Industrial vehicle edge gateway system based on 5G RedCap module

Abstract

The invention provides an industrial vehicle edge gateway system based on a 5G RedCap module, and the system comprises an industrial sensor which is used for collecting the operation data of an industrial vehicle and the environment data of the industrial vehicle; the local storage unit is used for carrying out localized storage on the operation data of the industrial vehicle and the environment data of the industrial vehicle; the edge calculation unit is used for determining operation state data of the industrial vehicle according to the operation data of the industrial vehicle and the environment data of the industrial vehicle so as to generate a risk avoiding strategy for the industrial vehicle; and the data uploading unit is used for uploading the operation data of the industrial vehicle, the environment data of the industrial vehicle, the operation state data of the industrial vehicle and the risk avoiding strategy of the industrial vehicle to a cloud platform, wherein the operation data, the environment data, the operation state data and the risk avoiding strategy are stored in the local storage unit.

Description

Technical Field

[0001] The present application relates to the fields of Industrial Internet of Things (AIoT) and intelligent traffic management, and in particular to an industrial vehicle edge gateway system based on a 5GRedCap module. Background Art

[0002] With the rapid development of the logistics and warehousing industries, industrial vehicles such as forklifts and transporters are widely used in various operating scenarios. However, traditional vehicle management systems have many shortcomings, including large communication delays, weak data processing capabilities, and inability to monitor vehicle status in real time. These problems directly affect the operating efficiency and safety of industrial vehicles, especially in complex working environments, where traditional systems are difficult to meet the growing demand for real-time monitoring.

[0003] Currently, there is a lack of mature solutions for industrial vehicle application scenarios in the market. There is an urgent need for an edge gateway system that can fully utilize the advantages of the 5G RedCap module to enhance the real-time monitoring and management capabilities of industrial vehicles. Summary of the invention

[0004] The purpose of this application is to propose an industrial vehicle edge gateway system based on a 5G RedCap module to solve or alleviate the technical problems existing in the prior art.

[0005] An industrial vehicle edge gateway system based on a 5G RedCap module, comprising:

[0006] Industrial sensors for collecting operating data of industrial vehicles and environmental data of said industrial vehicles;

[0007] A local storage unit, used for locally storing the operation data of the industrial vehicle and the environmental data of the industrial vehicle;

[0008] The edge computing unit is used to determine the operation status data of the industrial vehicle according to the operation data of the industrial vehicle and the environmental data of the industrial vehicle, so as to generate a risk avoidance strategy for the industrial vehicle:

[0009] The 5G RedCap module is used to upload the operation data of the industrial vehicle, the environmental data of the industrial vehicle, the operation status data of the industrial vehicle, and the risk avoidance strategy of the industrial vehicle stored in the local storage unit to the cloud platform.

[0010] Optionally, the edge computing unit performs the following steps to generate a risk avoidance strategy for the industrial vehicle:

[0011] Determining whether the industrial vehicle has a safety risk according to the operation status data;

[0012] When there is a safety risk to the industrial vehicle, a remote control instruction is generated and transmitted to the control system of the industrial vehicle to adjust the output of the control system and perform emergency braking or automatic deceleration on the industrial vehicle accordingly.

[0013] Optionally, the industrial vehicle edge gateway system based on the 5G RedCap module also includes: a multi-interface module, the multi-interface includes multiple industrial communication interfaces, the multiple industrial communication interfaces include at least: a CAN bus interface, an RS485 interface, and an RS232 interface, the CAN bus interface is used to connect the industrial sensor to the control system of the industrial vehicle to collect the operating data of the industrial vehicle, the RS485 interface is used to enable the industrial sensor to collect the environmental data of the industrial vehicle, and the RS232 interface is used to enable the industrial sensor to collect the location data of the industrial vehicle.

[0014] Optionally, the industrial sensor includes an operation data sensor and an environmental sensor. The operation data sensor is at least one of a speed sensor, an acceleration sensor, an attitude angle sensor, and a position sensor, and is used to collect at least one of the speed data, acceleration data, attitude angle data, and position data of the industrial vehicle. The environmental sensor is a temperature sensor and a humidity sensor, and is used to collect at least one of the temperature data and humidity data of the environment in which the industrial vehicle is located.

[0015] Optionally, the operating status detection model includes at least one of a posture detection model, an abnormality recognition model, and an energy consumption monitoring model. The posture detection model determines the operating posture of the industrial vehicle based on the operating data of the industrial vehicle, and the operating posture includes at least one of the tilt angle and the roll angle of the industrial vehicle; the abnormality recognition model determines whether the industrial vehicle is in an abnormal state based on the operating data of the industrial vehicle and the environmental data of the industrial vehicle. The energy consumption monitoring model is used to monitor the energy consumption of the industrial vehicle based on the operating data of the industrial vehicle and the environmental data of the industrial vehicle, including at least one of the remaining battery power and the real-time power consumption.

