Intelligent self-adaptive control system of energy-saving compressor based on multi-sensor fusion

Abstract

The invention provides an energy-saving compressor intelligent self-adaptive control system based on multi-sensor fusion, which belongs to the technical field of industrial compressor intelligent control and comprises a data acquisition module, a signal conditioning module, a multi-sensor information fusion module, an intelligent control decision module, an execution driving module and a system power supply management module. A state display alarm and remote communication module can be additionally arranged. Multiple sensors collect operation and environment parameters of the compressor, and after conditioning, a comprehensive state evaluation result is generated through D-S evidence theory or fuzzy logic fusion; the intelligent module generates a control instruction based on a load prediction algorithm and a fuzzy PID self-tuning strategy, and the execution module drives the compressor to act; the power supply module supports solar power supply and multi-power supply switching. The system overcomes the limitation that a traditional compressor is single in sensing, rigid in control and the like, comprehensive sensing, accurate evaluation and self-adaptive energy-saving control are achieved, the operation stability is improved, and the energy consumption and the operation and maintenance cost are reduced.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology for industrial compressors, specifically to an intelligent adaptive control system for energy-saving compressors based on multi-sensor fusion. Background Technology

[0002] Traditional compressor control systems generally have the following limitations, making it difficult to meet the demands of industrial scenarios for efficient, stable, and energy-saving operation: 1. Limited sensing dimensions: It relies on a single or few sensors (such as only monitoring exhaust pressure and motor temperature), which cannot fully capture key parameters such as air pressure fluctuations, mechanical vibrations, and ambient humidity. It is easy to miss faults or shut down the machine due to misjudgment of local parameters. 2. Rigid control mode: It mostly adopts PID control with fixed parameters or manual adjustment, which cannot adapt to dynamic operating conditions such as load fluctuations (such as changes in gas consumption in the workshop) and environmental changes (such as high temperature in the machine room in summer). It either wastes energy due to excess power or causes unstable operation due to adjustment lag. 3. Low reliability of status assessment: Judging the operating status based on a single parameter threshold (such as alarming when the temperature exceeds the set value) without considering the correlation between parameters (such as abnormal vibration may be accompanied by temperature rise), is prone to "false alarms" or "missed alarms", increasing operation and maintenance costs; 4. Management and power supply limitations: It relies heavily on on-site monitoring, lacks remote monitoring and early warning capabilities, and has a delayed fault response; the power system only relies on traditional mains power, without clean energy access and backup switching design, making it prone to shutdown due to power outages, and unable to further reduce energy consumption.

[0003] To solve the above problems, it is necessary to build an intelligent control system that can "fully perceive, accurately assess, adaptively control, conveniently manage, and stably supply power". The maturity of multi-sensor fusion technology, load prediction algorithm, fuzzy PID control and multi-power supply management technology provides a foundation for the realization of this system. Summary of the Invention

[0004] The present invention aims to solve the problems mentioned in the background art by providing an intelligent adaptive control system for energy-saving compressors based on multi-sensor fusion.

[0005] The specific technical solution is as follows: An intelligent adaptive control system for an energy-saving compressor based on multi-sensor fusion includes: The data acquisition module is used to collect compressor operating status parameters and environmental parameters in real time through multiple sensors; The signal conditioning module, whose input is connected to the output of the data acquisition module, is used to filter and amplify the acquired parameter signals. The multi-sensor information fusion processing module has its input end connected to the output end of the signal conditioning module. It is used to receive the processed parameter signals and generate a comprehensive compressor operating status evaluation result through feature-level fusion and decision-level fusion. The intelligent control decision module has its input end connected to the output end of the multi-sensor information fusion processing module. It is used to receive the comprehensive operating status evaluation results and generate control commands based on the built-in energy-saving optimization algorithm and adaptive control strategy. An execution drive module, whose input end is connected to the output end of the intelligent control decision module, is used to receive the control command and drive the compressor's actuator to move; The system power management module has its output terminals connected to the power input terminals of the data acquisition module, signal conditioning module, multi-sensor information fusion processing module, intelligent control decision module, and execution drive module, respectively, to provide the required power to each module in the system.

[0006] This solution achieves multi-module collaborative operation by constructing a complete system architecture encompassing "data acquisition - signal conditioning - multi-sensor fusion - intelligent control decision-making - execution drive - power management". Multi-sensor real-time acquisition of operating and environmental parameters overcomes the limitations of single-sensor perception, enabling comprehensive perception of the compressor's status. Signal conditioning, filtering, and amplification reduce interference signals, providing accurate raw data for subsequent fusion processing. Comprehensive evaluation through feature-level and decision-level fusion avoids the one-sidedness of single-parameter judgment, improving the comprehensiveness and reliability of operating status assessment. Intelligent decision-making with built-in energy-saving optimization algorithms and adaptive control strategies can dynamically generate control commands based on actual operating conditions, avoiding the rigidity of fixed control modes while achieving targeted energy saving. The execution drive module ensures accurate implementation of control commands, and the power management module provides stable power to all modules, ultimately achieving the overall effect of "comprehensive perception - accurate evaluation - intelligent regulation - stable operation - energy saving and consumption reduction" for the compressor.

[0007] The aforementioned intelligent adaptive control system for energy-saving compressors based on multi-sensor fusion, wherein the data acquisition module includes: Pressure sensors are installed at the compressor's intake port, exhaust port, and inside the cylinder to collect parameters such as intake pressure, exhaust pressure, and cylinder gas pressure. Temperature sensors are installed on the compressor cylinder surface, lubricating oil outlet, and cooling system inlet and outlet to collect cylinder temperature, lubricating oil temperature, and cooling medium temperature parameters. Vibration sensors are installed in the compressor crankcase and bearing housing to collect the vibration frequency and amplitude parameters of the machine body. A noise sensor is installed within 1 meter of the outside of the compressor body to collect noise sound pressure level parameters during operation. A humidity sensor is installed in the compressor's intake pipe and operating environment to collect parameters such as intake air humidity and ambient air humidity.

[0008] This solution deploys targeted sensors at key parts of the compressor and in the operating environment, clearly defining the installation location and data acquisition parameters of each sensor: pressure sensors cover the intake port, exhaust port, and inside the cylinder, accurately capturing changes in air pressure to provide a basis for judging whether the air path is unobstructed and the pressure is normal; temperature sensors target the cylinder, lubrication oil circuit, and cooling system, monitoring the heating and lubrication / cooling effects of key components in real time to avoid malfunctions caused by overheating or insufficient lubrication; vibration and noise sensors focus on core mechanical components (crankcase, bearing housing) and the surrounding area of ​​the compressor, promptly detecting abnormalities such as mechanical wear and loosening, and identifying potential mechanical failures in advance; humidity sensors monitor intake air and ambient humidity to prevent abnormal humidity from affecting compression efficiency or causing component corrosion; overall, it achieves accurate and comprehensive acquisition of core parameters of the compressor's air path, mechanics, thermal management, and environmental impact, providing sufficient and crucial raw data support for subsequent signal processing and status assessment, reducing misjudgments of status due to missing parameters or acquisition deviations.

