Abnormal state grading response method based on self-adaptive temperature control infusion pipeline

Abstract

The invention relates to the technical field of medical instruments, in particular to an abnormal state grading response method based on a self-adaptive temperature control infusion pipeline, which comprises the following steps: S1, dynamic temperature threshold generation: calculating a dynamic temperature threshold interval through a temperature compensation model; s2, multi-parameter real-time monitoring: synchronously acquiring current temperature, flow velocity and pressure data in the infusion pipeline, and correcting a flow velocity value through a pressure fluctuation compensation algorithm; s3, abnormal state score calculation: generating an abnormal state score; s4, abnormal state grade judgment: the abnormal state is divided into first-level early warning, second-level intervention and third-level emergency shutdown; and S5, graded response execution: according to different grades of abnormal states, respectively triggering acousto-optic early warning, flow velocity adaptive adjustment, pipeline heating compensation or shutdown instructions. According to the invention, the continuity of the medication process of a patient is guaranteed, and clinical risks such as low-temperature mistaken transfusion, liquid medicine failure and abnormal flow velocity are reduced to the greatest extent.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and particularly to an abnormal state grading response method based on an adaptive temperature control infusion pipeline. Background Art

[0002] During the clinical infusion process, the temperature and flow rate of the liquid medicine have important effects on the treatment effect and patient comfort. Especially for temperature-sensitive drugs, such as protein preparations, vaccines, etc., once the delivery temperature deviates from the set range, it may lead to a reduction in drug efficacy, a change in chemical properties, and even adverse stimulation to the patient. Most traditional infusion devices adopt a constant set temperature and fixed flow rate parameters, and cannot be dynamically adjusted according to environmental changes and the type of liquid medicine, which is likely to cause potential safety hazards during the infusion process. Therefore, the research and development of an intelligent infusion system that can perform adaptive control based on the characteristics of the liquid medicine and environmental changes has become an important direction for clinical refined management.

[0003] Existing temperature control infusion devices usually lack the ability to sense real-time environmental temperature, pressure fluctuations, and the differential requirements of liquid medicine, and it is difficult to realize the intelligent generation and dynamic adjustment of temperature thresholds. At the same time, the existing flow rate measurement mechanism fails to fully consider the influence of pressure fluctuations on the measured value, resulting in a low recognition accuracy of the abnormal state of the system. In addition, most systems lack a grading response mechanism based on the degree of deviation, and cannot effectively distinguish minor abnormalities from serious faults, resulting in over-intervention or reaction lag, affecting the safety and efficiency of clinical use. Summary of the Invention

[0004] The present invention provides an abnormal state grading response method based on an adaptive temperature control infusion pipeline, which realizes a closed-loop control from acoustic and optical warnings to flow rate adjustment, heating compensation, and shutdown protection, and comprehensively improves the safety, self-adaptability, and intelligent level of the infusion system.

[0005] The abnormal state grading response method based on an adaptive temperature control infusion pipeline includes the following steps:

[0006] S1, dynamic temperature threshold generation: According to the real-time environmental temperature and the type of infusion liquid medicine, calculate the dynamic temperature threshold interval through a temperature compensation model;

[0007] S2, multi-parameter real-time monitoring: Synchronously collect the current temperature, flow rate, and pressure data in the infusion pipeline, and correct the flow rate value through a pressure fluctuation compensation algorithm;

[0008] S3, abnormal state score calculation: Based on the corrected flow rate value, combine the deviation value between the current temperature and the dynamic temperature threshold interval to generate an abnormal state score;

[0009] S4, Abnormal State Level Judgment: According to the comparison result between the abnormal state score and the preset grading threshold, the abnormal state is divided into level-one early warning, level-two intervention, and level-three emergency shutdown.

[0010] S5, Graded Response Execution: For different levels of abnormal states, respectively trigger audible and visual warnings, flow rate adaptive adjustment, pipeline heating compensation, or shutdown instructions.

[0011] Optionally, the dynamic temperature threshold generation in S1 includes:

[0012] S11, Ambient Temperature Monitoring: Real-time monitor the temperature of the infusion environment, and input the temperature of the infusion environment into the temperature compensation model to generate a compensated ambient temperature adjustment parameter.

