Safety early warning system and method for electric vehicle charging equipment

Abstract

The invention discloses a safety early warning system and method for electric vehicle charging equipment. The safety early warning system comprises a central control unit, and an early warning unit, a cloud management platform and a plurality of charging state monitoring units which are connected with the central control unit, the charging state monitoring unit comprises a charging parameter monitoring unit, a charging duration statistical unit, a battery temperature monitoring unit and a battery electric quantity monitoring unit; the central control unit is used for judging the current charging state according to the accumulated charging duration monitored by the charging duration statistical unit, the current charging duration, the battery electric quantity increment calculated by the battery electric quantity monitoring unit, the charging pile temperature monitored by the charging parameter monitoring unit and the battery temperature monitored by the battery temperature monitoring unit. The method has the advantages that the charging state can be pre-judged according to the current charging parameters, so that early warning is performed, and the inspection workload and the accident probability can be effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of charging equipment early warning, and in particular to a safety early warning system and method for electric vehicle charging equipment. Background Art

[0002] As charging technology continues to mature, the market share of electric vehicles has increased year by year, and the construction scale of charging stations has also expanded year by year. At present, the operation and maintenance of charging piles mainly rely on manual inspections, which is labor-intensive and cannot be timely and effective. Most existing intelligent monitoring systems monitor the current, voltage, temperature and other parameters of the charging process and combine them with video monitoring to achieve charging parameter monitoring. The problem is that it is impossible to predict the charging status, issue warnings before possible failures or fires, generate warning information, and reduce the inspection workload and the probability of accidents. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a safety warning system and method for electric vehicle charging equipment, which can predict the charging status according to the current charging parameters, thereby giving an early warning, which can effectively reduce the inspection workload and the probability of accidents.

[0004] In order to solve the above technical problems, the present invention provides a safety early warning system for electric vehicle charging equipment, including a central control unit and an early warning unit connected thereto, a cloud management platform and a plurality of charging status monitoring units; the charging status monitoring unit includes a charging parameter monitoring unit, a charging time statistics unit, a battery temperature monitoring unit and a battery power monitoring unit;

[0005] The charging parameter monitoring unit is used to monitor the temperature of the charging pile in real time; the charging time statistics unit is used to calculate the cumulative charging time of the charging pile and the current charging time within the unit period T; the battery power monitoring unit is used to monitor the real-time power of the battery and calculate the battery power increment compared to the initial state at any time within the unit period T; the central control unit is used to determine the current charging state according to the cumulative charging time monitored by the charging time statistics unit, the current charging time and the battery power increment calculated by the battery power monitoring unit, the charging pile temperature monitored by the charging parameter monitoring unit, and the battery temperature monitored by the battery temperature monitoring unit; the method for determining the current charging state is:

[0006] (1) The central control unit obtains the historical charging data of the cloud management platform, and establishes the historical relationship curves of the current charging time and the battery power increment and the battery temperature model, and the historical relationship curves of the cumulative charging time and the charging pile temperature. The k-means algorithm is used to perform cluster analysis on the above three curves, and several cluster curves are obtained for each type of curve. The data center point of each cluster is obtained, and the corresponding threshold is calculated;

[0007] (2) The central control unit obtains the cumulative charging time, the current charging time, the battery power increment, the charging pile temperature, and the battery temperature in real time, determines which clustering curve the current charging state belongs to, and compares the current data with the data center point of the corresponding clustering curve. The comparison results are analyzed and if the threshold of any clustering curve is exceeded, it is judged as a high-risk state and a fault message is sent to the early warning unit.

[0008] Furthermore, the central control unit is also used to set a safety threshold, and the safety threshold is less than the threshold; when the comparison result is that it does not exceed the safety threshold, it is judged to be a normal state; if the comparison result is that it exceeds the safety threshold but does not exceed the threshold, it is judged to be a medium-risk state, and a warning message is sent to the early warning unit.

[0009] Furthermore, the safety thresholds of different clustering curves can be set manually; the safety threshold=K*threshold, K≦1.

[0010] Furthermore, the central control unit is also used to predict the probability P of a charging failure based on the historical charging data of the cloud management platform as a training sample set, with the cumulative charging time, the current charging time, the battery power increment, the charging pile temperature, and the battery temperature as input features; compare the predicted probability P with the preset [P1, P2]; and comprehensively judge the current charging state based on the comparison result of P and the comparison structure of the clustering:

[0011] (1) When P≧P2, or any of the comparison results of the three clustering curves corresponding to the current data is in a high-risk state, the comprehensive judgment is a high-risk state.

