A smart dispatching system and method for drug transport vehicles

Abstract

The present invention discloses an intelligent dispatching system and method for drug transport vehicles, and relates to the technical field of vehicle transport dispatching. The present invention adopts an adaptive control algorithm to automatically adjust temperature control system parameters according to real-time monitored temperature data and environmental changes, so as to provide more accurate and stable temperature control; the adaptive controller adopts a neural network controller NNC to adjust the working mode of the refrigeration equipment in real time according to the ambient temperature and the vehicle status; at the same time, a sensor network is used to collect temperature data inside and outside the vehicle in real time, and the control parameters are dynamically adjusted through a feedback mechanism to keep the temperature of the drug transport environment constant, thereby solving the problem that the control method based on a preset temperature range in the prior art is solved. In the actual transportation process, it will be affected by the external environment temperature and the vehicle operation status, and it is difficult to maintain a stable drug storage environment; once a sensor failure or data loss occurs, the effectiveness of temperature monitoring will be greatly affected.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle transportation scheduling, and in particular to an intelligent scheduling system and method for drug transportation vehicles. Background Art

[0002] Vehicle dispatch is one of the important functions of the vehicle dispatch management system. Its main purpose is to arrange the use of vehicles reasonably and ensure the normal and safe operation of vehicles. Vehicle dispatch can be adjusted according to different needs, such as adjusting the number of vehicles, adjusting the use time of vehicles, adjusting the departure time of vehicles, etc. The specific implementation of vehicle dispatch can be achieved through the vehicle dispatch algorithm. At present, the supervision of drug transportation is roughly similar to that of the fresh cold chain, but in fact, the temperature and timeliness requirements of drugs are much higher than those of the cold chain. It is extremely important to monitor the quality of drugs during transportation.

[0003] For example, the patent with publication number CN117273565A discloses an order recommendation method, system and storage medium based on smart logistics, and the method includes: obtaining the basic carrier information of the target driver and the transport vehicle information of the target driver; establishing the personal card of the target driver according to the basic carrier information and the transport vehicle information, and determining the transport area preference of the target driver; when it is monitored that the matching degree between the transport route of the order to be dispatched and the transport area preference of the target driver is higher than the first preset threshold, and it is monitored that the matching degree between the cargo information of the order to be dispatched and the transport vehicle information is higher than the second preset threshold; recommending the order to be dispatched to the display terminal of the target driver, or sending the personal card of the target driver to the terminal of the consignor of the order to be dispatched. The present invention will give priority to recommending the orders to be dispatched that meet the transport areas that the target driver is familiar with or prefers to the target driver or recommending the target driver to the consignor, thereby improving the efficiency of vehicle-cargo matching.

[0004] The above-mentioned solution is the transportation monitoring method of most traditional solutions. This method cannot provide sufficient monitoring effects when used in drug transportation. The quality assurance of drugs mainly lies in two aspects: temperature control and real-time monitoring during drug transportation. Drugs are very sensitive to temperature changes, especially vaccines and blood products, which have extremely strict temperature requirements. Traditional temperature control methods are mostly based on a preset temperature range for control, but in the actual transportation process, factors such as the external ambient temperature and the vehicle's operating status will cause temperature fluctuations, making it difficult to maintain a stable drug storage environment. In addition, the current temperature sensor network also has limitations in reliability and accuracy, and is easily affected by external interference. Once a sensor failure or data loss occurs, it will have a great impact on the effectiveness of temperature monitoring. Therefore, there is an urgent need for an intelligent scheduling system and method for drug transportation vehicles to solve such problems. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides an intelligent scheduling system and method for drug transport vehicles to solve the problem that the prior art uses a control method based on a preset temperature range. During the actual transportation process, it will be affected by the external ambient temperature and the vehicle operating status, making it difficult to maintain a stable drug storage environment; once a sensor failure or data loss occurs, it will have a great impact on the effectiveness of temperature monitoring.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0007] The present invention provides a method for intelligent dispatching of drug transport vehicles, comprising:

[0008] Step 1. Initialize the smart dispatching system, perform vehicle inspection and system self-inspection. The vehicle inspection includes inspection of refrigeration equipment, neural network controller NNC, and redundant temperature sensor network, and calibrate all temperature sensors. The system self-inspection includes control effect inspection of neural network controller NNC, sensor network transmission inspection, and cloud platform communication inspection.

