Factory motor energy-saving operation monitoring system based on big data analysis

Abstract

The present application relates to the technical field of motor operation monitoring, and discloses a factory motor energy-saving operation monitoring system based on big data analysis, including: a data acquisition module, which is used to collect multi-dimensional data of motor operation in real time; a data processing module, which pre-processes the collected data and marks abnormal data; an analysis and diagnosis module, which performs trend analysis and fault prediction on the motor operation status based on big data algorithms; a storage module, which is used to store raw data and analysis results, and supports historical data retrieval; a communication module, which is connected to a cloud server or a local terminal by wireless or wired means to achieve data interaction. Winding faults are judged by electrical parameters, and early hidden dangers are identified by audio characteristics. The characteristics of multi-dimensional data fusion enable the system to warn of faults in advance and make targeted diagnostic suggestions, reducing downtime and economic losses caused by faults.

Description

Technical Field

[0001] The present invention relates to the technical field of motor operation monitoring, and in particular to a factory motor energy-saving operation monitoring system based on big data analysis. Background Art

[0002] In modern industrial production, motors are the main power equipment, and the reliability and energy efficiency of their operating status play a key role in production efficiency and cost control. However, traditional motor monitoring methods mostly rely on regular inspections and empirical judgments, which lack real-time and scientific nature, making it difficult to detect potential faults in a timely manner, often causing equipment to shut down due to sudden failures, causing immeasurable losses to production. In addition, regular shutdown maintenance methods usually cannot accurately judge the actual health status of the motor, which may lead to waste of resources or insufficient maintenance, further affecting the operating efficiency of the equipment.

[0003] In recent years, with the rapid development of sensing technology and data analysis technology, motor operation status monitoring technology based on sensor acquisition has gradually become a research hotspot. For example, the temperature rise of the motor is monitored by temperature sensors, and the looseness or damage of mechanical parts is identified by vibration sensors. However, these single-dimensional monitoring methods are usually only targeted at specific types of faults, lack the ability to fuse multi-dimensional data, and cannot comprehensively analyze the comprehensive operation status of the motor. In addition, most existing technologies only provide passive monitoring, lack the ability to deeply process and analyze data, and it is difficult to achieve early prediction and effective intervention of faults. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides a factory motor energy-saving operation monitoring system based on big data analysis, which solves the problems that the existing monitoring system lacks multi-dimensional data fusion capability, cannot conduct a comprehensive analysis of the comprehensive operating status of the motor, and only provides passive monitoring and lacks the ability to deeply process and analyze data.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a factory motor energy-saving operation monitoring system based on big data analysis, comprising:

[0006] Data acquisition module, used to collect multi-dimensional data of motor operation in real time;

[0007] Data processing module, which pre-processes the collected data and marks abnormal data;

[0008] Analysis and diagnosis module, which performs trend analysis and fault prediction on motor operation status based on big data algorithms;

[0009] Storage module, used to store raw data and analysis results, and support historical data retrieval;

[0010] The communication module connects to the cloud server or local terminal wirelessly or wiredly to achieve data interaction;

[0011] Alarm module, triggering sound and light alarm and remote notification when abnormal operation or deviation of energy-saving indicators is detected;

[0012] User terminal module, providing real-time monitoring interface and analysis reports;

[0013] The energy-saving control module adjusts the motor operating parameters based on the analysis results to achieve energy-saving optimization.

[0014] Preferably, the data acquisition module includes:

[0015] Temperature sensing unit, used to collect temperature data of the motor and the environment;

[0016] Vibration sensor unit, used to collect the vibration amplitude and direction when the motor is running;

[0017] Electrical parameter sensing unit, used to measure voltage, current and power factor;

[0018] The audio sensor unit is used to monitor the noise level and abnormal sound wave signals when the motor is running.

[0019] Preferably, the data processing module includes:

[0020] Data cleaning unit, used to remove invalid data and correct abnormal data;

[0021] A data compression unit, used to compress a large amount of real-time data to improve storage and transmission efficiency;

[0022] A feature extraction unit, used to extract key parameters from the collected data;

[0023] Parameter normalization unit is used to unify the data dimension to support subsequent analysis.

