Peritoneal dialysis solution incubator control method and incubator

Abstract

The invention provides a peritoneal dialysis solution heat preservation box control method and a heat preservation box, and relates to the technical field of equipment control. Performing heating power deviation analysis on the heating assembly to obtain heating power error information; carrying out weighing deviation analysis to obtain weighing error information; dialysate weighing information of the weighing assembly is obtained; error compensation is carried out, and calibration dialysate weighing information is obtained; performing error compensation to obtain calibrated heating power; and controlling the peritoneal dialysis solution incubator. According to the invention, the technical problem of inaccurate dialysate heating and metering caused by deviation of the heating power and the weighing of the peritoneal dialysis solution incubator in the prior art is solved, and accurate error compensation and control of the heating power and the weighing information of the peritoneal dialysis solution incubator are realized; and the heating and weighing accuracy and reliability of the dialysate in the peritoneal dialysis treatment process are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment control, and in particular to a peritoneal dialysis fluid incubator control method and an incubator. Background Art

[0002] Traditional peritoneal dialysis fluid incubator technology has many defects. On the one hand, in the heating process, since the heating components are affected by various factors, such as ambient temperature fluctuations and unstable power supply, it is difficult to accurately maintain the target heating power, resulting in a large deviation between the actual temperature of the dialysis fluid and the ideal temperature. On the other hand, the weighing components also face problems. Due to aging of the mechanical structure and changes in sensor sensitivity, weighing deviations occur, resulting in errors in ultrafiltration calculations, affecting medical staff's judgment of the patient's dialysis effect.

[0003] Therefore, the prior art has a technical problem that the peritoneal dialysis fluid incubator has inaccurate heating and metering of the dialysis fluid due to deviations in heating power and weighing. Summary of the invention

[0004] The present application provides a peritoneal dialysis fluid incubator control method and incubator, which are used to solve the technical problem of inaccurate heating and metering of dialysis fluid caused by deviations in heating power and weighing of peritoneal dialysis fluid incubators in the prior art.

[0005] In view of the above problems, the present application provides a peritoneal dialysis fluid incubator control method and an incubator.

[0006] In a first aspect of the present application, a peritoneal dialysis fluid incubator control method is provided, the method comprising:

[0007] Obtaining a dialysate target heating power; performing a heating power deviation analysis on a heating component to obtain heating power error information; performing a weighing deviation analysis on a weighing component to obtain weighing error information; obtaining dialysate weighing information of the weighing component; performing error compensation on the dialysate weighing information according to the weighing error information to obtain calibrated dialysate weighing information; performing error compensation on the dialysate target heating power according to the heating power error information to obtain calibrated heating power; and executing peritoneal dialysis fluid incubator control according to the calibrated dialysate weighing information and the calibrated heating power.

[0008] A second aspect of the present application provides a peritoneal dialysis fluid incubator, the incubator comprising:

[0009] An insulation chamber; a heating component, the heating component is deployed inside the insulation chamber; a weighing component, the weighing component is deployed on the bottom surface of the insulation chamber; a font observation window, the font observation window is deployed on the side of the insulation chamber, is made of transparent material, and has a preset font scale; a voice announcer.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] Obtain the target heating power of the dialysate; perform heating power deviation analysis on the heating component to obtain heating power error information; perform weighing deviation analysis to obtain weighing error information; obtain dialysate weighing information of the weighing component; perform error compensation on the dialysate weighing information to obtain calibrated dialysate weighing information; perform error compensation on the dialysate target heating power to obtain calibrated heating power; and execute peritoneal dialysis fluid incubator control. The system achieves the technical effect of realizing accurate error compensation and control of the heating power and weighing information of the peritoneal dialysis fluid incubator, and improving the accuracy and reliability of dialysate heating and weighing during peritoneal dialysis treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A schematic flow chart of a peritoneal dialysis fluid incubator control method is provided for this application;

[0013] Figure 2 A schematic flow chart of obtaining a target heating power of a peritoneal dialysis fluid incubator in a peritoneal dialysis fluid incubator control method is provided for the present application. DETAILED DESCRIPTION

[0014] The present application provides a peritoneal dialysis fluid incubator control method, which is used to solve the technical problem of inaccurate heating and metering of dialysis fluid caused by deviations in heating power and weighing of peritoneal dialysis fluid incubators in the prior art.

[0015] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0016] Embodiment 1, as Figure 1 As shown, the present application provides a peritoneal dialysis fluid incubator control method, the method comprising:

[0017] Step S100: Obtaining the dialysate target heating power.

[0018] Specifically, obtaining the dialysate target heating power is the key initial step to achieve accurate heating of peritoneal dialysis fluid. This requires comprehensive consideration of multiple factors and is achieved through a variety of data collection and processing methods. First, high-precision temperature sensors are used to accurately measure the dialysate target temperature, the initial temperature of the insulation chamber, and the environmental monitoring temperature. The dialysate target temperature clarifies the ideal temperature state that the dialysate needs to reach during the treatment process, which is the core guide for subsequent power calculations; the initial temperature of the insulation chamber reflects the basic heat condition in the chamber at the beginning of heating, which has an important impact on heat transfer and power requirements; the environmental monitoring temperature reflects the heat exchange conditions of the external environment. Different ambient temperatures will affect the heat dissipation rate of the insulation box, and thus affect the setting of the heating power. Subsequently, these collected temperature data are used as input and input into the pre-built and strictly verified heating component-associated heating power configuration model. The model is based on a large amount of experimental data, thermodynamic principles, and actual operating experience. It can perform complex mathematical operations and logical judgments based on the input temperature data, and finally output the target heating power that adapts to the current dialysate heating needs. This power value will serve as the benchmark for subsequent heating operations, ensuring that the dialysate can be efficiently heated to the target temperature during the heating process, while avoiding problems such as waste of resources or insufficient heating due to excessively high or low power, laying a solid foundation for the precise control of the entire peritoneal dialysis fluid incubator.

[0019] Step S200: performing heating power deviation analysis on the heating component to obtain heating power error information.

