Intelligent refrigerator temperature and humidity control system based on real-time monitoring of Internet of Things platform

Through the intelligent refrigerator temperature and humidity control system of the Internet of Things platform, the problem of insufficient real-time and accuracy of the traditional cold storage temperature and humidity monitoring system is solved, and the continuous tracking and high-precision control of the refrigerator status is realized, which reduces downtime and maintenance costs and increases the cost of Food safety and management efficiency.

CN118912804APending Publication Date: 2024-11-08QINGDAO AOHUI LENGYUN IOT TECHNOLOGY CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411232195.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-04
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

Traditional cold storage temperature and humidity monitoring systems are difficult to meet the current high-standard food storage requirements, and are lacking in real time and accuracy, and are labor-intensive and difficult to reduce energy consumption.

Method used

Adopt the intelligent refrigerator temperature and humidity control system based on the Internet of Things platform, including data acquisition unit, temperature and humidity control unit, fault prediction unit and user interaction unit, and real-time monitoring and automation are carried out through temperature sensors, humidity sensors, equipment monitoring sensors and data processing modules. Control, predict potential failures and provide adjustment recommendations.

Benefits of technology

It realizes continuous tracking of refrigerator status and high-precision temperature and humidity control, reduces unplanned downtime and maintenance costs, and improves food safety and management efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118912804A_ABST
    Figure CN118912804A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of Internet of Things, in particular to an intelligent refrigerator temperature and humidity control system based on real-time monitoring of an Internet of Things platform. The system comprises a data acquisition unit used for acquiring and processing data; the temperature and humidity control unit analyzes the data acquired by the data acquisition unit to determine whether the working state of the refrigerator needs to be adjusted or not; the fault prediction unit can predict potential faults of the refrigerator by analyzing the data acquired by the data acquisition unit; the decision support unit is used for giving adjustment and repair suggestions according to the potential faults predicted by the fault prediction unit and is used for reducing unplanned shutdown; the user interaction unit is used for visually displaying and storing information of all the units, and the temperature and humidity range of the refrigerator can be directly set through the user interaction unit. According to the system, by integrating advanced data acquisition, processing, temperature and humidity control, fault prediction and decision support technologies, the stability and reliability of the system are remarkably improved, and the operation cost is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to an intelligent refrigerator temperature and humidity control system based on real-time monitoring of an Internet of Things platform. Background Art

[0002] In modern cold chain logistics, the temperature and humidity control of cold storage is crucial to ensure the quality and safety of sensitive items such as food and medicine. Traditional cold storage temperature and humidity monitoring systems mostly rely on manual detection and timed recording, which is not only labor-intensive, but also difficult to meet the current high standards of food storage in terms of real-time and accuracy. With the development of science and technology, intelligence has become an important development trend in many fields. The intelligent upgrade of cold storage temperature and humidity monitoring systems has become the key to improving management efficiency, ensuring food safety and reducing energy consumption.

[0003] An intelligent refrigerator temperature and humidity control system based on real-time monitoring on the Internet of Things platform has real-time monitoring capabilities, so that the status of the refrigerator can be continuously tracked. In addition, the system can maintain a constant temperature and humidity environment and predict potential equipment failures, significantly improving the accuracy and automation level of temperature and humidity control. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent refrigerator temperature and humidity control system based on real-time monitoring of the Internet of Things platform to solve the problem that the traditional cold storage temperature and humidity monitoring system proposed in the above background technology is difficult to meet the current high-standard food storage requirements.

[0005] To achieve the above object, the present invention aims to provide an intelligent refrigerator temperature and humidity control system based on real-time monitoring of the Internet of Things platform, comprising:

[0006] A data acquisition unit, including a temperature sensor, a humidity sensor, an equipment monitoring sensor, a data processing module and a wireless communication module;

[0007] A temperature and humidity control unit, which analyzes the temperature and humidity data collected by the data collection unit to determine whether the working state of the refrigerator needs to be adjusted;

[0008] The temperature and humidity control unit includes a temperature and humidity control module and an alarm module;

[0009] A fault prediction unit, based on analyzing the temperature data, humidity data and equipment monitoring data collected by the data collection unit, uses a fault prediction model to predict potential faults of the refrigerator;

[0010] The decision support unit gives adjustment and repair suggestions based on the potential faults predicted by the fault prediction unit to reduce unplanned downtime;

[0011] The user interaction unit includes a temperature and humidity setting module, a visual interface module, a wireless communication module 2 and a storage module.

