Motor electric energy quality monitoring method based on Internet of Things

Abstract

The invention provides a motor electric energy quality monitoring method based on the Internet of Things, and relates to the technical field of industrial electrical measurement and operation and maintenance management, and the method comprises the steps: collecting electric energy quality data of a motor through an electric energy quality sensor, and the electric energy quality data comprise voltage data, frequency data, harmonic data and temperature data; and performing deep analysis on the power quality data through a machine learning algorithm to generate power quality monitoring data. According to the motor power quality monitoring method based on the Internet of Things, power quality data acquisition, machine learning algorithm analysis and an intelligent alarm system are combined, power quality data such as voltage, frequency, harmonic waves and temperature of a motor can be acquired in real time, and power quality monitoring data are generated through deep analysis; real-time monitoring and abnormal early warning of the electric energy quality of the motor are realized, and the operation parameters of the motor are adjusted by optimizing the control instruction, so that the operation efficiency is improved and the energy consumption is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial electrical measurement and operation and maintenance management, in particular to a motor power quality monitoring method based on Internet of Things. BACKGROUND

[0002] Currently, power quality monitoring has been widely applied in industrial fields. In the operation and management of large equipment such as motors, the stability of power quality is crucial for the efficiency and safety of the equipment. Existing power quality monitoring technologies usually use sensors to collect power parameters such as voltage, frequency, harmonics and temperature. Through the collected data, basic information can be provided for the operation status of the motor, so as to help maintenance personnel understand the working status of the motor in time. Many current power quality monitoring systems transmit data to monitoring platforms or clouds through wireless transmission technology, which is convenient for remote monitoring and data storage. With the promotion of industrial Internet of Things technology, monitoring systems gradually develop towards intelligence and automation. Combined with data analysis and processing technologies such as machine learning and big data analysis, some systems can preliminarily analyze the collected power quality data, provide power quality diagnosis and fault warning functions, etc.

[0003] However, the existing technology still has obvious defects. The existing power quality monitoring systems have made progress in data collection and basic analysis, but they still have a lot of room for improvement in terms of intelligence and real-time performance. Traditional monitoring systems usually rely on fixed thresholds to determine whether the power quality is abnormal. This static threshold determination method does not fully consider the dynamic changes in motor operation. In complex industrial environments, the load and operating status of the motor are constantly changing, and the power quality also fluctuates. This static threshold method is prone to false alarms or missed alarms, and cannot accurately reflect the true situation of motor power quality. Most existing power quality monitoring systems lack efficient adaptive adjustment functions, and it is difficult to provide personalized optimization suggestions for different working environments and motor characteristics. When power quality problems occur, traditional systems can only provide basic alarm functions, lack more in-depth analysis and subsequent optimization control measures, and the frequency of motor failure is high, and the maximum improvement of motor operating efficiency cannot be achieved. SUMMARY

[0004] In view of the deficiencies of the prior art, the present application provides a motor power quality monitoring method based on Internet of Things, which solves the technical problem of how to use machine learning algorithms to deeply analyze power quality data and generate power quality monitoring data to realize real-time monitoring and fault warning of motor power quality.

[0005] To achieve the above object, the present application is implemented by the following technical solutions: A motor electric energy quality monitoring method based on Internet of Things, comprising: S1. Collecting electric energy quality data of a motor through an electric energy quality sensor, wherein the electric energy quality data comprises voltage data, frequency data, harmonic data and temperature data.

[0006] S2. Generating electric energy quality monitoring data by deeply analyzing the electric energy quality data through a machine learning algorithm.

[0007] S3. Forming comparison analysis data by comparing the electric energy quality data and the electric energy quality monitoring data, forming an electric energy quality monitoring report by using a dynamic threshold adjustment method, and judging whether the electric energy quality of the motor is abnormal by a preset intelligent alarm strategy, and generating fault warning information if the electric energy quality is abnormal.

