Device and method for displaying and alarming state of actuating mechanism of command vehicle

Abstract

The invention discloses a command vehicle actuating mechanism state display and alarm device and method, relates to the technical field of command vehicle driving safety monitoring, and solves the technical problem that the recovery efficiency of an actuating mechanism is low due to the fact that the recovery state cannot be effectively detected during recovery inspection of the actuating mechanism of a command vehicle in the prior art. Generating an irrelevant person approaching alarm signal through the category label of the surrounding detection image; generating a recovery abnormity alarm signal according to the state of the actuating mechanism; when the state of any actuating mechanism is incomplete recovery, generating a recovery abnormal coefficient according to the predicted recovery degree grade of the actuating mechanism and the recovery degree grade of the actuating mechanism; generating a comprehensive recovery anomaly coefficient according to the recovery anomaly coefficient; a corresponding alarm signal is generated according to the comprehensive recovery abnormal coefficient, the influence of surrounding personnel during recovery of the actuating mechanism is considered, and environmental factors and recovery equipment parameter factors are considered in the influence of a recovery state, so that the effectiveness judgment of recovery of the actuating mechanism is increased, and the recovery efficiency of the actuating mechanism is improved.

Description

Technical Field

[0001] The present application belongs to the technical field of command vehicle driving safety monitoring, and specifically is a command vehicle actuation mechanism status display alarm device and method. Background Art

[0002] The command vehicle is a multifunctional special vehicle that plays an important role in various fields. As a special vehicle, the command vehicle is generally equipped with a variety of detection or support equipment on the roof, body and bottom of the vehicle, such as lifting rods, lodging mechanisms, support legs, etc. Before the vehicle is driven, it is necessary to ensure that all the actuating mechanisms of the vehicle are fully recovered, otherwise it is very easy to cause damage to the actuating mechanism or the vehicle body, resulting in driving safety accidents.

[0003] At present, there are two main methods for recovery inspection of command vehicles. One is through manual inspection, which is easy to cause omissions or incomplete recovery; the other is to use software to read the current status through the data interface provided by the actuator mechanism, which increases the complexity of operation and is usually difficult to achieve complete monitoring. Both methods make it difficult to display and warn the status of the command vehicle's actuator mechanism reliably and safely. Therefore, the display and warning device for the status of the command vehicle's actuator mechanism still needs to be further improved. Summary of the invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art; to this end, the present application proposes a command vehicle actuation mechanism status display alarm device and method, which is used to solve the technical problem that the prior art fails to effectively detect the recovery status when implementing the recovery inspection of the actuation mechanism of the command vehicle, resulting in low recovery efficiency of the actuation mechanism.

[0005] To achieve the above-mentioned purpose, the first aspect of the present application provides a command vehicle actuation mechanism status display and warning device, comprising: a data acquisition device, a data analysis device, an early warning device, a display device and a database;

[0006] The data acquisition device: acquires the surrounding detection image, the state of the actuating mechanism, the actuating mechanism detection image, the recovery device parameter data and the environmental data through the data acquisition device; and performs preprocessing operations on the surrounding detection image, the actuating mechanism detection image, the recovery device parameter data and the environmental data to obtain processed surrounding detection image, the actuating mechanism detection image, the recovery device parameter data and the environmental data;

[0007] The data analysis device: inputs the surrounding detection image into the personnel detection model to obtain the category label; when the category label is an unrelated person, generates an unrelated person approaching alarm signal; otherwise, extracts the states of several actuators of the roof, body and bottom of the vehicle in turn, and generates a recovery abnormality alarm signal according to the actuator state; when the state of any actuator of the roof, body and bottom of the vehicle is not completely recovered, inputs the corresponding actuator detection image into the recovery degree detection model to obtain the corresponding actuator recovery degree level; inputs the environmental data and the recovery equipment parameter data into the corresponding recovery degree prediction model to obtain the corresponding actuator predicted recovery degree level; generates the recovery abnormality coefficient of each position according to the actuator predicted recovery degree level and the actuator recovery degree level; generates the comprehensive recovery abnormality coefficient according to the recovery abnormality coefficient of each position; generates the corresponding alarm signal according to the comprehensive recovery abnormality coefficient, the recovery abnormality coefficient and the actuator recovery degree level; otherwise, the recovery of the actuator of the command vehicle is completed, and no operation is performed;

[0008] The early warning device: gives corresponding prompts to the alarm signal and contacts relevant personnel;

[0009] The display device displays the corresponding detection images after the actuating mechanisms of the roof, the body and the bottom of the vehicle are recovered.