[0013] S12, Liquid Medicine Characteristic Analysis: Based on the generated compensated ambient temperature adjustment parameter, output a dynamic temperature threshold range according to the temperature requirements of the liquid medicine type.

[0014] Optionally, the ambient temperature monitoring in S11 includes:

[0015] S111, Ambient Temperature Real-time Monitoring: Real-time monitor the temperature of the infusion environment through a temperature sensor installed around the infusion pipeline, and collect the ambient temperature T env (t), where t is the current time point.

[0016] S112, Temperature Compensation Calculation: Input the real-time collected ambient temperature T env (t) into the temperature compensation model, and output the initial ambient temperature adjustment parameter ΔT(t), expressed as:

[0017] ΔT(t) = α · (T env (t) - T ref );

[0018] where α is the temperature compensation coefficient, used to adjust the sensitivity of temperature fluctuations, and T ref is the reference temperature (set to 22 °C).

[0019] S113, Generate Adjustment Parameter: Based on the initial ambient temperature adjustment parameter ΔT(t), generate the compensated ambient temperature adjustment parameter T adj (t).

[0020] Optionally, the liquid medicine characteristic analysis in S12 includes:

[0021] S121, Liquid Medicine Type Identification and Characteristic Acquisition: According to the input liquid medicine type L, extract the temperature range required by the liquid medicine during transportation from the liquid medicine database. Let the minimum temperature requirement of the liquid medicine be The maximum temperature requirement is

[0022] S122, Input the ambient temperature adjustment parameter: Combine the generated compensated ambient temperature adjustment parameter T adj (t) with the temperature requirement of the liquid medicine type to calculate the dynamic temperature threshold range It is expressed as:

[0023]

[0024] Among them, is the minimum temperature requirement of liquid medicine type L, is the maximum temperature requirement of liquid medicine type L, and β is the temperature adjustment coefficient.

[0025] Optionally, the multi-parameter real-time monitoring in S2 includes:

[0026] S21, Real-time data acquisition: Through the sensors (temperature sensor, flow rate sensor, pressure sensor) installed in the infusion pipeline, real-time collect the current temperature T fluid (t), flow rate V flow (t) and pressure P fluid (t);

[0027] S22, Pressure fluctuation compensation calculation: According to the pressure fluctuation and flow rate compensation coefficient, correct the flow rate measurement value to generate a compensated flow rate value

[0028] Optionally, the abnormal state score calculation in S3 includes:

[0029] S31, Deviation value calculation: By comparing the currently corrected flow rate value and the actually measured temperature in the pipeline with the set desired flow rate value and the dynamic temperature threshold range, calculate the flow rate deviation value and the temperature deviation value;

[0030] S32, Abnormal score generation: Input the calculated flow rate deviation value and temperature deviation value into the multi-dimensional scoring model to generate an abnormal state score.

[0031] Optionally, the deviation value calculation in S31 includes:

[0032] S311, Flow rate deviation value calculation: Obtain the corrected flow rate value Q actual (t) at the current moment t, and find the desired flow rate Q of this liquid medicine in the normal infusion state expected , and calculate the flow rate deviation value D Q (t) through the absolute difference between the corrected flow rate value and the desired flow rate;

[0033] S312, Temperature deviation value calculation: Record the temperature θ of the liquid medicine in the pipeline at the current moment t tube(t), and call the dynamic temperature threshold range If the temperature θ of the liquid medicine in the current pipeline tube (t) exceeds the dynamic temperature threshold range, calculate the temperature deviation value D according to the degree of exceeding the upper and lower limits θ (t).

