Fault prediction management method and system based on industrial park

Abstract

The invention discloses a fault prediction management method and system based on an industrial park, and relates to the technical field of fault prediction management of industrial parks, and the method comprises the following steps: S1, obtaining the voltage and image abnormal values of each camera, obtaining a camera abnormal coefficient through the voltage and image abnormal values, and carrying out the fault prediction management of each camera; obtaining air quality, temperature and shielding view values near each camera, obtaining a camera environment coefficient through the air quality, the temperature and the shielding view values, and obtaining an anomaly evaluation score of each camera through the camera anomaly coefficient and the camera environment coefficient; according to the scheme, the internal factor anomaly coefficient and the external factor environment coefficient of the camera are combined to obtain the anomaly evaluation score of the camera, so that the potential fault of the camera can be judged more accurately.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial park fault prediction management, in particular to a fault prediction management method and system based on an industrial park. BACKGROUND

[0002] Industrial parks are important carriers of modern industrial development. They optimize resource allocation, reduce operating costs, promote industrial agglomeration and upgrading by scientific planning, centralized layout, and organic integration of related enterprises, infrastructure and service platforms in a specific area. They are not only the engine driving regional economic growth, but also the model of modern industrial communities achieving intensive, green and intelligent development. Surveillance cameras are indispensable "intelligent eyes" in industrial parks. They build a full-coverage, dead-angle-free three-dimensional security system, achieving real-time safety monitoring and efficient management of personnel, vehicles and materials. They can also visually monitor key links such as production areas, equipment operation status and warehouse logistics, effectively preventing accidents, improving operational efficiency and ensuring production order, providing core data support and decision-making basis for intelligent management and digital transformation of the park. Industrial parks need to review surveillance videos at the scene of the incident after operational problems and accidents occur. However, surveillance videos and camera equipment often malfunction, resulting in a lack of important evidence for post-mortem accountability. The working status and video storage of surveillance cameras in the park lack predictive management. To facilitate predictive management and protection of surveillance equipment and surveillance video storage in industrial parks, we propose a fault prediction management method and system based on an industrial park. SUMMARY

[0003] (I) Technical problems solved To address the shortcomings of the prior art, the present application provides a fault prediction management method and system based on an industrial park to solve the above problems in the prior art.

[0004] (II) Technical solutions To achieve the above purpose, the present application is implemented by the following technical solutions: a fault prediction management method based on an industrial park, comprising the following steps: S1: Obtain the voltage and picture abnormal value of each camera. Obtain the camera abnormality coefficient by the voltage and picture abnormal value, obtain the air quality, temperature and occluded view value near each camera, obtain the camera environment coefficient by the air quality, temperature and occluded view value, and obtain the abnormality evaluation score of each camera by the camera abnormality coefficient and the camera environment coefficient. S2: dividing a plurality of monitoring areas according to work types in the industrial park, establishing a monitoring video storage database, establishing a plurality of data storage spaces in the monitoring video storage database according to the number of monitoring areas, and dividing and storing all camera monitoring videos in each monitoring area in the plurality of data storage spaces respectively; S3: acquiring the working time and the storage data size of each camera respectively, comparing the storage data size of the same working time in the same monitoring area to determine whether data loss occurs, capturing the position of the data loss camera according to the determination result, and marking it as an irregular area; S4: informing the management personnel to maintain and repair the camera according to the abnormal evaluation, adding a camera in the irregular area according to the data loss determination result, and backup and encrypted storage of the storage data in the irregular area according to the data loss determination result.

[0005] Preferably, in S1, the picture abnormal value of each camera is obtained, specifically: S101: acquiring the monitoring picture of the camera, setting a picture loss time length preset threshold, judging whether the monitoring picture of the camera appears a blue screen picture, a black screen picture or a no signal picture, if the monitoring picture appears a blue screen picture, a black screen picture or a no signal picture, judging whether the total time length of the blue screen picture, the black screen picture or the no signal picture in the monitoring picture is less than the picture loss time length preset threshold, if the total time length of the blue screen picture, the black screen picture or the no signal picture in the monitoring picture is less than the picture loss time length preset threshold, the picture loss is marked as 0, if the total time length of the blue screen picture, the black screen picture or the no signal picture in the monitoring picture is greater than or equal to the picture loss time length preset threshold, the picture loss is marked as 1; S102: setting a signal interference time length preset threshold, judging whether snowflakes or stripes appear in the monitoring picture of the camera, if snowflakes or stripes appear in the monitoring picture of the camera, judging whether the total time length of the snowflakes or stripes appearing in the monitoring picture is less than the signal interference time length preset threshold, if the total time length of the snowflakes or stripes appearing in the monitoring picture is less than the signal interference time length preset threshold, the signal interference is marked as 0, if the total time length of the snowflakes or stripes appearing in the monitoring picture is greater than or equal to the signal interference time length preset threshold, the signal interference is marked as 1; S103: acquiring the picture loss result, acquiring the signal interference result, and summing the picture loss result and the signal interference result to obtain the picture abnormal value.