[0024] Preferably, the analysis and diagnosis module includes:

[0025] A prediction unit that predicts the probability of motor failure or reduced efficiency based on a machine learning algorithm;

[0026] A fault classification unit, used to identify specific fault types;

[0027] Trend analysis unit, used to analyze the change of motor operation status over time;

[0028] An energy-saving evaluation unit is used to calculate the energy efficiency of the current operating state and provide optimization suggestions. Preferably, the storage module includes:

[0029] A real-time storage unit for storing current operation data;

[0030] Historical data storage unit, used to store the historical data of motor operation for a long time;

[0031] A data retrieval unit is used to quickly locate the operation records of a specific time period or parameters; a data backup unit is used to back up important data to the cloud or local storage device. Preferably, the communication module includes:

[0032] Wireless communication unit, supporting Wi-Fi, Bluetooth and 4G / 5G connections;

[0033] Wired communication unit, supporting industrial standard communication protocols such as RS485 and Ethernet;

[0034] Data encryption unit, used to ensure the security of data transmission;

[0035] A cloud synchronization unit is used to synchronize local data to a remote server or management platform. Preferably, the alarm module includes:

[0036] Sound and light alarm unit, used to remind operators to pay attention on site;

[0037] Remote notification unit, push alarm information via SMS, email or mobile application; threshold customization unit, support users to set alarm trigger conditions;

[0038] A multi-level alarm unit is divided into early warning, minor and major alarms according to the severity of the fault. Preferably, the user terminal module includes:

[0039] Real-time monitoring unit, used to display real-time data of motor operation status;

[0040] Report generation unit, generating energy saving and fault analysis reports;

[0041] User interaction unit, supporting parameter setting and query;

[0042] The mobile access unit supports remote access via a smart phone or tablet computer. Preferably, the energy-saving control module includes:

[0043] Parameter adjustment unit, automatically adjusts operating parameters based on optimization strategies;

[0044] Energy-saving mode switching unit, automatically switches to high-efficiency energy-saving mode according to operating conditions; energy efficiency evaluation unit, calculates motor operating energy consumption in real time and provides improvement suggestions;

[0045] Intelligent shutdown unit automatically stops the motor during non-essential operation to save energy.

[0046] Preferably, the system also includes a big data platform, which is used to:

[0047] Centrally store operating data from multiple motors;

[0048] Provide global analysis of multi-motor operating status;

[0049] Support customized energy-saving strategies and automatically send them to each motor;

[0050] Generate regular energy-saving operation reports and score the motor health status.

[0051] The present invention provides a factory motor energy-saving operation monitoring system based on big data analysis.

[0052] Beneficial effects:

[0053] 1. The present invention significantly improves the comprehensiveness and accuracy of motor operation status monitoring through real-time collection and fusion analysis of multi-dimensional data such as temperature, vibration, electrical parameters, and audio frequency. The collaborative processing of different data dimensions can not only capture abnormal information that may be missed by a single sensor, but also accurately locate the source of the fault through multi-feature correlation analysis, such as identifying mechanical problems through vibration spectrum, judging winding faults through electrical parameters, and identifying early hidden dangers through audio frequency features. The characteristics of multi-dimensional data fusion enable the system to warn of faults in advance and make targeted diagnostic suggestions, reducing downtime and economic losses caused by faults.

[0054] 2. Based on data analysis, the present invention combines the energy-saving control module to achieve intelligent optimization of motor operation. Through dynamic adjustment of motor operating parameters (such as speed and load), intelligent switching of energy-saving modes, and ineffective operation shutdown and other strategies, the system can adapt to production needs in real time and reduce unnecessary energy consumption. In addition, based on the energy efficiency evaluation module, the system can provide quantitative energy consumption analysis and optimization suggestions, thereby significantly improving the energy utilization efficiency of the equipment and promoting green production.

