Silica gel stirring motor abnormality monitoring method and system

Abstract

The present application belongs to the technical field of industrial control, and relates to a silica gel stirring motor abnormality monitoring method and system. The method comprises: collecting stator current, rotating speed, DC bus voltage and temperature data in the motor operation process, and pre-processing; using preset fluid rheological characteristic parameters and mechanical loss parameters to calculate dynamic rheological impedance index; based on the dynamic rheological impedance index, constructing thermal coupling abnormal confidence, introducing a temperature drift penalty term, and combining the fluctuation characteristics of the dynamic rheological impedance index in the time window to evaluate the equipment health state; according to the calculated abnormal confidence, determining whether the motor is abnormal, and performing corresponding early warning or shutdown operation. The present application solves the false alarm and missed alarm problems caused by the fixed threshold in the non-Newtonian fluid stirring of the prior art, can effectively decouple the rotating speed interference, accurately identifies the early failure and thermal failure risk at low speed, and realizes high signal-to-noise ratio monitoring under all working conditions.

Description

Technical Field

[0001] This invention belongs to the field of industrial control technology, specifically relating to a method and system for abnormal monitoring of silicone stirring motors. Background Technology

[0002] In the production of polymer materials such as silicone and sealants, the drive motors of core equipment such as planetary mixers and high-intensity dispersers operate under extremely complex conditions for extended periods. Because silicone is a typical non-Newtonian fluid with significant shear-thinning properties, its viscosity is not constant but exhibits a non-linear change with increasing stirring speed. This unique rheological characteristic means that the relationship between motor load and speed no longer follows a simple linear correlation, posing a significant challenge to equipment condition monitoring.

[0003] Existing technologies for monitoring such equipment typically employ fixed current thresholds or simple overload protection mechanisms. However, this traditional method has significant limitations in practical applications. During high-speed mixing, the motor current naturally increases to overcome the fluid's immense inertia and high shear force. This is a normal process requirement, but it is easily misinterpreted as an overload by rigid monitoring systems, leading to frequent false alarms and disrupting normal production.

[0004] More seriously, during low-speed mixing or heat preservation and pressure holding stages, the motor typically operates at low current. Even if serious faults such as rotor rubbing or transmission bearing wear have occurred inside the motor, the resulting abnormal current increase, superimposed on the base current under low-speed conditions, is often still far below the alarm threshold set at full load. This phenomenon causes fault signals to be masked by the appearance of low-speed operation, preventing the system from issuing timely alarms. This results in the equipment continuing to operate in a faulty state until it is completely damaged or even causes a safety accident. Furthermore, current technology struggles to effectively distinguish whether the current increase is caused by increased load or motor heat dissipation failure, thus failing to accurately predict the risk of thermal failure and creating hidden dangers for the safe operation of the equipment. Summary of the Invention

[0005] The purpose of this invention is to propose a method and system for abnormal monitoring of silicone stirring motors, in order to solve the technical problems in silicone stirring production, where existing fixed threshold monitoring technology cannot decouple the nonlinear relationship between speed and load, resulting in false alarms during high-speed operation, missed early faults during low-speed operation, and inability to accurately identify the risk of motor thermal failure.

[0006] To solve the above problems, the technical solution of the abnormal monitoring method for silicone stirring motor proposed in this invention is as follows: A method for monitoring abnormalities in a silica gel stirring motor includes the following steps: Real-time status data of the silica gel stirring motor during operation is collected. The real-time status data includes stator current, mechanical speed, DC bus voltage, and motor temperature. The real-time status data is then filtered and preprocessed. Based on the stator current, DC bus voltage and mechanical speed, the dynamic rheological impedance index is calculated using preset fluid rheological characteristic parameters and mechanical loss parameters. The dynamic rheological impedance index is used to characterize the system impedance characteristics after eliminating nonlinear interference from speed and fluid viscosity. Based on the dynamic rheological impedance index and the motor temperature, the confidence level of thermo-coupling anomaly is calculated. The confidence level of thermo-coupling anomaly is obtained by statistically analyzing the fluctuation energy of the dynamic rheological impedance index within a time window and weighting it in combination with the deviation of the real-time temperature of the motor stator winding or housing from the standard reference temperature. The confidence level of the thermal coupling anomaly is compared with a preset fault threshold. If the threshold is exceeded, the silicone stirring motor is determined to be abnormal, and the monitoring result is output.