[0010] The present application obtains a category label by inputting surrounding detection images into a personnel detection model; when the category label is an unrelated person, an unrelated person approaching alarm signal is generated; a recovery abnormality alarm signal is generated according to the state of the actuator; when the state of any actuator of the roof, body and bottom of the vehicle is incomplete recovery, the corresponding actuator detection image is input into the recovery degree detection model to obtain the corresponding actuator recovery degree level; environmental data and recovery equipment parameter data are input into the corresponding recovery degree prediction model to obtain the corresponding actuator predicted recovery degree level; recovery abnormality coefficients of various positions are generated according to the actuator predicted recovery degree level and the actuator recovery degree level; a comprehensive recovery abnormality coefficient is generated according to the recovery abnormality coefficients of various positions; a corresponding alarm signal is generated according to the comprehensive recovery abnormality coefficient, the recovery abnormality coefficient and the actuator recovery degree level, the influence factors of surrounding personnel when the actuator of the command vehicle is recovered are taken into consideration, environmental factors and recovery equipment parameter factors are taken into consideration in the influence of the recovery state, the effectiveness judgment of the actuator recovery is increased, and the recovery efficiency of the actuator is improved.

[0011] Furthermore, the preprocessing operation includes image preprocessing and data preprocessing.

[0012] Furthermore, the personnel detection model is constructed by an artificial intelligence model, including:

[0013] Acquire a number of historical surrounding detection images and their corresponding category labels through a database; the category labels include no personnel, relevant personnel, and irrelevant personnel;

[0014] The historical surrounding detection images are divided into training data, verification data and test data according to category labels; the training data, verification data and test data are image preprocessed to obtain a training set, a verification set and a test set;

[0015] Select an AI model as the base model;

[0016] Train the basic model with the training set, and adjust the learning rate or other hyperparameters on the validation set to obtain the pre-trained model;

[0017] By verifying the pre-trained model on the test set, we finally get a person detection model that inputs surrounding detection images and outputs category labels.

[0018] The present application ensures that timely response can be made if unrelated personnel approach during the recovery by real-time detection of the surrounding conditions of the command vehicle when the actuator is recovered, thereby avoiding the possibility of causing unrelated personnel to be injured.

[0019] Furthermore, the generating of the recovery abnormality alarm signal according to the state of the actuating mechanism includes:

[0020] Sequentially extracting the states of several actuating mechanisms of the roof, the body and the bottom of the vehicle; the actuating mechanism states include fully recovered and incompletely recovered;

[0021] When the corresponding actuating mechanism is in an incompletely recovered state, a recovery abnormality alarm signal is generated;

[0022] Otherwise, do nothing.

[0023] Furthermore, the recycling degree detection model is constructed by an artificial intelligence model, including:

[0024] Obtaining a number of historical mechanism detection images and their corresponding category labels and actuating mechanism recovery degree levels through a database; the actuating mechanism recovery degree level is the corresponding actuating mechanism recovery degree, and the greater the recovery degree, the smaller the actuating mechanism recovery degree level;

[0025] The historical actuating mechanism detection images are divided into training data, verification data and test data according to the category labels and the recovery degree levels of the actuating mechanisms; the training data, verification data and test data are image preprocessed to obtain the training set, verification set and test set;

[0026] Select an AI model as the base model;

[0027] Train the basic model with the training set, and adjust the learning rate or other hyperparameters on the validation set to obtain the pre-trained model;

[0028] By verifying the pre-trained model on the test set, we finally get an input actuating mechanism detection image, and output a recovery degree detection model that is a category label and an actuating mechanism recovery degree grade.

[0029] Furthermore, the recovery degree prediction model is constructed by an artificial intelligence model, including:

[0030] Obtain historical recycling levels and their corresponding environmental data and recycling equipment parameter data;

[0031] The environmental data and the recovery equipment parameter data are divided according to the recovery degree level of the actuator to obtain training data, verification data and test data; the training data, verification data and test data are preprocessed to obtain a training set, a verification set and a test set;

[0032] Select an AI model as the base model;

[0033] Train the basic model with the training set, and adjust the learning rate or other hyperparameters on the validation set to obtain the pre-trained model;

[0034] By verifying the pre-trained model on the test set, the input environmental data and recycling equipment parameter data are finally obtained, and the output is a recycling degree prediction model that predicts the recycling degree level of the actuator.

[0035] Furthermore, the recovery anomaly coefficient of each position is generated according to the predicted recovery level of the actuating mechanism and the recovery level of the actuating mechanism, including:

[0036] Extract the predicted recovery level JYDij and the recovery level JHDij of the actuator at each position;

[0037] Calculate the actuating mechanism recovery abnormality coefficient JHYXi at the current position through the formula;

[0038] JHYXi=ki×arctan(∑αij×|JYDij-JHDij|^βij); wherein, j represents the number of the actuator that has not been fully recovered in the current position, j=1, 2,…, N; N represents the total number of the actuator that has not been fully recovered in the current position; ki is the proportional coefficient, ki∈(0,2 / π); αij is the weight coefficient, αij∈(0,1); βij is the exponential coefficient, βij∈(0,1).