[0006] Preferably, in S1, the camera abnormality coefficient is obtained by the voltage and the picture abnormal value, specifically: S104: Obtain the current voltage of the camera, set a monitoring period, obtain the voltage of the camera again after a monitoring period, take the absolute value of the difference between the two voltages before and after a monitoring period to obtain a voltage difference, set a voltage difference preset threshold, determine whether the voltage difference is less than the voltage difference preset threshold, if the voltage difference is greater than or equal to the voltage difference preset threshold, mark the voltage corresponding to the monitoring period as an abnormal voltage, obtain the number of abnormal voltages within 24 hours of the camera and mark it as a voltage abnormal value; S105: Obtain the picture abnormal value of the camera within 24 hours, and obtain the camera abnormal coefficient by weighted sum of the picture abnormal value and the voltage abnormal value within 24 hours.

[0007] Preferably, in S1, the air quality, temperature and occluded field of view value near each camera are obtained, and the camera environment coefficient is obtained by the air quality, temperature and occluded field of view value, specifically: S106: Obtain the dust concentration near the camera, set a dust concentration preset threshold, determine whether the dust concentration near the camera is less than the dust concentration preset threshold, if the dust concentration near the camera is greater than or equal to the dust concentration preset threshold, the air quality is marked as 1, if the dust concentration near the camera is less than the dust concentration preset threshold, the air quality is marked as 0; S107: Obtain the air temperature near the camera, set an air temperature preset threshold, determine whether the air temperature near the camera is less than the air temperature preset threshold, if the air temperature near the camera is greater than or equal to the air temperature preset threshold, the temperature is marked as 1, if the air temperature near the camera is less than the air temperature preset threshold, the temperature is marked as 0; S108: Determine whether there is a field of view occlusion in front of the camera, if there is a field of view occlusion in front of the camera, the occluded field of view value is marked as 1, if there is no field of view occlusion in front of the camera, the occluded field of view value is marked as 0; S109: Obtain the camera environment coefficient by weighted sum of the air quality, temperature and occluded field of view value of the camera.

[0008] Preferably, in S1, the abnormal evaluation score of each camera is obtained by the camera abnormal coefficient and the camera environment coefficient, specifically: obtain the camera abnormal coefficient, obtain the camera environment coefficient, and obtain the abnormal evaluation score of the camera by weighted sum of the camera abnormal coefficient and the camera environment coefficient.

[0009] Preferably, in S3, the storage data sizes of the same working time length in the same monitoring area are compared to determine whether data loss occurs, specifically: S301: acquire all monitoring video data in each monitoring area respectively, mark the monitoring working time corresponding to each monitoring video data on the monitoring video data, capture all monitoring video data with the same monitoring working time in the same monitoring area and mark as reference video; S302: acquire the storage data size of all reference videos, arrange the storage data size of all reference videos in order from small to large, remove the highest value and the lowest value of the storage data size, and sum the storage data size of the remaining all reference videos to obtain the mean value of the storage data size; S303: respectively subtract the storage data size of all reference videos from the mean value of the storage data size to obtain a plurality of storage data size fluctuation values, set a storage data size fluctuation preset threshold, and respectively determine whether the storage data size fluctuation value of each reference video is less than the storage data size fluctuation preset threshold, if the storage data size fluctuation value of the reference video is less than the storage data size fluctuation preset threshold, the reference video is marked as normal, if the storage data size fluctuation value of the reference video is greater than or equal to the storage data size fluctuation preset threshold, the reference video is marked as abnormal; S304: determine whether the number of reference videos marked as abnormal is greater than 0, if the number of reference videos marked as abnormal is greater than 0, the result of the determination is that data loss occurs.

[0010] Preferably, in S4, the management personnel is notified to maintain and repair the camera according to the abnormal evaluation score, specifically: S401: acquire the abnormal evaluation score of the camera, determine whether the abnormal evaluation score of the camera is 0, if the abnormal evaluation score of the camera is not 0, execute S402, if the abnormal evaluation score of the camera is 0, mark the camera as normal; S402: acquire the abnormal coefficient of the camera, determine whether the abnormal coefficient of the camera is 0, if the abnormal coefficient of the camera is 0, notify the management personnel to maintain the air quality, temperature and obstructed view near the camera, if the abnormal coefficient of the camera is not 0, notify the management personnel to maintain the voltage and signal picture of the camera.

