Intelligent temperature control and alarm system for medical cold-chain logistics

Abstract

The invention relates to the field of medical cold-chain logistics, and discloses an intelligent temperature control and alarm system for medical cold-chain logistics, and the system comprises a temperature monitoring module which comprises a plurality of temperature sensors and a plurality of key nodes distributed in transit, collects the temperature data of an environment where medicines are located in real time, and transmits a temperature signal to a control module; the control module is used for receiving the temperature signal and calculating a required control signal based on a self-adaptive control algorithm according to the deviation between the preset target temperature and the actual temperature; and the refrigeration module adjusts the working state of refrigeration equipment according to the control signal output by the control module, and adjusts the refrigeration power by adopting a frequency conversion technology. Through multi-point temperature monitoring, an intelligent optimization control algorithm and a multi-layer alarm mechanism, high-precision temperature control, real-time response and energy optimization are realized, and the temperature control stability and the intelligent level of the cold-chain logistics system are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of medical cold chain logistics, and in particular to an intelligent temperature control and alarm system for medical cold chain logistics. Background Art

[0002] In modern society, the transportation and storage of pharmaceuticals in the medical field place extremely strict demands on temperature control. This is especially true for sensitive medications such as vaccines and biologics, where temperature fluctuations during transportation can directly impact the effectiveness and safety of the drugs. Therefore, ensuring that the temperature of pharmaceuticals remains within a strictly specified range during transportation is crucial. To ensure accurate and stable temperature control during transportation, traditional temperature control systems are increasingly unable to meet these increasingly stringent requirements.

[0003] Currently, many cold chain logistics management systems utilize temperature sensor-based monitoring technology. These systems collect real-time ambient temperature data through temperature sensors and issue alarm signals when the temperature exceeds the set range. The advantage of these systems is that they can provide basic temperature monitoring and alarm functions. Some advanced systems also integrate data storage and cloud platform analysis, providing management personnel with real-time monitoring data and historical trend charts, facilitating temperature management and record keeping.

[0004] However, existing technologies still have obvious shortcomings, especially in terms of temperature adjustment accuracy and alarm mechanisms. Existing cold chain systems usually rely on a single temperature sensor with limited placement locations and low monitoring frequency, resulting in a slow response to temperature fluctuations and the easy miss of the best time to handle temperature control anomalies. The alarm method is also too simple, mostly sound alarms or simple visual signals, which can be easily ignored in noisy environments. In addition, the existing system lacks intelligent analysis and optimization of real-time data. The adjustment strategy of the refrigeration module is usually fixed and cannot be flexibly adjusted according to changes in the real-time environment, resulting in energy waste or unstable temperature control effects. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention provides an intelligent temperature control and alarm system for medical cold chain logistics, which solves the problems of inaccurate temperature control, single alarm method and insufficient temperature data analysis in the existing cold chain logistics system.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A medical cold chain logistics intelligent temperature control and alarm system, comprising: The temperature monitoring module includes multiple temperature sensors distributed at multiple key nodes during transportation, which collect temperature data of the environment where the medicine is located in real time and transmit the temperature signal to the control module; A control module is used to receive the temperature signal and calculate the required control signal based on the adaptive control algorithm according to the deviation between the preset target temperature and the actual temperature; The refrigeration module adjusts the working state of the refrigeration equipment according to the control signal output by the control module and uses frequency conversion technology to adjust the refrigeration power; Alarm module, when the temperature deviation exceeds the set range, it will send multiple alarm signals, including audible alarm, visual alarm and notification via mobile device; The optimization module dynamically optimizes the operating parameters of the cooling module through machine learning algorithms based on the real-time collected temperature data and sliding into historical temperature fluctuations.

[0007] Preferably, the temperature monitoring module includes: Multiple temperature sensor units, each of which is placed at a key node in the cold chain transportation to collect real-time ambient temperature data at the location; A data acquisition unit is used to collect real-time temperature data from multiple temperature sensors and convert it into digital signals that can be processed by the control module; The transmission unit is used to transmit the temperature signal to the control module for subsequent processing.

