Directed maintenance method and platform for electromechanical equipment combined with dynamic prediction of component life

Abstract

The present invention relates to a method and platform for directional maintenance of electromechanical equipment combined with dynamic prediction of the life of parts and components, and relates to the technical field of equipment operation and maintenance, including: performing performance testing on fill-in lights, cameras and warning devices in electromechanical equipment, and performing basic life prediction, obtaining fill-in light life information, basic camera life information and basic warning device life information; based on the performance parameters of the fill-in lights, performing life impact analysis on the camera, and correcting the basic camera life information; based on the performance parameters of the fill-in lights and cameras, performing life impact analysis on the warning device, and correcting the basic warning device life information; performing directional maintenance based on the life information of the fill-in lights, cameras and warning devices. The present invention solves the technical problem in the prior art that electromechanical equipment cannot accurately predict the life of parts and components, resulting in low maintenance efficiency, poor accuracy, and inability to achieve accurate directional maintenance.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment maintenance, and in particular to a method and platform for directional maintenance of electromechanical equipment combined with dynamic prediction of component life. Background Art

[0002] As common electromechanical equipment, existing security access control devices are widely used in places such as residences and parks. They use cameras to identify strangers and issue warnings. However, as the use time increases, key components in the security access control device, such as fill lights, cameras, and warning devices, may experience performance degradation or even failure, directly affecting its normal operation. In order to ensure the stability and safety of the equipment, regular maintenance is usually adopted for operation and maintenance. However, regular maintenance has the problems of low efficiency and high maintenance cost, and it is impossible to perform accurate maintenance based on the actual usage status of specific components.

[0003] At present, some technologies are based on the life prediction of parts for maintenance. Although this improves the effectiveness of maintenance to a certain extent, it ignores the dynamic influence of the life of various parts in the access control device. There are technical problems such as low maintenance efficiency and poor accuracy of electromechanical equipment, and inability to achieve accurate and targeted maintenance. Summary of the invention

[0004] The present invention aims to solve the technical problems in the prior art that electromechanical equipment maintenance has low efficiency, poor accuracy and cannot achieve accurate and directional maintenance.

[0005] In a first aspect, the present invention provides a method for directional maintenance of electromechanical equipment combined with dynamic prediction of component life, including: performing performance testing on fill light, camera and warning device in the electromechanical equipment, and performing basic life prediction to obtain fill light life information, basic camera life information and basic warning device life information;

[0006] Based on the performance parameters of the fill light, perform life impact analysis on the camera to obtain parameters affecting the camera life, and correct the basic camera life information to obtain camera life information;

[0007] Based on the performance parameters of the fill light and the camera, the life impact analysis of the warning device is performed to obtain the life impact parameters of the warning device, and the basic warning device life information is corrected to obtain the warning device life information, wherein the life impact analysis of the warning device includes performing misidentification analysis in combination with the flow information;

[0008] According to the life information of the fill light, the life information of the camera and the life information of the warning device, targeted maintenance is performed on the fill light, the camera and the warning device in the electromechanical equipment.

[0009] In a second aspect, the present invention provides a mechanical and electrical equipment directional maintenance platform combined with dynamic prediction of component life, the platform comprising:

[0010] The basic life prediction module is used to perform performance testing on the fill light, camera and warning device in the electromechanical equipment, and to perform basic life prediction to obtain the fill light life information, basic camera life information and basic warning device life information;

[0011] A camera life correction module, used to perform life impact analysis of the camera based on the performance parameters of the fill light, obtain camera life impact parameters, correct the basic camera life information, and obtain camera life information;

[0012] A warning device life correction module, based on the performance parameters of the fill light and the camera, performs a life impact analysis on the warning device, obtains a warning device life impact parameter, corrects the basic warning device life information, and obtains the warning device life information, wherein the warning device life impact analysis includes performing a misidentification analysis in combination with the flow information;

[0013] The directional maintenance module is used to perform directional maintenance on the fill light, camera and warning device in the electromechanical equipment according to the fill light life information, camera life information and warning device life information.

[0014] In a third aspect, the present invention provides an electronic device comprising: a memory for storing a computer software program; and a processor for reading and executing the computer software program, thereby implementing the first aspect of the method for targeted maintenance of electromechanical equipment combined with dynamic prediction of component life.

[0015] The present invention uses one or more of the above-mentioned technical solutions, combines the characteristics of the dynamic life influence between the parts of the electromechanical equipment, performs life prediction, realizes the precise maintenance of each key component in the electromechanical equipment, and significantly improves the efficiency and accuracy of maintenance. The technical solution detects the performance parameters of the fill light, camera and warning device, and performs basic life prediction respectively, so as to preliminarily grasp the life of each component. On this basis, the life influence relationship between the components is further considered, and the life information of the camera and the warning device is corrected by the performance parameters of the fill light and the camera, so as to more accurately reflect the actual working status of each component. In particular, in the life analysis of the warning device, by combining the flow information and the probability of misidentification for analysis, the influence of the false alarm on the life of the warning device can be considered, thereby improving the accuracy of the life prediction of the warning device. On the whole, the solution performs equipment maintenance through the prediction of life influence parameters and dynamic influence correction, realizes directional maintenance, avoids the waste of resources and inadequate maintenance of traditional regular maintenance, and avoids the problems of inaccurate maintenance and low effectiveness, and improves the service life and reliability of electromechanical equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flow chart of a method for directional maintenance of electromechanical equipment combined with dynamic prediction of component life provided by an embodiment of the present invention;

[0017] Figure 2 A schematic diagram of the structure of a mechanical and electrical equipment directional maintenance platform combined with dynamic prediction of component life provided by an embodiment of the present invention;

[0018] Figure 3 A functional block diagram of an electronic device provided by an embodiment of the present invention.