[0007] Furthermore, the formula for calculating the dynamic rheological impedance index is as follows:

[0008] In the formula, express The dynamic rheological impedance index at time t. express The effective value of the motor stator current at time t. This indicates the DC bus voltage of the frequency converter. express The mechanical speed of the motor at any given moment. This represents the power-law factor of rheology. Indicates the fluid resistance coefficient. Indicates the coefficient of mechanical friction. This represents the static bias constant.

[0009] Furthermore, the rheological power-law factor The acquisition method includes: acquiring historical data of the same type of silicone produced by the equipment in a healthy state, performing linear fitting with the natural logarithm of power as the ordinate and the natural logarithm of rotation speed as the abscissa, and the slope of the fitted line being the rheological power-law factor.

[0010] Furthermore, the fluid resistance coefficient It is obtained by fitting historical health data using the least squares method and is used to characterize the basic viscosity contribution of silicone; the mechanical friction coefficient is... It is obtained through no-load testing or regression analysis, and characterizes the linear frictional resistance of bearings and gears.

[0011] Furthermore, the static bias constant The value ranges from 3% to 5% of the motor's rated power. It is used to prevent the denominator of the formula from being zero during motor startup or in extremely low-speed standby mode, and to characterize the static friction power consumption of the system.

[0012] Furthermore, the formula for calculating the confidence level of the thermo-coupling anomaly is as follows: ; In the formula, Indicates the confidence level of the thermo-coupling anomaly. This indicates the number of sampling points in the sliding statistics window. Indicates the past number The dynamic rheological impedance index at each sampling point This represents the historical average of the dynamic rheological impedance index under healthy conditions. This indicates the real-time temperature of the motor stator windings or housing. Indicates the standard reference temperature. Indicates the thermal weighting coefficient. This indicates that the larger value between the real-time temperature and the standard reference temperature is taken.

[0013] Furthermore, the formula for calculating the confidence level of thermo-coupling anomalies uses... The function performs a temperature limit clamping when the real-time temperature... Below standard reference temperature When, the forced value is To ensure that the input value of the logarithmic function is not less than 1, this prevents the calculation result from being negative or reducing the fault signal.

[0014] Furthermore, the thermal weighting coefficient The setting is based on the insulation and heat resistance class of the motor. The lower the insulation and heat resistance class, the larger the set value of the thermistor weighting coefficient.

[0015] Furthermore, the filtering preprocessing includes: using a sliding median filtering method to process the collected stator current, mechanical speed, DC bus voltage and motor temperature, with the filtering window length set to 500ms, in order to eliminate spike pulses caused by electromagnetic interference.

[0016] The technical solution of the silica gel stirring motor abnormality monitoring system proposed in this invention is as follows: A silicone stirring motor abnormality monitoring system includes a processor and a memory. The memory stores computer instructions, which, when executed by the processor, implement the silicone stirring motor abnormality monitoring method described in any of the above technical solutions.

[0017] The beneficial effects of this invention are as follows: By constructing a dynamic impedance model based on rheological characteristics and establishing a power model decoupled from rotational speed using a rheological power-law factor, this invention effectively eliminates the nonlinear interference caused by the shear-thinning characteristics of non-Newtonian fluids. This mechanism ensures that the monitoring indicators remain highly consistent across different rotational speeds, solving the technical problems of false alarms under high-speed stirring conditions and missed alarms under low-speed heat preservation conditions caused by the use of fixed current thresholds in existing technologies, thus improving the monitoring reliability of the equipment over a wide speed range.

[0018] This invention introduces a thermo-coupled anomaly scoring mechanism, deeply integrating the statistical characteristics of load fluctuations with the degree of temperature drift. By calculating the fluctuation energy of the dynamic rheological impedance index within a time window and combining it with a temperature penalty term, the fault characteristics are amplified using a multiplicative effect. When the motor is at a high temperature and the load exhibits slight abnormal fluctuations, the system can generate extremely high fault confidence, thereby achieving accurate detection and rapid response to early mechanical faults and thermal failure risks, effectively preventing safety accidents caused by continuous operation of equipment under high-temperature and faulty conditions.