[0008] Preferably, the control module includes: A signal receiving unit, configured to receive a temperature signal transmitted from a data acquisition unit of the temperature monitoring module; A temperature deviation calculation unit is used to calculate the deviation between the current temperature and the target temperature; The adaptive control unit, based on the adaptive control algorithm, dynamically adjusts the control parameters and calculates the required control signal according to the temperature deviation. The control signal u(t) is optimized and adjusted according to the system requirements to minimize temperature fluctuations. The formula is: Among them, K p ,K i , and K d are proportional, integral and differential coefficients respectively; ΔT(t) is the temperature deviation; is the differential term, which indicates the rate of change of temperature deviation; t is the integral term.

[0009] Preferably, the refrigeration module includes: The refrigeration unit uses variable frequency technology to adjust the power of the refrigeration equipment. The refrigeration effect is adjusted by controlling the frequency of the refrigeration compressor. The refrigeration power is related to the control signal u(t). The adjustment formula of the refrigeration unit is: P(t)=f(u(t),T actual (t)); Where P(t) is the cooling power; f is the regulation function; u(t) is the control signal; T actual (t) is the current measured temperature; Refrigeration efficiency optimization unit, used to monitor the energy efficiency of the refrigeration unit and optimize it.

[0010] Preferably, the alarm module includes: An alarm signal detection unit is used to detect whether the temperature deviation exceeds a preset threshold range. If the temperature deviation exceeds the set range, an alarm mechanism is triggered; An audible alarm unit, used for sounding an audible alarm to draw the attention of operators; Visual alarm unit, used to issue warning signs through LED display screen to warn of abnormal temperature; Notification unit, used to send alarm signals to relevant personnel via mobile devices and text messages for remote monitoring and intervention.

[0011] Preferably, the optimization module includes: Real-time data analysis unit, used to analyze the real-time data collected by the temperature monitoring module, including current temperature, historical temperature fluctuations and environmental factors, and generate temperature change trends; The machine learning unit dynamically optimizes the system based on real-time and historical data through machine learning algorithms and automatically adjusts the operating parameters of the cooling module; The energy efficiency evaluation unit is used to calculate the energy consumption and temperature control effect of the current system, evaluate whether the optimal operating state is achieved, and dynamically adjust the cooling power and control strategy based on the evaluation results. The optimization goal is to minimize energy consumption and temperature deviation. The optimization formula is: Where J is the optimization objective; x(t) is the temperature deviation; P(t) is the cooling power; λ1 and λ2 are the weights of temperature deviation and energy consumption, respectively; and T is the total number of time steps.

[0012] Preferably, the data acquisition unit includes: A temperature data conversion unit, configured to convert analog signals collected by the multiple temperature sensor units into digital signals; The data verification unit is used to verify and preprocess the collected temperature signal to ensure the accuracy and integrity of the signal; the data cache unit is used to temporarily store the collected temperature data.

[0013] Preferably, the temperature deviation calculation unit includes: a temperature deviation acquisition unit, configured to receive a temperature signal and calculate the deviation between the current ambient temperature and a preset target temperature, thereby generating a temperature deviation signal; The data processing unit is used to process the temperature deviation signal to ensure data accuracy and transmit the processed temperature deviation to the adaptation control unit for further control and analysis; The threshold judgment unit is used to set and adjust the allowable range of temperature deviation. When the temperature deviation exceeds the preset threshold, a signal is sent to the alarm module to indicate temperature control abnormality. The historical data comparison unit is used to compare with historical temperature fluctuation data to help analyze whether the current temperature deviation is a normal fluctuation.

[0014] Preferably, the alarm signal detection unit includes: A temperature threshold setting unit is used to set and adjust the alarm threshold of temperature deviation; An alarm trigger unit is used to automatically activate the alarm mechanism and trigger audible and visual alarms when the temperature deviation exceeds the set threshold; The alarm recording unit is used to record each temperature deviation exceeding the standard and generate a log file for management personnel to conduct subsequent analysis and tracking.

[0015] Preferably, the machine learning unit includes: Data preprocessing unit, used to preprocess real-time data and historical data, including denoising, normalization and feature extraction; The training module is used to train the machine learning algorithm, select the appropriate model, and optimize it according to the actual operation of the system; the model optimization unit dynamically adjusts the parameters in the machine learning model based on real-time data feedback and system operation results, so that the model can better adapt to environmental changes and system requirements.

[0016] The present invention provides an intelligent temperature control and alarm system for medical cold chain logistics. It has the following beneficial effects: 1. This invention utilizes multi-point temperature monitoring and intelligent temperature control technology. By deploying temperature sensors at multiple key nodes along the transportation route, it collects real-time temperature data from the environment surrounding the medicine. This achieves the technical effect of full-process real-time monitoring. Compared with existing solutions that use a single temperature control method and a small number of monitoring points, this solution solves the problems of incomplete temperature information and inaccurate temperature control.

