Monitoring device based on Internet of Things charging equipment

Abstract

The invention relates to the technical field of charging equipment monitoring, in particular to a monitoring device for charging equipment based on the Internet of Things. Comprising the steps that S1, a monitoring device collects and processes local data of charging equipment in real time; s2, the monitoring device performs information interaction between the charging equipment and an external remote monitoring platform through a communication module; according to the invention, the charging data collected in real time is preprocessed, analyzed and stored, the timeliness of real-time monitoring and anomaly detection is ensured, and the charging equipment can quickly process the data locally and make a response, so that the dependence on the cloud is reduced, the delay of data transmission is reduced, the maintenance period is adaptively adjusted, the maintenance cost is reduced, and the maintenance efficiency is improved. According to the method, the service life of the equipment is prolonged, the downtime caused by sudden equipment faults is shortened by predicting faults in advance, the complexity of field maintenance is avoided through remote maintenance and software updating functions, the labor cost and the equipment cost are reduced, and particularly, the method has extremely high operation benefits for charging equipment deployed on a large scale.

Description

Technical Field

[0001] The present invention relates to the technical field of charging equipment monitoring, and in particular to a monitoring device based on an Internet of Things charging equipment. Background Art

[0002] Charging equipment refers to devices used to provide electrical energy to various electronic devices, batteries or electric vehicles. These devices can be simple household appliances or complex industrial systems. By monitoring the charging equipment, the status of the charging equipment can be understood in real time.

[0003] The patent application number is CN202410951733.7, which states in its specification that "the present invention discloses an intelligent safety protection method for a charging pile, comprising the following steps: Step 1: pre-start safety check, and perform an overall check on the charging pile before the first use; Step 2: user identity authentication and authorization, after the charging pile is put into use, when the user needs to use the charging pile, the identity authorization and verification are performed; Step 3: real-time monitoring during charging: during the charging process, the charging pile will continuously monitor the charging status and issue an alarm when an abnormality is found; Step 4: emergency treatment in an emergency situation, when an abnormal situation occurs, the power is cut off, and the charging pile will send an alarm signal to remind users and managers to handle it; Step 5: perform a safety check after the power is turned off, and after the charging is completed, the status of the charging pile itself is checked again to prepare for the next charging; the present invention can better protect the charging pile", although the above technology can monitor the charging equipment in real time, but in the case of poor network conditions, transmission delays will occur during work, which will lead to the inability to detect abnormalities in time and take emergency measures. At the same time, the above technology requires professional personnel and equipment support for remote monitoring and regular maintenance, which increases the operation and maintenance costs.

[0004] In summary, developing a monitoring device based on IoT charging equipment is still a key issue that needs to be urgently solved in the field of charging equipment monitoring technology. Summary of the invention

[0005] In order to solve the problem in the prior art that although the above-mentioned technology can monitor the charging equipment in real time, when the network conditions are poor, transmission delays will occur, which leads to the inability to detect abnormalities in time and take emergency measures. At the same time, the above-mentioned technology requires professional personnel and equipment support for remote monitoring and regular maintenance, which increases the operation and maintenance costs. The present invention provides a monitoring device based on the Internet of Things charging equipment.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The present invention provides a monitoring device based on an Internet of Things charging device, comprising:

[0008] S1. The monitoring device collects and processes the local data of the charging equipment in real time;

[0009] S2. The monitoring device exchanges information between the charging device and the external remote monitoring platform through the communication module;

[0010] S3, based on the big data and AI technology of the prediction module, predicts sudden failures of charging equipment and generates personalized maintenance plans;

[0011] S4. Use the multi-level network security mechanism and blockchain technology of the protection module to protect data;

[0012] S5. The recognition module can intelligently identify abnormal patterns and issue early warning signals;

[0013] S6, linkage adjustment module intelligently links with the external power grid to adjust the working status of the charging equipment in real time;

[0014] S7, multi-modular design, supports users to expand and reduce hardware and software.