[0019] In the accompanying drawings, the components represented by the reference numerals are listed as follows:

[0020] Basic life prediction module 11, camera life correction module 12, warning device life correction module 13, directional maintenance module 14, electronic device 100, memory 110, processor 120, computer program 111. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0022] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0023] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0024] Example 1

[0025] like Figure 1 As shown, an embodiment of the present invention provides a method for directional maintenance of electromechanical equipment combined with dynamic prediction of component life, including the following steps.

[0026] S10: Performing performance testing on the fill light, camera and warning device in the electromechanical equipment, and performing basic life prediction to obtain life information of the fill light, basic camera life information and basic warning device life information;

[0027] In the embodiment of the present application, the electromechanical equipment is preferably an access control system in the prior art, which can recognize the facial image of the accessing person, unlock the door for the person who is identified as having a record (for example, a person stored in the access control database), such as opening the gate, and warn the person who is identified as having no record (for example, a stranger) to protect safety and prevent illegal entry.

[0028] The electromechanical equipment includes multiple parts, such as fill light, camera and warning device. The fill light is used to provide lighting when the light is low, so as to help the camera to collect a clearer user's facial image. The camera is used to collect the user's facial image and identify it through the algorithm in the access control system. The warning device is used to issue a warning, such as a buzzer, or a voice "stranger visit" when the facial image of the person is identified as a person who does not exist in the record.

[0029] First, the performance of the fill light, camera and warning device in the electromechanical equipment is tested. Performance testing refers to the collection of performance parameters of each component through sensors or monitoring equipment, and then a preliminary life analysis is performed on the fill light, camera and warning device to obtain fill light life information, basic camera life information and basic warning device life information. Among them, the fill light will not be affected by the camera and the warning device, and the life information obtained by analysis is directly used as the fill light life information. The life of the camera will be affected by the fill light, and the life of the warning device will be affected by the fill light and the camera. Therefore, the life information obtained by analysis is used as the basic camera life information and the basic warning device life information, pending subsequent correction.

[0030] For example, when the performance of the fill light is reduced, the camera will work under poor lighting conditions. For example, if the fill light fails, the camera needs to extend the exposure time and increase the gain to capture enough light, which will increase the power consumption of the camera and increase the temperature, affecting the life of the camera. When the performance of the fill light and the camera is reduced, the quality of the collected image will be reduced, leading to misidentification, which will cause the warning device to start up incorrectly. The start-up current impact will affect the life of the warning device, and the increase in operating time will affect the life of the warning device.

[0031] Through this process, we can obtain the life information of the fill light, basic camera and basic warning device respectively. This life information not only provides a reference for subsequent maintenance, but also serves as basic data for further analysis of the mutual influence of components, supporting more accurate maintenance decisions.

[0032] Step S10 in the method provided in the embodiment of the present application includes:

[0033] Performing performance testing on a fill light, a camera, and a warning device in the electromechanical equipment to obtain performance parameters of the fill light, the camera, and the warning device, wherein the electromechanical equipment is a door access control system;

[0034] According to the fill light performance parameters, camera performance parameters and warning device performance parameters, basic life predictions of the fill light, camera and warning device are performed respectively to obtain fill light life information, basic camera life information and basic warning device life information.

[0035] In the embodiment of the present application, the performance of the fill light, camera and warning device in the electromechanical equipment is tested to obtain their respective performance parameters. The electromechanical equipment is a door access control system, which is usually equipped with a camera for identifying people entering, a fill light for providing an auxiliary light source for the camera at night or in a low light environment, and a warning device for issuing an audible and visual alarm.

[0036] During the performance test, the key performance parameters of the fill light, camera and warning device are collected in real time through sensors or monitoring equipment. The performance parameters of the fill light include information such as its brightness, power consumption, and working current. The performance parameters of the camera include the clarity of the collected image, the image signal-to-noise ratio, and the frame rate. The performance parameters of the warning device include its warning volume and power consumption. In this way, the performance parameters of the fill light, camera and warning device are collected and obtained.

[0037] Furthermore, the performance parameters of the fill light, camera and warning device are related to their remaining operating life. For example, the better the performance parameters, the longer the life. Based on the fill light performance parameters, camera performance parameters and warning device performance parameters, basic life predictions of the fill light, camera and warning device are performed respectively to obtain fill light life information, basic camera life information and basic warning device life information. Exemplarily, basic life prediction is performed based on machine learning.

[0038] Through this step, the life information of the fill light, the basic camera and the basic warning device is finally obtained, which provides an important basis for equipment maintenance personnel to estimate the remaining life of each component, helps to formulate a reasonable time plan for subsequent precise maintenance, and improves the overall operational reliability of the equipment.