[0055] 3. The present invention realizes the big data fault prediction capability driven by multi-sensor collaboration through the deep integration of the data acquisition module and the analysis and diagnosis module. Compared with the traditional fault monitoring system based on a single sensor, the present invention adopts multi-dimensional data fusion technology such as temperature, vibration, electrical parameters and audio frequency, and inputs multiple signals collected in real time into a unified analysis model. By extracting features from transient signals and combining machine learning algorithms for multivariate trend analysis and prediction, the system can accurately identify early signs of faults. The system can locate the source of the fault by combining the frequency characteristics of vibration and audio signals, and further verify it by analyzing temperature change trends and electrical parameter anomalies. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 is a system architecture diagram of the present invention;

[0057] Figure 2 It is a schematic diagram of a data acquisition module of the present invention;

[0058] Figure 3 It is a schematic diagram of a data processing module of the present invention;

[0059] Figure 4 is a schematic diagram of the analysis and diagnosis module of the present invention;

[0060] Figure 5 It is a schematic diagram of a storage module of the present invention;

[0061] Figure 6 It is a schematic diagram of a communication module of the present invention;

[0062] Figure 7 It is a schematic diagram of an alarm module of the present invention;

[0063] Figure 8 It is a schematic diagram of a user terminal module of the present invention;

[0064] Fig. 9 It is a schematic diagram of the energy-saving control module of the present invention. DETAILED DESCRIPTION

[0065] The following will be combined with the drawings in the specification of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] Example:

[0067] Please see attached Figure 1 -Attached Fig. 9 The embodiment of the present invention provides a factory motor energy-saving operation monitoring system based on big data analysis, including:

[0068] 1. Data acquisition module:

[0069] The data acquisition module is the primary link of the system, responsible for real-time monitoring of the multi-dimensional physical and electrical parameters of the motor operation, providing comprehensive and accurate data support for subsequent processing and analysis. The module contains a variety of sensor units, which work together to achieve high-frequency and wide-coverage state perception, ensuring the diversity and accuracy of the collected data.

[0070] In this embodiment, the temperature sensing unit uses a Pt100 platinum resistance sensor, which is installed on the motor housing and bearings to detect temperature fluctuations through resistance changes. The sensor is connected to the sampling circuit, and the sampling frequency is set to 10Hz. In order to enhance the temperature response speed, the outer layer of the sensor adopts a protective shell with high thermal conductivity, and a calibration experiment is performed before sampling to eliminate system deviations.

[0071] In this embodiment, the vibration sensing unit uses a MEMS (micro-electromechanical system) accelerometer installed near the motor bearing seat, which collects vibration acceleration signals and calculates the vibration amplitude and frequency in combination with a three-axis direction correction algorithm. The sensor outputs an analog signal, which is converted into a digital signal by an analog-to-digital converter and then transmitted to the data processing module.

[0072] In this embodiment, the electrical parameter sensing unit is composed of a Hall current sensor and a voltage sensor, which monitors current and voltage fluctuations in a non-contact manner, with a collection frequency of 1kHz, and the output data is transmitted to the processing module via the SPI interface. The power factor is calculated from the phase difference between current and voltage, and the formula is as follows:

[0073]

[0074] PF: power factor;

[0075] P: active power (unit: W);

[0076] Q: reactive power (unit: VAR);

[0077] P and Q are calculated using current and voltage sensors, respectively.

[0078] In this embodiment, the audio sensor unit uses a combination of a digital microphone and a noise filtering circuit to identify abnormal audio features by picking up the running sound wave signal and combining the short-time Fourier transform (STFT) to analyze the sound spectrum changes, where the time-frequency energy distribution formula of the signal is:

[0079]

[0080] STFT{x(t)}: The result of short-time Fourier transform, which represents the amplitude of the signal at frequency f and time τ;

[0081] x(t): time domain signal;

[0082] w(t-τ): sliding window function, commonly used Hanning window or Gaussian window;

[0083] f: frequency (unit: Hz);

[0084] τ: time offset (unit: s);

[0085] x(t) is the collected original signal, which is input into the STFT algorithm after preprocessing;

[0086] w(t-τ) is calculated by selecting a suitable window function.