[0012] (2) When P≦P1, and the comparison results of the three clustering curves corresponding to the current data are all normal, the comprehensive judgment is normal;

[0013] (3) Except for the above situations, the overall assessment is that the risk level is medium.

[0014] Furthermore, the charging parameter monitoring unit is also used to monitor the voltage and current of this charging in real time; the input characteristics also include voltage and current.

[0015] Furthermore, it also includes an environmental temperature and humidity monitoring unit; the environmental temperature and humidity monitoring unit is used to monitor the temperature and humidity of the environment in real time; the input characteristics also include temperature and humidity.

[0016] Furthermore, if the comprehensive judgment result is a normal state, but a charging failure or fire eventually occurs, the values ​​of P1 and the safety threshold are reduced; if the comprehensive judgment result is a medium-risk state, but a charging failure or fire eventually occurs, the values ​​of P2 and the safety threshold are reduced.

[0017] The present invention also provides an electric vehicle charging equipment safety warning method of an electric vehicle charging equipment safety warning system, comprising the following steps:

[0018] (1) The central control unit obtains the historical charging data of the cloud management platform, and establishes the historical relationship curves of the current charging time and the battery power increment and the battery temperature model, and the historical relationship curves of the cumulative charging time and the charging pile temperature. The k-means algorithm is used to perform cluster analysis on the above three curves, and several cluster curves are obtained for each type of curve. The data center point of each cluster is obtained, and the corresponding threshold is calculated;

[0019] (2) The central control unit obtains the cumulative charging time, the current charging time, the battery power increment, the charging pile temperature, and the battery temperature in real time, determines which clustering curve the current charging state belongs to, and compares the current data with the data center point of the corresponding clustering curve, and analyzes the comparison results: if it exceeds the threshold, it is judged as a high-risk state, and a fault message is sent to the early warning unit; when the comparison result is that it does not exceed the safety threshold, it is judged as a normal state; if the comparison result exceeds the safety threshold but does not exceed the threshold, it is judged as a medium-risk state, and a warning message is sent to the early warning unit; the safety threshold is less than the threshold.

[0020] Furthermore, the safety thresholds of the different clustering curves may be set manually.

[0021] Furthermore, the safety threshold=K*threshold, K≦1.

[0022] Furthermore, the central control unit is also used to predict the probability P of a charging failure based on the historical charging data of the cloud management platform as a training sample set, with the cumulative charging time, the current charging time, the battery power increment, the charging pile temperature, the battery temperature, the voltage and current of this charging, and the temperature and humidity of the environment as input features; compare the predicted probability P with the preset [P1, P2]; and comprehensively judge the current charging state based on the comparison result of P and the comparison structure of the clustering:

[0023] (1) When P≧P2, or any of the comparison results of the three clustering curves corresponding to the current data is in a high-risk state, the comprehensive judgment is a high-risk state.

[0024] (2) When P≦P1, and the comparison results of the three clustering curves corresponding to the current data are all normal, the comprehensive judgment is normal;

[0025] (3) In addition to the above situations, the overall risk is judged to be medium risk;

[0026] (4) If the comprehensive judgment result is a normal state, but a charging failure or fire eventually occurs, the values ​​of P1 and the safety threshold are reduced; if the comprehensive judgment result is a medium-risk state, but a charging failure or fire eventually occurs, the values ​​of P2 and the safety threshold are reduced.

[0027] Beneficial effects of the present invention:

[0028] The present invention uses a large amount of charging data stored in the cloud management platform to establish a historical relationship curve of the current charging time and the battery power increment and the battery temperature model, and a historical relationship curve of the cumulative charging time and the charging pile temperature. The k-means algorithm is used to perform cluster analysis on the above three curves, and the corresponding thresholds are calculated. The central control unit obtains the cumulative charging time, the current charging time, the battery power increment, the charging pile temperature, and the battery temperature in real time, determines which cluster curve the current charging state belongs to, and compares the current data with the data center point of the corresponding cluster curve, analyzes the comparison results, and if it exceeds the threshold of any cluster curve, it is judged as a high-risk state, and the fault information is sent to the early warning unit. The present invention can predict the charging state according to the current charging parameters, thereby giving an early warning, which can effectively reduce the inspection workload and the probability of accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 This is a schematic block diagram of the overall structure of Example 1;