[0009] Step 2. Drug loading and departure: After the system is initialized, the drugs are loaded according to the temperature requirements and transportation conditions of the drugs, and the loading information is recorded; transportation begins according to the route planned in the initialization step of the smart scheduling system;

[0010] Step 3. Adaptive temperature control and monitoring: temperature sensors are installed inside and outside the vehicle, and temperature data is monitored in real time using the temperature sensors inside and outside the vehicle;

[0011] The adaptive temperature control method is: using a neural network controller NNC to automatically adjust the working mode of the refrigeration equipment according to the real-time monitored temperature data and environmental changes, and dynamically adjust the control parameters through the feedback mechanism to keep the temperature inside the car constant within the temperature requirement range of the medicine;

[0012] In the adaptive temperature control and monitoring steps, data fusion and redundancy management are performed:

[0013] Multiple groups of temperature sensors integrate data through Bayesian inference algorithms to eliminate the error of a single sensor. Redundant sensors are designed here so that even if some sensors fail, the system can still obtain accurate temperature data through other sensors.

[0014] Step 4. Monitoring and early warning during transportation: upload the temperature data of all vehicles during drug transportation to the cloud platform in real time, and monitor the temperature change trend in real time through big data analysis and machine learning algorithms; when the temperature deviates from the set range, the system automatically triggers an early warning, notifies relevant personnel to take measures, and records the abnormal situation;

[0015] Step 5. Emergency response adjustment: Based on big data and AI technology, possible emergencies are predicted in real time, including equipment failure, traffic jams, and weather changes, and targeted response strategies are provided;

[0016] Step 6. Drug delivery: After arriving at the destination, deliver the drugs and record the delivery information and transportation process data information.

[0017] The present invention is further configured such that system initialization also includes drug information input and route planning:

[0018] Enter detailed information about the medicines being transported, including temperature requirements, destination, and estimated shipping time; use intelligent scheduling algorithms to plan shipping routes based on current traffic, weather, and historical data;

[0019] The present invention is further configured such that the adaptive temperature control and monitoring method is:

[0020] Suppose that multiple sets of redundant temperature sensors T are installed inside the vehicle. in,i , i represents the specific number of internal sensor groups, each group of sensors is used to monitor the temperature at different locations in the vehicle; multiple groups of redundant temperature sensors are installed outside the vehicle and are set to T out,j , j is the number of external sensor groups: T in ={T in,1 ,T in,2 ,...,T in,i}, T out ={T out,1 ,T out,2 ,...,T out,j}

[0021] Set the data collection frequency to once per second and fuse the temperature data using the Bayesian inference algorithm: P(T true |T in )∝P(T in |T true )P(T true ), where P(T true |T in ) represents the actual temperature distribution after fusion, P(T in |T true ) is the likelihood function of sensor data, P(T true ) is the prior distribution;

[0022] The sensor data is smoothed using the weighted average method. Where T fused represents the temperature after fusion, w i represents the data weight of the i-th sensor, where the weight is dynamically adjusted according to the historical accuracy and current stability of the sensor;

[0023] The smoothed data is input into the neural network controller NNC for subsequent processing;

[0024] The present invention is further configured such that the adaptive temperature control and monitoring method further includes:

[0025] The fused in-vehicle temperature data T fused And external ambient temperature data T out Input neural network controller NNC, expressed as X = [T fused ,T out ,ΔT env ,S], where ΔT env =T out -T fused represents the temperature difference between inside and outside, S represents other vehicle status parameters, including speed and vibration;

[0026] NNC receives input data and calculates the operating parameters of the refrigeration equipment according to the training model, ω={w 1 ,w 2 ,...w k}, y = f{w,X}, where

[0027] ω is the weight of the neural network, and y is the output control signal, including the working mode and intensity of the refrigeration equipment;

[0028] The adaptive controller adjusts the working mode of the refrigeration equipment in real time according to the calculation results of NNC, Q = α·y + β, where Q is the working parameter of the refrigeration equipment, and α and β are adjustment coefficients;

[0029] Dynamically adjust control parameters through feedback mechanism to keep the temperature inside the car constant within the set range;

[0030] The present invention is further configured such that the feedback mechanism is expressed as:

[0031] ΔT=T target -T fused ;