[0039] In the embodiment of the present application, according to the performance parameters of the fill light, the performance parameters of the camera and the performance parameters of the warning device, basic life predictions of the fill light, the camera and the warning device are performed respectively, including:

[0040] According to the life test record data of the fill light, camera and warning device, a sample fill light performance parameter set, a sample camera performance parameter set and a sample warning device performance parameter set are collected, and a sample fill light life information set, a sample basic camera life information set and a sample basic warning device life information set are collected, and three sets of supervised training data are obtained by combining them;

[0041] Using the three sets of supervised training data, respectively train the fill light life prediction branch, the camera life prediction branch and the warning device life prediction branch to obtain a basic life predictor;

[0042] The basic life predictor is used to perform basic life prediction on the fill light performance parameters, camera performance parameters and warning device performance parameter inputs to obtain fill light life information, basic camera life information and basic warning device life information.

[0043] In an embodiment of the present application, based on the life test record data of the fill light, camera and warning device in the past, for example, the performance of the fill light, camera and warning device is tested after different operating time, and the test data of the remaining life until failure is continued to be tested, a sample fill light performance parameter set, a sample camera performance parameter set and a sample warning device performance parameter set are collected.

[0044] Also, collect the life information of the fill light under different sample fill light performance parameters as the sample fill light life information, such as the time when the fill light continues to run until the brightness is less than 70% of its initial brightness (L70 standard) under different sample fill light performance parameters, so as to collect and obtain a sample fill light life information set. Collect the life information of the camera under different sample basic camera life information as the sample basic camera life information, such as the remaining shooting time when the camera continues to run until the frame rate drops below 10 frames / second under different sample camera performance parameters, so as to collect and obtain a sample camera performance parameter set. Collect the life information of the warning device under different sample warning device performance parameters as the sample warning device performance parameters, such as the number of remaining warnings until the warning device runs until the volume drops below 50 decibels, so as to obtain a sample basic warning device life information set.

[0045] The combined sample fill light performance parameter set is used as input data, and the sample fill light life information set is used as output supervision data; the combined sample camera performance parameter set is used as input data, and the sample basic camera life information set is used as output supervision data; the combined sample basic warning device life information set is used as input data, and the sample warning device performance parameter set is used as output supervision data to obtain three sets of supervised training data.

[0046] Three sets of supervised training data are used to train the fill light life prediction branch, camera life prediction branch and warning device life prediction branch respectively for basic life prediction.

[0047] Exemplarily, based on a feedforward neural network, a sample fill light performance parameter set and a sample fill light life information set are used to train a fill light life prediction branch. For example, based on a feedforward neural network, an input layer, a hidden layer, and an output layer of a fill light life prediction branch are constructed, the number of nodes in the input layer is the same as the number of types of fill light performance parameters, the hidden layer uses a ReLU activation function, and the number of nodes in the output layer is 1, corresponding to the fill light life information. During the training process, the fill light performance parameters are used as input, input into the input layer, and the hidden layer is gradually passed to the output layer to obtain the predicted fill light life, combined with the real sample fill light life information, the error is calculated, and according to the error, the network parameters of the fill light life prediction branch are optimized by a gradient descent algorithm to reduce the error until the requirements are met, for example, the error is less than 5%. After multiple groups of supervised training data are trained to meet the requirements, the training is completed.

[0048] Continue to use the sample camera performance parameter set and the sample warning device performance parameter set, as well as the sample basic camera life information set and the sample basic warning device life information set to train the camera life prediction branch and the warning device life prediction branch. The training process is the same as that of the fill light life prediction branch and will not be repeated here.

[0049] Based on the trained fill light life prediction branch, camera life prediction branch and warning device life prediction branch, a basic life predictor is obtained.

[0050] The fill light performance parameters, camera performance parameters and warning device performance parameters obtained from the current detection are input into the fill light life prediction branch, camera life prediction branch and warning device life prediction branch in the basic life predictor, and basic life predictions are performed respectively to obtain the fill light life information, basic camera life information and basic warning device life information.

[0051] S20: Based on the performance parameters of the fill light, perform life impact analysis on the camera to obtain camera life impact parameters, and correct the basic camera life information to obtain camera life information;

[0052] In the embodiment of the present application, the lifespan of the camera is analyzed based on the performance parameters of the fill light. The fill light is an auxiliary light source for the camera in low light or nighttime environments. The performance changes of the fill light such as brightness and power consumption may directly affect the working quality and lifespan of the camera. Specifically, the performance parameters of the fill light include indicators such as brightness attenuation and power consumption increase. If the brightness of the fill light is insufficient, the camera may need a longer exposure time when capturing an image, which will increase the sensor load and accelerate aging, thus affecting the lifespan of the camera.

[0053] By analyzing the impact of fill light performance on camera operation, we can derive parameters that affect camera life, such as the ratio of accelerated attenuation of camera life compared to normal fill light.

[0054] Based on the camera life influencing parameters, the basic camera life information is corrected to obtain more realistic camera life information of the camera under the dynamic influence of the current fill light performance parameters.

[0055] Through the above steps, the long-term impact of the fill light on the camera can be comprehensively considered, making the dynamic life prediction of the camera more accurate, providing more reliable data support for equipment maintenance, and avoiding errors caused by relying solely on the camera's own performance parameters and ignoring external influencing factors.