[0030] Figure 2 for Figure 1 Schematic block diagram of the charging state monitoring unit. DETAILED DESCRIPTION

[0031] The specific embodiments of the present invention are further described below in conjunction with the accompanying drawings. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0032] Example 1

[0033] A safety early warning system for electric vehicle charging equipment, such as Figure 1-2 As shown, it includes a central control unit and an early warning unit connected thereto, a cloud management platform and several charging status monitoring units; the charging status monitoring unit includes a charging parameter monitoring unit, a charging time statistics unit, a battery temperature monitoring unit and a battery power monitoring unit;

[0034] The charging parameter monitoring unit is used to monitor the temperature of the charging pile in real time; the charging time statistics unit is used to calculate the cumulative charging time of the charging pile and the current charging time within the unit period T; the battery power monitoring unit is used to monitor the real-time power of the battery and calculate the battery power increment compared to the initial state at any time within the unit period T; the central control unit is used to determine the current charging state according to the cumulative charging time monitored by the charging time statistics unit, the current charging time and the battery power increment calculated by the battery power monitoring unit, the charging pile temperature monitored by the charging parameter monitoring unit, and the battery temperature monitored by the battery temperature monitoring unit; the method for determining the current charging state is:

[0035] (1) The central control unit obtains the historical charging data of the cloud management platform, and establishes the historical relationship curves of the current charging time and the battery power increment and battery temperature model, and the historical relationship curves of the cumulative charging time and the charging pile temperature. The k-means algorithm is used to perform cluster analysis on the above three curves. Each type of curve obtains several cluster curves, obtains the data center point of each cluster, and calculates the corresponding threshold value; the K value in each cluster analysis can be set according to the type of charging pile and the type of electric vehicle.

[0036] (2) The central control unit obtains the cumulative charging time, the current charging time, the battery power increment, the charging pile temperature, and the battery temperature in real time, determines which clustering curve the current charging state belongs to, and compares the current data with the data center point of the corresponding clustering curve. The comparison results are analyzed and if the threshold of any clustering curve is exceeded, it is judged as a high-risk state and a fault message is sent to the early warning unit.

[0037] Furthermore, the central control unit is also used to set a safety threshold, which is less than the threshold; when the comparison result is that the safety threshold is not exceeded, it is judged as a normal state; if the comparison result is that the safety threshold is exceeded but the threshold is not exceeded, it is judged as a medium-risk state, and a warning message is sent to the early warning unit. By setting the safety threshold, charging equipment in a medium-risk state is screened out to remind staff and car owners to pay attention in time.

[0038] Furthermore, the safety thresholds of different clustering curves can be set manually; the safety threshold = K*threshold, K≦1. In this embodiment, the initial value of K is set to 0.85, and can also be adaptively adjusted according to actual conditions.

[0039] Furthermore, the central control unit is also used to predict the probability P of a charging failure based on the historical charging data of the cloud management platform as a training sample set, with the cumulative charging time, the current charging time, the battery power increment, the charging pile temperature, and the battery temperature as input features; compare the predicted probability P with the preset [P1, P2]; and comprehensively judge the current charging state based on the comparison result of P and the comparison structure of the clustering:

[0040] (1) When P≧P2, or any of the comparison results of the three clustering curves corresponding to the current data is in a high-risk state, the comprehensive judgment is a high-risk state.

[0041] (2) When P≦P1, and the comparison results of the three clustering curves corresponding to the current data are all normal, the comprehensive judgment is normal;

[0042] (3) Except for the above situations, the overall assessment is that the risk level is medium.

[0043] Furthermore, the charging parameter monitoring unit is also used to monitor the voltage and current of this charging in real time; the input characteristics also include voltage and current.

[0044] Furthermore, it also includes an environmental temperature and humidity monitoring unit; the environmental temperature and humidity monitoring unit is used to monitor the temperature and humidity of the environment in real time; the input characteristics also include temperature and humidity.

[0045] Furthermore, if the comprehensive judgment result is a normal state, but a charging failure or fire eventually occurs, the values ​​of P1 and the safety threshold are reduced; if the comprehensive judgment result is a medium-risk state, but a charging failure or fire eventually occurs, the values ​​of P2 and the safety threshold are reduced.

