An open non-contact liquid heating method

Abstract

This invention discloses an open, non-contact liquid heating method, comprising: collecting temperature data of multiple points of dialysis fluid and heating unit, and obtaining flow rate deviation and temperature sensor consistency deviation indices during dialysis fluid infusion; preprocessing the temperature data to obtain a stable multi-source temperature data sequence; fusing the multi-source temperature data to obtain the dialysis fluid characterization temperature, and analyzing it in conjunction with temperature change characteristics, flow rate deviation, and temperature sensor consistency deviation indices to construct a system state characterization quantity; identifying the heating stage based on the system state characterization quantity, using the dialysis fluid characterization temperature as the control target, generating heating control quantities according to the heating stage, and introducing compensation corrections when the flow rate changes; performing anomaly detection based on the system state characterization quantity, and jointly judging it in conjunction with the flow rate deviation and temperature sensor consistency deviation indices, generating anomaly scores based on the judgment results, and outputting corresponding hierarchical control strategies.

Description

Technical Field

[0001] This invention relates to the field of non-contact liquid heating technology, and more particularly to an open non-contact liquid heating method. Background Technology

[0002] With the development of medical procedures such as peritoneal dialysis and intravenous infusion, heating fluids to improve patient comfort and treatment efficacy has become a common need. Current technologies typically employ heating plates, heating bags, or circulating heating devices to heat fluids, with open, non-contact heating methods being widely used due to their simple structure and ease of maintenance.

[0003] In existing liquid heating systems, temperature sensors are typically used to collect the liquid temperature or the temperature of the heating unit. Based on preset temperature thresholds, the heating unit is controlled to switch on / off or its power is adjusted. For example, basic temperature control is achieved by measuring temperature at single or multiple points and selecting the maximum or average value as the control basis. Additionally, some systems incorporate over-temperature protection and sensor fault detection mechanisms to ensure basic operational safety.

[0004] However, in practical applications, as the usage scenarios become more complex and the requirements for control precision increase, the aforementioned control methods based on simple rules have gradually revealed their limitations. First, since liquid temperature is often measured at multiple locations, different sensors vary in installation location, response characteristics, and measurement stability. Existing technologies often use direct value taking or simple averaging for multi-source temperature data, lacking differentiation and comprehensive utilization of data reliability. This results in insufficient accuracy of temperature characterization when noise interference or measurement deviations are present.

[0005] Inaccurate temperature characterization further impacts the effectiveness of heating control strategies. Existing control methods often rely on fixed thresholds or simple hysteresis adjustment, lacking characterization of the dynamic characteristics of the heating process and failing to adjust the control strategy in conjunction with temperature change trends. This makes them prone to overshoot during heating and fluctuations when approaching the target temperature, thus making it difficult to balance heating efficiency and control stability.

[0006] Furthermore, during liquid delivery, changes in flow rate directly affect heat exchange efficiency, causing the liquid temperature to exhibit significant dynamic changes. However, existing technologies typically treat temperature control separately from the delivery process, lacking a mechanism for coordinated analysis and adjustment of parameters such as flow rate. This results in a lag in heating control response when operating conditions change, making it difficult to match actual heat demands in a timely manner.

[0007] Under the combined effects of the aforementioned multiple factors, the system's operating state exhibits distinct phased and dynamic characteristics. However, existing technologies lack the ability to identify and differentiate operating states, still employing a uniform control strategy that makes it difficult to differentiate adjustments for different stages, further impacting the overall control effectiveness. The lack of joint analysis of multi-source information makes it difficult to accurately distinguish between different types of problems such as sensor anomalies, heating anomalies, and infusion anomalies, leading to misjudgments or missed diagnoses and reducing system reliability.

[0008] The purpose of this invention is to design an open, non-contact liquid heating method to address the problems existing in the prior art. Summary of the Invention

[0009] In view of this, the purpose of this invention is to propose an open, non-contact liquid heating method that can solve the above-mentioned problems.

