Method and system for calibrating the rotation speed of a centrifuge

Abstract

The present invention relates to the technical field of separation engineering, and in particular to a method and system for calibrating the speed of a centrifuge, wherein the method comprises: analyzing the changes in the centrifuge drum speed and the propeller speed within a historical time period to determine a plurality of first time periods indicating a target speed change phase of the centrifuge drum and a plurality of second time periods indicating a target speed change phase of the propeller; analyzing the similarity between the centrifuge's target operating data in the current time period and its plurality of first historical operating data in the plurality of first time periods, and analyzing the similarity between the centrifuge's target operating data in the current time period and its plurality of second historical operating data in the plurality of second time periods; and accordingly correcting the initial adjustment interval, and then performing PID control on the speed of the centrifuge according to the corrected adjustment interval. The present invention can achieve a better speed control effect for the centrifuge by dynamically adjusting the adjustment interval of PID control.

Description

Technical Field

[0001] The present invention relates to the technical field of separation engineering, and in particular to a rotation speed calibration method and system for a centrifuge. Background Art

[0002] Centrifugal separation technology, one of the core processes in modern grain processing, food manufacturing, chemical, and pharmaceutical industries, is widely used for the efficient separation of multiphase materials. In particular, in the production of gluten, edible starch, and plant protein, three-phase centrifuges have become key equipment due to their ability to achieve continuous and efficient separation of solid-liquid-liquid multiphase materials. With the increasing demand for automated and intelligent production, centrifuge operation control is gradually evolving from traditional fixed parameter and manual intervention modes to intelligent control driven by real-time operating data, achieving higher-purity separation results, lower energy consumption, and better process adaptability.

[0003] Existing centrifuge speed control methods, primarily based on fixed sampling frequencies and traditional PID control strategies, struggle to adapt to the multi-parameter coupled control requirements triggered by factors such as dynamic changes in target speed, drum load fluctuations, and differential speed variations. In actual three-phase centrifugal separation processes, target speed changes corresponding to different separation stages are often accompanied by complex coupled changes in drum pressure, vibration, drum speed, and propeller speed, and the correlation between each parameter varies with different speed changes.

[0004] That is to say, the speed control effect of the centrifuge control solution provided by the prior art is relatively poor. Summary of the Invention

[0005] In order to solve the technical problem that the speed control effect of the centrifuge control solution provided by the prior art is poor, the purpose of the present invention is to provide a speed calibration method and system for a centrifuge. The technical solution adopted is as follows:

[0006] In a first aspect, an embodiment of the present invention provides a method for calibrating the rotational speed of a centrifuge, the method comprising:

[0007] Analyzing changes in the centrifuge drum speed and propeller speed over a historical time period to determine a plurality of first time periods and a plurality of second time periods, wherein the first time periods are used to indicate historical operating time periods during which the centrifuge drum was switched to a target speed, and the second time periods are used to indicate historical operating time periods during which the propeller was switched to a target speed;

[0008] Analyzing the similarity between the target operating data of the centrifuge in the current time period and a plurality of first historical operating data thereof in a plurality of first time periods to obtain a first probability; and analyzing the similarity between the target operating data of the centrifuge in the current time period and a plurality of second historical operating data thereof in a plurality of second time periods to obtain a second probability, wherein the first probability represents a probability that the target speed of the centrifuge drum changes phases in the current time period, and the second probability represents a probability that the target speed of the centrifuge propeller changes phases in the current time period;

[0009] Correcting the initial adjustment interval according to the first probability and the second probability to obtain a corrected adjustment interval, wherein the adjustment interval is used to indicate the duration of an operation interval between two adjacent PID adjustment operations performed by the centrifuge;

[0010] According to the corrected adjustment interval, PID control is performed on the drum speed and the propeller speed of the centrifuge.