[0011] Preferably, in S4, a camera is added in the irregular area according to the data loss determination result, specifically: acquire the data loss determination result, if the data loss determination result is that data loss occurs, a camera is added in the irregular area.

[0012] Preferably, in S4, the storage data of the irregular area is backup encrypted storage according to the data loss determination result, specifically: acquire the data loss determination result, if the data loss determination result is that data loss occurs, the storage data of the irregular area is backup encrypted storage subsequently.

[0013] An industrial park-based fault prediction management system comprises the following modules: An equipment state monitoring module acquires voltage and picture abnormal values of each camera, obtains a camera abnormality coefficient from the voltage and picture abnormal values, acquires air quality, temperature and occluded field of view values near each camera, obtains a camera environment coefficient from the air quality, temperature and occluded field of view values, and obtains an abnormality evaluation score of each camera from the camera abnormality coefficient and the camera environment coefficient. A data storage management module divides multiple monitoring areas according to work types in the industrial park, establishes a monitoring video storage database, establishes multiple data storage spaces in the monitoring video storage database according to the number of monitoring areas, and divides and stores all camera monitoring videos in each monitoring area in the multiple data storage spaces. An irregular area capturing module acquires working time and storage data size of each camera, compares storage data sizes of the same working time in the same monitoring area to determine whether data loss occurs, captures the position of a data loss camera and marks it as an irregular area according to the determination result. A hazard management module notifies a maintenance personnel to maintain and repair the camera according to the abnormality evaluation score, adds a camera in the irregular area according to the data loss determination result, and performs backup and encrypted storage of storage data in the irregular area according to the data loss determination result.

[0014] (Three) beneficial effects The application provides an industrial park-based fault prediction management method and system, which has the following beneficial effects: Since the environment of an industrial park is different from that of a common household camera, the industrial park has more dust, worse air quality, higher temperature and higher environmental complexity, the camera is aged and damaged in the environment with poor air quality and high temperature for a long time, and the camera is more likely to be blocked by leaves, sundries or human beings in the environment with high environmental complexity, therefore, the potential fault risk of the camera is determined by monitoring the air quality, temperature and occluded field of view, thereby further helping to maintain and repair the camera before damage, the abnormality evaluation score of the camera is obtained by combining the internal factor abnormality coefficient and the external factor environment coefficient, thereby more accurately determining the potential fault of the camera.

[0015] This solution divides the industrial park into multiple monitoring zones based on the type of work. All camera surveillance videos within each zone are then evenly distributed and stored in multiple data storage spaces. This avoids storing all videos from a single monitoring zone in the same storage space, thus preventing the loss of all video data for the entire monitoring zone. Even if one storage space is damaged or lost, the monitoring zone can be revisited and its correlation checked in other storage spaces. This also increases the difficulty for non-technical personnel to find specific videos that have been intentionally deleted. Furthermore, since the types of work within the monitoring zones are similar, the pixel change complexity of each frame in the video is similar, making it easy to determine whether a video has been deleted by observing the amount of storage space occupied. Attached Figure Description

[0016] Fig. 1 This is a flowchart of a fault prediction and management method based on industrial parks according to the present invention. Fig. 2 This is a schematic diagram of the module structure of a fault prediction management system based on an industrial park according to the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Please see Figs. 1-2 This invention provides a fault prediction and management method based on industrial parks, comprising the following steps: S1: Obtain the voltage and image anomaly values ​​of each camera, obtain the camera anomaly coefficient from the voltage and image anomaly values, obtain the air quality, temperature and obstruction of view values ​​near each camera, obtain the camera environment coefficient from the air quality, temperature and obstruction of view values, and obtain the anomaly evaluation score of each camera from the camera anomaly coefficient and the camera environment coefficient. S2: Within the industrial park, multiple monitoring areas are defined according to the type of operation. A monitoring video storage database is established. Within the monitoring video storage database, multiple data storage spaces are established according to the number of monitoring areas. All camera monitoring videos in each monitoring area are equally distributed and stored in the multiple data storage spaces respectively. S3: Obtain the working time and stored data size of each camera respectively, compare the stored data size of the same working time in the same monitoring area to determine whether there is data missing, and capture the location of the camera with missing data and mark it as an irregular area based on the judgment result; S4: According to the abnormality evaluation score, the management personnel is informed to maintain and repair the camera, according to the data loss judgment result, the camera is added in the irregular area, and according to the data loss judgment result, the storage data of the irregular area is backed up and stored.

