Lane equipment monitoring, operation and maintenance control system based on modular intelligent cloud box

Abstract

The present invention relates to the field of lane equipment monitoring technology, and specifically discloses a lane equipment monitoring, operation, and maintenance control system based on a modular intelligent cloud box. The system includes: an operation data acquisition terminal for obtaining operation data of lane equipment, wherein the operation data includes input data and process data of the lane equipment; a modular intelligent cloud box for performing AI simulation on the input data through an AI model to obtain reference process data; a power data acquisition terminal for obtaining power data of the lane equipment; a life management module for managing the lane equipment based on historical operation data and obtaining life data of the lane equipment; and a monitoring, operation, and maintenance control module for performing risk monitoring of the lane equipment based on the comparison results of the lane equipment process data with the reference process data, power data, and life data. The present invention can make timely judgments in the abnormal state stage before a lane equipment failure occurs, thereby improving the sensitivity of the judgment results.

Description

Technical Field

[0001] The present invention relates to the field of lane equipment monitoring technology, and specifically to a lane equipment monitoring, operation and maintenance control system based on a modular intelligent cloud box. Background Art

[0002] The stable operation of lane equipment is the core foundation for ensuring an efficient, safe and orderly transportation system. Among them, lane controllers, ETC-specific RSUs, high-definition license plate recognition devices, etc. are core equipment. Their failure or failure may cause multi-dimensional chain reactions such as reduced traffic efficiency and increased economic losses. At the same time, since many lane equipment are installed outdoors, their operating status needs to be monitored to ensure their safe and stable operation. With the development of the Internet of Things, edge computing, and cloud computing technologies, modular intelligent cloud boxes are used to obtain the operating data of lane equipment for analysis, thereby enabling more timely and accurate monitoring of the operating status of lane equipment.

[0003] The existing lane equipment monitoring and operation control system mainly compares the operating data and power data of the lane equipment with the corresponding benchmark data to judge its operating status. For example, by comparing the recognition efficiency of the high-definition license plate recognition device with the average recognition efficiency, when the actual recognition efficiency is much lower than the average efficiency, it indicates that there is an abnormality in the equipment. In this way, the abnormality in the lane equipment can be judged and the faulty equipment can be discovered in time for repair and replacement.

[0004] In actual operation, lane equipment failures are cumulative, so early abnormality judgment of lane equipment is of great significance for early maintenance and replacement of equipment. However, in the judgment process of the existing monitoring system, if the corresponding benchmark data is set too high, the judgment sensitivity is insufficient and the abnormal problems of lane equipment cannot be judged in time. If the corresponding benchmark data is set too low, it will cause misjudgment. Therefore, how to improve the sensitivity of judging abnormal problems of lane equipment is the fundamental problem to be solved by the present invention. Summary of the Invention

[0005] The purpose of this invention is to provide a lane equipment monitoring, operation and maintenance control system based on a modular intelligent cloud box to solve the following technical problems:

[0006] How to improve the sensitivity of judging abnormal problems of lane equipment.

[0007] The purpose of the invention can be achieved through the following technical solutions:

[0008] Lane equipment monitoring, operation and maintenance control system based on modular intelligent cloud box, the system includes:

[0009] An operation data acquisition terminal is used to obtain operation data of lane equipment, wherein the operation data includes input data and process data of lane equipment;

[0010] A modular smart cloud box for performing AI simulation on input data through AI models to obtain reference process data;

[0011] Power data collection terminal, used to obtain power data of lane equipment;

[0012] Life management module, used to manage lane equipment based on historical operation data and obtain lane equipment life data;

[0013] The monitoring and operation control module is used to monitor the risks of lane equipment based on the comparison results of lane equipment process data and reference process data, power data and life data.

[0014] Furthermore, the process of risk monitoring of lane equipment includes:

[0015] Obtaining a performance coefficient of the lane equipment based on a comparison result of the lane equipment process data and the reference process data;

[0016] Obtain the power risk factor of lane equipment based on power data;

[0017] Obtain the life coefficient of lane equipment based on life data;

[0018] The risk coefficient of the lane equipment is obtained based on the performance coefficient, power risk coefficient and life coefficient, and risk monitoring is performed based on the size of the lane equipment risk coefficient.