[0034] Optionally, the multi-dimensional scoring model in S32 adopts a dynamic threshold scoring model, and the dynamic threshold scoring model includes:

[0035] S321, deviation normalization: Normalize the flow rate deviation value and the temperature deviation value;

[0036] S322, define the temperature overstep direction weight: According to the direction of the current temperature deviating from the dynamic threshold range, assign the low-temperature overstep weight γ low and the high-temperature overstep weight γ high ;

[0037] S323, non-linear scoring function calculation: Perform non-linear scoring on the flow rate deviation value and the temperature deviation value respectively. Among them, the flow rate deviation value is modeled by a logarithmic function (tolerating small errors and emphasizing large deviations), and the temperature deviation value is modeled by an exponential function (rapidly increasing the score when the temperature oversteps), generating the flow rate deviation score and the temperature deviation score;

[0038] S324, cross-term penalty: When the flow rate deviation value and the temperature deviation value exist at the same time, calculate the product of the normalized flow rate deviation value and the temperature deviation value, and introduce the penalty coefficient δ to generate the cross-term penalty score;

[0039] S325, abnormal score calculation: Superimpose the flow rate deviation score, the temperature deviation score, and the cross-term penalty score to generate the abnormal state score S(t).

[0040] Optionally, the abnormal level determination in S4 includes:

[0041] S41, set the abnormal classification threshold: Preset the scoring thresholds for dividing different abnormal levels, including the first-level warning threshold θ1 (set to 1.5), the second-level intervention threshold θ2 (set to 3), and the third-level emergency shutdown threshold θ3 (set to 6);

[0042] S42, abnormal score level determination: Obtain the abnormal state score value S(t) at the current moment, compare it with the scoring threshold, and divide the abnormal state level. When S(t) < θ1, it is determined to be in the normal state. When θ1 ≤ S(t) < θ2, it is determined to be a first-level warning. When θ2 ≤ S(t) < θ3, it is determined to be a second-level intervention. When S(t) ≥ θ3, it is determined to be a third-level emergency shutdown.

[0043] Optionally, the hierarchical response execution in S5 includes:

[0044] S51, Trigger audible and visual warnings: When the abnormal status level is a first-level warning, trigger the audible and visual warning device, and remind the caregiver through the buzzer and indicator light that there is a preliminary deviation in the current infusion status. At the same time, prompt the current deviation type and suggested attention items on the terminal interface, and there is no need to immediately intervene in the infusion process;

[0045] S52, Flow rate adaptive adjustment or pipeline heating compensation: When the abnormal status level is a second-level intervention, trigger the flow rate adaptive adjustment mechanism or the pipeline heating compensation mechanism. If the flow rate deviation value is the main one, automatically adjust the infusion pump rate to approach the expected value. If the temperature deviation value is the main one, start the heating module and raise the pipeline temperature to the dynamic threshold range by adjusting the temperature control element;

[0046] S53, Shutdown instruction: When the abnormal status level is a third-level emergency shutdown, trigger the shutdown instruction of the infusion system, stop the liquid output and maintain the locked state, synchronously output a strong prompt signal, send an alarm to the care terminal, and require manual review and on-site intervention.

[0047] Advantages of the present invention:

[0048] In the present invention, by constructing a dynamic temperature control model based on the real-time ambient temperature and liquid medicine type, it is possible to intelligently generate a personalized temperature threshold range, effectively solve the problem that the temperature control in the traditional infusion system is static and cannot adapt to the needs of multiple types of liquid medicines. At the same time, by integrating multiple types of sensors, synchronous monitoring of the temperature, flow rate and pressure of the infusion pipeline is realized, and a pressure fluctuation compensation algorithm is used to improve the flow rate measurement accuracy, ensuring the accuracy and reliability of the monitoring data from the source.

[0049] In the present invention, by introducing a dynamic threshold scoring model combining deviation normalization, non-linear scoring and cross-punishment mechanism, it is possible to finely evaluate the influence degree of flow rate deviation and temperature deviation on the infusion safety in different directions and different amplitudes. Through strengthening the modeling of low-temperature risk and multi-dimensional fusion calculation of abnormal scores, the quantitative expression of abnormal status is realized, and combined with the setting of hierarchical thresholds, it is ensured that the system has sensitive and scientific hierarchical judgment ability under different degrees of risk, and the discrimination accuracy and response logic rationality of the infusion system are improved.

