Failure early warning and remote diagnosis system for refrigeration equipment

Abstract

The invention relates to the technical field of refrigeration equipment detection, and discloses a refrigeration equipment fault early warning and remote diagnosis system comprising an intelligent sensor network module used for collecting various operation data of refrigeration equipment, including temperature, pressure, vibration, sound and image data, and transmitting the collected data to a data preprocessing module; the data preprocessing module is connected with the intelligent sensor network module and is used for carrying out feature extraction and dimension reduction processing on the acquired operation data and transmitting the processed data to the local edge computing module and the remote cloud platform module; and the local edge calculation module is connected with the data preprocessing module and is used for carrying out preliminary analysis on the processed data, and by adopting a multi-modal data fusion technology and combining a deep learning algorithm, tiny fault signals, such as early leakage of a refrigerant, slight vibration abnormity of a compressor and the like, of the refrigeration equipment in the operation process can be effectively captured.

Description

Technical Field

[0001] This invention relates to the field of refrigeration equipment testing technology, specifically a refrigeration equipment fault early warning and remote diagnostic system. Background Technology

[0002] Refrigeration equipment plays a vital role in modern industry and daily life, and its operational stability and reliability directly impact production efficiency and quality of life. With the widespread application of refrigeration equipment, the demand for fault early warning and remote diagnostic technologies is increasing. Traditional refrigeration equipment fault early warning systems primarily rely on sensor monitoring and threshold judgment. By installing temperature, pressure, and other sensors on key parts of the equipment, real-time operational data is collected and compared with preset thresholds to determine if a fault has occurred. For example, when the condensing pressure of the refrigeration system exceeds a set upper limit threshold, the system will issue a fault warning signal. While this threshold-based method is relatively simple and low-cost, it has significant limitations. It can only detect obvious faults exceeding the threshold range. It struggles to provide early warnings for complex, progressive faults (such as early-stage refrigerant leaks or early compressor wear), which can lead to further escalation of the fault, increasing maintenance costs and equipment downtime.

[0003] Furthermore, most existing remote diagnostic systems are based on expert systems, using a series of rule-based reasoning to determine the type of fault. These rules are summaries of expert experience; for example, when the system detects an abnormally high evaporator temperature and fluctuating compressor current, expert rules can determine that the fault is likely caused by evaporator frosting. However, this expert-based diagnostic method relies on the completeness of expert knowledge. When new fault types are encountered or equipment models are updated, the expert knowledge base needs to be updated promptly; otherwise, effective diagnosis is impossible. Moreover, the reasoning process of expert systems is relatively complex, making it difficult for non-professionals to understand and use.

[0004] With the development of IoT and big data technologies, some refrigeration equipment fault early warning and remote diagnostic systems have begun to utilize IoT technology to transmit equipment data to the cloud for analysis, enabling remote monitoring and diagnosis. However, these systems are inefficient in data processing and analysis, unable to accurately assess equipment status in real time, and unable to provide timely and accurate fault information to maintenance personnel. Furthermore, refrigeration equipment operating data is characterized by high frequency and high precision; data transmission delays and errors can affect the accuracy of diagnosis. In addition, most existing remote diagnostic systems lack user-friendly interfaces, making it difficult for maintenance personnel to easily obtain equipment status information and fault analysis reports, thus impacting the system's practicality and promotional value.

[0005] In summary, existing refrigeration equipment fault early warning and remote diagnostic systems suffer from insufficient early fault warning capabilities, poor adaptability, inadequate accuracy and real-time performance of remote diagnostics, and unsatisfactory user experience. These problems limit the further development and application of refrigeration equipment fault early warning and remote diagnostic technologies. Therefore, those skilled in the art propose a refrigeration equipment fault early warning and remote diagnostic system to address these issues. Summary of the Invention

[0006] To address the shortcomings of existing technologies, this invention provides a refrigeration equipment fault early warning and remote diagnostic system, which solves the problems of insufficient early fault warning capability, poor adaptability, and unsatisfactory user interaction experience in existing technologies.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a refrigeration equipment fault early warning and remote diagnostic system, comprising:

[0008] The intelligent sensor network module is used to collect various operating data of the refrigeration equipment, including temperature, pressure, vibration, sound and image data, and transmit the collected data to the data preprocessing module;

[0009] The data preprocessing module, connected to the intelligent sensor network module, is used to extract features and reduce dimensions of the collected operational data, and transmit the processed data to the local edge computing module and the remote cloud platform module.

[0010] The local edge computing module is connected to the data preprocessing module. It is used to perform preliminary analysis on the processed data, determine whether there are obvious fault characteristics, and transmit the preliminary analysis results to the remote cloud platform module.

