Safety supervision alarm method, system and equipment for road hazardous goods transport vehicles

Abstract

The present application relates to the technical field of transport vehicle supervision, and provides a safety supervision alarm method, system and equipment for road hazardous goods transport vehicles. The supervision alarm method includes: determining whether the hazardous goods sensor data matches the preset risk judgment standard; in the case that the hazardous goods sensor data does not match the risk judgment standard, combining the vehicle sensor data and the hazardous goods sensor data to predict the change of the hazardous goods sensor data to obtain hazardous goods prediction data; determining whether the hazardous goods prediction data matches the risk judgment standard; in the case that the hazardous goods prediction data matches the risk judgment standard, determining that the transport vehicle has a safety risk and outputting an alarm message. By adopting the above technical solution, when the current hazardous goods data indicates that there is no risk, the change of the hazardous goods sensor data can be further predicted in combination with the vehicle sensor data, which can help to predict risks, and further help to improve the effectiveness of safety supervision.

Description

Technical Field

[0001] The present application relates to the technical field of transport vehicle supervision, and in particular to a method, system and equipment for safety supervision and alarm of road hazardous goods transport vehicles. Background Art

[0002] The transportation of dangerous goods (such as dangerous chemicals) is an important branch of the logistics field. Because it involves flammable, explosive, toxic and other high-risk substances, the safety issues in the transportation process have always attracted much attention. In recent years, with the development of economic construction, the demand for dangerous chemical raw materials in various industries has continued to increase, and the scale and frequency of dangerous goods logistics have also expanded accordingly, which has put forward higher requirements for the safety supervision of dangerous goods transportation.

[0003] At present, the safety supervision of dangerous goods transport vehicles mainly relies on traditional monitoring methods, such as manual inspections, regular inspections and simple on-board monitoring systems. However, these traditional methods have many shortcomings and are difficult to meet the needs of real-time, accurate and comprehensive safety monitoring. For example, manual inspections are not only inefficient, but also difficult to cover all transportation links; although regular inspections can find some potential problems, they cannot achieve real-time monitoring and early warning; simple on-board monitoring systems can often only record part of the driving data and lack intelligent analysis and alarm functions.

[0004] A Chinese patent application (publication number: CN117522180A) discloses a risk control method for hazardous chemicals transport vehicles. Although this method can calculate the probability of risk occurrence through a preset risk model and determine whether the transport vehicle is a risk vehicle based on the probability value, the accuracy of risk judgment still needs to be improved. Summary of the invention

[0005] In order to facilitate the supervision of the dangerous goods transportation process, the present application provides a safety supervision alarm method, system and equipment for road dangerous goods transportation vehicles.

[0006] In the first aspect, the present application provides a method for safety supervision and alarm of highway hazardous goods transport vehicles, which adopts the following technical solution:

[0007] A method for safety supervision and alarm of a highway hazardous goods transport vehicle, the method comprising:

[0008] Acquire vehicle sensor data collected by a vehicle sensor provided on a transport vehicle and dangerous goods sensor data collected by a dangerous goods sensor provided on a dangerous goods container of the transport vehicle;

[0009] Determining whether the dangerous goods sensing data matches a preset risk judgment standard;

[0010] In the case where the dangerous goods sensor data does not match the risk judgment standard, inputting the vehicle sensor data and the dangerous goods sensor data into a data prediction model to obtain dangerous goods prediction data;

[0011] Determining whether the dangerous goods prediction data matches the risk judgment standard;

[0012] In the case where the dangerous goods prediction data matches the risk judgment standard, determining that the transport vehicle has a safety risk and outputting an alarm message;

[0013] The data prediction model is obtained by training an initial network model using training data, the initial network model is a long short-term memory network model, the training data includes at least one set of sample data, and the sample data is determined based on vehicle sensor data within a sample period and sample dangerous goods sensor data within the sample period;

[0014] The sample data includes speed influencing factors and vibration influencing factors, and the process of determining the sample data includes:

[0015] Predicting a vibration change of the vehicle based on a change in the vehicle speed during the sample time period to obtain predicted vibration data;

[0016] Determining the speed influencing factor based on the difference between the predicted vibration data within the sample time period and the vibration condition;

[0017] Predicting a change in the speed of the vehicle based on a change in the vibration condition within the sample time period to obtain predicted speed data;

[0018] The vibration influencing factor is determined based on a difference between the predicted speed data within the sample time period and the vehicle speed.

[0019] By adopting the above technical solution, when the current hazardous materials data indicates that there is no risk, the changes in hazardous materials sensor data can be further predicted in combination with vehicle sensor data. This can help to predict risks, thereby helping to avoid risks that may arise during transportation in advance, and further helping to improve the effectiveness of safety supervision.

[0020] In addition, since the sample data includes the speed influencing factor and the vibration influencing factor, the speed influencing factor can weaken the influence of speed on vibration changes, and the vibration influencing factor can weaken the influence of vibration on speed changes, the model can better learn the influence of speed and vibration on hazardous goods sensor data during the training process, which can help improve the accuracy of hazardous goods prediction data.

[0021] Optionally, after determining whether the dangerous goods sensing data matches a preset risk judgment standard, the method further includes:

[0022] In the case where the dangerous goods sensing data matches the risk judgment standard, determining whether to verify the judgment result;

[0023] In the case where it is determined that the judgment result is not to be verified, determining that there is a safety risk for the transport vehicle;

[0024] In the case where it is determined to verify the judgment result, determining whether the transport vehicle has a safety risk by combining the vehicle sensor data and the dangerous goods sensor data;

[0025] When it is determined that the transport vehicle has a safety risk, an alarm message is output.