[0032] Where ΔT represents the temperature error, that is, the difference between the set temperature and the current fusion temperature, k p is the proportional control gain, k i is the integral control gain, k d is the differential control gain, the control parameter adjusts the system response through the PID controller, Q(t) represents the operating parameter of the refrigeration equipment at the current time step, and Q(t-1) represents the operating parameter of the refrigeration equipment at the previous time step;

[0033] The present invention is further configured that the transportation process monitoring and early warning method is:

[0034] Real-time collection of vehicle temperature data T through temperature sensors in And the outside temperature data T out ;Upload temperature data to the cloud platform in real time through the vehicle communication module;

[0035] The cloud platform stores the uploaded temperature data in the cloud platform database, uses big data analysis technology to process historical temperature data, and identifies temperature change trends: T trend =T sis (T in ,T out ), where T trend is the temperature change trend, T sis It is the process of using ARIMA model for trend analysis;

[0036] Machine learning algorithms are used to predict future temperature changes and assist the adaptive control system in parameter adjustment. pred =M l (T in ,T out ,S), where T pred represents the predicted future temperature, M l Represents the machine learning prediction algorithm, using linear regression, decision tree regression and LSTM,

[0037] S represents relevant environment and state parameters;

[0038] The present invention is further configured that the transportation process monitoring and early warning method also includes:

[0039] Calculate the temperature error, E(t) = |T in (t)-T target |, where E(t) is the temperature error, T in (t) represents the current temperature inside the car, T target Indicates the set target temperature;

[0040] The warning condition is expressed as: Among them A l (t) is the warning signal, 1 indicates abnormal temperature, 0 indicates normal temperature, ΔT td Indicates the temperature deviation threshold;

[0041] When an abnormality is detected, the system automatically triggers an early warning and notifies relevant personnel to take measures;

[0042] The present invention also provides a drug transport vehicle intelligent dispatching system, using the above-mentioned drug transport vehicle intelligent dispatching method, comprising:

[0043] Adaptive temperature control system, used for adaptive temperature control; the adaptive temperature control system includes refrigeration equipment, neural network controller NNC and redundant temperature sensor network;

[0044] Central control system, used for temperature data transmission, storage and analysis during transportation; the central control system includes cloud platform and early warning unit;

[0045] The monitoring and early warning methods for the transportation process are:

[0046] All temperature data is uploaded to the cloud platform in real time. Through big data analysis and machine learning algorithms, the temperature change trend is monitored to assist the adaptive control system in parameter adjustment. Through cloud platform monitoring, the effect of the adaptive temperature control system is further confirmed to ensure the accuracy and stability of temperature control.

[0047] When the temperature deviates from the set range, the system automatically triggers an early warning;

[0048] Communication system, used for data transmission between modules; the communication system includes real-time monitoring equipment and communication modules;

[0049] The communication system monitors the temperature data in real time based on the temperature sensors inside and outside the vehicle, and uploads the collected temperature data to the cloud platform in real time through the communication module;

[0050] Data is stored on the cloud platform, and machine learning algorithms are used on the cloud platform to analyze temperature data in real time and detect temperature anomalies;

[0051] When the temperature is detected to deviate from the set range, the system automatically generates an early warning notification;

[0052] The present invention is further configured such that the adaptive temperature control and monitoring method is:

[0053] Use temperature sensors inside and outside the vehicle to monitor temperature data in real time; redundant temperature sensor network collects ambient temperature and vehicle status data in real time:

[0054] The neural network controller NNC automatically adjusts the working mode of the refrigeration equipment according to the real-time monitored temperature data and environmental changes;

[0055] The adaptive controller dynamically adjusts the control parameters and keeps the temperature inside the vehicle constant within the set range through a feedback mechanism;

[0056] The adaptive temperature control system inputs the collected data of vehicle internal and external temperature into the NNC for analysis and outputs adjustment signals to the refrigeration equipment;

[0057] The NNC receives the data and calculates the operating parameters of the refrigeration equipment based on the training model;

[0058] The controller adjusts the working mode of the refrigeration equipment in real time according to the NNC calculation results;

[0059] The present invention is further configured such that the data fusion and redundancy management method is:

[0060] Multiple groups of temperature sensors integrate data through Bayesian inference algorithms. The redundant design of the temperature sensor network ensures that even if some sensors fail, the system can still obtain temperature data through other sensors, providing data support for adaptive temperature control.