[0046] Example 2

[0047] A safety early warning method for electric vehicle charging equipment comprises the following steps:

[0048] (1) The central control unit obtains the historical charging data of the cloud management platform, and establishes the historical relationship curves of the current charging time and the battery power increment and the battery temperature model, and the historical relationship curves of the cumulative charging time and the charging pile temperature. The k-means algorithm is used to perform cluster analysis on the above three curves, and several cluster curves are obtained for each type of curve. The data center point of each cluster is obtained, and the corresponding threshold is calculated;

[0049] (2) The central control unit obtains the cumulative charging time, the current charging time, the battery power increment, the charging pile temperature, and the battery temperature in real time, determines which clustering curve the current charging state belongs to, and compares the current data with the data center point of the corresponding clustering curve, and analyzes the comparison results: if it exceeds the threshold, it is judged as a high-risk state, and a fault message is sent to the early warning unit; when the comparison result is that it does not exceed the safety threshold, it is judged as a normal state; if the comparison result exceeds the safety threshold but does not exceed the threshold, it is judged as a medium-risk state, and a warning message is sent to the early warning unit; the safety threshold is less than the threshold.

[0050] Furthermore, the safety thresholds of the different clustering curves may be set manually.

[0051] Furthermore, the safety threshold=K*threshold, K≦1.

[0052] Furthermore, the central control unit is also used to predict the probability P of a charging failure based on the historical charging data of the cloud management platform as a training sample set, with the cumulative charging time, the current charging time, the battery power increment, the charging pile temperature, the battery temperature, the voltage and current of this charging, and the temperature and humidity of the environment as input features; compare the predicted probability P with the preset [P1, P2]; and comprehensively judge the current charging state based on the comparison result of P and the comparison structure of the clustering:

[0053] (1) When P≧P2, or any of the comparison results of the three clustering curves corresponding to the current data is in a high-risk state, the comprehensive judgment is a high-risk state.

[0054] (2) When P≦P1, and the comparison results of the three clustering curves corresponding to the current data are all normal, the comprehensive judgment is normal;

[0055] (3) In addition to the above situations, the overall risk is judged to be medium risk;

[0056] (4) If the comprehensive judgment result is a normal state, but a charging failure or fire eventually occurs, the values ​​of P1 and the safety threshold are reduced; if the comprehensive judgment result is a medium-risk state, but a charging failure or fire eventually occurs, the values ​​of P2 and the safety threshold are reduced.

[0057] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the described embodiments. For those skilled in the art, various changes, modifications, substitutions and variations of these embodiments are made without departing from the principles and spirit of the present invention, and still fall within the scope of protection of the present invention.

Claims

1. A safety warning system for electric vehicle charging equipment, characterized in that: It includes a central control unit and an early warning unit connected thereto, a cloud management platform and several charging status monitoring units; the charging status monitoring unit includes a charging parameter monitoring unit, a charging time statistics unit, a battery temperature monitoring unit and a battery power monitoring unit; The charging parameter monitoring unit is used to monitor the temperature of the charging pile in real time; the charging time statistics unit is used to calculate the cumulative charging time of the charging pile and the current charging time within the unit period T; the battery power monitoring unit is used to monitor the real-time power of the battery and calculate the battery power increment compared to the initial state at any time within the unit period T; the central control unit is used to determine the current charging state according to the cumulative charging time monitored by the charging time statistics unit, the current charging time and the battery power increment calculated by the battery power monitoring unit, the charging pile temperature monitored by the charging parameter monitoring unit, and the battery temperature monitored by the battery temperature monitoring unit; the method for determining the current charging state is: (1) The central control unit obtains the historical charging data of the cloud management platform, and establishes the historical relationship curves of the current charging time and the battery power increment and the battery temperature model, and the historical relationship curves of the cumulative charging time and the charging pile temperature. The k-means algorithm is used to perform cluster analysis on the above three curves, and several cluster curves are obtained for each type of curve. The data center point of each cluster is obtained, and the corresponding threshold is calculated; (2) The central control unit obtains the cumulative charging time, the current charging time, the battery power increment, the charging pile temperature, and the battery temperature in real time, determines which clustering curve the current charging state belongs to, and compares the current data with the data center point of the corresponding clustering curve. The comparison results are analyzed and if the threshold of any clustering curve is exceeded, it is judged as a high-risk state and a fault message is sent to the early warning unit.

2. The electric vehicle charging equipment safety warning system according to claim 1 is characterized in that: The central control unit is also used to set a safety threshold, which is less than the threshold; when the comparison result is that it does not exceed the safety threshold, it is judged to be a normal state; if the comparison result is that it exceeds the safety threshold but does not exceed the threshold, it is judged to be a medium-risk state and a warning message is sent to the early warning unit.