[0019] Furthermore, the process of obtaining the performance coefficient includes:

[0020] Get the time before the current point Lane equipment process data under time period;

[0021] By formula Calculate and obtain the performance coefficient of lane equipment;

[0022] Where f(x) is the definition function. When x≥0, f(x)=x, when x<0, f(x)=0, n is the response item of the lane equipment, i∈[1,n], is the mean response time of the i-th response item of the process data, is the mean response time of the i-th response item of the reference process data, is the weight coefficient of the i-th response item.

[0023] Furthermore, the process of establishing the AI ​​model includes:

[0024] Obtain test data corresponding to different input data of lane equipment of the same specifications in a stable operating state in the empirical data;

[0025] Use the preset input data and corresponding test data as samples for machine learning training to obtain an AI model.

[0026] Furthermore, the process of obtaining the power risk coefficient includes:

[0027] Get the current time based on the power data The real-time current and temperature of the key monitoring points of the lane equipment in each time period are simulated based on the input data to obtain the real-time reference current of the lane equipment. The real-time reference current is divided into states to obtain the working state period and the non-working state period;

[0028] The difference threshold between the real-time current and the reference current is judged in the working state period and the non-working state period respectively: when the maximum difference exceeds the corresponding threshold, it is judged that the lane equipment is abnormal; otherwise, the formula is used:

[0029]

[0030]

[0031]

[0032] Calculate the power risk coefficient of the working state period separately and power risk coefficient during non-working periods ;

[0033] Where q is the number of working state periods, k∈[1,q], is the real-time current change curve of the kth working period, is the reference current variation curve of the kth working period, is the kth working period and The mean of the differences, is the first preset coefficient, Temperature influence coefficient, is the current unit reference value, is the average value of the real-time current in all non-working periods, is the reference current for all non-working periods, is the second preset coefficient, m is the number of time points selected according to fixed time intervals during all non-working periods, j∈[1,m], is the real-time current corresponding to the i-th time point, T(t) is the monitored temperature, is the ambient temperature, is the heat determination function of the lane equipment, is the reference current variation curve, is the allowable value of temperature error.

[0034] Furthermore, the process of obtaining the life coefficient includes:

[0035] Obtain the timestamp of each operation based on the historical operation data of the lane equipment, obtain the time interval between two adjacent operation processes based on the timestamp, establish the time interval into a sequence, compare each sequence value with a preset fixed value, obtain several sequence values ​​less than the preset fixed value as selected sequence values, and group the selected sequence values ​​with consecutive sequence numbers into a group to obtain u groups of data;

[0036] By formula:

[0037]

[0038]

[0039] Calculate and obtain the life coefficient Lf;

[0040] in, is the rated life of the lane equipment, L is the current remaining life of the lane equipment, is the additional lost life of lane equipment, x∈[1,u], is the number of consecutive serial numbers in the xth group, , is the sequence value corresponding to the yth sequence number in the xth group, is a preset fixed value. is the life loss rate step function.

[0041] Furthermore, the process of obtaining the risk factor of lane equipment includes:

[0042] By formula:

[0043]

[0044] Calculate the risk factor R of lane equipment;

[0045] Among them, Rt is the preset risk threshold, for The corresponding threshold, for The corresponding threshold, 、 、 is the preset weight coefficient, is the life coefficient risk baseline, ;

[0046] The process of risk monitoring based on the risk factor of lane equipment includes:

[0047] The risk factor R is compared with the preset risk threshold Rt, and an early warning is issued to the lane equipment when R≥Rt.

[0048] Furthermore, the process of risk monitoring based on the risk coefficient of lane equipment also includes:

[0049] When R<Rt, the maintenance frequency of lane equipment is dynamically adjusted according to the size of R.