[0011] In one embodiment, analyzing the changes in the centrifuge drum speed and the propeller speed within a historical time period to determine a plurality of first time periods and a plurality of second time periods includes:

[0012] Analyzing the degree of change and the degree of dispersion of multiple drum speeds of the centrifuge in a historical time period to obtain a plurality of first segmented probabilities corresponding to the plurality of historical moments, and analyzing the degree of change and the degree of dispersion of multiple propeller speeds of the centrifuge in a historical time period to obtain a plurality of second segmented probabilities corresponding to the plurality of historical moments;

[0013] Among the multiple historical moments, the larger one between the first segment probability and the second segment probability of each historical moment is determined as the moment segment probability of the historical moment, so as to obtain multiple moment segment probabilities;

[0014] Among the multiple moment segment probabilities, all moment segment probabilities that are greater than or equal to the probability threshold are determined as target segment probabilities;

[0015] The multiple target segmentation probabilities are divided into time periods according to the multiple historical moments to obtain the multiple first time periods and the multiple second time periods.

[0016] In one embodiment, the variation and discreteness of the rotation speeds of the drum of the centrifuge in a historical time period are analyzed to obtain a plurality of first segmented probabilities corresponding to a plurality of historical moments, including:

[0017] Calculating the ratio of the drum variation value and the drum discrete value of the centrifuge at each historical moment to obtain a plurality of first segmented probabilities, wherein the drum variation value is a first-order difference value of the target drum speed of the centrifuge at the corresponding historical moment, and the drum discrete value is a standard deviation corresponding to the actual drum speed of the centrifuge at the corresponding historical moment;

[0018] Analyzing the degree of change and discreteness of the rotational speeds of multiple propellers of the centrifuge in a historical time period to obtain multiple second segmented probabilities corresponding to the multiple historical moments, including:

[0019] The ratio of the propeller change value and the propeller discrete value of the centrifuge at each historical moment is calculated to obtain multiple second segmented probabilities, wherein the propeller change value is the first-order difference value of the target speed of the propeller of the centrifuge at the corresponding historical moment, and the propeller discrete value is the standard deviation corresponding to the actual speed of the propeller of the centrifuge at the corresponding historical moment.

[0020] In one embodiment, dividing the time periods according to the multiple historical moments at which the multiple target segmentation probabilities are located to obtain the multiple first time periods and the multiple second time periods includes:

[0021] Divide the time period according to the multiple historical moments where the multiple target segmentation probabilities are located to obtain multiple candidate time periods;

[0022] Distinguishing the plurality of candidate time periods based on a preset differentiation rule to determine the plurality of first time periods and the plurality of second time periods;

[0023] The differentiation rules include:

[0024] When the first segment probability of the last historical moment of the candidate time period is greater than or equal to the second segment probability, the candidate time period is determined as the first time period;

[0025] When the first segment probability of the last historical moment of the candidate time period is less than the second segment probability, the candidate time period is determined as the second time period.

[0026] In one embodiment, the first probability is obtained by analyzing the similarity between the target operating data of the centrifuge in the current time period and a plurality of first historical operating data in a plurality of first time periods, including:

[0027] Under each dimension, calculating the degree of difference between the target operating data and the first historical operating data of the target first time period to obtain a plurality of first dimension difference values, wherein the target first time period is any first time period among the plurality of first time periods;

[0028] Obtaining a data similarity probability between the current time period and the target first time period based on the multiple first dimension difference values ​​and the first correlation value of each dimension, wherein the first correlation value is used to indicate a degree of correlation between the data of the corresponding dimension and the drum speed;

[0029] Among a plurality of data similarity probabilities between the current time period and a plurality of first time periods, determining the greatest data similarity probability as the first probability;

[0030] The second probability is obtained by analyzing the similarity between the target operating data of the centrifuge in the current time period and a plurality of second historical operating data in a plurality of second time periods, including:

[0031] Under each dimension, calculating the degree of difference between the target operating data and the second historical operating data of the target second time period to obtain a plurality of second dimension difference values, wherein the target second time period is any second time period among the plurality of second time periods;

[0032] Obtaining a data similarity probability between the current time period and the target second time period based on the plurality of second dimension difference values ​​and a second correlation value of each dimension, wherein the second correlation value is used to indicate a degree of correlation between the data of the corresponding dimension and the propeller speed;

[0033] Among a plurality of data similarity probabilities between the current time period and a plurality of second time periods, the greatest data similarity probability is determined as the second probability.