[0012] As a further improvement of the technical solution, the temperature sensor is used to collect temperature data of the refrigerator, and the humidity sensor is used to collect humidity data of the refrigerator;

[0013] Among them, the equipment monitoring sensor includes at least a relay status sensor, a current sensor, a fan speed sensor, a magnetic induction switch sensor and a current and voltage sensor. The appliance status sensor and the current sensor are used to monitor the working status of the heater and the cooler respectively, the fan speed sensor is used to monitor the working status of the fan, the magnetic induction switch sensor is used to monitor the switch status of the refrigerator door, and the current and voltage sensor is used to monitor energy consumption information.

[0014] As a further improvement of the present technical solution, the data processing module is used to remove and fill in abnormal values ​​and missing values ​​in the data collected by the temperature sensor, humidity sensor and equipment monitoring sensor, and normalize the data. The processed data is sent to the temperature and humidity control unit, the fault prediction unit and the user interaction unit through the wireless communication module.

[0015] As a further improvement of the technical solution, the data processing module includes an outlier processing module, a missing value processing module and a normalization module, and the outlier processing module is specifically:

[0016]

[0017] Among them, X represents the original data point; μ represents the sample mean; σ represents the sample standard deviation;

[0018] The missing value processing module is as follows:

[0019]

[0020] Among them, x filled Represents the data point after filling; x i represents the data point of the i-th neighbor; k represents the number of nearest neighbors;

[0021] Wherein, the normalization module is specifically as follows:

[0022]

[0023] Among them, x ′ represents the normalized data point; x represents the original data point, min(x) and max(x) are the minimum and maximum values ​​in the data set, respectively.

[0024] As a further improvement of the technical solution, the working steps of the temperature and humidity control unit are:

[0025] S2.1, receiving the temperature and humidity data processed by the data acquisition unit;

[0026] S2.2, if the temperature and humidity are not within the set range, the temperature and humidity control module calculates the control signal that needs to be adjusted, and sends the control signal to the control actuator of the refrigerator to adjust the working state;

[0027] S2.3, continuously monitor whether the temperature and humidity return to the set range, if the temperature and humidity do not return to the set range, the alarm module is triggered;

[0028] S2.4. The alarm module sends the alarm information to the administrator's mobile phone through the wireless communication module 2.

[0029] As a further improvement of the technical solution, the temperature and humidity control module in S2.2 is specifically:

[0030]

[0031] Among them, u PID (t) represents the control output, which is used to adjust the working state of the refrigerator; e(t) represents the error, that is, the difference between the target value (set point) and the actual measured value (process variable); K p Represents the proportionality coefficient; K i Represents the integral coefficient; K d represents the differential coefficient;

[0032] Among them, the temperature and humidity control module is introduced into the model predictive control to improve the robustness and response speed. The formula after introduction is:

[0033]

[0034] Among them, u represents the control sequence, that is, the future control signal; r k represents the reference value at future time k, that is, the set value of temperature and humidity; y(k|t) represents the predicted output at future time k based on the prediction model; λ represents the regularization coefficient, which is used to balance the change amplitude of the control sequence; u(k|t) represents the control signal for the moment.

[0035] As a further improvement of the technical solution, the fault prediction model is specifically:

[0036]

[0037] st

[0038] Among them, w represents the weight vector, which determines the direction of the hyperplane; b represents the bias term, which determines the position of the hyperplane; ξ i represents the slack variable, allowing some sample points to deviate from the hyperplane; C represents the penalty parameter, which is used to balance the trade-off between classification error and model complexity; x i Represents the feature vector of the i-th sample; y i represents the class label of the i-th sample; n represents the number of samples in the training data set.