[0050] Beneficial effects of the present invention:

[0051] (1) The present invention can accurately obtain more accurate comparison standards based on different scenarios and different input contents. Compared with the benchmark data, this data can more accurately reflect the standard operating status. Therefore, the comparison results of the lane equipment process data and the reference process data are obtained through the monitoring and operation control module, and the lane equipment is monitored for risks based on the power data and life data. It can make timely judgments in the abnormal state stage before the lane equipment fails, thereby improving the sensitivity of the judgment results. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The present invention will be further described below with reference to the accompanying drawings.

[0053] Figure 1 It is a logic block diagram of the lane equipment monitoring, operation and maintenance control system of the present invention. DETAILED DESCRIPTION

[0054] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making any creative efforts shall fall within the scope of protection of the present invention.

[0055] In one embodiment, a lane equipment monitoring and operation control system based on a modular intelligent cloud box is provided, which mainly monitors and controls the lane controller, ETC dedicated RSU and high-definition license plate recognition device in the lane core equipment. Figure 1As shown, the system includes an operation data acquisition terminal, a modular intelligent cloud box, a power data acquisition terminal, a life management module, and a monitoring and operation control module. It can be seen that this embodiment comprehensively judges the operation risk of lane equipment based on its operation status, power status, and life status. Among them, the operation data acquisition is used to obtain the operation data of the lane equipment, and the operation data includes the input data and process data of the lane equipment; the power data acquisition is used to obtain the power data of the lane equipment; the life management module is used to manage the lane equipment based on historical operation data and obtain the life data of the lane equipment. Compared with the existing method of comparing the operation data and power data of the lane equipment with the corresponding benchmark data, this embodiment is provided with a modular intelligent cloud box, which can perform AI simulation on the input data through an AI model to obtain reference process data. Through this process, a more accurate comparison standard can be accurately obtained according to different scenarios and different input content. Compared with the benchmark data, this data can more accurately reflect the standard operation status. Therefore, the comparison results of the lane equipment process data and the reference process data are obtained by the monitoring and operation control module, and the risk monitoring of the lane equipment is then carried out based on the power data and life data. It can make timely judgments in the abnormal state stage before the lane equipment fails, thereby improving the sensitivity of the judgment results.

[0056] The process of establishing the AI ​​model in the above-mentioned modular intelligent cloud box includes: first, obtaining the test data corresponding to different input data of lane equipment of the same specifications in a stable operating state in the empirical data, and using the preset input data and the corresponding test data as samples for machine learning training to obtain an AI model, wherein the machine model can select a random forest algorithm model. The specific training process is the existing technology in this field and will not be further described here. By inputting the corresponding input information into the trained AI model, the operating data of the lane equipment in a non-abnormal state can be obtained, and this can be used as reference data for comparison, thereby improving the sensitivity of the judgment result.

[0057] In one embodiment, a process for risk monitoring of lane equipment is provided, including: obtaining a performance coefficient of the lane equipment based on a comparison result between lane equipment process data and reference process data; obtaining a power risk coefficient of the lane equipment based on power data; obtaining a life coefficient of the lane equipment based on life data; obtaining a risk coefficient of the lane equipment based on the performance coefficient, power risk coefficient and life coefficient, and performing risk monitoring based on the size of the lane equipment risk coefficient. By quantifying the performance status, power risk status and life status of the lane equipment as described above, the performance coefficient, power risk coefficient and life coefficient are obtained, and the risk coefficient is obtained based on them, and then the abnormality can be judged by the size of the risk coefficient of the lane equipment, thereby improving the timeliness of the judgment.

[0058] It should be noted that the above-mentioned risk coefficient represents the abnormal state of the lane equipment in a period of time. When making timely judgments, the risk coefficient can be calculated periodically, and the risk coefficient within a time window can be calculated in real time according to the sliding time window to obtain the real-time risk coefficient of the lane equipment.