[0010] This invention provides an open, non-contact liquid heating method, comprising: S1 collects multi-point temperature data of dialysis fluid and temperature data of heating unit, and obtains flow rate deviation and temperature sensor consistency deviation index during dialysis fluid infusion. All temperature data are preprocessed to obtain a stable multi-source temperature data sequence. S2 performs fusion processing based on multi-source temperature data to obtain the characterization temperature of the dialysis liquid, and combines temperature change characteristics, flow rate deviation and temperature sensor consistency deviation index for joint analysis to construct system state characterization quantities; S3 identifies the heating stage based on system state characterization quantities, takes the temperature of the dialysis liquid as the control target, generates heating control quantities according to the heating stage, and introduces compensation correction when the flow rate changes. S4 performs anomaly detection based on system state characterization parameters, and combines flow rate deviation and temperature sensor consistency deviation indicators for joint judgment. Based on the judgment results, it generates anomaly scores and outputs corresponding hierarchical control strategies.

[0011] The beneficial effects of this invention are: Firstly, by collecting multi-point temperature data of the dialysis fluid and the heating unit, and preprocessing it using flow rate deviation and sensor consistency indicators, along with anomaly removal, filtering, and time alignment, a stable and time-consistent multi-source temperature data sequence can be obtained. Compared to existing technologies that directly use single-point or unprocessed data, this invention can effectively suppress noise interference, eliminate abnormal measurements, and solve data asynchrony problems, thereby improving the reliability and usability of temperature data.

[0012] Secondly, by introducing fluctuation variance and rate of change to construct adaptive weights, multi-source temperature data are fused to obtain a more representative liquid characterization temperature. Furthermore, temperature deviation, rate of change, flow rate deviation, and sensor consistency indicators are combined to construct a system state characterization quantity. This invention can dynamically allocate weights based on the stability and dynamic characteristics of each sensor's data, avoiding the error amplification problem caused by simple averaging. Simultaneously, it achieves multi-factor joint modeling, improving the accuracy and comprehensiveness of the system state description.

[0013] Third, by identifying the heating process in stages based on temperature deviation and rate of change, and generating heating control quantities using differentiated control strategies at different stages, combined with power hierarchical scheduling, smoothing processing, and flow rate feedforward compensation, dynamic adjustment of the heating process is achieved. Compared with traditional fixed control methods, this invention can balance heating efficiency and steady-state accuracy, effectively suppress temperature overshoot and fluctuations, and respond quickly to changes in flow rate, thereby improving the system's control performance and adaptability.

[0014] Fourth, by comprehensively analyzing sensor consistency, temperature change characteristics, and control response, this invention enables the identification and differentiation of various types of operational anomalies, including sensor malfunctions, heating anomalies, and infusion anomalies. This invention avoids the misjudgment or missed judgment problems caused by relying solely on a single parameter in existing technologies, thereby improving the safety and reliability of system operation and providing a basis for subsequent protection or adjustment strategies. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings required in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart of the method in this embodiment. Detailed Implementation

[0017] To facilitate understanding by those skilled in the art, the structure of the present invention will now be described in further detail with reference to the accompanying drawings. It should be understood that, unless otherwise specified, the order of the steps mentioned in this embodiment can be adjusted according to actual needs, and they can even be executed simultaneously or partially simultaneously.

[0018] like Figure 1 As shown, this embodiment of the invention provides an open, non-contact liquid heating method, comprising: S1 collects multi-point temperature data of dialysis fluid and temperature data of heating unit, and obtains flow rate deviation and temperature sensor consistency deviation index during dialysis fluid infusion. All temperature data are preprocessed to obtain a stable multi-source temperature data sequence. S101 sets a first temperature sensor in the heating area of ​​the liquid container, a second temperature sensor in the liquid output path, and a third temperature sensor in the heating unit, which are used to collect temperature data at different locations respectively. In this step, the heating area of ​​the body container reflects the initial state of overall liquid heating, the liquid output path characterizes the final temperature of the liquid before it is actually infused into the patient, and the location of the heating unit reflects the heat source output state and heating intensity. Through the coordinated placement of these three types of locations, the entire process information—from heat source temperature to intermediate transfer temperature to final output temperature—can be obtained, thus constructing a complete temperature transfer chain. This setup solves the problem that relying solely on single-point or localized temperatures cannot accurately reflect the true heating state of the liquid.