[0016] Optionally, the posture detection model performs the following steps to determine the working posture of the industrial vehicle according to the operation data of the industrial vehicle:

[0017] Extracting characteristic variables from the operation data of the industrial vehicle to construct a corresponding covariance matrix;

[0018] Determine the eigenvalues ​​and eigenvectors of the covariance matrix corresponding to the operation data of the industrial vehicle;

[0019] For the operation data of the industrial vehicle, according to the size of the corresponding eigenvalues, select the eigenvectors corresponding to the first several largest eigenvalues ​​as the principal components of the operation data of the industrial vehicle, so as to construct a low-dimensional space representation of the operation data of the industrial vehicle;

[0020] Based on the trained clustering model, cluster analysis is performed on the low-dimensional space representation of the operation data of the industrial vehicle to obtain an operation posture label, so as to determine the operation posture of the industrial vehicle.

[0021] Optionally, the abnormality recognition model is used to perform the following steps to determine whether the industrial vehicle is in an abnormal state according to the operation data of the industrial vehicle and the environmental data of the industrial vehicle:

[0022] Serializing the operation data of the industrial vehicle and the environmental data of the industrial vehicle to obtain an operation time series and an environmental time series;

[0023] Performing unsupervised feature fusion with piece-by-piece contrast loss on the running time series and the environment time series to obtain cross-domain fusion features;

[0024] Performing probability density statistics on the cross-domain fusion features to generate a probability density value;

[0025] The probability density value is compared with a set probability density threshold to determine whether the industrial vehicle is in an abnormal state.

[0026] Optionally, the energy consumption monitoring model is used to perform the following steps to monitor the energy consumption of the industrial vehicle according to the operation data of the industrial vehicle and the environmental data of the industrial vehicle:

[0027] Energy consumption characteristics are extracted from the operation data of the industrial vehicle and the environmental data of the industrial vehicle, and characteristics of a direct correlation between the rate of change of speed and the power consumption of the motor, characteristics of a direct correlation between changes in acceleration and attitude angle and the resistance and efficiency of the vehicle, and characteristics of a direct correlation between temperature and humidity and the capacity attenuation adjustment of the battery and the change in internal resistance are obtained;

[0028] According to the direct correlation characteristics between the speed change rate and the power consumption of the motor, the direct correlation characteristics between the changes in acceleration and attitude angle and the resistance and efficiency of the vehicle, the direct correlation adjustment between temperature and humidity and the capacity attenuation of the battery, and the direct correlation characteristics between the internal resistance change, the real-time power consumption of the motor and the real-time resistance of the vehicle are calculated;

[0029] The total energy consumption of the vehicle is calculated according to the real-time power consumption of the motor and the real-time resistance of the vehicle, so as to monitor the energy consumption of the industrial vehicle.

[0030] Optionally, the industrial vehicle edge gateway system based on the 5G RedCap module includes an encryption unit for encrypting the operating data of the industrial vehicle and the environmental data of the industrial vehicle to obtain ciphertext data; correspondingly, the local storage unit locally stores the ciphertext data corresponding to the operating data of the industrial vehicle and the environmental data of the industrial vehicle.

[0031] Optionally, when the encryption unit encrypts the operating data of the industrial vehicle and the environmental data of the industrial vehicle, it rates the sensitivity of the operating data of the industrial vehicle and the environmental data of the industrial vehicle, so that if the sensitivity level is greater than a set sensitivity threshold, the data is encrypted using field encryption, and if the sensitivity level is less than or equal to the set sensitivity threshold, the data is encrypted using data block or file level.

[0032] The solution provided in the embodiment of the present application significantly improves the real-time monitoring and management capabilities of industrial vehicles by integrating the 5G RedCap module into the industrial vehicle edge gateway system, which is specifically reflected in the following aspects:

[0033] (1) High-speed and low-latency data transmission:

[0034] As a subset of 5G technology, the 5G RedCap (Reduced Capability) module is designed for Internet of Things (IoT) devices and has the characteristics of high speed and low latency. This feature enables the operation data, environmental data, operation status data and risk avoidance strategies of industrial vehicles to be transmitted to the cloud platform in real time and quickly through the 5G network. Compared with traditional communication methods (such as Wi-Fi, 4G, etc.), 5G RedCap greatly reduces the delay of data transmission, ensures the immediacy and accuracy of data, and provides strong technical support for real-time monitoring.

[0035] (2) Enhanced data processing capabilities:

[0036] The edge computing unit performs preliminary processing and analysis on the collected data locally to generate the operating status data and risk avoidance strategies of industrial vehicles. This "edge computing + cloud processing" architecture not only reduces the processing pressure of the cloud platform, but also improves the response speed of the system. The edge computing unit can quickly identify abnormal situations and make preliminary responses, effectively improving the real-time processing capability and intelligence level of the system.