[0015] Furthermore, in step S1, the method by which the monitoring device collects and processes the local data of the charging device in real time is:

[0016] The local sensor can process the charging data of the charging equipment collected in real time, including but not limited to voltage, current, and temperature data. The local sensor is installed in the charging equipment in a modular and centralized manner, and the data is pre-processed locally. At the same time, important data is uploaded to the external cloud server for long-term storage and in-depth analysis. A part of the recent historical data will also be retained locally for rapid backtracking. The module runs a set of monitoring algorithms, including but not limited to current and voltage fluctuation detection algorithms and temperature overheating alarm algorithms. The electric power expression formula is: Q(s) = A(s) × L(s), where Q(s) is the electric power at the moment, A(s) is the voltage, and L(s) is the current. The power fluctuation rate expression formula is: The formula for expressing the dynamic rate of temperature change is: When the temperature change rate ΔW exceeds the threshold, it indicates that the device is overheated. The expression formula for the threshold definition is: Where W zd is the maximum safe operating temperature of the equipment or material, W abt is the ambient temperature, w aq is the time allowed for the device temperature to approach safe limits.

[0017] Furthermore, in step S2, the method by which the monitoring device exchanges information between the charging device and the external remote monitoring platform through the communication module is:

[0018] The monitoring device establishes a connection with the external remote monitoring platform through Wi-Fi, 4G or 5G network. The external remote monitoring platform can obtain the working status of the charging equipment in real time and identify potential faults through analysis algorithms. The external remote monitoring platform supports remote fault diagnosis, automatic repair and remote software updates, while monitoring abnormalities or potential faults and notifying maintenance personnel of early warnings.

[0019] Furthermore, in step S2, the method for exchanging information between the charging device and the external remote monitoring platform through the communication module is:

[0020] The formula for large data transmission and anomaly detection is: Where Y is the transmission delay, J is the transmission distance, S is the signal propagation speed, T is the size of the data packet, and K is the bandwidth. The expression formula of the fault diagnosis model based on the Bayesian network is: The expression formula for remote maintenance is used to calculate the probability of failure through equipment monitoring data: Among them, F n is the maintenance cost of the nth device, W n is the time required for remote maintenance, and α is the time cost coefficient.

[0021] Furthermore, in step S3, based on the big data and AI technology of the prediction module, the method for predicting sudden failures of charging equipment and generating a personalized maintenance plan is as follows:

[0022] Based on big data and AI technology, the historical operation data of charging equipment is automatically analyzed, including but not limited to parameters such as usage frequency, power fluctuations, and temperature changes. The health status model of the charging equipment is established through historical operation data, and potential failures of the charging equipment during operation are predicted. A personalized maintenance plan is generated based on the health status of the charging equipment.

[0023] Furthermore, in step S3, based on the big data and AI technology of the prediction module, the method for predicting sudden failures of charging equipment and generating a personalized maintenance plan is as follows:

[0024] The expression formula for establishing the health status model of charging equipment is: S(i) = l1×f[R(i)]+l2×g[ΔQ(i)]+l3×s[ΔM(i)], where S(i) is the health index at time i, and the value range is usually [0,1], 1 indicates the best health status, and 0 indicates the worst. R(i) is the frequency of use of the equipment, which can be defined as the accumulation of equipment working time. ΔQ(i) is the power fluctuation rate, which indicates the rate of change of electric power over time. ΔM(i) is the temperature fluctuation rate, which indicates the rate of change of temperature. l1, l2, and l3 are weighting coefficients used to adjust the impact of different factors on the health status according to actual conditions. f[R(i)], g[ΔQ(i)], and s[ΔM(i)] are nonlinear mapping functions used to standardize various parameters. The change in the health status of the charging equipment can be expressed by the rate of change of the health index: when When the rate of change is large, it indicates that the health status of the equipment has deteriorated sharply, indicating that potential failures are about to occur. The expression formula for calculating the failure probability is: Among them, H f (i) is the failure probability at time i, μ is the characteristic life parameter of the equipment, θ is the shape parameter, which indicates the changing trend of the failure rate over time, S(i) is the health index. The lower the health index, the more likely the equipment is to fail. The expression formula for generating a personalized maintenance plan based on the equipment health status and failure probability is: ttl (i) = B w (i)+B f (i)×H f (i), where B w is the maintenance cost, B f (i) is the failure cost, which is used to form the maintenance scheduling optimization formula through AI algorithm: Where m is the number of devices, S is the time range, and B w (i, s) is the maintenance cost, B f (i, s) is the failure cost, H f (i, t) is the failure probability. The formula to ensure reasonable maintenance arrangement under limited resources is: The expression formula of health status constraint is: S(n, s)≥S min , the optimal maintenance time window, the expression formula for balancing maintenance and failure costs is:

[0025] Further, in step S4, the method of protecting data using the multi-level network security mechanism of the protection module and blockchain technology is as follows:

[0026] The multi-level network security mechanism requires users to verify access rights to charging equipment through multi-factor authentication, including but not limited to fingerprints, passwords, and RFID cards. The user's identity information is locally encrypted and uploaded to the cloud for verification. Charging data and operation logs are recorded through blockchain technology to ensure data security and non-tamperability.