[0019] S102 calculates the mean deviation of each temperature sensor based on the temperature data from each sensor, using this deviation as a sensor consistency index. The calculation formula is as follows: , , in, This represents the temperature data from the first temperature sensor. This indicates the temperature data from the second temperature sensor. This indicates the temperature data from the third temperature sensor. This represents the average temperature data from three temperature sensors. Indicates sensor consistency metrics; This step is used to evaluate the consistency of measurement results from each sensor, thereby identifying sensor drift or localized abnormal temperatures and resolving measurement distortion issues caused by sensor malfunctions or localized overheating. For example, when a sensor experiences drift due to aging, its measured value will deviate significantly from the average value, thus increasing the consistency index, which can be used for anomaly identification.

[0020] S103 collects the current flow rate during the liquid infusion process and calculates the flow rate deviation between it and the reference flow rate; This step aims to reflect changes in operating conditions during liquid delivery and address the issue of altered heat exchange conditions caused by flow rate fluctuations. For example, when the flow rate suddenly increases, the liquid's residence time in the heating zone shortens, leading to a drop in outlet temperature. Introducing flow rate deviations can provide a basis for compensation in subsequent control.

[0021] After performing outlier removal and filtering on the temperature data, S104 will perform time alignment on the multi-source temperature data to construct a synchronized temperature sequence.

[0022] If the difference between adjacent temperature data in S1041 exceeds the temperature threshold, it is judged as an anomaly and removed. The S1042 applies a first-order low-pass filter to the temperature data, followed by time alignment to construct a synchronized temperature sequence.

[0023] This step effectively addresses issues such as spike noise, random fluctuations, and asynchronous sampling in temperature data, thereby obtaining a continuous, stable, and time-consistent multi-source temperature data sequence, providing a reliable foundation for subsequent data fusion and control decisions.

[0024] S2 performs fusion processing based on multi-source temperature data to obtain the characterization temperature of the dialysis liquid, and combines temperature change characteristics, flow rate deviation and temperature sensor consistency deviation index for joint analysis to construct system state characterization quantities; In this step, scattered multi-source information is transformed into a unified state description, solving the problems of insufficient utilization of multi-source data and single control basis in the existing technology.

[0025] S201 calculates the fluctuation variance and rate of change of each temperature signal, constructs weighting coefficients based on the fluctuation and rate of change, and then fuses the temperature sequences after normalization to obtain the liquid characterization temperature. In this step, the contribution of different sensor data is dynamically adjusted based on their reliability, thus addressing the problem that traditional averaging methods cannot distinguish data quality. For example, when a sensor signal fluctuates significantly or changes abnormally, its weight will be reduced, thereby minimizing interference with the fusion result.

[0026] After applying a sliding window to the temperature series, S2011 calculates the... i The mean temperature and variance of a temperature signal within a window are calculated using the following formulas: （k）= , , in, Let N represent the variance of the i-th temperature signal fluctuation, and let N represent the sliding window length. This represents the average temperature within the window. () represents the temperature value of the i-th temperature sensor at time k; This step is used to characterize the stability of the temperature signal over a short period of time, addressing the impact of transient noise on weight calculation. For example, in the presence of environmental interference, the temperature signal may experience short-term fluctuations; a sliding window can smoothly reflect its true fluctuation level.

[0027] S2012 calculates the rate of change of each temperature signal based on temperature signal values ​​at adjacent times, using the following formula: ， in, This represents the rate of change of the i-th temperature signal. Indicates the time sampling interval; This step characterizes the temperature change trend, addressing the problem that relying solely on static values ​​cannot reflect dynamic processes. For example, during the heating phase, the rate of temperature increase varies at different locations; the rate of change can be used to identify measuring points with faster or slower responses.

[0028] S2013 constructs weighting coefficients based on volatility variance and rate of change, and then performs normalization processing. The calculation formula is as follows: ， ， in, Indicates the first i The initial weights of each temperature signal, Indicates the influence coefficient of the rate of change. This indicates a small positive number that prevents the denominator from being zero. Represents the normalized weights, Indicates the number of temperature signals.