[0026] By adopting the above technical solution, when the dangerous goods sensor data matches the risk judgment standard and needs to be verified, the vehicle sensor data and the dangerous goods sensor data can be combined to verify whether there is a safety risk in the transport vehicle, which can help improve the accuracy of safety risk judgment.

[0027] Optionally, the determining whether to verify the judgment result includes:

[0028] Determining whether the dangerous goods sensing data matches a preset abnormality judgment standard;

[0029] In the case where the dangerous goods sensing data does not match the abnormality judgment standard, determining whether the transport vehicle has dangerous driving behavior;

[0030] In the case where it is determined that the transport vehicle does not have any dangerous driving behavior, it is determined to verify the judgment result.

[0031] By adopting the above technical solution, it is possible to determine whether to verify the judgment result based on the risk level, which can help improve the accuracy of safety risk judgment while ensuring the safety of the transportation process, and further help improve the accuracy of alarm information output.

[0032] Optionally, determining whether the transport vehicle has dangerous driving behavior includes:

[0033] Acquiring positioning data of the transport vehicle;

[0034] Determine the road condition information of the current road of the transport vehicle based on the positioning data;

[0035] Determining whether the type of dangerous goods in the transport vehicle matches the road condition information;

[0036] In the case where the type of dangerous goods in the transport vehicle matches the road condition information, determining whether the vehicle sensor data matches the road condition information;

[0037] When the vehicle sensor data matches the road condition information, it is determined that there is no dangerous driving behavior of the transport vehicle.

[0038] By adopting the above technical scheme, the road condition information can be determined in combination with the location information of the transport vehicle, and whether the transport vehicle has dangerous driving behavior can be determined based on the type of dangerous goods and the matching relationship between the vehicle sensor data and the road condition information. This can help to make targeted judgments on the dangerous driving behaviors corresponding to the dangerous goods, and further help to improve the accuracy of the dangerous driving behavior judgment results.

[0039] Optionally, determining whether the dangerous goods sensing data matches a preset risk judgment standard includes:

[0040] Determining whether the dangerous goods sensing data exceeds a preset safety range;

[0041] In the case where the dangerous goods sensing data does not exceed the safety range, determining whether the fluctuation amplitude of the dangerous goods sensing data is greater than a preset amplitude threshold;

[0042] When the fluctuation amplitude is greater than the amplitude threshold, it is determined that the dangerous goods sensing data matches the risk judgment standard.

[0043] By adopting the above technical scheme, it is possible to determine whether the dangerous goods sensor data matches the risk judgment standard by combining the relationship between the dangerous goods sensor data and the safety range and the fluctuation range of the dangerous goods sensor data, so that the dangerous goods sensor data can be analyzed and judged from different dimensions, which can help improve the accuracy of risk judgment.

[0044] Optionally, the combining the vehicle sensor data and the dangerous goods sensor data to determine whether the transport vehicle has a safety risk includes:

[0045] When the hazardous goods sensor data exceeds the safety range, a monitoring duration is determined based on the vehicle sensor data, and monitoring of the hazardous goods sensor data begins; when the hazardous goods sensor data does not fall within the safety range within the monitoring duration, it is determined that there is a safety risk with the transport vehicle.

[0046] By adopting the above technical solution, the monitoring time can be dynamically determined based on the vehicle sensor data, and whether there is a safety risk in the transport vehicle can be determined based on the changes in the dangerous goods sensor data during the monitoring time, which can help improve the accuracy of safety risk judgment.

[0047] Optionally, determining the monitoring duration based on the vehicle sensor data includes: determining the monitoring duration based on the vehicle speed and / or the vibration condition.

[0048] Optionally, the combining the vehicle sensor data and the dangerous goods sensor data to determine whether the transport vehicle has a safety risk includes:

[0049] When the fluctuation amplitude is greater than a preset amplitude threshold, the amplitude threshold is adjusted based on the vehicle sensor data, and when the fluctuation amplitude is greater than the adjusted fluctuation amplitude threshold, it is determined that the transport vehicle has a safety risk.

[0050] By adopting the above technical solution, the fluctuation amplitude threshold can be dynamically adjusted based on the vehicle sensor data, and when the fluctuation amplitude is greater than the adjusted fluctuation amplitude threshold, it is determined that there is a safety risk for the transport vehicle, which can help improve the accuracy of safety risk judgment.

[0051] In the second aspect, the present application provides a road hazardous goods transport vehicle safety supervision alarm system, which adopts the following technical solution:

[0052] A road hazardous goods transport vehicle safety supervision and alarm system, the system comprising a vehicle sensor, a hazardous goods sensor, an Internet of Things gateway and a central processor;

[0053] The vehicle sensor is arranged on the transport vehicle and is used to collect vehicle sensor data;

[0054] The hazardous goods sensor is disposed on the hazardous goods container of the transport vehicle and is used to collect hazardous goods sensing data;

[0055] The Internet of Things gateway is respectively connected to the vehicle sensor, the dangerous goods sensor and the central processor by signal, and is used to send the received vehicle sensor data and the dangerous goods sensor data to the central processor;

[0056] The central processing unit is used to execute any one of the road hazardous goods transport vehicle safety supervision and alarm methods provided in the first aspect.

[0057] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0058] An electronic device, comprising:

[0059] at least one processor;

[0060] Memory;

[0061] At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute any one of the road hazardous goods transport vehicle safety supervision and alarm methods provided in the first aspect.