[0017] 2. This invention introduces a temperature control optimization module based on a machine learning algorithm to dynamically adjust the operating parameters of the refrigeration system. This achieves the technical effects of improving energy efficiency and reducing temperature control errors. Compared with existing solutions based on fixed strategy control, this solves the problem of poor flexibility and inability to adapt to environmental changes.

[0018] 3. The alarm module of this invention provides multiple alarm signals, including audio, visual, and mobile device notifications, ensuring that temperature control anomalies are promptly detected. This achieves a multi-level, multi-dimensional alarm response. Compared to existing single-alarm solutions, it solves the problems of delayed alarms and incomplete information transmission.

[0019] 4. This invention utilizes an optimization algorithm based on real-time and historical data analysis, enabling the system to adjust its temperature control strategy in real time based on environmental conditions, enhancing the system's adaptability. This improves the system's intelligence and automation, and addresses the issues of susceptibility to human interference and low efficiency, compared to existing solutions that require extensive manual intervention and have low intelligence levels. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 Schematic diagram of the system architecture of the present invention; Figure 2 This is a framework diagram of the temperature monitoring module of the present invention; Figure 3 This is a control module framework diagram of the present invention; Figure 4 This is a framework diagram of the refrigeration module of the present invention; Figure 5 This is a framework diagram of the alarm module of the present invention; Figure 6 This is the optimization module framework diagram of the present invention. DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the present specification. 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 making creative efforts are within the scope of protection of the present invention.

[0022] Please see the attached Figure 1 -Attached Figure 6 The embodiment of the present invention provides an intelligent temperature control and alarm system for medical cold chain logistics, including: The temperature monitoring module includes multiple temperature sensors distributed at multiple key nodes during transportation, which collect temperature data of the environment where the medicine is located in real time and transmit the temperature signal to the control module; As the front-end sensing unit of the entire medical cold chain logistics intelligent temperature control and alarm system, the temperature monitoring module's functionality and data transmission directly impact the accuracy and stability of subsequent control modules, refrigeration modules, and alarm and optimization modules. This module performs the fundamental task of real-time sensing of temperature changes in the pharmaceutical transportation environment and provides data support for the control logic of subsequent systems.

[0023] In order to achieve a high-precision and timely temperature monitoring mechanism, this system sets up a distributed temperature sensor network at multiple key nodes. By continuously collecting the temperature of the entire cold chain transportation path in space and time, it forms a three-dimensional monitoring of the transportation environment.

[0024] In this embodiment, the temperature monitoring module includes multiple temperature sensor units, each deployed at key points in the cold chain transportation process. These locations typically include, but are not limited to, the interior of the pharmaceutical refrigeration box, the top and bottom, left and right walls of the refrigerated vehicle compartment, the exterior walls and doorways of the compartment, around cold storage shelves, and in different corners of the cargo transport container.

[0025] As an option, these temperature sensor units can be highly sensitive digital temperature sensors with a wide temperature measurement range and small error. The raw analog signal output by the sensor is digitized through voltage-to-current conversion or directly through a built-in analog-to-digital converter (ADC).

[0026] In one possible implementation, the system also sets up a redundant sensor configuration. That is, two or more sets of temperature sensors are deployed at some key nodes. In this way, in the event of sensor failure, deviation, or abnormal fluctuation, a cross-check mechanism can be used to determine data reliability.

[0027] Specifically, all temperature sensor units are connected to the data acquisition unit via wired communication (such as the CAN bus) or wireless communication (such as LoRa, ZigBee, or Wi-Fi). The data acquisition unit is responsible for unified scheduling and time synchronization, periodically sampling data from different sensors with microsecond time resolution. For example, temperature data may be collected every 10 seconds and packaged and uploaded to the control module.

[0028] In some embodiments, the temperature monitoring module further includes a temperature data conversion unit for converting the collected raw temperature signal into a standard digital temperature value. The conversion can use the following calculation model: Among them, T i represents the temperature value collected by the i-th sensor; V i Indicates the voltage signal value output by the sensor; V offset It represents the zero offset voltage of the sensor; G represents the sensitivity coefficient of the sensor.