[0029] In this step, signal stability and dynamic response characteristics are considered comprehensively, so that stable and reasonably varying temperature signals are given higher weights, thereby improving the representativeness and robustness of the fused temperature. For example, when a sensor is both stable and conforms to the overall trend, its weight is higher, while the weights of abnormal fluctuations or abrupt changes are suppressed.

[0030] S202 constructs temperature change characteristics based on the rate of temperature change of the liquid and the temperature deviation from the target temperature. The calculation formula is as follows: , = - , in, This represents the rate of change of temperature in a liquid. This indicates the temperature deviation between the current temperature and the target temperature. Indicates the target set temperature. Indicates the temperature of the liquid; This step is used to simultaneously characterize the current temperature state and its changing trend, addressing the lack of dynamic information in existing control methods. For example, when approaching the target temperature, even if the temperature deviation is small, a large rate of change may pose an overshoot risk. Introducing the rate of change allows for advance adjustment of the control strategy.

[0031] S203 combines temperature change characteristics, flow rate deviation, and sensor consistency indicators to form a system state characterization vector.

[0032] In this step, temperature conditions, flow conditions, and measurement reliability are modeled in a unified manner to solve the problem of fragmented treatment of various factors in existing technologies.

[0033] S3 identifies the heating stage based on system state characterization quantities, takes the temperature of the dialysis liquid as the control target, generates heating control quantities according to the heating stage, and introduces compensation correction when the flow rate changes. In this step, the heating process is transformed from a single control mode to a staged dynamic control mode, thereby solving the problem of existing technologies having a single control strategy and difficulty in balancing heating efficiency and stability. For example, rapid heating is required in the initial stage of heating, while overshoot needs to be suppressed when approaching the target temperature. Differentiated control can be achieved through stage differentiation. The specific steps are as follows: S301 identifies the current heating process stage based on temperature change characteristics, thus obtaining the heating stage; S3011 If temperature deviation If the temperature deviation threshold is reached, it is determined to be in the heating stage; S3012 If temperature deviation ≤Temperature deviation threshold and the rate of change of liquid characterization temperature If the rate of change exceeds the threshold, it is determined to be in the approximation stage; S3013 If temperature deviation ≤Temperature deviation threshold and the rate of change of liquid characterization temperature If the change rate is less than or equal to the threshold, it is determined to be in the steady-state maintenance stage.

[0034] In this step, the heating phase indicates a significant difference between the current liquid temperature and the target temperature, requiring the system to provide greater heating power to improve heating efficiency. For example, at the beginning of dialysis, the initial liquid temperature is low, and this determination allows the system to quickly enter a high-power heating state.

[0035] The approach phase indicates that the temperature is close to the target value but still has an upward trend. By identifying this state, the heating intensity can be appropriately reduced to prevent temperature overshoot due to inertia. For example, when the liquid temperature is close to the set value but still rising rapidly, the system can adjust in advance by entering the approach phase.

[0036] The steady-state maintenance phase indicates that the system is close to thermal equilibrium. Maintaining temperature stability and reducing fluctuations can be achieved through small-scale adjustments. For example, during stable infusion, the system maintains the liquid temperature within a set range through low-power regulation.

[0037] S302 generates heating control quantities based on the heating stage, combined with temperature deviation and the rate of change of liquid characterization temperature. The calculation formula is as follows: , in, Indicates the heating control amount. and This indicates the different control parameters corresponding to different heating stages; In this step, by employing a combined control method that includes both proportional and rate-of-change terms, the controlled quantity reflects both the current temperature deviation and the temperature change trend, thereby solving the problem of response lag or over-adjustment when relying solely on a single temperature error for control. For example, when the temperature deviation is small but the rate of change is large, the heating power can be reduced in advance to suppress overshoot.

[0038] S303 performs hierarchical scheduling of heating control quantities, and compensates and corrects them in combination with operating parameters to obtain control output.

[0039] S3031 maps continuous heating control quantities to a preset set of power levels, satisfying: , in, = Indicates the heating power after the stage. Represents a hierarchical mapping function. Indicates the continuous heating control quantity; In this step, the control quantity is discretized through a hierarchical mapping function to accommodate the characteristic that actual heating units typically only support a limited number of power levels, thereby solving the problem that continuous control quantities cannot be directly executed. For example, the calculated power is mapped to one of several fixed power levels.

