Intelligent shielding modular freezer system based on the Internet of Things

Abstract

The present invention provides an intelligent shielding modular freezer system based on the Internet of Things, belonging to the technical field of the Internet of Things. The system includes an intelligent freezer main body and a control system. The control system includes: a data acquisition module, including high-precision sensors deployed inside the intelligent freezer main body, used to collect the operation data of the intelligent freezer main body; a maintenance module, used to construct a knowledge graph based on the collected operation data and the historical fault data of the freezer for multi-dimensional correlation analysis, and use unsupervised learning algorithms to mine normal operation modes, identify abnormal operation states, and is also used to determine abnormal components and locate the root cause of faults through a preset health assessment strategy when an abnormal operation state is identified; an energy-saving regulation module, used to obtain personnel activity information and adjust the operation state of the intelligent freezer main body according to the obtained information through a preset regulation strategy. The present invention significantly improves the intelligent level, reliability and operation efficiency of the freezer.

Description

Technical Field

[0001] The present invention relates to the technical field of the Internet of Things, and more particularly to an intelligent shielding modular freezer system based on the Internet of Things. Background Art

[0002] With the rapid development of the Internet of Things technology, freezers, as important storage devices, are increasingly widely used in commercial, medical, scientific research and other fields. To meet the requirements of intelligent and efficient management, how to achieve intelligent operation and maintenance, energy consumption optimization and precise item management of freezers has become a research hotspot. The introduction of the Internet of Things technology enables freezers to collect and transmit data in real time, providing a technical basis for the intelligent upgrade of freezers, and the research investment in the intelligent system of freezers in related fields continues to increase.

[0003] However, there are still many deficiencies in the existing freezer management systems. In terms of equipment maintenance, traditional freezers lack comprehensive monitoring and intelligent analysis of the equipment operation status, making it difficult to give early warnings before faults occur. Usually, they can only be repaired passively after faults occur, resulting in high maintenance costs and affecting the normal use of the equipment. In terms of energy consumption management, most freezers cannot dynamically adjust the operation status according to the usage scenarios and personnel activities, resulting in energy waste. In the item management link, relying on manual inventory or simple barcode identification is inefficient and error-prone, making it difficult to achieve precise positioning and efficient management of items, and unable to meet the requirements of intelligent and refined management of the freezer system in modern warehousing management. Summary of the Invention

[0004] The present invention provides an intelligent shielding modular freezer system based on the Internet of Things to solve the problems such as lagging early warning of equipment faults and extensive energy consumption management existing in the prior art.

[0005] To achieve the above object, an embodiment of the present invention provides an intelligent shielding modular freezer system based on the Internet of Things. The intelligent shielding modular freezer system includes an intelligent freezer main body and a control system. The control system includes: a data acquisition module, including sensors deployed inside the intelligent freezer main body, for acquiring the operation data of the intelligent freezer main body; a maintenance module, for constructing a knowledge graph based on the acquired operation data and the historical fault data of the freezer to perform multi-dimensional correlation analysis, and using an unsupervised learning algorithm to mine normal operation modes, identify abnormal operation states, and further, when an abnormal operation state is identified, determine abnormal components and locate the root cause of the fault through a preset health assessment strategy; an energy-saving regulation module, for acquiring personnel activity information and adjusting the operation state of the intelligent freezer main body according to the acquired information through a preset regulation strategy.

[0006] Optionally, the control system further includes: an energy harvesting module, which includes a solar panel and a thermoelectric power generation module deployed above the main body of the intelligent refrigerator, and is used to convert light energy and temperature difference energy into electrical energy and store the electrical energy in a lithium battery pack.

[0007] Optionally, the energy harvesting module is also used to distribute the stored electrical energy to the low-power modules in the main body of the intelligent refrigerator when power is off, so as to maintain the operation of some functions of the refrigerator.

[0008] Optionally, the use of unsupervised learning algorithms to mine normal operation modes and identify abnormal operation states includes: based on the results of association analysis, using unsupervised learning algorithms to cluster the operation data of the refrigerator under normal operation conditions to mine the normal operation modes of the refrigerator; comparing the real-time operation data with the operation data of the normal operation modes, and when the deviation of a certain dimension of data exceeds the first preset threshold, it is identified that the refrigerator is in an abnormal operation state.