[0034] In one embodiment, the step of obtaining the first correlation value of each dimension includes:

[0035] Acquire a plurality of first feature data and a plurality of first target changes, wherein the plurality of first feature data correspond one-to-one to the plurality of first time periods, the first feature data is used to represent data features of first historical operating data corresponding to the first time period in a target dimension, the target dimension being any one of the plurality of dimensions, the plurality of first target changes correspond one-to-one to the plurality of first time periods, and the first target change is a change in the target speed of the drum at the last historical moment of the corresponding first time period;

[0036] Performing correlation analysis on the plurality of first feature data and the plurality of first target variation amounts to obtain a first correlation value of the target dimension;

[0037] The steps for obtaining the second related value of each dimension include:

[0038] Acquire a plurality of second feature data and a plurality of second target changes, wherein the plurality of second feature data and the plurality of second time periods correspond one-to-one, the second feature data are used to represent data features of the second historical operating data in the target dimension for the corresponding second time period, the plurality of second target changes and the plurality of second time periods correspond one-to-one, and the second target change is a change in the target speed of the propeller at the last historical moment of the corresponding second time period;

[0039] Correlation analysis is performed on the plurality of second feature data and the plurality of second target variations to obtain a second correlation value of the target dimension.

[0040] In one embodiment, obtaining the data similarity probability between the current time period and the target first time period based on the multiple first dimension difference values ​​and the first correlation value of each dimension includes:

[0041] Among the plurality of first dimension difference values, determining the largest first dimension difference value as the first dimension difference extreme value;

[0042] respectively calculating the ratios of the plurality of first dimension difference values ​​to the first dimension difference extreme values ​​to obtain a plurality of first dimension difference indexes;

[0043] According to the plurality of first dimension difference indices, a plurality of first dimension similarity indices corresponding one to one with the plurality of first dimension difference indices are obtained, wherein the sum of the first dimension similarity index and the corresponding first dimension difference index is 1;

[0044] Using the first correlation value of each dimension as a weight, weighted calculation is performed on the multiple first dimension similarity indexes to obtain the data similarity probability between the current time period and the target first time period;

[0045] Obtaining a data similarity probability between the current time period and the target second time period based on the multiple second dimension difference values ​​and the second correlation value of each dimension includes:

[0046] Among the plurality of second dimension difference values, determining the largest second dimension difference value as the second dimension difference extreme value;

[0047] respectively calculating the ratios of the plurality of second dimension difference values ​​to the second dimension difference extreme values ​​to obtain a plurality of second dimension difference indexes;

[0048] According to the plurality of second dimension difference indices, a plurality of second dimension similarity indices corresponding one-to-one to the plurality of second dimension difference indices are obtained, wherein the sum of the second dimension similarity index and the corresponding second dimension difference index is 1;

[0049] The second correlation value of each dimension is used as a weight to perform weighted calculation on the multiple second dimension similarity indexes to obtain the data similarity probability between the current time period and the target second time period.

[0050] In one embodiment, the first feature data includes a plurality of first feature sub-data corresponding to a plurality of feature categories, and the second feature data includes a plurality of second feature sub-data corresponding to the plurality of feature categories;

[0051] The performing correlation analysis on the plurality of first feature data and the plurality of first target variation amounts to obtain the first correlation value of the target dimension includes:

[0052] Performing correlation analysis on a plurality of first feature sub-data corresponding to each feature category and a plurality of first target variation amounts to obtain a first candidate correlation value corresponding to each feature category;

[0053] Determining the largest first candidate correlation value among multiple first candidate correlation values ​​corresponding to multiple feature categories as the first correlation value;

[0054] The performing correlation analysis on the plurality of second feature data and the plurality of second target variation amounts to obtain the second correlation value of the target dimension includes:

[0055] Performing correlation analysis on the plurality of second feature sub-data corresponding to each feature category and the plurality of second target variation amounts to obtain a second candidate correlation value corresponding to each feature category;

[0056] Among multiple second candidate correlation values ​​corresponding to multiple feature categories, the largest second candidate correlation value is determined as the second correlation value.