[0008] S4. Sending the fault warning information and the electric energy quality monitoring report to a user terminal, and showing the real-time state of the motor electric energy quality to the user through the user terminal, wherein the user terminal collects user feedback data through a data visualization tool.

[0009] S5. Generating electric energy operation optimization control instructions through a control model, wherein the control model generates the electric energy operation optimization control instructions according to the electric energy quality data and the user feedback data, guiding the user to take corresponding operation measures, thereby optimizing the motor operation efficiency, reducing energy consumption and prolonging the service life of the equipment.

[0010] Preferably, the electric energy quality sensor comprises a voltage sensor, a frequency sensor, a harmonic sensor and a temperature sensor.

[0011] Preferably, the formula of the machine learning algorithm is as follows: .

[0012] wherein, is an electric energy quality comprehensive score, is a weight coefficient trained according to the electric energy quality data, is voltage fluctuation, dimensionless, is frequency change, dimensionless, is harmonic content, dimensionless, and the voltage fluctuation, the frequency change and the harmonic content are normalized to the [0, 1] interval.

[0013] Preferably, the formula of the dynamic threshold adjustment method is as follows: .

[0014] wherein, is a dynamically adjusted electric energy quality threshold, dimensionless, is an initial threshold value, dimensionless, is a rate of change of voltage, dimensionless, is a rate of change of frequency, dimensionless, is an adjustment coefficient, dimensionless.

[0015] Preferably, the power quality monitoring report includes voltage monitoring data, frequency monitoring data, harmonic monitoring data and temperature monitoring data, the intelligent alarm strategy compares the power quality monitoring report with dynamic thresholds to generate the fault warning information, the dynamic thresholds range from a voltage monitoring data deviation of ±5%, a frequency monitoring data deviation of ±0.5 Hz, a harmonic monitoring data harmonic distortion THD≤5%, and a temperature monitoring data range of 130-155°C.

[0016] Preferably, the user terminal includes a smartphone and a computer, the fault warning information and the power quality monitoring report are transmitted to the user terminal through a wireless communication mode, the wireless communication mode conforms to the IEEE 802.11 standard, and the fault warning information includes voltage anomaly warning, frequency fluctuation warning, harmonic distortion warning and temperature anomaly warning.

[0017] Preferably, the data visualization tool collects the power quality data through the following model formula: .

[0018] wherein, is a voltage display value of a real-time power quality visualization chart, dimensionless, is a display coefficient, dimensionless, is a voltage amplitude, dimensionless, is a time series phase, dimensionless, is a relationship with time , is an angular frequency, unit , is time, unit s, is an initial phase, unit rad.

[0019] Preferably, the control model determines the optimized and adjusted motor operating parameters through the power operation optimization instruction, and the formula of the control model is as follows: wherein, is an optimized motor power, unit W, is a nominal power of the motor, unit W, is a deviation value of the power quality score, dimensionless, The adjustment coefficient, in W, is used to dynamically adjust the motor's operating parameters based on the comprehensive power quality score, thereby optimizing power quality and improving operating efficiency.

[0020] This invention provides a method for monitoring the power quality of motors based on the Internet of Things (IoT). It has the following beneficial effects: This invention utilizes an IoT-based power quality monitoring method, combining power quality data acquisition, machine learning algorithm analysis, and an intelligent alarm system, to acquire real-time power quality data such as motor voltage, frequency, harmonics, and temperature. Through in-depth analysis, it generates power quality monitoring data. This motor power quality monitoring method can accurately monitor the motor's power quality status, promptly identify potential power quality anomalies, and prevent equipment failures caused by power quality issues, thereby ensuring stable motor operation and reducing maintenance costs.