[0062] In summary, the present application includes at least one of the following beneficial technical effects:

[0063] 1. Since the current dangerous goods data indicates that there is no risk, the changes in dangerous goods sensor data can be further predicted in combination with vehicle sensor data, which can help to predict risks, thereby helping to avoid risks that may occur during transportation in advance, and thus help to improve the effectiveness of safety supervision;

[0064] 2. Since whether to verify the judgment result is determined based on the risk level, this can help improve the accuracy of safety risk judgment while ensuring the safety of the transportation process, and further help improve the accuracy of alarm information output. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a flow chart of a method for safety supervision and alarm of a highway hazardous goods transport vehicle provided in an embodiment of the present application;

[0066] Figure 2 It is a flow chart of another method for safety supervision and alarm of a highway hazardous goods transport vehicle provided in an embodiment of the present application;

[0067] Figure 3 It is a flowchart of a verification judgment method provided in an embodiment of the present application;

[0068] Figure 4 It is a flowchart of a dangerous driving behavior judgment method provided in an embodiment of the present application;

[0069] Figure 5 This is a flow chart of a security risk determination method provided by an embodiment of the present application;

[0070] Figure 6 It is a structural diagram of a road hazardous goods transport vehicle safety supervision alarm system provided by an embodiment of the present application;

[0071] Figure 7 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0072] In order to make the purpose, technical solutions and advantages of this application more clear, the following Figure 1-7It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0073] The present application embodiment discloses a safety supervision alarm method for road hazardous goods transport vehicles. Figure 1 The safety supervision and alarm method for road dangerous goods transportation vehicles includes the following steps:

[0074] Step 101, obtaining vehicle sensor data collected by a vehicle sensor installed on a transport vehicle and dangerous goods sensor data collected by a dangerous goods sensor installed on a dangerous goods container of the transport vehicle.

[0075] The vehicle sensors are used to collect data related to the transport vehicle. Specifically, the vehicle sensors may include sensors for collecting data of the transport vehicle itself, such as speed sensors, vibration sensors, satellite locators, etc., and may also include sensors for collecting data of the environment in which the transport vehicle is located, such as temperature sensors, humidity sensors, light sensors, etc.

[0076] Correspondingly, the vehicle sensor data may include data related to the transport vehicle itself, such as vehicle speed and vibration conditions, and may also include data related to the environment in which the transport vehicle is located, such as ambient temperature, ambient humidity, and ambient light intensity.

[0077] Dangerous goods sensors are used to collect data related to dangerous goods. Specifically, dangerous goods sensors may include sensors for collecting data about dangerous goods themselves, such as temperature sensors for collecting the temperature of dangerous goods during transportation, and dangerous goods sensors may include sensors for collecting data about dangerous goods, such as pressure sensors for collecting the pressure of dangerous goods containers.

[0078] Accordingly, the dangerous goods sensing data may include data related to the dangerous goods themselves, such as the temperature of the dangerous goods, or may also include data related to the dangerous goods container, such as the pressure of the dangerous goods container.

[0079] Step 102, determining whether the dangerous goods sensing data matches a preset risk judgment standard.

[0080] Among them, the risk judgment standard is used to determine whether there is a safety risk. Specifically, if the dangerous goods sensor data matches the risk judgment standard, there may be a safety risk; if the dangerous goods sensor data does not match the risk judgment standard, there is a high probability that there is no safety risk.

[0081] The risk judgment standard is associated with the type of the dangerous goods sensor data. In one example, the risk judgment standard includes that the dangerous goods sensor data is not within a preset safety range. In another example, the risk judgment standard includes that the fluctuation range of the dangerous goods sensor data is greater than a preset risk range threshold.

[0082] Optionally, when the dangerous goods sensor data matches the risk judgment standard, it can be directly determined that the transport vehicle has a safety risk and output an alarm message, or further risk judgment can be performed based on other methods.

[0083] Step 103: When the dangerous goods sensor data does not match the risk judgment standard, the vehicle sensor data and the dangerous goods sensor data are input into a data prediction model to obtain dangerous goods prediction data.

[0084] Specifically, it was found in practice that the driving conditions of the vehicle and the environmental conditions in which the vehicle is located will affect the status of dangerous goods during transportation. Therefore, when the current dangerous goods data indicates that there is no risk, this solution will further combine the vehicle sensor data to predict the changes in the dangerous goods sensor data. This can help to predict risks and, in turn, help to avoid risks that may arise during transportation in advance.

[0085] In this embodiment, the data prediction model is obtained by training the initial network model using the training data. In one example, the initial network model is a long short-term memory network (LSTM) model, and the training data includes at least one set of sample data, and the sample data is determined based on the vehicle sensor data within the sample period and the sample dangerous goods sensor data within the sample period. Specifically, since the initial neural network model is a long short-term memory network model, and the long short-term memory network model can remember long-term dependent information, the dangerous goods sensor data can be predicted based on the changes in the vehicle sensor data and the dangerous goods sensor data to obtain the dangerous goods prediction data, which can help improve the accuracy of the dangerous goods prediction data.

[0086] In this embodiment, the vehicle sensor data includes vehicle speed and vibration conditions, and the process of determining the sample data includes: predicting the vibration change of the vehicle based on the change of the vehicle speed within the sample time period to obtain predicted vibration data; determining the speed influencing factor based on the difference between the predicted vibration data and the vibration conditions within the sample time period; predicting the speed change of the vehicle based on the change of the vibration conditions within the sample time period to obtain predicted speed data; determining the vibration influencing factor based on the difference between the predicted speed data within the sample time period and the vehicle speed; the sample data includes speed influencing factors and vibration influencing factors.