[0057] In one embodiment, the step of modifying the initial adjustment interval according to the first probability and the second probability to obtain a modified adjustment interval includes:

[0058] Taking the larger of the first probability and the second probability to obtain an extreme value probability;

[0059] Transforming the extreme value probability to obtain a correction coefficient, wherein the sum of the correction coefficient and the extreme value probability is 1;

[0060] The product of the correction coefficient and the initial adjustment interval is calculated to obtain the corrected adjustment interval.

[0061] In a second aspect, another embodiment of the present invention provides a rotation speed calibration system for a centrifuge, the system comprising:

[0062] a historical analysis module, configured to analyze changes in the centrifuge drum speed and propeller speed within a historical time period to determine a plurality of first time periods and a plurality of second time periods, wherein the first time periods are used to indicate historical operating time periods during which the centrifuge drum was subjected to a target speed transition, and the second time periods are used to indicate historical operating time periods during which the propeller was subjected to a target speed transition;

[0063] a real-time analysis module configured to analyze a degree of similarity between target operating data of the centrifuge in a current time period and a plurality of first historical operating data thereof in a plurality of first time periods to obtain a first probability; and to analyze a degree of similarity between target operating data of the centrifuge in the current time period and a plurality of second historical operating data thereof in a plurality of second time periods to obtain a second probability, wherein the first probability represents a probability that the target speed of the centrifuge drum changes phases in the current time period, and the second probability represents a probability that the target speed of the centrifuge propeller changes phases in the current time period;

[0064] an interval correction module, configured to correct an initial adjustment interval according to the first probability and the second probability to obtain a corrected adjustment interval, wherein the adjustment interval is used to indicate a duration of an operation interval between two adjacent PID adjustment operations performed by the centrifuge;

[0065] The speed control module is used to perform PID control on the drum speed and the propeller speed of the centrifuge according to the corrected adjustment interval.

[0066] In a third aspect, another embodiment of the present invention further provides an electronic device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the method described in the first aspect when executed by the processor.

[0067] In a fourth aspect, another embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0068] The present invention has the following beneficial effects:

[0069] The present invention determines a plurality of first time periods and a plurality of second time periods by analyzing the changes in the centrifuge drum speed and the propeller speed in a historical time period, that is, determines a plurality of time periods corresponding to the centrifuge drum target speed transition phase and a plurality of time steps corresponding to the centrifuge propeller target speed transition phase, and then analyzes the similarity between the target operation data of the centrifuge in the current time period and its historical operation data in the plurality of first time periods, and analyzes the similarity between the target operation data and the historical operation data of the centrifuge in the plurality of second time periods, determines the probability that the centrifuge drum target speed transition phase in the current time period, and determines the probability that the centrifuge propeller target speed transition phase in the current time period. The probability of the phase transition in the previous time period is calculated, and the adjustment interval is corrected accordingly. Then, the PID control of the drum speed and the propeller speed of the centrifuge is performed based on the corrected adjustment interval to adapt to the situation where the PID control intervals of the centrifuge in different working stages are different. This can dynamically reduce the frequency of sampling operations and adjustment operations associated with PID control when the target speed of the centrifuge remains stable, thereby reducing system resource consumption and control disturbances; and dynamically increase the frequency of sampling operations and adjustment operations associated with PID control when the target speed of the centrifuge fluctuates, so as to facilitate fast and accurate speed regulation, and ultimately enable the centrifuge to obtain better speed regulation effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0071] Figure 1 A schematic flow chart of a method for calibrating the rotational speed of a centrifuge provided in one embodiment of the present invention;

[0072] Figure 2 A schematic structural diagram of a rotation speed calibration system for a centrifuge provided in one embodiment of the present invention;

[0073] Figure 3 The present invention provides a schematic structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0074] To further illustrate the technical means and effectiveness of the present invention in achieving its intended objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail a method and system for centrifuge speed calibration, including its specific implementation, structure, features, and effectiveness. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0075] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0076] The following describes in detail a method and system for calibrating the rotational speed of a centrifuge provided by the present invention with reference to the accompanying drawings.