[0059] In one embodiment, a process for obtaining the performance coefficient is provided, including: obtaining the performance coefficient before the current time point Lane equipment process data under time period; through the formula Calculate and obtain the performance coefficient of lane equipment; where f(x) is the definition function, when x ≥ 0, f(x) = x, when x < 0, f(x) = 0, n is the response item of lane equipment, and the corresponding items of different lane equipment are different. Taking the high-definition license plate recognition device as an example, its response items include image acquisition and recognition items, recognition response items, and upload recognition items. The response items of the ETC dedicated RSU and lane controller include vehicle perception response items, transaction request recognition items, transaction processing recognition items, control instruction upload recognition items, etc., i∈[1, n], is the mean response time of the i-th response item of the process data, is the mean response time of the i-th response item of the reference process data, is the weight coefficient of the i-th response item. The weight coefficient is selected and set by the management personnel according to the correlation strength and importance of the corresponding identification item and the equipment performance. Therefore, through the above performance coefficient calculation process, the gap between the current operating status of the lane equipment and the standard operating status can be accurately judged, and then the operating risk status of the lane equipment can be judged by the size of the performance coefficient. The larger the performance coefficient, the higher the operating risk.

[0060] In one embodiment, a process for obtaining a power risk coefficient is provided, including: obtaining the power risk coefficient before the current time point according to the power data Real-time current and temperature monitoring of key monitoring points of lane equipment during the time period, The duration is set within a reasonable range, and the real-time reference current of the lane equipment is obtained by simulating the input data. This process determines the corresponding standard current based on the time point of the input data and the input instruction. Taking the ETC-specific RSU as an example, the power supply current of its ETC antenna remains stable in the non-working state and increases in the working state. Therefore, the real-time reference current is divided into states to obtain the working state period and the non-working state period; the difference threshold between the real-time current and the reference current is judged in the working state period and the non-working state period respectively. The difference threshold is selected and set based on the empirical error data. Therefore, when the maximum difference exceeds the corresponding threshold, it means that the data gap exceeds the error range, so it is judged that the lane equipment is abnormal; otherwise, further judgment is made by the formula, which is as follows:

[0061]

[0062]

[0063]

[0064] The power risk coefficient of the working period is calculated by the above formula and power risk coefficient during non-working periods ; Where q is the number of working state periods, k∈[1,q], is the real-time current change curve of the kth working period, is the reference current variation curve of the kth working period, is the kth working period and The mean of the differences, is the first preset coefficient, Temperature influence coefficient, is the current unit reference value, is the average value of the real-time current in all non-working periods, is the reference current for all non-working periods, is the second preset coefficient, m is the number of time points selected according to fixed time intervals during all non-working periods, j∈[1,m], is the real-time current corresponding to the i-th time point, T(t) is the monitored temperature, is the ambient temperature, is the heat determination function of the lane equipment, is the reference current variation curve, is the allowable value of temperature error, where the first preset coefficient With the second preset coefficient is a fixed value, which is obtained by fitting the test data, and the current unit reference value According to the unit setting of the power data, in this embodiment , heat measurement function of lane equipment The allowable temperature error is obtained by fitting the test temperature data of lane equipment at different current step values ​​under standard conditions. According to the empirical data fitting setting, the temperature influence coefficient The calculation process can be achieved through The size of the temperature deviation is used to determine the proportion of the temperature deviation relative to the allowable value of the temperature error. When the value exceeds 0, it indicates that there is a risk of abnormal heating, and the larger the value, the higher the risk. The power risk coefficient during the working period In the calculation process, this embodiment makes a comprehensive judgment by combining the maximum difference and average difference of the integrated current data, and then combines the temperature influence coefficient to obtain the power risk coefficient. Realize the power risk judgment of lane equipment working status, and calculate the power risk coefficient during non-working period In the calculation process, this embodiment obtains the power risk coefficient by comprehensively analyzing the current stability and the difference between the real-time current and the standard current. , and then when the current stability is poor or the difference between the real-time current and the standard current is large, the power risk coefficient The size of reflects the electrical risk of lane equipment during non-operation.