[0039] As a further improvement of this technical solution, the working steps of the decision support unit are:

[0040] S4.1. Build a solution library, which contains known failure modes and corresponding solutions;

[0041] S4.2, receiving potential fault prediction information from the fault prediction unit;

[0042] S4.3, using a cosine similarity algorithm, matching the potential faults predicted by the fault prediction unit with the known faults included in the solution library;

[0043] S4.4. Provide solutions based on the matched failure mode.

[0044] As a further improvement of the technical solution, the cosine similarity algorithm in S4.3 is specifically as follows:

[0045]

[0046] Among them, cos(θ) represents the cosine similarity between two vectors; n represents the dimension of the feature vector, that is, the number of features; represents the i-th eigenvalue in the predicted fault feature vector; y fault,i represent.

[0047] As a further improvement of the present technical solution, the temperature and humidity setting module is used to set the temperature and humidity range of the refrigerator, the visual interface module is used to intuitively display the information collected by the data acquisition unit, the alarm information of the temperature and humidity control unit, the prediction information of the fault prediction unit and the solution information of the decision support unit, and the storage module is used to store the information collected by the data acquisition unit, the alarm information of the temperature and humidity control unit, the prediction information of the fault prediction unit and the solution information of the decision support unit.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] 1. Through the real-time monitoring capability of the sensor and the data analysis of the data processing unit, the continuous tracking of the refrigerator status and the accuracy of the data are ensured, providing a solid data foundation for the stable operation of the refrigerator; the intelligent control unit can automatically adjust the working status of the refrigerator according to real-time data, achieve high-precision environmental control, and ensure the stability of storage conditions and the safety of items.

[0050] 2. The introduction of the fault prediction model enables the system to predict potential equipment failures, thereby taking preventive measures to reduce unplanned downtime and maintenance costs, which has a significant effect on reducing operational risks and improving the overall efficiency of the system; the decision support unit can quickly match the corresponding solution from the solution library based on the results of fault prediction, and provide maintenance personnel with specific adjustment and repair suggestions, effectively reducing the time for fault handling; this patent realizes the intelligent and automated temperature and humidity control of refrigerators through the integrated application of Internet of Things technology, which has a significant effect on improving storage safety, reducing maintenance costs, and optimizing management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is one of the overall flow charts of the present invention;

[0052] Figure 2 This is the second overall flow chart of the present invention.

[0053] The meaning of each number in the figure is:

[0054] 1. Data acquisition unit; 11. Temperature sensor; 12. Humidity sensor; 13. Data processing module; 14. Wireless communication module 1; 15. Equipment monitoring sensor; 2. Temperature and humidity control unit; 21. Temperature and humidity control module; 22. Alarm module; 3. Fault prediction unit; 4. Decision support unit; 5. User interaction unit; 51. Temperature and humidity setting module; 52. Visual interface module; 53. Wireless communication module 2; 54. Storage module. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] Example

[0057] See also Figure 1As shown, a smart refrigerator temperature and humidity control system based on real-time monitoring of an Internet of Things platform is provided, including a data acquisition unit 1, including a temperature sensor 11, a humidity sensor 12, an equipment monitoring sensor 15, a data processing module 13 and a wireless communication module 14.

[0058] The temperature sensor 11 is used to collect the temperature data of the refrigerator, and the humidity sensor 12 is used to collect the humidity data of the refrigerator;

[0059] Among them, the equipment monitoring sensor 15 includes at least a relay status sensor, a current sensor, a fan speed sensor, a magnetic induction switch sensor and a current and voltage sensor. The appliance status sensor and the current sensor are used to monitor the working status of the heater and the cooler respectively, the fan speed sensor is used to monitor the working status of the fan, the magnetic induction switch sensor is used to monitor the switch status of the refrigerator door, and the current and voltage sensor is used to monitor energy consumption information.

[0060] The data processing module 13 is used to remove and fill in abnormal values ​​and missing values ​​in the data collected by the temperature sensor 11, humidity sensor 12 and equipment monitoring sensor 15, and normalize the data. The processed data is sent to the temperature and humidity control unit 2, fault prediction unit 3 and user interaction unit 5 through the wireless communication module 14.