[0039] Furthermore, generating a comprehensive recovery anomaly coefficient according to the recovery anomaly coefficients at each position includes:

[0040] Obtain the recovery anomaly coefficient JHYXi at each location;

[0041] The comprehensive recovery anomaly coefficient of the command vehicle is calculated by the formula ZHYX=∑(αi×JHYXi); wherein, i represents the number of each position in the command vehicle, i=1,…,M; M represents the total number of positions where the actuator in the command vehicle is recovered; αi is the weight coefficient, αi∈(0,1).

[0042] Furthermore, the generating of corresponding alarm signals according to the comprehensive recovery abnormality coefficient, the recovery abnormality coefficient and the recovery degree level of the actuating mechanism includes:

[0043] Obtaining the comprehensive recovery anomaly coefficient, the recovery anomaly coefficient and the recovery degree level of the actuating mechanism and the predicted recovery degree level of the actuating mechanism;

[0044] Determine whether the comprehensive recovery anomaly coefficient is greater than the comprehensive anomaly threshold;

[0045] Yes, generate a comprehensive failure alarm signal of the recovery equipment;

[0046] If no, determine whether the recovery anomaly coefficient of each position is greater than its corresponding recovery anomaly threshold;

[0047] If yes, a recovery equipment failure alarm signal at the corresponding position is generated;

[0048] No, determine whether the recovery degree levels of the actuators of several actuators at each position are consistent with the predicted recovery degree levels of the actuators; yes, generate a recovery device failure alarm signal for the corresponding actuator; no, do nothing.

[0049] Another aspect of the present invention provides a method for displaying and warning the state of an actuating mechanism of a command vehicle, comprising:

[0050] S0: Acquire surrounding detection images, actuator status, actuator detection images, recycling equipment parameter data and environmental data;

[0051] S1: performing a preprocessing operation on the surrounding detection image, the actuating mechanism detection image, the recovery equipment parameter data and the environmental data to obtain the processed surrounding detection image, the actuating mechanism detection image, the recovery equipment parameter data and the environmental data;

[0052] S2: Input the surrounding detection image into the person detection model to obtain the category label; determine whether the category label is an unrelated person, if yes, generate an unrelated person approaching alarm signal; if no, enter S3;

[0053] S3: extracting the states of several actuating mechanisms of the roof, body and bottom of the vehicle in sequence, and generating a recovery abnormality alarm signal according to the states of the actuating mechanisms; judging whether the states of all actuating mechanisms of the roof, body and bottom of the vehicle are fully retracted, if yes, proceed to S4; if no, proceed to S5;

[0054] S4: The command vehicle's actuating mechanism is recovered and no operation is performed;

[0055] S5: inputting the corresponding actuating mechanism detection image into the recycling degree detection model to obtain the corresponding actuating mechanism recycling degree level; inputting the environmental data and recycling equipment parameter data into the corresponding recycling degree prediction model to obtain the corresponding actuating mechanism predicted recycling degree level;

[0056] S6: generating recovery anomaly coefficients of various positions according to the predicted recovery degree level of the actuator and the recovery degree level of the actuator; generating a comprehensive recovery anomaly coefficient according to the recovery anomaly coefficients of various positions; generating a corresponding alarm signal according to the comprehensive recovery anomaly coefficient, the recovery anomaly coefficient and the recovery degree level of the actuator;

[0057] S7: Prompt the alarm signal accordingly and contact relevant personnel; and display the corresponding detection images after the actuating mechanisms of the roof, body and bottom of the vehicle are recovered.

[0058] Compared with the prior art, the beneficial effects of this application are:

[0059] 1. The present application obtains a category label by inputting surrounding detection images into a personnel detection model; when the category label is an unrelated person, an unrelated person approaching alarm signal is generated; a recovery abnormality alarm signal is generated according to the state of the actuator; when the state of any actuator of the roof, body and bottom of the vehicle is incomplete recovery, the corresponding actuator detection image is input into the recovery degree detection model to obtain the corresponding actuator recovery degree level; the environmental data and the recovery equipment parameter data are input into the corresponding recovery degree prediction model to obtain the corresponding actuator predicted recovery degree level; the recovery abnormality coefficient of each position is generated according to the actuator predicted recovery degree level and the actuator recovery degree level; the comprehensive recovery abnormality coefficient is generated according to the recovery abnormality coefficient of each position; the corresponding alarm signal is generated according to the comprehensive recovery abnormality coefficient, the recovery abnormality coefficient and the actuator recovery degree level, the influence factors of the surrounding personnel when the actuator of the command vehicle is recovered are considered, the environmental factors and the recovery equipment parameter factors are considered in the influence of the recovery state, the effectiveness judgment of the actuator recovery is increased, and the recovery efficiency of the actuator is improved.