[0009] The aforementioned intelligent adaptive control system for energy-saving compressors based on multi-sensor fusion, wherein the multi-sensor information fusion processing module employs a fusion algorithm based on DS evidence theory or fuzzy logic to complete decision-level fusion.

[0010] The solution specifies that the multi-sensor fusion module adopts DS evidence theory or fuzzy logic for decision-level fusion: DS evidence theory is good at handling the uncertainty of multi-source information, while fuzzy logic can effectively deal with imprecise and fuzzy operating condition information. Both algorithms are suitable for the errors and uncertainties that may exist in multi-sensor information. Decision-level fusion using such algorithms can effectively integrate the information processed by multi-source sensors, offset the errors and limitations of single sensor information, improve the reliability and accuracy of the comprehensive operating status assessment results of the compressor, provide a more reliable judgment basis for subsequent intelligent control decisions, and avoid decision errors caused by single information bias.

[0011] The aforementioned intelligent adaptive control system for energy-saving compressors based on multi-sensor fusion includes an energy-saving optimization algorithm built into the intelligent control decision module, which is a dynamic power adjustment algorithm based on load prediction.

[0012] This solution defines the energy-saving algorithm of intelligent control as a dynamic power adjustment algorithm based on load prediction: load prediction can sense the changing trend of compressor load in advance, rather than passively adjusting based solely on real-time load; dynamic power adjustment based on prediction results can avoid energy waste caused by maintaining high power operation when the load decreases, and can also adjust power in advance to meet demand before the load increases, ensuring that the compressor output matches the actual load, minimizing useless power consumption, further enhancing the energy-saving effect of the system, and avoiding the energy loss problem of traditional fixed power control.

[0013] The aforementioned intelligent adaptive control system for energy-saving compressors based on multi-sensor fusion, wherein the intelligent control decision module employs a fuzzy PID controller to implement an adaptive control strategy.

[0014] The solution explicitly adopts a "fuzzy PID controller" to achieve an adaptive control strategy: the PID controller has the traditional advantage of precise adjustment, which can ensure control accuracy; fuzzy control can cope with uncertain scenarios such as nonlinearity and operating condition fluctuations that may occur during compressor operation, and make up for the problem of adjustment lag or insufficient accuracy of traditional fixed parameter PID when operating conditions change; the adaptive control combining the two can flexibly adjust the control logic according to the changes in the actual operating conditions of the compressor, so that the control system can adapt to the operating requirements of different loads and different environments, improve the adaptability and accuracy of control, and ensure that the compressor can still operate stably under complex operating conditions.

[0015] In the aforementioned intelligent adaptive control system for energy-saving compressors based on multi-sensor fusion, the control parameters of the fuzzy PID controller can be self-tuned online based on the comprehensive operating status evaluation results.

[0016] This solution adds an "online self-tuning of control parameters" function to the fuzzy PID control: the control parameters can be adjusted in real time according to the comprehensive operating status evaluation results without manual intervention. This ensures that the controller parameters are always in the optimal state under different operating conditions (such as sudden load changes, changes in ambient temperature and humidity), avoiding the decline in control performance caused by fixed parameters. It further improves the response speed and adjustment accuracy of the control system to changes in operating conditions, reduces operating fluctuations caused by parameter mismatch, and ensures long-term stable and efficient operation of the compressor.

[0017] The aforementioned intelligent adaptive control system for energy-saving compressors based on multi-sensor fusion includes an execution drive module comprising a frequency converter and a stepper motor driver for controlling the opening degree of the intake valve or exhaust valve.

[0018] The solution clearly defines the drive module as including a frequency converter and a stepper motor driver: the frequency converter can achieve smooth and precise adjustment of the compressor drive motor speed, avoiding the impact of sudden speed changes on the equipment, while adapting to the speed requirements under different loads; the stepper motor driver can precisely control the opening of the intake or exhaust valve, achieving fine adjustment of the airflow; the combination of the two can accurately and flexibly execute the instructions generated by the intelligent control decision module, ensuring that key operating parameters such as compressor speed and valve opening can be precisely adjusted according to control requirements, ensuring that control instructions are effectively implemented, and thus achieving precise control of the compressor's operating status.

[0019] The aforementioned intelligent adaptive control system for energy-saving compressors based on multi-sensor fusion also includes a status display and alarm module. The input of the status display and alarm module is connected to the output of the intelligent control decision module, and is used to display the real-time operating status of the compressor and issue an alarm when the compressor operates abnormally.

[0020] This solution adds a status display and alarm module: the status display function can present the compressor's operating parameters and status in real time, allowing staff to intuitively grasp the equipment's operating status without the need for complex operations; the abnormal alarm function can promptly issue reminders when the compressor's parameters exceed the standard or its operation is abnormal, preventing the fault from escalating due to staff not noticing the abnormality in time; overall, it improves the visibility and safety of equipment operation, reduces the risk of equipment damage caused by the failure to handle abnormalities in a timely manner, and ensures the safe and stable operation of the compressor.

[0021] The aforementioned intelligent adaptive control system for energy-saving compressors based on multi-sensor fusion also includes a remote communication module. The bidirectional communication terminal of the remote communication module is connected to the bidirectional communication terminal of the intelligent control decision module, and is used to remotely transmit system data to the monitoring center or receive remote control commands from the monitoring center.

[0022] This solution adds a remote communication module: the two-way communication function can remotely transmit compressor operating data to the monitoring center, enabling managers to remotely monitor the equipment in real time without on-site duty, thus reducing management costs; on the other hand, it can receive remote control commands from the monitoring center, enabling remote parameter adjustment, start-stop control and other operations on the compressor, improving the convenience and timeliness of equipment management; it is especially suitable for scenarios where multiple compressors are centrally managed or where equipment is deployed in locations where on-site operation is inconvenient, optimizing equipment management efficiency and reducing the workload of on-site maintenance.

[0023] The aforementioned intelligent adaptive control system for energy-saving compressors based on multi-sensor fusion includes a power management module that integrates a solar power interface and a power switching circuit.

[0024] This solution integrates a solar power interface and a power switching circuit into the system's power management module. The solar power interface allows access to clean energy, reducing the system's reliance on traditional electricity and further lowering overall energy consumption, aligning with the system's energy-saving goals. The power switching circuit enables flexible switching between traditional and solar power, prioritizing solar power when it is sufficient and automatically switching to backup power when the main power supply is abnormal or solar power is insufficient. This enhances the system's energy-saving effect while ensuring the continuity and reliability of power supply to each module, preventing system shutdowns or malfunctions due to power outages and improving the overall system stability.