[0065] In one embodiment, a process for obtaining a life coefficient is provided, including: first, obtaining a timestamp of each operation based on historical operation data of a lane device, obtaining a time interval between two adjacent operation processes based on the timestamp, establishing the time intervals as a sequence, comparing each sequence value with a preset fixed value, the preset fixed value being set based on empirical data, determining that the lane device is operating continuously when each sequence value (time interval between each operation) is less than the preset fixed value, obtaining a number of sequence values ​​less than the preset fixed value as selected sequence values, and grouping the selected sequence values ​​with consecutive sequence numbers as a group to obtain u groups of data; using the formula:

[0066]

[0067]

[0068] The life coefficient Lf is calculated; where, is the rated life of the lane equipment, which is obtained based on the factory data of the equipment. L is the current remaining life of the lane equipment, which is obtained based on the historical statistical data of the lane equipment. is the additional lost life of lane equipment, x∈[1,u], is the number of consecutive serial numbers in the xth group, , is the sequence value corresponding to the yth sequence number in the xth group, is a preset fixed value, so the formula The size reflects the continuous operation status of the lane equipment. Since the longer the lane equipment is in continuous operation, the greater the impact on its life loss, therefore, by continuously running the lane equipment and obtaining test data, different life impact coefficients are divided according to the use status of the lane equipment in the test results, and then the life loss rate step function is fitted. , >0, so through , and then the additional life loss caused by the continuous operation process corresponding to the xth group can be determined, and the additional life loss of the u group can be accumulated to obtain the additional life loss of the lane equipment. , and then obtain the life coefficient Lf. When the life coefficient Lf ≥ 1, it means that the vehicle equipment is in a scrapped state, and then the abnormal risk of lane equipment can be judged through the life coefficient.

[0069] In one embodiment, a process for obtaining a risk factor of a lane device is provided, including: using the formula:

[0070]

[0071] Calculate the risk coefficient R of the lane equipment; where Rt is the preset risk threshold, for The corresponding threshold, for corresponding threshold, corresponding threshold 、 Determined by the standard of division after fitting the test data, 、 、 is a preset weight coefficient, which is selected based on the frequency of occurrence of different factors in the empirical data and the degree of their influence. is the proportion of working hours, is the proportion of non-working time, , The life coefficient risk baseline is set according to the equipment type and the corresponding empirical data. For example, when the life of a certain equipment reaches 80%, its operating status drops rapidly, and its life coefficient risk baseline can be set at 0.8. The life coefficient risk baseline range of the lane equipment selected in this embodiment is Through the above-mentioned risk coefficient calculation process, the preset risk threshold Rt can be directly triggered when the life reaches the rated life. When the rated life is not reached, the abnormal risk of the lane equipment can be judged promptly and accurately based on a variety of factors. Risk monitoring is performed according to the size of the lane equipment risk coefficient, and the risk coefficient R is compared with the preset risk threshold Rt. The preset risk threshold Rt is set according to the critical value fitting in the test data. Therefore, when R≥Rt, the lane equipment is warned. When R<Rt, the maintenance frequency of the lane equipment is dynamically adjusted according to the size of R, so as to adaptively improve the targeted maintenance, realize early detection of lane equipment failures, and avoid the adverse impact of sudden failures on traffic.

[0072] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. Lane equipment monitoring and operation control system based on modular intelligent cloud box, characterized by: The system comprises: An operation data acquisition terminal is used to obtain operation data of lane equipment, wherein the operation data includes input data and process data of lane equipment; A modular smart cloud box for performing AI simulation on input data through AI models to obtain reference process data; Power data collection terminal, used to obtain power data of lane equipment; Life management module, used to manage lane equipment based on historical operation data and obtain lane equipment life data; The monitoring and operation control module is used to monitor the risk of lane equipment based on the comparison results of the lane equipment's process data with the reference process data, power data, and life data; The process of risk monitoring of lane equipment includes: Obtaining a performance coefficient of the lane equipment based on a comparison result of the process data of the lane equipment and the reference process data; Obtain the power risk factor of lane equipment based on power data; Obtain the life coefficient of lane equipment based on life data; Obtain the risk factor of lane equipment based on performance coefficient, power risk coefficient and life coefficient, and conduct risk monitoring based on the size of the lane equipment risk factor; The process of obtaining the performance coefficient includes: Get the time before the current point Process data of lane equipment during the time period; By formula Calculate and obtain the performance coefficient of lane equipment; Where f(x) is the definition function. When x≥0, f(x)=x, when x<0, f(x)=0, n is the response item of the lane equipment, i∈[1,n], is the mean response time of the i-th response item of the process data, is the mean response time of the i-th response item of the reference process data, is the weight coefficient of the i-th response item; The process of obtaining the power risk coefficient includes: Get the current time based on the power data The real-time current and temperature of the key monitoring points of the lane equipment in each time period are simulated based on the input data to obtain the real-time reference current of the lane equipment. The real-time reference current is divided into states to obtain the working state period and the non-working state period; The difference threshold between the real-time current and the reference current is judged in the working state period and the non-working state period respectively: when the maximum difference exceeds the corresponding threshold, it is judged that there is an abnormality in the lane equipment; otherwise, the power risk coefficient of the working state period is calculated by the formula and power risk coefficient during non-working periods .