[0037] (3) Comprehensive data collection and storage:

[0038] Industrial sensors are widely deployed in industrial vehicles and their surroundings, and can comprehensively and accurately collect vehicle operation data and environmental data. These data are stored locally through local storage units, which not only provides a rich data source for real-time analysis and processing, but also ensures the security and traceability of the data. Even in the case of network instability or interruption, the locally stored data can still support a certain degree of offline analysis and decision-making.

[0039] (4) Intelligent hedging strategy generation:

[0040] Based on the processing and analysis of data by the edge computing unit, the system can evaluate the operating status of industrial vehicles in real time and generate risk avoidance strategies based on the evaluation results. These strategies are designed to prevent potential safety risks, improve operating efficiency, and ensure the safety of personnel and vehicles. Through intelligent risk avoidance strategies, the system can automatically adjust vehicle behavior or issue warnings to operators, thereby achieving refined management of industrial vehicles.

[0041] (5) Collaborative management of cloud platforms:

[0042] The 5G RedCap module uploads the processed data to the cloud platform in a timely manner, allowing managers to remotely monitor the real-time status of industrial vehicles and centrally manage and dispatch vehicles. The cloud platform also has functions such as data analysis and report generation to provide decision support for management. This collaborative working mode of the cloud and the edge makes the monitoring and management of industrial vehicles more efficient and convenient. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Hereinafter, some specific embodiments of the present application will be described in detail in an exemplary and non-limiting manner with reference to the accompanying drawings. The same reference numerals in the accompanying drawings indicate the same or similar components or parts. It should be understood by those skilled in the art that these drawings are not necessarily drawn to scale. In the accompanying drawings:

[0044] Figure 1 This is a structural schematic diagram of an industrial vehicle edge gateway system based on a 5G RedCap module according to an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings 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. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the embodiments of the present application should fall within the scope of protection of the embodiments of the present application.

[0046] Figure 1This is a schematic diagram of the structure of an industrial vehicle edge gateway system based on a 5G RedCap module according to an embodiment of the present application. Figure 1 As shown, it includes:

[0047] Industrial sensors for collecting operating data of industrial vehicles and environmental data of said industrial vehicles;

[0048] A local storage unit, used for locally storing the operation data of the industrial vehicle and the environmental data of the industrial vehicle;

[0049] The edge computing unit is used to determine the operation status data of the industrial vehicle according to the operation data of the industrial vehicle and the environmental data of the industrial vehicle, so as to generate a risk avoidance strategy for the industrial vehicle:

[0050] The 5G RedCap module is used to upload the operation data of the industrial vehicle, the environmental data of the industrial vehicle, the operation status data of the industrial vehicle, and the risk avoidance strategy of the industrial vehicle stored in the local storage unit to the cloud platform.

[0051] In the field of industrial vehicle monitoring and management, this solution achieves high-speed and low-latency data transmission by integrating the 5G RedCap module. Combined with the enhanced data processing capabilities of the edge computing unit, it realizes the comprehensive collection, real-time processing and local storage of industrial vehicle operation data and environmental data. The real-time generation and response of intelligent risk avoidance strategies ensure the safety and efficiency of industrial vehicle operations. At the same time, the collaborative management of the cloud platform provides solid support for remote monitoring, centralized scheduling and intelligent decision-making of data.

[0052] Optionally, the edge computing unit performs the following steps to generate a risk avoidance strategy for the industrial vehicle:

[0053] Determining whether the industrial vehicle has a safety risk according to the operation status data;

[0054] When there is a safety risk to the industrial vehicle, a remote control instruction is generated and transmitted to the control system of the industrial vehicle to adjust the output of the control system and perform emergency braking or automatic deceleration on the industrial vehicle accordingly.

[0055] For example, in some cases, the edge computing unit may take a series of measures to generate a risk avoidance strategy for industrial vehicles. First, the edge computing unit uses the collected operation status data to conduct a detailed analysis of the current operating status of the industrial vehicle. With this data, the edge computing unit can determine whether there are potential safety risks for the industrial vehicle. For example, it can detect whether the vehicle is speeding too fast, whether it has deviated from the predetermined driving path, or whether there are other factors that may cause an accident.

[0056] Once the edge computing unit determines that an industrial vehicle presents a safety risk, it immediately takes action to ensure the safety of the vehicle and the surrounding environment. Specifically, the edge computing unit generates a series of remote control instructions that are designed to intervene in the control system of the industrial vehicle. These instructions are quickly transmitted to the control system of the industrial vehicle so that the operating status of the vehicle can be adjusted in real time.

[0057] In this way, the edge computing unit can precisely control the control system output of the industrial vehicle, thereby achieving emergency braking or automatic deceleration of the vehicle. For example, if an obstacle is detected ahead, the edge computing unit will send an emergency braking command to stop the vehicle quickly to avoid a collision. Similarly, if the vehicle is moving too fast, the edge computing unit will send a deceleration command to gradually slow the vehicle down until it reaches a safe speed.

