Manufacturing monitoring system for gas cloud refrigeration

Abstract

The invention discloses a manufacturing monitoring system for gas cloud refrigeration, which relates to the technical field of gas cloud refrigeration and comprises a data acquisition module for acquiring working state data of gas cloud refrigeration equipment in real time; the wireless transmission module transmits the data to a cloud platform through a wireless network; the data processing and analysis module is used for analyzing the equipment data transmitted by the cloud end in real time based on machine learning and big data analysis technologies, and carrying out early warning on equipment faults by adopting an intelligent prediction algorithm; the control feedback module is used for automatically adjusting operation parameters of the gas cloud refrigeration equipment according to the analysis result; and the user interface module is used for providing an interactive interface for equipment operators and managers. By integrating the functions of real-time monitoring, intelligent analysis, automatic control and remote management of the gas cloud refrigeration equipment, the intelligent level, the operation efficiency and the safety of the equipment are greatly improved, the equipment fault risk can be effectively reduced, the equipment stability is improved, and the operation and maintenance cost is saved.

Description

Technical Field

[0001] The present invention relates to the technical field of gas cloud refrigeration, and specifically relates to a manufacturing monitoring system for gas cloud refrigeration. Background Art

[0002] With the intelligent development of industrial equipment, as a new type of refrigeration technology, gas cloud refrigeration technology has significant advantages in energy conservation and environmental protection, temperature control accuracy, and equipment management. Gas cloud refrigeration equipment is widely used in equipment cooling in high-temperature environments, temperature control of precision equipment, and other industrial applications. However, the traditional monitoring and management methods of refrigeration equipment have the following problems.

[0003] Traditional refrigeration systems often rely on manual inspections and regular maintenance, resulting in the inability to detect equipment failures or efficiency reductions in a timely manner, affecting the reliability and operating efficiency of the equipment. The operating data collected by the equipment is often limited to local records, lacking real-time cloud analysis and intelligent prediction functions, resulting in managers being unable to adjust equipment parameters in a timely manner to optimize performance. When equipment failures occur, there is often no effective early warning mechanism, resulting in the equipment being discovered only when it is severely damaged, bringing high maintenance costs to the enterprise. The operation and adjustment of the equipment usually require on-site operations and cannot achieve efficient equipment control and maintenance through remote means, increasing the burden and time cost of operators. To solve these problems, intelligent monitoring and control systems have emerged, which can realize functions such as real-time monitoring of equipment status, fault early warning, and automatic adjustment by integrating sensors, cloud platforms, big data analysis, and machine learning algorithms. Summary of the Invention

[0004] To solve the above technical problems, a manufacturing monitoring system for gas cloud refrigeration is provided, and this technical solution solves the above problems.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] A manufacturing monitoring system for gas cloud refrigeration, comprising:

[0007] A data acquisition module: used for real-time acquisition of the working state data of the gas cloud refrigeration equipment;

[0008] A wireless transmission module: The wireless transmission module is electrically connected to the data acquisition module, and the wireless transmission module is used to transmit the data obtained by the data acquisition module to the cloud platform through a wireless network for remote transmission and monitoring;

[0009] A data processing and analysis module: The data processing and analysis module is electrically connected to the wireless transmission module, and the data processing and analysis module is used to perform real-time analysis on the equipment data transmitted from the cloud based on machine learning and big data analysis technologies, adopt intelligent prediction algorithms to give early warnings of equipment failures, and generate performance optimization solutions;

[0010] Control feedback module: The control feedback module is electrically connected to the data processing and analysis module. The control feedback module is used to automatically adjust the operating parameters of the gas cloud refrigeration equipment according to the analysis results.

[0011] User interface module: The user interface module is electrically connected to the control feedback module. The user interface module is used to provide an interactive interface for equipment operators and managers, display real-time monitoring data, alarm information, and equipment operation trends, and support remote control and parameter adjustment.

[0012] Preferably, the data acquisition module specifically includes:

[0013] Sensor data acquisition module: Based on the API interfaces of temperature sensors, pressure sensors, flow sensors, current sensors, and humidity sensors, it acquires temperature data in real time, monitors the pressure status of the system, monitors flow data in real time, monitors the current data of the equipment, and obtains the humidity data of the equipment operating environment.