[0009] Optionally, determining abnormal components through a preset health assessment strategy includes: when the refrigerator is in an abnormal operation state, according to the design parameter data of each component in the refrigerator, the historical operation data of the refrigerator, and the real-time operation data, using reinforcement learning algorithms to dynamically adjust the basic weights of each data; using the entropy weight method to calculate the objective weights of each data to measure the information entropy size of each data; using grey relational degree analysis to calculate the correlation degree between the real-time operation data and the operation data of the normal operation modes, and combining the basic weights and the calculated objective weights to construct a comprehensive scoring model; according to the constructed comprehensive scoring model, calculating the health scores of each component in the refrigerator; when the health score of a certain component is lower than the second preset threshold or the change rate exceeds the third threshold, it is determined that the component is an abnormal component.

[0010] Optionally, locating the root cause of the fault includes: when an abnormal component is identified, using the density peak clustering algorithm to dynamically cluster the real-time operation data of the refrigerator according to the local density and relative distance of the data to generate clustering clusters; according to the distribution and morphological changes of the clustering clusters, combined with the typical data clustering characteristics corresponding to different fault types in the historical fault data, extracting the fault characteristics of the current fault; matching the extracted fault characteristics with the indexes in the preset fault mode database, and using the inverted index technology to retrieve multiple fault modes with high similarity to the fault characteristics to generate a fault candidate list; based on the generated fault candidate list, using a Bayesian network, combined with the real-time operation data and the historical fault data, calculating the posterior probability of each fault cause in the fault candidate list; and locating the root cause of the fault according to the calculated posterior probability.

[0011] Optionally, the intelligent freezer body includes a millimeter-wave radar and a thermal imaging sensor for collecting personnel activity information. The energy-saving regulation module is configured to: obtain and analyze the collected personnel activity information to determine whether there is a person approaching the freezer; when no person approaches the freezer, reduce the lighting brightness of the freezer to the basic level and reduce the start-stop frequency of the compressor to reduce energy consumption; when no person approaches the freezer and the duration exceeds a preset time, control the freezer to enter the sleep mode, only maintaining the basic temperature and humidity monitoring function; when a person approaches the freezer, control the freezer to enter the normal mode.

[0012] Optionally, the intelligent freezer body further includes an RFID radio frequency identification device for identifying the RFID tags carried by the items in the freezer to obtain the identity information, storage location information, and inbound and outbound time information of the items.

[0013] Optionally, the maintenance module is further configured to issue a warning message and fault root cause location information after determining the fault root cause.

[0014] Optionally, the control system further includes a remote monitoring module. The remote monitoring module is connected to the intelligent freezer body through Internet of Things communication technology for real-time monitoring of the freezer operation status, including viewing operation data, health scores, and receiving the information sent by the maintenance module.

[0015] The intelligent shielding modular freezer system provided by the present invention realizes all-round intelligent management through the coordinated operation of multiple modules. The data acquisition module accurately obtains operation data. The maintenance module combines a knowledge graph and intelligent algorithms to achieve early warning, accurate positioning, and efficient processing of faults. The energy-saving regulation module intelligently adjusts the operation status according to personnel activities, effectively reducing energy consumption. At the same time, the energy harvesting module realizes self-power supply, RFID technology helps with accurate item management, and the modular design is convenient for maintenance and upgrading, comprehensively improving the intelligence level, operation efficiency, and reliability of the freezer, significantly reducing operation costs and improving management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. In the drawings:

[0017] Figure 1 is the structural diagram of the intelligent shielding modular freezer system provided by the embodiment of the present invention;

[0018] Figure 2 is the abnormal detection flowchart provided by the embodiment of the present invention;

[0019] Figure 3 is the flowchart for determining abnormal components provided by an embodiment of the present invention;

[0020] Figure 4 is the flowchart for locating the root cause of faults provided by an embodiment of the present invention;

[0021] Figure 5 is the energy-saving regulation flowchart provided by an embodiment of the present invention. Detailed Description of the Invention

[0022] The following will describe in detail the specific implementation manners of the embodiments of the present invention with reference to the accompanying drawings. It should be understood that the specific implementation manners described herein are only for the purpose of illustrating and explaining the embodiments of the present invention, and are not used to limit the embodiments of the present invention.