[0056] Step S20 in the method provided in the embodiment of the present application includes:

[0057] Based on the test data of the effect of fill light on the life of the camera, a set of sample fill light performance parameters is collected, and the life aging rate of the camera under different sample fill light performance parameters is obtained to obtain a set of sample camera life aging rate;

[0058] Constructing a mapping relationship between the sample fill light performance parameter set and the sample camera life aging rate set to obtain a camera life impact classifier;

[0059] The performance parameters of the fill light are input into the camera life impact classifier, the camera life aging rate is obtained by classification, and the basic camera life information is corrected and calculated to obtain the camera life information.

[0060] In an embodiment of the present application, based on the test data of the effect of the fill light on the life of the camera, sample data is collected. For example, based on the test of the life of the camera under different fill light performance parameters, sample data is collected. First, a set of sample fill light performance parameters is collected, which includes different sample fill light performance parameters of the fill light, such as different brightness.

[0061] Furthermore, the test collects the life aging rate of the camera under different sample fill light performance parameters. For example, when the fill light brightness decreases by 10%, the aging rate of the camera increases by 3% compared with the normal fill light, which is 103%. In this way, a set of sample camera life aging rates is collected. For another example, when the fill light is running at normal brightness (100%), the camera can work under ideal lighting conditions without increasing the exposure time or processing too much noise. Under such conditions, the expected life of the camera may be 5 years, and the life aging rate of the camera is 20% / year. When the brightness of the fill light drops to 80%, the camera needs to slightly increase the exposure time to compensate for the low light environment, resulting in a slight increase in the sensor load. Due to the deterioration of lighting conditions, the working environment of the camera is no longer ideal, and its expected life may be shortened from 5 years to 4.5 years. The life aging rate of the camera is 22% per year.

[0062] A mapping relationship between the sample fill light performance parameter set and the sample camera life aging rate set is constructed as a camera life impact classifier, wherein each sample fill light performance parameter is mapped to a corresponding camera life aging rate of the test.

[0063] The performance parameters of the current fill light are input into the camera life impact classifier, and the corresponding camera life aging rate is obtained by mapping and classifying. Among them, the sample camera life aging rate corresponding to the sample fill light performance parameter closest to the performance parameter of the current fill light in the camera life impact classifier is output to obtain the current camera life aging rate.

[0064] According to the camera life aging rate, the basic camera life information predicted in the above content is corrected and calculated. For example, the remaining camera operating time in the basic camera life information is divided by the camera life aging rate to obtain more accurate camera life information under the influence of fill light performance.

[0065] S30: Based on the performance parameters of the fill light and the camera, perform a life impact analysis of the warning device to obtain a life impact parameter of the warning device, correct the basic warning device life information to obtain the warning device life information, wherein the life impact analysis of the warning device includes performing a misidentification analysis in combination with the flow information;

[0066] In the embodiment of the present application, when the performance of the fill light and the camera is reduced, the image acquisition quality will be reduced, which may lead to misidentification, such as identifying a person with a record as a person without a record, which will lead to a false alarm of the warning device, and increase the working frequency of the warning device. The warning device may frequently trigger the alarm in the case of misidentification, and such frequent operation will shorten its lifespan, which will lead to the accelerated consumption of the lifespan of the warning device.

[0067] Therefore, based on the performance parameters of the fill light and the camera, an analysis of the impact on the life of the warning device is performed to obtain the parameters affecting the life of the warning device, such as the ratio of the increase in the number of false warnings of the warning device. Then, based on the parameters affecting the life of the warning device, a correction calculation is performed on the basic warning device life information to obtain the life information of the warning device under the influence of the performance parameters of the fill light and the camera.

[0068] Among them, in the process of analyzing the parameters affecting the life of the warning device, the ratio of the increase in the number of false alarms of the warning device is related to the personnel flow. The misidentification analysis is performed in combination with the flow information to identify the parameters affecting the life of the warning device under misidentification.

[0069] By combining the analysis of fill light, camera performance parameters and flow information, the corrected warning device life information will be more accurate and reflect the life changes in the actual working environment. This analysis process ensures that the warning device life prediction is more reliable when various devices work together and dynamically influence each other, and introduces the excessive consumption of warning device life by frequent false alarms combined with flow analysis.

[0070] Step S30 in the method provided in the embodiment of the present application includes:

[0071] Collecting multiple flow information of the electromechanical equipment within multiple historical time ranges;

[0072] Perform misidentification probability analysis based on the performance parameters of the fill light and the camera to obtain the misidentification probability;

[0073] According to the plurality of flow information, average flow information is calculated and obtained, flow stability information is calculated and analyzed, and the average flow information is corrected to obtain corrected flow information;

[0074] The false alarm ratio of the warning device is calculated based on the false recognition probability and the corrected flow information, and the basic warning device life information is corrected and calculated to obtain the warning device life information.

[0075] In the embodiment of the present application, the flow information of electromechanical equipment within multiple historical time ranges is first collected. The flow information refers to the number of people identified and entered and exited by the access control system in different time periods, such as the number of people flow from 18:00 to 24:00 in the past 30 days, as multiple flow information.

[0076] According to the performance parameters of the fill light and the camera obtained by detection, the misrecognition probability of the electromechanical equipment access control system that may be caused by the reduction in image acquisition quality is analyzed to obtain the misrecognition probability.