[0025] The present invention has the following beneficial effects: 1. More comprehensive and accurate condition assessment: Multiple sensors cover the dimensions of air path, mechanical, thermal management and environment. Combined with DS evidence theory or fuzzy logic fusion, it avoids misjudgment by a single parameter. For example, if only the vibration is abnormal, the combination of normal temperature and pressure can rule out serious faults and reduce unnecessary shutdowns. Multi-parameter correlation assessment can also detect potential problems in advance (such as the risk of water accumulation in the air path can be predicted if the humidity rises and the intake pressure fluctuates). 2. More adaptive and energy-efficient control: The load prediction algorithm can adapt to load changes in advance, avoiding energy waste due to "high power and low load"; the fuzzy PID controller can dynamically adjust parameters to adapt to fluctuations in operating conditions (such as quickly stabilizing pressure when the load suddenly increases), ensuring operational stability (such as keeping pressure fluctuations within a reasonable range) and reducing unnecessary power consumption. 3. More stable and reliable operation: The signal conditioning module reduces interference signals and ensures the accuracy of raw data; the precise adjustment and protection functions of the execution drive module prevent damage to the actuator; the power management module seamlessly switches between multiple power supplies, reducing the risk of power outages and reducing the overall probability of equipment failure. 4. More convenient and efficient management: The status display module makes the operating data intuitive, and the alarm module shortens the time for anomaly detection; the remote communication module realizes "unattended operation + remote control", reducing the workload of on-site operation and maintenance, and is especially suitable for centralized management of multiple compressors or deployment in remote scenarios; 5. More environmentally friendly and sustainable energy supply: The solar power interface can connect to clean energy sources, reducing reliance on traditional mains power and aligning with the system's energy-saving goals; the backup power design ensures that core modules (such as fusion processing and alarms) do not stop working under extreme conditions, further improving system reliability. Attached Figure Description

[0026] Figure 1 A schematic diagram of the architecture of an energy-saving compressor intelligent adaptive control system based on multi-sensor fusion provided in an embodiment of the present invention; Figure 2 This is a graph showing the changes in the compressor operating parameters of this system. Figure 3This is a curve comparing the predicted and actual compressor load of this system. Figure 4 This is a graph showing the trend of compressor energy consumption in this system. Figure 5 The diagram shows the self-tuning effect curve of the control parameters of the intelligent adaptive control system for energy-saving compressors based on multi-sensor fusion, provided in an embodiment of the present invention. Detailed Implementation

[0027] The technical solution of the present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0028] The accompanying drawings are for illustrative purposes only and are schematic diagrams, not actual images. They should not be construed as limiting the scope of this application. To better illustrate the embodiments of the present invention, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual dimensions of the product. It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0029] In the accompanying drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components. In the description of the present invention, it should be understood that if terms such as "upper," "lower," "left," "right," "inner," and "outer" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, the terms used to describe positional relationships in the drawings are only for illustrative purposes and should not be construed as limiting the present application. For those skilled in the art, the specific meaning of the above terms can be understood according to the specific circumstances.

[0030] In the description of this invention, unless otherwise explicitly specified and limited, the term "connection" or similar designation indicating a connection between components should be interpreted broadly. For example, it can refer to a fixed connection, a detachable connection, or an integral part; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can refer to the internal communication between two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances. Example

[0031] Reference Figures 1-5 As shown, where Figure 2 It shows the trends of intake pressure, exhaust pressure, cylinder temperature, and vibration amplitude over time, reflecting the dynamic operating status of the compressor; Figure 3 The difference between the predicted load rate and the actual load rate is shown, verifying the accuracy of the load prediction algorithm; Figure 4The display shows how motor power and average daily power consumption change with load range, intuitively demonstrating the energy-saving effect; Figure 5 The self-tuning process of PID parameters under sudden load increase conditions and their impact on pressure settling time are presented, verifying the effectiveness of the adaptive control strategy.

[0032] The energy-saving compressor intelligent adaptive control system based on multi-sensor fusion provided in this embodiment includes: a data acquisition module, a signal conditioning module, a multi-sensor information fusion processing module, an intelligent control decision module, an execution drive module, and a system power management module, wherein: The data acquisition module is used to collect compressor operating status parameters and environmental parameters in real time through multiple types of compatible sensors. The sensors include, but are not limited to, pressure, temperature, vibration, noise and humidity sensors. The sampling frequency of each sensor is adapted and set according to the parameter characteristics (e.g., the sampling frequency of pressure and temperature parameters is 1Hz-5Hz, and the sampling frequency of vibration and noise parameters is 10Hz-50Hz) to ensure the real-time and effective acquisition of parameters.

[0033] The input of the signal conditioning module is connected to the output of the data acquisition module via a shielded cable. It is used to perform targeted processing on the acquired parameter signals. Specifically, it uses an RC low-pass filter circuit or an active filter circuit to filter out electromagnetic interference (such as 50Hz power frequency interference and motor radiation interference), and uses an operational amplifier to form a non-inverting amplifier circuit to amplify weak signals (such as mV level signals output by vibration sensors) so that the signal amplitude is stabilized within the standard range of 0-5V or 4-20mA, providing accurate signals for subsequent processing.

[0034] The input of the multi-sensor information fusion processing module is connected to the output of the signal conditioning module via an SPI or I2C communication interface. It has a built-in microprocessor based on the ARM Cortex-M7 architecture (such as STM32H743) to receive the processed parameter signals. First, the key features of each parameter (such as pressure fluctuation amplitude, temperature change rate, and vibration peak frequency) are extracted through feature-level fusion. Then, the feature information is integrated through decision-level fusion to generate a comprehensive evaluation result of the compressor's operating status (such as "normal operation", "high load", "mechanical abnormality", "insufficient cooling").

[0035] The input of the intelligent control decision module is connected to the output of the multi-sensor information fusion processing module via a CAN bus. It has a built-in embedded control chip (such as TITMS320F28335) and control algorithm library. After receiving the comprehensive operating status evaluation results, it calls the built-in energy-saving optimization algorithm to calculate the optimal operating parameters and generates targeted control commands (such as "adjust the motor speed to 1450 r / min", "adjust the exhaust valve opening to 60%", "start the backup cooling fan").

[0036] The input terminal of the actuator drive module is connected to the output terminal of the intelligent control decision module through the power drive circuit. It is used to receive control commands and convert them into drive signals that the actuator can recognize. It can drive the motor speed regulation component, valve adjustment component or auxiliary equipment (such as cooling fan, lubricating oil pump) to operate according to the type of control command, and has overcurrent and overvoltage protection functions to avoid damage to the actuator.

[0037] The output of the system power management module is connected to the power input of the data acquisition module, signal conditioning module, multi-sensor information fusion processing module, intelligent control decision module, and execution drive module through multiple voltage regulator circuits. It can convert the external AC220V or AC380V voltage into the DC voltage required by each module (such as 5V, 12V, 24V), and has voltage stabilization, overload protection and low power consumption modes to ensure stable power supply to each module while reducing standby power consumption.