[0027] Further, in step S5, the method in which the recognition module can intelligently recognize the abnormal pattern and issue an early warning signal is:

[0028] The monitoring device collects multi-dimensional data including but not limited to voltage, current, and temperature during the charging process through multiple sensors inside it, extracts key features through feature extraction algorithms, and analyzes equipment operating parameters in real time based on historical data through AI and machine learning technology, automatically identifies abnormal patterns and issues warning signals. The expression formula for abnormal identification is: Where V is the current measurement value, η is the historical mean, and γ is the standard deviation. At the same time, the algorithm can be continuously learned to reduce false alarms and improve the ability to identify real faults. The expression formula for model optimization is: where ε is the classification boundary weight, τ s is the slack variable, F is the penalty coefficient, and the expression formula of the abnormal warning probability model is: Where J(BC) is the probability of anomaly B based on data C.

[0029] Further, in step S6, the linkage adjustment module is intelligently linked with the external power grid to adjust the working state of the charging device in real time in the following method:

[0030] The monitoring device interacts with the power grid through intelligent linkage information, monitors the load of the power grid in real time, obtains the available power and load pressure of the current power grid, adjusts the working state of the charging equipment in real time, and adjusts the charging power and load distribution through the optimization algorithm. The expression formula is: where q s is the power of the sth charging device, D s is its resistance, and the power adjustment expression formula is: When the monitoring device detects that the grid load is close to the threshold, the grid output power q is automatically reduced grid (i).

[0031] Furthermore, in step S7, the multi-modular design supports the user to expand and reduce the hardware and software in the following manner:

[0032] The monitoring device has a modular design, allowing users to add or modify functional modules according to different needs. It supports users to expand hardware and software according to actual needs, and can easily update and upgrade hardware and software. Users only need to install the corresponding modules without replacing the entire charging pile equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a flow chart of a monitoring device based on an Internet of Things charging device of the present invention;

[0034] Figure 2 A plan view of a charging device based on a monitoring device of an Internet of Things charging device according to the present invention;

[0035] Figure 3 It is a plan view of a monitoring device based on an Internet of Things charging device of the present invention;

[0036] Figure 4 This is an internal plan view of a monitoring device of a monitoring apparatus based on an Internet of Things charging device according to the present invention.

[0037] Legend:

[0038] 1. Charging equipment; 2. Monitoring device; 201. Communication module; 202. Prediction module; 203. Protection module; 204. Identification module; 205. Linkage adjustment module. DETAILED DESCRIPTION

[0039] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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 should fall within the scope of protection of the present invention.

[0040] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0041] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0042] Example:

[0043] like Figure 1-Figure 4 As shown, the present invention provides a monitoring device 2 based on an Internet of Things charging device 1, comprising:

[0044] S1. The monitoring device 2 collects and processes the local data of the charging device 1 in real time.

[0045] Furthermore, in step S1, the method by which the monitoring device 2 collects and processes the local data of the charging device 1 in real time is:

[0046] The local sensor 201 can process the charging data of the charging device 1 collected in real time, including but not limited to voltage, current, and temperature data. The local sensor 201 is installed in the charging device 1 in a modular centralized manner, and pre-processes the data locally. At the same time, important data is uploaded to the external cloud server for long-term storage and in-depth analysis. A part of the recent historical data is also retained locally for rapid backtracking. The module runs a set of monitoring algorithms, including but not limited to current and voltage fluctuation detection algorithms and temperature overheating alarm algorithms. The electric power expression formula is: Q(s) = A(s) × L(s), where Q(s) is the electric power at the moment, A(s) is the voltage, L(s) is the current, and the power fluctuation rate expression formula is: The formula for expressing the dynamic rate of temperature change is:

[0047] When the temperature change rate ΔW exceeds the threshold, it indicates that the device is overheated. The expression formula for the threshold definition is: Where W zd is the maximum safe operating temperature of the equipment or material, W abt is the ambient temperature, w aq is the time allowed for the device temperature to approach safe limits.