[0040] S3032 performs continuous interpolation between adjacent power levels to achieve a smooth transition. The calculation formula is as follows: , in, This indicates the smoothed heating control amount. ∈[0,1] represents the interpolation coefficients. This represents the i-th power level; In this step, a smoothed heating control value is obtained to avoid sudden output changes caused by power level switching. For example, interpolation can be used to achieve a transition between two adjacent power levels, which can reduce temperature fluctuations and system oscillations.

[0041] During liquid delivery, when a change in flow rate is detected, S3033 introduces feedforward compensation based on the deviation between the current flow rate and the reference flow rate to correct the smoothed heating control quantity. The calculation formula is as follows: , in, This indicates the compensated heating control amount. This represents the velocity compensation coefficient. This indicates the velocity deviation between the current velocity and the reference velocity.

[0042] This step addresses the impact of flow rate variations on the heat exchange process, enabling the control system to respond proactively to changes in operating conditions. For example, when the flow rate increases, the liquid's heating time shortens; by adding a compensation term, the heating power can be increased, thereby maintaining a stable output temperature.

[0043] S4 performs anomaly detection based on system state characterization parameters, and combines flow rate deviation and temperature sensor consistency deviation indicators for joint judgment. Based on the judgment results, it generates anomaly scores and outputs corresponding hierarchical control strategies.

[0044] S401 If the sensor consistency deviation exceeds its threshold, it is marked as a sensor abnormality; if the rate of change of the liquid characterization temperature exceeds its threshold, it is marked as a heating abnormality; if the flow rate deviation exceeds its threshold, it is marked as an infusion abnormality, thus obtaining several abnormality types. In this step, anomalies are categorized to address the problem of indistinguishable anomaly sources in existing technologies. For example, when a temperature sensor drifts, it manifests as an increased consistency deviation rather than a true temperature change. This categorization helps avoid misjudging it as a heating anomaly.

[0045] S402 calculates an anomaly score based on the sensor consistency deviation index, the rate of change of liquid characterization temperature, flow rate deviation, and their corresponding anomaly types. The calculation formula is as follows: , in, Indicates an abnormal score. Indicates sensor consistency deviation. Indicator values ​​that represent the types of exceptions. , These represent the corresponding weights; In this step, a weighted fusion model is constructed to comprehensively and quantitatively assess different anomaly factors, addressing the problem that a single threshold judgment is insufficient to reflect the severity of anomalies. For example, when the flow rate deviation is small but the temperature change is drastic, the system can still identify potential risks through comprehensive scoring, thereby enabling proactive measures to be taken.

[0046] S403 generates a graded control strategy based on anomaly scoring to correct or limit the heating control quantity.

[0047] S4031 When the abnormal score is less than or equal to the first abnormal threshold, reduce the heating control quantity; S4032 When the first abnormal threshold < abnormal score ≤ second abnormal threshold, degraded operation is executed to limit the maximum output power; When the abnormal score exceeds the second abnormal threshold, the S4033 shuts off the heating and outputs an alarm signal.

[0048] In this step, reducing the heating control amount is used for preventative adjustments in the event of minor abnormalities. For example, when temperature fluctuations increase slightly, reducing the power can prevent further fluctuations or overshoot.

[0049] Limiting the maximum output power is used in moderately abnormal scenarios, such as when there are significant fluctuations in flow rate or abnormally severe temperature changes, to prevent the system from entering an unstable state by limiting the output.

[0050] In severe abnormal situations, such as sensor failure or a rapid and abnormal rise in temperature, the heating can be shut off immediately and an alarm signal can be issued to prevent safety risks to patients.

[0051] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0052] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0053] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0054] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0055] It should be noted that any reference signs placed between parentheses in the claims should not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The words first, second, and third, etc., do not indicate any order. These words can be interpreted as names.