[0077] The present invention proposes a method for calibrating the rotational speed of a centrifuge. Figure 1 , which shows a flow chart of a method for calibrating the rotational speed of a centrifuge provided by one embodiment of the present invention, the method comprising the following steps:

[0078] Step S1: Analyze the changes in the centrifuge drum speed and the propeller speed within a historical time period to determine a plurality of first time periods and a plurality of second time periods.

[0079] The first time period is used to indicate the historical operating period of the drum target speed transition stage, and the second time period is used to indicate the historical operating period of the propeller target speed transition stage.

[0080] More specifically, the first period is used to indicate the historical operating period when the target rotation speed of the drum changes dramatically. Similarly, the second period is used to indicate the historical operating period when the propeller changes dramatically.

[0081] In the present invention, the duration of the historical time period is set to be greater than or equal to a duration threshold (such as 24 hours) to ensure that the historical time period covers multiple speed adjustment processes of the centrifuge. For example, the historical time period can be the time period of the date before the current date.

[0082] In some embodiments, if each historical date before the current date is set to correspond to a candidate time period, then among multiple candidate time periods, the candidate time period closest to the material properties (such as the weight of the material) of the material to be processed on the current date can be determined as the historical time period, so as to further improve the accuracy of the centrifuge speed control on the current date by selecting the historical operating data of the closest material situation as a reference.

[0083] It should be noted that in order to support the execution of multiple steps in the present invention, it is necessary to obtain the target speed of the centrifuge drum at each historical moment in the historical time period (obtained based on the PID control algorithm), the actual speed of the centrifuge drum (obtained based on the magnetoelectric speed sensor installed on the main shaft end of the centrifuge, the real-time pulse count is converted into RPM, and the timestamp is recorded synchronously), the target speed of the propeller (obtained based on the PID control algorithm), the actual speed of the propeller (obtained based on the magnetoelectric speed sensor installed on the main shaft end of the propeller, the real-time pulse count is converted into RPM, and the timestamp is recorded synchronously), the internal pressure data of the centrifuge drum (obtained through the strain / capacitive intelligent pressure sensor installed at the dedicated sampling port inside the centrifuge drum, the numerical unit of the internal pressure data is Pa), and the vibration data of the centrifuge main shaft (obtained through the three-axis acceleration sensor on the bearing seat of the centrifuge main shaft).

[0084] The above data are all collected in the form of time-series data streams marked with timestamps. The data are stored in real time on the industrial computer and aligned by timestamps. After standardization processing (such as maximum and minimum normalization processing) and dimension removal, they are used for subsequent analysis.

[0085] In centrifuges, particularly three-phase centrifuges, the drum speed directly determines the centrifugal force required for material separation, impacting both separation efficiency and purity. The propeller speed directly determines the solid-phase material discharge rate, impacting both production capacity and discharge efficiency. Therefore, the present invention selects the drum and propeller speeds as key speeds for centrifuge speed analysis, ensuring accurate PID control of the centrifuge and ensuring that the centrifuge's output meets expectations.

[0086] During the PID control of the centrifuge's speed, a decrease in the purity of the separated material, increased entrainment, and unstable interface conditions will trigger PID control intervention and cause changes in the target speed of the drum. Increased vibration, a step-wise increase in drum pressure, and an extended slag discharge cycle will also trigger PID control intervention, but will cause changes in the target speed of the propeller. In other words, the operating conditions that affect changes in the target speed of the drum and the target speed of the propeller are different. Based on this, in the above process, by determining multiple first time periods and multiple second time periods to distinguish between different stages of changes in the drum speed and different stages of changes in the propeller speed, the centrifuge can achieve more accurate and effective PID control by adapting the two to different operating conditions.