[0087] The method for predicting the vibration change of the vehicle based on the change of the vehicle speed is preset. In one example, the vehicle can be controlled to change speed on a horizontal test road surface, and the speed change and the vibration change can be recorded to obtain the corresponding relationship between the speed and the vibration.

[0088] The method for predicting the speed change of the vehicle based on the change of the vibration condition is preset. In one example, the vehicle can be controlled to pass through a bumpy test road at a fixed power, and the vibration change and speed change are recorded to obtain the corresponding relationship between the vibration and the speed.

[0089] In an example, the correspondence between speed and vibration is used as an example for explanation. During the test, it is found that vibration and speed are roughly linearly correlated within a certain range. Therefore, the speed range can be divided into several speed intervals. Within each speed interval, vibration and speed are roughly linearly correlated. The vibration conditions corresponding to the speed endpoint values ​​of each speed interval are pre-set according to the experimental results.

[0090] Accordingly, in the process of predicting the vibration change of the vehicle based on the change of the vehicle speed, when the vehicle speed and the speed endpoint value are the same, the vibration condition corresponding to the speed endpoint value can be directly determined as the vibration condition corresponding to the vehicle speed; when the speed and the speed endpoint value are different, the vibration and speed have the following corresponding relationship:

[0091]

[0092] The above formula can be deduced into the following formula:

[0093]

[0094] Among them, v0 is the vehicle speed, f0 is the vibration condition corresponding to the vehicle speed v0; v1 is the lower speed endpoint value of the speed interval to which the speed v0 belongs, f1 is the vibration condition corresponding to the speed v1; v2 is the upper speed endpoint value of the speed interval to which the speed v0 belongs, f2 is the vibration condition corresponding to the speed v2.

[0095] Based on the same principle, the speed change can also be predicted based on the vibration change, which will not be elaborated here.

[0096] In the above example, considering that the impact of different vehicle sensor data on the safety status may have an overlapping effect, if the original vehicle sensor data is directly used for model training, it may lead to differences in the degree of learning of the model for different influencing factors. Therefore, in the above further scheme, the change in vibration conditions is predicted based on the change in vehicle speed, and then the speed influencing factors are determined based on the difference between the predicted vibration data and the vibration conditions. This allows the determined speed influencing factors to weaken the impact of speed on vibration changes. Based on the same principle, the vibration influencing factors can weaken the impact of vibration on speed changes. In this way, the sample data contains speed influencing factors and vibration influencing factors, which can enable the model to better learn the impact of speed and vibration on dangerous goods sensor data during training, which can help improve the accuracy of dangerous goods prediction data.

[0097] Furthermore, before using the training data to train the initial network model, it also includes: performing data enhancement processing on the initial data set to generate more diverse training samples by simulating different transportation scenarios and conditions to enhance the generalization ability of the model. Specifically, it includes but is not limited to the following methods:

[0098] The first one is to simulate different weather conditions: based on historical weather data or simulation software, generate temperature and pressure data under different weather conditions such as temperature, humidity, wind speed, etc.

[0099] The second method is to simulate different road conditions: considering different road types (such as highways, mountain roads, urban roads, etc.) and road conditions (such as dry, slippery, icy, etc.), and generating temperature, pressure, and vibration data measured under these road conditions.

[0100] The third method is to simulate different transport speeds: based on the vehicle's travel speed, generate temperature, pressure, and vibration data measured at different speeds to consider the impact of speed on the collected data.

[0101] Through the above method, a more diverse and representative data set can be generated, thereby improving the generalization ability of the trained data prediction model.

[0102] In some embodiments, the initial network model can be based on a model that has been trained in the field of transportation, and through targeted training, the model can be used for the specific task of safety supervision of dangerous goods transport vehicles. In this way, existing knowledge and experience can be fully utilized, the model training process can be accelerated, and the accuracy of prediction can be improved.

[0103] In an example, taking temperature prediction as an example, the LSTM model can use the historical temperature information in the time series data to predict future temperature changes. By training the LSTM model, the laws and trends of temperature changes can be learned, and future temperatures can be predicted based on these laws and trends.

[0104] First, the historical temperature data needs to be converted into a time series format and normalized or standardized. This helps to eliminate noise and outliers in the data and improve the predictive performance of the model.

[0105] The LSTM model is constructed using a deep learning framework (TensorFlow is used in this invention). When constructing the model, appropriate network structure and hyperparameters are set, including the number of network layers, number of neurons, learning rate, etc.

[0106] Use the training data set to train the LSTM model. During the training process, it is necessary to monitor the model's loss function and performance indicators in order to adjust the hyperparameters and optimize the model structure in a timely manner until the training is completed.

[0107] Step 104, determining whether the dangerous goods prediction data matches the risk judgment standard.

[0108] Specifically, the method of determining whether the dangerous goods prediction data matches the risk judgment standard is the same as the method of determining whether the dangerous goods sensing data matches the preset risk judgment standard in the above step 102, and will not be repeated here.

[0109] Optionally, when the dangerous goods prediction data does not match the risk assessment criteria, it is possible to directly determine that the transport vehicle has a safety risk and output an alarm message, or further perform risk assessment based on other methods.

[0110] Step 105: When the dangerous goods prediction data matches the risk judgment standard, it is determined that the transport vehicle has a safety risk and an alarm message is output.

[0111] Optionally, the output method of the alarm information may include sending an alarm signal through an audible and visual alarm device in the transport vehicle, and the alarm information may also be sent to the driver, fleet manager and relevant departments via text messages, phone calls, application (APP) push, etc.