[0020] Specifically, the heating power deviation analysis of the heating component is a key link to ensure the accuracy of dialysate heating. This process is achieved by deeply mining the historical operation data of the heating component. First, the heating control record data of the heating component in the preset time zone is obtained. The preset time zone is the interval covered by a certain time step from the current moment. These data record the working status and power output of the heating component in the past period in detail. Then, the target heating power record data and the actual heating power record data are extracted from these record data. The target heating power record data represents the theoretically expected heating power value, while the actual heating power record data truly reflects the actual power output of the heating component at that time. By calculating the deviation vector set between the two, the size and direction of the power deviation can be intuitively presented. Finally, the frequency fitting technology is used to conduct a comprehensive and in-depth analysis of the deviation vector set. In this process, by traversing the deviation vector set, the distribution density of each deviation vector is evaluated, the deviation vector distribution density set is constructed, and the distribution density weight set is further calculated. According to these weight sets, the deviation vector set is weighted mean analyzed to accurately obtain the heating power error information. This information can accurately reveal the power deviation patterns and characteristics of the heating component in actual operation, provide a key basis for subsequent error compensation, and ensure that the heating component can output more accurate and stable heating power in subsequent work to meet the strict requirements of peritoneal dialysis fluid for temperature control.

[0021] Step S300: performing weighing deviation analysis on the weighing component to obtain weighing error information.

[0022] Specifically, it is necessary to collect various data related to the weighing component, including but not limited to its historical weighing records, weighing data under different load conditions, and environmental factors that may affect weighing. These data will provide basic materials for subsequent analysis. Then, the collected data is deeply mined, and the discrete degree and deviation trend of the weighing data are calculated by comparing the weighing results of the same dialysate sample at different times or on different weighing components. At the same time, the potential impact of environmental factors such as temperature and humidity on the weighing accuracy is considered, and a corresponding compensation model is established. Then, the physical properties of the weighing component itself are accurately measured and analyzed, such as the sensitivity and linearity of the sensor, and the changes of these characteristics during long-term use and their impact on the weighing results are evaluated. By comprehensively considering the above factors, the weighing error range and error distribution law of the weighing component under various working conditions are calculated, so as to obtain accurate weighing error information. Finally, the obtained weighing error information is sorted and recorded so that it can be used for real-time error compensation of the dialysate weighing information in subsequent steps, ensuring that the weighing component can provide more accurate and reliable dialysate weight data in actual use, and provide strong support for the safety and effectiveness of peritoneal dialysis treatment.

[0023] Step S400: Obtain dialysate weighing information of the weighing component.

[0024] Specifically, obtaining dialysate weighing information from the weighing component is an important part of achieving accurate management of peritoneal dialysis fluid. This process relies on the high-precision sensing and data acquisition functions of the weighing component. When the dialysate is placed in the insulation chamber of the peritoneal dialysis fluid incubator, the weighing component deployed on the bottom of the chamber starts working immediately. The sensor in the weighing component senses the gravity exerted by the dialysate in real time and converts it into an electrical signal. The electrical signal is processed by the built-in analog-to-digital conversion circuit, converted into a digital signal and transmitted to the control system. The control system analyzes and calculates these digital signals according to the preset algorithm and data processing program, so as to accurately obtain the real-time weight value of the dialysate. Throughout the process, in order to ensure the accuracy and stability of the weighing information, the weighing component will continue to perform self-calibration and environmental compensation. It can automatically adapt to slight changes in environmental factors such as temperature and humidity in the incubator, and at the same time correct the drift and nonlinear errors of the sensor itself in real time. Through such a series of rigorous data collection and processing operations, accurate and reliable dialysate weighing information is finally obtained, providing key data support for subsequent error compensation, heating power control and precise management of the entire peritoneal dialysis fluid incubator.

[0025] Step S500: performing error compensation on the dialysate weighing information according to the weighing error information to obtain calibrated dialysate weighing information.

[0026] Specifically, error compensation of dialysate weighing information based on weighing error information is a key step to improve weighing accuracy. When accurate weighing error information is obtained, the error compensation mechanism is quickly started. First, the characteristics of weighing error information are deeply analyzed, including the size and direction of the error (positive deviation or negative deviation) and its distribution law in different weighing ranges. Then, for the dialysate weighing information, real-time adjustments are made according to the established compensation algorithm. If the weighing error information shows a positive deviation, it means that the actual weighing value is larger than the true value. At this time, the control system will subtract the corresponding deviation from the dialysate weighing information according to the specific value of the deviation; conversely, if it is a negative deviation, the corresponding deviation will be added. In the process of error compensation, the dynamic change of the error will also be fully considered. For example, if it is found that the weighing error shows a certain trend with the change of time or environmental factors, the control system will adopt a dynamic compensation strategy to update the compensation parameters in real time to ensure that the compensated dialysate weighing information is closer to the true value. After such a series of fine calculations and adjustments, the calibrated dialysate weighing information is finally obtained. This calibrated information not only eliminates the systematic error of the weighing component itself, but also reduces the random error caused by factors such as environmental interference to a certain extent, providing a more reliable data basis for the precise control of the peritoneal dialysis fluid incubator and ensuring accurate control of the dialysate dosage during dialysis treatment.

[0027] Step S600: performing error compensation on the dialysate target heating power according to the heating power error information to obtain a calibrated heating power.

[0028] Specifically, error compensation for the dialysate target heating power based on the heating power error information is a key operation to achieve precise heating control. Once the heating power error information is obtained, the compensation action is immediately carried out. First, the specific characteristics of the heating power error information are carefully analyzed to clarify the positive and negative directions of the error (that is, the actual power is higher or lower than the target power) and the magnitude of the error. At the same time, the changing trend of the error under different heating conditions and time periods is studied. Subsequently, based on the dialysate target heating power, precise compensation is implemented according to the error information. If the error information indicates that the actual heating power is lower than the target power, that is, there is a power shortage, the control system will increase the target heating power accordingly according to the size of the error to ensure that the dialysate can obtain sufficient heat supply; conversely, if the actual heating power is high and exceeds the target power, the control system will appropriately reduce the target heating power to avoid excessive heating and cause energy waste and possible adverse effects on the quality of the dialysate. During the compensation process, the dynamic changes of environmental factors inside and outside the incubator are fully considered, such as fluctuations in ambient temperature and changes in the heat dissipation rate of the insulation chamber. These factors will affect the actual demand for heating power. By real-time monitoring of environmental data and combining heating power error information, the compensation strategy is dynamically adjusted so that the calibrated heating power can always accurately adapt to the heating needs of the dialysate. The calibrated heating power finally obtained will provide more accurate power instructions for the heating components of the peritoneal dialysis fluid incubator, ensuring that the dialysate is stably maintained within the ideal temperature range throughout the heating process, ensuring the safety and efficiency of dialysis treatment.