[0029] After data conversion is complete, the data verification unit performs signal consistency analysis. This includes CRC redundancy check, mean filtering, and limit filtering. Data with significant jumps within a short period of time is removed through a dynamic filter.

[0030] In some implementations, the system also includes a data cache unit for temporarily storing historical data collected by the sensors. This cache can be structured as a circular buffer, with a typical caching window of 10 minutes to 2 hours, allowing for subsequent use in temperature trend analysis and error backtracking.

[0031] The temperature monitoring module also supports adjusting the sensor sampling frequency based on system requirements. In low-risk sections or when the ambient temperature is stable, the sampling period can be extended to 30 seconds; in high-risk areas or when the temperature fluctuates frequently, the sampling period can be compressed to 2 seconds, improving response speed.

[0032] The temperature monitoring module also integrates a status detection unit to determine whether each temperature sensor is in normal working order. If there is a signal loss, voltage anomaly, or data instability, the unit automatically records the sensor failure and sends an abnormality identification signal to the control module.

[0033] A control module is used to receive the temperature signal and calculate the required control signal based on the adaptive control algorithm according to the deviation between the preset target temperature and the actual temperature; As the core component of the intelligent temperature control and alarm system for medical cold chain logistics, the control module plays a crucial role. Its primary function is to receive real-time temperature signals from the temperature monitoring module and, based on the deviation between the preset target temperature and the actual temperature, calculate control signals to adjust the operating state of the refrigeration module. This process requires not only precise control signal calculation but also real-time response to temperature changes to ensure temperature stability during transportation.

[0034] In this embodiment, the control module receives temperature data from the temperature monitoring module. The temperature monitoring module collects ambient temperatures at multiple key points along the transport route in real time and transmits this data to the control module via a data transmission unit. After receiving the temperature signal, the control module first analyzes the data and calculates the temperature deviation—the difference between the target temperature and the actual temperature. This temperature deviation serves as an input signal, which is processed by a control algorithm to generate a control signal. This control signal is then transmitted to the refrigeration module via a data output unit to adjust the operating status of the refrigeration equipment.

[0035] In general, the temperature deviation ΔT(t) is calculated using the following formula: ΔT(t)=T actual (t)-T set ; Among them, T actual (t) is the real-time temperature; T set is the target temperature; ΔT(t) is the temperature deviation.

[0036] Alternatively, in this embodiment, the control module uses an adaptive control algorithm to calculate the required control signal. The introduction of the adaptive control algorithm enables the system to automatically adjust the control parameters according to the temperature deviation to cope with different temperature control requirements and changes in environmental conditions.

[0037] Specifically, the control module uses the PID (Proportional-Integral-Derivative) control algorithm to calculate the control signal. The PID control algorithm uses three components to comprehensively adjust the temperature deviation to generate the control signal u(t): Among them, K p ,K i , and K d are proportional, integral and differential coefficients respectively; ΔT(t) is the temperature deviation; is the differential term, which indicates the rate of change of temperature deviation; t is the integral term.

[0038] In some embodiments, in order to adapt to complex temperature control environments and changes in system response, the control module also uses an adaptive adjustment mechanism. This mechanism adjusts the coefficient K in the PID control algorithm based on historical data and real-time feedback. p ,K i , and K d , in order to achieve the best control effect in different cold chain transportation scenarios. Specifically, the control module monitors the temperature change trend in real time and continuously adjusts these control coefficients through dynamic learning algorithms. For example, when the ambient temperature fluctuates greatly, increasing K p and K d When the environment is stable, these coefficients should be appropriately reduced to avoid over-adjustment.

[0039] As another possible implementation, the control module also includes a state estimation unit. This unit preprocesses the temperature data using a Kalman filter or particle filter algorithm to obtain a more accurate temperature estimate. By predicting and correcting the temperature signal, the state estimation unit improves the system's responsiveness to short-term temperature fluctuations and avoids control signal distortion caused by signal noise or sensor errors.

[0040] The control signal is transmitted to the refrigeration module via the output unit. The module adjusts the refrigeration unit's operating status based on this signal to ensure stable temperature during transport. The amplitude of the control signal is closely related to temperature deviation. The control signal calculated by the control module based on real-time data directly affects the refrigeration unit's operating efficiency. To maximize the refrigeration unit's energy utilization, the control signal output is optimized to balance energy consumption and temperature control effectiveness.