[0021] This IoT-based motor power quality monitoring method, combining dynamic threshold adjustment and intelligent alarm strategies, provides accurate early warning information when motor anomalies occur. User feedback is collected through data visualization tools on user terminals to further optimize motor operating parameters. By optimizing control commands, motor operating efficiency is effectively improved, energy consumption is reduced, equipment lifespan is extended, and the overall reliability and economy of the industrial system are enhanced. Attached Figure Description

[0022] Fig. 1 This is a schematic diagram of the power quality data acquisition and processing flow. Fig. 2 This is a flowchart of intelligent alarm and fault early warning; Fig. 3 This is a schematic diagram of the overall structure of the power quality monitoring system. Detailed Implementation

[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] Example 1 like Figs. 1-3 As shown, this embodiment of the invention provides a method for monitoring the power quality of a motor based on the Internet of Things, including: S1. Collecting power quality data of the motor through power quality sensors, the power quality data including voltage data, frequency data, harmonic data, and temperature data. The power quality sensors include a voltage sensor, a frequency sensor, a harmonic sensor, and a temperature sensor.

[0025] Voltage data refers to the voltage values ​​experienced by the motor during operation, including instantaneous voltage, average voltage, and voltage fluctuations. Voltage data can reflect whether the motor is affected by excessively high or low voltage. Excessive voltage fluctuations may threaten the stability and lifespan of the motor.

[0026] Frequency data: Frequency data indicates the frequency variation of the power supply when the motor is running.

[0027] Harmonic data: Harmonic data involves the non-sinusoidal waveform components in the motor current. Harmonics are caused by non-linear loads generated during equipment operation. The effects of harmonics on motors typically manifest as decreased efficiency, overheating, and damage.

[0028] Temperature data: Temperature data refers to the temperature changes inside the motor and its surrounding environment. Excessively high temperatures can damage the motor's insulation, affecting its normal operation.

[0029] Voltage sensors are used to monitor voltage fluctuations in motors in real time, ensuring that the voltage remains within the normal operating range of the motor and preventing equipment failures caused by abnormal voltage.

[0030] The frequency sensor is responsible for detecting frequency changes during motor operation. Frequency fluctuations in the motor may affect its performance, and excessive frequency changes may cause equipment damage.

[0031] Harmonic sensors are used to capture harmonic components in motor current. Harmonics can affect the operating efficiency of the motor and may cause problems such as overheating.

[0032] Temperature sensors monitor the motor's operating temperature in real time. High temperatures can cause the motor to overheat or even burn out, so temperature monitoring is crucial for the safe operation of the motor.

[0033] S2. Power quality data is generated through in-depth analysis of power quality data using machine learning algorithms. The formula for the machine learning algorithm is as follows: .

[0034] in, The overall power quality score is calculated as follows: These are the weighting coefficients obtained by training based on the power quality data. Voltage fluctuation, dimensionless. It represents frequency variation, dimensionless. The harmonic content is dimensionless, and the voltage fluctuation, frequency change, and harmonic content are normalized to the [0, 1] interval.

[0035] Example dataset: Suppose the following data is collected: Table 1: Power quality monitoring data.

[0036]

[0037] in, These are the weight coefficients obtained after training. Assume the training results are as follows: =0.5.

[0038] =0.3.

[0039] =0.2.

[0040] =10.

[0041] Based on the above formula, the comprehensive score at each time point is calculated. : Table 2: Electric power quality monitoring data and normalized comprehensive score of motor.

[0042]

[0043] Voltage, frequency, harmonics, and temperature are real-time power quality data for motors.

[0044] By using machine learning models and combining data to generate a comprehensive score Q(t), the quality of electrical energy in a motor can be assessed.

[0045] S3. By comparing power quality data and power quality monitoring data, comparative analysis data is generated. A dynamic threshold adjustment method is used to create a power quality monitoring report from this comparative analysis data. A preset intelligent alarm strategy is then used to determine if there are any abnormalities in the motor's power quality. If an abnormality is found, a fault warning is generated. The formula for the dynamic threshold adjustment method is as follows: .