[0038] Specifically, in this embodiment, the data acquisition module includes: a pressure sensor, a temperature sensor, a vibration sensor, a noise sensor, and a humidity sensor, wherein: The pressure sensor adopts a piezoresistive pressure sensor (such as the MPX5700 series), which is installed in the horizontal section of the compressor intake pipe (15cm away from the machine body), the vertical section of the exhaust pipe (20cm away from the valve), and the reserved detection hole on the top of the cylinder through a threaded sealing connection. The range is adapted to the intake pressure (0-1MPa), exhaust pressure (0-1.6MPa), and cylinder gas pressure (0-2MPa) to collect three types of pressure parameters in real time, with a resolution ≤0.1%FS.

[0039] The temperature sensor uses a PT100 platinum resistance temperature sensor (accuracy class A), which is installed on the surface of the compressor cylinder block (near the cylinder liner) via a magnetic mounting bracket, and installed on the lubricating oil outlet pipe (diameter DN20) and the cooling system inlet and outlet pipes via a compression fitting. The measurement range covers -20℃ to 200℃, and is used to collect cylinder block temperature (key monitoring ≤120℃), lubricating oil temperature (key monitoring ≤80℃), and the temperature difference between the inlet and outlet of the cooling medium (key monitoring ≤15℃).

[0040] The vibration sensor uses a piezoelectric accelerometer (such as CA-YD-105), which is fixed to the side wall of the compressor crankcase (near the main shaft bearing) and the bearing housing end cover by bolts; the measurement direction is bidirectional, vertical and horizontal, with a range of 0-500m / s², and a frequency response of 1Hz-10kHz. It is used to collect the vibration frequency of the machine body (focusing on monitoring the 100Hz-500Hz frequency band) and the amplitude (focusing on monitoring ≤0.1mm).

[0041] The noise sensor uses a capacitive sound level meter sensor (such as AWA5636), which is fixed within 1 meter of the outside of the compressor body by a bracket, in an unobstructed location and away from other noise sources; the measurement range is 30dB-130dB, and the frequency weighting characteristic is A-weighted, used to collect the noise sound pressure level during operation (key monitoring ≤85dB).

[0042] The humidity sensor uses a capacitive humidity sensor (such as SHT30), which is embedded in the compressor intake pipe (near the air filter outlet) through a pipe-type mounting bracket, and installed in the compressor room (1.5 meters above the ground) through a wall-mounted housing; the measurement range is 0-100%RH, the accuracy is ±2%RH, and it is used to collect intake air humidity (focusing on monitoring ≤80%RH) and ambient air humidity.

[0043] Specifically, in this embodiment, the multi-sensor information fusion processing module uses a fusion algorithm based on DS evidence theory or fuzzy logic to complete decision-level fusion: If the Dempster evidence theory is adopted: First, the parameters collected by each sensor (such as pressure, temperature, vibration) are divided into three evidence bodies: "normal", "slightly abnormal" and "severely abnormal". The basic probability allocation function (BPA) of each evidence body is set by historical data and expert experience. Then, the Dempster synthesis rule is used to fuse multiple evidence bodies to eliminate conflicts between evidence (such as adjusting the weights by the conflict coefficient when the pressure is normal but the vibration is abnormal). Finally, the state assessment result with the highest overall confidence level is output.

[0044] If fuzzy logic is used: first, the processed parameter signals are fuzzified (e.g., temperature "70℃-90℃" is mapped to the "moderate" fuzzy subset, and vibration "0.05mm-0.1mm" is mapped to the "slightly abnormal" fuzzy subset); then, a fuzzy rule base is constructed according to the compressor's operating rules (e.g., "if the cylinder temperature is moderate and the vibration is slightly abnormal, the overall status is 'mechanical wear needs attention'"); finally, the center of gravity method is used for declarative processing to convert the fuzzy output into a clear comprehensive operating status evaluation result.

[0045] Specifically, in this embodiment, the energy-saving optimization algorithm built into the intelligent control decision module is a dynamic power adjustment algorithm based on load prediction: The algorithm takes historical load data collected by multiple sensors (such as changes in exhaust pressure and intake flow rate over the past 24 hours) and real-time environmental parameters (such as ambient temperature and humidity) as input, and extracts load change trend features using the sliding window method. The compressor load for the next 10-30 minutes is predicted using a grey prediction model (GM(1,1)) or an LSTM neural network, and is divided into three intervals: "low load" (load rate < 40%), "medium load" (load rate 40%-70%), and "high load" (load rate > 70%). The compressor drive motor power is dynamically adjusted according to the predicted load range: when the load is low, the motor speed is reduced (e.g., from 1500r / min to 900r / min) and the exhaust valve opening is reduced (e.g., from 100% to 50%). When the load is medium, the motor speed is maintained at 80%-90% of the rated speed. When the load is high, the motor speed is increased to the rated speed and the exhaust valve is fully opened to achieve "power supply on demand" and reduce ineffective power consumption.

[0046] Specifically, in this embodiment, the intelligent control decision module uses a fuzzy PID controller to implement an adaptive control strategy: The input variables of the fuzzy PID controller are "comprehensive operating state deviation" (such as the difference between the actual exhaust pressure and the set pressure) and "deviation change rate" (such as the change in pressure deviation per minute), and the output variables are the proportional coefficient (Kp), integral coefficient (Ki), and derivative coefficient (Kd) of the PID controller. To address the nonlinear characteristics (such as rapid pressure fluctuations during sudden load changes) and time-delay characteristics (such as delayed temperature changes after cooling system adjustments) of the compressor during operation, a fuzzy control rule base is constructed (e.g., "If the deviation is large and the rate of change of the deviation is large, then increase Kp, decrease Ki, and increase Kd to quickly suppress the deviation"). By dynamically adjusting Kp, Ki, and Kd through fuzzy inference, the PID controller can maintain adjustment accuracy when the operating conditions are stable (e.g., pressure fluctuation ≤ ±0.02MPa) and respond quickly when the operating conditions change (e.g., stabilizing pressure within 10 seconds after a sudden load change), thus achieving adaptive control.

[0047] Specifically, in this embodiment, the control parameters of the fuzzy PID controller can be self-tuned online based on the comprehensive operating status evaluation results: Set self-tuning trigger conditions: When the comprehensive operation status evaluation result shows "operating condition change range > 20%" (such as the load rate suddenly increases from 50% to 80%), or the control parameter deviation exceeds the threshold (such as the actual pressure and the set pressure deviation lasting for 5 seconds > 0.05MPa), parameter self-tuning will be automatically started. Self-tuning process: Based on the comprehensive operating status evaluation results (such as "sudden load increase" and "insufficient cooling"), the corresponding parameter adjustment strategy is called (such as increasing Kp first to quickly increase power when "sudden load increase"), and the membership function in the fuzzy rule base is optimized by gradient descent method, thereby adjusting the output values ​​of Kp, Ki, and Kd. After self-tuning, the adjustment effect is verified by real-time parameter monitoring. If the working condition returns to stability after adjustment (deviation < 0.02MPa), the new parameters are saved; if the standard is not met, the self-tuning process is repeated until the parameters are adapted to the current working condition.