[0061] The data processing module 13 includes an outlier processing module, a missing value processing module and a normalization module. The outlier processing module is specifically:

[0062]

[0063] Where X represents the original data point; μ represents the sample mean; σ represents the sample standard deviation; for each data point, (if its Z is greater than a certain threshold, such as 3), the data point is considered to be an outlier and is removed;

[0064] Among them, the missing value processing module is as follows:

[0065]

[0066] Among them, x filled Represents the data point after filling; x i represents the data point of the i-th neighbor; k represents the number of nearest neighbors; this formula calculates the average of the k nearest neighbor data points as the estimated value of the missing value, and fills the missing value by finding the k neighbors that are most similar to the row where the missing value is located and calculating their average value;

[0067] Among them, the normalization module is as follows:

[0068]

[0069] Among them, x ′ represents the normalized data point; x represents the original data point, min(x) and max(x) are the minimum and maximum values ​​in the data set respectively; through this formula, all data points will be mapped between 0 and 1.

[0070] The temperature and humidity control unit 2 analyzes the temperature and humidity data collected by the data collection unit 1 to determine whether the working state of the refrigerator needs to be adjusted.

[0071] The temperature and humidity control unit 2 includes a temperature and humidity control module 21 and an alarm module 22 .

[0072] The working steps of the temperature and humidity control unit 2 are:

[0073] S2.1, receiving the temperature and humidity data processed by the data acquisition unit 1;

[0074] S2.2, if the temperature and humidity are not within the set range, the temperature and humidity control module 21 calculates the control signal that needs to be adjusted, and sends the control signal to the control actuator (such as a heater or a cooler) of the refrigerator to adjust the working state;

[0075] S2.3, continuously monitor whether the temperature and humidity return to the set range, if the temperature and humidity do not return to the set range, trigger the alarm module 22;

[0076] S2.4. The alarm module 22 sends the alarm information to the administrator's mobile phone via the wireless communication module 2 53.

[0077] The temperature and humidity control module 21 in S2.2 is specifically:

[0078]

[0079] Among them, u PID (t) represents the control output, which is used to adjust the working state of the refrigerator; e(t) represents the error, that is, the difference between the target value (set point) and the actual measured value (process variable); K p Represents the proportional coefficient, which determines the control output u PID The size of the proportional term in (t) directly affects the rapid response capability of the control; K i Represents the integral coefficient, which determines the control output u PID The size of the integral term in (t) is used to eliminate steady-state errors and improve control accuracy; K d Represents the differential coefficient, which determines the control output u PID The size of the differential term in (t) is used to predict the changing trend of the process variables and improve the dynamic performance of the control; this formula can ensure that the temperature and humidity in the refrigerator are stable within the required range by continuously adjusting the control signal;

[0080] Among them, the temperature and humidity control module 21 is introduced into the model predictive control (MPC) to improve the robustness and response speed. The formula after introduction is:

[0081]

[0082] Among them, u represents the control sequence, that is, the future control signal; r k represents the reference value at future time k, that is, the set value of temperature and humidity; y(k|t) represents the predicted output at future time k based on the prediction model; λ represents the regularization coefficient, which is used to balance the change amplitude of the control sequence; u(k|t) represents the control signal for the moment; the prediction model of y(k|t) can be expressed as y(k|t)=f(u(k|t),t), y(k|t) is the predicted output at future time k, u(k|t) is the control signal at future time k, and f is the functional form of the prediction model, which can be a linear regression model, a neural network, or other types of prediction models.

[0083] The fault prediction unit 3 uses a fault prediction model to predict potential faults of the refrigerator based on analyzing the temperature data, humidity data and equipment monitoring data collected by the data collection unit 1.

[0084] The specific fault prediction model is:

[0085]

[0086] st

[0087] Among them, w represents the weight vector, which determines the direction of the hyperplane; b represents the bias term, which determines the position of the hyperplane; ξ i represents the slack variable, allowing some sample points to deviate from the hyperplane; C represents the penalty parameter, which is used to balance the trade-off between classification error and model complexity; x i represents the feature vector of the i-th sample; y i represents the class label of the i-th sample; n represents the number of samples in the training data set; this formula can predict whether a new data point has a potential fault.

[0088] The decision support unit 4 gives adjustment and repair suggestions based on the potential faults predicted by the fault prediction unit 3 to reduce unplanned downtime.

