Centrifugal machine temperature control method and centrifugal machine

Abstract

The invention relates to the technical field of medical equipment, in particular to a centrifugal machine temperature control method and a centrifugal machine. The temperature value of the centrifugal machine at the current time node is obtained, the temperature value of the next time node is predicted according to the deviation state of the temperature value at the current time node, and the temperature adjusting range is determined according to the deviation between the predicted temperature value and the standard temperature value. The temperature control device of the centrifugal machine is adjusted through the PID controller based on the dynamic adjustment parameters, so that the working environment temperature of the centrifugal machine meets the target requirement. According to the scheme provided by the embodiment of the invention, the working environment of the centrifugal machine and the environment change in the predicted working period can be obtained, and dynamic and accurate temperature adjustment is realized based on the environment change, so that the influence and damage of the temperature change on the centrifugal effect in the use process of the centrifugal machine are reduced.

Description

Technical Field

[0001] The present application relates to the technical field of medical equipment, and specifically to a centrifuge temperature control method and a centrifuge. Background Art

[0002] Desktop medical centrifuges are usually used to separate blood components, such as separating plasma and red blood cells, or extracting biological molecules such as DNA and RNA. When the centrifuge performs high-speed centrifugal motion, friction heat is generated, causing the temperature in the separation chamber to rise. If the temperature exceeds the sample tolerance range, there is a risk of sample damage. For example, for proteins, the abnormal increase in temperature will cause enzymes and antibodies to be inactivated, thereby affecting the accuracy of detection; deposited cells will produce hemolysis due to the increase in temperature, thereby destroying blood components, such as unsuccessful separation of red blood cells; DNA / RNA is prone to breakage at high temperatures, thus affecting the extraction quality.

[0003] At present, most medical centrifuges are equipped with temperature control devices to control the temperature of the centrifugal environment. However, the temperature control system in the prior art has a slow response speed to temperature changes, and the temperature change in the environment is not a linear change. It is difficult for the existing temperature control system to quickly reach the set temperature after startup, and the existing temperature control system cannot adapt to load changes and hot melting differences of different samples. Usually, only one universal temperature control logic is used, which is difficult to meet the temperature changes of multiple samples and multiple speeds, and cannot achieve precise control of temperature. Summary of the invention

[0004] In order to solve the technical problems existing in the prior art, the embodiments of the present application provide a centrifuge temperature control method and a centrifuge, which obtains the working environment of the centrifuge and predicts the environmental changes within the working cycle, and realizes dynamic and accurate temperature adjustment based on such environmental changes, thereby reducing the influence and damage of temperature changes on the centrifugal effect during the use of the centrifuge.

[0005] In order to achieve the above purpose, the technical solution adopted in the embodiment of the present application is as follows: In a first aspect, a centrifuge temperature control method is provided, the method comprising: obtaining a predicted centrifugal ambient temperature of the centrifuge at a next time node, and determining the degree of deviation from a standard centrifugal ambient temperature; the predicted centrifugal ambient temperature is a predicted value of the centrifugal ambient temperature corresponding to the next time node; when the degree of deviation exceeds a predetermined range, the deviation is treated as an error and processed by a PID controller with dynamically adjusted parameters to generate a control signal, and the control signal acts on a temperature control device.

[0006] In some specific implementations, the method further includes: obtaining a real-time centrifugal ambient temperature at a current time point of the centrifuge, and obtaining a predicted centrifugal ambient temperature based on a degree of deviation between the real-time centrifugal ambient temperature and a standard centrifugal ambient temperature.

[0007] In some specific implementations, the standard centrifugal environment temperature at the current time node and the next time node is determined based on the time node and the temperature rise curve.

[0008] In some specific implementations, when a first temperature difference between the real-time centrifugal environment temperature and the standard centrifugal environment temperature exceeds a temperature threshold, a predicted centrifugal environment temperature of the centrifuge at a next time node is obtained.

[0009] In some specific implementations, when the degree of deviation exceeds a predetermined range, the deviation is taken as an error and processed through a PID controller with dynamic parameter adjustment to generate a control signal, including: when a second temperature difference between the predicted centrifugal ambient temperature and the standard centrifugal ambient temperature corresponding to the next time node exceeds a temperature threshold, the second temperature difference is taken as an error and processed through a PID controller with dynamic parameter adjustment to generate a control signal.