[0077] In the embodiment of the present application, the misidentification probability analysis is performed according to the performance parameters of the fill light and the camera to obtain the misidentification probability, including:

[0078] According to the recognition data records of the fill light and the camera, a sample fill light performance parameter set and a sample camera performance parameter set are collected, and the probability of misidentification under different sample fill light performance parameters and sample camera performance parameters is obtained to obtain a sample misidentification probability set;

[0079] Using the sample fill light performance parameter set, the sample camera performance parameter set and the sample misidentification probability set, training a misidentification probability analyzer;

[0080] The misidentification probability analyzer is used to perform misidentification probability analysis on the performance parameter inputs of the fill light and the camera to obtain the misidentification probability.

[0081] In the embodiment of the present application, based on the previous performance test parameters of the fill light and camera in the access control system of the same type of electromechanical equipment (for example, the same type of electromechanical equipment), the sample fill light performance parameter set and the sample camera performance parameter set are collected. And the probability of misidentification of the same type of access control system under different sample fill light performance parameters and sample camera performance parameters is collected to obtain a sample misidentification probability set. The probability of misidentification is, for example, calculated as the proportion of the number of misidentifications in the total number of identifications, as the sample misidentification probability, for example, 5%.

[0082] The sample fill light performance parameter set, the sample camera performance parameter set and the sample misidentification probability set are used as supervised training data to train the misidentification probability analyzer. Exemplarily, the misidentification probability analyzer is trained based on a feedforward neural network. Among them, the input data of the misidentification probability analyzer are the fill light performance parameters and the camera performance parameters, and the output data are the misidentification probability. First, based on the feedforward neural network, the input layer, hidden layer and output layer of the misidentification probability analyzer are constructed. The number of nodes in the input layer is the same as the number of parameter types of the fill light performance parameters and the camera performance parameters. The hidden layer uses the ReLU activation function, and the node of the output layer is 1, corresponding to the misidentification probability. During the training process, the sample fill light performance parameters and the sample camera performance parameters are used as inputs, input to the input layer, and the hidden layer is gradually transferred to the output layer to obtain the predicted misidentification probability. Combined with the real sample misidentification probability, the error is calculated. According to the error, the network parameters of the misidentification probability analyzer are optimized by the gradient descent algorithm to reduce the error until the requirements are met, for example, the error is less than 5%. After multiple groups of supervised training data are trained to meet the requirements, the training is completed.

[0083] Using a trained misrecognition probability analyzer, the performance parameters of the currently detected fill light and camera are input into the misrecognition probability analyzer to perform misrecognition probability analysis to obtain an output misrecognition probability, that is, the probability that the current electromechanical equipment misrecognizes a person's facial image, for example 5%.

[0084] Through the above steps, the impact of changes in fill light and camera performance on the probability of misidentification can be accurately predicted, which can then serve as a basis for analyzing the increase in the number of warning operations of the warning device caused by misidentification.

[0085] Furthermore, based on the multiple flow information, the average flow information is calculated and the stability of the multiple flow information is analyzed. The flow of people in the electromechanical equipment access control system has certain changes. By analyzing the stability, the flow stability information is obtained, and the average flow information is corrected to more accurately reflect the flow of people in the electromechanical equipment under normal conditions, and to obtain corrected flow information.

[0086] In the embodiment of the present application, according to the plurality of flow information, average flow information is calculated and obtained, flow stability information is calculated and analyzed, and the average flow information is corrected, including:

[0087] Calculate and obtain average flow information according to the plurality of flow information;

[0088] Randomly extract a number of flow information, calculate a number of flow difference ratios with the average flow information, and calculate the average to obtain the average flow difference ratio as flow stability information;

[0089] The average flow information is corrected and calculated according to the flow stability information to obtain corrected flow information.

[0090] In the embodiment of the present application, the average is calculated based on multiple flow information to obtain the average flow information of the electromechanical equipment.

[0091] Furthermore, among the multiple flow information, a number of flow information are randomly selected, for example, 5 flow information are randomly selected, and a number of flow difference ratios with the average flow information are calculated respectively, that is, the ratio of the difference between the randomly selected flow information and the average flow information to the average flow information is calculated. For example, if the average flow information is 2000 and the randomly selected flow information is 1800, the flow difference ratio is 10%.

[0092] Calculate the mean of several flow difference ratios to obtain the average flow difference ratio as the flow stability information, where the larger the average flow difference ratio, the greater the difference between the randomly selected flow information and the average flow information, and the more unstable the flow; conversely, the smaller the average flow difference ratio, the more stable the flow.

[0093] Furthermore, based on the flow stability information, the average flow information is corrected and calculated. For example, in order to prevent damage to electromechanical equipment that causes temporary unavailability and affects park operation and maintenance, the average flow information is amplified and corrected to increase the life loss of the warning device caused by misidentification, so as to avoid damage to electromechanical equipment caused by sudden excessive flow of people.

[0094] Exemplarily, the average flow information is corrected by adding 1 to the flow stability information, for example, multiplying the average flow information to obtain the corrected flow information after the correction calculation.

[0095] The corrected traffic information is more real and reliable, and takes into account the flow of people in the access control system under larger circumstances. It helps to analyze the life loss of the warning device caused by misidentification in combination with the traffic information under the probability of misidentification, and provide more accurate analysis for targeted maintenance.