[0089] The working steps of decision support unit 4 are:

[0090] S4.1. Build a solution library, which contains known failure modes and corresponding solutions;

[0091] S4.2, receiving potential fault prediction information from the fault prediction unit 3;

[0092] S4.3, using the cosine similarity algorithm, matching the potential faults predicted by the fault prediction unit 3 with the known faults included in the solution library;

[0093] S4.4. Provide one or more solutions based on the matched failure mode.

[0094] The cosine similarity algorithm in S4.3 is as follows:

[0095]

[0096] Among them, cos(θ) represents the cosine similarity between two vectors; n represents the dimension of the feature vector, that is, the number of features; represents the i-th eigenvalue in the predicted fault feature vector; y fault,i Represents; This formula is used to calculate the predicted fault feature vector and the known fault feature vector y in the solution library fault The similarity between them is between -1 and 1. The closer the value is to 1, the more similar the two vectors are. The closer the value is to -1, the less similar the two vectors are. 0 means that the two vectors are completely unrelated.

[0097] The user interaction unit 5 includes a temperature and humidity setting module 51 , a visual interface module 52 , a wireless communication module 2 53 and a storage module 54 .

[0098] The temperature and humidity setting module 51 is used to set the temperature and humidity range of the refrigerator, the visual interface module 52 is used to intuitively display the information collected by the data acquisition unit 1, the alarm information of the temperature and humidity control unit 2, the prediction information of the fault prediction unit 3 and the solution information of the decision support unit 4, and the storage module 53 is used to store the information collected by the data acquisition unit 1, the alarm information of the temperature and humidity control unit 2, the prediction information of the fault prediction unit 3 and the solution information of the decision support unit 4.

[0099] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. An intelligent refrigerator temperature and humidity control system based on real-time monitoring of the Internet of Things platform, Features: include: A data acquisition unit (1) comprising a temperature sensor (11), a humidity sensor (12), an equipment monitoring sensor (15), a data processing module (13) and a wireless communication module (14); A temperature and humidity control unit (2) is configured to analyze the temperature and humidity data collected by the data collection unit (1) to determine whether the working state of the refrigerator needs to be adjusted; The temperature and humidity control unit (2) comprises a temperature and humidity control module (21) and an alarm module (22); A fault prediction unit (3) is configured to predict potential faults of the refrigerator by using a fault prediction model based on analyzing the temperature data, humidity data and equipment monitoring data collected by the data collection unit (1); A decision support unit (4) provides adjustment and repair suggestions based on the potential faults predicted by the fault prediction unit (3) to reduce unplanned downtime; The user interaction unit (5) comprises a temperature and humidity setting module (51), a visual interface module (52), a wireless communication module 2 (53) and a storage module (54).

2. According to claim 1, a smart refrigerator temperature and humidity control system based on real-time monitoring of the Internet of Things platform, Features: The temperature sensor (11) is used to collect temperature data of the refrigerator, and the humidity sensor (12) is used to collect humidity data of the refrigerator; The equipment monitoring sensor (15) at least comprises a relay status sensor, a current sensor, a fan speed sensor, a magnetic induction switch sensor and a current and voltage sensor. The electrical status sensor and the current sensor are used to monitor the working status of the heater and the cooler respectively. The fan speed sensor is used to monitor the working status of the fan. The magnetic induction switch sensor is used to monitor the switch status of the refrigerator door. The current and voltage sensor is used to monitor energy consumption information.

3. According to claim 1, a smart refrigerator temperature and humidity control system based on real-time monitoring of the Internet of Things platform, Features: The data processing module (13) is used to remove and fill in abnormal values ​​and missing values ​​in the data collected by the temperature sensor (11), the humidity sensor (12) and the equipment monitoring sensor (15), and to normalize the data. The processed data is sent to the temperature and humidity control unit (2), the fault prediction unit (3) and the user interaction unit (5) through the wireless communication module 1 (14).