[0061] A redundant temperature sensor network transmits data in real time to a central control system;

[0062] Data analysis is performed in the central control system, and the data from different sensors are comprehensively processed using the Bayesian inference algorithm. If partial sensor failure or data anomaly is detected, the system automatically ignores the sensor data with the failure and data anomaly and compensates with data from other sensors.

[0063] Compared with the prior art, the present invention has the following beneficial effects:

[0064] The present invention adopts an adaptive control algorithm to automatically adjust the temperature control system parameters according to the real-time monitored temperature data and environmental changes, providing more accurate and stable temperature control;

[0065] The adaptive controller uses a neural network controller NNC to adjust the working mode of the refrigeration equipment in real time according to the ambient temperature and vehicle status. At the same time, it uses a sensor network to collect temperature data inside and outside the vehicle in real time, and dynamically adjusts control parameters through a feedback mechanism to keep the temperature of the drug transportation environment constant.

[0066] The present invention aims at the problem of unstable temperature sensor network, adopts a multi-redundant temperature sensor network, and combines data fusion technology to improve the reliability and accuracy of temperature data; installs multiple groups of temperature sensors in the vehicle, integrates the data of each sensor through the Bayesian reasoning algorithm, eliminates the error of a single sensor, and thus improves the monitoring accuracy;

[0067] Redundant sensor design is adopted. Even if some sensors fail, the system can still obtain accurate temperature data through other sensors.

[0068] The present invention deploys a real-time remote monitoring and early warning system based on a cloud platform, and any temperature anomalies that occur during transportation can be handled in a timely manner;

[0069] The temperature data of all vehicles is uploaded to the cloud platform in real time. Through big data analysis and machine learning algorithms, the temperature change trend is monitored in real time. When the temperature deviates from the set range, the system automatically triggers an early warning, notifies relevant personnel to take measures, and records the abnormal situation.

[0070] The invention solves the problem that the control method based on a preset temperature range in the prior art is difficult to maintain a stable drug storage environment due to the influence of the external ambient temperature and the vehicle operating status during the actual transportation process; once a sensor failure or data loss occurs, it will have a great impact on the effectiveness of temperature monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 This is a framework diagram of the intelligent scheduling system for drug transport vehicles of the present invention. DETAILED DESCRIPTION

[0072] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0073] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0074] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0075] Example 1

[0076] See also Figure 1 The present invention provides a method for intelligently dispatching drug transport vehicles, comprising:

[0077] Step 1. Initialize the smart dispatching system, perform vehicle inspection and system self-inspection. The vehicle inspection includes inspection of refrigeration equipment, neural network controller NNC, and redundant temperature sensor network, and calibrate all temperature sensors. The system self-inspection includes control effect inspection of neural network controller NNC, sensor network transmission inspection, and cloud platform communication inspection.

[0078] System initialization also includes drug information input and route planning:

[0079] Enter detailed information about the medicines being transported, including temperature requirements, destination, and estimated shipping time; use intelligent scheduling algorithms to plan shipping routes based on current traffic, weather, and historical data;

[0080] Step 2. Drug loading and departure: After the system is initialized, the drugs are loaded according to the temperature requirements and transportation conditions of the drugs, and the loading information is recorded; transportation begins according to the route planned in the initialization step of the smart scheduling system;

[0081] Step 3. Adaptive temperature control and monitoring: temperature sensors are installed inside and outside the vehicle, and temperature data is monitored in real time using the temperature sensors inside and outside the vehicle;

[0082] The adaptive temperature control method is: using a neural network controller NNC to automatically adjust the working mode of the refrigeration equipment according to the real-time monitored temperature data and environmental changes, and dynamically adjust the control parameters through the feedback mechanism to keep the temperature inside the car constant within the temperature requirement range of the medicine;

[0083] In the adaptive temperature control and monitoring steps, data fusion and redundancy management are performed:

[0084] Multiple groups of temperature sensors integrate data through Bayesian inference algorithms to eliminate the error of a single sensor. Redundant sensors are designed here so that even if some sensors fail, the system can still obtain accurate temperature data through other sensors.