[0029] Step S700: Execute peritoneal dialysis fluid incubator control according to the calibration dialysate weighing information and the calibration heating power.

[0030] Specifically, the control of the peritoneal dialysis fluid incubator based on the calibrated dialysate weighing information and the calibrated heating power is the core embodiment of the precise operation of the entire system. Based on the calibrated dialysate weighing information, the real-time weight of the dialysate in the insulation chamber is accurately grasped, and the working state of the heating component is reasonably regulated on this basis. When the weighing information shows that the dialysate weight has changed, such as injecting or withdrawing the dialysate, it can respond quickly and adjust the heating power according to the weight change to ensure that the dialysate can be heated evenly under different weight states and the temperature remains stable. At the same time, with the calibrated heating power, the output heat of the heating component can be accurately controlled to match it with the actual needs of the dialysate. During the heating process, key parameters such as the insulation chamber temperature, ambient temperature, and dialysate weight are continuously monitored. According to the dynamic changes of these parameters, the heating power is fine-tuned in real time to maintain the dialysate temperature always within the preset ideal range, avoiding excessively high or low temperatures that have adverse effects on the dialysate quality and treatment effect. In addition, based on the calibrated dialysate weighing information, when the dialysate weight approaches the critical value or reaches specific conditions, a corresponding warning signal will be issued to remind the operator to deal with it in time to ensure the safety, stability and efficiency of the peritoneal dialysis treatment process and ensure that patients can receive continuous and high-quality dialysis services.

[0031] In one possible implementation, Figure 2 As shown, step S100 also includes:

[0032] Step S110: Obtain the dialysate target temperature, the insulation chamber initial temperature and the environmental monitoring temperature.

[0033] Step S120: Processing the dialysate target temperature, the insulation chamber initial temperature and the environmental monitoring temperature through the associated heating power configuration model of the heating component, and outputting the dialysate target heating power.

[0034] Specifically, accurate acquisition of various temperature data is the basis for subsequent precise control. Use high-sensitivity temperature sensors to carefully measure the dialysate target temperature, the initial temperature of the insulation chamber, and the environmental monitoring temperature. The acquisition of the dialysate target temperature clarifies the temperature value that the dialysate should reach under ideal conditions, and is the core goal guide for the entire heating control process. The initial temperature of the insulation chamber reflects the heat condition in the chamber at the beginning of heating. This data is critical for the subsequent calculation of heat losses during heat transfer and the initial setting of heating power. The environmental monitoring temperature takes into account the impact of the external environment on the heat exchange of the insulation box. Different ambient temperatures will lead to differences in the heat dissipation rate of the insulation box, which in turn affects the demand for heating power.

[0035] When the dialysate target temperature, the initial temperature of the insulation chamber and the environmental monitoring temperature are processed by the associated heating power configuration model of the heating component to output the dialysate target heating power, the core algorithm idea is as follows: First, the key role of these three temperature parameters in the heat transfer process is clarified. The dialysate target temperature is the ideal state that is ultimately expected to be achieved. The initial temperature of the insulation chamber determines the initial heat basis, and the environmental monitoring temperature affects the heat exchange rate. The model builds a calculation framework for heat balance based on the principles of thermodynamics. For the heat transfer inside the insulation chamber, various modes such as heat conduction, convection and radiation are considered. According to Fourier's heat conduction law, the heat flux density generated by the temperature difference on the wall of the insulation chamber and the dialysate is calculated. At the same time, combined with the principle of convective heat transfer, the heat exchange caused by liquid flow and air flow is evaluated. Taking the initial temperature of the insulation chamber as the starting point, the outward heat loss rate and the temperature rise trend after the heating component inputs heat are determined based on the environmental monitoring temperature. Through step-by-step iterative calculation, an initial heating power is assumed, and the heat absorbed by the dialysate and the heat dissipated to the environment per unit time are calculated based on this power, thereby obtaining the change in dialysate temperature. The calculated temperature is compared with the dialysate target temperature. If there is a large deviation between the two, the assumed heating power is adjusted according to the direction and magnitude of the deviation, and the heat calculation and temperature prediction are performed again. This cycle is repeated to continuously optimize the assumed value of the heating power until the difference between the calculated dialysate temperature and the target temperature is within an extremely small acceptable range. The heating power determined at this time is the final output of the dialysate target heating power that is precisely adapted to the current working conditions, thereby ensuring that the dialysate can be driven by appropriate power and efficiently and stably heated to the ideal temperature state, meeting the strict temperature requirements of peritoneal dialysis treatment.

[0036] In a possible implementation, step S120 further includes:

[0037] Step S121: collecting historical heating record data of the heating component, wherein the historical heating record data includes dialysate target temperature record data, insulation chamber initial temperature record data, environmental monitoring temperature record data and heating power identification data.

[0038] Step S122: using the heating power identification data as supervision data, and using the dialysate target temperature record data, the insulation chamber initial temperature record data, and the environmental monitoring temperature record data as input data, to train a first heating power configuration channel.

[0039] Step S123: until the heating power identification data is used as the supervision data, the dialysate target temperature record data, the insulation chamber initial temperature record data, and the environmental monitoring temperature record data are used as the input data, and the Nth heating power configuration channel is trained, where N is an integer and N≥5.

[0040] Step S124: Perform mean full connection on the first heating power configuration channel to the Nth heating power configuration channel to obtain the associated heating power configuration model.