[0048] Specifically, in this embodiment, the drive module includes a frequency converter and a stepper motor driver for controlling the opening degree of the intake valve or exhaust valve: Inverter: A vector control inverter (such as Siemens MM440 series) is adopted, with input voltage adapted to the rated voltage of the compressor drive motor (such as AC380V), and output frequency range of 0-50Hz; after receiving the speed command from the intelligent control decision module, the output voltage and frequency are adjusted through vector control algorithm to achieve smooth adjustment of motor speed (speed fluctuation ≤ ±5r / min), and it has overload, overvoltage and undervoltage protection functions.

[0049] Stepper motor driver: A two-phase hybrid stepper motor driver (such as Leadshine DM542) is used, which is compatible with stepper motors with a step angle of 1.8°. It receives the opening command from the intelligent control decision module through pulse signal (such as "60% opening" corresponding to 300 pulses), drives the stepper motor to rotate the valve stem of the intake / exhaust valve, and realizes precise adjustment of valve opening (opening accuracy ≤ ±1%). It also has a step loss detection function, and automatically issues an alarm signal when step loss is detected.

[0050] Specifically, in this embodiment, a status display and alarm module is also included. The input terminal of the status display and alarm module is connected to the output terminal of the intelligent control decision module via an RS485 bus, and is used to display the real-time operating status of the compressor and issue an alarm when the compressor operates abnormally. Status display unit: It adopts a 7-inch TFT LCD touch screen (resolution 800×480) to display the raw parameters collected by each sensor in real time (such as intake pressure 0.6MPa, cylinder temperature 75℃), comprehensive operating status evaluation results (presented in the form of text + icon, such as "normal operation" with a green checkmark icon), and control command execution status (such as "motor speed 1450r / min"); it supports querying parameter historical curves (such as the temperature change curve of the past 1 hour).

[0051] Alarm unit: Includes an audible and visual alarm (installed in a prominent location in the computer room) and an SMS alarm module (with built-in SIM card); when the comprehensive operating status assessment result is "abnormal" (such as cylinder temperature > 120℃, vibration amplitude > 0.1mm), the audible and visual alarm emits a flashing red light (frequency 1Hz) and a buzzer sound (volume ≥ 85dB), and at the same time the SMS alarm module sends an alarm message (including abnormal parameters, abnormal type, and occurrence time) to the preset mobile phone number of the management personnel; the alarm threshold can be manually set or remotely modified through the touch screen.

[0052] Specifically, in this embodiment, a remote communication module is also included. The bidirectional communication end of the remote communication module is connected to the bidirectional communication end of the intelligent control decision module via an Ethernet or 4G / 5G module, and is used to remotely transmit system data to the monitoring center or receive remote control commands from the monitoring center. Data transmission function: The system uses the MQTT communication protocol to transmit system data to the monitoring center at regular intervals (e.g., every minute), including real-time operating parameters, comprehensive status assessment results, alarm records, and control command execution logs. Data transmission uses encryption algorithms (e.g., AES-128) to prevent data leakage or tampering.

[0053] Remote control function: The monitoring center can send remote control commands to the system (such as "modify the exhaust pressure setting to 0.8MPa" or "start the compressor shutdown procedure"). After receiving the command, the remote communication module verifies the authorization (requires the administrator's account and password authentication), ensures the integrity of the command through CRC check, and then transmits it to the intelligent control decision module for execution. It supports centralized monitoring of multiple compressors, and the monitoring center can display the operating status map of each device.

[0054] Specifically, in this embodiment, the system power management module integrates a solar power interface and a power switching circuit: Solar power interface: Adopts DC24V standard interface, compatible with 200W-500W monocrystalline silicon solar panels (conversion efficiency ≥22%); the unstable voltage output by the solar panel is converted into stable DC24V through the solar controller (with MPPT maximum power point tracking function) to power the various modules of the system; the interface has reverse connection protection function to prevent the circuit from being damaged by reverse connection of the positive and negative terminals of the solar panel.

[0055] Power switching circuit: A dual-power automatic switching chip (such as TITPS2115) is used to connect the solar power supply and the DC24V power supply converted from the traditional mains power. The voltage detection circuit monitors the voltage of the two power supplies in real time. When the solar power supply voltage is ≥22V, the system will switch to solar power first. When the solar power supply voltage is <20V (such as on cloudy days or at night), the system will automatically switch to mains power. The switching process is uninterrupted (switching time <10ms), ensuring that the system power supply is uninterrupted. At the same time, a lithium battery backup power interface (DC24V / 10Ah) is integrated. When both main power supplies fail, the backup power supply will automatically be put into operation to maintain the operation of the core modules of the system (such as information fusion, remote communication, and alarm modules) for ≥4 hours.

[0056] This embodiment uses an industrial screw air compressor (rated displacement 10m³ / min, rated pressure 1.0MPa, drive motor power 75kW) as the application object, and builds an intelligent adaptive control system based on multi-sensor fusion, which is implemented as follows: I. System Hardware Setup 1. Deployment of the data acquisition module Install one MPX5700 piezoresistive pressure sensor (range 0-1MPa) through a G1 / 2 thread on the horizontal section of the compressor intake pipe (DN80) to collect the intake pressure; install one MPX5700 sensor (range 0-1.6MPa) through a G1 / 2 thread on the vertical section of the exhaust pipe (DN65) to collect the exhaust pressure; install one miniature piezoresistive pressure sensor (range 0-2MPa) in the M16 detection hole reserved at the top of the cylinder to collect the cylinder pressure.

[0057] One PT100 platinum resistance temperature sensor (Class A accuracy) is installed near the cylinder liner in the cylinder block using a magnetic mounting bracket to collect the cylinder block temperature; one PT100 sensor is installed in the lubricating oil outlet pipe (DN20) using a compression fitting to collect the lubricating oil temperature; and one PT100 sensor is installed in each of the cooling system inlet and outlet pipes (DN50) to collect the temperature difference of the cooling medium.

[0058] One CA-YD-105 piezoelectric accelerometer is fixed to the crankcase side wall (near the main shaft bearing) and the bearing housing end cover with M6 bolts to collect the vibration frequency and amplitude in the vertical and horizontal directions; one AWA5636 sound level sensor is installed on a bracket 1 meter outside the compressor body, away from the fan, to collect the noise sound pressure level; one SHT30 humidity sensor is embedded in the intake duct near the air filter outlet through a pipe mounting bracket, and one SHT30 sensor is installed at a height of 1.5 meters in the machine room to collect the intake air humidity and ambient humidity respectively.

[0059] 2. Implementation of the signal conditioning and fusion processing module The signal conditioning module adopts a PCB integrated design: for the 4-20mA signals output by the pressure and temperature sensors, an RC low-pass filter circuit (R=1kΩ, C=0.1μF) is used to filter out 50Hz power frequency interference; for the mV level signals output by the vibration sensor, an AD8221 operational amplifier is used to form a non-inverting amplifier circuit to amplify the signal to the 0-5V standard range; all conditioned signals are transmitted to the fusion processing module through the SPI interface.