[0046] in, The dynamically adjusted power quality threshold is dimensionless. The initial threshold is dimensionless. The rate of change of voltage is dimensionless. The rate of change of frequency is dimensionless. The adjustment coefficient is dimensionless. The power quality monitoring report includes voltage monitoring data, frequency monitoring data, harmonic monitoring data, and temperature monitoring data. The intelligent alarm strategy compares the power quality monitoring report with dynamic thresholds to generate fault warning information. The dynamic threshold ranges are: voltage monitoring data deviation ±5%, frequency monitoring data deviation ±0.5Hz, harmonic distortion (THD) of harmonic monitoring data ≤5%, and temperature monitoring data range is 110℃ to 130℃.

[0047] S4. Send fault warning information and power quality monitoring reports to the user terminal, displaying the real-time status of the motor's power quality to the user. The user terminal collects user feedback data through data visualization tools. The user terminal includes smartphones and computers. Fault warning information and power quality monitoring reports are transmitted to the user terminal wirelessly, conforming to the IEEE 802.11 standard. Fault warning information includes voltage anomaly warnings, frequency fluctuation warnings, harmonic distortion warnings, and temperature anomaly warnings. The data visualization tool collects power quality data using the following model formula: in, The voltage display value is a dimensionless value for a real-time power quality visualization chart. To display the coefficients, dimensionless. The voltage amplitude is dimensionless. The phase of the time series is dimensionless. The relationship with time is , Angular frequency, unit , For time, in seconds. The initial phase is expressed in rad.

[0048] S5. The control model generates optimized power operation control commands based on power quality data and user feedback data. These commands guide users to take appropriate operational measures, thereby optimizing motor operating efficiency, reducing energy consumption, and extending equipment lifespan. The control model determines the optimized motor operating parameters using these optimized power operation commands. The formulas for the control model are as follows: in, The optimized motor power is expressed in watts (W). The nominal power of the motor is expressed in watts (W). The deviation value for the power quality score, dimensionless. The adjustment coefficient, measured in W, dynamically adjusts the motor's operating parameters based on the comprehensive power quality score, thereby optimizing power quality and improving operating efficiency.

[0049] Example 2 This embodiment explains how to form comparative analysis data by comparing power quality data and power quality monitoring data, and how to use a dynamic threshold adjustment method to generate a power quality monitoring report from the comparative analysis data. The monitoring and analysis of motor power quality can promptly detect problems and generate fault warnings, ensuring that the motor can be dealt with in a timely manner under abnormal conditions.

[0050] 1. Data collection and preliminary processing Motor operating data is collected from power quality sensors. This data includes voltage. ,frequency And other power quality related parameters.

[0051] For example, suppose power quality data of a motor was collected at multiple time points, and the data is as follows: Table 3: Power quality monitoring data for motors.

[0052]

[0053] 2. Dynamic threshold adjustment According to the formula: in, The dynamically adjusted power quality threshold is dimensionless. The initial threshold is dimensionless. The rate of change of voltage is dimensionless. The rate of change of frequency is dimensionless. The adjustment coefficient is dimensionless.

[0054] Assumption: Initial power quality value =75.

[0055] Voltage change rate and rate of change of frequency It is calculated from the change between the current time and the previous time.

[0056] Adjustment coefficient =0.5、 =0.3.

[0057] 2.1 Power Quality After Calculation Adjustment Time point 1: Time point 2: Time point 3: Time point 4: 3. Dynamic threshold setting and alarm logic Based on the set dynamic threshold, the range of power quality monitoring data is as follows: The voltage monitoring data deviation is ±5%, meaning the normal range of voltage is ±5% of the voltage value.

[0058] The frequency monitoring data deviation is ±0.5Hz, and the normal frequency range is 50Hz ±0.5Hz, that is, 49.5Hz to 50.5Hz.

[0059] The harmonic distortion rate of the harmonic monitoring data should be less than or equal to 5%.

[0060] The normal range for temperature monitoring data is 130℃ to 155℃.

[0061] Comparison and Alarm: Time point 1: Voltage 220.0V, frequency 50.2Hz, harmonics 3.0%, temperature 76℃. Voltage: 220.0V is within the range of 209.0V to 231.0V, which is normal.

[0062] Frequency: 50.2Hz is within the range of 49.7Hz to 50.7Hz, which is normal.