[0010] In some specific implementations, obtaining the predicted centrifugal ambient temperature at the next time node includes: obtaining centrifugal ambient temperature data, centrifuge speed data and centrifuge motor temperature data of multiple previous time nodes, and processing the centrifugal ambient temperature data, centrifuge speed data and centrifuge motor temperature data by encoding and decoding based on a temperature prediction model to obtain the predicted centrifugal ambient temperature at the next time node.

[0011] In some specific implementations, the method also includes: dividing the previous multiple time nodes in time order to obtain a first sequence group and a second sequence group, each sequence group containing centrifuge environment temperature data, centrifuge speed data and centrifuge motor temperature data corresponding to at least one time node; encoding and decoding the first sequence group and the second sequence group based on the self-attention mechanism respectively to obtain the predicted centrifuge environment temperature of the next time node.

[0012] In some specific implementations, the method also includes: obtaining a centrifugal ambient temperature memory information matrix through encoding processing, obtaining a centrifugal ambient temperature change sequence through decoding processing, performing attention calculation on the centrifugal ambient temperature memory information matrix and the centrifugal ambient temperature change sequence to obtain a predicted centrifugal ambient temperature at the next time node.

[0013] In some specific implementations, the dynamic adjustment of the parameters generates an initial control quantity through a PID controller, and determines the control performance based on the initial control quantity, and optimizes the parameters of the PID controller until the control performance is maximized to determine the target parameters of the PID controller.

[0014] In a second aspect, a centrifuge is provided, comprising: a centrifugal motor, a centrifugal chamber, a temperature control device, a sensor assembly and a processing device; the sensor assembly comprises a first temperature sensor and a second temperature sensor, the first temperature sensor is used to obtain the centrifugal motor temperature of the centrifugal motor, and the second temperature sensor is used to obtain the centrifugal environment temperature in the centrifugal chamber; the processing device is used to execute the centrifuge temperature control method described in any of the above items, and send a control signal to the temperature control device, the processing device comprises: a data processing module, used to obtain the predicted centrifugal environment temperature of the centrifuge at the next time node, and determine the degree of deviation from the standard centrifugal environment temperature; a control module, used to, when the degree of deviation exceeds a predetermined range, treat the deviation as an error and generate a control signal through a PID controller with dynamic parameter adjustment, and the control signal acts on the temperature control device.

[0015] In the technical solution provided by the embodiment of the present application, the temperature value of the current time node of the centrifuge is obtained and the temperature value of the next time node is predicted according to the deviation state of the current node temperature value, and the range of temperature adjustment is determined according to the deviation between the predicted temperature value and the standard temperature value, and the temperature control device of the centrifuge is adjusted by a PID controller based on dynamic adjustment parameters, so that the working environment temperature of the centrifuge meets the target requirements. The solution provided by the embodiment of the present application can obtain the working environment of the centrifuge and predict the environmental changes within the working cycle, and realize dynamic and accurate temperature adjustment based on such environmental changes, thereby reducing the influence and damage of temperature changes on the centrifugal effect during the use of the centrifuge. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] The methods, systems and / or programs in the accompanying drawings will be further described according to exemplary embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These exemplary embodiments are non-limiting exemplary embodiments, wherein example numbers represent similar mechanisms in the various views of the accompanying drawings.

[0018] Figure 1It is a schematic diagram of the structure of a centrifuge provided in an embodiment of the present application.

[0019] Figure 2 It is a flow chart of the centrifuge temperature control method provided in the embodiment of the present application.

[0020] Figure 3 It is a schematic diagram of the structure of the processing device provided in an embodiment of the present application.

[0021] Figure 4 It is a schematic diagram of the terminal device structure provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to better understand the above technical scheme, the technical scheme of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical scheme of the present application, rather than limitations on the technical scheme of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0023] In the following detailed description, numerous specific details are set forth by way of example in order to provide a comprehensive understanding of the relevant guidance. However, it will be apparent to those skilled in the art that the present application may be practiced without these details. In other cases, well-known methods, procedures, systems, compositions and / or circuits have been described at a relatively high level, without detail, in order to avoid unnecessarily obscuring aspects of the present application.