[0060] The fusion processing module uses an STM32H743 microprocessor as its core and incorporates a Dempster evidence theory fusion algorithm. It divides each sensor parameter into three evidence bodies: "normal," "slightly abnormal," and "severely abnormal." The BPA function is set based on historical operating data (the normal operating condition parameter range of the past three months). For example, the BPA for "normal" is 0.8 when the intake pressure is 0.5-0.7 MPa, and the BPA for "slightly abnormal" is 0.6 when the intake pressure is 0.4-0.5 MPa or 0.7-0.8 MPa. When the following data is collected at a certain moment: "Intake pressure 0.85 MPa (slightly abnormal, BPA=0.6), cylinder temperature 85℃ (normal, BPA=0.8), vibration amplitude 0.08 mm (slightly abnormal, BPA=0.7)," the Dempster synthesis rules are used to fuse the data, and the resulting assessment is "Overall status is slightly abnormal (confidence level 0.75), intake pressure fluctuations need attention."

[0061] 3. Implementation of the intelligent control decision-making module It uses the TITMS320F28335 embedded chip as the core, and incorporates a dynamic power adjustment algorithm based on load prediction and a fuzzy PID controller. Load prediction algorithm: Using the exhaust pressure and intake flow data of the past 24 hours as input, the load of the next 20 minutes is predicted through the GM(1,1) model. If the predicted load rate increases from the current 50% to 65% (medium load range), the optimized parameters of "motor speed needs to increase from 1200r / min to 1350r / min and exhaust valve opening needs to be maintained at 80%" are calculated.

[0062] Fuzzy PID controller: The input variables are "exhaust pressure deviation" (set pressure 1.0MPa, actual pressure 1.05MPa, deviation 0.05MPa) and "deviation change rate" (change of 0.02MPa per minute). Through fuzzy rule base inference, it outputs "Kp=2.5, Ki=0.1, Kd=0.05" and dynamically adjusts the PID parameters to reduce the exhaust pressure to 1.0MPa±0.02MPa within 15 seconds. When the load suddenly rises to 80% (high load), it triggers online self-tuning of the parameters, adjusting Kp to 3.0 and Ki to 0.15 to ensure rapid pressure stabilization.

[0063] 4. Implementation of driver and power management modules The drive module employs a Siemens MM440 vector control frequency converter (AC380V input, 0-50Hz output) to smoothly drive a 75kW motor after receiving speed commands, achieving smooth speed adjustment without impact when the speed increases from 1200r / min to 1350r / min; it also uses a Leadshine DM542 stepper motor driver to drive a stepper motor with a step angle of 1.8° to control the opening of the exhaust valve (butterfly valve), outputting 320 pulses after receiving the "80% opening" command, achieving a valve opening accuracy of ±0.5%.

[0064] Power Management Module: Integrated DC24V solar interface, compatible with 300W monocrystalline silicon solar panels (conversion efficiency 23%), converts solar energy to stable DC24V via MPPT solar controller; adopts TITPS2115 power switching chip, prioritizes power supply when solar voltage is ≥22V (can meet 60% of the system's energy consumption requirements on sunny days), automatically switches to DC24V mains power conversion when voltage is <20V; integrated DC24V / 10Ah lithium battery backup power supply, maintains the operation of the fusion processing, remote communication, and alarm modules for ≥5 hours when both mains and solar power fail.

[0065] 5. Implementation of auxiliary modules Status display and alarm module: It adopts a 7-inch TFT touch screen to display information such as "intake pressure 0.65MPa, cylinder temperature 78℃, motor speed 1350r / min, and overall status normal" in real time. It supports querying the temperature change curve of the past hour. When the cylinder temperature rises to 125℃, the audible and visual alarm (red light + 85dB buzzer) is activated, and at the same time, the SMS module sends an alarm message to the management personnel: "Cylinder temperature abnormal (125℃), please check the cooling system in time".

[0066] Remote communication module: Employs a 4G module (supporting full network compatibility) to transmit data to the monitoring center via the MQTT protocol (once every minute). The monitoring center can display the real-time status of the compressor. Management personnel can send a command to "modify the exhaust pressure setpoint to 0.95MPa" through the monitoring center. After the command is encrypted with AES-128 and verified by CRC, it is received by the remote communication module and transmitted to the control decision module. After execution, the module will output the result "Setpoint has been modified, current pressure 0.95MPa".

[0067] II. System Performance Comprehensive perception and accurate assessment: By covering the dimensions of air path, mechanical, thermal management and environment through multiple sensors, combined with DS evidence fusion, it avoids misjudgment of a single parameter (such as when only vibration is abnormal, serious faults can be ruled out by combining normal temperature and pressure, reducing unnecessary shutdowns), and the condition assessment accuracy rate is over 98%.

[0068] Adaptive control and energy saving: The fuzzy PID controller can adapt to load fluctuations (such as the workshop gas consumption increasing from 5m³ / min to 9m³ / min), with a pressure stabilization time of ≤20 seconds and pressure fluctuation of ≤±0.02MPa; based on load prediction, dynamic power adjustment reduces the average motor power from 75kW to 62kW, reducing daily power consumption by 15% and saving approximately 5400kWh per month.

[0069] Stable operation and convenient management: The power management module enables seamless switching between multiple power supplies, reducing the power interruption rate to below 0.1%; remote monitoring and alarm functions reduce the need for on-site supervision, shortening the abnormal response time from 30 minutes to 5 minutes, and reducing the equipment failure rate by 25%.

[0070] This embodiment fully demonstrates the advantages of multi-sensor fusion through the collaborative work of various modules, realizing intelligent adaptive control and energy-saving operation of the compressor. It is suitable for industrial workshops, chemical plants, pharmaceutical plants and other scenarios with high requirements for compressed air quality and energy consumption.

[0071] Specifically, in this embodiment, a fuzzy weighted DS evidence theory state assessment equation based on multi-sensor information fusion is introduced. This equation integrates the basic probability assignment (BPA) of DS evidence theory with the membership function of fuzzy logic to improve the accuracy and robustness of state assessment.

[0072] The multi-sensor information fusion processing module employs the following fuzzy weighted DS evidence theory fusion equation for decision-level fusion: ; in, ; ; In the formula: m fused (A): The basic probability assignment value of proposition A after fusion; m1(B), m2(C): BPA of evidence bodies B and C from the two sensors; w(B,C): Fuzzy weighting factor, reflecting the reliability of the current data, determined by the fuzzy membership degree μ of the sensor data. B (x) and μ C (y) is calculated; K: Conflict factor, representing the degree of conflict between pieces of evidence; μ B (x),μ C (y): Membership degree of sensor data x, y on fuzzy subsets B and C; A / B / C: Combined propositions (reflecting the compressor's operating status, such as "normal", "minor abnormality", "serious abnormality").

