtain the importance of each element in each category of values; then the importance of each element in each category of values ​​and its sorting are input into the LSTM model, and the LSTM model is processed based on historical data and current input data to determine whether the generator is faulty, so as to improve the accuracy of the judgment result, avoid invalid shutdown, and cause unnecessary losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 An exemplary flow chart of a method for controlling a motor shutdown check provided in some embodiments of the present invention;

[0018] Figure 2An exemplary block diagram of a system for controlling motor shutdown inspection provided in some embodiments of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0020] Figure 1 The present invention provides an exemplary flow chart of a method for controlling a motor shutdown check in some embodiments of the present invention. In some embodiments, the process 100 can be executed by the system 200. Figure 1 As shown, process 100 may include the following contents:

[0021] Step 110 , determining vibration measurement points, temperature measurement points, and sound measurement points on the motor. In some embodiments, step 110 may be performed by the determination module 210 .

[0022] In some embodiments, the vibration measuring points include bearings, a front cover, a rear cover, a fan and a base of the motor.

[0023] In some embodiments, the temperature measurement points include the air inlet and outlet, bearings, windings and casing of the motor.

[0024] In some embodiments, the sound measurement points include windings, bearings, base and casing of the motor.

[0025] Step 120 , obtaining the vibration value at the vibration measuring point, the temperature value at the temperature measuring point, and the noise value at the sound measuring point. In some embodiments, step 120 may be performed by the obtaining module 220 .

[0026] In some embodiments, the vibration value includes the bearing vibration value, the front cover vibration value, the rear cover vibration value, the fan vibration value and the base vibration value; the temperature value includes the air inlet temperature value, the air outlet temperature value, the bearing temperature value, the winding temperature value and the casing temperature value; the noise value includes the winding noise value, the bearing noise value, the base noise value and the casing noise value. In some embodiments, a vibration sensor can be placed at the corresponding vibration measuring point to obtain the vibration value; a temperature sensor can be placed at the corresponding temperature measuring point to obtain the temperature value; and a noise sensor can be placed at the corresponding sound measuring point to obtain the noise value.

[0027] Step 130 , based on the vibration value, the temperature value and the noise value, determine whether the motor needs to be shut down for inspection. In some embodiments, step 130 may be performed by the determination module 230 .

[0028] In some embodiments, whether the motor needs to be shut down for inspection is determined as follows: when the vibration value is not within a preset vibration threshold, the temperature value is not within a preset temperature threshold, or the noise value is not within a preset noise threshold, it is determined that the motor needs to be shut down for inspection.

[0029] The preset vibration threshold refers to the preset vibration range when the motor is in normal operation. For example, the preset vibration threshold may include a displacement threshold, a vibration velocity, and a vibration acceleration; wherein the displacement threshold is 21-35um; the vibration velocity is 1.3-2.2mm / s; and the vibration acceleration is 2.0-3.5m / s. 2 .

[0030] The preset temperature threshold refers to a preset temperature range when the motor is in a normal operating state. For example, the preset temperature threshold may be 80-110 degrees.

[0031] The preset noise threshold refers to a preset noise range when the motor is in a normal operating state. For example, the preset noise threshold may be 55-110 dB.

[0032] In some embodiments, determining whether the motor needs to be shut down for inspection includes:

[0033] Construct an initial shutdown judgment model.

[0034] In some embodiments, the initial shutdown judgment model includes an initial temperature value sorting model, an initial vibration value sorting model, an initial noise value sorting model, and an initial fault determination model. The initial temperature value sorting model is a CatBoost model; the initial vibration value sorting model is a CatBoost model; the initial noise value sorting model is a CatBoost model; and the initial fault determination model is an LSTM model.