[0011] The deep learning diagnostic model module is deployed in the remote cloud platform module and connected to the remote cloud platform module. It is used to receive data from the data preprocessing module and the local edge computing module, and to perform comprehensive analysis of the data through deep learning algorithms to identify the fault modes of the refrigeration equipment and generate a fault diagnosis report.

[0012] The remote cloud platform module is connected to the data preprocessing module, the local edge computing module, and the deep learning diagnostic model module. It is used to receive and store the processed data from the data preprocessing module, the preliminary analysis results from the local edge computing module, and the fault diagnosis report from the deep learning diagnostic model module, and transmit the fault diagnosis report to the user interaction module.

[0013] The user interaction module connects to the remote cloud platform module. It is used to receive fault diagnosis reports from the remote cloud platform module and display them to the user through the user interface. It also receives user operation commands and transmits them to the remote cloud platform module.

[0014] Preferably, the intelligent sensor network module includes:

[0015] Temperature sensors are used to collect temperature data from key components of refrigeration equipment.

[0016] Pressure sensors are used to collect refrigerant pressure data from refrigeration equipment.

[0017] Vibration sensors are used to collect vibration signal data from refrigeration equipment;

[0018] A sound sensor is used to collect sound data of the refrigeration equipment during operation.

[0019] Infrared thermal imaging equipment is used to collect image data of the temperature distribution on the surface of refrigeration equipment.

[0020] Preferably, the data preprocessing module uses wavelet transform to extract features from the vibration signal data, extracting key features that can reflect the equipment status.

[0021] Preferably, the deep learning diagnostic model module adopts a hybrid model of convolutional neural network and long short-term memory network, with the convolutional neural network used to process image data and the long short-term memory network used to process time series data.

[0022] Preferably, the remote cloud platform module includes:

[0023] Data storage unit, used to store the collected operational data and processed data;

[0024] The computing unit is used to run the deep learning diagnostic model module for data processing and analysis.

[0025] The communication unit is used for data transmission and communication with the data preprocessing module, the local edge computing module, and the user interaction module.

[0026] Preferably, the user interaction module includes:

[0027] User interface for displaying fault diagnosis reports and equipment status information;

[0028] The operation instruction input unit is used to receive user operation instructions and transmit them to the remote cloud platform module.

[0029] Preferably, the local edge computing module can determine whether there are obvious fault characteristics based on the preliminary analysis results, and immediately send an alarm signal to the remote cloud platform module when obvious fault characteristics are found.

[0030] Preferably, the remote cloud platform module can adjust the parameter settings of the deep learning diagnostic model module according to the user's operation instructions.

[0031] Preferably, the user interaction module can access the remote cloud platform module through a mobile terminal or computer terminal.

[0032] Preferably, the system further includes a security module to ensure the security of data transmission and storage, and to prevent data leakage and unauthorized access.

[0033] This invention provides a fault early warning and remote diagnostic system for refrigeration equipment. It has the following beneficial effects:

[0034] 1. This invention, employing multimodal data fusion technology combined with deep learning algorithms, can effectively capture minute fault signals during the operation of refrigeration equipment, such as early refrigerant leakage and slight abnormal compressor vibration. Compared with existing technologies, this innovative method can not only identify obvious fault modes but also provide early warnings of faults, preventing further escalation. Early warnings allow maintenance personnel to take timely measures at the initial stage of a fault, reducing maintenance costs and equipment downtime, and improving equipment reliability and lifespan. Furthermore, the self-learning capability of the deep learning model enables the system to continuously optimize the diagnostic model, adapting to changes in different equipment and operating conditions, further improving the accuracy and reliability of fault warnings.

[0035] 2. This invention combines IoT technology with deep learning algorithms to construct a highly versatile and flexible fault early warning and remote diagnostic system for refrigeration equipment. This system can quickly adapt to different types of refrigeration equipment and operating conditions without requiring extensive customized development for each type of equipment. Edge computing technology is used to perform preliminary processing on the collected data, reducing data transmission volume and improving data transmission efficiency and system real-time performance. Simultaneously, leveraging the powerful computing capabilities and distributed architecture of the cloud platform, the deep learning model can efficiently process and analyze data from multiple devices, generating detailed fault diagnosis reports. This innovative system architecture not only improves the accuracy and real-time performance of remote diagnostics but also, through a user-friendly interface, enables maintenance personnel to access equipment status information and fault analysis reports anytime, anywhere, improving maintenance efficiency and user experience. Attached Figure Description

[0036] Figure 1 This is the overall flowchart of the present invention;

[0037] Figure 2 This is a data processing flowchart of the present invention. Detailed Implementation

[0038] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0039] Please see the appendix Figure 1 - Appendix Figure 2 This invention provides a refrigeration equipment fault early warning and remote diagnosis system, including:

[0040] The intelligent sensor network module is used to collect various operating data of the refrigeration equipment, including temperature, pressure, vibration, sound and image data, and transmit the collected data to the data preprocessing module;

[0041] The intelligent sensor network module includes:

[0042] Temperature sensors are used to collect temperature data from key components of refrigeration equipment.