2. The lane equipment monitoring, operation and maintenance control system based on modular intelligent cloud box according to claim 1 is characterized in that: The process of establishing the AI ​​model includes: Obtain test data corresponding to different input data of lane equipment of the same specifications in a stable operating state in the empirical data; Use the preset input data and corresponding test data as samples for machine learning training to obtain an AI model.

3. The lane equipment monitoring, operation and maintenance control system based on modular intelligent cloud box according to claim 1 is characterized in that: Power risk factor during working period and power risk coefficient during non-working periods The calculation process includes: By formula: ; ； ； Calculate the power risk coefficient of the working state period separately and power risk coefficient during non-working periods ; Where q is the number of working state periods, k∈[1,q], is the real-time current change curve of the kth working period, is the reference current variation curve of the kth working period, is the kth working period and The mean of the differences, is the first preset coefficient, Temperature influence coefficient, is the current unit reference value, is the average value of the real-time current in all non-working periods, is the reference current for all non-working periods, is the second preset coefficient, m is the number of time points selected according to fixed time intervals during all non-working periods, j∈[1,m], is the real-time current corresponding to the i-th time point, T(t) is the monitored temperature, is the ambient temperature, is the heat determination function of the lane equipment, is the reference current variation curve, is the allowable value of temperature error.

4. The lane equipment monitoring, operation and maintenance control system based on modular intelligent cloud box according to claim 3 is characterized in that: The process of obtaining the life coefficient includes: Obtain the timestamp of each operation based on the historical operation data of the lane equipment, obtain the time interval between two adjacent operation processes based on the timestamp, establish the time interval into a sequence, compare each sequence value with a preset fixed value, obtain several sequence values ​​less than the preset fixed value as selected sequence values, and group the selected sequence values ​​with consecutive sequence numbers into a group to obtain u groups of data; By formula: ; ； Calculate and obtain the life coefficient Lf; in, is the rated life of the lane equipment, L is the current remaining life of the lane equipment, is the additional lost life of lane equipment, x∈[1,u], is the number of consecutive serial numbers in the xth group, ], is the sequence value corresponding to the yth sequence number in the xth group, is a preset fixed value. is the life loss rate step function.

5. The lane equipment monitoring, operation and maintenance control system based on modular intelligent cloud box according to claim 4 is characterized in that: The process of obtaining the risk factor of lane equipment includes: By formula: ； Calculate the risk factor R of lane equipment; Among them, Rt is the preset risk threshold, for The corresponding threshold, for The corresponding threshold, 、 、 is the preset weight coefficient, is the life coefficient risk baseline, 0.7≤ <1; The process of risk monitoring based on the risk factor of lane equipment includes: The risk factor R is compared with the preset risk threshold Rt, and an early warning is issued to the lane equipment when R≥Rt.

6. The lane equipment monitoring, operation and maintenance control system based on modular intelligent cloud box according to claim 5 is characterized in that: The process of risk monitoring based on the risk factor of lane equipment also includes: When R<Rt, the maintenance frequency of lane equipment is dynamically adjusted according to the size of R.

Images