[0019] In this embodiment, the abnormality coefficient of the camera is obtained by the voltage of the camera and the display picture. Since the power supply voltage fluctuation of the camera is unstable, it will affect the shooting work effect of the camera. The abnormality of the display picture is most likely signal interference or unstable circuit connection. Therefore, by monitoring the voltage and the picture, the potential failure of the camera can be judged, so as to benefit the maintenance and repair of the camera before it is damaged, and avoid not shooting the key picture after the key accident. Since the environment of the industrial park is different from that of the ordinary household camera, the dust in the industrial park is large, the air quality is worse, the temperature may be higher, and the environmental complexity is also relatively higher. The camera in the environment with poor air quality and high temperature for a long time will accelerate the aging and damage of the camera. The environment with high environmental complexity is also more likely to cause the camera to be blocked by leaves and sundries or human beings. Therefore, by monitoring the air quality, temperature and blocked view, the potential failure risk of the camera can be judged, so as to further benefit the maintenance and repair of the camera before it is damaged. The abnormality evaluation score of the camera is obtained by combining the internal factor abnormality coefficient of the camera with the external factor environment coefficient, so as to more accurately judge the potential failure of the camera. In this scheme, a plurality of monitoring areas are divided in the industrial park according to the work types, and all the camera monitoring videos in each monitoring area are divided and stored in a plurality of data storage spaces, so as to avoid that all the videos in a monitoring area are stored in the same storage space, thereby benefiting to avoid the loss of video data causing the loss of all the video data of the whole monitoring area. Even if one storage space is damaged or lost, the relevant check and review of the monitoring area can be performed through other storage spaces. At the same time, it also increases the difficulty for non-technical personnel to find and delete specific monitoring videos. At the same time, since the work types in the monitoring area are the same, the pixel change complexity of each frame of video picture is close, so that whether the video is deleted can be judged by the size of the occupied storage space in the subsequent process. In this scheme, the storage data size of the same work duration in the same monitoring area is compared to judge whether the data is missing. Since the work types in the same monitoring area are the same, the pixel change complexity of each frame of video picture is close, so that whether the storage video is deleted or the video is missing due to no signal in the middle can be judged by the same work duration of the camera and the occupied storage size, so as to facilitate marking the irregular area according to the position of the camera, and then facilitating subsequent attention to the irregular area. The abnormality evaluation score is used to determine whether the management personnel need to be notified to maintain and repair the camera, and the abnormality coefficient and the environment coefficient in the abnormality evaluation score can accurately feed back the range that needs to be maintained and repaired to the management personnel, thereby reducing the workload of the management personnel for maintenance, increasing the monitoring intensity of the area by adding a camera in the irregular area, avoiding single monitoring, and avoiding loss of storage of monitoring video in the accident-prone area by backing up and encrypting the storage data of the irregular area, thereby facilitating the prevention of human deletion and modification of the monitoring video. It is worth mentioning that the weight value of the weighting in the present scheme can be obtained by the analytic hierarchy process, and the value of the preset threshold can be obtained by the weight analysis method, which will not be described in detail here.

[0020] In S1, the picture abnormal value of each camera is obtained, specifically: S101: Obtain the monitoring picture of the camera, set a picture loss time length preset threshold, determine whether the monitoring picture of the camera appears a blue screen picture, a black screen picture or a no signal picture, if the monitoring picture appears a blue screen picture, a black screen picture or a no signal picture, determine whether the total time length of the blue screen picture, the black screen picture or the no signal picture in the monitoring picture is less than the picture loss time length preset threshold, if the total time length of the blue screen picture, the black screen picture or the no signal picture in the monitoring picture is less than the picture loss time length preset threshold, the picture loss mark is 0, if the total time length of the blue screen picture, the black screen picture or the no signal picture in the monitoring picture is greater than or equal to the picture loss time length preset threshold, the picture loss mark is 1; S102: Set a signal interference time length preset threshold, determine whether snowflakes or stripes appear in the monitoring picture of the camera, if snowflakes or stripes appear in the monitoring picture of the camera, determine whether the total time length of the snowflakes or stripes appearing in the monitoring picture is less than the signal interference time length preset threshold, if the total time length of the snowflakes or stripes appearing in the monitoring picture is less than the signal interference time length preset threshold, the signal interference mark is 0, if the total time length of the snowflakes or stripes appearing in the monitoring picture is greater than or equal to the signal interference time length preset threshold, the signal interference mark is 1; S103: Obtain the picture loss result, obtain the signal interference result, and sum the picture loss result and the signal interference result to obtain the picture abnormal value.