[0041] The refrigeration module adjusts the working state of the refrigeration equipment according to the control signal output by the control module and uses frequency conversion technology to adjust the refrigeration power; The refrigeration module is designed to closely follow the control module, and its functions are based on the control signals it outputs. This module primarily drives and regulates the operating status of the refrigeration equipment to ensure that the transport environment temperature remains stable and approaches the preset target temperature. Within the system's overall temperature control loop, the refrigeration module executes control commands and regulates the heat balance. The temperature monitoring module provides raw temperature data, which the control module processes and generates adjustment commands. The refrigeration module then dynamically controls the cooling output based on these signals, achieving closed-loop temperature control.

[0042] In this embodiment, the refrigeration module includes a variable-frequency compressor refrigeration unit, an electronically controlled drive circuit, a signal receiving interface, and a refrigeration power adjustment unit. The signal receiving interface is used to receive a control signal from the control module. This control signal is an output control variable derived from a real-time temperature deviation and an adaptive PID algorithm. After receiving this control signal, the refrigeration module adjusts the operating state of the refrigeration equipment in real time based on the amplitude and direction of the control signal.

[0043] In general, the control signal u(t) is a continuously changing analog quantity, the magnitude of which determines the operating frequency of the refrigeration equipment and its corresponding output power. The refrigeration power P(t) can be expressed as the following function: P(t)=f(u(t),T actual (t)); Where P(t) is the cooling power; f is the regulation function; u(t) is the control signal; T actual (t) is the current measured temperature.

[0044] As an option, the variable frequency control is implemented based on a variable frequency drive. The variable frequency drive receives the control signal u(t) and adjusts the operating frequency f of the compressor motor in real time. r (t), and adjust the compressor speed accordingly. Compressor cooling capacity Q c The approximate relationship between this and the compressor operating frequency is: Among them, Q c (t) represents the cooling capacity; Q rated Indicates the rated cooling capacity, which is the compressor at the rated frequency f rated The cooling capacity of the output; f r (t) represents the real-time operating frequency.

[0045] In one possible implementation, the cooling module also includes a power feedback channel. This channel monitors the actual power consumption of the cooling unit in real time and feeds the power consumption data back to the control module for subsequent correction of control parameters. This power feedback can be implemented through voltage and current sampling circuits, combined with the effective power calculation formula: Pactual (t) = V(t)·I(t)·cos(φ); Among them, P actual (t) is the effective power actually consumed; V(t) is the voltage at the compressor motor terminal; I(t) is the compressor input current; cos(φ) is the power factor, which reflects the power conversion efficiency.

[0046] Specifically, after being processed internally by the variable frequency drive, the control signal is converted into a PWM (pulse width modulation) signal to control the operating state of the inverter bridge arm, thereby varying the equivalent voltage and frequency of the motor's stator windings, achieving fine speed regulation. This approach offers high regulation sensitivity and energy control accuracy.

[0047] In some embodiments, the cooling module also incorporates a temperature hysteresis determination unit to prevent frequent starts and stops due to temperature measurement fluctuations. This unit sets upper and lower limits, such as ±0.3°C. When the temperature is within the hysteresis range of the set target value, the control signal remains unchanged, thereby improving system stability and reducing equipment wear.

[0048] As a supplemental note, the power level and power interface standard of the refrigeration module can be configured differently based on the specific application environment, such as transport vehicles, electric refrigerators, and pharmaceutical cold storage. For smaller mobile cold chain units, a DC compressor refrigeration system can be used; for larger warehouses, a three-phase AC compressor and independent refrigeration station system can be used.

[0049] Alarm module, when the temperature deviation exceeds the set range, it will send multiple alarm signals, including audible alarm, visual alarm and notification via mobile device; As a crucial component of the intelligent temperature control and alarm system for medical cold chain logistics, the alarm module provides timely feedback and warnings regarding temperature anomalies. Its primary function is to issue various alarm signals when the temperature monitoring module detects temperature deviations outside a preset range, alerting staff or system administrators to take necessary countermeasures. This alarm module works closely with the aforementioned temperature monitoring and control modules to ensure the system's timely response to temperature fluctuations and safeguard the safe transportation of pharmaceuticals.

[0050] In this embodiment, when the temperature monitoring module detects that the transport environment's temperature deviates from a set threshold, the alarm module immediately activates and issues multiple alarm signals. These alarm signals include audible and visual alarms, as well as notifications sent via mobile devices. Specifically, the alarm module compares real-time temperature data with a preset temperature range. If the deviation exceeds the set range, the alarm module triggers the alarm process.