[0085] Suppose that multiple sets of redundant temperature sensors T are installed inside the vehicle. in,i，i represents the specific number of internal sensor groups, each group of sensors is used to monitor the temperature at different locations in the vehicle; multiple groups of redundant temperature sensors are installed outside the vehicle and are set to T out,j , j is the number of external sensor groups: T in ={T in,1 ,T in,2 ,...,T in,i}, T out ={T out,1 ,T out,2 ,...,T out,j}

[0086] Set the data collection frequency to once per second and fuse the temperature data using the Bayesian inference algorithm: P(T true |T in )∝P(T in |T true )P(T true ), where P(T true |T in ) represents the actual temperature distribution after fusion, P(T in |T true ) is the likelihood function of sensor data, P(Ttrue ) is the prior distribution;

[0087] The sensor data is smoothed using the weighted average method. Where T fused represents the temperature after fusion, w i represents the data weight of the i-th sensor, where the weight is dynamically adjusted according to the historical accuracy and current stability of the sensor;

[0088] The smoothed data is input into the neural network controller NNC for subsequent processing;

[0089] The fused in-vehicle temperature data T fused And external ambient temperature data T out Input neural network controller NNC, expressed as X = [T fused ,T out ,ΔT env ,S], where ΔT env =T out -T fused represents the temperature difference between inside and outside, S represents other vehicle status parameters, including speed and vibration;

[0090] NNC receives input data and calculates the operating parameters of the refrigeration equipment according to the training model, ω={w 1 ,w 2 ,...w k}, y = f{w,X}, where

[0091] ω is the weight of the neural network, and y is the output control signal, including the working mode and intensity of the refrigeration equipment;

[0092] The adaptive controller adjusts the working mode of the refrigeration equipment in real time according to the calculation results of NNC, Q = α·y + β, where Q is the working parameter of the refrigeration equipment, and α and β are adjustment coefficients;

[0093] Dynamically adjust control parameters through feedback mechanism to keep the temperature inside the car constant within the set range;

[0094] ΔT=T target -T fused ;

[0095] Where ΔT represents the temperature error, that is, the difference between the set temperature and the current fusion temperature, k p is the proportional control gain, k i is the integral control gain, k dis the differential control gain, the control parameter adjusts the system response through the PID controller, Q(t) represents the operating parameter of the refrigeration equipment at the current time step, and Q(t-1) represents the operating parameter of the refrigeration equipment at the previous time step;

[0096] Step 4. Monitoring and early warning during transportation: upload the temperature data of all vehicles during drug transportation to the cloud platform in real time, and monitor the temperature change trend in real time through big data analysis and machine learning algorithms; when the temperature deviates from the set range, the system automatically triggers an early warning, notifies relevant personnel to take measures, and records the abnormal situation;

[0097] Real-time collection of vehicle temperature data T through temperature sensors in And the outside temperature data T out ;Upload temperature data to the cloud platform in real time through the vehicle communication module;

[0098] The cloud platform stores the uploaded temperature data in the cloud platform database, uses big data analysis technology to process historical temperature data, and identifies temperature change trends: T trend =T sis (T in ,T out ), where T trend is the temperature change trend, T sis It is the process of using ARIMA model for trend analysis;

[0099] Machine learning algorithms are used to predict future temperature changes and assist the adaptive control system in parameter adjustment. pred =M l (T in ,T out ,S), where T pred represents the predicted future temperature, M l Represents the machine learning prediction algorithm, using linear regression, decision tree regression and LSTM,

[0100] S represents relevant environment and state parameters;

[0101] Calculate the temperature error, E(t) = |T in (t)-T target |, where E(t) is the temperature error, T in (t) represents the current temperature inside the car, T target Indicates the set target temperature;

[0102] The warning condition is expressed as: Among them A l (t) is the warning signal, 1 indicates abnormal temperature, 0 indicates normal temperature, ΔT td Indicates the temperature deviation threshold;

[0103] When an abnormality is detected, the system automatically triggers an early warning and notifies relevant personnel to take measures;

[0104] Step 5. Emergency response adjustment: Based on big data and AI technology, possible emergencies are predicted in real time, including equipment failure, traffic jams, and weather changes, and targeted response strategies are provided;

[0105] Step 6. Drug delivery: After arriving at the destination, deliver the drugs and record the delivery information and transportation process data information;

[0106] The present invention also provides a drug transport vehicle intelligent dispatching system, comprising:

[0107] Adaptive temperature control system, used for adaptive temperature control; the adaptive temperature control system includes refrigeration equipment, neural network controller NNC and redundant temperature sensor network;

[0108] The adaptive temperature control and monitoring methods are:

[0109] Use temperature sensors inside and outside the vehicle to monitor temperature data in real time; redundant temperature sensor network collects ambient temperature and vehicle status data in real time:

[0110] The neural network controller NNC automatically adjusts the working mode of the refrigeration equipment according to the real-time monitored temperature data and environmental changes;

[0111] The adaptive controller dynamically adjusts the control parameters and keeps the temperature inside the vehicle constant within the set range through a feedback mechanism;

[0112] The adaptive temperature control system inputs the collected data of vehicle internal and external temperature into the NNC for analysis and outputs adjustment signals to the refrigeration equipment;

[0113] The NNC receives the data and calculates the operating parameters of the refrigeration equipment based on the training model;

[0114] The controller adjusts the working mode of the refrigeration equipment in real time according to the NNC calculation results;

[0115] Central control system, used for temperature data transmission, storage and analysis during transportation; the central control system includes cloud platform and early warning unit;

[0116] The monitoring and early warning methods for the transportation process are:

[0117] All temperature data is uploaded to the cloud platform in real time. Through big data analysis and machine learning algorithms, the temperature change trend is monitored to assist the adaptive control system in parameter adjustment. Through cloud platform monitoring, the effect of the adaptive temperature control system is further confirmed to ensure the accuracy and stability of temperature control.

[0118] When the temperature deviates from the set range, the system automatically triggers an early warning;

[0119] Data fusion and redundancy management methods are:

[0120] Multiple groups of temperature sensors integrate data through Bayesian inference algorithms. The redundant design of the temperature sensor network ensures that even if some sensors fail, the system can still obtain temperature data through other sensors, providing data support for adaptive temperature control.

[0121] A redundant temperature sensor network transmits data in real time to a central control system;

[0122] Data analysis is performed in the central control system, and the Bayesian inference algorithm is used to comprehensively process the data from different sensors. If some sensor failures or data anomalies are detected, the system automatically ignores the sensor data with failures and data anomalies, and compensates with data from other sensors;

[0123] Communication system, used for data transmission between modules; the communication system includes real-time monitoring equipment and communication modules;

[0124] The communication system monitors the temperature data in real time based on the temperature sensors inside and outside the vehicle, and uploads the collected temperature data to the cloud platform in real time through the communication module;

[0125] Data is stored on the cloud platform, and machine learning algorithms are used on the cloud platform to analyze temperature data in real time and detect temperature anomalies;

[0126] When it is detected that the temperature deviates from the set range, the system automatically generates an early warning notification.

[0127] The present invention performs vehicle detection and system self-checking during the initialization phase of the intelligent dispatching system; inputs detailed information of the transported medicines, including temperature requirements, destination, and estimated transport time, and uses an intelligent dispatching algorithm to plan the transport route based on current traffic, weather, and historical data;

[0128] During the drug loading and departure stage, the drugs are loaded according to the temperature requirements and transportation conditions of the drugs, and the loading information is recorded. Then, the transportation begins according to the route planned in the initialization stage of the intelligent scheduling system. During the transportation process, the system monitors the temperature data in real time through temperature sensors installed inside and outside the vehicle, and adopts an adaptive temperature control method. The NNC automatically adjusts the working mode of the refrigeration equipment according to the real-time monitored temperature data and environmental changes. In the adaptive temperature control and monitoring steps, data fusion and redundancy management are performed, and the Bayesian inference algorithm is used to integrate multiple sets of temperature sensor data, eliminate the error of a single sensor, and design redundant sensors. Even if some sensors fail, the system can still obtain accurate temperature data through other sensors.

[0129] During the adaptive temperature control and monitoring process, the integrated in-vehicle temperature data and external ambient temperature data are input into the NNC to calculate the working parameters of the refrigeration equipment, and the working mode of the refrigeration equipment is adjusted in real time according to the calculation results of the NNC; the control parameters are dynamically adjusted through the feedback mechanism to keep the in-vehicle temperature constant within the set range, and the PID controller is used to adjust the system response; in the monitoring and early warning stage of the transportation process, the temperature data of all vehicles are uploaded to the cloud platform in real time, and the temperature change trend is monitored in real time through big data analysis and machine learning algorithms. When the temperature deviates from the set range, the system automatically triggers an early warning, notifies relevant personnel to take measures, and records abnormal situations.