[0048] In this embodiment, the charging data collected in real time is preprocessed and analyzed before being saved to ensure the timeliness of real-time monitoring and abnormality detection, which is beneficial for the charging device 1 to quickly process data and respond locally to reduce dependence on the cloud and reduce data transmission delays. At the same time, important data is uploaded to the cloud server for long-term storage and in-depth analysis.

[0049] S2. The monitoring device 2 exchanges information between the charging device 1 and the external remote monitoring platform through the communication module 201.

[0050] Further, in step S2, the monitoring device 2 uses the communication module 201 to exchange information between the charging device 1 and the external remote monitoring platform as follows:

[0051] The monitoring device 2 establishes a connection with an external remote monitoring platform via a Wi-Fi, 4G or 5G network. The external remote monitoring platform can obtain the working status of the charging device 1 in real time and identify potential faults through analysis algorithms. The external remote monitoring platform supports remote fault diagnosis, automatic repair and remote software updates, while monitoring abnormalities or potential faults and notifying maintenance personnel of early warnings.

[0052] Furthermore, in step S2, the method for exchanging information between the charging device 1 and the external remote monitoring platform through the communication module 201 is:

[0053] The formula for large data transmission and anomaly detection is: Where Y is the transmission delay, J is the transmission distance, S is the signal propagation speed, T is the size of the data packet, and K is the bandwidth. The expression formula of the fault diagnosis model based on the Bayesian network is: The expression formula for remote maintenance is used to calculate the probability of failure through equipment monitoring data: Among them, F n is the maintenance cost of the nth device, W n is the time required for remote maintenance, and α is the time cost coefficient.

[0054] In this embodiment, the historical data is analyzed by utilizing the large computing power of the external monitoring platform through information interaction, and the analyzed data is fed back to the monitoring device 2, thereby adaptively adjusting the maintenance cycle, reducing maintenance costs, and extending the life of the equipment. By predicting failures in advance, the downtime caused by sudden equipment failures is reduced. Through remote maintenance and software update functions, the complexity of on-site maintenance is avoided, and labor and equipment costs are reduced, which has extremely high operational benefits, especially for charging equipment 1 deployed on a large scale.

[0055] S3. Based on the big data and AI technology of the prediction module 202, predict the sudden failure of the charging device 1 and generate a personalized maintenance plan.

[0056] Furthermore, in step S3, based on big data and AI technology, a method for predicting sudden failures of the charging device 1 and generating a personalized maintenance plan is as follows:

[0057] Based on big data and AI technology, the historical operation data of the charging device 1 is automatically analyzed, including but not limited to parameters such as usage frequency, power fluctuation, and temperature change. A health status model of the charging device 1 is established through the historical operation data, and potential failures of the charging device 1 during operation are predicted. A personalized maintenance plan is generated based on the health status of the charging device 1.

[0058] Furthermore, in step S3, based on the big data and AI technology of the prediction module 202, a method for predicting sudden failures of the charging device 1 and generating a personalized maintenance plan is as follows:

[0059] The expression formula for establishing the health status model of charging device 1 is: S(i)=l1×f[R(i)]+l2×g[ΔQ(i)]+l3×s[ΔM(i)], where S(i) is the health index at time i, and the value range is usually [0,1], 1 indicates the best health status, and 0 indicates the worst. R(i) is the frequency of use of the equipment, which can be defined as the accumulation of equipment working time. ΔQ(i) is the power fluctuation rate, which indicates the rate of change of electric power over time. ΔM(i) is the temperature fluctuation rate, which indicates the rate of change of temperature. l1, l2, and l3 are weighting coefficients used to adjust the impact of different factors on the health status according to actual conditions. f[R(i)], g[ΔQ(i)], and s[ΔM(i)] are nonlinear mapping functions used to standardize various parameters. The change in the health status of charging device 1 can be expressed by the rate of change of the health index: when When the rate of change is large, it indicates that the health status of the equipment has deteriorated sharply, indicating that potential failures are about to occur. The expression formula for calculating the failure probability is: Among them, H f (i) is the failure probability at time i, μ is the characteristic life parameter of the equipment, θ is the shape parameter, which indicates the changing trend of the failure rate over time, S(i) is the health index. The lower the health index, the more likely the equipment is to fail. The expression formula for generating a personalized maintenance plan based on the equipment health status and failure probability is: ttl (i) = B w (i)+B f (i)×H f (i), where B w is the maintenance cost, B f (i) is the failure cost, which is used to form the maintenance scheduling optimization formula through AI algorithm: Where m is the number of devices, S is the time range, and B w (i, s) is the maintenance cost, B f (i, s) is the failure cost, H f (i, t) is the failure probability. The formula to ensure reasonable maintenance arrangement under limited resources is: The expression formula of health status constraint is: S(n, s)≥S min , the optimal maintenance time window, the expression formula for balancing maintenance and failure costs is:

[0060]

[0061] In this embodiment, on the basis of establishing information interaction with the external monitoring platform, based on the big data and AI technology of the external monitoring platform, the historical operation data of the charging device 1 is automatically analyzed, and a health status model of the charging device 1 is established, so as to predict the potential failure of the charging device 1 during operation. At the same time, a personalized maintenance plan is generated according to the health status of the charging device 1, which is conducive to reducing unnecessary maintenance frequency, effectively extending the service life of the equipment, and being able to perform preventive maintenance before a major failure of the equipment occurs, thereby reducing the operational risks and high repair costs caused by equipment failure.

[0062] S4. Use the multi-level network security mechanism and blockchain technology of the protection module 203 to protect the data.

[0063] Further, in step S4, the method of using the multi-level network security mechanism of the protection module 203 and the blockchain technology to protect the data is:

[0064] The multi-level network security mechanism requires users to verify access rights to the charging device 1 through multi-factor authentication, including but not limited to fingerprints, passwords, and RFID cards. The user's identity information is locally encrypted and uploaded to the cloud for verification. The charging data and operation logs are recorded through blockchain technology to ensure data security and non-tamperability.

[0065] In this embodiment, through identity authentication, data encryption and blockchain multi-level security protection technology, the access security of the charging device 1 and the security of data transmission are ensured, malicious attacks, data tampering and information leakage are prevented, and it is convenient for operators and managers to trace the historical operations of the charging device 1 and improve the transparency of the system.

[0066] S5. The recognition module 204 can intelligently recognize abnormal patterns and issue warning signals.

[0067] Furthermore, in step S5, the method of intelligently identifying abnormal patterns and issuing warning signals is:

[0068] The monitoring device 2 collects multi-dimensional data including but not limited to voltage, current, and temperature during the charging process through multiple sensors inside it, extracts key features through feature extraction algorithms, analyzes equipment operating parameters in real time based on historical data through AI and machine learning technology, automatically identifies abnormal modes and issues warning signals. The expression formula for abnormal identification is: Where V is the current measurement value, η is the historical mean, and γ is the standard deviation. At the same time, the algorithm can be continuously learned to reduce false alarms and improve the ability to identify real faults. The expression formula for model optimization is: where ε is the classification boundary weight, τ s is the slack variable, F is the penalty coefficient, and the expression formula of the abnormal warning probability model is: Where J(BC) is the probability of anomaly B based on data C.

[0069] In this embodiment, by collecting multi-dimensional data during the charging process and extracting key data features, and then using AI and machine learning to perform real-time analysis on the charging data, potential abnormalities of the charging device 1 can be effectively detected, the false alarm rate can be reduced, and the accuracy of fault identification can be improved. Before a fault or abnormality occurs, the system can actively issue an early warning to remind maintenance personnel to intervene in time to prevent serious faults from occurring, thereby improving the stability and safety of the system.

[0070] S6. The linkage adjustment module 205 is intelligently linked with the external power grid to adjust the working state of the charging device 1 in real time.

[0071] Further, in step S6, the linkage adjustment module is intelligently linked with the external power grid to adjust the working state of the charging device 1 in real time in the following method:

[0072] The monitoring device 2 interacts with the power grid intelligent linkage information, monitors the load of the power grid in real time, obtains the available power and load pressure of the current power grid, adjusts the working state of the charging device 1 in real time, and adjusts the charging power and load distribution through the optimization algorithm. The expression formula is: where q s is the power of the sth charging device 1, D s is its resistance, and the power adjustment expression formula is: When the monitoring device 2 detects that the grid load is close to the threshold, the grid output power q is automatically reduced. grid (i).

[0073] In this embodiment, the charging power of the charging device 1 is dynamically adjusted according to the real-time information of the available power and load pressure of the current power grid to avoid excessive pressure on the power grid during peak hours, balance the equipment load and power grid resources, and improve the charging efficiency.

[0074] S7, multi-modular design, supports users to expand and reduce hardware and software.