[0060] 2. This application ensures that timely response can be made if unrelated personnel approach during the recovery by real-time detection of the surrounding conditions of the command vehicle during the recovery, thus avoiding the possibility of causing unrelated personnel to be injured. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0062] Figure 1 This is a schematic diagram of the principle of a command vehicle actuation mechanism status display and warning device of the present application;

[0063] Figure 2 This is a flow chart of a method for displaying and warning the status of an actuating mechanism of a command vehicle according to the present application. DETAILED DESCRIPTION

[0064] The technical solution of the present application will be described clearly and completely below in conjunction with the embodiments. 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 ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0065] See also Figure 1 , the first embodiment of the present application provides a command vehicle actuation mechanism state display and warning device, including: a data acquisition device, a data analysis device, an early warning device, a display device and a database;

[0066] Data acquisition device: the surrounding detection image, the state of the actuator, the actuator detection image, the recovery equipment parameter data and the environmental data are acquired through the data acquisition device; and the surrounding detection image, the actuator detection image, the recovery equipment parameter data and the environmental data are pre-processed to obtain the processed surrounding detection image, the actuator detection image, the recovery equipment parameter data and the environmental data; the data acquisition device includes a high-precision camera and corresponding sensors; the surrounding detection image refers to the image of the surroundings of the command vehicle within a certain distance; the actuator detection image refers to the image of the actuator that is not completely recovered; the recovery equipment parameter data is the parameter data related to the recovery equipment; the environmental data includes temperature, wind speed and humidity, etc.;

[0067] Data analysis device: input the surrounding detection image into the personnel detection model to obtain the category label; when the category label is an unrelated person, generate an unrelated person approaching alarm signal, which indicates that if there is an unrelated person when the actuator is recovering, the unrelated person may be injured if the recovery is continued; otherwise, extract the states of several actuators on the roof, body and bottom of the vehicle in turn, generate a recovery abnormality alarm signal according to the states of the actuators, and the recovery abnormality alarm signal indicates an alarm signal issued by the actuator for recovery to the specified position; when the state of any actuator on the roof, body and bottom of the vehicle is not completely recovered, input the corresponding actuator detection image into the recovery degree detection model to obtain the corresponding Actuator recovery degree level; input environmental data and recovery equipment parameter data into the corresponding recovery degree prediction model to obtain the corresponding actuator predicted recovery degree level; generate recovery anomaly coefficients for each position based on the actuator predicted recovery degree level and the actuator recovery degree level, the recovery anomaly coefficient is expressed as the degree of deviation between the recovery degree level and the predicted recovery degree in each position; generate a comprehensive recovery anomaly coefficient based on the recovery anomaly coefficient of each position, the comprehensive recovery anomaly coefficient is expressed as the degree of deviation of the overall recovery of the command vehicle; generate a corresponding alarm signal based on the comprehensive recovery anomaly coefficient, the recovery anomaly coefficient and the actuator recovery degree level; otherwise, the recovery of the actuator of the command vehicle is completed and no operation is performed;

[0068] Early warning device: Prompt corresponding alarm signals and contact relevant personnel; alarm signals include alarm signals of unrelated personnel approaching, alarm signals of abnormal recovery, alarm signals of comprehensive recovery equipment failure, and alarm signals of several recovery equipment failures;

[0069] Display device: displays the corresponding detection images after the actuating mechanisms of the roof, body and bottom of the vehicle are recovered.

[0070] In this embodiment, a category label is obtained by inputting surrounding detection images into a personnel detection model; when the category label is an unrelated person, an unrelated person approaching alarm signal is generated; a recovery abnormality alarm signal is generated according to the state of the actuator; when the state of any actuator of the roof, body and bottom of the vehicle is incomplete recovery, the corresponding actuator detection image is input into the recovery degree detection model to obtain the corresponding actuator recovery degree level; environmental data and recovery equipment parameter data are input into the corresponding recovery degree prediction model to obtain the corresponding actuator predicted recovery degree level; recovery abnormality coefficients of various positions are generated according to the actuator predicted recovery degree level and the actuator recovery degree level; a comprehensive recovery abnormality coefficient is generated according to the recovery abnormality coefficients of various positions; a corresponding alarm signal is generated according to the comprehensive recovery abnormality coefficient, the recovery abnormality coefficient and the actuator recovery degree level, the influence factors of surrounding personnel when the actuator of the command vehicle is recovered are considered, environmental factors and recovery equipment parameter factors are considered in the influence of the recovery state, the effectiveness judgment of the actuator recovery is increased, and the recovery efficiency of the actuator is improved.