[0023] It should be noted that the acquisition, transmission, storage, use, processing, etc. of data in the technical solution of this application all comply with the relevant regulations of national laws and regulations. In the embodiments of this application, certain industry-existing solutions such as software, components, models, etc. may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility in the implementation of the technical solution of this application, but it does not mean that the applicant has already or necessarily used this solution.

[0024] With the wide application of special items such as vaccines, biological reagents, and highly active drugs in key fields such as medical treatment, scientific research, pharmaceuticals, and public safety, higher technical requirements are put forward for the stability, safety, and intelligent management ability of the storage environment. The traditional shielded cold cabinet system has been difficult to meet the needs of modern management. Therefore, it is urgent to develop a cold cabinet system with higher intelligent level and reliability.

[0025] In view of the above problems, the present invention provides an intelligent shielded modular cold cabinet system based on the Internet of Things. Through the Internet of Things technology and multi-module collaboration, it realizes intelligent acquisition and analysis of cold cabinet operation data, accurate prediction of faults, dynamic optimization of energy consumption, efficient management of items, and modular convenient maintenance, significantly improving the intelligent level, reliability, and operation efficiency of the cold cabinet.

[0026] The following will describe the present invention in combination with Figures 1 - 5 Specifically describe the present invention.

[0027] As Figure 1As shown in the figure, an embodiment of the present invention provides an intelligent shielding modular freezer system based on the Internet of Things. The intelligent shielding modular freezer system includes an intelligent freezer main body and a control system. The control system includes: a data acquisition module, including high-precision sensors deployed inside the intelligent freezer main body, for collecting the operation data of the intelligent freezer main body; a maintenance module, for constructing a knowledge graph based on the collected operation data and the historical fault data of the freezer to perform multi-dimensional correlation analysis, and using unsupervised learning algorithms to mine normal operation modes, identify abnormal operation states, and also for determining abnormal components and locating the root cause of the fault through a preset health assessment strategy when an abnormal operation state is identified; an energy-saving regulation module, for obtaining personnel activity information and adjusting the operation state of the intelligent freezer main body according to the obtained information through a preset regulation strategy.

[0028] The intelligent shielding modular freezer system provided by the present invention constructs a core architecture of "intelligent freezer main body + control system". Among them, the data acquisition module, through high-precision sensors deployed inside the intelligent freezer main body, collects key data such as temperature, pressure, and current during the operation of the freezer in real time and accurately, providing basic data support for subsequent intelligent analysis; the maintenance module deeply integrates operation data and historical fault data, constructs a knowledge graph to achieve multi-dimensional correlation analysis, uses unsupervised learning algorithms to mine normal operation modes, can keenly capture abnormal states, and locates abnormal components and the root cause of the fault through a preset health assessment strategy, changing passive maintenance to active prevention, and greatly improving the reliability and stability of the freezer operation; the energy-saving regulation module adjusts the operation state of the freezer flexibly according to personnel activity information by using a preset regulation strategy, reduces energy consumption when not in use, and responds quickly when people approach, effectively balancing the use experience and energy consumption. Through systematic and intelligent design, this system deeply integrates Internet of Things technology into all aspects of freezer management, not only achieving comprehensive perception and intelligent analysis of the freezer operation state, but also significantly improving the equipment maintenance efficiency, reducing the operation cost, and providing an innovative and practical technical solution for the intelligent upgrade of freezers.

[0029] Preferably, the control system further includes: an energy harvesting module, and the energy harvesting module includes a solar panel and a thermoelectric power generation module deployed above the intelligent freezer main body, for converting light energy and temperature difference energy into electrical energy and storing the electrical energy in a lithium battery pack.

[0030] More preferably, the energy harvesting module is also used for distributing the stored electrical energy to low-power modules inside the intelligent freezer main body to maintain the operation of some functions of the freezer when power is off.