[0058] Optionally, the industrial vehicle edge gateway system based on the 5G RedCap module also includes: a multi-interface module, the multi-interface includes multiple industrial communication interfaces, the multiple industrial communication interfaces include at least: a CAN bus interface, an RS485 interface, and an RS232 interface, the CAN bus interface is used to connect the industrial sensor to the control system of the industrial vehicle to collect the operating data of the industrial vehicle, the RS485 interface is used to enable the industrial sensor to collect the environmental data of the industrial vehicle, and the RS232 interface is used to enable the industrial sensor to collect the location data of the industrial vehicle.

[0059] In the present invention, the industrial vehicle edge gateway system based on the 5G RedCap module may further include a multifunctional multi-interface module. This multi-interface module has multiple industrial communication interfaces that can meet the communication needs in different industrial scenarios. Specifically, these industrial communication interfaces include at least: CAN bus interface, RS485 interface and RS232 interface.

[0060] CAN bus interface is a communication protocol widely used in the field of industrial automation. It can achieve high reliability and real-time data transmission. In this system, CAN bus interface is mainly used to connect industrial sensors with the control system of industrial vehicles, so as to realize real-time collection of industrial vehicle operation data. These operation data include but are not limited to key parameters such as speed, temperature, pressure, etc., which are essential for monitoring and optimizing the performance of industrial vehicles.

[0061] The RS485 interface is a serial communication interface that is widely used in industrial environments, especially in scenarios where long-distance transmission and multi-device connection are required. In this system, the RS485 interface is used to connect industrial sensors to collect environmental data around industrial vehicles. These environmental data may include temperature, humidity, light intensity, etc., which are important for ensuring the reliable operation of industrial vehicles in specific environments.

[0062] RS232 is a traditional serial communication interface. Although its transmission rate and distance are not as good as RS485, it still has its unique advantages in some specific application scenarios. In this system, RS232 is used to connect industrial sensors to collect the location data of industrial vehicles. These location data include but are not limited to information such as latitude, longitude, and altitude, which are essential for achieving accurate navigation and positioning functions.

[0063] Optionally, the industrial sensor includes an operation data sensor and an environmental sensor. The operation data sensor is at least one of a speed sensor, an acceleration sensor, an attitude angle sensor, and a position sensor, and is used to collect at least one of the speed data, acceleration data, attitude angle data, and position data of the industrial vehicle. The environmental sensor is a temperature sensor and a humidity sensor, and is used to collect at least one of the temperature data and humidity data of the environment in which the industrial vehicle is located.

[0064] In some embodiments, the operation data sensor is mainly used to monitor the operation status of the industrial vehicle, including but not limited to key parameters such as speed, acceleration, attitude angle and position. For example, the speed sensor can measure the vehicle's driving speed in real time, the acceleration sensor can monitor the acceleration change of the vehicle during movement, the attitude angle sensor can provide the vehicle's tilt angle information in three-dimensional space, and the position sensor can determine the precise position of the vehicle in a specific area. The combined use of these sensors can provide comprehensive and detailed data support for the vehicle's operation status.

[0065] Environmental sensors, on the other hand, focus on monitoring the external environmental conditions of industrial vehicles. These sensors mainly include temperature sensors and humidity sensors. Temperature sensors can monitor and record temperature changes in the environment in which the vehicle is located in real time, which is essential to ensure the normal operation of the vehicle under extreme temperature conditions. Humidity sensors are used to measure the humidity level in the environment, which is important to prevent equipment failure or performance degradation caused by excessive or low humidity. Through the monitoring of these environmental sensors, it can be ensured that industrial vehicles operate in a suitable environment, thereby improving their reliability and safety.

[0066] Optionally, the operating status detection model includes at least one of a posture detection model, an abnormality recognition model, and an energy consumption monitoring model. The posture detection model determines the operating posture of the industrial vehicle based on the operating data of the industrial vehicle, and the operating posture includes at least one of the tilt angle and the roll angle of the industrial vehicle; the abnormality recognition model determines whether the industrial vehicle is in an abnormal state based on the operating data of the industrial vehicle and the environmental data of the industrial vehicle. The energy consumption monitoring model is used to monitor the energy consumption of the industrial vehicle based on the operating data of the industrial vehicle and the environmental data of the industrial vehicle, including at least one of the remaining battery power and the real-time power consumption.

[0067] Optionally, the posture detection model performs the following steps to determine the working posture of the industrial vehicle according to the operation data of the industrial vehicle:

[0068] Extracting characteristic variables from the operation data of the industrial vehicle to construct a corresponding covariance matrix;

[0069] Determine the eigenvalues ​​and eigenvectors of the covariance matrix corresponding to the operation data of the industrial vehicle;

[0070] For the operation data of the industrial vehicle, according to the size of the corresponding eigenvalues, select the eigenvectors corresponding to the first several largest eigenvalues ​​as the principal components of the operation data of the industrial vehicle, so as to construct a low-dimensional space representation of the operation data of the industrial vehicle;

[0071] Based on the trained clustering model, cluster analysis is performed on the low-dimensional space representation of the operation data of the industrial vehicle to obtain an operation posture label, so as to determine the operation posture of the industrial vehicle.