[0130] The above contents are only for explaining the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A method for intelligent dispatching of drug transport vehicles, characterized in that: include: Step 1. Initialize the smart dispatching system, perform vehicle inspection and system self-inspection. The vehicle inspection includes inspection of refrigeration equipment, neural network controller NNC, and redundant temperature sensor network, and calibrate all temperature sensors. The system self-inspection includes control effect inspection of neural network controller NNC, sensor network transmission inspection, and cloud platform communication inspection. Step 2. Drug loading and departure: After the system is initialized, the drugs are loaded according to the temperature requirements and transportation conditions of the drugs, and the loading information is recorded; transportation begins according to the route planned in the initialization step of the smart scheduling system; Step 3. Adaptive temperature control and monitoring: temperature sensors are installed inside and outside the vehicle, and temperature data is monitored in real time using the temperature sensors inside and outside the vehicle; The adaptive temperature control method is: using a neural network controller NNC to automatically adjust the working mode of the refrigeration equipment according to the real-time monitored temperature data and environmental changes, and dynamically adjust the control parameters through the feedback mechanism to keep the temperature inside the car constant within the temperature requirement range of the medicine; In the adaptive temperature control and monitoring steps, data fusion and redundancy management are performed: Multiple groups of temperature sensors integrate data through Bayesian inference algorithms to eliminate the error of a single sensor; Step 4. Monitoring and early warning during transportation: upload the temperature data of all vehicles during drug transportation to the cloud platform in real time, and monitor the temperature change trend in real time through big data analysis and machine learning algorithms; when the temperature deviates from the set range, the system automatically triggers an early warning and records the abnormal situation; Step 5. Emergency response adjustment: Based on big data and AI technology, possible emergencies are predicted in real time, including equipment failure, traffic jams, and weather changes, and targeted response strategies are provided; Step 6. Drug delivery: After arriving at the destination, deliver the drugs and record the delivery information and transportation process data information; The system initialization also includes drug information input and route planning: Enter detailed information about the medicines being transported, including temperature requirements, destination, and estimated shipping time; use intelligent scheduling algorithms to plan shipping routes based on current traffic, weather, and historical data; The adaptive temperature control and monitoring method is: Suppose that multiple sets of redundant temperature sensors T are installed inside the vehicle. in,i , i represents the specific number of internal sensor groups, each group of sensors is used to monitor the temperature at different locations in the vehicle; multiple groups of redundant temperature sensors are installed outside the vehicle and are set to T out,j , j is the number of external sensor groups: T in ={T in,1 ,T in,2 ,...,T in,i }, T out ={T out,1 ,T out,2 ,...,T out,j } Set the data collection frequency to once per second and fuse the temperature data using the Bayesian inference algorithm: P(T true |T in )∝P(T in |T true )P(T true ), where P(T true |T in ) represents the actual temperature distribution after fusion, P(T in |T true ) is the likelihood function of sensor data, P(T true ) is the prior distribution; The sensor data is smoothed using the weighted average method. Where T fused represents the temperature after fusion, w i represents the data weight of the i-th sensor, where the weight is dynamically adjusted according to the historical accuracy and current stability of the sensor; The smoothed data is input into the neural network controller NNC for subsequent processing; The adaptive temperature control and monitoring method also includes: The fused in-vehicle temperature data T fused And external ambient temperature data T out Input neural network controller NNC, expressed as X = [T fused ,T out ,ΔT env ,S], where ΔT env =T out -T fused represents the temperature difference between inside and outside, S represents other vehicle status parameters, including speed and vibration; NNC receives input data and calculates the operating parameters of the refrigeration equipment according to the training model, ω={w1,w2,...w k }, y = f{w,X}, where ω is the weight of the neural network, and y is the output control signal, including the working mode and intensity of the refrigeration equipment; The adaptive controller adjusts the working mode of the refrigeration equipment in real time according to the calculation results of NNC, Q = α·y + β, where Q is the working parameter of the refrigeration equipment, and α and β are adjustment coefficients; Dynamically adjust control parameters through feedback mechanism to keep the temperature inside the car constant within the set range; The feedback mechanism is expressed as: ΔT=T target -T fused ; Where ΔT represents the temperature error, that is, the difference between the set temperature and the current fusion temperature, k p is the proportional control gain, k i is the integral control gain, k d is the differential control gain. The control parameter adjusts the system response through the PID controller. Q(t) represents the operating parameter of the refrigeration equipment at the current time step, and Q(t-1) represents the operating parameter of the refrigeration equipment at the previous time step.