[0031] In a preferred embodiment of the present invention, an energy harvesting module is proposed. This module utilizes a solar panel and a thermoelectric power generation module deployed above the main body of the intelligent refrigerator to convert light energy and temperature difference energy into electrical energy, which is then stored in a lithium battery pack. This design embodies an innovative idea of energy utilization, enabling the refrigerator to make full use of renewable energy in the environment and achieve a certain degree of self-power supply. On the one hand, it reduces the dependence on the traditional power grid and lowers the long-term usage cost; on the other hand, it responds to the contemporary demand for energy conservation and environmental protection, contributing to reducing carbon emissions. Meanwhile, the setting of this module enhances the adaptability and stability of the refrigerator in complex environments. Even in the case of unstable power supply or power outage, it can rely on the stored electrical energy to maintain the operation of some functions, providing an additional guarantee for the storage safety of the items in the refrigerator.

[0032] Preferably, the use of unsupervised learning algorithms to mine normal operation modes and identify abnormal operation states includes: based on the results of association analysis, using unsupervised learning algorithms to cluster the operation data of the refrigerator in the normal operation state to mine the normal operation modes of the refrigerator; comparing the real-time operation data with the operation data of the normal operation modes. When the deviation of a certain dimension of data exceeds the first preset threshold, it is identified that the refrigerator is in an abnormal operation state.

[0033] In a preferred embodiment of the present invention, the calculation method of energy income and expenditure in the temperature control system is elaborated in detail, which is the core of the energy balance algorithm. First, multiply the power parameter of the heating device by the operation time to obtain the input energy; then, according to the surface area, heat transfer coefficient, temperature difference inside and outside the platform, and usage time of the food storage platform, calculate the energy dissipated by heat conduction through the heat conduction formula; combined with the heat absorbed by the refrigeration device when working in the food storage space, obtain the output energy; finally, subtract the output energy from the input energy to calculate the energy income and expenditure, providing a key basis for the selection of subsequent control strategies.

[0034] As Figure 2 shown, preferably, the selection of corresponding preset control strategies according to the calculated energy income and expenditure includes: if the energy income and expenditure exceeds the first preset value and the temperature rising rate exceeds the preset rate, select the control strategy of reducing the heating power or starting the refrigeration device; if the energy income and expenditure is lower than the second preset value and the temperature decreasing rate exceeds the preset rate, select to increase the heating; if the energy income and expenditure is within the range of the first preset value and the second preset value, or the temperature change rate is less than the preset rate, select the control strategy of maintaining the current working state of the device.

[0035] In a preferred embodiment of the present invention, a specific method for the maintenance module to utilize unsupervised learning algorithms to mine normal operating modes and identify abnormal operating states is introduced. First, based on the results of association analysis, unsupervised learning algorithms are used to perform clustering processing on the operating data of the freezer under normal operating conditions to find the internal laws and patterns in the data, thereby accurately mining the normal operating mode of the freezer. Subsequently, the real-time operating data is compared with the operating data of the normal operating mode. Once the deviation of a certain dimension of data exceeds the first preset threshold, it is determined that the freezer is in an abnormal operating state. This method has significant advantages. The use of unsupervised learning algorithms can autonomously discover data features and patterns without the need for a large amount of labeled data, reducing the labor cost and the difficulty of data labeling. Through multi-dimensional data comparison and threshold judgment, the abnormal operating state of the freezer can be identified in a timely and accurate manner, realizing real-time monitoring and early warning of the operating state of the freezer, providing strong support for subsequent abnormal handling and maintenance, and greatly improving the safety and reliability of the freezer operation.

[0036] For example, assume that in a large pharmaceutical storage center, during the operation of the intelligent shielding modular freezer system for storing vaccines. The data acquisition module continuously collects operating data such as the temperature of the freezer and the operating frequency of the compressor. Based on the results of association analysis, the maintenance module uses unsupervised learning algorithms to perform clustering processing on the operating data of the freezer when storing vaccines normally on a daily basis, and determines the normal operating mode of the freezer when storing vaccines: the temperature is stably maintained at 2 - 8 °C, the compressor starts once every 30 minutes, and each operation lasts about 5 minutes. One day, the real-time data feedback by the data acquisition module shows that the temperature inside the freezer has continuously risen to 10 °C within 2 hours, far exceeding the first preset threshold (for example, 5 °C / hour) set when comparing with the normal operating mode. The maintenance module immediately identifies that the freezer is in an abnormal operating state. Subsequently, the staff of the storage center intervened in a timely manner and found that the solenoid valve of the refrigeration system was faulty, avoiding the problem of drug failure caused by abnormal vaccine storage temperature, ensuring the safety of pharmaceutical storage, and at the same time reflecting the high-efficiency and accurate identification ability of this technical solution for the abnormal state of the freezer in the actual scenario.