[0014] Data preprocessing unit: It preliminarily processes the collected raw data, converts analog signals into digital signals, sets the sampling period, and regularly obtains the numerical data of each sensor.

[0015] Data preprocessing and filtering: Based on Kalman filtering, it removes data noise, calibrates the output of the sensors, and corrects the deviation.

[0016] Data formatting and standardization unit: It organizes and converts the data of different sensors collected according to a unified standard format, and marks the data according to the timestamp.

[0017] Preferably, the wireless transmission module specifically includes:

[0018] Data preparation and encapsulation unit: It encapsulates the collected raw data, including the timestamp and equipment ID information, to form a data packet in a unified format.

[0019] Data encryption and compression unit: It encrypts the data based on AES technology and compresses the data.

[0020] Data transmission unit: It directly sends the data from the wireless transmission module to the cloud platform based on Wi-Fi.

[0021] Network connection management and monitoring unit: It monitors the network connection status in real time to ensure the stability of data transmission. When network fluctuations and interruptions occur, the system reduces data loss through methods such as automatic reconnection and caching mechanisms.

[0022] Routing and optimization unit for transmitted data: According to the network load situation, it establishes an optimal routing selection model and selects the best routing path for data transmission.

[0023] Cloud data receiving and verification unit: After the cloud platform receives the data packet from the wireless transmission module, it parses and decrypts the data packet, extracts the working status data, verifies the received data, stores it in the cloud database, and backs up the data to multiple storage nodes;

[0024] Transmission status report and alarm unit: The wireless transmission module reports the data transmission status to the platform, including transmission success, failure, and delay information. When transmission anomalies occur, including data transmission failure and network interruption, the system automatically triggers an alarm.

[0025] Preferably, the establishment of the optimal routing selection model according to the network load situation and the selection of the optimal routing path for data transmission specifically include:

[0026] Analyze the network topology structure to obtain the connection relationship, communication link, and node information between devices;

[0027] Collect the network performance data in real time, including bandwidth, delay, packet loss rate, signal strength, and node load;

[0028] Establish an optimal routing selection model with the goal of minimizing delay and load. Among them, the formula for the optimal routing selection model is:

[0029] TC = α·L + β·P + γ·N

[0030] In the formula, TC is the total transmission cost, α is the weight coefficient, L is the delay, β is the weight coefficient, P is the packet loss rate, γ is the weight coefficient, and N is the node load;

[0031] Based on the output of the optimal routing selection model, select the routing with the minimum total transmission cost.

[0032] Preferably, the data processing and analysis module specifically includes:

[0033] Real-time data analysis unit: Use a stream processing engine to analyze and process real-time data streams, extract key features from the original data, and through a visual dashboard and alarm system, monitor the device status in real time, detect abnormal behaviors and issue alarms. Based on historical fault data, construct fault labels to indicate which device behaviors are manifestations of faults;

[0034] Fault prediction unit: Analyze the time series trend of device data based on time series analysis technology, predict future fault occurrences, deploy the trained model to the production environment, monitor the device status in real time, and perform fault prediction according to real-time data;

[0035] Early warning unit: Set a fault early warning threshold. When the model predicts that a device is about to fail, the system issues an alarm notification;

[0036] Performance Optimization and Solution Generation Unit: Analyze the performance data of the device, identify performance bottlenecks, generate device optimization solutions based on machine learning technology, and automatically adjust device parameters and optimize device operation through the system's self-learning ability.

[0037] Preferably, based on historical failure data, fault labels are constructed to indicate which device behaviors are manifestations of faults, specifically including:

[0038] Collect device fault data from past fault records, including device fault time, fault type, and fault cause information;

[0039] According to fault instances in historical data, construct fault labels to indicate which device behaviors are related to faults, manually annotate the historical fault data, and combine data analysis to mark which data points and time windows indicate that the device has a fault;

[0040] Use the annotated fault data as a training set to train a machine learning model for fault prediction and classification.