[0073] Equation derivation process: This equation introduces a fuzzy weighting factor w(B,C) based on the classical DS evidence theory synthesis rules. It is used to dynamically adjust the weights of different pieces of evidence, making them not only dependent on historical BPA, but also on the fuzzy membership degree of the current data, thus making them more adaptable to dynamic working conditions.

[0074] 1. Classic DS Synthesis Rules: , ; 2. Introduce fuzzy weighting factors: Fuzzy membership degree μ using current sensor data B (x) and μ C (y) Calculate the weighted average: ; Introducing weighting factors into the synthesis formula enhances the weight of evidence with high credibility based on current data.

[0075] 3. Final fusion formula: .

[0076] Example (taking the integration of compressor oil temperature and vibration as an example): Assumption: Oil temperature sensor output: m1 (normal) = 0.7, m1 (abnormal) = 0.3; Vibration sensor output: m2 (normal) = 0.6, m2 (abnormal) = 0.4; Current oil temperature membership: μnormal(x) = 0.8; Current vibration membership: μnormal(y) = 0.7; Calculate the weighting factors: ; Fusion computing: .

[0077] Technical effects: 1. Improve the accuracy of state assessment: Reduce misjudgments caused by sensor drift or environmental interference by dynamically adjusting evidence weights through fuzzy weighting; 2. Enhance system robustness: Integrate current data membership to make the system more adaptable to dynamic changes; 3. Reduce the impact of conflicting evidence: Weighting factors can alleviate the decision failure problem caused by highly conflicting evidence in DS theory; 4. Compatible with existing systems: It can be embedded in existing DS or fuzzy logic fusion modules without hardware modifications.

[0078] Working principle and process: 1. Data preprocessing: Data from each sensor is input after signal conditioning; 2. Fuzzification: Calculate the membership degree of the current data in each fuzzy subset (such as "normal" and "abnormal"); 3. BPA Allocation: BPA is allocated based on historical data and expert experience; 4. Weighted fusion: This equation is used for evidence fusion; 5. Decision output: Output comprehensive status assessment results (such as "normal", "needs attention", "abnormal").

[0079] In summary, the energy-saving compressor intelligent adaptive control system based on multi-sensor fusion provided in this embodiment achieves intelligent adaptive control of the compressor through a closed-loop process of "perception-processing-decision-execution-guarantee". The collaborative working logic of each link is as follows: 1. Data Acquisition Stage: By deploying pressure, temperature, vibration, noise, and humidity sensors in key parts of the compressor (inlet, outlet, cylinder block, crankcase, etc.) and the operating environment, various operating and environmental parameters are collected in real time. Different sensors are matched with sampling frequencies according to parameter characteristics (e.g., high-frequency sampling for vibration parameters and low-frequency sampling for temperature parameters) to ensure that the raw data covers all dimensions of "gas path - mechanical - thermal management - environment". 2. Signal conditioning stage: Filtering (removing power frequency interference and motor radiation interference) and amplification (amplifying the mV-level signal from the vibration sensor to the standard voltage range) are used to eliminate noise and errors in the original signal, providing a precise and stable signal source for subsequent fusion processing; 3. Information fusion stage: With the microprocessor as the core, the key features of each parameter (such as pressure fluctuation amplitude and vibration peak frequency) are first extracted through "feature-level fusion". Then, "decision-level fusion" is carried out through DS evidence theory or fuzzy logic to integrate the features of multiple parameters, avoid the one-sidedness of single parameter judgment, and finally generate clear comprehensive status assessment results such as "normal operation", "high load" and "mechanical abnormality". 4. Intelligent Decision-Making Process: Based on the comprehensive state assessment results, the built-in algorithm is invoked to generate control commands. By analyzing historical and real-time data through a "load prediction algorithm", future load changes can be predicted to determine the optimal power output; By dynamically adjusting the proportional, integral, and derivative coefficients (Kp, Ki, Kd) using a "fuzzy PID controller," the system can adapt to fluctuations in operating conditions (such as increasing Kp to quickly boost power when the load suddenly increases), thus avoiding the lag of fixed parameter control. 5. Drive execution stage: The frequency converter receives speed commands and smoothly adjusts the power of the drive motor; the stepper motor driver receives valve opening commands and precisely controls the action of the intake / exhaust valve to ensure that the control commands are implemented without impact or deviation, while also having overcurrent and overvoltage protection to prevent damage to the actuator; 6. Support procedures: The power management module converts mains power or solar power into the voltage required by each module, and achieves seamless switching between "solar power priority - mains power backup - lithium battery emergency" through the power switching circuit to ensure uninterrupted power supply; The status display and alarm module presents real-time operating data and triggers audible, visual, and SMS alarms when abnormalities occur; the remote communication module enables two-way interaction of "data upload - command issuance" and supports remote monitoring and parameter adjustment.

[0080] How to use The system is used in three phases: "deployment and debugging," "daily operation," and "maintenance and management." The operation process is clear and easy to understand. 1. Deployment and debugging phase Sensor installation: Fix each sensor according to the design position - for example, pressure sensor is installed in the intake / exhaust pipe with threaded seal, vibration sensor is fixed to crankcase with bolts, and noise sensor is installed on the machine body 1 meter away from obstruction with bracket, ensuring that the sensor is in close contact with the detection part and without interference; Module connection: Connect the data acquisition module and the signal conditioning module through shielded cables, connect the signal conditioning module and the fusion processing module through SPI / CAN bus, connect the control decision module and the execution drive module through power lines, and finally connect the power management module to the power supply terminals of each module. Parameter configuration: Set basic parameters via the status display touch screen, such as normal thresholds for pressure / temperature / vibration, load prediction cycle (e.g., 20 minutes), initial parameters for fuzzy PID, alarm receiving mobile phone number, and MQTT server address for remote communication. After completion, start the system for no-load operation to verify whether the communication and data acquisition of each module are normal.

[0081] 2. Daily Operation Phase Real-time monitoring: Maintenance personnel can view the compressor's real-time parameters (such as suction pressure and motor speed), overall operating status (such as "normal" and "load requiring attention") and control command execution status (such as "exhaust valve opening 80%)" through on-site touch screens or remote monitoring centers, without the need for continuous on-site monitoring; Automatic control: The system operates automatically based on real-time operating conditions—for example, when the load decreases, the load prediction algorithm predicts and controls the frequency converter to reduce the motor speed; when the ambient humidity increases, the system automatically adjusts the air intake pretreatment equipment (such as starting the dryer) without manual intervention. Anomaly Handling: When the system issues an alarm (such as a flashing audible and visual alarm or receiving an alarm SMS), maintenance personnel first check the abnormal parameters (such as "cylinder block temperature exceeds threshold") through the touch screen or monitoring center, and then locate the cause (such as "cooling system failure") by combining the comprehensive status assessment results. After troubleshooting and repair, the alarm is reset through the touch screen, and the system returns to normal operation.