[0087] Temperature and vibration signals reflect the mechanical operating status of the motor, electrical parameters show energy efficiency and load characteristics, and audio data supplements fault location information. Multiple sensors work together to form a three-dimensional monitoring network, improving system data richness and diagnostic accuracy.

[0088] 2. Data processing module:

[0089] The data processing module cleans, compresses, extracts features and normalizes the collected raw signals to ensure the validity and uniformity of the data and provide high-quality data input for subsequent analysis. The module focuses on the accuracy and efficiency of the processing process and designs multiple sub-modules for division of labor and collaboration.

[0090] In this embodiment, the data cleaning unit uses a two-layer algorithm based on threshold detection and outlier analysis to process abnormal data. Data with a temperature signal change rate exceeding 10°C / second is marked as abnormal; data is removed when the root mean square value of the vibration signal deviates from the mean by 3 times the standard deviation. The cleaned data is filled by linear interpolation.

[0091] In this embodiment, the data compression unit uses a lossless compression algorithm (such as Huffman coding) to compress 100 data points collected in 1 second to 30% of the original size. In addition, the time-frequency characteristics are optimized using wavelet compression technology to reduce storage overhead.

[0092] In this embodiment, the feature extraction unit combines wavelet transform and fast Fourier transform (FFT) to perform spectrum feature decomposition on the vibration signal to extract frequency, amplitude and harmonic characteristics. The electrical signal is decomposed by fundamental wave to extract harmonic content and total harmonic distortion rate;

[0093] 1. The vibration frequency feature extraction formula is as follows:

[0094]

[0095] f k : frequency component of the vibration signal (unit: Hz);

[0096] F s : Sampling frequency (unit: Hz), set by the vibration sensor unit sampling;

[0097] N: number of signal sampling points;

[0098] k: frequency index, corresponding to the frequency component of FFT;

[0099] The time domain signal is collected by the vibration sensing unit, and the frequency domain characteristics are obtained by discrete Fourier transform.

[0100] 2. The calculation formula of harmonic distortion rate is as follows:

[0101]

[0102] THD: Total harmonic distortion (unit: %), a measure of the degree of harmonic distortion of electrical signals;

[0103] V1: amplitude of fundamental component (unit: V);

[0104] V n : The amplitude of the nth harmonic component (unit: V);

[0105] The voltage signal is collected through the electrical parameter sensing unit, and the amplitude of each harmonic component is extracted using FFT.

[0106] In this embodiment, the parameter normalization unit uses the Z-score normalization method to normalize all data to the range of [0,1]. For data with nonlinear distribution such as temperature and current, the Box-Cox transformation is used to improve the distribution symmetry.

[0107] The cleaning step ensures data quality, compression reduces data redundancy, feature extraction increases data expressiveness, and normalization unifies the scale to facilitate analysis and modeling.

[0108] 3. Analysis and diagnosis module:

[0109] The analysis and diagnosis module combines machine learning and statistical analysis techniques to perform fault prediction, classification and trend analysis on the processed data, while evaluating the energy efficiency of motor operation, providing a reliable basis for optimization decision-making.

[0110] In this embodiment, the prediction unit uses a memory network to predict the motor operating state. The input includes multidimensional data from the last 24 hours, and the output is the probability distribution of the motor operating state in the next hour. The training model uses the historical data set, and the optimization goal is to minimize the prediction error. The memory network formula is as follows:

[0111]

[0112] L: loss value, used to optimize the memory formula model;

[0113] N: number of training data samples;

[0114] y i : actual observed value;

[0115] Model prediction value;

[0116] y i From historical sensor data; is the prediction result of the memory model.

[0117] In this embodiment, the fault classification unit uses a support vector machine (SVM) to accurately classify the fault type, including bearing wear, rotor imbalance, and winding overheating. The input features include spectral features and temperature rise rate. The temperature rise rate formula is as follows:

[0118] ΔT=T motor -T ambient

[0119] ΔT: Motor temperature rise (unit: °C), that is, the difference between the motor operating temperature and the ambient temperature.

[0120] T motor : Motor operating temperature (unit: °C), measured by the temperature sensor unit (Pt100).