[0072] To this end, introducing the posture detection model into the industrial vehicle edge gateway system has the following key technical benefits through a series of sophisticated data processing steps:

[0073] (1) Dimensionality reduction improves efficiency: Through feature variable extraction and covariance matrix analysis, the main components of the running data are selected to construct a low-dimensional space representation. This process effectively reduces the dimension of the data, reduces computational complexity and storage requirements, and thus improves the efficiency of data processing. In a low-dimensional space, the relationship between data points is clearer, which facilitates subsequent clustering analysis.

[0074] (2) Improve recognition accuracy: Based on the trained clustering model, cluster analysis of operation data in low-dimensional space can more accurately classify different work posture categories. This method overcomes the misjudgment problem that may be caused by data redundancy or noise interference in traditional methods and improves the accuracy of posture recognition.

[0075] (3) Real-time response capability: Due to the use of efficient data processing methods and edge computing technology, the posture detection model can quickly process and analyze the real-time operation data of industrial vehicles, and realize instant recognition and feedback of working postures. This is particularly important for work scenarios that require rapid response and decision-making, and can significantly improve work efficiency and safety.

[0076] (4) Intelligent decision support: Accurately identifying the operating posture of industrial vehicles not only helps to monitor the vehicle status in real time, but also provides support for intelligent decision-making. For example, when the vehicle is found to be in an unsafe or inefficient posture, the system can automatically adjust the vehicle behavior or issue an early warning to the operator, thereby improving the safety and efficiency of the operation.

[0077] For ease of understanding, the following example code is provided:

[0078] #Industrial vehicle operation data, and stored in the numpy array data

[0079] #1. Construct the covariance matrix

[0080] cov_matrix=np.cov(data,rowvar=False)

[0081] #2. Calculate the eigenvalues ​​and eigenvectors of the covariance matrix

[0082] eigenvalues,eigenvectors=np.linalg.eigh(cov_matrix)

[0083] #3. Select the eigenvectors corresponding to the first N largest eigenvalues

[0084] N=3#Select the first 3 principal components

[0085] selected_eigenvectors=eigenvectors[:,np.argsort(eigenvalues)[::-1][:N]]

[0086] #4. Construct low-dimensional space representation

[0087] low_dim_representation=np.dot(data,selected_eigenvectors)

[0088] #5. Use the clustering model for posture recognition (assuming that the clustering model has been trained and saved as model)

[0089] #Using K-means

[0090] fromsklearn.cluster import KMeans

[0091] kmeans=KMeans(n_clusters=4,

[0092] random_state=0).fit(low_dim_representation)

[0093] labels = kmeans.labels_#job posture label

[0094] # Output results

[0095] for i,label in enumerate(labels):

[0096] print(f"The job posture label of data point {i} is: {label}")

[0097] Optionally, the abnormality recognition model is used to perform the following steps to determine whether the industrial vehicle is in an abnormal state according to the operation data of the industrial vehicle and the environmental data of the industrial vehicle:

[0098] Serializing the operation data of the industrial vehicle and the environmental data of the industrial vehicle to obtain an operation time series and an environmental time series;

[0099] Performing unsupervised feature fusion with piece-by-piece contrast loss on the running time series and the environment time series to obtain cross-domain fusion features;

[0100] Performing probability density statistics on the cross-domain fusion features to generate a probability density value;

[0101] The probability density value is compared with a set probability density threshold to determine whether the industrial vehicle is in an abnormal state.

[0102] To this end, an abnormality recognition model is introduced in one embodiment, and through comprehensive analysis of operation data and environmental data, the following key technical benefits are achieved:

[0103] (1) Enhanced comprehensiveness of detection: Traditional anomaly detection methods often rely on only a single data source (such as only operating data or only environmental data), which may cause some abnormal situations to be ignored. This solution achieves cross-domain feature fusion by considering both operating data and environmental data, thereby being able to more comprehensively capture the abnormal status of industrial vehicles. This comprehensiveness helps reduce missed reports and false positives and improves detection accuracy.

[0104] (2) Improve the real-time performance of detection: By performing unsupervised feature fusion on time series data with piece-by-piece contrast loss, the model can quickly extract key features and generate cross-domain fusion features without relying on a large amount of labeled data. This process reduces the time overhead of data processing, allowing the system to monitor and analyze the status of industrial vehicles in real time, thereby quickly responding to abnormal situations.

[0105] (3) Enhance the adaptability and robustness of the system: Due to the use of unsupervised learning methods, the model does not need to predefine all possible abnormal patterns, but can automatically discover anomalies based on the distribution and characteristics of the data. This adaptability enables the system to cope with various unknown or unforeseen abnormal situations, enhancing the robustness of the system.