[0019] This invention eliminates the need for additional vibration or acoustic sensors. It only requires collecting conventional data such as motor current, voltage, speed, and temperature, and combining this data with preprocessing algorithms like sliding median filtering. This enables high signal-to-noise ratio online monitoring without altering the existing hardware architecture. This significantly reduces system hardware costs and maintenance complexity, and also allows for sensitive identification of hidden faults such as rotor rubbing and bearing wear through in-depth multi-dimensional data mining. Attached Figure Description

[0020] Figure 1 This is a flowchart of the abnormal monitoring method for the silicone stirring motor of the present invention; Figure 2 This is a schematic diagram of monitoring results based on a fixed threshold in existing technology; Figure 3 This is a schematic diagram of the monitoring results based on the rheological impedance characteristics of this invention. Detailed Implementation

[0021] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0022] Specific embodiments of the abnormal monitoring method for silicone stirring motor proposed in this invention: like Figure 1 As shown, the method for monitoring abnormalities in a silica gel stirring motor includes steps S1-S4: S1. Collect real-time status data of the silica gel stirring motor during operation. The real-time status data includes stator current, mechanical speed, DC bus voltage and motor temperature. Perform filtering preprocessing on the real-time status data.

[0023] Specifically, at the hardware level, an industrial PLC such as the Siemens S7-1200 series is used as the core controller, and a communication connection is established with the frequency converter driving the motor using Modbus or EtherCAT bus.

[0024] The real-time status data collected through this communication connection includes stator current, mechanical speed, DC bus voltage, and motor temperature. The stator current is the effective value of the motor stator current, measured in amperes; the mechanical speed is measured in revolutions per minute (rpm); the DC bus voltage is the real-time voltage value of the inverter's DC bus, measured in volts; this parameter is introduced to compensate for deviations in power calculation caused by grid fluctuations; and the motor temperature is the real-time temperature of the motor stator windings or housing, measured in Kelvin.

[0025] After acquiring the original data sequence, the system preprocesses it using a sliding median filter algorithm, setting the filter window length to 500 milliseconds. This filtering process effectively smooths the data sequence and removes spike noise caused by the complex electromagnetic environment at the site. It is a well-known and commonly used technique in the field of industrial signal preprocessing, and can effectively ensure the quality of input data for subsequent model calculations.

[0026] In this way, by acquiring and filtering multidimensional data in real time, an accurate and clean data foundation can be provided for subsequent model calculations, avoiding the impact of electromagnetic interference on monitoring accuracy.

[0027] S2. Based on the stator current, DC bus voltage and mechanical speed, calculate the dynamic rheological impedance index using preset fluid rheological characteristic parameters and mechanical loss parameters. The dynamic rheological impedance index is used to characterize the system impedance characteristics after eliminating nonlinear interference from speed and fluid viscosity.

[0028] Specifically, the load on a silica gel agitator consists of two main parts: the work done to overcome fluid viscosity resistance and the work done to overcome mechanical friction. Because silica gel exhibits shear-thinning properties, its resistance torque has a power-law relationship with the rotational speed. To accurately monitor motor health, it is necessary to eliminate interference from rotational speed and fluid characteristics, and to construct a theoretically constant dynamic rheological resistance index.

[0029] The formula for calculating the dynamic rheological impedance index is as follows:

[0030] This formula is based on the power-law fluid constitutive equation in rheology that describes the shear-thinning properties of non-Newtonian fluids. The viscosity of silica-based fluids is not constant but decreases with increasing shear rate (rotation speed). Traditional linear models cannot characterize this property; therefore, the denominator of the formula incorporates a rheological power-law factor. The nonlinear power prediction model decouples fluid resistance work from mechanical loss work and compares the actual electrical power with the theoretical resistance model, thereby eliminating the normal disturbances caused by changes in rotational speed and fluid viscosity and extracting the impedance characteristics of the health of the reaction equipment itself.

[0031] In the formula, express The dynamic rheological impedance index at any given time is dimensionless and its physical meaning is the ratio of the actual input power to the theoretical model power. When the equipment is healthy and the process is normal, this value stabilizes around 1.

[0032] As a power characteristic quantity that has a fixed proportional relationship with the active power input of the motor, since the subsequent model coefficients are all obtained by fitting health data of the same dimension, the proportionality constant is completely canceled in the ratio calculation, which does not affect the calculation result and physical meaning of the dynamic rheological impedance index. This indicates the DC bus voltage of the frequency converter. express The effective value of the motor stator current at any given time; express The mechanical rotation speed of the motor at any given time.