[0121] T ambient : Ambient temperature (unit: °C), measured by sensors installed around the motor.

[0122] T motor and T ambient The temperature is directly collected by the temperature sensor, and the sampling frequency can be set to 10 times per second.

[0123] In this embodiment, the trend analysis unit analyzes the time variation trend of temperature, current and efficiency by a sliding window method to identify periodic anomalies or efficiency decline, wherein the sliding average trend calculation formula is as follows:

[0124]

[0125] y t : The sliding average of time t;

[0126] x i : the i-th item in the original data sequence;

[0127] w: sliding window size;

[0128] x i It is the operating parameter data collected in real time (such as temperature and vibration amplitude).

[0129] In this embodiment, the energy-saving evaluation unit calculates the energy efficiency index of the motor (such as power factor, output power / input power ratio) in real time and provides energy-saving optimization suggestions.

[0130] Fault prediction and classification provide early warnings for operations management, trend analysis identifies performance change patterns, and energy saving assessment helps optimize energy efficiency.

[0131] 4. Storage module:

[0132] The storage module provides the system with efficient and secure data storage and backup functions, supports fast access to real-time data and long-term preservation of historical data, and ensures data traceability.

[0133] In this embodiment, the real-time storage unit uses a Redis memory database to store data within the last minute, with a delay of less than 1 millisecond.

[0134] In this embodiment, the historical data storage unit is based on the distributed time series database TimescaleDB, which supports concurrent queries and dynamic expansion.

[0135] In this embodiment, the data retrieval unit uses a query algorithm based on index optimization to support fast retrieval of data by time, parameter or device.

[0136] In this embodiment, the data backup unit uploads data to the cloud through a scheduled task, while retaining local backup and supporting offline recovery.

[0137] Real-time storage provides support for monitoring, historical storage is used for long-term analysis, and backup ensures data integrity and security.

[0138] 5. Communication module:

[0139] Overview: The communication module is responsible for realizing real-time data interaction between the system and external devices, supporting multiple communication protocols and network environments, and ensuring the efficiency and security of data transmission. The module combines wireless and wired communication methods to adapt to different application scenarios.

[0140] In this embodiment, the wireless communication unit supports Wi-Fi (802.11ac standard), 4G LTE and 5G networks, realizes efficient data transmission through the MQTT protocol, and adopts the QoS (quality of service) mechanism to prioritize the transmission of important data and reduce the packet loss rate.

[0141] In this embodiment, the wired communication unit implements industrial-grade communication through the Modbus protocol and the RS485 interface, ensuring the stability of data transmission in a high electromagnetic interference environment, and supporting the Ethernet interface for high-speed data exchange.

[0142] In this embodiment, the data encryption unit uses the AES-256 encryption algorithm to encrypt the data packet, combined with TLS (Transport Layer Security Protocol) to ensure the confidentiality and integrity of the data during the transmission process.

[0143] In this embodiment, the cloud synchronization unit is connected to the cloud platform through a RESTful API to achieve real-time data upload and support two-way data flow for cloud parameter distribution.

[0144] Wireless communication meets flexible deployment requirements, wired communication provides high stability, and data encryption and cloud synchronization jointly ensure data security and availability.

[0145] 6. Alarm module:

[0146] The alarm module will send out alarms in various ways when the motor is running abnormally, reminding on-site operators and remote managers to handle the problem in time to prevent the fault from expanding. The module is designed with multi-level alarms and flexible trigger mechanisms to meet the needs of different scenarios.

[0147] In this embodiment, the sound and light alarm unit uses a buzzer and a high-brightness LED light for local alarm, and adjusts the frequency of sound and light according to the severity of the abnormality. For example, a mild alarm is once every 5 seconds, and a severe alarm flashes and sounds continuously.

[0148] In this embodiment, the remote notification unit pushes notifications via email, SMS gateway, and mobile application. For example, when the motor temperature is detected to exceed a preset threshold (such as 100°C), an alarm message is sent to the management personnel, along with the operating parameter details.