[0087] Furthermore, the analyzing of the changes in the centrifuge drum speed and the propeller speed within the historical time period to determine a plurality of first time periods and a plurality of second time periods includes:

[0088] Analyzing the degree of change and the degree of dispersion of multiple drum speeds of the centrifuge in a historical time period to obtain a plurality of first segmented probabilities corresponding to the plurality of historical moments, and analyzing the degree of change and the degree of dispersion of multiple propeller speeds of the centrifuge in a historical time period to obtain a plurality of second segmented probabilities corresponding to the plurality of historical moments;

[0089] Among the multiple historical moments, the larger one between the first segment probability and the second segment probability of each historical moment is determined as the moment segment probability of the historical moment, so as to obtain multiple moment segment probabilities;

[0090] Among the multiple moment segment probabilities, all moment segment probabilities that are greater than or equal to the probability threshold are determined as target segment probabilities;

[0091] The multiple target segmentation probabilities are divided into time periods according to the multiple historical moments to obtain the multiple first time periods and the multiple second time periods.

[0092] The first segmentation probability can be understood as the degree to which time segments are necessary due to changes in the centrifuge's drum speed at the corresponding historical moment. The greater the first segmentation probability, the more necessary it is to use the corresponding historical moment as the time anchor point for segmentation. Similarly, the second segmentation probability can be understood as the degree to which time segments are necessary due to changes in the centrifuge's propeller speed at the corresponding historical moment. The greater the second segmentation probability, the more necessary it is to use the corresponding historical moment as the time anchor point for segmentation.

[0093] It is important to emphasize that the degree of change in drum speed at a given historical moment specifically refers to the degree of change in the target drum speed at that moment, while the degree of dispersion in drum speed at a given historical moment specifically refers to the degree of dispersion in the actual drum speed at that moment. Similarly, the degree of change in propeller speed at a given historical moment specifically refers to the degree of change in the target propeller speed at that moment, while the degree of dispersion in propeller speed at a given historical moment specifically refers to the degree of dispersion in the actual propeller speed at that moment.

[0094] In the above setting, based on the analysis of the target value change degree and the actual value discreteness of the drum speed (or propeller speed) at the corresponding historical moment, the determined first segment probability (or second segment probability) can be made more accurate.

[0095] It should be noted that in the present invention, the operation of dividing the time period is for the purpose of making a more refined comparison between the historical operating data and the target operating data of the current time period in the time domain, so as to accurately complete the dynamic adjustment of the operation interval of the PID adjustment operation. Among them, the higher the degree of change of the target speed, the greater the amplitude of the speed adjustment required by the PID control program at the corresponding historical moment, and the stronger the necessity of separating the historical moment and several historical moments before it from the time domain for subsequent comparative analysis. Therefore, the corresponding segmentation probability is also higher. Accordingly, the higher the discrete degree of the actual speed, the higher the actual speed adjustment efficiency of the corresponding historical moment under the intervention of the PID control program, and the weaker the necessity of separating the historical moment and several historical moments before it from the time domain for subsequent comparative analysis, and the lower the corresponding segmentation probability.

[0096] Among multiple historical moments, the larger one between the first segment probability and the second segment probability of each historical moment is determined as the moment segment probability of the historical moment, which can further improve the accuracy of the time period segmentation operation.

[0097] Exemplarily, the probability threshold may be set to 1.2.