[0024] Flowcharts are used in the present application to illustrate the execution process performed by the system according to the embodiment of the present application. It should be clearly understood that the execution process of the flowchart may not be performed in order. On the contrary, these execution processes may be performed in reverse order or simultaneously. In addition, at least one other execution process may be added to the flowchart. One or more execution processes may be deleted from the flowchart.

[0025] Before further describing the embodiments of the present invention in detail, the nouns and terms involved in the embodiments of the present invention are described. The nouns and terms involved in the embodiments of the present invention are subject to the following interpretations.

[0026] (1) In response to, it is used to indicate the conditions or states on which the executed operation depends. When the dependent conditions or states are met, one or more operations executed may be in real time or with a set delay. Unless otherwise specified, there is no restriction on the order in which the multiple operations executed are executed.

[0027] (2) Based on: used to indicate the conditions or states on which the executed operations depend. When the dependent conditions or states are met, one or more operations executed may be in real time or with a set delay. Unless otherwise specified, there is no restriction on the order in which the multiple operations executed are executed.

[0028] See also Figure 1 An embodiment of the present application provides a centrifuge 10, including a centrifuge body 11 and a processing device 12, wherein the centrifuge body drives objects to rotate, especially non-solid objects, through rotation to achieve separation between substances, and is commonly used in medical detection scenarios, including but not limited to plasma separation, tissue fluid separation and other scenarios.

[0029] The structure of the centrifuge body mainly includes a centrifugal motor for providing rotational power and a centrifugal chamber for providing a centrifugal space for the object to be centrifuged. The structure of the centrifugal motor and the centrifugal chamber is a non-connected structure. It also includes a temperature control device 13 for controlling the temperature in the centrifugal chamber so that the centrifugal environment temperature meets the temperature requirements of the object to be centrifuged; and a sensor component 14 for acquiring specific data.

[0030] In this embodiment, the sensor assembly is a temperature sensor for obtaining specific temperature data. Further, the sensor assembly is composed of two independent temperature sensors, namely, a first temperature sensor placed at the centrifugal motor and a second temperature sensor placed in the centrifugal chamber, wherein the first temperature sensor is used to obtain the first temperature of the centrifugal motor, and the second temperature sensor is used to obtain the real-time centrifugal environment temperature in the centrifugal chamber.

[0031] In actual use scenarios, different objects to be centrifuged have different temperature sensitivities according to their own characteristics, that is, the temperature in the centrifugal chamber of the centrifuge should have different upper and lower temperature limits according to different objects to be centrifuged, especially biological objects such as blood and tissue fluid should have a strict upper temperature limit, so as to avoid the inactivation of the objects to be centrifuged and invalid samples. Therefore, a temperature control device is provided to adjust the temperature of the centrifugal chamber. Generally, in the prior art, the logic for temperature regulation is to obtain the ambient temperature of the unit time node in the centrifugal chamber through a second temperature sensor, and when the ambient temperature exceeds the warning value, the temperature is regulated by the temperature control device.

[0032] However, this control method cannot achieve precise control, because in actual scenarios, the temperature control device is difficult to quickly reach the set temperature after startup. In addition, the main reason for the temperature change in the centrifugal chamber is the heat generated by the motor and the heat generated by the rotational friction, and this heat change is not a linear change. If the traditional temperature control method is used, it is necessary to set a time point with a small interval to collect multiple data to avoid the problem of delayed processing time points caused by a long collection time interval. However, if a multi-node short time interval data collection strategy is adopted, the operating cost of the temperature control device will increase, and because the temperature control is difficult to quickly reach the set temperature after startup, the temperature control cannot achieve the corresponding effect within a time period. In addition, for the use scenario of this centrifuge, the heat melting difference for different medical samples is large, and the heat dissipation generated by the different speeds of the centrifugal operation of the unused samples is also different. Therefore, the centrifuge in the prior art cannot achieve the effect of fine temperature control for different types of samples.

[0033] In order to solve this problem, a processing device is also provided in the centrifuge in this embodiment, and a temperature control method is configured in the processing device to generate a control signal acting on the temperature control device so that the temperature control device can accurately control the ambient temperature in the centrifugal chamber. Among them, the processing device in this embodiment can be a module set in the central control end, or a module set in the temperature control device, and its physical structure and hardware structure are not described in detail in this embodiment.