4. According to claim 3, a smart refrigerator temperature and humidity control system based on real-time monitoring of the Internet of Things platform, Features: The data processing module (13) includes an outlier processing module, a missing value processing module and a normalization module. The outlier processing module is specifically: Among them, X represents the original data point; μ represents the sample mean; σ represents the sample standard deviation; The missing value processing module is as follows: Among them, x filled Represents the data point after filling; x i represents the data point of the i-th neighbor; k represents the number of nearest neighbors; Wherein, the normalization module is specifically as follows: Among them, x ′ represents the normalized data point; x represents the original data point, min(x) and max(x) are the minimum and maximum values ​​in the data set, respectively.

5. According to claim 1, a smart refrigerator temperature and humidity control system based on real-time monitoring of the Internet of Things platform, Features: The working steps of the temperature and humidity control unit (2) are: S2.1, receiving the temperature and humidity data processed by the data acquisition unit (1); S2.2, if the temperature and humidity are not within the set range, the temperature and humidity control module (21) calculates the control signal that needs to be adjusted, and sends the control signal to the control actuator of the refrigerator to adjust the working state; S2.3, continuously monitoring whether the temperature and humidity return to the set range, if the temperature and humidity do not return to the set range, triggering the alarm module (22); S2.

4. The alarm module (22) sends the alarm information to the administrator's mobile phone via the wireless communication module 2 (53).

6. According to claim 5, a smart refrigerator temperature and humidity control system based on real-time monitoring of the Internet of Things platform, Features: The temperature and humidity control module (21) in S2.2 is specifically: Among them, u PID (t) represents the control output, which is used to adjust the working state of the refrigerator; e(t) represents the error, that is, the difference between the target value (set point) and the actual measured value (process variable); K p Represents the proportionality coefficient; K i Represents the integral coefficient; K d represents the differential coefficient; The temperature and humidity control module (21) is introduced into the model predictive control to improve robustness and response speed. The formula after introduction is: Among them, u represents the control sequence, that is, the future control signal; r k represents the reference value at future time k, that is, the set value of temperature and humidity; y(k|t) represents the predicted output at future time k based on the prediction model; λ represents the regularization coefficient, which is used to balance the change amplitude of the control sequence; u(k|t) represents the control signal for the moment.

7. According to claim 1, a smart refrigerator temperature and humidity control system based on real-time monitoring of the Internet of Things platform, Features: The fault prediction model is specifically: Among them, w represents the weight vector, which determines the direction of the hyperplane; b represents the bias term, which determines the position of the hyperplane; ξ i represents the slack variable, allowing some sample points to deviate from the hyperplane; C represents the penalty parameter, which is used to balance the trade-off between classification error and model complexity; x i represents the feature vector of the i-th sample; y i represents the class label of the i-th sample; n represents the number of samples in the training data set.

8. According to claim 1, a smart refrigerator temperature and humidity control system based on real-time monitoring of the Internet of Things platform, Features: The working steps of the decision support unit (4) are: S4.

1. Build a solution library, which contains known failure modes and corresponding solutions; S4.2, receiving potential fault prediction information from the fault prediction unit (3); S4.3, using a cosine similarity algorithm, matching the potential faults predicted by the fault prediction unit (3) with the known faults included in the solution library; S4.

4. Provide solutions based on the matched failure mode.

9. According to claim 8, a smart refrigerator temperature and humidity control system based on real-time monitoring of the Internet of Things platform, Features: The cosine similarity algorithm in S4.3 is as follows: Among them, cos(θ) represents the cosine similarity between two vectors; n represents the dimension of the feature vector, that is, the number of features; represents the i-th eigenvalue in the predicted fault feature vector; y fault,i represent.

10. According to claim 1, a smart refrigerator temperature and humidity control system based on real-time monitoring of the Internet of Things platform, Features: The temperature and humidity setting module (51) is used to set the temperature and humidity range of the refrigerator; the visual interface module (52) is used to intuitively display the information collected by the data acquisition unit (1), the alarm information of the temperature and humidity control unit (2), the prediction information of the fault prediction unit (3) and the solution information of the decision support unit (4); and the storage module (53) is used to store the information collected by the data acquisition unit (1), the alarm information of the temperature and humidity control unit (2), the prediction information of the fault prediction unit (3) and the solution information of the decision support unit (4).

Citation Information

Cited By

  • Energy-saving refrigerator management system based on block chain and energy-saving refrigerator

    CN119988972A