[0106] (4) Provide decision support: By generating probability density values ​​and comparing them with the set thresholds, the system can clearly determine whether the industrial vehicle is in an abnormal state and issue an early warning to the operator or management system accordingly. This clear judgment result helps the operator take timely countermeasures to reduce potential safety risks and economic losses.

[0107] To this end, an exemplary code is also provided to illustrate the implementation of the solution of this application:

[0108] #Serialized running time series data_run and environment time series data_env

[0109] #1. Feature Fusion

[0110] deffeature_fusion(data_run,data_env,window_size):

[0111] fused_features=[]

[0112] for iin range(len(data_run)-window_size+1):

[0113] run_window=data_run[i:i+window_size]

[0114] env_window=data_env[i:i+window_size]

[0115] fused=np.concatenate((run_window,env_window),axis=1)

[0116] fused_features.append(fused)

[0117] returnnp.array(fused_features)

[0118] #window_size is 5

[0119] fused_features=feature_fusion(data_run,data_env,5)

[0120] #2. Probability density statistics

[0121] fromsklearn.neighbors import KernelDensity

[0122] # Use Gaussian kernel for estimation

[0123] kde=KernelDensity(kernel='gaussian',bandwidth=0.1).fit(fused_features)

[0124] log_density = kde.score_samples(fused_features) #Returns the logarithmic probability density value

[0125] #3. Determine the abnormality

[0126] threshold = -np.log(0.01) #Use 1% probability density as the threshold

[0127] anomalies = log_density <threshold

[0128] # Output results

[0129] for i,is_anomaly in enumerate(anomalies):

[0130] ifis_anomaly:

[0131] print(f"In the time window {i} to {i+4}, the industrial vehicle may be in an abnormal state.

[0132] ")

[0133] Optionally, the energy consumption monitoring model is used to perform the following steps to monitor the energy consumption of the industrial vehicle according to the operation data of the industrial vehicle and the environmental data of the industrial vehicle:

[0134] Energy consumption characteristics are extracted from the operation data of the industrial vehicle and the environmental data of the industrial vehicle, and characteristics of a direct correlation between the rate of change of speed and the power consumption of the motor, characteristics of a direct correlation between changes in acceleration and attitude angle and the resistance and efficiency of the vehicle, and characteristics of a direct correlation between temperature and humidity and the capacity attenuation adjustment of the battery and the change in internal resistance are obtained;

[0135] According to the direct correlation characteristics between the speed change rate and the power consumption of the motor, the direct correlation characteristics between the changes in acceleration and attitude angle and the resistance and efficiency of the vehicle, the direct correlation adjustment between temperature and humidity and the capacity attenuation of the battery, and the direct correlation characteristics between the internal resistance change, the real-time power consumption of the motor and the real-time resistance of the vehicle are calculated;

[0136] The total energy consumption of the vehicle is calculated according to the real-time power consumption of the motor and the real-time resistance of the vehicle, so as to monitor the energy consumption of the industrial vehicle.

[0137] In the management of industrial vehicles, the energy consumption monitoring model is used to combine the operation data and environmental data of industrial vehicles to conduct refined energy consumption analysis, which has the following significant technical benefits:

[0138] (1) Accurate energy consumption assessment: By extracting multiple features directly related to energy consumption (such as speed change rate, motor power consumption, acceleration, attitude angle change, ambient temperature and humidity, etc.), the model can more accurately calculate the real-time power consumption of the motor and the real-time resistance of the vehicle, and then derive the total energy consumption of the vehicle. This accurate assessment provides a solid data foundation for energy consumption management.

[0139] (2) Real-time dynamic monitoring: The model can process operating data and environmental data in real time to achieve dynamic monitoring of energy consumption. This is particularly important for scenarios that require rapid response and adjustment of energy consumption strategies, such as automatically adjusting the working mode according to current environmental conditions and vehicle status to achieve energy saving and consumption reduction.

[0140] (3) Multi-dimensional analysis and optimization: Combined with the analysis of the impact of environmental data (such as temperature and humidity) on battery performance, the model can identify the changing patterns of energy consumption under different environmental conditions, providing a basis for formulating targeted energy-saving measures. At the same time, by analyzing the impact of vehicle attitude angle and acceleration on resistance and efficiency, the vehicle design and operation strategy can be further optimized to reduce unnecessary energy consumption.

[0141] (4) Decision support: Based on the results of energy consumption monitoring, data-driven decision support can be provided to the enterprise management. For example, based on energy consumption data and vehicle operating status, the energy efficiency of different vehicle types or operating modes can be evaluated to provide a scientific basis for procurement, scheduling and maintenance.

[0142] (5) Improve operational efficiency: Through accurate energy consumption monitoring and optimization measures, enterprises can reduce the operating costs of industrial vehicles and improve overall operational efficiency. At the same time, reducing energy consumption also means reducing the impact on the environment, which is in line with the concept of green development.

[0143] An exemplary code is also provided below to illustrate the implementation of the above solution:

[0144] #Get the processed running data and environmental data, including speed change rate (speed_rate), acceleration (acceleration), orientation angle (orientation_angle), temperature (temperature), humidity (humidity), etc.