[0033] The rheological power-law factor is a dimensionless constant. It is obtained by selecting historical data on the production of the same type of silicone rubber under healthy conditions, and performing a linear fit with the natural logarithm of power on the ordinate and the natural logarithm of rotational speed on the abscissa. The slope of the fitted line is the rheological power-law factor. For silicone rubber, the value of the rheological power-law factor is typically between 1.2 and 1.8. By introducing the rheological power-law factor... The nonlinear coupling relationship between rotational speed change and fluid viscosity decrease was successfully decoupled mathematically, thereby extracting pure mechanical impedance characteristics independent of operating conditions.

[0034] This is the fluid resistance coefficient, and its dimensionless unit is... The value was obtained by fitting historical health data using the least squares method and is used to characterize the basic viscosity contribution of silicone.

[0035] The coefficient of mechanical friction has dimensions and units of . It is obtained through motor no-load testing or regression analysis, and represents the linear frictional resistance of bearings and gears.

[0036] This is the static bias constant, and its unit is _____. The value is set to 3% to 5% of the motor's rated power; its function is to prevent the denominator of the formula from being zero at the moment of motor start-up or in a very low-speed standby state, and at the same time to characterize the static friction power consumption of the system.

[0037] To more intuitively understand the physical meaning and calculation process of this formula, a specific calculation example is given here.

[0038] Suppose the parameters of a certain stirring motor are set as follows: Rheological power-law factor ; Fluid resistance coefficient ; mechanical friction coefficient ; Static bias constant .

[0039] When the equipment is operating at normal high speed, the motor speed is... rpm; the actual measured effective value of the motor stator current. A, DC bus voltage V, substituting into the above formula, yields: ; = ; ; at this time, This indicates that the equipment is operating normally.

[0040] Even when the equipment experiences bearing wear failure, the motor speed remains unchanged. rpm .

[0041] Increased mechanical friction due to bearing wear requires the motor to output greater torque to maintain its speed, resulting in an increase in current. The measured RMS value of the motor stator current at this time... A, the actual input power is At this time The value is significantly greater than 1, indicating a possible anomaly.

[0042] As can be seen from the above calculation process, this method, by constructing an impedance model that conforms to the characteristics of non-Newtonian fluids, can effectively compare the actual input power with the theoretical model power, successfully decouple the influence of speed change on load monitoring, and ensure that the monitoring indicators remain consistent at different speeds.

[0043] S3. Based on the dynamic rheological impedance index and the motor temperature, calculate the confidence level of thermo-coupling anomaly. The confidence level of thermo-coupling anomaly is obtained by statistically analyzing the fluctuation energy of the dynamic rheological impedance index within a time window and weighting it in combination with the deviation of the real-time temperature of the motor stator winding or housing from the standard reference temperature.

[0044] Specifically, the formula for calculating the confidence level of thermo-coupling anomalies is as follows: ; The formula is based on Arrhenius's law in physical chemistry, which states that the rate of aging of insulating materials and failure of lubricating grease accelerates exponentially with increasing temperature. By extrapolating to the threshold penalty, the logarithmic function can accurately map this physical law that deteriorates rapidly with increasing temperature.

[0045] In the formula, Indicates the confidence level of the thermo-coupling anomaly; This represents the number of sampling points in the sliding statistical window. For example, if we are taking data from the past 3 seconds and the sampling frequency is 10Hz, then... ; Indicates the past number The dynamic rheological impedance index at each sampling point The historical average of the dynamic rheological impedance index under healthy conditions is typically 1; This indicates the real-time temperature of the motor stator windings or housing. Indicates the standard reference temperature, for example, 300K; use The function performs a temperature limit clamping when the real-time temperature... Below standard reference temperature When, the forced value is To ensure that the input value of the logarithmic function is not less than 1, to prevent the calculation result from being negative or to reduce the fault signal; This is the thermal weighting coefficient, which is set according to the insulation and heat resistance class of the motor. The lower the insulation and heat resistance class, the larger the value of this coefficient.

[0046] In the above formula, the square root of the first term represents the fluctuation rate of the rheological impedance, which often manifests as unstable operation in the early stages of a fault. The oscillations intensified. The confidence level of the thermo-coupling anomaly in this step... The calculation formula incorporates the thermodynamic degradation model of the motor and introduces a logarithmic temperature drift penalty term, which not only utilizes... The function constructs a safe thermal threshold gating, which does not introduce additional interference within the normal temperature range. Moreover, the logarithmic gain curve truly maps the physical law of the rapid acceleration of motor stator insulation material aging and bearing grease failure with temperature rise, realizing the transformation from traditional single-dimensional dead zone threshold alarm to adaptive feature identification coupled with multi-physics field.