[0035] In some embodiments, the input of the initial temperature value sorting model includes the air inlet temperature value, the air outlet temperature value, the bearing temperature value, the winding temperature value, the casing temperature value, whether the generator is faulty or not, and the classification characteristics of each temperature value; the classification characteristics of each temperature value are the ratio of the number of samples of each temperature value within the normal temperature value range to the total number of samples; the input of the initial vibration value sorting model includes the bearing vibration value, the front cover vibration value, the rear cover vibration value, the fan vibration value and the base vibration value, whether the generator is faulty or not, and the classification characteristics of each vibration value; the classification characteristics of each vibration value are the ratio of the number of samples of each vibration value within the normal vibration value range to the total number of samples; the input of the initial noise value sorting model includes the winding noise value, the bearing noise value, the base noise value and the casing noise value, whether the generator is faulty or not, and the classification characteristics of each noise value; the classification characteristics of each noise value are the ratio of the number of samples of each noise value within the normal noise value range to the total number of samples.

[0036] The normal vibration value range, the normal temperature value range and the normal noise value range can be set based on experience, and different types of temperature values, different types of vibration values ​​and different types of noise values ​​can correspond to different ranges.

[0037] Acquire historical data; the historical data includes historical fault data and historical non-fault data; the historical fault data and the historical non-fault data at least include historical vibration values, historical temperature values ​​and historical noise values.

[0038] The historical data is input into the initial shutdown judgment model, and the model judges whether the motor is faulty.

[0039] A loss function is constructed based on the result of the initial shutdown judgment model and the type of the historical data.

[0040] The parameters of the initial shutdown judgment model are updated based on the loss function to obtain a trained shutdown judgment model.

[0041] In some embodiments, the shutdown judgment model includes a temperature value sorting model, a vibration value sorting model, a noise value sorting model and a fault determination model. The temperature values ​​at the plurality of temperature measurement points are input into the temperature value sorting model, and the model outputs the importance of the temperature values; the temperature values ​​at the plurality of vibration measurement points are input into the vibration value sorting model, and the model outputs the importance of the vibration values; the noise values ​​at the plurality of sound measurement points are input into the noise value sorting model, and the model outputs the importance of the noise values; the temperature value, the importance of the temperature value, the vibration value, the importance of the vibration value, the noise value and the importance of the noise value are input into the fault determination model, and the model outputs the probability of whether the motor is faulty; when the probability of fault is greater than a preset fault threshold, it is determined that the motor is faulty.

[0042] The preset fault threshold may refer to a preset maximum fault value of the generator fault. For example, the preset fault threshold may be 50%, and when the probability of the fault is greater than 50%, it is determined that the motor has a fault.

[0043] The vibration value, the temperature value, and the noise value are input into the shutdown judgment model, and the shutdown judgment model outputs whether the motor is faulty.

[0044] If yes, the motor is shut down for inspection. If no, no processing is performed.

[0045] Figure 2 An exemplary module diagram of a system for controlling motor shutdown inspection provided in some embodiments of the present invention. Figure 2 As shown, the system 200 may include a determination module 210 , an acquisition module 220 and a judgment module 230 .

[0046] The determination module 210 is used to determine the vibration measurement points, temperature measurement points and sound measurement points on the motor. For more information about the determination module 210, see Figure 1 and its related description.

[0047] The acquisition module 220 is used to acquire the vibration value at the vibration measurement point, the temperature value at the temperature measurement point, and the noise value at the sound measurement point. For more information about the acquisition module 220, see Figure 1 and its related description.

[0048] The judgment module 230 is used to judge whether it is necessary to stop the motor for inspection based on the vibration value, the temperature value and the noise value. For more information about the judgment module 230, see Figure 1 and its related description.

[0049] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for controlling a motor to stop for inspection, characterized in that: include: Determine the vibration measurement points, temperature measurement points and sound measurement points on the motor; Acquire the vibration value at the vibration measuring point, the temperature value at the temperature measuring point, and the noise value at the sound measuring point; Based on the vibration value, the temperature value and the noise value, it is determined whether the motor needs to be stopped for inspection.

2. The method for controlling the motor shutdown inspection according to claim 1, characterized in that: The vibration measuring points include the bearings, front cover, rear cover, fan and base of the motor.

3. The method for controlling the motor shutdown inspection according to claim 1, characterized in that: The temperature measurement points include the air inlet and outlet, bearings, windings and casing of the motor.

4. The method for controlling the motor shutdown inspection according to claim 1, characterized in that: The sound measurement points include the windings, bearings, base and casing of the motor.