[0041] Preferably, analyzing the time series trend of device data based on time series analysis technology to predict future fault occurrences, deploy the trained model to the production environment, monitor the device status in real time, and perform fault prediction based on real-time data, specifically including:

[0042] Among them, the fault prediction formula is:

[0043]

[0044] In the formula, X t is the observed value at time t, μ is the constant term, is the autoregressive coefficient, X t-1 X t-2 X t-p is the lag value, ∈ t is the noise term, θ 1 θ q is the moving average coefficient, ∈ t-1 ∈ t-q is the lag error term.

[0045] Preferably, the control feedback module specifically includes:

[0046] Device Status Evaluation Unit: Based on real-time data and historical trends, analyze the current status of the device, including load, efficiency, power consumption, and fault warning;

[0047] Optimization Goal Setting Unit: Set the device operation parameters to be adjusted according to the preset goals, including target temperature, compressor speed, and cooling water flow;

[0048] Automatic adjustment and manual intervention: Based on the machine learning model control algorithm, automatically adjust the operating parameters of the device to meet the target requirements.

[0049] Preferably, the automatic adjustment of the operating parameters of the device based on the machine learning model control algorithm to meet the target requirements specifically includes:

[0050] Automatically adjust the working load, valve opening, and flow rate of the refrigeration device according to the set target temperature;

[0051] Automatically adjust the speed or start / stop of the compressor according to the cooling demand and load conditions to optimize power consumption and refrigeration effect;

[0052] Adjust the refrigerant flow rate by controlling the working state of the refrigerant valve or pump to optimize the refrigeration efficiency, and adjust the speed of the fan to optimize the heat exchange effect;

[0053] If the automatic adjustment does not meet the expectations, the operator manually adjusts the device parameters for fine-tuning, and monitors the real-time effect after the device adjustment to ensure that the device operates within the expected range;

[0054] Manually adjust the parameters according to the feedback results to correct the previous adjustment and ensure that the device continues to operate in the optimal state;

[0055] Execution and control instruction issuing unit: Send the adjusted control signal to the device execution unit, monitor the device response during the adjustment process, and store the real-time data, parameter adjustment records, and device status information during the adjustment process in the database.

[0056] Preferably, the user interface module specifically includes:

[0057] Data display unit: Display the current operating parameters of the device, including temperature, humidity, pressure, flow rate, current, and power;

[0058] Alarm information display: When the device fails or is abnormal, the alarm information is displayed through the interface, including the alarm type, occurrence time, alarm level, fault location, and fault description, providing the working status of each part of the device;

[0059] Control and adjustment unit: The operator manually adjusts the operating parameters of the device through the interface, supports the remote operation function, and the operator adjusts the parameters, starts and stops the device, and views the status through the Internet.

[0060] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0061] The present invention proposes to integrate the functions of real-time monitoring, intelligent analysis, automatic control and remote management of the gas cloud refrigeration equipment, which greatly improves the intelligent level, operation efficiency and safety of the equipment. Its advantages include real-time data collection and transmission, fault prediction and intelligent early warning, automatic adjustment of operation parameters, remote control and convenient interaction with operators, etc. It can effectively reduce the equipment failure risk, improve the equipment stability and save the operation and maintenance costs. Therefore, the gas cloud refrigeration manufacturing monitoring system of the present invention has broad application prospects, especially suitable for fields such as industrial production, precision equipment cooling, energy management, etc. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 It is a system framework diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0063] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments in the following description are only examples, and those skilled in the art can think of other obvious variations.

[0064] Referring to Figure 1 as shown, a manufacturing monitoring system for gas cloud refrigeration includes:

[0065] Data acquisition module:

[0066] Sensor data acquisition module: Based on the API interfaces of temperature sensors, pressure sensors, flow sensors, current sensors and humidity sensors, it acquires temperature data in real time, monitors the pressure state of the monitoring system, monitors flow data in real time, monitors the current data of the equipment, and obtains the humidity data of the equipment operation environment;

[0067] Data preprocessing unit: Preliminarily processes the collected raw data, converts analog signals into digital signals, sets the sampling period, and regularly obtains the numerical data of each sensor;

[0068] Data preprocessing and filtering: Removes data noise based on Kalman filtering, calibrates the output of the sensor, and corrects the deviation;

[0069] Data formatting and standardization unit: Organizes and converts the collected data of different sensors according to a unified standard format, and marks the data according to the time stamp.