[0037] Such as Figure 3As shown, preferably, an abnormal component is determined through a preset health assessment strategy, including: when the refrigerator is in an abnormal operating state, based on the design parameter data of each component in the refrigerator, the historical operating data of the refrigerator, and the real-time operating data, using a reinforcement learning algorithm to dynamically adjust the basic weights of each data; using the entropy weight method to calculate the objective weights of each data to measure the information entropy size of each data; using grey relational analysis to calculate the correlation degree between the real-time operating data and the operating data of the normal operating mode, and combining the basic weights and the calculated objective weights to construct a comprehensive scoring model; according to the constructed comprehensive scoring model, calculating the health scores of each component in the refrigerator; when the health score of a certain component is lower than the second preset threshold or the change rate exceeds the third threshold, determining that the component is an abnormal component.

[0038] In a preferred embodiment of the present invention, the specific process of determining abnormal components through a preset health assessment strategy when the refrigerator is in an abnormal operating state is elaborated in detail. When the refrigerator is identified as being in an abnormal operating state, first, based on the design parameter data, historical operating data, and real-time operating data of each component in the refrigerator, a reinforcement learning algorithm is used to dynamically adjust the basic weights of each data. Reinforcement learning can enable the system to automatically learn and optimize the importance of each data in the assessment according to the changing operating conditions, making the assessment more in line with the actual situation. Then, the entropy weight method is used to calculate the objective weights of each data to measure the information entropy size of the data, ensuring the objectivity and scientificity of the weight allocation. Then, through grey relational analysis, the correlation degree between the real-time operating data and the operating data of the normal operating mode is calculated, and combining the above basic weights and objective weights, a comprehensive scoring model is constructed. This model integrates the advantages of multi-dimensional data and multiple algorithms and can comprehensively and accurately evaluate the conditions of each component. Finally, according to the comprehensive scoring model, the health scores of each component in the refrigerator are calculated. When the health score of a certain component is lower than the second preset threshold or the change rate exceeds the third threshold, it can be determined that the component is an abnormal component. The advantage of this assessment strategy is that it abandons the limitations of single data or simple assessment methods. Through the cooperation of multiple algorithms, it evaluates the refrigerator components from multiple angles, can more accurately locate the problematic components, provides a clear direction for subsequent repair and maintenance, effectively reduces the repair troubleshooting time, improves the repair efficiency, and ensures the stable operation of the refrigerator.

[0039] For example, during the operation of a low-temperature freezer in a food processing factory, the temperature of the freezer suddenly fluctuates abnormally. At this time, the health assessment strategy starts to operate: First, the reinforcement learning algorithm dynamically adjusts the basic weights of various data according to the design parameter data of components such as the freezer compressor and condenser (such as the rated power of the compressor is 5 kW and the heat exchange area of the condenser is 8 ㎡), historical operation data (the average current of the compressor in the past month is 8 A, and the operation frequency is 6 times per hour), and real-time operation data (the current current of the compressor suddenly rises to 12 A, and the operation frequency reaches 10 times per hour), and increases the data weights of the compressor operation current and operation frequency to 0.3 and 0.25 respectively. Then, the entropy weight method is used to calculate the objective weights of each data, and the objective weight of the compressor operation current is obtained as 0.28, and the objective weight of the operation frequency is 0.22. Then, through grey relational analysis, the correlation degree between the real-time operation data and the operation data of the normal operation mode is calculated, and it is found that the correlation degree of the compressor-related data and the normal mode data is only 0.4 (the normal correlation degree needs to reach more than 0.7). Combining the basic weight and the objective weight, after constructing a comprehensive scoring model, it is calculated that the health score of the compressor is 55 points (for example, the second preset threshold is 70 points), and the score change rate reaches 30% within 1 hour (for example, the third threshold is 20%). Finally, the system determines that the compressor is an abnormal component. After the maintenance personnel arrive at the scene, it is found that the internal bearing of the compressor is worn. After timely replacement, the freezer resumes normal operation, avoiding the loss caused by the deterioration of food due to abnormal temperature, highlighting the accuracy and practicality of the evaluation strategy combined with specific numerical judgments.