[0051] As an option, the audible alarm portion of the alarm module includes a built-in speaker that emits a high-decibel alarm to ensure that staff can promptly detect temperature anomalies in the presence of high ambient noise. The trigger frequency, volume, and duration of the audible alarm can be adjusted as needed to adapt to the needs of use in different environments. For example, in some embodiments, the alarm frequency can be set to sound once every 5 seconds and last for 3 seconds. The volume of the alarm sound can reach 100 decibels to ensure that the alarm sound can penetrate background noise in a relatively noisy environment.

[0052] Specifically, the visual alarm function of the alarm module is typically implemented through an LED display or light indicator. When the temperature deviation exceeds a set range, the alarm module activates the visual alarm device, typically by illuminating a red warning light to alert on-site personnel. To enhance the visibility of the alarm, the visual alarm light can be placed in a prominent position on the equipment and have a high brightness.

[0053] In one possible implementation, the alarm module is also linked to a mobile device. When the temperature deviation reaches the alarm condition, the alarm module transmits the alarm signal to the mobile device of the relevant manager through the communication unit. This transmission method can be carried out through wireless protocols such as Wi-Fi, Bluetooth, and ZigBee. For example, when using the Wi-Fi protocol, the alarm module is connected to the cloud server through the control module, and sends SMS, email, or App push notifications to designated personnel through the cloud platform. The notification content may include the specific location of the temperature anomaly, the current temperature data and deviation, as well as recommended measures.

[0054] As a further option, the content of alarm notifications can be intelligently processed using AI algorithms. For example, if the system detects large temperature fluctuations, the notification content may include analysis results of the current temperature trend, allowing managers to determine whether emergency measures are needed.

[0055] The alarm module connects to the aforementioned temperature monitoring module through data transmission and real-time processing. When temperature data collected by the temperature monitoring module exceeds a set threshold, the alarm module receives temperature deviation information from the control module, determines whether to trigger an alarm, and executes the alarm action according to the preset strategy. The alarm module can select different alarm methods based on different temperature exceedance levels, further enhancing the relevance and effectiveness of the alarm.

[0056] This design allows the alarm module to provide multi-level, multi-channel alarms, ensuring that temperature anomalies are detected and addressed promptly. This multi-signal alarm mechanism not only improves system reliability but also enhances the efficiency and accuracy of personnel responses.

[0057] To enhance the stability and adaptability of the alarm module, the system supports custom adjustments to alarm thresholds and response strategies. Operators can flexibly set alarm sensitivity, frequency, duration, and other parameters based on varying transportation environments, temperature control requirements, and management needs.

[0058] The optimization module dynamically optimizes the operating parameters of the cooling module through machine learning algorithms based on real-time collected temperature data and historical temperature fluctuations; The optimization module, the system's core intelligent unit, uses machine learning algorithms to dynamically optimize the cooling module's operating parameters based on real-time temperature data and historical temperature fluctuations. This module works closely with the temperature monitoring module, the alarm module, and the cooling module to ensure the cooling system always operates optimally, achieving energy savings and precise temperature control. The optimization module intelligently analyzes real-time and historical data to predict and adjust the cooling system's operating status, thereby improving system efficiency and responsiveness.

[0059] In this embodiment, the optimization module receives real-time temperature data from the temperature monitoring module, as well as historical temperature fluctuation data. Specifically, the real-time data includes the current ambient temperature and its rate of change, while the historical data includes the temperature fluctuation patterns over a period of time. This data serves as input for analysis and processing by the machine learning algorithm to dynamically optimize the operating parameters of the cooling module.

[0060] Typically, the optimization module is trained using supervised learning or reinforcement learning algorithms. By annotating historical data, the system learns the optimal cooling response under different temperature change patterns, allowing it to make accurate adjustment decisions when encountering similar temperature changes in the future.

[0061] Alternatively, the optimization module can use a machine learning algorithm based on regression analysis, where the optimal cooling control strategy is found by minimizing an objective function. The objective function can be expressed as: The optimization goal is to minimize energy consumption and temperature deviation. The optimization formula is: Where J is the optimization objective; x(t) is the temperature deviation; P(t) is the cooling power; λ1 and λ2 are the weights of temperature deviation and energy consumption, respectively; and T is the total number of time steps.