[0021] In the present embodiment, the blue screen picture, the black screen picture and the no signal picture are all circuit connection abnormal conditions, indicating that the line connection is unstable, and the snowflakes and the stripes are caused by signal interference, so the reason can be inferred through the picture feedback, and finally whether the monitoring equipment has abnormal conditions can be mastered through the picture condition, thereby facilitating subsequent calculation of the abnormality evaluation score, and facilitating predictive monitoring and management of the camera failure before the accident occurs.

[0022] In S1, the camera abnormality coefficient is obtained by the voltage and the picture abnormal value, specifically: S104: Obtain the current voltage of the camera, set a monitoring period, and obtain the voltage of the camera again after one monitoring period. The voltage difference is obtained by taking the absolute value of the difference between the two voltages before and after one monitoring period. Set a voltage difference preset threshold, and determine whether the voltage difference is less than the voltage difference preset threshold. If the voltage difference is greater than or equal to the voltage difference preset threshold, the voltage corresponding to the monitoring period is marked as an abnormal voltage. Obtain the number of abnormal voltages within 24 hours of the camera and mark it as a voltage abnormal value; S105: Obtain the picture abnormal value within 24 hours of the camera, and obtain the camera abnormality coefficient by weighted sum of the picture abnormal value and the voltage abnormal value within 24 hours of the camera.

[0023] In this embodiment, the abnormality coefficient of the camera is obtained by the voltage and the display picture of the camera. Since the unstable fluctuation of the power supply voltage of the camera will affect the shooting work effect of the camera, the abnormality of the display picture is most likely to be signal interference or unstable circuit connection. Therefore, the potential failure of the camera can be determined by monitoring the voltage and the picture, thereby facilitating maintenance and repair of the camera before it is damaged, and avoiding the failure to shoot key pictures after a critical accident.

[0024] In S1, the air quality, temperature and occluded view value near each camera are obtained, and the camera environment coefficient is obtained by the air quality, temperature and occluded view value, specifically: S106: Obtain the dust concentration near the camera, set a dust concentration preset threshold, and determine whether the dust concentration near the camera is less than the dust concentration preset threshold. If the dust concentration near the camera is greater than or equal to the dust concentration preset threshold, the air quality is marked as 1. If the dust concentration near the camera is less than the dust concentration preset threshold, the air quality is marked as 0. S107: Obtain the air temperature near the camera, set an air temperature preset threshold, and determine whether the air temperature near the camera is less than the air temperature preset threshold. If the air temperature near the camera is greater than or equal to the air temperature preset threshold, the temperature is marked as 1. If the air temperature near the camera is less than the air temperature preset threshold, the temperature is marked as 0. S108: Determine whether there is a view occlusion in front of the camera. If there is a view occlusion in front of the camera, the occluded view value is marked as 1. If there is no view occlusion in front of the camera, the occluded view value is marked as 0. S109: Obtain the camera environment coefficient by weighted sum of the air quality, temperature and occluded view value of the camera.

[0025] In this embodiment, because the industrial park is different from the environment of the ordinary household camera, the industrial park has more dust, worse air quality, and higher temperature, and the environmental complexity is also relatively higher. The camera in the environment with poor air quality and high temperature will accelerate the aging and damage of the camera, and the environment with high environmental complexity is more likely to cause the camera to be blocked by leaves, debris or human beings. Therefore, by monitoring the air quality, temperature and blocked view, the potential failure risk of the camera can be judged, thereby further benefiting the maintenance and repair of the camera before the camera is damaged.

[0026] In S1, the abnormality evaluation score of each camera is obtained by the camera abnormality coefficient and the camera environment coefficient. Specifically, the camera abnormality coefficient is obtained, the camera environment coefficient is obtained, and the camera abnormality coefficient and the camera environment coefficient are weighted and summed to obtain the abnormality evaluation score of the camera.

[0027] In this embodiment, the abnormality evaluation score of the camera is obtained by combining the internal factor abnormality coefficient of the camera and the external factor environment coefficient, so that the potential failure of the camera can be more accurately judged.