[0096] Furthermore, the false alarm ratio of the warning device is calculated based on the false recognition probability and the corrected flow information. For example, the false recognition probability is multiplied by the corrected flow information to obtain the predicted false alarm flow of the warning device due to false recognition, and then the ratio of the false alarm flow to the corrected flow information is calculated as the false alarm ratio. Alternatively, the ratio of the false alarm flow information to the average flow information is used as the false alarm ratio to amplify the false alarm ratio, so as to perform targeted maintenance before the warning device runs out of service life.

[0097] The false alarm ratio is used to perform correction calculations on the basic warning device life information, for example, the basic warning device life information is divided by the sum of 1 and the false alarm ratio to obtain the remaining valid warning times of the warning device, for example, the number of warnings with a volume greater than 50 decibels, as the warning device life information.

[0098] Based on the false alarm ratio and flow correction information, more accurate information on the life of the alarm device can be obtained, reflecting the changes in its life affected by false identification and false alarms in actual use. This correction process helps to avoid premature exhaustion of equipment life due to false alarms, and conducts targeted maintenance in advance, thereby extending the actual service life of the equipment and ensuring the reliable operation of electromechanical equipment.

[0099] S40: performing targeted maintenance on the fill light, camera and warning device in the electromechanical equipment according to the fill light life information, camera life information and warning device life information.

[0100] In the embodiment of the present application, based on the obtained life information of the fill light, the life information of the camera and the life information of the warning device, targeted maintenance is performed on the fill light, the camera and the warning device in the electromechanical equipment.

[0101] For example, it is determined whether the life information of the fill light, camera and warning device reaches the life threshold of the fill light, camera and warning device, and then, based on the judgment result, targeted maintenance is performed on the fill light, camera and warning device in the electromechanical equipment. If it reaches the life threshold, targeted maintenance is performed on the fill light, camera or warning device that reaches the life threshold. If it does not reach the life threshold, operation and maintenance monitoring continues.

[0102] Exemplarily, the life threshold values ​​of the fill light, camera and warning device are, for example, that the fill light continues to operate until the brightness is less than 70% of its initial brightness for less than 24 hours, targeted maintenance is performed after the fill light life information reaches less than 24 hours, the camera continues to operate until the remaining shooting time when the frame rate drops below 10 frames per second is less than 24 hours, and the warning device operates until the number of remaining warnings before the volume drops below 50 decibels is less than 200 times.

[0103] The embodiments of the present application achieve the following technical effects through the above specific implementation methods:

[0104] The embodiment of the present application uses the above scheme to predict the life of each key component in the electromechanical equipment by combining the characteristics of the dynamic life of the components of the electromechanical equipment, thereby realizing the precise maintenance of each key component in the electromechanical equipment and significantly improving the efficiency and accuracy of maintenance. The technical scheme detects the performance parameters of the fill light, camera and warning device, and performs basic life prediction respectively, so as to preliminarily grasp the life of each component. On this basis, the life influence relationship between the components is further considered, and the life information of the camera and the warning device is corrected by using the performance parameters of the fill light and the camera, so as to more accurately reflect the actual working status of each component. In particular, in the life analysis of the warning device, by combining the flow information and the probability of misidentification for analysis, the influence of the false alarm on the life of the warning device can be considered, thereby improving the accuracy of the life prediction of the warning device. On the whole, the scheme performs equipment maintenance through the prediction of life influence parameters and dynamic influence correction, realizes directional maintenance, avoids the waste of resources and inadequate maintenance of traditional regular maintenance, and avoids the problems of inaccurate maintenance and low effectiveness, thereby improving the service life and reliability of electromechanical equipment.

[0105] Example 2

[0106] like Figure 2 As shown, based on the same inventive concept of the electromechanical equipment directional maintenance method combined with dynamic prediction of component life provided in Example 1, an embodiment of the present invention provides an electromechanical equipment directional maintenance platform combined with dynamic prediction of component life, the platform comprising:

[0107] The basic life prediction module 11 is used to perform performance testing on the fill light, camera and warning device in the electromechanical equipment, and perform basic life prediction to obtain the fill light life information, basic camera life information and basic warning device life information;

[0108] A camera life correction module 12 is used to perform a life impact analysis of the camera based on the performance parameters of the fill light, obtain camera life impact parameters, and correct the basic camera life information to obtain camera life information;

[0109] The warning device life correction module 13 performs life impact analysis of the warning device based on the performance parameters of the fill light and the camera, obtains the warning device life impact parameters, corrects the basic warning device life information, and obtains the warning device life information, wherein the warning device life impact analysis includes misidentification analysis combined with flow information;

[0110] The directional maintenance module 14 is used to perform directional maintenance on the fill light, camera and warning device in the electromechanical equipment according to the fill light life information, camera life information and warning device life information.

[0111] Furthermore, the basic life prediction module 11 is also used for:

[0112] Performing performance testing on a fill light, a camera, and a warning device in the electromechanical equipment to obtain performance parameters of the fill light, the camera, and the warning device, wherein the electromechanical equipment is a door access control system;

[0113] According to the fill light performance parameters, camera performance parameters and warning device performance parameters, basic life predictions of the fill light, camera and warning device are performed respectively to obtain fill light life information, basic camera life information and basic warning device life information.