2. The intelligent dispatching method for drug transport vehicles according to claim 1 is characterized in that: The monitoring and early warning methods for the transportation process are: Real-time collection of vehicle temperature data T through temperature sensors in And the outside temperature data T out ;Upload temperature data to the cloud platform in real time through the vehicle communication module; The cloud platform stores the uploaded temperature data in the cloud platform database, uses big data analysis technology to process historical temperature data, and identifies temperature change trends: T trend =T sis (T in ,T out ), where T trend is the temperature change trend, T sis It is the process of using ARIMA model for trend analysis; Machine learning algorithms are used to predict future temperature changes and assist the adaptive control system in parameter adjustment. pred =M l (T in ,T out ,S), where T pred represents the predicted future temperature, M l Represents the machine learning prediction algorithm, using linear regression, decision tree regression and LSTM, S represents relevant environment and state parameters.

3. The intelligent dispatching method for drug transport vehicles according to claim 2 is characterized in that: The transportation process monitoring and early warning methods also include: Calculate the temperature error, E(t) = |T in (t)-T target |, where E(t) is the temperature error, T in (t) represents the current temperature inside the car, T target Indicates the set target temperature; The warning condition is expressed as: Among them A l (t) is the warning signal, 1 indicates abnormal temperature, 0 indicates normal temperature, ΔT td Indicates the temperature deviation threshold; When an abnormality is detected, the system automatically triggers an early warning and notifies relevant personnel to take measures.

4. A smart dispatching system for drug transport vehicles, characterized in that: A method for intelligent dispatching of drug transport vehicles according to any one of claims 1 to 3 is used, comprising: Adaptive temperature control system, used for adaptive temperature control; the adaptive temperature control system includes refrigeration equipment, neural network controller NNC and redundant temperature sensor network; Central control system, used for temperature data transmission, storage and analysis during transportation; the central control system includes cloud platform and early warning unit; The monitoring and early warning methods for the transportation process are: All temperature data is uploaded to the cloud platform in real time. Through big data analysis and machine learning algorithms, the temperature change trend is monitored and the adaptive control system is assisted to adjust parameters. When the temperature deviates from the set range, the system automatically triggers an early warning; Communication system, used for data transmission between modules; the communication system includes real-time monitoring equipment and communication modules; The communication system monitors the temperature data in real time based on the temperature sensors inside and outside the vehicle, and uploads the collected temperature data to the cloud platform in real time through the communication module; Data is stored on the cloud platform, and machine learning algorithms are used on the cloud platform to analyze temperature data in real time and detect temperature anomalies; When it is detected that the temperature deviates from the set range, the system automatically generates an early warning notification.

5. The intelligent dispatching system for drug transport vehicles according to claim 4 is characterized in that: The adaptive temperature control and monitoring methods are: Use temperature sensors inside and outside the vehicle to monitor temperature data in real time; redundant temperature sensor network collects ambient temperature and vehicle status data in real time: The neural network controller NNC automatically adjusts the working mode of the refrigeration equipment according to the real-time monitored temperature data and environmental changes; The adaptive controller dynamically adjusts the control parameters and keeps the temperature inside the vehicle constant within the set range through a feedback mechanism; The adaptive temperature control system inputs the collected data of vehicle internal and external temperature into the NNC for analysis and outputs adjustment signals to the refrigeration equipment; The NNC receives the data and calculates the operating parameters of the refrigeration equipment based on the training model; The controller adjusts the working mode of the refrigeration equipment in real time according to the NNC calculation results.

6. The intelligent dispatching system for drug transport vehicles according to claim 5 is characterized in that: Data fusion and redundancy management methods are: A redundant temperature sensor network transmits data in real time to a central control system; Data analysis is performed in the central control system, and the data from different sensors are comprehensively processed using the Bayesian inference algorithm. If partial sensor failure or data anomaly is detected, the system automatically ignores the sensor data with the failure and data anomaly and compensates with data from other sensors.

Images