[0043] Pressure sensors are used to collect refrigerant pressure data from refrigeration equipment.

[0044] Vibration sensors are used to collect vibration signal data from refrigeration equipment.

[0045] A sound sensor is used to collect sound data of the refrigeration equipment during operation.

[0046] Infrared thermal imaging equipment is used to collect image data of the temperature distribution on the surface of refrigeration equipment.

[0047] Specifically, temperature sensors monitor temperature changes in key components of the refrigeration equipment, such as the compressor, evaporator, and condenser. Pressure sensors measure refrigerant pressure within the system. Vibration sensors capture vibration signals from the refrigeration equipment; by analyzing parameters such as vibration frequency and amplitude, potential wear or loosening of internal components can be detected early. Sound sensors collect sound signals generated during equipment operation; abnormal sound changes often indicate early signs of equipment malfunction. Furthermore, infrared thermal imaging equipment captures images of the temperature distribution on the surface of the refrigeration equipment, visually displaying areas of thermal anomalies.

[0048] The data collected by these sensors will be transmitted to the data preprocessing module for further analysis and processing. Through multimodal data acquisition via the intelligent sensor network module, this invention can more comprehensively and accurately monitor the operating status of refrigeration equipment, providing a solid data foundation for early warning and precise diagnosis of faults, thereby effectively improving the operational reliability and maintenance efficiency of refrigeration equipment.

[0049] The data preprocessing module, connected to the intelligent sensor network module, is used to extract features and reduce dimensions of the collected operational data, and transmit the processed data to the local edge computing module and the remote cloud platform module. The data preprocessing module uses wavelet transform to extract features from the vibration signal data, extracting key features that can reflect the equipment status.

[0050] Specifically, the data preprocessing module is closely connected to the intelligent sensor network module and is mainly responsible for feature extraction and dimensionality reduction of the collected operational data. The role of this module is to transform the raw data, which may contain a lot of redundant information, into more valuable feature data so that subsequent modules can analyze and process it more efficiently.

[0051] In this invention, the data preprocessing module specifically employs wavelet transform technology to process vibration signal data. Wavelet transform is a powerful signal processing tool capable of decomposing signals into components at different frequencies and time scales, thereby extracting key features that reflect the equipment's state. Through wavelet transform, noise can be effectively removed, highlighting important features in the signal, such as abnormal frequency components or time-domain features in the vibration signal.

[0052] After feature extraction and dimensionality reduction, the data will be transmitted to both the local edge computing module and the remote cloud platform module. The local edge computing module can use this processed data for preliminary fault diagnosis, while the remote cloud platform module can further utilize advanced algorithms such as deep learning for comprehensive analysis and diagnosis. This data preprocessing method not only improves data availability and analysis efficiency but also provides strong support for the system's real-time performance and accuracy.

[0053] The local edge computing module is connected to the data preprocessing module. It is used to perform preliminary analysis on the processed data, determine whether there are obvious fault characteristics, and transmit the preliminary analysis results to the remote cloud platform module.

[0054] The deep learning diagnostic model module is deployed in the remote cloud platform module and connected to the remote cloud platform module. It is used to receive data from the data preprocessing module and the local edge computing module, and to perform comprehensive analysis of the data through deep learning algorithms to identify the fault modes of the refrigeration equipment and generate fault diagnosis reports. The deep learning diagnostic model module adopts a hybrid model of convolutional neural network and long short-term memory network. The convolutional neural network is used to process image data, and the long short-term memory network is used to process time series data.

[0055] Specifically, the deep learning diagnostic model module employs a hybrid model of Convolutional Neural Networks (CNN) and Long Short-Term Memory Networks (LSTM). This hybrid model combines the advantages of CNN in processing image data with the advantages of LSTM in processing time-series data. Specifically, CNN is used to analyze image data from infrared thermal imaging equipment, automatically extracting features from the images and identifying abnormal temperature areas on the equipment surface, which is highly effective for detecting problems such as refrigerant leaks and decreased heat exchanger efficiency. LSTM, on the other hand, is used to process time-series data, such as data collected by sensors for temperature, pressure, and vibration, capturing the patterns of change in these data over time.