[0028] In S3, the storage data sizes of the same working time in the same monitoring area are compared to determine whether data loss occurs. Specifically, S301: Obtain all monitoring video data in each monitoring area, mark the monitoring working time corresponding to each monitoring video data on the monitoring video data, and capture all monitoring video data with the same monitoring working time in the same monitoring area and mark them as reference video; S302: Obtain the storage data sizes of all reference videos, arrange the storage data sizes of all reference videos in ascending order, remove the maximum value and the minimum value of the storage data sizes, and sum the storage data sizes of the remaining all reference videos to obtain the mean value of the storage data sizes; S303: Subtract the mean value of the storage data sizes from the storage data sizes of all reference videos to obtain a plurality of storage data size fluctuation values, set a storage data size fluctuation preset threshold, and respectively determine whether the storage data size fluctuation value of each reference video is less than the storage data size fluctuation preset threshold. If the storage data size fluctuation value of the reference video is less than the storage data size fluctuation preset threshold, the reference video is marked as normal. If the storage data size fluctuation value of the reference video is greater than or equal to the storage data size fluctuation preset threshold, the reference video is marked as abnormal; S304: Determine whether the number of reference videos marked as abnormal is greater than 0. If the number of reference videos marked as abnormal is greater than 0, the result is that data loss occurs.

[0029] In the embodiment, whether data is missing is determined by comparing the storage data size of the same working time in the same monitoring area. Since the types of work in the same monitoring area are the same, the pixel change complexity of each frame of the video picture is close, and therefore whether the stored video is deleted or missing due to no signal in the middle can be determined by the same working time of the camera and the storage size occupied, so as to facilitate marking the irregular area according to the position of the camera, and then facilitating subsequent focus on the irregular area.

[0030] In S4, the management personnel is notified to maintain and repair the camera according to the abnormal evaluation score, specifically: S401: Obtain the abnormal evaluation score of the camera, and determine whether the abnormal evaluation score of the camera is 0. If the abnormal evaluation score of the camera is not 0, S402 is executed, and if the abnormal evaluation score of the camera is 0, the camera is marked as normal. S402: Obtain the abnormal coefficient of the camera, and determine whether the abnormal coefficient of the camera is 0. If the abnormal coefficient of the camera is 0, the management personnel is notified to maintain the air quality, temperature and obstructed view near the camera, and if the abnormal coefficient of the camera is not 0, the management personnel is notified to maintain the voltage and signal picture of the camera.

[0031] In the embodiment, whether the management personnel needs to be notified to maintain and repair the camera is determined by the abnormal evaluation score, and the range that needs to be maintained and repaired can be accurately fed back to the management personnel according to the abnormal coefficient and the environmental coefficient in the abnormal evaluation score, thereby reducing the workload of the management personnel for maintenance.

[0032] In S4, a camera is added in the irregular area according to the data loss judgment result, specifically: obtaining the data loss judgment result, if the data loss judgment result is that data is missing, a camera is added in the irregular area.

[0033] In the embodiment, the monitoring intensity of the area is increased by adding a camera in the irregular area, thereby avoiding single monitoring.

[0034] In S4, the storage data of the irregular area is backup and encrypted according to the data loss judgment result, specifically: obtaining the data loss judgment result, if the data loss judgment result is that data is missing, the storage data of the irregular area is backup and encrypted.

[0035] In the embodiment, the storage data of the irregular area is backup and encrypted, thereby avoiding loss of monitoring video storage in the area where accidents occur frequently, and also avoiding human deletion and modification of monitoring video.

[0036] Please refer to Figs. 1-2This invention provides a fault prediction and management system based on industrial parks, comprising the following modules: The device status monitoring module acquires the voltage and abnormal image values ​​of each camera, obtains the camera abnormality coefficient from the voltage and abnormal image values, acquires the air quality, temperature and obstruction of view values ​​near each camera, obtains the camera environment coefficient from the air quality, temperature and obstruction of view values, and obtains the abnormality assessment score of each camera from the camera abnormality coefficient and the camera environment coefficient. The data storage management module divides multiple monitoring areas within the industrial park according to the type of operation, establishes a monitoring video storage database, and establishes multiple data storage spaces within the monitoring video storage database according to the number of monitoring areas. All camera monitoring videos in each monitoring area are evenly distributed and stored in multiple data storage spaces respectively. The unconventional area capture module acquires the working time and stored data size of each camera, compares the stored data size of the same working time in the same monitoring area to determine whether there is data missing, and captures the location of the camera with missing data and marks it as an unconventional area based on the judgment result. The hazard management module notifies management personnel to maintain and repair cameras based on anomaly assessment scores, adds cameras to non-standard areas based on data missing judgment results, and backs up and encrypts the stored data in non-standard areas based on data missing judgment results.