[0071] Preprocessing operations include image preprocessing and data preprocessing;

[0072] Image preprocessing includes image denoising and image enhancement;

[0073] Image denoising: denoising is performed on the surrounding detection images and the actuator detection images, and the median filtering method is selected to remove the noise in the image to obtain the denoised image;

[0074] Image enhancement: Enhancement processing is performed on the denoised image after denoising. The clarity and contrast of the denoised image are improved by contrast enhancement method to obtain the pre-processed surrounding detection image and actuating mechanism detection image.

[0075] Data preprocessing includes data cleaning and data normalization;

[0076] Data cleaning: directly remove missing values ​​in the acquired recycling equipment parameter data and environmental data to obtain normal data;

[0077] Data normalization: Normalize the normal data using the maximum and minimum normalization method to obtain the preprocessed recycling equipment parameter data and environmental data.

[0078] The person detection model is built using an artificial intelligence model, including:

[0079] Obtain several historical surrounding detection images and their corresponding category labels through the database; the category labels include no personnel, relevant personnel and irrelevant personnel;

[0080] The historical surrounding detection images are divided into training data, verification data and test data according to the category labels; the training data, verification data and test data are image preprocessed to obtain the training set, verification set and test set; the ratio between the training set, the test set and the verification set is 7:2:1;

[0081] Select an artificial intelligence model as the basic model; the artificial intelligence model includes a convolutional neural network model, etc.;

[0082] Train the basic model with the training set, and adjust the learning rate or other hyperparameters on the validation set to obtain the pre-trained model;

[0083] By verifying the pre-trained model on the test set, we finally get a person detection model that inputs surrounding detection images and outputs category labels.

[0084] This embodiment detects the surrounding conditions of the command vehicle when it is recovering the mechanism in real time, thereby ensuring that a timely response can be made if any unrelated personnel approach during the recovery, thereby avoiding the possibility of causing unrelated personnel to be injured.

[0085] Generate recovery abnormal alarm signals according to the state of the actuator, including:

[0086] The states of several actuators of the roof, body and bottom of the vehicle are extracted in sequence; the states of the actuators include complete recovery and incomplete recovery; complete recovery means that the actuator is completely recovered to the specified position; incomplete recovery means that the actuator is not recovered or the recovery does not reach the specified position;

[0087] When the corresponding actuating mechanism is in an incompletely recovered state, a recovery abnormality alarm signal is generated;

[0088] Otherwise, do nothing.

[0089] The recycling degree detection model is constructed through an artificial intelligence model, including:

[0090] A number of historical mechanism detection images and their corresponding category labels and actuating mechanism recovery degree levels are obtained through a database; the actuating mechanism recovery degree level is the corresponding actuating mechanism recovery degree, and the greater the recovery degree, the smaller the actuating mechanism recovery degree level;

[0091] The historical actuator detection images are divided into training data, verification data and test data according to the category labels and the recovery degree levels; the training data, verification data and test data are image preprocessed to obtain the training set, verification set and test set; the ratio between the training set, the test set and the verification set is 7:2:1;

[0092] Select an artificial intelligence model as the basic model; the artificial intelligence model includes a convolutional neural network model, etc.;

[0093] Train the basic model with the training set, and adjust the learning rate or other hyperparameters on the validation set to obtain the pre-trained model;

[0094] By verifying the pre-trained model on the test set, we finally get an input actuating mechanism detection image, and output a recovery degree detection model that is a category label and an actuating mechanism recovery degree grade.

[0095] The recycling degree prediction model is constructed through artificial intelligence model, including:

[0096] Obtain historical actuator recovery level levels and their corresponding environmental data and recovery equipment parameter data;

[0097] The environmental data and the recovery equipment parameter data are divided according to the recovery degree level of the actuator to obtain training data, verification data and test data; the training data, verification data and test data are preprocessed to obtain the training set, verification set and test set; the ratio between the training set, the test set and the verification set is 7:2:1;

[0098] Select an artificial intelligence model as the basic model; the artificial intelligence model includes a neural network model, etc.;

[0099] Train the basic model with the training set, and adjust the learning rate or other hyperparameters on the validation set to obtain the pre-trained model;

[0100] By verifying the pre-trained model on the test set, the input environmental data and recycling equipment parameter data are finally obtained, and the output is a recycling degree prediction model that predicts the recycling degree level of the actuator.

[0101] The recovery anomaly coefficients of various positions are generated according to the predicted recovery level of the actuator and the recovery level of the actuator, including:

[0102] Extract the predicted recovery level JYDij and the recovery level JHDij of the actuator at each position;

[0103] Calculate the actuating mechanism recovery abnormality coefficient JHYXi at the current position through the formula;

[0104] JHYXi=ki×arctan(∑αij×|JYDij-JHDij|^βij); wherein, j represents the number of the actuator that has not been fully recovered in the current position, j=1, 2,…, N; N represents the total number of the actuator that has not been fully recovered in the current position; ki is the proportional coefficient, ki∈(0,2 / π), the specific value is set according to experience, and the setting of ki is to make JKYXi∈(0,1); αij is the weight coefficient, αij∈(0,1), the specific value is set according to experience; βij is the exponential coefficient, βij∈(0,1), the specific value is set according to experience; the greater the deviation between the current actuator recovery level and the actuator predicted recovery level, the worse the recovery effect of the current actuator, which in turn leads to an increase in the current actuator recovery abnormality coefficient.