[0040] As Figure 4 shown, preferably, the locating of the root cause of the fault includes: when an abnormal component is identified, using the density peak clustering algorithm, dynamically clustering the real-time operation data of the freezer according to the local density and relative distance of the data to generate clustering clusters; according to the distribution and morphological changes of the clustering clusters, combining the typical data clustering characteristics corresponding to different fault types in the historical fault data, extracting the fault characteristics of the current fault; matching the extracted fault characteristics with the indexes in the preset fault mode database, using the inverted index technology to retrieve multiple fault modes with high similarity to the fault characteristics, generating a fault candidate list; based on the generated fault candidate list, using the Bayesian network, combining the real-time operation data and the historical fault data, calculating the posterior probability of each fault cause in the fault candidate list; and locating the root cause of the fault according to the calculated posterior probability.

[0041] In a preferred embodiment of the present invention, the specific technical path for locating the root cause of a fault is elaborated in detail after determining that there is an abnormal component in the refrigerator. When the maintenance module determines the abnormal component according to the above evaluation strategy, first, the density peak clustering algorithm is used to dynamically cluster the real-time operation data of the refrigerator (such as temperature fluctuation curve, compressor current change, fan speed data, etc.). By calculating the local density and relative distance of data points, this algorithm groups similar data points into the same clustering cluster. For example, the relevant data during the stage of abnormal temperature increase is grouped into one cluster, and the abnormal current data of the compressor is grouped into another cluster, thus presenting the complex operation data in a structured manner. Then, according to the distribution characteristics and morphological changes of the clustering clusters, combined with the typical data clustering characteristics corresponding to different fault types in the historical fault data (such as the temperature data clustering shows a stepwise increase when the refrigeration system is blocked, and the dispersion degree of the current data clustering increases when the compressor fails, etc.), the key fault characteristics of the current fault are extracted. For example, if it is found that the temperature clustering cluster shows a continuous and slow upward trend, and the compressor current clustering cluster fluctuates violently, the fault can be initially locked to be related to the refrigeration cycle. Then, the extracted fault characteristics are matched with the indexes in the preset fault mode database, and the inverted index technology is used to quickly retrieve multiple fault modes with high similarity to the fault characteristics, generating a fault candidate list, such as refrigeration pipeline blockage, compressor valve damage, etc. Finally, based on the fault candidate list, using the Bayesian network, combined with the real-time operation data and historical fault data, the posterior probability of each fault cause is calculated. For example, through calculation, the posterior probability of refrigeration pipeline blockage is 75%, the posterior probability of compressor valve damage is 20%, and the probability of other fault causes is 5%. Thus, it is determined that the refrigeration pipeline blockage is the most likely root cause of the fault. The advantage of this method is that through the organic combination of multiple algorithms, it realizes the full-process intelligent analysis from data clustering analysis to fault feature extraction and then to accurate location of the root cause of the fault. Compared with the traditional manual troubleshooting, it not only significantly shortens the fault diagnosis time, but also can significantly improve the accuracy of fault location by virtue of historical data and probability calculation, providing a strong guarantee for the rapid repair and efficient operation of the refrigerator.

[0042] As Figure 5 shown, preferably, the intelligent refrigerator body includes a millimeter-wave radar and a thermal imaging sensor for collecting personnel activity information. The energy-saving regulation module is configured to: obtain and analyze the collected personnel activity information to determine whether there is a person approaching the refrigerator; when there is no person approaching the refrigerator, reduce the illumination brightness of the refrigerator to the basic level and reduce the start-stop frequency of the compressor to reduce energy consumption; when there is no person approaching the refrigerator and the duration exceeds the preset time, control the refrigerator to enter the sleep mode, only maintaining the basic temperature and humidity monitoring function; when there is a person approaching the refrigerator, control the refrigerator to enter the normal mode.