[0041] Specifically, collecting the historical heating record data of the heating component is the key starting step to build an accurate correlation heating power configuration model. To this end, a comprehensive and reliable data acquisition system is established, which is closely connected to the heating component and various temperature sensors in the incubator. In the past peritoneal dialysis fluid heating process, whenever the heating operation is started, the data acquisition system will start to record relevant data synchronously. For the dialysate target temperature record data, it accurately records the ideal dialysate temperature value expected to be achieved during each heating process. These data come from the pre-set treatment plan or the target temperature requirements determined by the doctor according to the specific situation of the patient. The initial temperature record data of the insulation chamber records in detail the actual temperature conditions in the insulation chamber at the moment of each heating start. This data can reflect the heat basis of the insulation chamber under different initial conditions, which is of great significance for the subsequent analysis of heat transfer and power requirements during the heating process. The environmental monitoring temperature record data is obtained through the temperature sensor deployed in the surrounding environment of the incubator. It records the temperature changes of the external environment in real time during the entire heating period, because the fluctuation of the ambient temperature will directly affect the heat dissipation rate of the incubator, and then affect the workload and power requirements of the heating component. Finally, the heating power identification data accurately records the actual heating power output of the heating component at each specific moment. It clarifies the energy supply level during the heating process at that time. Through the continuous and accurate collection of these different types of data, a rich and complete historical heating record data set is formed, which provides a comprehensive data foundation for the subsequent training of the heating power configuration channel, ensuring that the model can fully learn the complex relationship between heating power and temperature and other factors under various working conditions.

[0042] Initialize the neural network parameters of the first heating power configuration channel, including the connection weights and biases between neurons in each layer. These parameters are initialized to small random values. Next, select a set of dialysate target temperature record data, insulation chamber initial temperature record data, and environmental monitoring temperature record data from the historical heating record data set as input samples, and input them into the input layer of the neural network. The input data is passed to the hidden layer through the input layer. In the hidden layer, each neuron performs a weighted summation operation on the input data, that is, the input value of the neuron is equal to the sum of the product of the input data and the corresponding connection weight, and then adds the bias value, and then passes through the activation function (such as sigmoid function or ReLU function, etc.) for nonlinear transformation to obtain the output of the hidden layer neuron. The output of the hidden layer is then passed to the output layer, and is also processed by weighted summation and activation function (the output layer activation function can be selected according to specific needs, for example, a linear function is used to directly output the predicted heating power value), and the heating power value predicted by the neural network for the group of input data is obtained. The predicted heating power value is compared with the corresponding heating power identification data (true value), and the error between the two is calculated. Common error calculation methods include mean square error (MSE), that is, the error is equal to the average of the square of the difference between the predicted value and the true value. Then, based on the error value, the gradient of the connection weights and biases of each layer of neurons is calculated from the output layer using the back propagation algorithm. The gradient represents the rate of change of the error relative to each parameter. Finally, based on the calculated gradient, the stochastic gradient descent method is used to update the connection weights and biases of each layer of neurons. The update formula is that the new value of the parameter is equal to the old value of the parameter minus the learning rate multiplied by the gradient value. The learning rate is a pre-set hyperparameter for controlling the update step. Repeat the above steps, and perform multiple iterations of training on all samples in the data set until the preset training stop condition is met (such as reaching the maximum number of iterations or the error converges to a certain threshold). At this time, the first heating power configuration channel training is completed, and the heating power can be more accurately predicted based on the input dialysate target temperature, the initial temperature of the insulation chamber, and the environmental monitoring temperature.

[0043] Continuously training multiple (N and N≥5) heating power configuration channels is to enhance the generalization ability and stability of the model so as to more accurately handle the complex situations in the dialysate heating process. Starting from the training of the first heating power configuration channel, in the same way, for each heating power configuration channel (from the second channel to the Nth channel), the heating power identification data is used as the supervision data, and the dialysate target temperature record data, the insulation chamber initial temperature record data, and the environmental monitoring temperature record data are used as the input data for training. During the training process, each channel will gradually learn different feature representations and data patterns due to factors such as the randomness of the initialization parameters and the random sampling order of the training data. This diversity helps the model understand and grasp the complex relationship between the dialysate target temperature, the insulation chamber initial temperature, the environmental monitoring temperature and the heating power from multiple perspectives. As the number of training channels increases, the model can cover a wider range of working conditions and data features, so that when faced with new input data, there is a higher probability of making accurate heating power predictions. The entire training process is a process of continuous exploration and optimization. Through the collaborative training of multiple channels, a solid foundation is laid for the final construction of a high-performance associated heating power configuration model to ensure that the peritoneal dialysis fluid incubator can achieve accurate and efficient heating control in various actual usage scenarios.

[0044] The output results of the N trained heating power configuration channels are summarized. After receiving the input data such as the dialysate target temperature, the initial temperature of the insulation chamber, and the environmental monitoring temperature, each channel will generate a corresponding heating power prediction value based on its own learned parameters and patterns. Then, the mean calculation is performed for these predicted values, that is, the predicted heating power values ​​of each channel under the same input conditions are added, and then divided by the total number of channels N to obtain an average predicted power value. This mean calculation process integrates the prediction information of each channel, which can effectively reduce the prediction deviation that may exist in a single channel, making the final result more robust and representative. Finally, this mean result is associated and mapped with the final model output through the fully connected layer. The neurons in the fully connected layer are fully connected with the mean result calculated previously. Each neuron receives this mean information and performs further calculations and transformations according to the pre-set connection weights and biases, thereby converting the integrated information into the dialysate target heating power output that meets actual needs. After such a mean full connection operation, the associated heating power configuration model was successfully constructed. This model can integrate the learning advantages of multiple channels and more accurately predict the appropriate heating power based on the input temperature data, providing a reliable model support for the precise heating control of the peritoneal dialysis fluid incubator.

[0045] In a possible implementation, step S122 further includes:

[0046] Step S1221: Using the heating power identification data as the monitoring data, and using the dialysate target temperature record data, the insulation chamber initial temperature record data, and the environmental monitoring temperature record data as the input data, an associated heating power configuration model is constructed to construct a data set.

[0047] Step S1222: Divide the associated heating power configuration model construction data set into k equal parts, and perform k extractions with replacement to obtain a first heating power configuration channel construction data set.

[0048] Step S1223: constructing a data set according to the first heating power configuration channel, and training the first heating power configuration channel.