[0056] Through this hybrid model, the deep learning diagnostic model module can comprehensively analyze multimodal data, thereby more accurately identifying the failure modes of refrigeration equipment. The generated fault diagnosis report not only includes the type and location of the fault but also provides possible causes and maintenance suggestions, offering crucial reference information for maintenance personnel. This deep learning-based diagnostic method can automatically learn the normal operating and failure modes of equipment under different operating conditions, possessing adaptive and self-learning capabilities. This effectively improves the accuracy and reliability of fault diagnosis, adapting to different types of refrigeration equipment and operating conditions.

[0057] The remote cloud platform module is connected to the data preprocessing module, the local edge computing module, and the deep learning diagnostic model module. It is used to receive and store the processed data from the data preprocessing module, the preliminary analysis results from the local edge computing module, and the fault diagnosis report from the deep learning diagnostic model module, and transmit the fault diagnosis report to the user interaction module.

[0058] The remote cloud platform module includes:

[0059] Data storage unit, used to store the collected operational data and processed data;

[0060] The computing unit is used to run the deep learning diagnostic model module for data processing and analysis.

[0061] The communication unit is used for data transmission and communication with the data preprocessing module, the local edge computing module, and the user interaction module.

[0062] The remote cloud platform module can adjust the parameter settings of the deep learning diagnostic model module according to the user's operation instructions.

[0063] Specifically, the data storage unit is responsible for storing the raw operational data collected from the intelligent sensor network module, as well as the data processed by the data preprocessing module. This data provides the foundation for subsequent fault diagnosis and analysis. The computing unit runs the deep learning diagnostic model module, utilizing its powerful computing capabilities to process and analyze the data to identify fault modes of the refrigeration equipment and generate fault diagnosis reports. The communication unit ensures smooth data transmission and communication between the remote cloud platform module, the data preprocessing module, the local edge computing module, and the user interaction module, enabling information exchange between the modules.

[0064] Furthermore, the remote cloud platform module also has the function of adjusting the parameter settings of the deep learning diagnostic model module based on the operation commands input by the user through the user interaction module. This function enables the system to flexibly adjust the parameters of the diagnostic model according to different diagnostic needs and user preferences, thereby improving the accuracy and adaptability of diagnosis and better meeting users' needs for early warning and remote diagnosis of refrigeration equipment faults.

[0065] The user interaction module connects to the remote cloud platform module. It is used to receive fault diagnosis reports from the remote cloud platform module and display them to the user through the user interface. It also receives user operation commands and transmits them to the remote cloud platform module.

[0066] The user interaction module includes:

[0067] The user interface is used to display fault diagnosis reports and equipment status information; the user interaction module can access the remote cloud platform module through mobile terminals or computer terminals.

[0068] The operation instruction input unit is used to receive user operation instructions and transmit them to the remote cloud platform module.

[0069] The local edge computing module can determine whether there are obvious fault characteristics based on the preliminary analysis results, and immediately send an alarm signal to the remote cloud platform module when obvious fault characteristics are found.

[0070] Specifically, the user interaction module includes a user interface and an operation command input unit. The user interface is used to intuitively display fault diagnosis reports and real-time status information of the equipment, enabling users to clearly understand the operating status of the refrigeration equipment and potential problems. The operation command input unit allows users to send commands to the system via mobile terminals or computer terminals. These commands are then transmitted to the remote cloud platform module, allowing users to remotely control and adjust the operating parameters of the diagnostic system or perform specific diagnostic operations.

[0071] Furthermore, the local edge computing module possesses preliminary analysis capabilities, enabling it to quickly process information received from the data preprocessing module and determine the presence of obvious fault characteristics. Once a clear fault indication is detected, the local edge computing module immediately sends an alarm signal to the remote cloud platform module, ensuring timely fault detection and handling. This design not only improves system response speed but also enhances the timeliness of fault warnings, allowing maintenance personnel to take swift action and reduce equipment downtime and maintenance costs.

[0072] The system also includes a security module to ensure the security of data transmission and storage, and to prevent data leakage and unauthorized access.