[0050] In the present invention, by automatically matching a three-level response mechanism according to the scoring results, it is possible to achieve audible and visual prompt warnings in case of mild abnormalities, intelligently execute flow rate adjustment and temperature compensation in case of moderate abnormalities, and trigger shutdown protection in case of severe abnormalities, constructing a complete closed-loop response system. This mechanism not only ensures the continuity of the patient's medication process, but also minimizes clinical risks such as low-temperature mis-infusion, liquid medicine failure, and abnormal flow rate, and has significant medical safety guarantee value and system engineering practical value. Description of the Drawings

[0051] To more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only those of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0052] Figure 1 Schematic diagram of the response method process for the embodiment of the present invention;

[0053] Figure 2 Schematic diagram of the generation of the dynamic temperature threshold for the embodiment of the present invention. Detailed implementation manners

[0054] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it should be noted here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments. For some well-known technologies, those skilled in the art can also adopt other alternative methods for implementation; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0055] It should be noted that in the specification, it is mentioned that "an embodiment", "embodiment", "exemplary embodiment", "some embodiments", etc. indicate that the described embodiment may include specific features, structures or characteristics, but not necessarily every embodiment includes such specific features, structures or characteristics. In addition, when combining an embodiment to describe a specific feature, structure or characteristic, implementing such a feature, structure or characteristic in combination with other embodiments (whether explicitly described or not) should be within the knowledge of those skilled in the relevant art.

[0056] Generally, the terms can be understood at least in part from their use in the context. For example, at least in part depending on the context, the term "one or more" used herein can be used to describe any feature, structure or characteristic in a singular sense, or can be used to describe a combination of features, structures or characteristics in a plural sense. In addition, the term "based on" can be understood as not necessarily intended to convey a set of exclusive factors, but rather, at least in part depending on the context, allowing for the existence of other factors that may not be explicitly described.

[0057] As Figure 1 - Figure 2 shown, the abnormal state grading response method based on the adaptive temperature control infusion pipeline includes the following steps:

[0058] S1. Generation of the dynamic temperature threshold: Calculate the dynamic temperature threshold range through the temperature compensation model according to the real-time environmental temperature and the type of infusion liquid medicine;

[0059] S2, Multi-parameter real-time monitoring: Synchronously collect the current temperature, flow rate, and pressure data in the infusion pipeline, and correct the flow rate value through the pressure fluctuation compensation algorithm;

[0060] S3, Abnormal state score calculation: Based on the corrected flow rate value, combined with the deviation value between the current temperature and the dynamic temperature threshold range, generate an abnormal state score;

[0061] S4, Abnormal state level determination: According to the comparison result between the abnormal state score and the preset grading threshold, divide the abnormal state into first-level warning, second-level intervention, and third-level emergency shutdown;

[0062] S5, Hierarchical response execution: For different levels of abnormal states, trigger audible and visual warnings, flow rate adaptive adjustment, pipeline heating compensation, or shutdown instructions respectively.

[0063] The generation of the dynamic temperature threshold in S1 includes:

[0064] S11, Ambient temperature monitoring: Real-time monitor the temperature of the infusion environment, and input the temperature of the infusion environment into the temperature compensation model to generate a compensated ambient temperature adjustment parameter;

[0065] S12, Liquid medicine characteristic analysis: Based on the generated compensated ambient temperature adjustment parameter, output the dynamic temperature threshold range according to the temperature requirements of the liquid medicine type.

[0066] The ambient temperature monitoring in S11 includes:

[0067] S111, Ambient temperature real-time monitoring: Real-time monitor the temperature of the infusion environment through the temperature sensor installed around the infusion pipeline, and collect the ambient temperature T env (t), where t is the current time point;

[0068] S112, Temperature compensation calculation: Input the real-time collected ambient temperature T env (t) into the temperature compensation model, and output the initial ambient temperature adjustment parameter ΔT(t), expressed as:

[0069] ΔT(t) = α·(T env (t) - T ref );

[0070] Among them, ɑ is the temperature compensation coefficient, used to adjust the sensitivity of temperature fluctuation, and T ref is the reference temperature (set as 22°C);

[0071] S113, Generate adjustment parameter: Based on the initial ambient temperature adjustment parameter ΔT(t), generate the compensated ambient temperature adjustment parameter T adj (t), expressed as:

[0072] Tadj T(t)=T ref +ΔT(t).