[0049] Specifically, constructing a dataset for the associated heating power configuration model is the basic work. Using the heating power identification data as the supervision data, it provides a clear target output value for model training, representing the accurate heating power that should be achieved under specific dialysate target temperature, insulation chamber initial temperature, and environmental monitoring temperature conditions. The dialysate target temperature recording data, insulation chamber initial temperature recording data, and environmental monitoring temperature recording data together constitute the input data, which comprehensively reflect the various key factors in the heating process. Each set of corresponding heating power identification data is combined with the dialysate target temperature, insulation chamber initial temperature, and environmental monitoring temperature recording data to form a large number of data samples, thereby constructing a rich dataset for the associated heating power configuration model.

[0050] In order to conduct effective model training, the constructed data set needs to be specially processed. The associated heating power configuration model construction data set is divided into k parts. This division method helps to use cross-validation and other techniques to evaluate and optimize model performance. Then perform k times of replacement extraction operations. Each extraction will randomly select samples from the entire data set, and each sample has the possibility of being selected repeatedly. In this way, the first heating power configuration channel construction data set is obtained. This data set not only retains the distribution characteristics of the original data set, but also introduces a certain diversity through random sampling, making the training data more representative and enabling the model to better learn the potential patterns in the data.

[0051] The first heating power configuration channel is constructed using the first heating power configuration channel to construct a data set to train the first heating power configuration channel, and a neural network structure including an input layer, a hidden layer, and an output layer is constructed. The number of neurons in the input layer corresponds to the number of features of the input data, that is, the three feature values ​​of the dialysate target temperature, the initial temperature of the insulation chamber, and the environmental monitoring temperature are received. The hidden layer uses multiple neurons to realize complex nonlinear transformation of the input data and mine the deep relationship between the data. The output layer outputs the predicted heating power value. During the training process, the input data in the data set constructed by the first heating power configuration channel is input into the input layer of the neural network, and after being processed by the hidden layer, the predicted heating power value is obtained in the output layer. Then the predicted value is compared with the corresponding heating power identification data (true value) in the data set, and the error (such as mean square error) is calculated. According to the error size, the back propagation algorithm is used to reversely adjust the connection weights and bias parameters between the neurons in the hidden layer and the input layer from the output layer, so that the model can gradually reduce the error in subsequent predictions and continuously improve the accuracy of the prediction. Through multiple iterative training on a large number of samples in the data set, the first heating power configuration channel gradually learns the complex mapping relationship between the dialysate target temperature, the initial temperature of the insulation chamber, the environmental monitoring temperature and the heating power, so that the heating power can be predicted more accurately based on the new input temperature data.

[0052] In a possible implementation, step S200 further includes:

[0053] Step S210: obtaining the preset time zone heating control record data of the heating component, wherein the preset time zone is the time zone distributed by the preset time step forward from the current moment.

[0054] Step S220: extracting target heating power record data and actual heating power record data according to the preset time zone heating control record data.

[0055] Step S230: Calculate a deviation vector set between the target heating power record data and the actual heating power record data.

[0056] Step S240: performing frequency fitting on the deviation vector set to obtain the heating power error information.

[0057] Specifically, according to the set time interval, the working data of the heating component is continuously collected, including but not limited to key information such as heating power output value, heating time, and working temperature. After the collection, these data are promptly stored in a special database, and are arranged and archived in chronological order to form a complete heating control record data set. When it is necessary to obtain the heating control record data of the preset time zone, the record data in the corresponding time period is accurately located and extracted from the database according to the current time and the preset time step. For example, if the preset time step is 1 hour and the current time is 10 o'clock, all heating control record data in the preset time zone from 9 o'clock to 10 o'clock will be extracted. These data record in detail the working process and state changes of the heating component during this period, providing a rich data basis for the subsequent analysis of the working stability and power output accuracy of the heating component, and are the key basis for accurately evaluating the performance of the heating component, discovering potential problems, and conducting heating power deviation analysis.

[0058] The heating control record data of the preset time zone is carefully parsed. These record data are stored in a specific data format, which contains various working parameters and status information of the heating component at each moment in the time period, and can quickly locate the record fields related to the heating power. For the target heating power record data, it is usually associated with a specific control instruction or set parameter in the record. At each time node in the preset time zone, the expected heating power value calculated according to the pre-set heating strategy or the dialysate temperature requirement is accurately extracted. These target heating power values ​​reflect the power that the heating component should output in order to achieve the expected dialysate heating effect under ideal conditions. The actual heating power record data is directly obtained from the real-time power monitoring feedback of the heating component during operation. At each moment in the preset time zone, the actual power value output by the heating component is accurately recorded and stored in the heating control record data, and these actual power values ​​are extracted one by one through specific data reading instructions. The extracted target heating power record data and the actual heating power record data will correspond one by one in chronological order to form two complete data sequences. These two sets of data sequences provide the necessary data basis for the subsequent calculation of the deviation vector set between the two, so that the difference between the power output of the heating component and the expected target within the preset time zone can be accurately analyzed, thereby providing a key basis for evaluating the working performance of the heating component and further error compensation.

[0059] Arrange the target heating power record data and the actual heating power record data one by one in chronological order. At each corresponding time point, subtract the actual heating power value from the target heating power value to obtain the power deviation value at that moment. For example, at a certain moment, the target heating power is 1000 watts and the actual heating power is 980 watts, then the deviation value at that moment is 20 watts. Then, combine the deviation values ​​calculated at each time point in chronological order to form a vector sequence, which is the deviation vector set. Each vector element in this set represents the degree and direction of the difference between the power output of the heating component and the expected target at a specific moment (a positive deviation indicates that the actual power is lower than the target power, and a negative deviation indicates that the actual power is higher than the target power). The deviation vector set comprehensively and meticulously depicts the dynamic changes in the power deviation of the heating component within the preset time zone. By analyzing this set, we can intuitively understand the size of the power deviation at different time points, the fluctuation trend, and whether there is periodicity, etc., which provides a rich and accurate data basis for subsequent frequency fitting and extraction of heating power error information, and helps to deeply understand the working performance of the heating component, thereby providing a strong basis for taking targeted error compensation measures and ensuring the accuracy and stability of the peritoneal dialysis fluid heating process.