[0063] Harmonics: 3.0% is less than 5%, which is normal.

[0064] Temperature: 76℃ is within the range of 130℃ to 155℃, which is normal.

[0065] Time point 2: Voltage 225.0V, frequency 50.7Hz, harmonics 4.0%, temperature 160℃. Voltage: 225.0V is within the range of 209.0V to 231.0V, which is normal.

[0066] Frequency: 50.7Hz is within the range of 49.7Hz to 50.7Hz, which is normal.

[0067] Harmonics: 4.0% is less than 5%, which is normal.

[0068] Temperature: 160℃ exceeds the upper limit of 155℃, temperature abnormality alarm.

[0069] Time point 3: Voltage 210.0V, frequency 49.8Hz, harmonics 2.5%, temperature 135℃. Voltage: 210.0V is within the range of 209.0V to 231.0V, which is normal.

[0070] Frequency: 49.8Hz is within the range of 49.7Hz to 50.7Hz, which is normal.

[0071] Harmonics: 2.5% is less than 5%, which is normal.

[0072] Temperature: 135℃. Within the range of 130℃ to 155℃, there is no alarm.

[0073] Time point 4: Voltage 230.0V, frequency 51.0Hz, harmonics 5.1%, temperature 145℃. Voltage: 230.0V is within the range of 209.0V to 231.0V, which is normal.

[0074] Frequency: 51.0Hz exceeds the upper limit of 50.7Hz, frequency abnormality alarm.

[0075] Harmonics: 5.1% exceeds 5%, triggering a harmonic anomaly alarm.

[0076] Temperature: 145℃ is within the range of 130℃ to 155℃, which is normal.

[0077] Frequency warning and harmonic warning.

[0078] 4. Power quality monitoring reports and early warning output Table 4: Power Quality Monitoring Report.

[0079]

[0080] Through dynamic threshold adjustment and intelligent alarm strategies, the system can monitor the power quality of the motor in real time, automatically detect abnormal power quality conditions, and generate corresponding fault warning information.

[0081] Example 3 This embodiment will demonstrate how to generate a power quality monitoring report through dynamic adjustment and model analysis, and transmit it to the user terminal via wireless communication, so that the user can monitor the power quality status of the motor in real time and receive timely alarms when abnormalities occur, ensuring the safe operation of the equipment.

[0082] 1. Data Acquisition and Processing The voltage data of the motor is collected in real time using a power quality monitoring sensor. Assume the collected voltage data is as follows: Table 5: Voltage values ​​at each moment.

[0083]

[0084] 2. Dynamic threshold adjustment and modeling of voltage monitoring data According to the formula: in, The voltage display value is a dimensionless value for a real-time power quality visualization chart. To display the coefficients, dimensionless. The voltage amplitude is dimensionless. The phase of the time series is dimensionless. The relationship with time is , Angular frequency, unit , For time, in seconds. Let be the initial phase, in rad. The voltage display value is a dimensionless value for a real-time power quality visualization chart. To display the coefficients, dimensionless. The voltage amplitude is dimensionless after normalization. The phase of the time series is dimensionless.

[0085] Normalization of voltage data: First, normalize the voltage data U(t), scaling the voltage amplitude to its maximum value. Assuming the maximum voltage is 230V, then: The voltage data after normalization is as follows: Table 6: Normalized voltage values.

[0086]

[0087] Choose dimensionless coefficients : Suppose that dimensionless coefficients are obtained through experiments or machine learning models. =0.8、 =1.2, =1.0.

[0088] Calculate the voltage display value V(t) from the power quality monitoring chart: The voltage display value V(t) is calculated according to the formula, assuming... The time interval for each moment: For time point 1, θ1 = 0°.

[0089] For time point 2, θ2 = 90°.

[0090] For time point 3, θ3 = 180°.

[0091] For time point 4, θ4 = 270°.

[0092] The power quality monitoring data V(t) is calculated using the angle value and the normalized voltage data.