[0112] The implementation principle of a safety supervision alarm method for highway hazardous goods transport vehicles in an embodiment of the present application is as follows: obtaining vehicle sensor data collected by vehicle sensors installed on the transport vehicle and hazardous goods sensor data collected by hazardous goods sensors installed on the hazardous goods container of the transport vehicle; determining whether the hazardous goods sensor data matches the preset risk judgment standard; in the case where the hazardous goods sensor data does not match the risk judgment standard, inputting the vehicle sensor data and the hazardous goods sensor data into a data prediction model to obtain hazardous goods prediction data; determining whether the hazardous goods prediction data matches the risk judgment standard; in the case where the hazardous goods prediction data matches the risk judgment standard, determining that the transport vehicle has a safety risk and outputting an alarm message. By adopting the above technical solution, when the current hazardous goods data indicates that there is no risk, the change of hazardous goods sensor data can be further predicted in combination with the vehicle sensor data, which can help to predict risks, thereby helping to avoid risks that may occur during transportation in advance, and further helping to improve the effectiveness of safety supervision.

[0113] In some embodiments, reference Figure 2 , step 102, after determining whether the dangerous goods sensing data matches the preset risk judgment standard, the following steps are also included:

[0114] Step 201, when the dangerous goods sensor data matches the risk judgment standard, determine whether to verify the judgment result.

[0115] Optionally, determining whether to verify the judgment result includes: determining whether the hazardous goods sensor data matches the preset abnormal judgment standard; determining not to verify the judgment result when the hazardous goods sensor data matches the abnormal judgment standard; determining to verify the judgment result when the hazardous goods sensor data does not match the abnormal judgment standard.

[0116] The abnormality judgment standard is higher than the risk judgment standard. In one example, the risk judgment standard includes that the dangerous goods sensor data is within a preset risk interval. In another example, the risk judgment standard includes that the fluctuation amplitude of the dangerous goods sensor data is greater than a preset abnormal amplitude threshold, and the abnormal amplitude threshold is greater than the risk amplitude threshold.

[0117] Step 202 , when it is determined that the judgment result is not to be verified, it is determined that there is a safety risk for the transport vehicle, and step 204 is executed.

[0118] Step 203, when it is determined that the judgment result is to be verified, it is determined whether there is a safety risk in the transport vehicle by combining the vehicle sensor data and the dangerous goods sensor data.

[0119] Optionally, combining vehicle sensor data and hazardous materials sensor data to determine whether a transport vehicle presents a safety risk includes: inputting the vehicle sensor data and hazardous materials sensor data into a safety judgment model, and determining whether a transport vehicle presents a safety risk based on an output result of the model.

[0120] The safety judgment model is obtained by training the initial network model using training data. The training data includes at least one set of sample data, and the sample data is based on sample vehicle sensor data, sample dangerous goods sensor data and corresponding safety judgment results.

[0121] Step 204: When it is determined that the transport vehicle has a safety risk, an alarm message is output.

[0122] The output method of the alarm information is the same as the output method of the alarm information in the above step 105, and will not be described in detail in this embodiment.

[0123] In the above implementation, when the hazardous goods sensor data matches the risk judgment standard and needs to be verified, the vehicle sensor data and the hazardous goods sensor data are combined to verify whether there is a safety risk in the transport vehicle, which can help improve the accuracy of safety risk judgment.

[0124] For further reference, Figure 3 In step 201, determining whether to verify the judgment result includes the following steps:

[0125] Step 301, determining whether the dangerous goods sensing data matches the preset abnormality judgment standard.

[0126] The abnormality judgment standard is higher than the risk judgment standard. In one example, the risk judgment standard includes that the dangerous goods sensor data is within a preset risk interval. In another example, the risk judgment standard includes that the fluctuation amplitude of the dangerous goods sensor data is greater than a preset abnormal amplitude threshold, and the abnormal amplitude threshold is greater than the risk amplitude threshold.

[0127] Step 302: When the dangerous goods sensing data does not match the abnormality judgment standard, determine whether the transport vehicle has dangerous driving behavior.

[0128] Optionally, based on the location information of the transport vehicle and changes in the location information, it is determined whether the transport vehicle has dangerous driving behavior. Accordingly, dangerous driving behavior includes not driving at the specified time, route, or speed.

[0129] Optionally, when it is determined that the transport vehicle has dangerous driving behavior, it can be directly determined not to verify the judgment result, or it can be determined based on other methods whether to verify the judgment result.

[0130] Step 303, when it is determined that the transport vehicle does not have any dangerous driving behavior, determine to verify the judgment result.

[0131] In the above technical solution, when the dangerous goods sensor data does not match the abnormal judgment standard, it is further determined whether the transport vehicle has dangerous driving behavior, and when the transport vehicle does not have dangerous driving behavior, it is determined to verify the judgment result. In this way, it can be determined whether to verify the judgment result based on the degree of risk, which can help improve the accuracy of safety risk judgment while ensuring the safety of the transportation process, and further help improve the accuracy of alarm information output.

[0132] For further reference, Figure 4 In step 302, determining whether the transport vehicle has dangerous driving behavior includes the following steps:

[0133] Step 401, obtaining the positioning data of the transport vehicle.

[0134] The positioning data is collected by a locator installed on the transport vehicle. In one example, the locator is a satellite locator, such as a Beidou locator or a GPS locator.

[0135] Step 402: Determine the road condition information of the current road on which the transport vehicle is traveling based on the positioning data.