[0073] The analysis of the liquid medicine characteristics in S12 includes:

[0074] S121, liquid medicine type identification and characteristic acquisition: According to the input liquid medicine type L, extract the temperature range required for this liquid medicine during transportation from the liquid medicine database. Let the minimum temperature requirement of the liquid medicine be The maximum temperature requirement is Specifically include:

[0075] Conventional liquid medicines (such as normal saline, glucose solution): Minimum temperature requirement The maximum temperature requirement

[0076] Temperature-sensitive drugs (such as certain protein drugs, vaccines): Minimum temperature requirement The maximum temperature requirement

[0077] Chemical drug solutions (such as antibiotic solutions): Minimum temperature requirement The maximum temperature requirement

[0078] Thermostable drugs (such as some liquid drugs, such as analgesics): Minimum temperature requirement The maximum temperature requirement

[0079] S122, input environmental temperature adjustment parameter: Combine the generated compensated environmental temperature adjustment parameter T adj (t) with the temperature requirements of the liquid medicine type to calculate the dynamic temperature threshold interval Expressed as:

[0080]

[0081] Among them, Is the minimum temperature requirement of the liquid medicine type L, Is the maximum temperature requirement of the liquid medicine type L, and β is the temperature adjustment coefficient.

[0082] The multi-parameter real-time monitoring in S2 includes:

[0083] S21, real-time data acquisition: Through the sensors (temperature sensor, flow rate sensor, pressure sensor) installed in the infusion pipeline, real-time collect the current temperature T fluid (t), flow rate V flow (t) and pressure P fluid (t);

[0084] S22, Pressure fluctuation compensation calculation: According to the pressure fluctuation and the flow rate compensation coefficient, correct the flow rate measurement value to generate a compensated flow rate value It is expressed as:

[0085]

[0086] Among them, V flow (t) is the original flow rate measurement value, ɑ flow is the flow rate compensation coefficient, ΔP(t) = P fluid (t) - P ref is the pressure fluctuation at time t.

[0087] The abnormal state score calculation in S3 includes:

[0088] S31, Deviation value calculation: By comparing the currently corrected flow rate value and the actually measured temperature inside the pipeline with the set desired flow rate value and the dynamic temperature threshold range, calculate the flow rate deviation value and the temperature deviation value;

[0089] S32, Abnormal score generation: Input the calculated flow rate deviation value and temperature deviation value into the multi-dimensional scoring model to generate an abnormal state score.

[0090] The deviation value calculation in S31 includes:

[0091] S311, Flow rate deviation value calculation: Obtain the currently corrected flow rate value Q actual (t), and find the desired flow rate Q expected of this medicinal liquid under normal infusion conditions. Calculate the flow rate deviation value D Q (t) through the absolute difference between the corrected flow rate value and the desired flow rate, expressed as:

[0092] D Q (t) = |Q actual (t) - Q expected |;

[0093] The setting of the desired flow rate Q expected specifically includes:

[0094] Conventional medicinal liquid (adult maintenance infusion): Q expected = 60 mL / h;

[0095] Temperature-sensitive drugs or special care scenarios (children, the elderly, patients with chronic diseases): Q expected = 30 mL / h;

[0096] Rapid fluid replacement or rescue scenarios (under controlled temperature conditions): Q expected = 100 mL / h;

[0097] S312, Temperature deviation value calculation: Record the temperature θ of the liquid medicine in pipeline y at the current moment tube (t), and call the dynamic temperature threshold range If the temperature θ of the liquid medicine in the current pipeline tube (t) exceeds the dynamic temperature threshold range, calculate the temperature deviation value D according to the degree of exceeding the upper and lower limits θ (t), expressed as:

[0098]

[0099] The multi-dimensional scoring model in S32 adopts a dynamic threshold scoring model, and the dynamic threshold scoring model includes:

[0100] S321, Deviation normalization: Normalize the flow rate deviation value and the temperature deviation value, expressed as:

[0101]

[0102] Among them, are the normalized flow rate deviation value and temperature deviation value respectively, is the temperature tolerance range of the liquid medicine;