[0037] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.

[0038] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0039] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for failure prediction management based on industrial park, characterized in that, Comprise the following steps: S1: obtain the voltage and picture abnormal value of each camera, obtain the camera environment coefficient through the air quality, temperature and shielding field of view value near each camera, obtain the camera environment coefficient through the camera abnormal coefficient and the camera environment coefficient, and obtain the abnormal evaluation of each camera; S2: divide a plurality of monitoring areas according to the work type in the industrial park, establish a monitoring video storage database, and establish a plurality of data storage spaces in the monitoring video storage database according to the number of monitoring areas; all camera monitoring videos in each monitoring area are divided and stored in the plurality of data storage spaces; S3: respectively obtain the working time and storage data size of each camera, compare the storage data size of the same working time in the same monitoring area to judge whether data loss occurs, capture the position of the data loss camera according to the judgment result and mark it as an irregular area; S4: according to the abnormal evaluation, the management personnel is informed to maintain and repair the camera, according to the data loss judgment result, the camera is added in the irregular area, and according to the data loss judgment result, the storage data of the irregular area is backed up and stored.

2. The method for failure prognosis management based on industrial park according to claim 1, characterized in that: In S1, the picture abnormal value of each camera is obtained, specifically: S101: obtain the monitoring picture of the camera, set the picture loss time length preset threshold, judge whether the monitoring picture of the camera appears blue screen picture, black screen picture or no signal picture, if the monitoring picture appears blue screen picture, black screen picture or no signal picture, whether the total time length of the blue screen picture, the black screen picture or the no signal picture in the monitoring picture is less than the picture loss time length preset threshold, if the total time length of the blue screen picture, the black screen picture or the no signal picture in the monitoring picture is less than the picture loss time length preset threshold, the picture loss mark is 0, if the total time length of the blue screen picture, the black screen picture or the no signal picture in the monitoring picture is greater than or equal to the picture loss time length preset threshold, the picture loss mark is 1; S102: set the signal interference time length preset threshold, judge whether the monitoring picture of the camera appears snowflake or stripe, if the monitoring picture of the camera appears snowflake or stripe, whether the total time length of the snowflake or stripe in the monitoring picture is less than the signal interference time length preset threshold, if the total time length of the snowflake or stripe in the monitoring picture is less than the signal interference time length preset threshold, the signal interference mark is 0, if the total time length of the snowflake or stripe in the monitoring picture is greater than or equal to the signal interference time length preset threshold, the signal interference mark is 1; S103: obtain the picture loss result, obtain the signal interference result, and sum the picture loss result and the signal interference result to obtain the picture abnormal value.

3. The method of claim 1, wherein: In S1, the camera abnormal coefficient is obtained through the voltage and the picture abnormal value, specifically: S104: Obtain the current voltage of the camera, set a monitoring period, obtain the voltage of the camera again after a monitoring period, take the absolute value of the difference between the two voltages before and after a monitoring period to obtain a voltage difference, set a voltage difference preset threshold, and determine whether the voltage difference is less than the voltage difference preset threshold. If the voltage difference is greater than or equal to the voltage difference preset threshold, the voltage corresponding to the monitoring period is marked as an abnormal voltage. Obtain the number of abnormal voltages within 24 hours of the camera and mark it as a voltage abnormal value; S105: Obtain the picture abnormal value of the camera within 24 hours, and obtain the camera abnormal coefficient by weighted sum of the picture abnormal value and the voltage abnormal value within 24 hours.

4. The method for failure prognosis management based on industrial park according to claim 1, characterized in that: In S1, the air quality, temperature and occluded field of view value near each camera are obtained, and the camera environment coefficient is obtained by the air quality, temperature and occluded field of view value. Specifically, S106: Obtain the dust concentration near the camera, set a dust concentration preset threshold, and determine whether the dust concentration near the camera is less than the dust concentration preset threshold. If the dust concentration near the camera is greater than or equal to the dust concentration preset threshold, the air quality is marked as 1. If the dust concentration near the camera is less than the dust concentration preset threshold, the air quality is marked as 0; S107: Obtain the air temperature near the camera, set an air temperature preset threshold, and determine whether the air temperature near the camera is less than the air temperature preset threshold. If the air temperature near the camera is greater than or equal to the air temperature preset threshold, the temperature is marked as 1. If the air temperature near the camera is less than the air temperature preset threshold, the temperature is marked as 0; S108: Determine whether there is a field of view occlusion in front of the camera. If there is a field of view occlusion in front of the camera, the occluded field of view value is marked as 1. If there is no field of view occlusion in front of the camera, the occluded field of view value is marked as 0; S109: Obtain the camera environment coefficient by weighted sum of the air quality, temperature and occluded field of view value of the camera.