[0136] The road condition information includes road feature information and / or road traffic conditions. Specifically, the road feature information includes road type (such as expressway, mountain road, urban road, etc.), road width, number of lanes, area, etc., and the traffic conditions include vehicle density, traffic speed, road surface conditions (such as dry, slippery, icy, etc.).

[0137] In actual implementation, traffic information can be obtained from a third-party map platform.

[0138] Step 403, determining whether the type of dangerous goods in the transport vehicle matches the road condition information.

[0139] The matching relationship between the dangerous goods type and the road condition information is preset. Specifically, different dangerous goods have different requirements for the transportation process. For example, some explosive goods need to avoid bumps during transportation, so they need to travel on roads with better conditions during transportation.

[0140] Optionally, determining whether the type of hazardous goods in the transport vehicle matches the road condition information includes: determining the hazard level corresponding to the type of hazardous goods; determining whether the hazard level matches the road condition information; if the hazard level matches the road condition information, determining that the type of hazardous goods matches the road condition information; if the hazard level does not match the road condition information, determining that the type of hazardous goods does not match the road condition information.

[0141] Among them, the danger levels corresponding to different types of dangerous goods, and the matching relationship between road condition information and danger levels are pre-set.

[0142] In one example, determining whether the danger level matches the road condition information includes: based on the road condition level corresponding to the road condition information; determining whether the danger level is higher than the road condition level; if the danger level is higher than the road condition level, determining whether the danger level matches the road condition level; if the danger level is not higher than the road condition level, determining that the danger level does not match the road condition level.

[0143] Among them, the corresponding relationship between the road condition information and the road condition level is preset.

[0144] Optionally, when the type of dangerous goods in the transport vehicle does not match the road condition information, it is determined that the transport vehicle has dangerous driving behavior.

[0145] Step 404: When the type of dangerous goods in the transport vehicle matches the road condition information, determine whether the vehicle sensor data matches the road condition information.

[0146] In one example, determining whether vehicle sensor data matches road condition information includes: determining a road speed limit based on the road condition information; determining whether a vehicle speed is greater than the road speed limit; and determining that the vehicle sensor data matches the road condition information when the vehicle speed is greater than the road speed limit.

[0147] The method of determining the road speed limit based on the road condition information is preset, for example, determining the road speed limit based on the road type, or determining the road speed limit based on the road's passing speed.

[0148] Optionally, when the vehicle sensor data does not match the road condition information, it is determined that the transport vehicle has dangerous driving behavior.

[0149] Step 405: When the vehicle sensor data matches the road condition information, it is determined that there is no dangerous driving behavior of the transport vehicle.

[0150] In the above technical scheme, the road condition information can be determined in combination with the location information of the transport vehicle, and whether the transport vehicle has dangerous driving behavior can be determined based on the type of dangerous goods and the matching relationship between the vehicle sensor data and the road condition information. This can help to make targeted judgments on the dangerous driving behaviors corresponding to the dangerous goods, and further help to improve the accuracy of the dangerous driving behavior judgment results.

[0151] In some embodiments, reference Figure 5 , step 102, determining whether the dangerous goods sensing data matches the preset risk judgment standard, includes the following steps:

[0152] Step 501, determining whether the dangerous goods sensing data exceeds a preset safety range.

[0153] In actual implementation, the safety range can be obtained through pre-testing. Further, in the case where the dangerous goods sensor data includes more than two, the safety ranges corresponding to different dangerous goods sensor data are set separately.

[0154] Optionally, when the dangerous goods sensor data exceeds a safety range, it is determined that the dangerous goods sensor data matches a risk judgment standard.

[0155] Furthermore, in step 203, the vehicle sensor data and the hazardous goods sensor data are combined to determine whether there is a safety risk for the transport vehicle, including: when the hazardous goods sensor data exceeds the safety range, determining the monitoring time based on the vehicle sensor data, and starting to monitor the hazardous goods sensor data; when the hazardous goods sensor data does not fall within the safety range within the monitoring time, determining that there is a safety risk for the transport vehicle.

[0156] In one example, determining the monitoring duration based on vehicle sensor data includes: determining the monitoring duration based on vehicle speed and / or vibration conditions. For example, the faster the driving speed, the shorter the monitoring duration.

[0157] In actual implementation, the vehicle status may be first determined based on the vehicle sensor data and then the monitoring duration may be determined based on the vehicle status.

[0158] In the above technical solution, since the monitoring time can be dynamically determined based on the vehicle sensor data, and whether there is a safety risk in the transport vehicle can be determined based on the changes in the dangerous goods sensor data during the monitoring time, this can help improve the accuracy of safety risk judgment.

[0159] Step 502: When the dangerous goods sensing data does not exceed the safety range, determine whether the fluctuation amplitude of the dangerous goods sensing data is greater than a preset amplitude threshold.

[0160] Optionally, when the fluctuation amplitude is less than or equal to the amplitude threshold, it can be directly determined that the dangerous goods sensor data does not match the risk judgment standard, or it can be determined by other methods whether the dangerous goods sensor data matches the risk judgment standard.

[0161] Step 503: When the fluctuation amplitude is greater than the amplitude threshold, it is determined that the dangerous goods sensor data matches the risk judgment standard.

[0162] Furthermore, in step 203, the vehicle sensor data and the hazardous materials sensor data are combined to determine whether there is a safety risk for the transport vehicle, including: when the fluctuation amplitude is greater than a preset amplitude threshold, adjusting the amplitude threshold based on the vehicle sensor data, and determining that there is a safety risk for the transport vehicle when the fluctuation amplitude is greater than the adjusted fluctuation amplitude threshold.