[0047] To more intuitively understand the physical meaning and calculation process of this formula, a specific calculation example is given here: Assuming the historical average of the dynamic rheological impedance index under healthy conditions The motor is running unstable, and at a certain moment, it was detected that the motor has been running for a period of time in the past. The fluctuations are large, and the calculated The value is 0.5. Set the standard temperature. K, real-time temperature K, thermal weighting coefficient .

[0048] at this time, ; ; final .

[0049] If the temperature rises even more rapidly to 360K, that is K, at this time, ; ; final .

[0050] It can be seen that as the temperature increases, even with the same volatility, the failure score increases significantly, reflecting the weighting of thermal failure risk.

[0051] Thus, by introducing a thermo-coupling mechanism, not only are load fluctuations considered, but the impact of temperature on equipment tolerance is also taken into account. The multiplicative effect amplifies fault characteristics, enabling sensitive detection of early faults and thermal failure risks.

[0052] S4. Compare the confidence level of the thermal coupling anomaly with the preset fault threshold. If the confidence level exceeds the fault threshold, it is determined that the silicone stirring motor is abnormal, and the monitoring result is output.

[0053] Specifically, the system presets a fault threshold, for example, 0.8. The real-time calculated confidence level of the thermal coupling anomaly is then used. The system compares the results with the fault threshold. If the confidence level of the thermal coupling anomaly exceeds the fault threshold, the system determines that the silica gel stirring motor is malfunctioning. At this point, the system will output the monitoring results, and specific actions include immediately triggering an audible and visual alarm signal to notify the operator to check, or directly sending a stop command to the frequency converter to cut off the power supply and prevent the damage to the equipment from spreading.

[0054] The following combination Figure 2 and Figure 3 The technical solution and technical effects of the present invention will be further explained.

[0055] Figure 2The diagram illustrates the monitoring results of existing technologies based on fixed thresholds. The solid line in the graph represents the real-time current waveform of the motor, while the dashed line represents the preset fixed alarm threshold. In the high-speed range (the first half), the increased load due to accelerated processing causes the current waveform to rise naturally and exceed the fixed alarm threshold, resulting in a false alarm. In the low-speed range (the second half), although the current waveform rises somewhat after a fault signal is manually introduced, its total amplitude remains below the fixed alarm threshold, and the existing technology fails to react, leading to missed alarms. This demonstrates that existing technologies cannot accurately monitor both high and low-speed conditions.

[0056] Figure 3 The figure demonstrates the monitoring results based on rheological impedance characteristics of this invention. The solid line in the figure represents the calculated dynamic rheological impedance index. The waveform, with the dashed line representing the preset health boundary line, shows that during the entire steady-state operation, regardless of whether the motor is accelerating or decelerating, the dynamic rheological impedance index waveform remains stable near the baseline of 1. This demonstrates that the calculation formula of this invention successfully counteracts the interference caused by speed changes and non-Newtonian fluid characteristics, completely eliminating false alarms. However, at the moment of fault occurrence in the latter half of the process, the dynamic rheological impedance index waveform spikes instantaneously, reaching an amplitude more than 1.5 times the normal value and significantly exceeding the health boundary line, achieving accurate detection of abnormal conditions.

[0057] Specific embodiments of the silicone stirring motor abnormality monitoring system proposed in this invention: The silicone stirring motor abnormality monitoring system includes a processor and a memory. The memory stores computer program instructions. When the computer program instructions are executed by the processor, the silicone stirring motor abnormality monitoring method in the above embodiments is implemented.

[0058] The silica gel stirring motor abnormality monitoring system also includes other components well known to those skilled in the art, such as communication buses and communication interfaces. Their settings and functions are known in the art and will not be described in detail here.

[0059] In this invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used or combined with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store desired information and can be accessed by an application, module, or both. Any such computer storage medium can be part of a device or accessible to or connected to a device. Any application or module described in this invention can be implemented by computer-readable / executable instructions stored or otherwise maintained on such a computer-readable medium.

[0060] While various embodiments of the invention have been shown and described in this specification, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many modifications, alterations, and alternatives will occur to those skilled in the art without departing from the spirit and essence of the invention.