[0149] In this embodiment, the threshold customization unit provides a user interface, allowing the alarm triggering conditions, such as the upper temperature limit, the vibration amplitude threshold, etc., to be flexibly set according to the device type and application scenario.

[0150] In this embodiment, the multi-level alarm unit divides the alarm level into four levels: information, warning, warning and emergency, which trigger different forms of notifications (such as log recording only, on-site alarm, remote notification, etc.).

[0151] Audible and visual alarms shorten on-site response time, remote notifications ensure information coverage, and threshold customization and multi-level alarms improve alarm flexibility and adaptability.

[0152] 7. User terminal module:

[0153] The user terminal module provides real-time monitoring of the motor's operating status, parameter adjustment, and historical data query functions through an interactive interface. The terminal supports multi-platform access, including PC and mobile terminals, making it convenient for users to manage equipment anytime and anywhere.

[0154] In this embodiment, the real-time monitoring unit adopts real-time refresh technology based on WebSocket, and the user can view the motor operation data through the browser, including temperature, current and vibration trend graphs, as well as key alarm information.

[0155] In this embodiment, the report generation unit generates customized reports based on the collected and analyzed data, such as daily reports containing motor energy consumption data, operating status summary and fault analysis suggestions, and supports exporting to PDF and Excel formats.

[0156] In this embodiment, the user interaction unit is designed with an interactive dashboard, and the user can adjust the monitoring parameters (such as sampling frequency, alarm threshold) and view the historical changes of the parameters through the slider.

[0157] In this embodiment, the mobile access unit provides remote access functions through iOS and Android applications, supports pushing real-time alarms, viewing historical data, and allows managers to perform control operations through mobile devices.

[0158] Real-time monitoring supports dynamic management of operating status, reporting functions help users understand the long-term performance of equipment, and interactive and mobile access improves the convenience and flexibility of operation.

[0159] 8. Energy-saving control module:

[0160] The energy-saving control module optimizes energy consumption by adjusting the motor operating parameters to avoid overload and no-load operation, and dynamically adjusts the operating mode according to actual needs to ensure high efficiency and energy saving.

[0161] In this embodiment, the parameter adjustment unit uses a frequency converter to control the motor speed and dynamically adjusts it to the optimal range (such as 30% to 100% of the rated speed) according to the load demand. The motor load rate calculation formula is as follows:

[0162]

[0163] LR: Motor load rate (unit: %);

[0164] P out : Motor output power (unit: W), measured according to load;

[0165] P rated : Rated power of the motor (unit: W), provided by the motor nameplate;

[0166] P out Calculated through load characteristic curve and real-time operation data collected by sensors;

[0167] P rated Provided by device ratings.

[0168] In this embodiment, the energy-saving mode switching unit is designed with automatic switching logic, and switches to the energy-saving mode when the load is lower than 20% of the rated value, thereby reducing ineffective energy consumption.

[0169] In this embodiment, the intelligent shutdown unit monitors the running status of the motor, and when it detects that the motor is running without load for 30 consecutive minutes, it triggers a shutdown command and issues a warning notification before the shutdown.

[0170] In this embodiment, the energy efficiency evaluation unit calculates the current operating efficiency based on the comparison between the operating data and the historical high efficiency status, and generates improvement suggestions, which are as follows:

[0171]

[0172] η: Motor operating efficiency (unit: %);

[0173] P out : Output power (unit: W), measured by load;

[0174] P in : Input power (unit: W), calculated through voltage and current signals;

[0175] P out Calculated by load characteristic curve; P in =V·I·PE.

[0176] Parameter adjustment and mode switching achieve real-time optimization, shutdown mechanism reduces ineffective operation, and energy efficiency evaluation provides a basis for long-term optimization.