[0043] In a preferred embodiment of the present invention, the millimeter-wave radar and thermal imaging sensor equipped on the intelligent freezer main body continuously collect personnel activity information, and accurately judge whether there is a person approaching the freezer through the collaborative work of the sensors. When the sensors do not detect a person approaching, the energy-saving regulation module immediately reduces the lighting brightness of the freezer to the basic level according to the preset regulation strategy. For example, the lighting brightness of 300 lumens is adjusted to 50 lumens, and at the same time, the start-stop frequency of the compressor is reduced. For example, the start-stop frequency of 6 times per hour is reduced to 2-3 times per hour, thereby effectively reducing the energy consumption of the freezer; if the state of no person approaching the freezer lasts for more than the preset time (such as 2 hours), the freezer will enter the sleep mode. At this time, only the basic temperature and humidity monitoring function is maintained, the compressor stops working, and the lighting system is turned off to minimize energy consumption. Once the sensors detect a person approaching, the energy-saving regulation module responds quickly, controls the freezer to immediately enter the normal mode, the lighting brightness returns to the normal level, and the compressor resumes the normal start-stop frequency to ensure the normal experience of users when using the freezer. This technical solution has significant advantages. Through the real-time perception and intelligent regulation of personnel activities, on the premise of not affecting the normal use function of the freezer, it realizes the refined management and efficient utilization of energy, reduces the operating cost of the freezer, and at the same time extends the service life of the relevant components of the freezer (such as compressors and lighting equipment), taking into account both energy conservation and practical performance.

[0044] Preferably, the intelligent freezer main body further includes an RFID radio frequency identification device for identifying the RFID tags carried by the items in the freezer to obtain the identity information, storage location information, and inbound and outbound time information of the items.

[0045] Further preferably, the maintenance module is also used to send a warning message and fault root cause location information after determining the fault root cause.

[0046] Further preferably, the control system further includes a remote monitoring module. The remote monitoring module is connected to the intelligent freezer main body through the Internet of Things communication technology and is used to monitor the running state of the freezer in real time, including viewing running data, health scores, and receiving the information sent by the maintenance module.

[0047] In a preferred embodiment of the present invention, the functional system of the intelligent shielding modular freezer system is further improved. The RFID radio frequency identification device added to the intelligent freezer main body can quickly and accurately obtain the identity information, storage location information, and inbound and outbound time information of items by reading the RFID tags carried by the items. For example, in the scenario of a medical freezer, it can track the batch number, expiration date, and storage location of each vaccine in real time, realizing the refined management of items. After determining the root cause of the fault, the maintenance module timely issues warning information and the root cause location information of the fault, providing clear repair guidance for maintenance personnel. The remote monitoring module is connected to the intelligent freezer main body by means of Internet of Things communication technology to achieve all-round real-time monitoring of the operating status of the freezer. Managers can not only remotely view the operating data and health scores, but also receive the warning information sent by the maintenance module. At the same time, this module supports remote operations, such as adjusting preset thresholds, control strategies, etc., facilitating managers to flexibly manage the freezer according to actual needs.

[0048] In summary, an intelligent shielding modular freezer system based on the Internet of Things provided by the present invention realizes all-round performance improvement and function optimization through the deep integration of multi-module collaborative innovation and intelligent technology. The data acquisition module uses high-precision sensors to accurately obtain operating data in real time, laying a solid foundation for the intelligent decision-making of the system; the maintenance module uses algorithms such as knowledge graphs and unsupervised learning to achieve early warning, accurate positioning, and efficient processing of faults, turning passive maintenance into active prevention, and greatly improving the reliability and stability of equipment; the energy-saving control module dynamically adjusts the operating state according to personnel activities and item status, effectively reducing energy consumption; the energy harvesting module realizes self-power supply, enhancing the environmental adaptability of the freezer; the RFID radio frequency identification technology helps to achieve refined and intelligent management of items; the remote monitoring and modular design further improve the management convenience and maintenance efficiency. Overall, the system significantly improves the intelligent level and operating efficiency of the freezer, reduces operating costs, ensures the safety of stored items, and strongly promotes the development of cold chain equipment towards high efficiency, intelligence, and greenness.