[0070] Wireless transmission module:

[0071] Data preparation and encapsulation unit: Encapsulates the collected raw data, including the time stamp and the equipment ID information, to form a data packet in a unified format;

[0072] Data encryption and compression unit: Encrypts the data based on AES technology and compresses the data;

[0073] Data transmission unit: Directly send data from the wireless transmission module to the cloud platform based on Wi-Fi;

[0074] Network connection management and monitoring unit: Real-time monitor the network connection status to ensure the stability of data transmission. When network fluctuations and interruptions occur, the system reduces data loss through automatic reconnection and caching mechanisms;

[0075] Routing and optimization unit for transmitted data: Establish an optimal routing selection model according to the network load situation, and select the best routing path for data transmission;

[0076] Analyze the network topology structure to obtain the connection relationships, communication links, and node information between devices;

[0077] Real-time collect network performance data, including bandwidth, latency, packet loss rate, signal strength, and node load;

[0078] Establish an optimal routing selection model with the goal of minimizing latency and load. Among them, the formula for the optimal routing selection model is:

[0079] TC = α·L + β·P + γ·N

[0080] In the formula, TC is the total transmission cost, α is the weight coefficient, L is the latency, β is the weight coefficient, P is the packet loss rate, γ is the weight coefficient, and N is the node load;

[0081] Based on the output of the optimal routing selection model, select the routing with the minimum total transmission cost;

[0082] Cloud data reception and verification unit: After the cloud platform receives the data packet from the wireless transmission module, parse and decrypt the data packet, extract the working status data, verify the received data, store it in the cloud database, and back up the data to multiple storage nodes;

[0083] Transmission status report and alarm unit: The wireless transmission module reports the data transmission status to the platform, including transmission success, failure, and latency information. When transmission anomalies occur, including data transmission failure and network interruption, the system automatically triggers an alarm.

[0084] Data processing and analysis module:

[0085] Real-time data analysis unit: Use a stream processing engine to analyze and process real-time data streams, extract key features from the original data, and through a visual dashboard and alarm system, real-time monitor the device status, detect abnormal behaviors and issue alarms. Based on historical fault data, construct fault labels to indicate which device behaviors are faults

[0086] Collect device failure data from past failure records, including device failure time, failure type, and failure cause information;

[0087] Based on the failure instances in historical data, construct failure labels to indicate which device behaviors are related to failures, manually annotate the historical failure data, and combine data analysis to mark which data points and time windows indicate that the device has failed;

[0088] Use the annotated failure data as a training set to train a machine learning model for failure prediction and classification;

[0089] Failure prediction unit: Analyze the time series trend of device data based on time series analysis technology, predict future failure occurrences, deploy the trained model to the production environment, monitor the device status in real time, and perform failure prediction based on real-time data;

[0090] Among them, the failure prediction formula is:

[0091]

[0092] In the formula, X t is the observed value at time t, μ is the constant term, is the autoregressive coefficient, X t-1 X t-2 X t-p are lag values, ∈ t is the noise term, θ 1 θ q is the moving average coefficient, ∈ t-1 ∈ t-q is the lag error term;

[0093] Warning unit: Set a failure warning threshold, and when the model predicts that the device is about to fail, the system issues an alarm notification;

[0094] Performance optimization and solution generation unit: Analyze the performance data of the device, identify performance bottlenecks, generate device optimization solutions based on machine learning technology, and automatically adjust device parameters through the system's self-learning ability to optimize device operation.