[0105] Generate a comprehensive recovery anomaly coefficient based on the recovery anomaly coefficients of each location, including:

[0106] Obtain the recovery anomaly coefficient JHYXi at each location;

[0107] The comprehensive recovery anomaly coefficient of the command vehicle is calculated by the formula ZHYX=∑(αi×JHYXi); wherein, i represents the number of each position in the command vehicle, i=1,…,M; M represents the total number of positions for the recovery of the actuating mechanism in the command vehicle; αi is the weight coefficient, αi∈(0,1), and the specific value is set based on experience; as the recovery anomaly coefficient of the actuating mechanism at each position increases, the recovery effect of the overall actuating mechanism of the command vehicle becomes worse and worse, and therefore the comprehensive recovery anomaly coefficient will also increase accordingly.

[0108] Generate corresponding alarm signals according to the comprehensive recovery abnormality coefficient, recovery abnormality coefficient and recovery degree level of the actuator, including:

[0109] Obtaining the comprehensive recovery anomaly coefficient, the recovery anomaly coefficient and the recovery degree level of the actuating mechanism and the predicted recovery degree level of the actuating mechanism;

[0110] Determine whether the comprehensive recovery anomaly coefficient is greater than the comprehensive anomaly threshold; the comprehensive anomaly threshold is set based on experience

[0111] Yes, generate a comprehensive failure alarm signal of the recovery equipment;

[0112] No, determine whether the recovery anomaly coefficient of each position is greater than its corresponding recovery anomaly threshold; the corresponding recovery anomaly threshold is set based on experience;

[0113] If yes, a recovery equipment failure alarm signal at the corresponding position is generated;

[0114] No, determine whether the recovery degree levels of the actuators of several actuators at each position are consistent with the predicted recovery degree levels of the actuators; yes, generate a recovery device failure alarm signal for the corresponding actuator; no, do nothing.

[0115] See also Figure 2 In another aspect, an embodiment of the present application provides a method for displaying and warning the state of an actuating mechanism of a command vehicle, comprising:

[0116] S0: Acquire surrounding detection images, actuator status, actuator detection images, recycling equipment parameter data and environmental data;

[0117] S1: performing a preprocessing operation on the surrounding detection image, the actuating mechanism detection image, the recovery equipment parameter data and the environmental data to obtain the processed surrounding detection image, the actuating mechanism detection image, the recovery equipment parameter data and the environmental data;

[0118] S2: Input the surrounding detection image into the person detection model to obtain the category label; determine whether the category label is an unrelated person; if yes, generate an unrelated person approaching alarm signal; if no, enter S3;

[0119] S3: extracting the states of several actuating mechanisms of the roof, body and bottom of the vehicle in sequence, and generating a recovery abnormality alarm signal according to the states of the actuating mechanisms; judging whether the states of all actuating mechanisms of the roof, body and bottom of the vehicle are fully retracted, if yes, proceed to S4; if no, proceed to S5;

[0120] S4: The command vehicle's actuating mechanism is recovered and no operation is performed;

[0121] S5: inputting the corresponding actuating mechanism detection image into the recycling degree detection model to obtain the corresponding actuating mechanism recycling degree level; inputting the environmental data and recycling equipment parameter data into the corresponding recycling degree prediction model to obtain the corresponding actuating mechanism predicted recycling degree level;

[0122] S6: generating recovery anomaly coefficients of various positions according to the predicted recovery degree level of the actuator and the recovery degree level of the actuator; generating a comprehensive recovery anomaly coefficient according to the recovery anomaly coefficients of various positions; generating a corresponding alarm signal according to the comprehensive recovery anomaly coefficient, the recovery anomaly coefficient and the recovery degree level of the actuator;

[0123] S7: Prompt the alarm signal accordingly and contact relevant personnel; and display the corresponding detection images after the actuating mechanisms of the roof, body and bottom of the vehicle are recovered.