[0098] Furthermore, the variation and discreteness of the rotation speeds of the drum of the centrifuge in the historical time period are analyzed to obtain a plurality of first segmented probabilities corresponding to a plurality of historical moments, including:

[0099] Calculating the ratio of the drum variation value and the drum discrete value of the centrifuge at each historical moment to obtain a plurality of first segmented probabilities, wherein the drum variation value is a first-order difference value of the target drum speed of the centrifuge at the corresponding historical moment, and the drum discrete value is a standard deviation corresponding to the actual drum speed of the centrifuge at the corresponding historical moment;

[0100] Analyzing the degree of change and discreteness of the rotational speeds of multiple propellers of the centrifuge in a historical time period to obtain multiple second segmented probabilities corresponding to the multiple historical moments, including:

[0101] The ratio of the propeller change value and the propeller discrete value of the centrifuge at each historical moment is calculated to obtain multiple second segmented probabilities, wherein the propeller change value is the first-order difference value of the target speed of the propeller of the centrifuge at the corresponding historical moment, and the propeller discrete value is the standard deviation corresponding to the actual speed of the propeller of the centrifuge at the corresponding historical moment.

[0102] The first-order difference value of the centrifuge's drum target speed at a corresponding historical moment is specifically the absolute value of the difference between the centrifuge's drum target speed at the corresponding historical moment and the centrifuge's drum target speed at the previous historical moment. Similarly, the first-order difference value of the centrifuge's propeller target speed at a corresponding historical moment is specifically the absolute value of the difference between the centrifuge's propeller target speed at the corresponding historical moment and the centrifuge's propeller target speed at the previous historical moment.

[0103] The standard deviation of the centrifuge's actual drum speed at a given historical moment is specifically calculated as: the standard deviation of the centrifuge's actual drum speeds for a set period of time (e.g., one minute) going back from the given historical moment. Similarly, the standard deviation of the centrifuge's actual propeller speed at a given historical moment is specifically calculated as: the standard deviation of the centrifuge's actual propeller speeds for a set period of time (e.g., one minute) going back from the given historical moment.

[0104] For example, the segmentation probability of historical moment t among the multiple historical moments included in the historical time period is It can be expressed as:

[0105]

[0106] in, express function (i.e. taking the maximum value of multiple function inputs as output), represents the target drum speed at historical time t, represents the target speed of the propeller at the historical moment t, represents the actual drum speed at historical time t, represents the actual speed of the propeller at the historical moment t, represents the standard deviation function, represents the drum change value at historical time t, represents the discrete value of the drum at historical time t, represents the propeller change value at historical time t, Represents the discrete value of the thruster at historical time t.

[0107] Furthermore, the dividing the time periods according to the multiple historical moments where the multiple target segmentation probabilities are located to obtain the multiple first time periods and the multiple second time periods includes:

[0108] Divide the time period according to the multiple historical moments where the multiple target segmentation probabilities are located to obtain multiple candidate time periods;

[0109] Distinguishing the plurality of candidate time periods based on a preset differentiation rule to determine the plurality of first time periods and the plurality of second time periods;

[0110] The differentiation rules include:

[0111] When the first segment probability of the last historical moment of the candidate time period is greater than or equal to the second segment probability, the candidate time period is determined as the first time period;

[0112] When the first segment probability of the last historical moment of the candidate time period is less than the second segment probability, the candidate time period is determined as the second time period.

[0113] The process of dividing the time period according to the multiple historical moments where the multiple target segmentation probabilities are located to obtain multiple candidate time periods is as follows:

[0114] Take the historical moment of each target segment probability as the end point of the time period and trace back to a period of a certain length (such as 10 seconds, 30 seconds, 60 seconds, etc.).

[0115] In the above setting, based on the comparison between the probability threshold and the moment segmentation probability, multiple target segmentation probabilities are selected, that is, multiple time anchor points for segmentation (that is, multiple historical moments where the multiple target segmentation probabilities are located) are selected to ensure the execution accuracy of the segmentation operation. Then, among the multiple candidate time periods obtained by segmentation, each candidate time period is further distinguished as belonging to the time period dominated by the change in drum speed (that is, distinguishing the candidate time period as the first time period) or the time period dominated by the change in propeller speed (that is, distinguishing the candidate time period as the second time period). This is to facilitate the subsequent comparison of the historical operation data of multiple candidate time periods with the target operation data, and to clarify whether the specific object to be compared is the drum or the propeller, thereby improving the correction accuracy of the adjustment interval.