[0163] In one example, adjusting the fluctuation amplitude based on vehicle sensor data includes: adjusting the fluctuation amplitude based on vehicle speed and / or vibration conditions. For example, the faster the vehicle speed, the greater the increase in the fluctuation amplitude.

[0164] In actual implementation, the vehicle state may be first determined based on the vehicle sensor data and then the adjustment method for the fluctuation amplitude may be determined based on the vehicle state.

[0165] In the above technical solution, since the fluctuation amplitude can be dynamically determined based on the vehicle sensor data, and when the fluctuation amplitude is greater than the adjusted fluctuation amplitude threshold, it is determined that there is a safety risk for the transport vehicle, this can help improve the accuracy of safety risk judgment.

[0166] In the above implementation manner, the relationship between the hazardous goods sensor data and the safety range and the fluctuation range of the hazardous goods sensor data can be combined to determine whether the hazardous goods sensor data matches the risk judgment standard, so that the hazardous goods sensor data can be analyzed and judged from different dimensions, which can help improve the accuracy of risk judgment.

[0167] The present application also provides a road hazardous goods transport vehicle safety supervision alarm system, referring to Figure 6 The highway hazardous goods transport vehicle safety supervision and alarm system includes a vehicle sensor 610, a hazardous goods sensor 620, an Internet of Things gateway 630 and a central processor 640.

[0168] The vehicle sensor 610 is arranged on the vehicle of the transport vehicle and is used to collect vehicle sensor data. In one example, the vehicle sensor includes a vibration sensor 611 and a satellite locator 612. Specifically, the vibration sensor 611 is installed on the vehicle chassis and connected to the sensor module through a wireless network to detect vibration changes during the vehicle's driving process, so as to timely detect potential collisions or severe bumps; the satellite locator 612 is integrated inside the vehicle and connected to the sensor module through a wireless network to provide real-time location information to ensure that the fleet manager can accurately track the vehicle's location.

[0169] The hazardous material sensor 620 is arranged on the hazardous material container of the transport vehicle and is used to collect hazardous material sensing data. In one example, taking the hazardous material container as a tank body as an example, the hazardous material sensor 620 includes a temperature sensor 621 and a pressure sensor 622. Specifically, the temperature sensor 621 is installed inside the tube body to monitor the temperature changes of the hazardous materials during transportation to ensure that the temperature remains within a safe range. The pressure sensor 622 is deployed on the top and side of the tank body to monitor the pressure inside the tank and prevent leakage or explosion caused by abnormal pressure. In actual implementation, the optical fiber grating can be set close to the surface of the tank body and do not overlap each other, and the temperature sensor 621 and the pressure sensor 622 are arranged in series on the grating.

[0170] The IoT gateway 630 is respectively connected to the vehicle sensor 610, the dangerous goods sensor 620 and the central processor 640 by signals, and is used to send the received vehicle sensor data and dangerous goods sensor data to the central processor 640. In one example, the IoT gateway 630 includes a sensor module 631 and a data processing module 632; the sensor module 631 is used to connect to the vehicle sensor 610 and the dangerous goods sensor 620 by signals to obtain the vehicle sensor data and the dangerous goods sensor data; the data processing module 632 is used to pre-process the vehicle sensor data and the dangerous goods sensor data to reduce the amount of data sent to the central processor 640.

[0171] The central processor 640 is used to execute the safety supervision and alarm method for road hazardous goods transport vehicles provided by the above method embodiment. In one example, the central processor 640 includes a data analysis module 641 and an alarm module 642; the data analysis module 641 is used to execute the safety supervision and alarm method for road hazardous goods transport vehicles provided by the above method embodiment, and further, the data analysis module 641 can store vehicle sensor data and hazardous goods sensor data; the alarm module 642 is used to output alarm information when it is determined that there is a safety risk in the transport vehicle, such as: controlling the sound and light alarm device set on the transport vehicle to alarm, and / or sending alarm information to the driver, fleet manager and relevant departments through SMS, phone call, application (APP) push, etc. Further, the central processor 640 also includes a communication module 643 for communicating with other devices (such as: Internet of Things gateway 630). In one example, the communication module 643 uses low-power LoRa, Bluetooth, Wi-Fi, 4G / 5G communication technology to ensure that sensor data can be stably and efficiently transmitted to the central processor 640.

[0172] Furthermore, the embodiment of the present application also includes a cloud platform 650 connected to the central processor 640 by signal, which is used to receive and display the vehicle's location information, status data and alarm records in real time. The cloud platform provides a visual interface to display the vehicle's real-time location, temperature, pressure, vibration and other status information, and supports historical data query and statistical analysis functions. Fleet managers can remotely monitor and manage the safety status of dangerous goods transport vehicles through the cloud platform, and respond and handle them in a timely manner.

[0173] The present application also provides an electronic device. Figure 7 As shown, Figure 7 The electronic device 700 shown includes: a processor 701 and a memory 703. The processor 701 and the memory 703 are connected, such as through a bus 702. Optionally, the electronic device 700 may also include a transceiver 704. It should be noted that in actual applications, the transceiver 704 is not limited to one, and the structure of the electronic device 700 does not constitute a limitation on the embodiments of the present application.

[0174] Processor 701 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 701 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0175] The bus 702 may include a path to transmit information between the above components. The bus 702 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 702 may be divided into an address bus, a data bus, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0176] The memory 703 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0177] The memory 703 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 701. The processor 701 is used to execute the application code stored in the memory 703 to implement the contents shown in the above method embodiment.