[0073] Specifically, the core function of the security module is to ensure the security of data transmission and storage during system operation, effectively preventing data leakage and unauthorized access. In this system, data transmission involves multiple stages, from the intelligent sensor network module to the data preprocessing module, the local edge computing module, and finally the remote cloud platform module. The remote cloud platform module also needs to store a large amount of important information such as equipment operation data and fault diagnosis reports. The security module encrypts the data during transmission using encryption algorithms to ensure that the data is not stolen or tampered with. Simultaneously, for data stored in the remote cloud platform module, the security module employs an access control mechanism, allowing only authorized users or modules verified by the system to access the corresponding data, thereby preventing unauthorized access. Furthermore, the security module has real-time monitoring capabilities, capable of detecting abnormal activities during system operation. Once a potential network attack or malicious access attempt is detected, it can quickly take measures to block it and promptly issue an alert to the system administrator. Through these functions of the security module, the refrigeration equipment fault early warning and remote diagnostic system can provide users with a safe and reliable operating environment, protecting user privacy and equipment data security, enhancing user trust in the system, and thus ensuring the stable operation and effective application of the system.

[0074] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A refrigeration equipment fault early warning and remote diagnostic system, characterized in that, include: The intelligent sensor network module is used to collect various operating data of the refrigeration equipment, including temperature, pressure, vibration, sound and image data, and transmit the collected data to the data preprocessing module; The data preprocessing module, connected to the intelligent sensor network module, is used to extract features and reduce dimensions of the collected operational data, and transmit the processed data to the local edge computing module and the remote cloud platform module. The local edge computing module is connected to the data preprocessing module. It is used to perform preliminary analysis on the processed data, determine whether there are obvious fault characteristics, and transmit the preliminary analysis results to the remote cloud platform module. The deep learning diagnostic model module is deployed in the remote cloud platform module and connected to the remote cloud platform module. It is used to receive data from the data preprocessing module and the local edge computing module, and to perform comprehensive analysis of the data through deep learning algorithms to identify the fault modes of the refrigeration equipment and generate a fault diagnosis report. The remote cloud platform module is connected to the data preprocessing module, the local edge computing module, and the deep learning diagnostic model module. It is used to receive and store the processed data from the data preprocessing module, the preliminary analysis results from the local edge computing module, and the fault diagnosis report from the deep learning diagnostic model module, and transmit the fault diagnosis report to the user interaction module. The user interaction module connects to the remote cloud platform module. It is used to receive fault diagnosis reports from the remote cloud platform module and display them to the user through the user interface. It also receives user operation commands and transmits them to the remote cloud platform module.

2. The refrigeration equipment fault early warning and remote diagnosis system according to claim 1, characterized in that, The intelligent sensor network module includes: Temperature sensors are used to collect temperature data from key components of refrigeration equipment. Pressure sensors are used to collect refrigerant pressure data from refrigeration equipment. Vibration sensors are used to collect vibration signal data from refrigeration equipment; A sound sensor is used to collect sound data of the refrigeration equipment during operation. Infrared thermal imaging equipment is used to collect image data of the temperature distribution on the surface of refrigeration equipment.

3. The refrigeration equipment fault early warning and remote diagnosis system according to claim 1, characterized in that, The data preprocessing module uses wavelet transform to extract features from vibration signal data, extracting key features that can reflect the equipment status.

4. The refrigeration equipment fault early warning and remote diagnosis system according to claim 1, characterized in that, The deep learning diagnostic model module adopts a hybrid model of convolutional neural networks and long short-term memory networks. The convolutional neural network is used to process image data, and the long short-term memory network is used to process time series data.

5. The refrigeration equipment fault early warning and remote diagnosis system according to claim 1, characterized in that, The remote cloud platform module includes: Data storage unit, used to store the collected operational data and processed data; The computing unit is used to run the deep learning diagnostic model module for data processing and analysis. The communication unit is used for data transmission and communication with the data preprocessing module, the local edge computing module, and the user interaction module.

6. The refrigeration equipment fault early warning and remote diagnosis system according to claim 1, characterized in that, The user interaction module includes: User interface for displaying fault diagnosis reports and equipment status information; The operation instruction input unit is used to receive user operation instructions and transmit them to the remote cloud platform module.

7. The refrigeration equipment fault early warning and remote diagnosis system according to claim 1, characterized in that, The local edge computing module can determine whether there are obvious fault characteristics based on the preliminary analysis results, and immediately send an alarm signal to the remote cloud platform module when obvious fault characteristics are found.

8. The refrigeration equipment fault early warning and remote diagnosis system according to claim 1, characterized in that, The remote cloud platform module can adjust the parameter settings of the deep learning diagnostic model module according to the user's operation instructions.

9. The refrigeration equipment fault early warning and remote diagnosis system according to claim 1, characterized in that, The user interaction module can access the remote cloud platform module through a mobile terminal or computer terminal.

10. The refrigeration equipment fault early warning and remote diagnosis system according to claim 1, characterized in that, The system also includes a security module to ensure the security of data transmission and storage, and to prevent data leakage and unauthorized access.

Images