[0103] S322, Define the temperature out-of-bounds direction weight: According to the direction of the current temperature deviating from the dynamic threshold range, assign the low-temperature out-of-bounds weight γ low and the high-temperature out-of-bounds weight γ high , which are used to differentially evaluate the influence intensity of low-temperature and high-temperature deviations in abnormal scoring, expressed as:

[0104]

[0105] Among them, w T (t) is the temperature out-of-bounds direction weight, γ low is the low-temperature out-of-bounds weight, set to 2, γ high is the high-temperature out-of-bounds weight, set to 1;

[0106] S323, Nonlinear scoring function calculation: Perform nonlinear scoring on the flow rate deviation value and the temperature deviation value respectively. Among them, the flow rate deviation value is modeled by a logarithmic function (tolerating small errors and emphasizing large deviations), and the temperature deviation value is modeled by an exponential function (rapidly increasing the score when the temperature is out of bounds), generating the flow rate deviation score and the temperature deviation score, expressed as:

[0107]

[0108] Among them, S Q (t) is the flow rate deviation score, w1 is the flow rate scoring sensitivity coefficient, s T(t) is the temperature deviation score, and w2 is the temperature score sensitivity coefficient;

[0109] S324, cross-term penalty: When both the flow rate deviation value and the temperature deviation value exist, calculate the product of the normalized flow rate deviation value and the temperature deviation value, and introduce a penalty coefficient δ to quantify the synergistic enhancement effect of the abnormal superposition on the score, generating a cross-term penalty score, expressed as:

[0110]

[0111] Among them, S cross (t) is the cross-term penalty score;

[0112] S325, abnormal score calculation: Superimpose the flow rate deviation score, the temperature deviation score, and the cross-term penalty score to generate an abnormal state score S(t), expressed as:

[0113] S(t) = λ1·S Q (t) + λ2·S T (t) + λ3·S cross (t);

[0114] Among them, λ1, λ2, and λ3 are the corresponding score weighting coefficients.

[0115] The abnormal level determination in S4 includes:

[0116] S41, set abnormal classification thresholds: Predetermine the score thresholds for dividing different abnormal levels, including the first-level warning threshold θ1 (set to 1.5), the second-level intervention threshold θ2 (set to 3), and the third-level emergency shutdown threshold θ3 (set to 6);

[0117] S42, abnormal score level determination: Obtain the abnormal state score value S(t) at the current moment, compare it with the score threshold, and divide the abnormal state level. When S(t) < θ1, it is determined to be in a normal state. When θ1 ≤ S(t) < θ2, it is determined to be a first-level warning. When θ2 ≤ S(t) < θ3, it is determined to be a second-level intervention. When S(t) ≥ θ3, it is determined to be a third-level emergency shutdown.

[0118] The hierarchical response execution in S5 includes:

[0119] S51, trigger an audible and visual warning: When the abnormal state level is a first-level warning, trigger the audible and visual warning device, and remind the nursing staff of the initial deviation in the current infusion state through the buzzer and indicator light. At the same time, prompt the current deviation type and recommended attention items on the terminal interface, and there is no need to immediately intervene in the infusion process;

[0120] S52, Flow rate adaptive adjustment or pipeline heating compensation: When the abnormal state level is at the secondary intervention level, trigger the flow rate adaptive adjustment mechanism or the pipeline heating compensation mechanism. If the flow rate deviation value is the main one, automatically adjust the infusion pump rate to make it approach the expected value. If the temperature deviation value is the main one, start the heating module and raise the pipeline temperature to the dynamic threshold range by adjusting the temperature control element to maintain the infusion stability;

[0121] S53, Shutdown instruction: When the abnormal state level is at the third-level emergency shutdown, trigger the shutdown instruction of the infusion system, stop the liquid output and maintain the locked state to prevent continued mis-infusion, and simultaneously output a strong prompt signal to send an alarm to the nursing terminal, requiring manual review and on-site intervention to ensure medication safety.

[0122] The present invention covers any substitutions, modifications, equivalent methods, and solutions made within the essence and scope of the present invention. For the public to have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention. However, those skilled in the art can fully understand the present invention without the description of these details. Additionally, to avoid unnecessary confusion to the essence of the present invention, well-known methods, processes, flows, components, and circuits are not described in detail.