[0056] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0057] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

[0058] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0059] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms should not be construed as necessarily referring to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

Claims

1. An open-type, non-contact liquid heating method, characterized in that, include: S1 collects multi-point temperature data of dialysis fluid and temperature data of heating unit, and obtains flow rate deviation and temperature sensor consistency deviation index during dialysis fluid infusion. All temperature data are preprocessed to obtain a stable multi-source temperature data sequence. S2 performs fusion processing based on multi-source temperature data to obtain the characterization temperature of the dialysis liquid, and combines temperature change characteristics, flow rate deviation and temperature sensor consistency deviation index for joint analysis to construct system state characterization quantities; S3 identifies the heating stage based on system state characterization quantities, takes the temperature of the dialysis liquid as the control target, generates heating control quantities according to the heating stage, and introduces compensation correction when the flow rate changes. S4 performs anomaly detection based on system state characterization parameters, and combines flow rate deviation and temperature sensor consistency deviation indicators for joint judgment. Based on the judgment results, it generates anomaly scores and outputs corresponding hierarchical control strategies.

2. The open-type non-contact liquid heating method according to claim 1, characterized in that, The process involves collecting multi-point temperature data of the dialysis fluid and temperature data from the heating unit, obtaining flow rate deviation and temperature sensor consistency deviation indices during the dialysis fluid infusion process, and preprocessing all temperature data to obtain a stable multi-source temperature data sequence, including: S101 sets a first temperature sensor in the heating area of ​​the liquid container, a second temperature sensor in the liquid output path, and a third temperature sensor in the heating unit, which are used to collect temperature data at different locations respectively. S102 calculates the mean deviation of each temperature sensor based on the temperature data from each sensor, using this deviation as a sensor consistency index. The calculation formula is as follows: ， ， in, This represents the temperature data from the first temperature sensor. This indicates the temperature data from the second temperature sensor. This indicates the temperature data from the third temperature sensor. This represents the average temperature data from three temperature sensors. Indicates sensor consistency metrics; S103 collects the current flow rate during the liquid infusion process and calculates the flow rate deviation between it and the reference flow rate; After performing outlier removal and filtering on the temperature data, S104 will perform time alignment on the multi-source temperature data to construct a synchronized temperature sequence.

3. The open-type non-contact liquid heating method according to claim 2, characterized in that, After outlier removal and filtering of the temperature data, the multi-source temperature data will be time-aligned to construct a synchronized temperature sequence, including: If the difference between adjacent temperature data in S1041 exceeds the temperature threshold, it is judged as an anomaly and removed. The S1042 applies a first-order low-pass filter to the temperature data, followed by time alignment to construct a synchronized temperature sequence.

4. The open-type non-contact liquid heating method according to claim 1, characterized in that, The process involves fusing multi-source temperature data to obtain the dialysis fluid characterization temperature. This temperature change characteristics, flow rate deviation, and temperature sensor consistency deviation indices are then combined for joint analysis to construct system state characterization parameters, including: S201 calculates the fluctuation variance and rate of change of each temperature signal, constructs weighting coefficients based on the fluctuation and rate of change, and then fuses the temperature sequences after normalization to obtain the liquid characterization temperature. S202 constructs temperature change characteristics based on the rate of temperature change of the liquid and the temperature deviation from the target temperature. The calculation formula is as follows: , = - , in, This represents the rate of change of temperature in a liquid. This indicates the temperature deviation between the current temperature and the target temperature. Indicates the target set temperature. Indicates the temperature of the liquid; S203 combines temperature change characteristics, flow rate deviation, and sensor consistency indicators to form a system state characterization vector.

5. The open-type non-contact liquid heating method according to claim 4, characterized in that, The process involves calculating the fluctuation variance and rate of change of each temperature signal, constructing weighting coefficients based on the fluctuation and rate of change, and then normalizing the temperature sequences before fusing them to obtain the liquid characterization temperature, including: After applying a sliding window to the temperature series, S2011 calculates the... i The mean temperature and variance of a temperature signal within a window are calculated using the following formulas: （k）= ， ， in, Let N represent the variance of the i-th temperature signal fluctuation, and let N represent the sliding window length. This represents the average temperature within the window. () represents the temperature value of the i-th temperature sensor at time k; S2012 calculates the rate of change of each temperature signal based on temperature signal values ​​at adjacent times, using the following formula: ， in, This represents the rate of change of the i-th temperature signal. Indicates the time sampling interval; S2013 constructs weighting coefficients based on volatility variance and rate of change, and then performs normalization processing. The calculation formula is as follows: ， ， in, Indicates the first i The initial weights of each temperature signal, Indicates the influence coefficient of the rate of change. This indicates the prevention of small positive numbers with a denominator of zero. Represents the normalized weights, Indicates the number of temperature signals.