[0060] Frequency fitting of the deviation vector set is the key to obtaining accurate heating power error information. First, Fourier transform is introduced, which can convert the complex deviation vector set from the time domain to the frequency domain. In the frequency domain, the power deviation signal strength corresponding to different frequency components can be clearly seen. Then, by analyzing the spectrum in the frequency domain, the main frequency components and their proportions are determined. Those high-frequency components may reflect the power deviation caused by small environmental fluctuations or instantaneous jitter of the equipment in a short period of time, while low-frequency components are often associated with long-term and relatively stable system error factors, such as the performance attenuation trend of the heating component. According to the characteristics of these frequency components, the average deviation value is calculated, which comprehensively reflects the overall deviation direction and size; then the standard deviation of the deviation is calculated to measure the degree of dispersion of the deviation and understand the stability of the power deviation. By integrating these average deviation values, standard deviations and related information of different frequency components, the heating power error information is obtained. This information accurately reveals the inherent law of the power deviation of the heating component in the preset time zone, providing solid data support for the subsequent error compensation strategy formulation, ensuring that the peritoneal dialysis fluid can reach the ideal temperature under stable and accurate heating power.

[0061] In a possible implementation, step S240 further includes:

[0062] Step S241: traverse the deviation vector set to perform distribution density evaluation to obtain a deviation vector distribution density set.

[0063] Step S242: Calculate the ratio of the deviation vector distribution density set to the sum of the deviation vector distribution densities, and set it as the distribution density weight set.

[0064] Step S243: performing weighted mean analysis on the deviation vector set according to the distribution density weight set to obtain the heating power error information.

[0065] Specifically, traversing the deviation vector set to evaluate the distribution density is the key starting point for exploring the inherent laws of power deviation. First, read each deviation vector element in the deviation vector set in order. For each element, use a professional statistical analysis algorithm to consider its position in the entire set, the difference between it and its adjacent elements, and other factors. By carefully analyzing the distribution of these deviation vectors on the numerical axis, the number of deviation vectors in different intervals is counted. For example, intervals are defined with a certain range of power deviation values, such as -10 watts to 0 watts, 0 watts to 10 watts, etc., and the proportion of the number of deviation vectors falling into each interval to the total number of vectors is calculated. In this way, the proportion information corresponding to each interval is summarized, and finally a deviation vector distribution density set is formed.

[0066] After obtaining the deviation vector distribution density set, the calculation process is immediately started. First, each element in the set is accurately located. These elements represent the distribution density of the deviation vectors in different intervals. Next, the sum of all elements is calculated, that is, the sum of the deviation vector distribution density, which reflects the overall distribution density scale. Then, for each element in the deviation vector distribution density set, it is divided by the sum just calculated. For example, if the deviation vector distribution density value of a certain interval is 0.2 and the sum is 1, then the ratio corresponding to the interval is 0.2. By performing such operations on all elements in the set, the series of ratios obtained together constitute the distribution density weight set. Each weight value in this set accurately corresponds to the relative importance of the deviation vector of the corresponding interval in the overall distribution. The larger the weight, the more significant the influence of the deviation vector of the interval on the overall error characteristics, which provides a key basis for subsequent weighted analysis based on weights.

[0067] The key finishing step of the entire error analysis process is to perform weighted mean analysis on the deviation vector set based on the distribution density weight set to obtain the heating power error information. After obtaining the distribution density weight set, it is quickly put into operation and closely associated with the deviation vector set. For each deviation vector in the deviation vector set, find the corresponding distribution density weight value, and then multiply the deviation vector by the weight value to achieve weighted processing of each deviation vector. For example, if a deviation vector is 5 watts and its corresponding weight value is 0.3, then the weighted value is 1.5 watts. After completing the weighting of all deviation vectors, these weighted values ​​are accumulated and summed. Then, the accumulated sum is divided by the sum of the weight values ​​to eliminate the cardinality difference caused by the weight distribution, and the result is the average deviation value after weighted correction. This average deviation value accurately reflects the central trend after considering the influence of the distribution density of each deviation vector, and ultimately constitutes the complete heating power error information, presenting the overall picture of the power deviation of the heating component during operation in an all-round and high-precision manner, laying a solid foundation for the subsequent targeted formulation of error compensation strategies to ensure the stability and accuracy of the peritoneal dialysis fluid heating process.

[0068] In a possible implementation, step S241 further includes:

[0069] Step S2411: extracting a first deviation vector according to the deviation vector set.

[0070] Step S2412: Obtain q deviation vectors adjacent to the first deviation vector.

[0071] Step S2413: Calculate the inverse of the deviation mean between the q deviation vectors and the first deviation vector, set it as the first deviation vector distribution density, and add it to the deviation vector distribution density set.

[0072] Specifically, first, the first deviation vector is extracted from the existing deviation vector set according to a specific selection rule. This selection is not random, but is determined in a predetermined order, such as from the starting position of the set or according to the order corresponding to a key time node, to ensure that the selected first deviation vector is representative and can serve as a benchmark for subsequent analysis.

[0073] Taking the first deviation vector as the core, we expand outward to find q adjacent deviation vectors. The adjacent ones here have a clear definition, which are several vectors that are closely adjacent to each other in the time series. Through precise positioning, these q deviation vectors are completely screened out. They are closely related to the first deviation vector and together reflect the changing trend of the deviation vector in the local area.

[0074] Perform difference operations on these q deviation vectors one by one with the first deviation vector to obtain a series of differences, and then add these differences to find the average value. The deviation mean calculated in this way accurately reflects the average deviation state of the surrounding deviation vectors relative to the first deviation vector. Next, take the reciprocal of this deviation mean, and the value obtained is the first deviation vector distribution density. This density value is of great significance. Its size intuitively reflects the density of the deviation vectors around the first deviation vector. The larger the value, the sparser the surrounding deviation vectors, and vice versa. Finally, the system accurately adds the newly calculated first deviation vector distribution density value to the deviation vector distribution density set, so that the content of the set can be enriched, and then it can provide more accurate data support for the subsequent in-depth exploration of the heating power error from the microscopic detail level, making the entire error analysis more rigorous and scientific.