[0062] In one possible implementation, the optimization module can also employ a reinforcement learning algorithm. In reinforcement learning, the optimization module is considered an intelligent agent, and the cooling module serves as its "environment." Through trial and error and a reward mechanism, the optimization module learns how to adjust the cooling module's operating parameters under varying temperature deviations to achieve optimal control. The optimization objective of reinforcement learning is to maximize the reward function, defined as: Where R is the total reward, r(t) is the immediate reward at time t, γ is the discount factor, T is the total number of time steps, and t is the integral term. The design of the reward function depends on the needs of the specific application scenario and may include multiple objectives such as reducing temperature fluctuations and optimizing energy consumption.

[0063] Specifically, the optimization module performs cluster analysis on historical temperature data to identify different types of temperature fluctuation patterns. For example, during transportation, when temperature fluctuations are small and stable, the optimization module can reduce cooling power to reduce energy consumption. However, when temperature fluctuations are large, the optimization module increases cooling power to quickly restore the temperature control range.

[0064] Furthermore, in certain embodiments, the optimization module can also combine real-time temperature data with external environmental conditions (such as ambient temperature and humidity) for coordinated optimization. For example, when the ambient temperature is low, the optimization module can automatically adjust the cooling power to avoid overcooling while maintaining the drug temperature within an appropriate range. In this case, the optimization module dynamically calculates the weighted sum of different variables to adjust the system's operating state.

[0065] The optimization module can also dynamically adjust its learning strategy based on environmental changes. In certain situations, when temperature fluctuations are large, the optimization module will increase the learning frequency to more quickly adapt to temperature control needs; when the ambient temperature changes tend to be stable, the optimization module will reduce the learning frequency to reduce the system's computational burden.

[0066] In some embodiments, the machine learning algorithm used by the optimization module can also support online learning. That is, as new temperature data is continuously input during system operation, the optimization module can gradually update its model, thereby continuously improving the cooling control strategy. This self-learning approach can enable the system to continuously improve accuracy and efficiency over the long term.

[0067] Through these optimization methods, the optimization module not only improves the control accuracy of the refrigeration module but also reduces energy consumption and system burden while ensuring drug quality. Overall, the optimization module in this embodiment dynamically adjusts the operating parameters of the refrigeration system by combining historical and real-time data with machine learning algorithms, achieving intelligent, efficient, and energy-efficient system performance, further enhancing the system's adaptability and reliability.

[0068] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A medical cold chain logistics intelligent temperature control and alarm system, characterized by: include: The temperature monitoring module includes multiple temperature sensors distributed at multiple key nodes during transportation, which collect temperature data of the environment where the medicine is located in real time and transmit the temperature signal to the control module; A control module is used to receive the temperature signal and calculate the required control signal based on the adaptive control algorithm according to the deviation between the preset target temperature and the actual temperature; The refrigeration module adjusts the working state of the refrigeration equipment according to the control signal output by the control module and uses frequency conversion technology to adjust the refrigeration power; Alarm module, when the temperature deviation exceeds the set range, it will send multiple alarm signals, including audible alarm, visual alarm and notification via mobile device; The optimization module dynamically optimizes the operating parameters of the cooling module through machine learning algorithms based on the real-time collected temperature data and sliding into historical temperature fluctuations.

2. The intelligent temperature control and alarm system for medical cold chain logistics according to claim 1 is characterized in that: The temperature monitoring module includes: Multiple temperature sensor units, each of which is placed at a key node in the cold chain transportation to collect real-time ambient temperature data at the location; A data acquisition unit is used to collect real-time temperature data from multiple temperature sensors and convert it into digital signals that can be processed by the control module; The transmission unit is used to transmit the temperature signal to the control module for subsequent processing.

3. The intelligent temperature control and alarm system for medical cold chain logistics according to claim 1 is characterized in that: The control module includes: A signal receiving unit, configured to receive a temperature signal transmitted from a data acquisition unit of the temperature monitoring module; A temperature deviation calculation unit is used to calculate the deviation between the current temperature and the target temperature; The adaptive control unit, based on the adaptive control algorithm, dynamically adjusts the control parameters and calculates the required control signal according to the temperature deviation. The control signal u(t) is optimized and adjusted according to the system requirements to minimize temperature fluctuations. The formula is: Among them, K p ,K i , and K d are proportional, integral and differential coefficients respectively; ΔT(t) is the temperature deviation; is the differential term, which indicates the rate of change of temperature deviation; t is the integral term.