[0095] Control feedback module:

[0096] Device status evaluation unit: Analyze the current status of the device based on real-time data and historical trends, including load, efficiency, power consumption, and failure warning;

[0097] Optimization target setting unit: Set the device operation parameters to be adjusted according to the preset target, including target temperature, compressor speed, and cooling water flow;

[0098] Automatic adjustment and manual intervention: Based on the machine learning model control algorithm, automatically adjust the operating parameters of the device to meet the target requirements;

[0099] Automatically adjust the working load, valve opening, and flow rate of the refrigeration equipment according to the set target temperature;

[0100] Automatically adjust the speed or start / stop of the compressor according to the cooling demand and load conditions to optimize power consumption and refrigeration effect;

[0101] Adjust the refrigerant flow rate by controlling the working state of the refrigerant valve or pump to optimize the refrigeration efficiency, and adjust the speed of the fan to optimize the heat exchange effect;

[0102] If the automatic adjustment does not meet the expectations, the operator manually adjusts the device parameters for fine-tuning, and monitors the real-time effect after the device adjustment to ensure that the device operates within the expected range;

[0103] Manually adjust the parameters according to the feedback results to correct the previous adjustment and ensure that the device continues to operate in the optimal state;

[0104] Execution and control instruction issuing unit: Send the adjusted control signal to the device execution unit, monitor the device response during the adjustment process, and store the real-time data, parameter adjustment records, and device status information during the adjustment process in the database.

[0105] User interface module:

[0106] Data display unit: Display the current operating parameters of the device, including temperature, humidity, pressure, flow rate, current, and power;

[0107] Alarm information display: When the device fails or malfunctions, the alarm information is displayed through the interface, including the alarm type, occurrence time, alarm level, fault location, and fault description, providing the working status of each part of the device;

[0108] Control and adjustment unit: The operator manually adjusts the operating parameters of the device through the interface, supporting the remote operation function. The operator can adjust the parameters, start / stop control, and view the status of the device through the Internet.

[0109] In summary, the advantages of the present invention are as follows:

[0110] Through the data acquisition module, the system can collect the working status data of the device in real time, including multiple key parameters such as temperature, humidity, pressure, and current, and upload these data to the cloud platform through the wireless transmission module, facilitating device management personnel to monitor the device through the Internet anytime and anywhere. Remote monitoring enables operators and management personnel to obtain the device status in a timely manner, view the alarm information in real time, and avoid downtime caused by device failures;

[0111] Using a data processing and analysis module, combined with machine learning and big data analysis technologies, it conducts real-time analysis on device data. The system can not only monitor the operating status of the device, but also perform intelligent prediction through historical fault data and time series analysis, discover potential fault risks in advance, reduce device downtime, lower maintenance costs. The generation of fault prediction and performance optimization solutions further improves the reliability and operating efficiency of the device, ensuring that the device always maintains the best working state;

[0112] The control feedback module can automatically adjust the operating parameters of the gas cloud refrigeration device according to the data analysis results, such as temperature, compressor speed, refrigerant flow rate, etc., to ensure that the device operates in the optimal state. This automatic control function enables the device to adjust the operating strategy in real time according to environmental changes, load demands, and energy efficiency goals, improving the refrigeration effect and saving energy. The application of the machine learning model control algorithm enables the device to self-learn and adjust operating parameters, not only reducing manual intervention but also improving the intelligent level of the system;

[0113] The wireless transmission module uses data encryption and compression technologies to ensure data security and transmission efficiency. At the same time, the system has a network connection management and monitoring unit that monitors the network status in real time, ensuring that data loss is reduced through automatic reconnection and caching mechanisms during network fluctuations or interruptions, guaranteeing the stability of data transmission. Optimizing the data transmission route based on network topology and load conditions reduces network latency and improves data transmission efficiency;

[0114] The user interface module displays the current operating parameters, alarm information, and device operation trends of the device through a graphical dashboard. Operators can intuitively monitor the device status and support the remote control function. Operators can remotely adjust the operating parameters of the device through the interface, perform start / stop control, and optimize the adjustment according to real-time feedback. This not only improves management efficiency but also reduces the inconvenience caused by on-site operations;

[0115] The system is equipped with a cloud data receiving and verification unit, which can securely store device data and perform multiple backups, avoiding the loss of critical data caused by device failures or disaster events. The long-term accumulation and analysis of data provide sufficient data support for device maintenance, fault diagnosis, and performance optimization.

[0116] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art of this industry should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection required by the present invention is defined by the appended claims and their equivalents.