[0075] In a possible implementation, step S700 further includes:

[0076] Step S710: Announce the dialysate temperature information and dialysate weight information through the voice announcer.

[0077] Specifically, the peritoneal dialysis fluid incubator contains a practical functional component called a voice announcer. When the device is in operation, the voice announcer can play a role in real time. On the one hand, it will accurately broadcast the dialysate temperature information and convey the current real-time temperature of the dialysate in the incubator in a clear and easy-to-understand voice form. For medical staff, there is no need to frequently check the display screen. When they are busy with other medical operations, they can instantly know whether the dialysate temperature is in the appropriate treatment range by hearing alone, which greatly improves work efficiency; for patients or their families, when they operate by themselves, they can also intuitively understand the temperature situation to ensure the safety of the dialysis process. On the other hand, the voice announcer is also responsible for broadcasting the dialysate weight information. Whether it is the weight of the new dialysate injected into the incubator or the remaining dialysate weight that changes with the dialysis process during use, it can be accurately informed by voice. In this way, users can better control the amount of dialysate used, ensure that each dialysis treatment can strictly follow the doctor's instructions, use the dialysate accurately, avoid treatment problems caused by improper dosage, and comprehensively improve the convenience and reliability of peritoneal dialysis treatment.

[0078] In a possible implementation, step S700 further includes:

[0079] Step S720: Observe the heat preservation chamber through the font observation window, wherein the font observation window has a preset font scale.

[0080] Specifically, the font observation window is cleverly integrated into the structure of the peritoneal dialysis fluid incubator. This observation window is usually made of a highly transparent material to ensure that the user can obtain a clear and unobstructed view. When the user approaches the incubator, the key situation in the incubator cavity can be directly observed through the font observation window. On the one hand, the liquid level of the dialysate can be viewed in real time, and it can be clearly distinguished whether the dialysate is in a sufficient state, about to be exhausted, or at an intermediate level during normal use, so as to prepare in advance and avoid interrupting the treatment process due to insufficient dialysate. On the other hand, the state of the dialysate can be intuitively monitored, such as whether there is turbidity, precipitation or abnormal color changes. These visual information can provide early warnings to medical staff or users in the first place, indicating possible dialysate quality problems. Moreover, in a dimly lit environment, the carefully designed auxiliary lighting device around the font observation window will automatically light up, and the soft light will illuminate the interior of the incubator cavity, further ensuring the accuracy and convenience of observation, allowing users to know the situation in the incubator cavity through this window anytime and anywhere, and escorting the smooth implementation of peritoneal dialysis treatment.

[0081] The preset font scales of the font observation window play a vital role. These preset font scales are carefully printed on the inner surface of the observation window, using special materials that are wear-resistant, corrosion-resistant and easy to identify, ensuring good visibility during long-term use and in the complex environment inside the incubator. The scales are arranged in an orderly manner along the height direction of the observation window, accurately corresponding to the different liquid level heights in the insulation chamber. Starting from the bottom, they are marked gradually upward in equal intervals. For example, every 100 ml has a striking scale mark, and is matched with corresponding digital fonts, so that users can see the specific volume value of the dialysate at a glance. When light shines into the insulation chamber, whether it is natural light or light emitted by auxiliary lighting devices, these scales will reflect clear light and shadow, forming a sharp contrast with the dialysate, and the dialysate level information can be quickly and accurately read through the scale, providing an efficient and reliable visual basis for dialysate monitoring during peritoneal dialysis treatment.

[0082] Embodiment 2, based on the same inventive concept as the peritoneal dialysis fluid incubator control method in the aforementioned embodiment, the present application provides a peritoneal dialysis fluid incubator, and the incubator and method embodiments in the embodiments of the present application are based on the same inventive concept. The incubator comprises:

[0083] Insulation chamber.

[0084] A heating component is disposed inside the heat preservation cavity.

[0085] A weighing component is disposed on the bottom surface of the heat preservation chamber.

[0086] A font observation window is disposed on the side of the heat preservation chamber and is made of a transparent material and has a preset font scale.

[0087] Voice announcer.

[0088] Specifically, the peritoneal dialysis fluid incubator is specially designed and developed based on the strict requirements of peritoneal dialysis treatment for precise temperature control and real-time status monitoring. In terms of structure, the insulation cavity, as the core storage area, uses high-performance insulation materials with low thermal conductivity. Through the optimized multi-layer composite structure design, the heat conduction rate is minimized to build a stable internal thermal environment, ensuring that heat loss is controlled within a very small range, providing a reliable warming foundation for the storage and heating process of peritoneal dialysis fluid.

[0089] The heating component is placed inside the insulation chamber, and uses heating elements based on advanced thermistor principles or thermocouple temperature control technology. Such elements have a millisecond-level thermal response speed and can be seamlessly connected to the built-in intelligent control system. The control system instantly issues precise power adjustment instructions to the heating component based on the pre-set temperature curve and multiple parameters such as the ambient temperature and current dialysate temperature collected in real time, ensuring that the appropriate heating power can be accurately matched in different stages such as dialysate preheating, maintaining constant temperature, and responding to sudden changes in ambient temperature, and strictly limiting the dialysate temperature to the ideal range specified for clinical treatment.

[0090] The weighing component is integrated on the bottom of the insulation chamber, using a high-precision piezoresistive pressure sensor or piezoelectric weighing sensor, which has ultra-high sensitivity and extremely small measurement error, and can capture the dynamic changes of dialysate weight in real time at a sampling frequency of microseconds. The weight data collected by the sensor is amplified, filtered and pre-processed by the built-in signal conditioning circuit, and then transmitted to the microprocessor for analysis and quantification, and finally accurately outputs the weight value that can be directly read by medical staff. Whether it is at the initial stage of the initial placement of dialysate or in the long-term dialysis treatment process to monitor the liquid consumption in real time, it can provide reliable data support for medical staff, so that they can accurately control the real-time usage of dialysate.