[0049] It should be understood that in various embodiments of the present invention, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0050] In short, the above are only preferred embodiments of the technical solution of the present invention, and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent shielding modular freezer system based on the Internet of Things, characterized in that, The intelligent shielding modular freezer system includes an intelligent freezer main body and a control system, and the control system includes: A data acquisition module, including sensors deployed inside the intelligent freezer main body, for acquiring the operation data of the intelligent freezer main body; A maintenance module, for constructing a knowledge graph based on the acquired operation data and the historical fault data of the freezer to perform multi-dimensional correlation analysis, and using an unsupervised learning algorithm to mine the normal operation mode, identify abnormal operation states, and is also used when an abnormal operation state is identified, through a preset health assessment strategy, including: When the freezer is in an abnormal operation state, according to the design parameter data of each component in the freezer, the historical operation data and the real-time operation data of the freezer, using a reinforcement learning algorithm to dynamically adjust the basic weights of each data; Using the entropy weight method to calculate the objective weights of each data to measure the information entropy size of each data; Using grey relational degree analysis to calculate the correlation degree between the real-time operation data and the operation data of the normal operation mode, and combining the basic weight and the calculated objective weight to construct a comprehensive scoring model; According to the constructed comprehensive scoring model, calculate the health scores of each component in the freezer; When the health score of a certain component is lower than the second preset threshold or the change rate exceeds the third threshold, determine that the component is an abnormal component; Determine the abnormal component and locate the root cause of the fault, including: When an abnormal component is identified, use the density peak clustering algorithm to dynamically cluster the real-time operation data of the freezer according to the local density and relative distance of the data to generate clustering clusters; According to the distribution and morphological changes of the clustering clusters, combined with the typical data clustering characteristics corresponding to different fault types in the historical fault data, extract the fault characteristics of the current fault; Match the extracted fault characteristics with the indexes in the preset fault mode database, and use the inverted index technology to retrieve multiple fault modes with high similarity to the fault characteristics to generate a fault candidate list; Based on the generated fault candidate list, use a Bayesian network, combined with the real-time operation data and the historical fault data, to calculate the posterior probability of each fault cause in the fault candidate list; Locate the root cause of the fault according to the calculated posterior probability; An energy-saving regulation module, for acquiring personnel activity information, and according to the acquired information, adjusting the operation state of the intelligent freezer main body through a preset regulation strategy.

2. The intelligent shielding modular freezer system according to claim 1, wherein, The control system further includes: An energy collection module, which includes a solar panel and a thermoelectric power generation module deployed above the intelligent freezer main body, for converting light energy and temperature difference energy into electrical energy and storing the electrical energy in a lithium battery pack.

3. The intelligent shielding modular freezer system according to claim 2, characterized in that The energy collection module is also used to distribute the stored electrical energy to the low-power modules inside the intelligent freezer main body when power is off to maintain the operation of some functions of the freezer.

4. The intelligent shielding modular freezer system according to claim 1, wherein The use of an unsupervised learning algorithm to mine the normal operation mode and identify abnormal operation states includes: Based on the results of the correlation analysis, use an unsupervised learning algorithm to cluster the operation data of the freezer in the normal operation state to mine the normal operation mode of the freezer; Compare the real-time operation data with the operation data of the normal operation mode. When the deviation of the data in a certain dimension exceeds the first preset threshold, it is identified that the refrigerator is in an abnormal operation state.

5. The intelligent shielding modular freezer system according to claim 1, wherein, The intelligent refrigerator body includes a millimeter-wave radar and a thermal imaging sensor for collecting personnel activity information. The energy-saving regulation module is configured to: Obtain and analyze the collected personnel activity information to determine whether there is a person approaching the refrigerator; When no one is approaching the refrigerator, reduce the lighting brightness of the refrigerator to the basic level and reduce the start-stop frequency of the compressor to reduce energy consumption; When no one is approaching the refrigerator and the duration exceeds the preset time, control the refrigerator to enter the sleep mode, only maintaining the basic temperature and humidity monitoring function; When there is a person approaching the refrigerator, control the refrigerator to enter the normal mode.

6. The intelligent shielding modular freezer system according to claim 1, wherein, The intelligent refrigerator body further includes an RFID radio frequency identification device for identifying the RFID tags carried by the items in the refrigerator to obtain the identity information, storage location information, and inbound and outbound time information of the items.

7. The intelligent shielding modular freezer system according to claim 1, wherein, The maintenance module is further configured to issue a warning message and fault root cause location information after determining the fault root cause.

8. The intelligent shielding modular freezer system according to claim 7, characterized in that, The control system further includes a remote monitoring module. The remote monitoring module is connected to the intelligent refrigerator body through Internet of Things communication technology for real-time monitoring of the operation state of the refrigerator, including viewing operation data, health scores, and receiving the information sent by the maintenance module.

Images