[0114] According to the performance parameters of the fill light, the performance parameters of the camera and the performance parameters of the warning device, basic life predictions of the fill light, the camera and the warning device are performed respectively, including:

[0115] According to the life test record data of the fill light, camera and warning device, a sample fill light performance parameter set, a sample camera performance parameter set and a sample warning device performance parameter set are collected, and a sample fill light life information set, a sample basic camera life information set and a sample basic warning device life information set are collected, and three sets of supervised training data are obtained by combining them;

[0116] Using the three sets of supervised training data, respectively train the fill light life prediction branch, the camera life prediction branch and the warning device life prediction branch to obtain a basic life predictor;

[0117] The basic life predictor is used to perform basic life prediction on the fill light performance parameters, camera performance parameters and warning device performance parameter inputs to obtain fill light life information, basic camera life information and basic warning device life information.

[0118] Furthermore, the camera life correction module 12 is also used for:

[0119] Based on the test data of the effect of fill light on the life of the camera, a set of sample fill light performance parameters is collected, and the life aging rate of the camera under different sample fill light performance parameters is obtained to obtain a set of sample camera life aging rate;

[0120] Constructing a mapping relationship between the sample fill light performance parameter set and the sample camera life aging rate set to obtain a camera life impact classifier;

[0121] The performance parameters of the fill light are input into the camera life impact classifier, the camera life aging rate is obtained by classification, and the basic camera life information is corrected and calculated to obtain the camera life information.

[0122] Furthermore, the warning device life correction module 13 is also used for:

[0123] Collecting multiple flow information of the electromechanical equipment within multiple historical time ranges;

[0124] Perform misidentification probability analysis based on the performance parameters of the fill light and the camera to obtain the misidentification probability;

[0125] According to the plurality of flow information, average flow information is calculated and obtained, flow stability information is calculated and analyzed, and the average flow information is corrected to obtain corrected flow information;

[0126] The false alarm ratio of the warning device is calculated based on the false recognition probability and the corrected flow information, and the basic warning device life information is corrected and calculated to obtain the warning device life information.

[0127] The method of performing misidentification probability analysis based on the performance parameters of the fill light and the camera to obtain the misidentification probability includes:

[0128] According to the recognition data records of the fill light and the camera, a sample fill light performance parameter set and a sample camera performance parameter set are collected, and the probability of misidentification under different sample fill light performance parameters and sample camera performance parameters is obtained to obtain a sample misidentification probability set;

[0129] Using the sample fill light performance parameter set, the sample camera performance parameter set and the sample misidentification probability set, training a misidentification probability analyzer;

[0130] The misidentification probability analyzer is used to perform misidentification probability analysis on the performance parameter inputs of the fill light and the camera to obtain the misidentification probability.

[0131] The method of calculating and obtaining average flow information according to the plurality of flow information, calculating and analyzing and obtaining flow stability information, and correcting the average flow information includes:

[0132] Calculate and obtain average flow information according to the plurality of flow information;

[0133] Randomly extract a number of flow information, calculate a number of flow difference ratios with the average flow information, and calculate the average to obtain the average flow difference ratio as flow stability information;

[0134] The average flow information is corrected and calculated according to the flow stability information to obtain corrected flow information.

[0135] Furthermore, the directional maintenance module 14 is also used for:

[0136] Respectively determine whether the life information of the fill light, the life information of the camera, and the life information of the warning device have reached a life threshold;

[0137] Based on the judgment result, targeted maintenance is performed on the fill light, camera and warning device in the electromechanical equipment.

[0138] See also Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 100, including a memory 110, a processor 120, and a computer program 111 stored in the memory 110 and executable on the processor 120. When the processor 120 executes the computer program 111, the steps of the method in Example 1 are implemented.

[0139] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0140] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0141] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0142] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0143] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0144] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0145] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for directional maintenance of electromechanical equipment combined with dynamic prediction of component life, characterized in that: The method comprises: Perform performance tests on fill-in lights, cameras and warning devices in electromechanical equipment, and make basic life predictions to obtain fill-in light life information, basic camera life information and basic warning device life information; Based on the performance parameters of the fill light, perform life impact analysis on the camera to obtain parameters affecting the camera life, and correct the basic camera life information to obtain camera life information; Based on the performance parameters of the fill light and the camera, the life impact analysis of the warning device is performed to obtain the life impact parameters of the warning device, and the basic warning device life information is corrected to obtain the warning device life information, wherein the life impact analysis of the warning device includes performing misidentification analysis in combination with the flow information; According to the life information of the fill light, the life information of the camera and the life information of the warning device, targeted maintenance is performed on the fill light, the camera and the warning device in the electromechanical equipment.

2. The method for directional maintenance of electromechanical equipment combined with dynamic prediction of component life according to claim 1 is characterized in that: Perform performance tests on fill lights, cameras and warning devices in electromechanical equipment, and make basic life predictions, including: Performing performance testing on a fill light, a camera, and a warning device in the electromechanical equipment to obtain performance parameters of the fill light, the camera, and the warning device, wherein the electromechanical equipment is a door access control system; According to the fill light performance parameters, camera performance parameters and warning device performance parameters, basic life predictions of the fill light, camera and warning device are performed respectively to obtain fill light life information, basic camera life information and basic warning device life information.