[0034] For details, please refer to the temperature control method configured in the processing device. Figure 2 , including the following steps: Step S21. Obtain the predicted centrifugal environment temperature of the centrifuge at the next time node, and determine the degree of deviation from the standard centrifugal environment temperature.

[0035] In this embodiment, the prerequisite for temperature adjustment in this process is that the predicted ambient temperature at the next time node needs to be compared with the standard centrifugal ambient temperature. When a deviation occurs and the degree of deviation does not meet the requirements, temperature adjustment is performed. However, it is worth noting that the predicted ambient temperature for the next time node is not determined every time the temperature is collected. In this embodiment, the collection is performed only when there is a deviation between the real-time centrifugal ambient temperature corresponding to the current time node and the standard centrifugal ambient temperature, and the degree of deviation does not meet the requirements.

[0036] Therefore, in this embodiment, according to the execution logic, the real-time centrifugal environment temperature at the current time node should be obtained first, and whether to obtain the predicted centrifugal environment temperature should be determined according to the deviation between the real-time centrifugal environment temperature and the standard centrifugal environment temperature.

[0037] Specifically, in the present embodiment, the standard centrifugal environment temperature at the current time node and the next time node is determined by a specific time node and a heating curve. Therefore, in the present embodiment, a heating curve is also provided in the processing device, wherein the heating curve is a curve of the temperature in the centrifugal chamber changing over time when the object to be centrifuged performs a centrifugal operation by itself without the influence of an external heat source, and it can be understood that the heating curve is the ideal temperature change of the object to be centrifuged. This heating curve is obtained by constructing a simulation model and performing multiple simulation experiments, and can also be obtained by fitting after multiple actual measurements away from a heat source under stable room temperature conditions. In the present embodiment, this heating curve is obtained by adopting a fitting method.

[0038] Furthermore, it is worth noting that the temperature rise curves for different centrifugal objects are also different. Therefore, in the present embodiment, the corresponding temperature rise curve can be obtained by selecting the object to be centrifuged during the actual centrifugal operation.

[0039] In this embodiment, the ideal heating process of the object in a centrifugal environment can be fully reflected by constructing a heating curve, and using the heating curve as a baseline for temperature control can better meet the changes in specific centrifugal operations, providing a more accurate reference object for temperature control.

[0040] Wherein, in the present embodiment, because different objects to be centrifuged have different centrifugal operation times, the setting of their time nodes is also different when performing temperature acquisition. In the present embodiment, the setting for the time node is determined according to the change of the tangent slope of the heating curve. It is well understood that the slope of the tangent of the curve can express the degree of temperature change in the temperature change, and the heating process can be better judged by determining multiple change inflection points in the heating curve and using the inflection point with a larger rate of change as the time point for temperature acquisition. Wherein, generally 8 are selected for the selection of the heating inflection point, and the setting of multiple time nodes should involve the overall centrifugal process. In this way, the processing cost caused by frequent temperature acquisition is reduced, and the problem of missing acquisition caused by reducing the sampling point can be guaranteed.

[0041] In this embodiment, the corresponding temperature rise curve and the corresponding time node are determined based on the object to be centrifuged, and the real-time centrifugal environment temperature of the corresponding time node is collected during the centrifugation process. The degree of deviation is judged based on the collected real-time centrifugal environment temperature and the standard centrifugal environment temperature, that is, the first temperature difference between the real-time centrifugal environment temperature and the standard centrifugal environment temperature is determined, and it is determined whether the first temperature difference exceeds the temperature threshold. Among them, the temperature threshold refers to the range of allowable deviation, not the range of temperature.

[0042] It is noteworthy that the setting of the temperature threshold in the present embodiment is not a uniform value, and the setting of this temperature threshold should be set according to the temperature value corresponding to the specific time node, for example, in the early stage of centrifugal treatment, the range of the temperature threshold is larger than that of the later stage of centrifugal treatment in order to reduce the control cost, and the range of the threshold for different centrifugal objects is also different. Regarding this process, the corresponding temperature threshold is first called based on the current time node, and then it is determined whether the first temperature difference between the real-time centrifugal environment temperature and the standard centrifugal environment temperature exceeds the temperature threshold. If it does not exceed, it means that the current temperature change is in the allowed range, and if it exceeds, it means that the current temperature change is in the unallowed range.