[0178] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, PDAs (personal digital assistants), PADs (tablet computers), etc., and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server terminal, etc. Figure 7 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0179] It should be understood that although the steps in the flowchart of the accompanying drawings are shown in sequence according to the instructions of the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise clearly stated in this document, the execution of these steps is not strictly limited in order and can be performed in other orders.

[0180] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A safety supervision and alarm method for road hazardous goods transport vehicles, characterized in that: The method comprises: Acquire vehicle sensor data collected by a vehicle sensor provided on a transport vehicle and dangerous goods sensor data collected by a dangerous goods sensor provided on a dangerous goods container of the transport vehicle, wherein the vehicle sensor data includes vehicle speed and vibration conditions; Determining whether the dangerous goods sensing data matches a preset risk judgment standard; In the case where the dangerous goods sensor data does not match the risk judgment standard, inputting the vehicle sensor data and the dangerous goods sensor data into a data prediction model to obtain dangerous goods prediction data; Determining whether the dangerous goods prediction data matches the risk judgment standard; In the case where the dangerous goods prediction data matches the risk judgment standard, determining that the transport vehicle has a safety risk and outputting an alarm message; The data prediction model is obtained by training an initial network model using training data, the initial network model is a long short-term memory network model, the training data includes at least one set of sample data, and the sample data is determined based on vehicle sensor data within a sample time period and sample dangerous goods sensor data within the sample time period; The sample data includes speed influencing factors and vibration influencing factors, and the process of determining the sample data includes: Predicting a vibration change of the vehicle based on a change in the vehicle speed during the sample time period to obtain predicted vibration data; Determining the speed influencing factor based on the difference between the predicted vibration data within the sample time period and the vibration condition; Predicting a change in the speed of the vehicle based on a change in the vibration condition within the sample time period to obtain predicted speed data; The vibration influencing factor is determined based on a difference between the predicted speed data within the sample time period and the vehicle speed.

2. The method according to claim 1, characterized in that After determining whether the dangerous goods sensing data matches the preset risk judgment standard, the method further includes: In the case where the dangerous goods sensing data matches the risk judgment standard, determining whether to verify the judgment result; In the case where it is determined that the judgment result is not to be verified, determining that there is a safety risk for the transport vehicle; In the case where it is determined to verify the judgment result, determining whether the transport vehicle has a safety risk by combining the vehicle sensor data and the dangerous goods sensor data; When it is determined that the transport vehicle has a safety risk, an alarm message is output.

3. The method according to claim 2, characterized in that The determining whether to verify the judgment result includes: Determining whether the dangerous goods sensing data matches a preset abnormality judgment standard; In the case where the dangerous goods sensing data does not match the abnormality judgment standard, determining whether the transport vehicle has dangerous driving behavior; In the case where it is determined that the transport vehicle does not have any dangerous driving behavior, it is determined to verify the judgment result.

4. The method according to claim 3, characterized in that Determining whether the transport vehicle has dangerous driving behavior includes: Acquiring positioning data of the transport vehicle; Determine the road condition information of the current road of the transport vehicle based on the positioning data; Determining whether the type of dangerous goods in the transport vehicle matches the road condition information; In the case where the type of dangerous goods in the transport vehicle matches the road condition information, determining whether the vehicle sensor data matches the road condition information; When the vehicle sensor data matches the road condition information, it is determined that there is no dangerous driving behavior of the transport vehicle.

5. The method according to claim 2, characterized in that: The determining whether the dangerous goods sensing data matches a preset risk judgment standard includes: Determining whether the dangerous goods sensing data exceeds a preset safety range; In the case where the dangerous goods sensing data does not exceed the safety range, determining whether the fluctuation amplitude of the dangerous goods sensing data is greater than a preset amplitude threshold; When the fluctuation amplitude is greater than the amplitude threshold, it is determined that the dangerous goods sensing data matches the risk judgment standard.

6. The method according to claim 5, characterized in that The combining of the vehicle sensor data and the dangerous goods sensor data to determine whether the transport vehicle presents a safety risk comprises: When the hazardous goods sensor data exceeds the safety range, a monitoring duration is determined based on the vehicle sensor data, and monitoring of the hazardous goods sensor data begins; when the hazardous goods sensor data does not fall within the safety range within the monitoring duration, it is determined that there is a safety risk with the transport vehicle.

7. The method according to claim 6, characterized in that The determining of the monitoring duration based on the vehicle sensor data includes: determining the monitoring duration based on the vehicle speed and / or the vibration condition.

8. The method according to claim 5, characterized in that The combining of the vehicle sensor data and the dangerous goods sensor data to determine whether the transport vehicle presents a safety risk comprises: When the fluctuation amplitude is greater than a preset amplitude threshold, the amplitude threshold is adjusted based on the vehicle sensor data, and when the fluctuation amplitude is greater than the adjusted fluctuation amplitude threshold, it is determined that the transport vehicle has a safety risk.

9. A road hazardous goods transport vehicle safety supervision and alarm system, characterized in that: The system includes vehicle sensors, hazardous materials sensors, an IoT gateway, and a central processor; The vehicle sensor is arranged on the transport vehicle and is used to collect vehicle sensor data; The hazardous goods sensor is disposed on the hazardous goods container of the transport vehicle and is used to collect hazardous goods sensing data; The Internet of Things gateway is respectively connected to the vehicle sensor, the dangerous goods sensor and the central processor by signal, and is used to send the received vehicle sensor data and the dangerous goods sensor data to the central processor; The central processing unit is used to execute the road hazardous goods transport vehicle safety supervision and alarm method as described in any one of claims 1 to 8.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; Memory; At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the road hazardous goods transport vehicle safety supervision and alarm method as described in any one of claims 1 to 8.

Images