[0075] Furthermore, in step S7, the multi-modular design supports the user to expand and reduce the hardware and software in the following manner:

[0076] The monitoring device 2 has a modular design, allowing users to add or modify functional modules according to different needs, supporting users to expand hardware and software according to actual needs, and can easily update and upgrade hardware and software. Users only need to install the corresponding modules without replacing the entire charging pile equipment.

[0077] In this embodiment, the modular design allows the monitoring device 2 to flexibly adapt to different application scenarios and needs. Users can expand functions according to needs and improve the scalability of the monitoring device 2. At the same time, the modular design makes the upgrade and maintenance of the monitoring device 2 simpler. There is no need to replace the entire system. Only relevant modules need to be replaced or added to complete functional expansion or performance improvement, thereby reducing maintenance costs and complexity.

[0078] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A monitoring device based on an Internet of Things charging device, characterized in that: include: S1. The monitoring device collects and processes the local data of the charging equipment in real time; S2. The monitoring device exchanges information between the charging device and the external remote monitoring platform through the communication module; S3, based on the big data and AI technology of the prediction module, predicts sudden failures of charging equipment and generates personalized maintenance plans; S4. Use the multi-level network security mechanism and blockchain technology of the protection module to protect data; S5. The recognition module can intelligently identify abnormal patterns and issue early warning signals; S6, linkage adjustment module intelligently links with the external power grid to adjust the working status of the charging equipment in real time; S7, multi-modular design, supports users to expand and reduce hardware and software.

2. A monitoring device based on an Internet of Things charging device according to claim 1, characterized in that: In step S1, the method for the monitoring device to collect and process the local data of the charging device in real time is: The local sensor can process the charging data of the charging device collected in real time, including but not limited to voltage, current, and temperature data. The local sensor is installed in the charging device in a modular and centralized manner, and the data is pre-processed locally. At the same time, important data is uploaded to the external cloud server for long-term storage and in-depth analysis. A part of the recent historical data will also be retained locally for rapid backtracking. The module runs a set of monitoring algorithms, including but not limited to current and voltage fluctuation detection algorithms and temperature overheating alarm algorithms. The electric power expression formula is: Q(s) = A(s) × L(s), where Q(s) is the electric power at the moment, A(s) is the voltage, and L(s) is the current. The power fluctuation rate expression formula is: The formula for expressing the dynamic rate of temperature change is: When the temperature change rate ΔW exceeds the threshold, it indicates that the device is overheated. The expression formula for the threshold definition is: Where W zd is the maximum safe operating temperature of the equipment or material, W abt is the ambient temperature, w aq is the time allowed for the device temperature to approach safe limits.

3. A monitoring device based on an Internet of Things charging device according to claim 2, characterized in that: In step S2, the method by which the monitoring device exchanges information between the charging device and the external remote monitoring platform through the communication module is: The monitoring device establishes a connection with the external remote monitoring platform through Wi-Fi, 4G or 5G network. The external remote monitoring platform can obtain the working status of the charging equipment in real time and identify potential faults through analysis algorithms. The external remote monitoring platform supports remote fault diagnosis, automatic repair and remote software updates, while monitoring abnormalities or potential faults and notifying maintenance personnel of early warnings.

4. A monitoring device based on an Internet of Things charging device according to claim 3, characterized in that: In step S2, the method for exchanging information between the charging device and the external remote monitoring platform through the communication module is: The formula for large data transmission and anomaly detection is: Where Y is the transmission delay, J is the transmission distance, S is the signal propagation speed, T is the size of the data packet, and K is the bandwidth. The expression formula of the fault diagnosis model based on the Bayesian network is: The expression formula for remote maintenance is used to calculate the probability of failure through equipment monitoring data: where F n is the maintenance cost of the nth device, W n is the time required for remote maintenance, and α is the time cost coefficient.

5. A monitoring device based on an Internet of Things charging device according to claim 4, characterized in that: In step S3, based on the big data and AI technology of the prediction module, the method for predicting sudden failures of charging equipment and generating a personalized maintenance plan is as follows: Based on big data and AI technology, the historical operation data of charging equipment is automatically analyzed, including but not limited to parameters such as usage frequency, power fluctuations, and temperature changes. The health status model of the charging equipment is established through historical operation data, and potential failures of the charging equipment during operation are predicted. A personalized maintenance plan is generated based on the health status of the charging equipment.