[0043] In the prior art, the temperature threshold is exceeded by directly controlling the temperature. However, for a temperature system, especially a non-ideal temperature change system, occasional temperature changes do not mean an overall temperature change trend. In order to reduce the frequency and cost of temperature control, in this embodiment, the centrifugal environment temperature at the next time point is predicted to determine whether the current temperature environment should be adjusted.

[0044] Among them, the temperature prediction value for the next time node is obtained by using a temperature prediction model in this embodiment. Because the interference sources of the temperature change of the centrifugal environment are mainly the rotation speed of the centrifuge and the heat dissipation temperature of the centrifugal motor, the temperature prediction model in this embodiment obtains the predicted temperature value of the next time node by collecting the above data and reasoning based on machine learning.

[0045] Furthermore, in order to better improve the accuracy of the temperature prediction model, the above data should be continuous data during the centrifugal operation, because continuous data can reflect the relationship between temperature and time. Therefore, in this embodiment, the input data of the temperature prediction model should be the pre-order data including the current time node, that is, the centrifugal environment temperature data, centrifuge speed data and centrifugal motor temperature data corresponding to multiple time points are obtained, and the output result is the predicted value of the centrifugal environment temperature at the next time node.

[0046] Among them, the temperature prediction model in this embodiment adopts a machine learning model, specifically a Transformer model, including an embedding layer, an encoder, a decoder and an output layer.

[0047] Specifically, the embedding layer is used to extract the time series, i.e., the time nodes, and the corresponding data. The above data is converted into a data embedding matrix, and the data embedding matrix is ​​converted into a time series embedding matrix by extracting the time series information of the time nodes. Among them, the data conversion process maps the centrifuge ambient temperature data, centrifuge speed data, and centrifuge motor temperature data to a high-dimensional representation space by setting the corresponding learnable parameter weight matrix and bias, so that the long-distance dependency of the centrifuge ambient temperature sequence can be better captured in the subsequent processing process.

[0048] The data embedding matrix is ​​expressed based on the following formula: ;in , , They represent the high-dimensional representations corresponding to the centrifuge speed data, centrifugal environment temperature data, and centrifugal motor temperature data, respectively. , and They represent the input matrices corresponding to the centrifuge speed data, centrifugal environment temperature data and centrifugal motor temperature data respectively. , and Respectively represent the weight matrices corresponding to the centrifuge speed data, centrifugal environment temperature data and centrifugal motor temperature data, , and They respectively represent the offsets corresponding to the centrifuge speed data, the centrifugal environment temperature data and the centrifugal motor temperature data.

[0049] The output of the embedding layer is the sum of the high-dimensional matrix of the above output and the position coding matrix, which is finally expressed as an embedding matrix. The position coding matrix is ​​obtained by processing the time series information based on the trigonometric function position coding. The trigonometric function position coding process can be implemented using the solution in the prior art, which will not be described in detail in this embodiment.

[0050] In this embodiment, the encoder is stacked with multiple coding fast layers with the same structure and different parameters, and each coding block layer includes a multi-head self-attention layer, a feedforward neural network, a residual connection and a layer normalization structure. Among them, in the multi-head self-attention layer, by calculating the coefficient attention distribution of the embedding matrix, the change trend of the centrifugal environment temperature, the centrifuge speed and the centrifugal motor temperature in the high-dimensional features is captured to obtain the similarity between each high-dimensional feature vector; the feedforward neural network layer extracts the temperature memory information matrix of the centrifugal motor temperature in the similarity, so that the decoder can perform predictive calculations.

[0051] The decoder has a similar structure to the encoder, and is also composed of a plurality of decoder layers with the same structure and different parameters. The input of the decoder is an embedding matrix processed by the embedding layer, wherein the acquisition of the embedding matrix of the decoder is different from the acquisition of the embedding matrix of the encoder in that the embedding matrix of the encoder is obtained by embedding processing based on the first sequence group, and the embedding matrix of the decoder is obtained by embedding processing based on the second sequence group.