[0123] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. An abnormal state grading response method based on an adaptive temperature control infusion pipeline, characterized in that, It includes the following steps: S1, Dynamic temperature threshold generation: Calculate the dynamic temperature threshold range according to the real-time environmental temperature and the type of infusion solution through a temperature compensation model; S2, Multi-parameter real-time monitoring: Synchronously collect the current temperature, flow rate, and pressure data in the infusion pipeline, and correct the flow rate value through a pressure fluctuation compensation algorithm; S3, Abnormal state score calculation: Based on the corrected flow rate value, combine the deviation value between the current temperature and the dynamic temperature threshold range to generate an abnormal state score; S4, Abnormal state level determination: According to the comparison result between the abnormal state score and the preset classification threshold, divide the abnormal state into level 1 early warning, level 2 intervention, and level 3 emergency shutdown; S5, Hierarchical response execution: For different levels of abnormal states, trigger audible and visual warnings, flow rate adaptive adjustment, pipeline heating compensation, or shutdown commands respectively.

2. The abnormal state grading response method based on the adaptive temperature control infusion pipeline according to claim 1, wherein, The dynamic temperature threshold generation in S1 includes: S11, Environmental temperature monitoring: Real-time monitor the temperature of the infusion environment, and input the temperature of the infusion environment into the temperature compensation model to generate a compensated environmental temperature adjustment parameter; S12, Liquid medicine characteristic analysis: Based on the generated compensated environmental temperature adjustment parameter, output the dynamic temperature threshold range according to the temperature requirements of the liquid medicine type.

3. The abnormal state classification response method based on the adaptive temperature control infusion pipeline according to claim 2, wherein, The environmental temperature monitoring in S11 includes: S111, Real-time monitoring of environmental temperature: The temperature of the infusion environment is monitored in real time through a temperature sensor installed around the infusion pipeline, and the environmental temperature T env (t) is collected, where t is the current time point; S112, Temperature compensation calculation: Input the real-time collected ambient temperature T env (t) into the temperature compensation model, and output the initial ambient temperature adjustment parameter ΔT(t), which is expressed as: ΔT(t) = ɑ·(T env (t) - T ref ); where ɑ is the temperature compensation coefficient for adjusting the sensitivity to temperature fluctuations, and T ref is the reference temperature; S113, Generate adjustment parameters: Based on the initial ambient temperature adjustment parameter ΔT(t), generate the compensated ambient temperature adjustment parameter T adj (t).

4. The abnormal state grading response method based on the adaptive temperature control infusion pipeline according to claim 3, characterized in that The liquid medicine characteristic analysis in S12 includes: S121, Liquid Medicine Type Identification and Characteristic Acquisition: According to the input liquid medicine type L, extract the temperature range required for this liquid medicine during transportation from the liquid medicine database. Let the minimum temperature requirement of the liquid medicine be and the maximum temperature requirement be S122, Input the environmental temperature adjustment parameter: Combine the generated compensated environmental temperature adjustment parameter T adj (t) with the temperature requirement of the liquid medicine type to calculate the dynamic temperature threshold range Expressed as: Among them, is the minimum temperature requirement for liquid medicine type L, is the maximum temperature requirement for liquid medicine type L, and β is the temperature adjustment coefficient.

5. The abnormal state classification response method based on the adaptive temperature control infusion pipeline according to claim 4, wherein, The multi-parameter real-time monitoring in S2 includes: S21, Real-time data acquisition: The current temperature T in the pipeline is collected in real time through the sensor installed in the infusion pipeline fluid (t), flow rate V flow (t) and pressure P fluid (t); S22, Pressure Fluctuation Compensation Calculation: Correct the measured flow velocity value based on the pressure fluctuation and flow velocity compensation coefficient to generate a compensated flow velocity value 6. The method for grading response to abnormal states of an adaptive temperature-controlled infusion pipeline according to claim 5, wherein, The abnormal state score calculation in S3 includes: S31, Deviation value calculation: By comparing the current corrected flow rate value and the actually measured temperature in the pipeline with the set desired flow rate value and the dynamic temperature threshold range, calculate the flow rate deviation value and the temperature deviation value; S32, Abnormal score generation: Input the calculated flow rate deviation value and temperature deviation value into a multi-dimensional scoring model to generate an abnormal state score.