3. The method for directional maintenance of electromechanical equipment combined with dynamic prediction of component life according to claim 2 is characterized in that: According to the performance parameters of the fill light, the performance parameters of the camera and the performance parameters of the warning device, basic life predictions of the fill light, the camera and the warning device are performed respectively, including: According to the life test record data of the fill light, camera and warning device, a sample fill light performance parameter set, a sample camera performance parameter set and a sample warning device performance parameter set are collected, and a sample fill light life information set, a sample basic camera life information set and a sample basic warning device life information set are collected, and three sets of supervised training data are obtained by combining them; Using the three sets of supervised training data, respectively train the fill light life prediction branch, the camera life prediction branch and the warning device life prediction branch to obtain a basic life predictor; The basic life predictor is used to perform basic life prediction on the fill light performance parameters, camera performance parameters and warning device performance parameter inputs to obtain fill light life information, basic camera life information and basic warning device life information.

4. The method for directional maintenance of electromechanical equipment combined with dynamic prediction of component life according to claim 1 is characterized in that: Based on the performance parameters of the fill light, the life impact analysis of the camera is performed to obtain the camera life impact parameters, and the basic camera life information is corrected, including: Based on the test data of the effect of fill light on the life of the camera, a set of sample fill light performance parameters is collected, and the life aging rate of the camera under different sample fill light performance parameters is obtained to obtain a set of sample camera life aging rate; Constructing a mapping relationship between the sample fill light performance parameter set and the sample camera life aging rate set to obtain a camera life impact classifier; The performance parameters of the fill light are input into the camera life impact classifier, the camera life aging rate is obtained by classification, and the basic camera life information is corrected and calculated to obtain the camera life information.

5. The method for directional maintenance of electromechanical equipment combined with dynamic prediction of component life according to claim 1 is characterized in that: Based on the performance parameters of the fill light and the camera, the life impact analysis of the warning device is performed to obtain the life impact parameters of the warning device, and the basic warning device life information is corrected, including: Collecting multiple flow information of the electromechanical equipment within multiple historical time ranges; Perform misidentification probability analysis based on the performance parameters of the fill light and the camera to obtain the misidentification probability; According to the plurality of flow information, average flow information is calculated and obtained, flow stability information is calculated and analyzed, and the average flow information is corrected to obtain corrected flow information; The false alarm ratio of the warning device is calculated based on the false recognition probability and the corrected flow information, and the basic warning device life information is corrected and calculated to obtain the warning device life information.

6. The method for directional maintenance of electromechanical equipment combined with dynamic prediction of component life according to claim 5, characterized in that: According to the performance parameters of the fill light and the camera, the misidentification probability analysis is performed to obtain the misidentification probability, including: According to the recognition data records of the fill light and the camera, a sample fill light performance parameter set and a sample camera performance parameter set are collected, and the probability of misidentification under different sample fill light performance parameters and sample camera performance parameters is obtained to obtain a sample misidentification probability set; Using the sample fill light performance parameter set, the sample camera performance parameter set and the sample misidentification probability set, training a misidentification probability analyzer; The misidentification probability analyzer is used to perform misidentification probability analysis on the performance parameter inputs of the fill light and the camera to obtain the misidentification probability.

7. The method for directional maintenance of electromechanical equipment combined with dynamic prediction of component life according to claim 5, characterized in that: According to the plurality of flow information, average flow information is calculated and obtained, flow stability information is calculated and analyzed, and the average flow information is corrected, including: Calculate and obtain average flow information according to the plurality of flow information; Randomly extract a number of flow information, calculate a number of flow difference ratios with the average flow information, and calculate the average to obtain the average flow difference ratio as flow stability information; The average flow information is corrected and calculated according to the flow stability information to obtain corrected flow information.

8. The method for directional maintenance of electromechanical equipment combined with dynamic prediction of component life according to claim 1, characterized in that: According to the life information of the fill light, the life information of the camera and the life information of the warning device, targeted maintenance is performed on the fill light, the camera and the warning device in the electromechanical equipment, including: Respectively determine whether the life information of the fill light, the life information of the camera, and the life information of the warning device have reached a life threshold; Based on the judgment result, targeted maintenance is performed on the fill light, camera and warning device in the electromechanical equipment.

9. A directional maintenance platform for electromechanical equipment combined with dynamic prediction of component life, characterized in that: The platform includes: The basic life prediction module is used to perform performance testing on the fill light, camera and warning device in the electromechanical equipment, and to perform basic life prediction to obtain the fill light life information, basic camera life information and basic warning device life information; A camera life correction module, used to perform life impact analysis of the camera based on the performance parameters of the fill light, obtain camera life impact parameters, correct the basic camera life information, and obtain camera life information; A warning device life correction module, based on the performance parameters of the fill light and the camera, performs a life impact analysis on the warning device, obtains a warning device life impact parameter, corrects the basic warning device life information, and obtains the warning device life information, wherein the warning device life impact analysis includes performing a misidentification analysis in combination with the flow information; The directional maintenance module is used to perform directional maintenance on the fill light, camera and warning device in the electromechanical equipment according to the fill light life information, camera life information and warning device life information.

10. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the method for directional maintenance of electromechanical equipment combined with dynamic prediction of component life as described in any one of claims 1-8.

Images