[0052] Among them, for the first sequence group and the second sequence group, the overall data sequence is divided according to the time nodes; that is, the previous multiple time nodes are divided in time order, which is equivalent to the sequence group corresponding to the embedded sequence input by the encoder as the first half of the time group, and the sequence group corresponding to the embedded sequence input by the decoder as the second half of the time group. The reason for this setting is that it can make the model understand the data changes corresponding to the time changes and better capture the relationship between time and changes.

[0053] Specifically, each decoder layer group is provided with a multi-head self-attention layer, an interactive attention layer, a feedforward neural network layer, a residual connection and a layer normalization structure. The sparse attention score of the embedding matrix is ​​calculated through the multi-head self-attention layer, and the obtained adjacent temperature trend is used as the query matrix of the interactive attention layer. The temperature memory information matrix output by the encoder layer is used as the key matrix and value matrix of the interactive attention layer. The interactive attention score is calculated to represent the similarity of the centrifugal ambient temperature change, and the centrifugal ambient temperature change trend is initially generated through the feedforward neural network layer.

[0054] For the output layer, a multi-layer perceptron structure is used. Each neuron in the first hidden layer shares the output of the decoder in the same layer. The output dimension of the second hidden layer is set to the number of prediction tasks so that the output of the decoder is gradually mapped to the target space, and the centrifugal ambient temperature is predicted at one time, thereby reducing the cumulative error of temperature prediction.

[0055] In this embodiment, the temperature prediction model of the above structure can determine the centrifugal environment temperature information at the next time point, and this information is used to determine whether the temperature in the current centrifugal environment has a deviation. Among them, the standard centrifugal environment temperature information is determined based on the time-temperature relationship of the heating curve.

[0056] Step S22. When the degree of deviation exceeds a predetermined range, the deviation is treated as an error and processed by a PID controller with dynamically adjusted parameters to generate a control signal, and the control signal acts on the temperature control device.

[0057] In this embodiment, step S21 can determine the predicted centrifugal ambient temperature at the next time point, and calculate the predicted centrifugal ambient temperature and the standard centrifugal ambient temperature to obtain a deviation value, and then compare the deviation value with the temperature threshold. When the deviation value exceeds the temperature threshold, it means that temperature adjustment is required.

[0058] Specifically, the temperature adjustment in this embodiment is implemented by using a PID controller, but it is different from the PID temperature control in the prior art. The PID controller in this embodiment determines the optimal PID control parameter value by dynamic adjustment.

[0059] Among them, the input for PID control is the deviation value determined in step S21, that is, the difference between the predicted centrifugal ambient temperature value and the standard centrifugal ambient temperature value. The deviation value is input into the PID controller to generate an initial control quantity, and the control performance is determined based on the initial control quantity; then the parameters of the PID controller are optimized until the control performance is maximized. At this time, the parameters of the PID controller are determined as the target parameters, and then a target PID controller is constructed based on the target parameters. The input deviation value is processed based on the target PID controller to obtain the final control quantity, and the temperature control device is adjusted based on this control quantity.

[0060] Specifically, the parameters for PID control include a proportional coefficient kp, an integral coefficient ki and a differential coefficient kd. Among them, the optimization and optimal search for the above three parameters are implemented by the ISSA algorithm in this embodiment. Specifically, the ISSA algorithm uses the PWLCM chaotic mapping initialization strategy and the Levy flight strategy to optimize the position equations of the initialization population of the standard sparrow search algorithm and the discoverer and the vigilant in the population, and seeks the sparrow individual with the smallest fitness value by improving the sparrow search algorithm. The sparrow individual with the smallest fitness value is the optimal PID control parameter.

[0061] Specifically, the processing process is to first initialize the sparrow population based on the PWLCM chaotic map. In this embodiment, the PWLCM chaotic map initialization strategy is used to enhance the diversity of the number of initial sparrow populations in the sparrow search algorithm, thereby improving the performance of subsequent iterative optimization of the sparrow search algorithm. The function representation of the chaotic map is as follows: ;in, and The values ​​are random numbers in [0,1]. The initial fitness value is calculated based on the fitness function, which is used to characterize the control adaptability of the current control system. The fitness function is expressed based on the following formula: ; Among them, u(t) represents the output of the PID controller, e(t) represents the deviation value, and tu represents the rise time of the PID controller. , , and They respectively represent the weighted values ​​of each item in the fitness function. In this embodiment, the above weighted values ​​are respectively taken as follows: 0.999, 0.111, 2 and 100.