[0145] #1. Energy consumption feature extraction

[0146] motor_power_features=speed_rate.apply(lambda x:

[0147] some_function_of_speed_rate(x))#Assumed function to calculate motor power-related characteristics based on speed change rate

[0148] resistance_features = (acceleration, orientation_angle).apply(lambda x, y: some_function_of_acceleration_and_orientation(x, y)) # Calculate resistance and efficiency related features

[0149] battery_features = (temperature, humidity).apply(lambda x, y: some_function_of_temperature_and_humidity(x, y)) # Calculate battery performance related features

[0150] #2. Calculate the real-time power consumption of the motor and the real-time resistance of the vehicle

[0151] motor_power_consumption=

[0152] some_model_or_function(motor_power_features)

[0153] vehicle_resistance=some_model_or_function(resistance_features)

[0154] #3. Calculate the total energy consumption of the vehicle

[0155] total_energy_consumption=

[0156] integrate_over_time(motor_power_consumption+vehicle_resistance*

[0157] some_factor)#Perform time integration to calculate total energy consumption

[0158] # Output results

[0159] print(f"In the current time period, the total energy consumption of industrial vehicles is: {total_energy_consumption} units")

[0160] Optionally, the industrial vehicle edge gateway system based on the 5G RedCap module includes an encryption unit for encrypting the operating data of the industrial vehicle and the environmental data of the industrial vehicle to obtain ciphertext data; correspondingly, the local storage unit locally stores the ciphertext data corresponding to the operating data of the industrial vehicle and the environmental data of the industrial vehicle.

[0161] Optionally, when the encryption unit encrypts the operating data of the industrial vehicle and the environmental data of the industrial vehicle, it rates the sensitivity of the operating data of the industrial vehicle and the environmental data of the industrial vehicle, so that if the sensitivity level is greater than a set sensitivity threshold, the data is encrypted using field encryption, and if the sensitivity level is less than or equal to the set sensitivity threshold, the data is encrypted using data block or file level.

[0162] The expressions "first", "second", "the first" or "the second" used in various embodiments of the present disclosure may modify various components regardless of order and / or importance, but these expressions do not limit the corresponding components. The above expressions are only configured for the purpose of distinguishing an element from other elements. For example, a first user device and a second user device represent different user devices, although both are user devices. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element without departing from the scope of the present disclosure.

[0163] When one element (e.g., a first element) is referred to as being "(operably or communicatively) coupled" or "(operably or communicatively) coupled to" or "connected to" another element (e.g., a second element), it is understood that the one element is directly connected to the other element or the one element is indirectly connected to the other element via yet another element (e.g., a third element). Conversely, it is understood that when an element (e.g., a first element) is referred to as being "directly connected" or "directly coupled" to another element (the second element), no element (e.g., a third element) is interposed between the two.

[0164] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above invention concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

Claims

1. An industrial vehicle edge gateway system based on a 5G RedCap module, characterized in that: include: Industrial sensors for collecting operating data of industrial vehicles and environmental data of said industrial vehicles; A local storage unit, used for locally storing the operation data of the industrial vehicle and the environmental data of the industrial vehicle; The edge computing unit is used to determine the operation status data of the industrial vehicle according to the operation data of the industrial vehicle and the environmental data of the industrial vehicle, so as to generate a risk avoidance strategy for the industrial vehicle: The 5G RedCap module is used to upload the operation data of the industrial vehicle, the environmental data of the industrial vehicle, the operation status data of the industrial vehicle, and the risk avoidance strategy of the industrial vehicle stored in the local storage unit to the cloud platform.

2. According to claim 1, an industrial vehicle edge gateway system based on a 5G RedCap module is characterized in that: The edge computing unit performs the following steps to generate a risk avoidance strategy for the industrial vehicle: Determining whether the industrial vehicle has a safety risk according to the operation status data; When there is a safety risk to the industrial vehicle, a remote control instruction is generated and transmitted to the control system of the industrial vehicle to adjust the output of the control system and perform emergency braking or automatic deceleration on the industrial vehicle accordingly.

3. The industrial vehicle edge gateway system based on the 5G RedCap module according to claim 1 is characterized in that: The industrial vehicle edge gateway system based on the 5G RedCap module also includes: a multi-interface module, the multi-interface includes multiple industrial communication interfaces, and the multiple industrial communication interfaces include at least: a CAN bus interface, an RS485 interface, and an RS232 interface. The CAN bus interface is used to connect the industrial sensor to the control system of the industrial vehicle to collect the operating data of the industrial vehicle, the RS485 interface is used to enable the industrial sensor to collect the environmental data of the industrial vehicle, and the RS232 interface is used to enable the industrial sensor to collect the location data of the industrial vehicle.