[0124] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0125] The working principle of the present application is as follows: by acquiring surrounding detection images, actuator status, actuator detection images, recovery equipment parameter data and environmental data; and pre-processing the surrounding detection images, actuator detection images, recovery equipment parameter data and environmental data to obtain processed surrounding detection images, actuator detection images, recovery equipment parameter data and environmental data; inputting the surrounding detection images into the personnel detection model to obtain the category label; when the category label is an unrelated person, generating an unrelated person approaching alarm signal; otherwise, generating a recovery abnormality alarm signal according to the actuator status; when the status of any actuator of the roof, body and bottom of the vehicle is not fully recovered, inputting the corresponding actuator detection image into the recovery degree detection model to obtain the corresponding actuator recovery degree level; inputting the environmental data and recovery equipment parameter data into the corresponding recovery degree prediction model to obtain the corresponding actuator prediction The recovery degree level is as follows: generating a recovery anomaly coefficient for each position according to the predicted recovery degree level of the actuator and the recovery degree level of the actuator; generating a comprehensive recovery anomaly coefficient according to the recovery anomaly coefficient of each position; generating a corresponding alarm signal according to the comprehensive recovery anomaly coefficient, the recovery anomaly coefficient and the recovery degree level of the actuator; otherwise, the recovery of the actuator of the command vehicle is completed and no operation is performed; making corresponding prompts for the alarm signal and contacting relevant personnel; and displaying the detection image after the recovery of the actuator, considering the influence of the surrounding personnel when the actuator of the command vehicle is recovered, and considering the environmental factors and the recovery equipment parameter factors in the influence of the recovery state, thereby increasing the effectiveness judgment of the recovery of the actuator, improving the recovery efficiency of the actuator, and avoiding the problem that the existing technology fails to effectively detect the recovery state when realizing the recovery inspection of the actuator of the command vehicle, resulting in low recovery efficiency of the actuator.

[0126] The above embodiments are only used to illustrate the technical method of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical method of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present application.

Claims

1. A command vehicle actuation mechanism status display and warning device, characterized in that: include: Data collection device, data analysis device, early warning device, display device and database; The data acquisition device: acquires the surrounding detection image, the state of the actuating mechanism, the actuating mechanism detection image, the recovery device parameter data and the environmental data through the data acquisition device; and performs preprocessing operations on the surrounding detection image, the actuating mechanism detection image, the recovery device parameter data and the environmental data to obtain processed surrounding detection image, the actuating mechanism detection image, the recovery device parameter data and the environmental data; The data analysis device: inputs the surrounding detection image into the personnel detection model to obtain the category label; when the category label is an unrelated person, generates an unrelated person approaching alarm signal; otherwise, extracts the states of several actuators of the roof, body and bottom of the vehicle in turn, and generates a recovery abnormality alarm signal according to the actuator state; when the state of any actuator of the roof, body and bottom of the vehicle is not completely recovered, inputs the corresponding actuator detection image into the recovery degree detection model to obtain the corresponding actuator recovery degree level; inputs the environmental data and the recovery equipment parameter data into the corresponding recovery degree prediction model to obtain the corresponding actuator predicted recovery degree level; generates the recovery abnormality coefficient of each position according to the actuator predicted recovery degree level and the actuator recovery degree level; generates the comprehensive recovery abnormality coefficient according to the recovery abnormality coefficient of each position; generates the corresponding alarm signal according to the comprehensive recovery abnormality coefficient, the recovery abnormality coefficient and the actuator recovery degree level; otherwise, the recovery of the actuator of the command vehicle is completed, and no operation is performed; The early warning device: gives corresponding prompts to the alarm signal and contacts relevant personnel; The display device displays the corresponding detection images after the actuating mechanisms of the roof, the body and the bottom of the vehicle are recovered.

2. A command vehicle actuation mechanism status display and warning device according to claim 1, characterized in that: The preprocessing operation includes image preprocessing and data preprocessing.

3. The command vehicle actuation mechanism status display and warning device according to claim 1 is characterized in that: The personnel detection model is constructed by an artificial intelligence model, including: Acquire a number of historical surrounding detection images and their corresponding category labels through a database; the category labels include no personnel, relevant personnel, and irrelevant personnel; The historical surrounding detection images are divided into training data, verification data and test data according to category labels; the training data, verification data and test data are image preprocessed to obtain a training set, a verification set and a test set; Select an AI model as the base model; Train the basic model with the training set, and adjust the learning rate or other hyperparameters on the validation set to obtain the pre-trained model; By verifying the pre-trained model on the test set, we finally get a person detection model that inputs surrounding detection images and outputs category labels.

4. The command vehicle actuation mechanism status display and warning device according to claim 1, characterized in that: The generating of the recovery abnormality alarm signal according to the state of the actuating mechanism comprises: Sequentially extracting the states of several actuating mechanisms of the roof, the body and the bottom of the vehicle; the actuating mechanism states include fully recovered and incompletely recovered; When the corresponding actuating mechanism is in an incompletely recovered state, a recovery abnormality alarm signal is generated; Otherwise, do nothing.