[0062] Levy flight is used to update the position of the discoverer, wherein Levy flight is a random walk strategy with the characteristic that the probability distribution of the step length is a heavy-tailed distribution. Based on this characteristic, when performing a random walk, the time for small-step walks is longer, and the time for large-step walks is shorter. Through this characteristic, the existing sparrow search algorithm will be improved, and the local search capability can be enhanced to find the local optimal solution. In this embodiment, by using Levy flight to update the discoverer position, the follower position update and the vigilant position, the individual fitness of the sparrow population is recalculated and the individual position of the sparrow is updated. If the maximum number of iterations is reached or the optimal solution is sought, the operation is stopped and the optimal PID controller parameters are output; if the iteration requirements are not met, the cycle operation of updating the discoverer position, the follower position update and the vigilant position update by Levy flight is continued.

[0063] In this embodiment, by improving the sparrow search algorithm, the technical problems of lack of diversity in the initialization population and easy to fall into local optimality in the prior art can be solved, thereby improving the overall optimization performance, so that the target parameters of the PID controller can be optimized, thereby greatly improving the overall temperature control accuracy.

[0064] In this embodiment, see Figure 3 Based on the processing of step S21-step S22, the processing device is configured with a virtual module for processing the above process, and in other embodiments, the virtual module can also independently perform the processing of step S21-step S22. The processing device 12 includes the following modules: The data processing module 121 is used to obtain the predicted centrifugal environment temperature of the centrifuge at the next time node, and determine the degree of deviation from the standard centrifugal environment temperature; The control module 122 is used to, when the degree of deviation exceeds a predetermined range, treat the deviation as an error and process it through a PID controller with dynamically adjusted parameters to generate a control signal, wherein the control signal acts on the temperature control device.

[0065] See also Figure 4 In other embodiments, the above method can also be integrated into the provided terminal device 40. In view of the fact that the device may have relatively large differences due to different configurations or performances, it can include one or more processors 401 and memory 402, and the memory 402 can store one or more storage applications or data. Among them, the memory 402 can be a temporary storage or a permanent storage. The application stored in the memory 402 may include one or more modules (not shown in the figure), and each module may include a series of computer executable instructions in the terminal device. Furthermore, the processor 401 can be configured to communicate with the memory 402, and the terminal device executes a series of computer executable instructions in the memory 402. The terminal device may also include one or more power supplies 403, one or more wired or wireless network interfaces 404, one or more input / output interfaces 405, one or more keyboards 406, etc.

[0066] In a specific embodiment, the terminal device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer executable instructions in the terminal device, and the one or more programs are configured to be executed by one or more processors, including computer executable instructions for performing the following: Obtain the predicted centrifugal ambient temperature of the centrifuge at the next time node, and determine the degree of deviation from the standard centrifugal ambient temperature; When the degree of deviation exceeds a predetermined range, the deviation is treated as an error and processed by a PID controller with dynamically adjusted parameters to generate a control signal, which acts on the temperature control device.

[0067] The following is a detailed introduction to the various components of the processor: In this embodiment, the processor is an application specific integrated circuit (ASIC), or is configured to implement one or more integrated circuits of the embodiments of the present application, such as one or more microprocessors (digital signal processor, DSP), or one or more field programmable gate arrays (field programmable gate array, FPGA).

[0068] Optionally, the processor may execute various functions by running or executing a software program stored in the memory and calling data stored in the memory, such as executing the above-mentioned Figure 1 The method shown.

[0069] In a specific implementation, as an embodiment, the processor may include one or more microprocessors.

[0070] Among them, the memory is used to store the software program that executes the solution of the present application, and the execution is controlled by the processor. The specific implementation method can refer to the above method embodiment and will not be repeated here.

[0071] Optionally, the memory may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may be integrated with the processor, or may exist independently and be coupled to the processing unit through the interface circuit of the processor, which is not specifically limited in the embodiments of the present application.

[0072] It should be noted that the structure of the processor shown in this embodiment does not constitute a limitation on the device, and the actual device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0073] In addition, the technical effects of the processor can refer to the technical effects of the method described in the above method embodiment, which will not be repeated here.