3. The electric vehicle charging equipment safety warning system according to claim 2 is characterized in that: The safety thresholds of different clustering curves can be set manually; the safety threshold=K*threshold, K≦1.

4. The electric vehicle charging equipment safety warning system according to claim 2 is characterized in that: The central control unit is also used to predict the probability P of a charging failure based on the historical charging data of the cloud management platform as a training sample set, with the cumulative charging time, the current charging time, the battery power increment, the charging pile temperature, and the battery temperature as input features; compare the predicted probability P with the preset [P1, P2]; and comprehensively judge the current charging state based on the comparison result of P and the comparison structure of the cluster: (1) When P≧P2, or any of the comparison results of the three clustering curves corresponding to the current data is in a high-risk state, the comprehensive judgment is a high-risk state. (2) When P≦P1, and the comparison results of the three clustering curves corresponding to the current data are all normal, the comprehensive judgment is normal; (3) Except for the above situations, the overall assessment is that the risk level is medium.

5. The electric vehicle charging equipment safety warning system according to claim 4 is characterized in that: The charging parameter monitoring unit is also used to monitor the voltage and current of this charging in real time; the input characteristics also include voltage and current.

6. The electric vehicle charging equipment safety warning system according to claim 5 is characterized in that: It also includes an environmental temperature and humidity monitoring unit; the environmental temperature and humidity monitoring unit is used to monitor the temperature and humidity of the environment in real time; the input characteristics also include temperature and humidity.

7. The electric vehicle charging equipment safety warning system according to any one of claims 4 to 6, characterized in that: If the comprehensive judgment result is a normal state, but a charging failure or fire eventually occurs, the values ​​of P1 and the safety threshold are reduced; if the comprehensive judgment result is a medium-risk state, but a charging failure or fire eventually occurs, the values ​​of P2 and the safety threshold are reduced.

8. The electric vehicle charging equipment safety warning method applied to the electric vehicle charging equipment safety warning system according to claims 1-7, characterized in that: The steps include: (1) The central control unit obtains the historical charging data of the cloud management platform, and establishes the historical relationship curves of the current charging time and the battery power increment and the battery temperature model, and the historical relationship curves of the cumulative charging time and the charging pile temperature. The k-means algorithm is used to perform cluster analysis on the above three curves, and several cluster curves are obtained for each type of curve. The data center point of each cluster is obtained, and the corresponding threshold is calculated; (2) The central control unit obtains the cumulative charging time, the current charging time, the battery power increment, the charging pile temperature, and the battery temperature in real time, determines which clustering curve the current charging state belongs to, and compares the current data with the data center point of the corresponding clustering curve, and analyzes the comparison results: if it exceeds the threshold, it is judged as a high-risk state and sends fault information to the early warning unit; When the comparison result shows that the safety threshold is not exceeded, it is judged to be in a normal state; If the comparison result exceeds the safety threshold but does not exceed the threshold, it is determined to be a medium-risk state and a warning message is sent to the early warning unit; the safety threshold is less than the threshold.

9. The electric vehicle charging equipment safety early warning method according to claim 8 is characterized in that: The safety thresholds of the different clustering curves can be set manually, and the safety threshold=K*threshold, K≦1.

10. The electric vehicle charging equipment safety early warning method according to claim 8 or 9, characterized in that: The central control unit is also used to predict the probability P of a charging failure based on the historical charging data of the cloud management platform as a training sample set, with the cumulative charging time, the current charging time, the battery power increment, the charging pile temperature, the battery temperature, the voltage and current of this charging, and the temperature and humidity of the environment as input features; compare the predicted probability P with the preset [P1, P2]; and comprehensively judge the current charging state based on the comparison result of P and the comparison structure of the cluster: (1) When P≧P2, or any of the comparison results of the three clustering curves corresponding to the current data is in a high-risk state, the comprehensive judgment is a high-risk state. (2) When P≦P1, and the comparison results of the three clustering curves corresponding to the current data are all normal, the comprehensive judgment is normal; (3) In addition to the above situations, the overall risk is judged to be medium risk; (4) If the comprehensive judgment result is a normal state, but a charging failure or fire eventually occurs, the values ​​of P1 and the safety threshold are reduced; if the comprehensive judgment result is a medium-risk state, but a charging failure or fire eventually occurs, the values ​​of P2 and the safety threshold are reduced.

Images