5. The method for failure prognosis management based on industrial park according to claim 1, characterized in that: In S1, the camera abnormal coefficient and the camera environment coefficient are obtained to obtain the abnormal evaluation score of each camera. Specifically, the camera abnormal coefficient and the camera environment coefficient are obtained, and the weighted sum of the camera abnormal coefficient and the camera environment coefficient is obtained to obtain the abnormal evaluation score of the camera.

6. The method for failure prognosis management based on industrial park according to claim 1, characterized in that: In S3, the storage data sizes of the storage data with the same working time length in the same monitoring area are compared to determine whether data loss occurs. Specifically, S301: Obtain all monitoring video data in each monitoring area, mark the monitoring working time length corresponding to each monitoring video data on the monitoring video data, capture all monitoring video data with the same monitoring working time length in the same monitoring area and mark it as reference video; S302: Obtain the storage data size of all reference videos, arrange all reference videos in order from small to large, remove the maximum and minimum values of the storage data size, and obtain the mean value of the sum of the storage data size of the remaining all reference videos. S303: respectively, the storage data size of all reference videos and the mean value of the storage data size are subtracted to obtain a plurality of storage data size fluctuation values, a storage data size fluctuation preset threshold is set, whether the storage data size fluctuation value of each reference video is less than the storage data size fluctuation preset threshold is judged respectively, if the storage data size fluctuation value of the reference video is less than the storage data size fluctuation preset threshold, the reference video is marked as normal, if the storage data size fluctuation value of the reference video is greater than or equal to the storage data size fluctuation preset threshold, the reference video is marked as abnormal; S304: judge whether the number of reference videos marked as abnormal is greater than 0, if the number of reference videos marked as abnormal is greater than 0, the result of the judgment is that data loss occurs.

7. The method of claim 1, wherein: In S4, the management personnel is informed to maintain the camera according to the abnormal evaluation score, specifically: S401: obtain the abnormal evaluation score of the camera, judge whether the abnormal evaluation score of the camera is 0, if the abnormal evaluation score of the camera is not 0, execute S402, if the abnormal evaluation score of the camera is 0, mark the camera as normal; S402: obtain the abnormal coefficient of the camera, judge whether the abnormal coefficient of the camera is 0, if the abnormal coefficient of the camera is 0, inform the management personnel to maintain the air quality, temperature and occluded field of view near the camera, if the abnormal coefficient of the camera is not 0, inform the management personnel to maintain the voltage and signal picture of the camera.

8. The industrial park-based failure prediction management method of claim 1, wherein: In S4, the camera is added in the irregular area according to the data loss judgment result, specifically: obtain the data loss judgment result, if the data loss judgment result is that data loss occurs, add the camera in the irregular area.

9. The method of claim 1, wherein: In S4, the storage data of the irregular area is backup encrypted storage according to the data loss judgment result, specifically: obtain the data loss judgment result, if the data loss judgment result is that data loss occurs, the storage data of the irregular area is backup encrypted storage subsequently.

10. An industrial park-based failure prediction management system applied to the industrial park-based failure prediction management method of any one of claims 1-9, characterized in that, Comprise the following modules: Device state monitoring module, obtain the voltage and picture abnormal value of each camera, obtain the camera abnormal coefficient through the voltage and picture abnormal value, obtain the air quality, temperature and occluded field of view value near each camera, obtain the camera environment coefficient through the air quality, temperature and occluded field of view value, obtain the abnormal evaluation score of each camera through the camera abnormal coefficient and the camera environment coefficient; Data storage management module, divide a plurality of monitoring areas in the industrial park according to the work type, establish a monitoring video storage database, establish a plurality of data storage spaces in the monitoring video storage database according to the number of monitoring areas, divide and store all camera monitoring videos in each monitoring area in the plurality of data storage spaces; Irregular area capture module, respectively, the working time and the storage data size of each camera are obtained, the storage data size of the same working time in the same monitoring area is compared to judge whether data loss occurs, the position of the data loss camera is captured and marked as an irregular area according to the judgment result; The hidden danger management module informs the maintenance personnel to maintain and repair the camera according to the abnormality evaluation, adds the camera in the non-conventional area according to the data loss judgment result, and stores the data in the non-conventional area in backup and encryption according to the data loss judgment result.

Images