Claims

1. A method for monitoring abnormalities in a silicone stirring motor, characterized in that, Includes the following steps: Real-time status data of the silica gel stirring motor during operation is collected. The real-time status data includes stator current, mechanical speed, DC bus voltage, and motor temperature. The real-time status data is then filtered and preprocessed. Based on the stator current, DC bus voltage and mechanical speed, the dynamic rheological impedance index is calculated using preset fluid rheological characteristic parameters and mechanical loss parameters. The dynamic rheological impedance index is used to characterize the system impedance characteristics after eliminating nonlinear interference from speed and fluid viscosity. Based on the dynamic rheological impedance index and the motor temperature, the confidence level of thermo-coupling anomaly is calculated. The confidence level of thermo-coupling anomaly is obtained by statistically analyzing the fluctuation energy of the dynamic rheological impedance index within a time window and weighting it in combination with the deviation of the real-time temperature of the motor stator winding or housing from the standard reference temperature. The confidence level of the thermal coupling anomaly is compared with a preset fault threshold. If the threshold is exceeded, the silicone stirring motor is determined to be abnormal, and the monitoring result is output.

2. The method for abnormal monitoring of a silicone stirring motor according to claim 1, characterized in that, The formula for calculating the dynamic rheological impedance index is as follows: In the formula, express The dynamic rheological impedance index at time t. express The effective value of the motor stator current at time t. This indicates the DC bus voltage of the frequency converter. express The mechanical speed of the motor at any given moment. This represents the power-law factor of rheology. Indicates the fluid resistance coefficient. Indicates the coefficient of mechanical friction. This represents the static bias constant.

3. The method for abnormal monitoring of a silicone stirring motor according to claim 2, characterized in that, The rheological power-law factor The acquisition method includes: acquiring historical data of the same type of silicone produced by the equipment in a healthy state, performing linear fitting with the natural logarithm of power as the ordinate and the natural logarithm of rotation speed as the abscissa, and the slope of the fitted line being the rheological power-law factor.

4. The method for abnormal monitoring of a silicone stirring motor according to claim 2, characterized in that, The fluid resistance coefficient It is obtained by fitting historical health data using the least squares method and is used to characterize the basic viscosity contribution of silicone; the mechanical friction coefficient is... It is obtained through no-load testing or regression analysis, and characterizes the linear frictional resistance of bearings and gears.

5. The method for abnormal monitoring of a silicone stirring motor according to claim 2, characterized in that, The static bias constant The value ranges from 3% to 5% of the motor's rated power. It is used to prevent the denominator of the formula from being zero during motor startup or in extremely low-speed standby mode, and to characterize the static friction power consumption of the system.

6. The method for abnormal monitoring of a silicone stirring motor according to claim 1, characterized in that, The formula for calculating the confidence level of the thermo-coupling anomaly is as follows: ； In the formula, Indicates the confidence level of the thermo-coupling anomaly. This indicates the number of sampling points in the sliding statistics window. Indicates the past number The dynamic rheological impedance index at each sampling point This represents the historical average of the dynamic rheological impedance index under healthy conditions. This indicates the real-time temperature of the motor stator windings or housing. Indicates the standard reference temperature. Indicates the thermal weighting coefficient. This indicates that the larger value between the real-time temperature and the standard reference temperature is taken.

7. The method for abnormal monitoring of a silicone stirring motor according to claim 6, characterized in that, The formula for calculating the confidence level of thermo-coupling anomalies uses The function performs a temperature limit clamping when the real-time temperature... Below standard reference temperature When, the forced value is To ensure that the input value of the logarithmic function is not less than 1, this prevents the calculation result from being negative or reducing the fault signal.

8. The method for abnormal monitoring of a silicone stirring motor according to claim 6, characterized in that, The thermal weighting coefficient The setting is based on the insulation and heat resistance class of the motor. The lower the insulation and heat resistance class, the larger the set value of the thermistor weighting coefficient.

9. The method for abnormal monitoring of a silicone stirring motor according to claim 1, characterized in that, The filtering preprocessing includes: using a sliding median filtering method to process the collected stator current, mechanical speed, DC bus voltage and motor temperature, with the filtering window length set to 500ms to remove spike pulses caused by electromagnetic interference.

10. A silica gel stirring motor malfunction monitoring system, characterized in that, It includes a processor and a memory, the memory storing computer instructions, which, when executed by the processor, implement the abnormal monitoring method for the silicone stirring motor according to any one of claims 1-9.

Images