7. The abnormal state grading response method based on the adaptive temperature control infusion pipeline according to claim 6, wherein The deviation value calculation in S31 includes: S311, Flow velocity deviation value calculation: Obtain the corrected flow velocity value Q actual (t) at the current moment t, and search for the expected flow velocity Q expected of the liquid medicine under normal infusion state. Calculate the flow velocity deviation value D Q (t) through the absolute difference between the corrected flow velocity value and the expected flow velocity; S312, Temperature deviation value calculation: Record the temperature θ of the liquid medicine in the pipeline at the current moment t tube (t), and call the dynamic temperature threshold range If the temperature θ of the liquid medicine in the current pipeline tube (t) exceeds the dynamic temperature threshold range, calculate the temperature deviation value D according to the degree of exceeding the upper and lower limits θ (t).

8. The method for grading response to abnormal states of an adaptive temperature-controlled infusion pipeline according to claim 7, wherein The multi-dimensional scoring model in S32 adopts a dynamic threshold scoring model, and the dynamic threshold scoring model includes: S321, Deviation normalization: Perform normalization processing on the flow rate deviation value and the temperature deviation value; S322. Define the temperature out-of-bounds direction weights: According to the direction in which the current temperature deviates from the dynamic threshold range, assign the low-temperature out-of-bounds weight γ low and the high-temperature out-of-bounds weight γ high respectively; S323, Non-linear scoring function calculation: Perform non-linear scoring on the flow rate deviation value and the temperature deviation value respectively. Among them, the flow rate deviation value is modeled by a logarithmic function, and the temperature deviation value is modeled by an exponential function to generate a flow rate deviation score and a temperature deviation score; S324, Cross-term penalty: When the flow rate deviation value and the temperature deviation value exist simultaneously, calculate the product of the normalized flow rate deviation value and the temperature deviation value, and introduce a penalty coefficient δ to generate a cross-term penalty score; S325, Abnormal score calculation: Superimpose the flow rate deviation score, the temperature deviation score, and the cross-term penalty score to generate an abnormal state score S(t).

9. The abnormal state classification response method based on the adaptive temperature control infusion pipeline according to claim 8, wherein, The abnormal level determination in S4 includes: S41, Set abnormal classification thresholds: Preset the scoring thresholds for dividing different abnormal levels, including a level 1 early warning threshold θ1, a level 2 intervention threshold θ2, and a level 3 emergency shutdown threshold θ3; S42, Abnormal score level determination: Obtain the abnormal status score value S(t) at the current moment, compare it with the score threshold, and classify the abnormal status level. When S(t) < θ1, it is determined to be in a normal state. When θ1 ≤ S(t) < θ2, it is determined to be a first-level warning. When θ2 ≤ S(t) < θ3, it is determined to be a second-level intervention. When S(t) ≥ θ3, it is determined to be a third-level emergency shutdown.

10. The method for hierarchical response to abnormal states of an adaptive temperature-controlled infusion pipeline according to claim 1, wherein, The hierarchical response execution in S5 includes: S51, Trigger audible and visual warnings: When the abnormal status level is a first-level warning, trigger the audible and visual warning device, remind the caregiver of the initial deviation in the current infusion state through the buzzer and indicator light, and at the same time prompt the current deviation type and recommended attention items on the terminal interface, without the need to immediately intervene in the infusion process; S52, Flow rate adaptive adjustment or pipeline heating compensation: When the abnormal status level is a second-level intervention, trigger the flow rate adaptive adjustment mechanism or the pipeline heating compensation mechanism. If the flow rate deviation value is the main one, automatically adjust the infusion pump rate to approach the expected value. If the temperature deviation value is the main one, start the heating module and raise the pipeline temperature to the dynamic threshold range by adjusting the temperature control element; S53, Shutdown command: When the abnormal status level is a third-level emergency shutdown, trigger the infusion system shutdown command, stop the liquid output and maintain the locked state, synchronously output a strong prompt signal, send an alarm to the caregiver terminal, and require manual review and on-site intervention.

Images