[0074] It should be understood that the processor in the embodiments of the present application may be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0075] It should also be understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0076] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0077] In this application, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0078] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0079] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0080] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0081] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0082] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0083] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0084] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0085] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A centrifuge temperature control method, characterized in that: The method comprises: Obtaining the predicted centrifugal environment temperature of the centrifuge at the next time node, and determining the degree of deviation from the standard centrifugal environment temperature; the predicted centrifugal environment temperature is the predicted value of the centrifugal environment temperature corresponding to the next time node; When the degree of deviation exceeds a predetermined range, the deviation is treated as an error and processed by a PID controller with dynamically adjusted parameters to generate a control signal, which acts on the temperature control device.

2. The centrifuge temperature control method according to claim 1, characterized in that: The method further includes: acquiring a real-time centrifugal environment temperature at a current time node of the centrifuge, and acquiring a predicted centrifugal environment temperature based on a degree of deviation between the real-time centrifugal environment temperature and a standard centrifugal environment temperature.

3. The centrifuge temperature control method according to claim 2, characterized in that: The standard centrifugal environment temperature of the current time node and the next time node is determined based on the time node and the temperature rise curve.

4. The centrifuge temperature control method according to claim 2, characterized in that: When a first temperature difference between the real-time centrifugal environment temperature and the standard centrifugal environment temperature exceeds a temperature threshold, a predicted centrifugal environment temperature of the centrifuge at a next time node is obtained.

5. The centrifuge temperature control method according to claim 4, characterized in that: When the degree of deviation exceeds a predetermined range, the deviation is taken as an error and processed by a PID controller with dynamically adjusted parameters to generate a control signal, including: when a second temperature difference between the predicted centrifugal ambient temperature and the standard centrifugal ambient temperature corresponding to the next time node exceeds a temperature threshold, the second temperature difference is taken as an error and processed by a PID controller with dynamically adjusted parameters to generate a control signal.

6. The centrifuge temperature control method according to claim 1, characterized in that: The method of obtaining the predicted centrifugal ambient temperature at the next time node includes: obtaining centrifugal ambient temperature data, centrifuge speed data and centrifugal motor temperature data at multiple previous time nodes, and processing the centrifugal ambient temperature data, centrifuge speed data and centrifugal motor temperature data by encoding and decoding based on a temperature prediction model to obtain the predicted centrifugal ambient temperature at the next time node.

7. The centrifuge temperature control method according to claim 6, characterized in that: The method also includes: dividing the previous multiple time nodes in time order to obtain a first sequence group and a second sequence group, each sequence group containing centrifuge environment temperature data, centrifuge speed data and centrifuge motor temperature data corresponding to at least one time node; respectively performing encoding processing and decoding processing based on the self-attention mechanism on the first sequence group and the second sequence group to obtain the predicted centrifuge environment temperature of the next time node.

8. The centrifuge temperature control method according to claim 7, characterized in that: The method also includes: obtaining a centrifugal environment temperature memory information matrix through encoding processing, obtaining a centrifugal environment temperature change sequence through decoding processing, and performing attention calculation on the centrifugal environment temperature memory information matrix and the centrifugal environment temperature change sequence to obtain a predicted centrifugal environment temperature at the next time node.

9. The centrifuge temperature control method according to claim 1, characterized in that: The dynamic adjustment of the parameters generates an initial control quantity through a PID controller, determines the control performance based on the initial control quantity, and optimizes the parameters of the PID controller until the control performance is maximized to determine the target parameters of the PID controller.

10. A centrifuge, characterized in that: include: A centrifugal motor, a centrifugal chamber, a temperature control device, a sensor assembly and a processing device; the sensor assembly includes a first temperature sensor and a second temperature sensor, the first temperature sensor is used to obtain the centrifugal motor temperature of the centrifugal motor, and the second temperature sensor is used to obtain the centrifugal environment temperature in the centrifugal chamber; The processing device is used to execute the centrifuge temperature control method according to any one of claims 1 to 9, and send a control signal to the temperature control device, and the processing device includes: A data processing module, used to obtain the predicted centrifugal environment temperature of the centrifuge at the next time node, and determine the degree of deviation from the standard centrifugal environment temperature; The control module is used to treat the deviation as an error and generate a control signal by processing it through a PID controller with dynamically adjusted parameters when the deviation exceeds a predetermined range, and the control signal acts on the temperature control device.

Images