5. The method for controlling the motor shutdown inspection according to claim 1, characterized in that: Whether the motor needs to be shut down for inspection is determined as follows: when the vibration value is not within a preset vibration threshold, the temperature value is not within a preset temperature threshold, or the noise value is not within a preset noise threshold, it is determined that the motor needs to be shut down for inspection.

6. The method for controlling the motor shutdown inspection according to claim 1, characterized in that: Determining whether the motor needs to be stopped for inspection includes: Construct an initial shutdown judgment model; Acquire historical data; the historical data includes historical fault data and historical non-fault data; the historical fault data and the historical non-fault data at least include historical vibration values, historical temperature values ​​and historical noise values; Inputting the historical data into the initial shutdown judgment model, and the model judges whether the motor is faulty; Constructing a loss function based on the result of the initial shutdown judgment model and the type of the historical data; Updating the parameters of the initial shutdown judgment model based on the loss function to obtain a trained shutdown judgment model; Inputting the vibration value, the temperature value and the noise value into the shutdown judgment model, the shutdown judgment model outputting whether the motor is faulty; If so, the motor is shut down for inspection.

7. The method for controlling the motor shutdown inspection according to claim 6, characterized in that: The shutdown judgment model includes a temperature value sorting model, a vibration value sorting model, a noise value sorting model and a fault determination model; the initial shutdown judgment model includes an initial temperature value sorting model, an initial vibration value sorting model, an initial noise value sorting model and an initial fault determination model; The initial temperature value sorting model is a CatBoost model; the temperature values ​​at the plurality of temperature measurement points are input into the temperature value sorting model, and the model outputs the importance of the temperature values; The initial vibration value sorting model is a CatBoost model; the temperature values ​​at the plurality of vibration measuring points are input into the vibration value sorting model, and the model outputs the importance of the vibration value; The initial noise value ranking model is a CatBoost model; the noise values ​​at the plurality of sound measurement points are input into the noise value ranking model, and the model outputs the importance of the noise values; The initial fault determination model is an LSTM model; Inputting the temperature value, the importance of the temperature value, the vibration value, the importance of the vibration value, the noise value and the importance of the noise value into the fault determination model, the model outputting the probability of whether the motor is faulty; When the probability of failure is greater than a preset failure threshold, it is determined that the motor fails.

8. The method for controlling the motor shutdown inspection according to claim 7, characterized in that: The temperature values ​​include air inlet temperature value, air outlet temperature value, bearing temperature value, winding temperature value and casing temperature value; The vibration values ​​include bearing vibration value, front cover vibration value, rear cover vibration value, fan vibration value and base vibration value; The noise values ​​include winding noise value, bearing noise value, base noise value and casing noise value.

9. The method for controlling the motor shutdown inspection according to claim 8, characterized in that: The input of the initial temperature value sorting model includes the air inlet temperature value, the air outlet temperature value, the bearing temperature value, the winding temperature value, the casing temperature value, whether the generator is faulty or not, and the classification characteristics of each temperature value; The classification feature of each temperature value is the ratio of the number of samples of each temperature value within the normal temperature value range to the total number of samples; The input of the initial vibration value sorting model includes the bearing vibration value, the front cover vibration value, the rear cover vibration value, the fan vibration value and the base vibration value, whether the generator is faulty or not, and the classification characteristics of each vibration value; the classification characteristics of each vibration value are the ratio of the number of samples of each type of vibration value within the normal vibration value range to the total number of samples; The input of the initial noise value ranking model includes the winding noise value, the bearing noise value, the base noise value and the casing noise value, whether the generator is faulty or not, and classification characteristics of each noise value; The classification feature of each noise value is the ratio of the number of samples of each type of noise value within the normal noise value range to the total number of samples.

10. A system for controlling motor shutdown inspection, characterized in that: It includes a determination module, an acquisition module and a judgment module; The determination module is used to determine the vibration measurement point, temperature measurement point and sound measurement point on the motor; the acquisition module is used to acquire the vibration value at the vibration measurement point, the temperature value at the temperature measurement point and the noise value at the sound measurement point; The judgment module is used to judge whether it is necessary to stop the motor for inspection based on the vibration value, the temperature value and the noise value.

Images