Claims

1. A gas-cloud refrigeration manufacturing monitoring system, characterized in that: include: Data acquisition module: used to collect working status data of gas-cloud refrigeration equipment in real time; Wireless transmission module: The wireless transmission module is electrically connected to the data acquisition module, and is used to transmit the data acquired by the data acquisition module to the cloud platform through a wireless network for remote transmission and monitoring; Data processing and analysis module: The data processing and analysis module is electrically connected to the wireless transmission module. The data processing and analysis module is used to perform real-time analysis on the device data transmitted from the cloud based on machine learning and big data analysis technology, use intelligent prediction algorithms to give early warnings of device failures, and generate performance optimization solutions; Control feedback module: The control feedback module is electrically connected to the data processing and analysis module, and the control feedback module is used to automatically adjust the operating parameters of the gas-cloud refrigeration equipment according to the analysis results; User interface module: The user interface module is electrically connected to the control feedback module. The user interface module is used to provide an interactive interface for equipment operators and managers, display real-time monitoring data, alarm information and equipment operation trends, and support remote control and parameter adjustment.

2. A gas-cloud refrigeration manufacturing monitoring system according to claim 1, characterized in that: The data acquisition module specifically includes: Sensor data acquisition module: Based on the API interface of temperature sensor, pressure sensor, flow sensor, current sensor and humidity sensor, it collects temperature data in real time, monitors the pressure status of the system, monitors flow data in real time, monitors the current data of the equipment, and obtains the humidity data of the equipment operating environment; Data preprocessing unit: performs preliminary processing on the collected raw data, converts analog signals into digital signals, sets sampling cycles, and regularly obtains numerical data from each sensor; Data preprocessing and filtering: Remove data noise based on Kalman filtering, calibrate the sensor output, and correct the deviation; Data formatting and standardization unit: Organize and convert the collected data from different sensors according to a unified standard format, and mark the data according to the timestamp.

3. A gas-cloud refrigeration manufacturing monitoring system according to claim 2, characterized in that: The wireless transmission module specifically includes: Data preparation and packaging unit: Packaging the collected raw data, including timestamp and device ID information, to form a data packet in a unified format; Data encryption and compression unit: Encrypts and compresses data based on AES technology; Data transmission unit: Send data directly from the wireless transmission module to the cloud platform based on Wi-Fi; Network connection management and monitoring unit: monitors the network connection status in real time to ensure the stability of data transmission. When network fluctuations and interruptions occur, the system reduces data loss through automatic reconnection and caching mechanisms; Routing and optimization unit for data transmission: Establish the best routing selection model according to the network load and select the best routing path for data transmission; Cloud data receiving and verification unit: After the cloud platform receives the data packet from the wireless transmission module, it parses and decrypts the data packet, extracts the working status data, verifies the received data, stores it in the cloud database, and backs up the data to multiple storage nodes; Transmission status reporting and alarm unit: The wireless transmission module reports the status of data transmission to the platform, including transmission success, failure and delay information. When transmission anomalies occur, including data transmission failure and network interruption, the system automatically triggers an alarm.

4. A gas-cloud refrigeration manufacturing monitoring system according to claim 3, characterized in that: The step of establishing an optimal routing selection model according to the load of the network and selecting the optimal routing path for data transmission specifically includes: Analyze the network topology to obtain the connection relationship, communication link and node information between devices; Collect network performance data in real time, including bandwidth, latency, packet loss rate, signal strength, and node load; The optimal routing model is established with the goal of minimizing delay and load, where the optimal routing model formula is: TC=α·L+β·P+γ·N In the formula, TC is the total transmission cost, α is the weight coefficient, L is the delay, β is the weight coefficient, P is the packet loss rate, γ is the weight coefficient, and N is the node load; Based on the output of the optimal routing selection model, the route with the minimum total transmission cost is selected.