4. The intelligent temperature control and alarm system for medical cold chain logistics according to claim 1 is characterized in that: The refrigeration module comprises: The refrigeration unit uses variable frequency technology to adjust the power of the refrigeration equipment. The refrigeration effect is adjusted by controlling the frequency of the refrigeration compressor. The refrigeration power is related to the control signal u(t). The adjustment formula of the refrigeration unit is: P(t)=f(u(t),T actual (t)); Where P(t) is the cooling power; f is the regulation function; u(t) is the control signal; T actual (t) is the current measured temperature; Refrigeration efficiency optimization unit, used to monitor the energy efficiency of the refrigeration unit and optimize it.

5. The intelligent temperature control and alarm system for medical cold chain logistics according to claim 1 is characterized in that: The alarm module includes: An alarm signal detection unit is used to detect whether the temperature deviation exceeds a preset threshold range. If the temperature deviation exceeds the set range, an alarm mechanism is triggered; An audible alarm unit, used for sounding an audible alarm to draw the attention of operators; Visual alarm unit, used to issue warning signs through LED display screen to warn of abnormal temperature; Notification unit, used to send alarm signals to relevant personnel via mobile devices and text messages for remote monitoring and intervention.

6. The intelligent temperature control and alarm system for medical cold chain logistics according to claim 1 is characterized in that: The optimization module includes: Real-time data analysis unit, used to analyze the real-time data collected by the temperature monitoring module, including current temperature, historical temperature fluctuations and environmental factors, and generate temperature change trends; The machine learning unit dynamically optimizes the system based on real-time and historical data through machine learning algorithms and automatically adjusts the operating parameters of the cooling module; The energy efficiency evaluation unit is used to calculate the energy consumption and temperature control effect of the current system, evaluate whether the optimal operating state is achieved, and dynamically adjust the cooling power and control strategy based on the evaluation results. The optimization goal is to minimize energy consumption and temperature deviation. The optimization formula is: Where J is the optimization objective; x(t) is the temperature deviation; P(t) is the cooling power; λ1 and λ2 are the weights of temperature deviation and energy consumption, respectively; and T is the total number of time steps.

7. The intelligent temperature control and alarm system for medical cold chain logistics according to claim 2 is characterized in that: The data acquisition unit includes: A temperature data conversion unit, configured to convert analog signals collected by the multiple temperature sensor units into digital signals; The data verification unit is used to verify and preprocess the collected temperature signal to ensure the accuracy and integrity of the signal; the data cache unit is used to temporarily store the collected temperature data.

8. The intelligent temperature control and alarm system for medical cold chain logistics according to claim 2 is characterized in that: The temperature deviation calculation unit includes: a temperature deviation acquisition unit, configured to receive a temperature signal and calculate the deviation between the current ambient temperature and a preset target temperature, thereby generating a temperature deviation signal; The data processing unit is used to process the temperature deviation signal to ensure data accuracy and transmit the processed temperature deviation to the adaptation control unit for further control and analysis; The threshold judgment unit is used to set and adjust the allowable range of temperature deviation. When the temperature deviation exceeds the preset threshold, a signal is sent to the alarm module to indicate temperature control abnormality. The historical data comparison unit is used to compare with historical temperature fluctuation data to help analyze whether the current temperature deviation is a normal fluctuation.

9. The intelligent temperature control and alarm system for medical cold chain logistics according to claim 5, characterized in that: The alarm signal detection unit includes: A temperature threshold setting unit is used to set and adjust the alarm threshold of temperature deviation; An alarm trigger unit is used to automatically activate the alarm mechanism and trigger audible and visual alarms when the temperature deviation exceeds the set threshold; The alarm recording unit is used to record each temperature deviation exceeding the standard and generate a log file for management personnel to conduct subsequent analysis and tracking.

10. The intelligent temperature control and alarm system for medical cold chain logistics according to claim 6, characterized in that: The machine learning unit includes: Data preprocessing unit, used to preprocess real-time data and historical data, including denoising, normalization and feature extraction; The training module is used to train the machine learning algorithm, select the appropriate model, and optimize it according to the actual operation of the system; the model optimization unit dynamically adjusts the parameters in the machine learning model based on real-time data feedback and system operation results, so that the model can better adapt to environmental changes and system requirements.

Images