[0091] The font observation window is set on the side of the insulation cavity. It uses high-strength transparent materials with an optical transparency of more than 95%, such as special acrylic or optical glass. It can not only withstand certain temperature changes and chemical corrosion, but also from the perspective of optical design, its surface has been specially treated with anti-glare and anti-reflection to ensure that medical staff can clearly and intuitively view the physical properties of the dialysate in the insulation cavity through the observation window, including key information such as whether there is particle precipitation and abnormal color changes. At the same time, the preset font scale precisely printed on the observation window is designed based on ergonomic principles and common liquid level observation requirements. The scale accuracy can reach millimeter level. Combined with the principle of geometric optics, medical staff can easily and accurately read the liquid level of the dialysate, and verify and complement the data obtained by the weighing component, further improving the comprehensive grasp of the real-time status information of the dialysate.

[0092] In addition, the voice announcer is equipped with an advanced speech synthesis chip and a high-fidelity audio amplifier circuit, which can quickly convert the dialysate temperature and weight data pushed by the control system in real time into clear, smooth, and volume-adjustable voice signals for broadcasting. The voice announcer transmits key information to medical staff in a timely and accurate manner through the auditory channel, ensuring that they can grasp the core parameters of the dialysate at the first time under any circumstances, thereby improving the execution efficiency and quality control level of the entire peritoneal dialysis treatment process.

[0093] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0094] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0095] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A peritoneal dialysis fluid incubator control method, characterized in that: Applied to a peritoneal dialysis fluid incubator, the peritoneal dialysis fluid incubator comprises an incubation chamber, a heating component, and a weighing component, the weighing component is disposed on the bottom surface of the incubation chamber, the heating component is disposed inside the incubation chamber, and the method comprises: Obtaining dialysate target heating power; Perform heating power deviation analysis on the heating component to obtain heating power error information; Perform weighing deviation analysis on weighing components to obtain weighing error information; Obtaining dialysate weighing information of a weighing component; performing error compensation on the dialysate weighing information according to the weighing error information to obtain calibrated dialysate weighing information; Performing error compensation on the dialysate target heating power according to the heating power error information to obtain a calibrated heating power; The peritoneal dialysis fluid incubator is controlled according to the calibration dialysate weighing information and the calibration heating power.

2. The method according to claim 1, characterized in that Obtain the dialysate target heating power, including: Obtain the dialysate target temperature, the initial temperature of the insulation chamber, and the environmental monitoring temperature; The dialysate target temperature, the insulation chamber initial temperature and the environmental monitoring temperature are processed through the associated heating power configuration model of the heating component, and the dialysate target heating power is output.

3. The method according to claim 2, characterized in that The dialysate target temperature, the initial temperature of the heat preservation chamber and the environmental monitoring temperature are processed by the associated heating power configuration model of the heating component to output the dialysate target heating power, which includes: Collecting historical heating record data of the heating component, wherein the historical heating record data includes dialysate target temperature record data, insulation chamber initial temperature record data, environmental monitoring temperature record data and heating power identification data; Using the heating power identification data as supervision data, and using the dialysate target temperature record data, the insulation chamber initial temperature record data, and the environment monitoring temperature record data as input data, training a first heating power configuration channel; Until the heating power identification data is used as the supervision data, the dialysate target temperature record data, the insulation chamber initial temperature record data, and the environment monitoring temperature record data are used as the input data, and the Nth heating power configuration channel is trained, where N is an integer, and N≥5; Perform mean full connection on the first heating power configuration channel to the Nth heating power configuration channel to obtain the associated heating power configuration model.

4. The method according to claim 3, characterized in that Taking the heating power identification data as supervision data, taking the dialysate target temperature record data, the insulation chamber initial temperature record data, and the environment monitoring temperature record data as input data, training the first heating power configuration channel includes: Taking the heating power identification data as the supervision data, and taking the dialysate target temperature record data, the insulation chamber initial temperature record data, and the environment monitoring temperature record data as the input data, a correlation heating power configuration model is constructed to construct a data set; Divide the associated heating power configuration model construction data set into k equal parts, and perform k extractions with replacement to obtain a first heating power configuration channel construction data set; A data set is constructed according to the first heating power configuration channel, and the first heating power configuration channel is trained.

5. The method according to claim 1, characterized in that Perform heating power deviation analysis on the heating component to obtain heating power error information, including: Obtaining preset time zone heating control record data of the heating component, wherein the preset time zone is the time zone distributed by the preset time step forward from the current moment; Extracting target heating power record data and actual heating power record data according to the preset time zone heating control record data; Calculating a deviation vector set between the target heating power record data and the actual heating power record data; Frequency fitting is performed on the deviation vector set to obtain the heating power error information.

6. The method according to claim 5, characterized in that Performing frequency fitting on the deviation vector set to obtain the heating power error information includes: Traversing the deviation vector set to perform distribution density evaluation to obtain a deviation vector distribution density set; Calculate the ratio of the deviation vector distribution density set to the deviation vector distribution density sum value respectively, and set it as the distribution density weight set; According to the distribution density weight set, a weighted mean analysis is performed on the deviation vector set to obtain the heating power error information.

7. The method according to claim 6, characterized in that Traversing the deviation vector set to perform distribution density evaluation, and obtaining a deviation vector distribution density set, including: Extracting a first deviation vector according to the deviation vector set; Obtaining q deviation vectors adjacent to the first deviation vector; The inverse of the mean deviation between the q deviation vectors and the first deviation vector is calculated, set as the first deviation vector distribution density, and added to the deviation vector distribution density set.

8. The method according to claim 1, characterized in that The peritoneal dialysis fluid incubator also includes a voice announcer, including: broadcasting the dialysis fluid temperature information and the dialysis fluid weight information through the voice announcer.

9. The method according to claim 1, characterized in that The peritoneal dialysis fluid incubator further comprises a font observation window, comprising: observing the incubation cavity through the font observation window, and the font observation window has a preset font scale.

10. A peritoneal dialysis fluid incubator, characterized in that: A method for controlling a peritoneal dialysis fluid incubator according to any one of claims 1 to 8, comprising: Insulation chamber; A heating component, the heating component is disposed inside the heat preservation cavity; A weighing assembly, the weighing assembly being disposed on the bottom surface of the heat preservation chamber; A font observation window, which is disposed on the side of the heat preservation chamber and is made of a transparent material and has a preset font scale; Voice announcer.

Images