5. A gas-cloud refrigeration manufacturing monitoring system according to claim 4, characterized in that: The data processing and analysis module specifically includes: Real-time data analysis unit: Uses stream processing engine to analyze and process real-time data streams, extracts key features from raw data, monitors device status in real time through visual dashboards and alarm systems, detects abnormal behaviors and issues alarms, and builds fault labels based on historical fault data to indicate which device behaviors are manifestations of faults. Fault prediction unit: Analyzes the time series trend of equipment data based on time series analysis technology, predicts future faults, deploys the trained model to the production environment, monitors the equipment status in real time, and predicts faults based on real-time data; Early warning unit: Set the fault warning threshold. When the model predicts that the equipment is about to fail, the system will issue an alarm notification. Performance optimization and solution generation unit: Analyzes the performance data of the equipment, identifies performance bottlenecks, generates equipment optimization solutions based on machine learning technology, and automatically adjusts equipment parameters and optimizes equipment operation through the system's self-learning capabilities.

6. A gas-cloud refrigeration manufacturing monitoring system according to claim 5, characterized in that: The construction of fault labels based on historical fault data to indicate which device behaviors are manifestations of faults specifically includes: Collect equipment failure data from past failure records, including equipment failure time, failure type, and failure cause information; Based on the fault instances in the historical data, fault labels are constructed to indicate which device behaviors are related to the faults. The historical fault data is manually annotated and combined with data analysis, which data points and time windows indicate that the device has failed. The labeled fault data is used as a training set to train the machine learning model for fault prediction and classification.

7. A gas-cloud refrigeration manufacturing monitoring system according to claim 6, characterized in that: The time series analysis technology is used to analyze the time series trend of equipment data, predict future failures, deploy the trained model to the production environment, monitor the equipment status in real time, and predict failures based on real-time data. include: Among them, the fault prediction formula is: Where, X t is the observed value at time t, μ is a constant term, is the autoregression coefficient, X t-1 X t-2 X t-p is the lag value, ∈ t is the noise term, θ1θ q is the moving average coefficient, ∈ t-1 ∈ t-q is the lagged error term.

8. A gas-cloud refrigeration manufacturing monitoring system according to claim 7, characterized in that: The control feedback module specifically includes: Equipment status evaluation unit: Analyzes the current status of equipment based on real-time data and historical trends, including load, efficiency, power consumption, and fault warning; Set optimization target unit: Set the equipment operating parameters that need to be adjusted according to the preset targets, including target temperature, compressor speed and cooling water flow; Automatic adjustment and manual intervention: Based on the machine learning model control algorithm, the operating parameters of the equipment are automatically adjusted to meet the target requirements.

9. A gas-cloud refrigeration manufacturing monitoring system according to claim 8, characterized in that: The automatic adjustment of the operating parameters of the equipment based on the machine learning model control algorithm to meet the target requirements specifically includes: Automatically adjust the workload, valve opening and flow rate of the refrigeration equipment according to the set target temperature; Automatically adjust the speed or start and stop of the compressor according to cooling demand and load conditions to optimize power consumption and cooling effect; By controlling the working status of the refrigerant valve or pump, the refrigerant flow rate is adjusted to optimize the refrigeration efficiency, and the fan speed is adjusted to optimize the heat exchange effect; If the automatic adjustment does not meet expectations, the operator manually adjusts the equipment parameters, performs fine-tuning, and monitors the effects of the equipment adjustments in real time to ensure that the equipment operates within the expected range; Manually adjust parameters based on feedback results and correct previous adjustments to ensure that the equipment continues to operate in the optimal state; Execution and control instruction sending unit: sends the adjusted control signal to the equipment execution unit, monitors the equipment response during the adjustment process, and stores the real-time data, parameter adjustment records and equipment status information during the adjustment process into the database.

10. A gas-cloud refrigeration manufacturing monitoring system according to claim 9, characterized in that: The user interface module specifically includes: Data display unit: displays the current operating parameters of the equipment, including temperature, humidity, pressure, flow, current and power; Alarm information display: When the equipment fails or is abnormal, the alarm information is displayed through the interface, including the alarm type, occurrence time, alarm level, fault location and fault description, providing the working status of each part of the equipment; Control and adjustment unit: The operator manually adjusts the operating parameters of the equipment through the interface. The remote operation function is supported. The operator can adjust the parameters, start and stop the equipment, and check the status through the Internet.

Images