[0177] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. The factory motor energy-saving operation monitoring system based on big data analysis is characterized by: include: Data acquisition module, used to collect multi-dimensional data of motor operation in real time; Data processing module, which pre-processes the collected data and marks abnormal data; Analysis and diagnosis module, which performs trend analysis and fault prediction on motor operation status based on big data algorithms; Storage module, used to store raw data and analysis results, and support historical data retrieval; The communication module connects to the cloud server or local terminal wirelessly or wiredly to achieve data interaction; Alarm module, triggering sound and light alarm and remote notification when abnormal operation or deviation of energy-saving indicators is detected; User terminal module, providing real-time monitoring interface and analysis reports; The energy-saving control module adjusts the motor operating parameters based on the analysis results to achieve energy-saving optimization.

2. The factory motor energy-saving operation monitoring system based on big data analysis according to claim 1 is characterized in that: The data acquisition module comprises: Temperature sensing unit, used to collect temperature data of the motor and the environment; Vibration sensor unit, used to collect the vibration amplitude and direction when the motor is running; Electrical parameter sensing unit, used to measure voltage, current and power factor; The audio sensor unit is used to monitor the noise level and abnormal sound wave signals when the motor is running.

3. The factory motor energy-saving operation monitoring system based on big data analysis according to claim 1 is characterized in that: The data processing module comprises: Data cleaning unit, used to remove invalid data and correct abnormal data; A data compression unit, used to compress a large amount of real-time data to improve storage and transmission efficiency; A feature extraction unit, used to extract key parameters from the collected data; Parameter normalization unit is used to unify the data dimension to support subsequent analysis.

4. The factory motor energy-saving operation monitoring system based on big data analysis according to claim 1 is characterized in that: The analysis and diagnosis module includes: A prediction unit that predicts the probability of motor failure or reduced efficiency based on a machine learning algorithm; A fault classification unit, used to identify specific fault types; Trend analysis unit, used to analyze the change of motor operation status over time; Energy-saving evaluation unit, used to calculate the energy efficiency of the current operating status and provide optimization suggestions.

5. The factory motor energy-saving operation monitoring system based on big data analysis according to claim 1 is characterized in that: The storage module comprises: A real-time storage unit for storing current operation data; Historical data storage unit, used to store the historical data of motor operation for a long time; Data retrieval unit, used to quickly locate operation records for a specific time period or parameters; Data backup unit, used to back up important data to the cloud or local storage device.

6. The factory motor energy-saving operation monitoring system based on big data analysis according to claim 1 is characterized in that: The communication module comprises: Wireless communication unit, supporting Wi-Fi, Bluetooth and 4G / 5G connections; Wired communication unit, supporting industrial standard communication protocols such as RS485 and Ethernet; Data encryption unit, used to ensure the security of data transmission; The cloud synchronization unit is used to synchronize local data to a remote server or management platform.

7. The factory motor energy-saving operation monitoring system based on big data analysis according to claim 1 is characterized in that: The alarm module comprises: Sound and light alarm unit, used to remind operators to pay attention on site; Remote notification unit, push alert information via SMS, email or mobile app; Threshold customization unit supports users to set alarm trigger conditions; Multi-level alarm unit, divided into early warning, minor and major alarm according to the severity of the fault.

8. The factory motor energy-saving operation monitoring system based on big data analysis according to claim 1 is characterized in that: The user terminal module comprises: Real-time monitoring unit, used to display real-time data of motor operation status; Report generation unit, generating energy saving and fault analysis reports; User interaction unit, supporting parameter setting and query; Mobile access unit, supporting remote access via smartphone or tablet.

9. The factory motor energy-saving operation monitoring system based on big data analysis according to claim 1 is characterized in that: The energy-saving control module comprises: Parameter adjustment unit, automatically adjusts operating parameters based on optimization strategies; Energy-saving mode switching unit, automatically switches to high-efficiency energy-saving mode according to operating conditions; Energy efficiency evaluation unit, which calculates the motor's energy consumption in real time and provides improvement suggestions; Intelligent shutdown unit automatically stops the motor during non-essential operation to save energy.

10. The factory motor energy-saving operation monitoring system based on big data analysis according to claim 1 is characterized in that: It also includes a big data platform for: Centrally store operating data from multiple motors; Provide global analysis of multi-motor operating status; Support customized energy-saving strategies and automatically send them to each motor; Generate regular energy-saving operation reports and score the motor health status.

Images