5. The command vehicle actuation mechanism status display and warning device according to claim 1 is characterized in that: The recovery degree prediction model is constructed by an artificial intelligence model, including: Obtain historical recycling levels and their corresponding environmental data and recycling equipment parameter data; The environmental data and the recovery equipment parameter data are divided according to the recovery degree level of the actuator to obtain training data, verification data and test data; the training data, verification data and test data are preprocessed to obtain a training set, a verification set and a test set; Select an AI model as the base model; Train the basic model with the training set, and adjust the learning rate or other hyperparameters on the validation set to obtain the pre-trained model; By verifying the pre-trained model on the test set, the input environmental data and recycling equipment parameter data are finally obtained, and the output is a recycling degree prediction model that predicts the recycling degree level of the actuator.

6. The command vehicle actuation mechanism status display and warning device according to claim 1, characterized in that: The generating of the recovery anomaly coefficient of each position according to the predicted recovery degree level of the actuating mechanism and the recovery degree level of the actuating mechanism comprises: Extract the predicted recovery level JYDij and the recovery level JHDij of the actuator at each position; Calculate the actuating mechanism recovery abnormality coefficient JHYXi at the current position through the formula; JHYXi=ki×arctan(∑αij×|JYDij-JHDij|^βij); wherein, j represents the number of the actuator that has not been fully recovered in the current position, j=1, 2,…, N; N represents the total number of the actuator that has not been fully recovered in the current position; ki is the proportional coefficient, ki∈(0,2 / π); αij is the weight coefficient, αij∈(0,1); βij is the exponential coefficient, βij∈(0,1).

7. The command vehicle actuation mechanism status display and warning device according to claim 1 is characterized in that: The step of generating a comprehensive recovery anomaly coefficient according to the recovery anomaly coefficients at each position includes: Obtain the recovery anomaly coefficient JHYXi at each location; The comprehensive recovery anomaly coefficient of the command vehicle is calculated by the formula ZHYX=∑(αi×JHYXi); wherein, i represents the number of each position in the command vehicle, i=1,…,M; M represents the total number of positions where the actuator in the command vehicle is recovered; αi is the weight coefficient, αi∈(0,1).

8. The command vehicle actuation mechanism status display and warning device according to claim 1 is characterized in that: The generating of corresponding alarm signals according to the comprehensive recovery abnormality coefficient, the recovery abnormality coefficient and the recovery degree level of the actuating mechanism includes: Obtaining the comprehensive recovery anomaly coefficient, the recovery anomaly coefficient and the recovery degree level of the actuating mechanism and the predicted recovery degree level of the actuating mechanism; Determine whether the comprehensive recovery anomaly coefficient is greater than the comprehensive anomaly threshold; Yes, generate a comprehensive failure alarm signal of the recovery equipment; If no, determine whether the recovery anomaly coefficient of each position is greater than its corresponding recovery anomaly threshold; If yes, a recovery equipment failure alarm signal at the corresponding position is generated; No, determine whether the recovery degree levels of the actuators of several actuators at each position are consistent with the predicted recovery degree levels of the actuators; yes, generate a recovery device failure alarm signal for the corresponding actuator; no, do nothing.

9. A command vehicle actuation mechanism status display and warning method, applied to a command vehicle actuation mechanism status display and warning device according to any one of claims 1 to 8, characterized in that: include: S0: Acquire surrounding detection images, actuator status, actuator detection images, recycling equipment parameter data and environmental data; S1: performing a preprocessing operation on the surrounding detection image, the actuating mechanism detection image, the recovery equipment parameter data and the environmental data to obtain the processed surrounding detection image, the actuating mechanism detection image, the recovery equipment parameter data and the environmental data; S2: Input the surrounding detection image into the person detection model to obtain the category label; determine whether the category label is an unrelated person, if yes, generate an unrelated person approaching alarm signal; if no, enter S3; S3: extracting the states of several actuating mechanisms of the roof, body and bottom of the vehicle in sequence, and generating a recovery abnormality alarm signal according to the states of the actuating mechanisms; judging whether the states of all actuating mechanisms of the roof, body and bottom of the vehicle are fully retracted, if yes, proceed to S4; if no, proceed to S5; S4: The command vehicle's actuating mechanism is recovered and no operation is performed; S5: inputting the corresponding actuating mechanism detection image into the recycling degree detection model to obtain the corresponding actuating mechanism recycling degree level; inputting the environmental data and recycling equipment parameter data into the corresponding recycling degree prediction model to obtain the corresponding actuating mechanism predicted recycling degree level; S6: generating recovery anomaly coefficients of various positions according to the predicted recovery degree level of the actuator and the recovery degree level of the actuator; generating a comprehensive recovery anomaly coefficient according to the recovery anomaly coefficients of various positions; generating a corresponding alarm signal according to the comprehensive recovery anomaly coefficient, the recovery anomaly coefficient and the recovery degree level of the actuator; S7: Prompt the alarm signal accordingly and contact relevant personnel; and display the corresponding detection images after the actuating mechanisms of the roof, body and bottom of the vehicle are recovered.

Images