6. The open-type non-contact liquid heating method according to claim 1, characterized in that, The heating stage identification based on system state characterization quantities, with the dialysate characterization temperature as the control target, generates heating control quantities according to the heating stage, and introduces compensation corrections when the flow rate changes, including: S301 identifies the current heating process stage based on temperature change characteristics, thus obtaining the heating stage; S302 generates heating control quantities based on the heating stage, combined with temperature deviation and the rate of change of liquid characterization temperature. The calculation formula is as follows: ， in, This indicates the heating control amount. and This indicates the different control parameters corresponding to different heating stages; S303 performs hierarchical scheduling of heating control quantities, and compensates and corrects them in combination with operating parameters to obtain control output.

7. The open-type non-contact liquid heating method according to claim 6, characterized in that, The heating stages are identified based on temperature change characteristics, resulting in the following heating stages: S3011 If temperature deviation If the temperature deviation threshold is reached, it is determined to be in the heating phase; S3012 If temperature deviation ≤Temperature deviation threshold and the rate of change of liquid characterization temperature If the rate of change exceeds the threshold, it is determined to be in the approximation stage; S3013 If temperature deviation ≤Temperature deviation threshold and the rate of change of liquid characterization temperature If the change rate is less than or equal to the threshold, it is determined to be in the steady-state maintenance stage.

8. The open-type non-contact liquid heating method according to claim 6, characterized in that, The step of hierarchically scheduling the heating control quantity and compensating and correcting it in conjunction with operating parameters to obtain the control output includes: S3031 maps continuous heating control quantities to a preset set of power levels, satisfying: ， in, = Indicates the heating power after the stage. Represents a hierarchical mapping function. Indicates the continuous heating control quantity; S3032 performs continuous interpolation between adjacent power levels to achieve a smooth transition. The calculation formula is as follows: ， in, This indicates the smoothed heating control amount. ∈[0,1] represents the interpolation coefficients. This represents the i-th power level; In the liquid delivery process, when a change in flow rate is detected, S3033 introduces feedforward compensation based on the deviation between the current flow rate and the reference flow rate to correct the smoothed heating control quantity. The calculation formula is as follows: ， in, This indicates the compensated heating control amount. This represents the velocity compensation coefficient. This indicates the velocity deviation between the current velocity and the reference velocity.

9. The open-type non-contact liquid heating method according to claim 1, characterized in that, The method of anomaly detection based on system state characteristics, combined with flow velocity deviation and temperature sensor consistency deviation indices for joint judgment, generates anomaly scores based on the judgment results, and outputs corresponding hierarchical control strategies, including: S401 If the sensor consistency deviation exceeds its threshold, it is marked as a sensor abnormality; if the rate of change of the liquid characterization temperature exceeds its threshold, it is marked as a heating abnormality; if the flow rate deviation exceeds its threshold, it is marked as an infusion abnormality, thus obtaining several abnormality types. S402 calculates an anomaly score based on the sensor consistency deviation index, the rate of change of liquid characterization temperature, flow rate deviation, and their corresponding anomaly types. The calculation formula is as follows: ， in, Indicates an abnormal score. Indicates sensor consistency deviation. Indicator values ​​that represent the types of exceptions. , These represent the corresponding weights; S403 generates a graded control strategy based on anomaly scoring to correct or limit the heating control quantity.

10. An open-type non-contact liquid heating method according to claim 9, characterized in that, The hierarchical control strategy based on anomaly scoring, which corrects or limits the heating control quantity, includes: S4031 When the abnormal score is less than or equal to the first abnormal threshold, reduce the heating control quantity; S4032 When the first abnormal threshold < abnormal score ≤ second abnormal threshold, degraded operation is executed to limit the maximum output power; When the abnormal score exceeds the second abnormal threshold, the S4033 shuts off the heating and outputs an alarm signal.

Images