[0093] 3. Generate power quality monitoring reports Based on the above calculations, a power quality monitoring report is generated, including real-time voltage display values. Assume the calculation results are as follows: Table 7: Real-time power quality monitoring data and voltage display value report.

[0094]

[0095] Power quality monitoring reports are sent to user terminals via wireless communication technology. If the voltage display value exceeds the set dynamic threshold range, an alarm mechanism is triggered.

[0096] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for monitoring the power quality of a motor based on the Internet of Things, characterized in that, include: S1. Collect power quality data of the motor through a power quality sensor, wherein the power quality data includes voltage data, frequency data, harmonic data and temperature data; S2. Power quality monitoring data is generated by performing in-depth analysis of the power quality data using machine learning algorithms; S3. By comparing the power quality data and the power quality monitoring data, comparative analysis data is formed. A dynamic threshold adjustment method is used to generate a power quality monitoring report from the comparative analysis data. A preset intelligent alarm strategy is used to determine whether there is an abnormality in the power quality of the motor. If there is an abnormality in the power quality, a fault warning message is generated. S4. Send the fault warning information and the power quality monitoring report to the user terminal, and display the real-time status of the motor power quality to the user through the user terminal. The user terminal collects user feedback data through data visualization tools. S5. Generate power operation optimization control instructions through a control model, wherein the control model generates the power operation optimization control instructions based on the power quality data and the user feedback data.

2. The method for monitoring the power quality of a motor based on the Internet of Things according to claim 1, characterized in that: The power quality sensor includes a voltage sensor, a frequency sensor, a harmonic sensor, and a temperature sensor.

3. The method for monitoring the power quality of a motor based on the Internet of Things according to claim 1, characterized in that: The formula for the machine learning algorithm is as follows: ， in, The overall power quality score is calculated as follows: These are the weighting coefficients obtained by training based on the power quality data. For voltage fluctuations, For frequency variation, The harmonic content is determined by normalizing the voltage fluctuation, frequency change, and harmonic content to the [0, 1] interval.

4. The method for monitoring the power quality of a motor based on the Internet of Things according to claim 1, characterized in that: The formula for the dynamic threshold adjustment method is as follows: ， in, The dynamically adjusted power quality threshold. As the initial threshold, The rate of change of voltage, The rate of change of frequency, This is for adjusting the coefficient.

5. The method for monitoring the power quality of a motor based on the Internet of Things according to claim 1, characterized in that: The power quality monitoring report includes voltage monitoring data, frequency monitoring data, harmonic monitoring data, and temperature monitoring data. The intelligent alarm strategy compares the power quality monitoring report with dynamic thresholds to generate the fault warning information. The range of the dynamic thresholds is ±5% for the voltage monitoring data deviation, ±0.5Hz for the frequency monitoring data deviation, ≤5% for the harmonic distortion (THD) of the harmonic monitoring data, and 110℃ to 130℃ for the temperature monitoring data.

6. The method for monitoring the power quality of a motor based on the Internet of Things according to claim 1, characterized in that: The user terminal includes a smartphone and a computer. The fault warning information and the power quality monitoring report are transmitted to the user terminal via wireless communication. The wireless communication method conforms to the IEEE 802.11 standard. The fault warning information includes voltage abnormality warning, frequency fluctuation warning, harmonic distortion warning, and temperature abnormality warning.

7. The method for monitoring the power quality of a motor based on the Internet of Things according to claim 1, characterized in that: The data visualization tool collects the power quality data using the following model formula: ， in, The voltage display value is for a real-time power quality visualization chart. To display the coefficients, Voltage amplitude, For time series phase, The relationship with time is , Angular frequency, For time, This is the initial phase.

8. The method for monitoring the power quality of a motor based on the Internet of Things according to claim 1, characterized in that: The control model determines the optimized motor operating parameters through the power operation optimization command, and the formula of the control model is as follows: ， in, For the optimized motor power, The nominal power of the motor. The deviation value for the power quality score. This is for adjusting the coefficient.

Images