[0082] 3. Maintenance and Management Phase Regular inspections: Monthly check for loose sensor installations (such as vibration sensor bolts) and aging cables; quarterly calibrate pressure / temperature sensor accuracy to ensure accurate data acquisition. Remote adjustment: If the gas consumption in the workshop changes over a long period of time (such as the increase in load due to the addition of new equipment), the pressure setpoint and load prediction model parameters can be modified through the remote monitoring center without on-site operation; Power maintenance: Regularly clean the dust on the surface of the solar panels, check the lithium battery level, ensure that the multi-power switching function is working properly, and avoid power outages in extreme weather.

[0083] Overall technical effect Through the collaborative design of its various modules, this system overcomes traditional limitations from multiple dimensions, including "sensing, assessment, control, management, and power supply," achieving the following technical effects: 1. More comprehensive and accurate condition assessment: Multiple sensors cover the dimensions of air path, mechanical, thermal management and environment. Combined with DS evidence theory or fuzzy logic fusion, it avoids misjudgment by a single parameter. For example, if only the vibration is abnormal, the combination of normal temperature and pressure can rule out serious faults and reduce unnecessary shutdowns. Multi-parameter correlation assessment can also detect potential problems in advance (such as the risk of water accumulation in the air path can be predicted if the humidity rises and the intake pressure fluctuates). 2. More adaptive and energy-efficient control: The load prediction algorithm can adapt to load changes in advance, avoiding energy waste due to "high power and low load"; the fuzzy PID controller can dynamically adjust parameters to adapt to fluctuations in operating conditions (such as quickly stabilizing pressure when the load suddenly increases), ensuring operational stability (such as keeping pressure fluctuations within a reasonable range) and reducing unnecessary power consumption. 3. More stable and reliable operation: The signal conditioning module reduces interference signals and ensures the accuracy of raw data; the precise adjustment and protection functions of the execution drive module prevent damage to the actuator; the power management module seamlessly switches between multiple power supplies, reducing the risk of power outages and reducing the overall probability of equipment failure. 4. More convenient and efficient management: The status display module makes the operating data intuitive, and the alarm module shortens the time for anomaly detection; the remote communication module realizes "unattended operation + remote control", reducing the workload of on-site operation and maintenance, and is especially suitable for centralized management of multiple compressors or deployment in remote scenarios; 5. More environmentally friendly and sustainable energy supply: The solar power interface can connect to clean energy sources, reducing reliance on traditional mains power and aligning with the system's energy-saving goals; the backup power design ensures that core modules (such as fusion processing and alarms) do not stop working under extreme conditions, further improving system reliability.

[0084] In summary, this system upgrades the compressor from "passive control" to "active perception-intelligent decision-adaptive adjustment," which can not only meet the requirements of stable operation in industrial scenarios, but also reduce energy consumption and operation and maintenance costs through multi-dimensional optimization.

[0085] The above are merely preferred embodiments of the present invention and are not intended to limit the implementation methods and protection scope of the present invention. Those skilled in the art should recognize that any equivalent substitutions and obvious changes made based on the description and illustrations of the present invention should be included within the protection scope of the present invention.

Claims

1. An intelligent adaptive control system for an energy-saving compressor based on multi-sensor fusion, characterized in that, include: The data acquisition module is used to collect compressor operating status parameters and environmental parameters in real time through multiple sensors; The signal conditioning module, whose input is connected to the output of the data acquisition module, is used to filter and amplify the acquired parameter signals. The multi-sensor information fusion processing module has its input end connected to the output end of the signal conditioning module. It is used to receive the processed parameter signals and generate a comprehensive compressor operating status evaluation result through feature-level fusion and decision-level fusion. The intelligent control decision module has its input end connected to the output end of the multi-sensor information fusion processing module. It is used to receive the comprehensive operating status evaluation results and generate control commands based on the built-in energy-saving optimization algorithm and adaptive control strategy. An execution drive module, whose input end is connected to the output end of the intelligent control decision module, is used to receive the control command and drive the compressor's actuator to move; The system power management module has its output terminals connected to the power input terminals of the data acquisition module, signal conditioning module, multi-sensor information fusion processing module, intelligent control decision module, and execution drive module, respectively, to provide the required power to each module in the system.

2. The intelligent adaptive control system for energy-saving compressors based on multi-sensor fusion according to claim 1, characterized in that, The data acquisition module includes: Pressure sensors are installed at the compressor's intake port, exhaust port, and inside the cylinder to collect parameters such as intake pressure, exhaust pressure, and cylinder gas pressure. Temperature sensors are installed on the compressor cylinder surface, lubricating oil outlet, and cooling system inlet and outlet to collect cylinder temperature, lubricating oil temperature, and cooling medium temperature parameters. Vibration sensors are installed in the compressor crankcase and bearing housing to collect the vibration frequency and amplitude parameters of the machine body. A noise sensor is installed within 1 meter of the outside of the compressor body to collect noise sound pressure level parameters during operation. A humidity sensor is installed in the compressor's intake pipe and operating environment to collect parameters such as intake air humidity and ambient air humidity.

3. The intelligent adaptive control system for energy-saving compressors based on multi-sensor fusion according to claim 1, characterized in that, The multi-sensor information fusion processing module uses a fusion algorithm based on DS evidence theory or fuzzy logic to complete decision-level fusion.

4. The intelligent adaptive control system for energy-saving compressors based on multi-sensor fusion according to claim 1, characterized in that, The energy-saving optimization algorithm built into the intelligent control decision module is a dynamic power adjustment algorithm based on load prediction.

5. The intelligent adaptive control system for energy-saving compressors based on multi-sensor fusion according to claim 1, characterized in that, The intelligent control decision module uses a fuzzy PID controller to implement an adaptive control strategy.

6. The intelligent adaptive control system for energy-saving compressors based on multi-sensor fusion according to claim 5, characterized in that, The control parameters of the fuzzy PID controller can be self-tuned online based on the comprehensive operating status evaluation results.

7. The intelligent adaptive control system for energy-saving compressors based on multi-sensor fusion according to claim 1, characterized in that, The execution drive module includes a frequency converter and a stepper motor driver for controlling the opening degree of the intake valve or exhaust valve.

8. The intelligent adaptive control system for energy-saving compressors based on multi-sensor fusion according to claim 1, characterized in that, It also includes a status display and alarm module, whose input is connected to the output of the intelligent control decision module, and is used to display the real-time operating status of the compressor and issue an alarm when the compressor is operating abnormally.

9. The intelligent adaptive control system for energy-saving compressors based on multi-sensor fusion according to claim 1, characterized in that, It also includes a remote communication module, whose bidirectional communication terminal is connected to the bidirectional communication terminal of the intelligent control decision module, for remotely transmitting system data to the monitoring center or receiving remote control commands from the monitoring center.

10. The intelligent adaptive control system for energy-saving compressors based on multi-sensor fusion according to any one of claims 1-9, characterized in that, The system power management module integrates a solar power interface and a power switching circuit.

Images