6. A monitoring device based on an Internet of Things charging device according to claim 5, characterized in that: In step S3, based on the big data and AI technology of the prediction module, the method for predicting sudden failures of charging equipment and generating a personalized maintenance plan is as follows: The expression formula for establishing the health status model of charging equipment is: Where S(i) is the health index at time i, and its value range is usually [0,1], where 1 indicates the best health status and 0 indicates the worst health status. R(i) is the frequency of use of the equipment, which can be defined as the cumulative working time of the equipment. ΔQ(i) is the power fluctuation rate, which indicates the rate of change of electric power over time. ΔM(i) is the temperature fluctuation rate, which indicates the rate of change of temperature. is a weighting coefficient used to adjust the impact of different factors on the health status according to the actual situation. f[R(i)], g[ΔQ(i)], s[ΔM(i)] are nonlinear mapping functions used to standardize various parameters. The change in the health status of the charging equipment can be expressed by the change rate of the health index: when When the rate of change is large, it indicates that the health status of the equipment has deteriorated sharply, indicating that potential failures are about to occur. The expression formula for calculating the failure probability is: Among them, H f (i) is the failure probability at time i, μ is the characteristic life parameter of the equipment, θ is the shape parameter, which indicates the changing trend of the failure rate over time, S(i) is the health index. The lower the health index, the more likely the equipment is to fail. The expression formula for generating a personalized maintenance plan based on the equipment health status and failure probability is: ttl (i) = B w (i)+B f (i)×H f (i), where B w is the maintenance cost, B f (i) is the failure cost, which is used to form the maintenance scheduling optimization formula through AI algorithm: Where m is the number of devices, S is the time range, and B w (i, s) is the maintenance cost, B f (i, s) is the failure cost, H f (i, t) is the failure probability. The formula to ensure reasonable maintenance arrangement under limited resources is: The expression formula of health status constraint is: S(n, s)≥S min , the optimal maintenance time window, the expression formula for balancing maintenance and failure costs is:

7. A monitoring device based on an Internet of Things charging device according to claim 6, characterized in that: In step S4, the method of protecting data by using the multi-level network security mechanism of the protection module and blockchain technology is as follows: The multi-level network security mechanism requires users to verify access rights to charging equipment through multi-factor authentication, including but not limited to fingerprints, passwords, and RFID cards. The user's identity information is locally encrypted and uploaded to the cloud for verification. Charging data and operation logs are recorded through blockchain technology to ensure data security and non-tamperability.

8. A monitoring device based on an Internet of Things charging device according to claim 7, characterized in that: In step S5, the method in which the recognition module can intelligently recognize the abnormal pattern and issue an early warning signal is: The monitoring device collects multi-dimensional data including but not limited to voltage, current, and temperature during the charging process through multiple sensors inside it, extracts key features through feature extraction algorithms, and analyzes equipment operating parameters in real time based on historical data through AI and machine learning technology, automatically identifies abnormal patterns and issues warning signals. The expression formula for abnormal identification is: Where V is the current measurement value, η is the historical mean, and γ is the standard deviation. At the same time, the algorithm can be continuously learned to reduce false alarms and improve the ability to identify real faults. The expression formula for model optimization is: where ε is the classification boundary weight, τ s is the slack variable, F is the penalty coefficient, and the expression formula of the abnormal warning probability model is: Where J(BC) is the probability of anomaly B based on data C.

9. A monitoring device based on an Internet of Things charging device according to claim 8, characterized in that: In step S6, the linkage adjustment module is intelligently linked with the external power grid to adjust the working state of the charging device in real time as follows: The monitoring device interacts with the power grid through intelligent linkage information, monitors the load of the power grid in real time, obtains the available power and load pressure of the current power grid, adjusts the working state of the charging equipment in real time, and adjusts the charging power and load distribution through the optimization algorithm. The expression formula is: where q s is the power of the sth charging device, D s is its resistance, and the power adjustment expression formula is: When the monitoring device detects that the grid load is close to the threshold, the grid output power q is automatically reduced grid (i).

10. A monitoring device based on an Internet of Things charging device according to claim 9, characterized in that: In step S7, the multi-modular design supports the user to expand and reduce the hardware and software in the following way: The monitoring device has a modular design, allowing users to add or modify functional modules according to different needs. It supports users to expand hardware and software according to actual needs, and can easily update and upgrade hardware and software. Users only need to install the corresponding modules without replacing the entire charging pile equipment.

Images