4. The industrial vehicle edge gateway system based on the 5G RedCap module according to claim 1 is characterized in that: The industrial sensor includes an operation data sensor and an environmental sensor. The operation data sensor is at least one of a speed sensor, an acceleration sensor, an attitude angle sensor, and a position sensor, and is used to collect at least one of the speed data, acceleration data, attitude angle data, and position data of the industrial vehicle. The environmental sensor is a temperature sensor and a humidity sensor, and is used to collect at least one of the temperature data and humidity data of the environment in which the industrial vehicle is located.

5. The industrial vehicle edge gateway system based on the 5G RedCap module according to claim 4 is characterized in that: The operation state detection model includes at least one of a posture detection model, an abnormality recognition model, and an energy consumption monitoring model. The posture detection model determines the operation posture of the industrial vehicle according to the operation data of the industrial vehicle. The operation posture includes at least one of a tilt angle and a roll angle of the industrial vehicle. The abnormality recognition model determines whether the industrial vehicle is in an abnormal state based on the operating data of the industrial vehicle and the environmental data of the industrial vehicle. The energy consumption monitoring model is used to monitor the energy consumption of the industrial vehicle based on the operating data of the industrial vehicle and the environmental data of the industrial vehicle, including at least one of the remaining power of the battery and the real-time power consumption.

6. The industrial vehicle edge gateway system based on the 5G RedCap module according to claim 5, characterized in that: The posture detection model performs the following steps to determine the working posture of the industrial vehicle according to the operation data of the industrial vehicle: Extracting characteristic variables from the operation data of the industrial vehicle to construct a corresponding covariance matrix; Determine the eigenvalues ​​and eigenvectors of the covariance matrix corresponding to the operation data of the industrial vehicle; For the operation data of the industrial vehicle, according to the size of the corresponding eigenvalues, select the eigenvectors corresponding to the first several largest eigenvalues ​​as the principal components of the operation data of the industrial vehicle, so as to construct a low-dimensional space representation of the operation data of the industrial vehicle; Based on the trained clustering model, a cluster analysis is performed on the low-dimensional space representation of the operation data of the industrial vehicle to obtain an operation posture label, so as to determine the operation posture of the industrial vehicle.

7. The industrial vehicle edge gateway system based on the 5G RedCap module according to claim 5, characterized in that: The abnormality recognition model is used to perform the following steps to determine whether the industrial vehicle is in an abnormal state according to the operation data of the industrial vehicle and the environmental data of the industrial vehicle: Serializing the operation data of the industrial vehicle and the environmental data of the industrial vehicle to obtain an operation time series and an environmental time series; Performing unsupervised feature fusion with piece-by-piece contrast loss on the running time series and the environment time series to obtain cross-domain fusion features; Performing probability density statistics on the cross-domain fusion features to generate a probability density value; The probability density value is compared with a set probability density threshold to determine whether the industrial vehicle is in an abnormal state.

8. The industrial vehicle edge gateway system based on the 5G RedCap module according to claim 5, characterized in that: The energy consumption monitoring model is used to perform the following steps to monitor the energy consumption of the industrial vehicle according to the operation data of the industrial vehicle and the environmental data of the industrial vehicle: Energy consumption characteristics are extracted from the operation data of the industrial vehicle and the environmental data of the industrial vehicle, and characteristics of a direct correlation between the rate of change of speed and the power consumption of the motor, characteristics of a direct correlation between changes in acceleration and attitude angle and the resistance and efficiency of the vehicle, and characteristics of a direct correlation between temperature and humidity and the capacity attenuation adjustment of the battery and the change in internal resistance are obtained; According to the direct correlation characteristics between the speed change rate and the power consumption of the motor, the direct correlation characteristics between the changes in acceleration and attitude angle and the resistance and efficiency of the vehicle, the direct correlation adjustment between temperature and humidity and the capacity attenuation of the battery, and the direct correlation characteristics between the internal resistance change, the real-time power consumption of the motor and the real-time resistance of the vehicle are calculated; The total energy consumption of the vehicle is calculated according to the real-time power consumption of the motor and the real-time resistance of the vehicle, so as to monitor the energy consumption of the industrial vehicle.

9. The industrial vehicle edge gateway system based on the 5G RedCap module according to claim 1, characterized in that: The industrial vehicle edge gateway system based on the 5G RedCap module includes an encryption unit, which is used to encrypt the operating data of the industrial vehicle and the environmental data of the industrial vehicle to obtain ciphertext data; correspondingly, the local storage unit locally stores the ciphertext data corresponding to the operating data of the industrial vehicle and the environmental data of the industrial vehicle.

10. The industrial vehicle edge gateway system based on the 5G RedCap module according to claim 9, characterized in that: When the encryption unit encrypts the operating data of the industrial vehicle and the environmental data of the industrial vehicle, the operating data of the industrial vehicle and the environmental data of the industrial vehicle are graded for sensitivity, so that if the sensitivity level is greater than the set sensitivity threshold, the data is encrypted using field encryption, and if the sensitivity level is less than or equal to the set sensitivity threshold, the data is encrypted using data block or file level.

Images