[0116] Step S2: Analyze the similarity between the target operating data of the centrifuge in the current time period and the plurality of first historical operating data in the plurality of first time periods to obtain a first probability; and analyze the similarity between the target operating data of the centrifuge in the current time period and the plurality of second historical operating data in the plurality of second time periods to obtain a second probability.

[0117] The first probability represents the probability that the target speed of the centrifuge drum changes phases in the current time period, and the second probability represents the probability that the target speed of the centrifuge propeller changes phases in the current time period.

[0118] The above-mentioned current time period can be understood as a time period starting from the current moment and tracing back to the target duration (such as 1 minute, 2 minutes, etc.).

[0119] When a centrifuge is operating, before a significant adjustment is made to the target speed via the PID control program, the multidimensional sensor data in the centrifuge (such as vibration data and internal pressure data) that influences the speed adjustment will exhibit certain trends or patterns of change (e.g., increased vibration indicates material accumulation or uneven loading, so the system increases the drum speed to enhance centrifugal force). Furthermore, since the first and second time periods indicate historical operating periods when the centrifuge's target speed has dramatically changed, analyzing the similarity between the centrifuge's target operating data in the current time period and its historical operating data in the first and second time periods allows for the rapid and accurate identification of the probability of a significant adjustment to the centrifuge's target speed in the current time period, thereby providing guidance for subsequent adjustment intervals.

[0120] Furthermore, the first probability is obtained by analyzing the similarity between the target operation data of the centrifuge in the current time period and a plurality of first historical operation data of the centrifuge in a plurality of first time periods, including:

[0121] Under each dimension, calculating the degree of difference between the target operating data and the first historical operating data of the target first time period to obtain a plurality of first dimension difference values, wherein the target first time period is any first time period among the plurality of first time periods;

[0122] Obtaining a data similarity probability between the current time period and the target first time period based on the multiple first dimension difference values ​​and the first correlation value of each dimension, wherein the first correlation value is used to indicate a degree of correlation between the data of the corresponding dimension and the drum speed;

[0123] Among a plurality of data similarity probabilities between the current time period and a plurality of first time periods, determining the greatest data similarity probability as the first probability;

[0124] The second probability is obtained by analyzing the similarity between the target operating data of the centrifuge in the current time period and a plurality of second historical operating data in a plurality of second time periods, including:

[0125] Under each dimension, calculating the degree of difference between the target operating data and the second historical operating data of the target second time period to obtain a plurality of second dimension difference values, wherein the target second time period is any second time period among the plurality of second time periods;

[0126] Obtaining a data similarity probability between the current time period and the target second time period based on the plurality of second dimension difference values ​​and a second correlation value of each dimension, wherein the second correlation value is used to indicate a degree of correlation between the data of the corresponding dimension and the propeller speed;

[0127] Among a plurality of data similarity probabilities between the current time period and a plurality of second time periods, the greatest data similarity probability is determined as the second probability.

[0128] The multiple dimensions corresponding to the centrifuge operation data may include: a pressure dimension (ie, internal pressure data of the centrifuge drum included in the operation data) and a vibration dimension (ie, vibration data of the centrifuge main shaft included in the operation data).

[0129] In the above setting, by analyzing the similarity between the target operating data and the historical operating data of each first time period / second time period in each dimension, the similarity between the operating conditions of the current time period and the historical conditions corresponding to the drastic changes in the target speed is evaluated from multiple aspects, thereby ensuring the data accuracy of the first probability and the second probability finally determined.

[0130] Among them, the degree of difference between the target operating data and the historical operating data of each first time period / second time period in each dimension is analyzed. In addition to comparing the degree of difference of the data itself in the corresponding dimension, the relevant value corresponding to the dimension is introduced to assist in the calculation, so as to use the degree of influence of the dimension on the adjustment of the target speed to correct the difference calculation result, which can further improve the data accuracy of the determined first probability and second probability.

[0131] Among them, the higher the difference between the calculated target operating data and the first historical operating data of the target first time period, the larger the corresponding calculated first dimension difference value.

[0132] For example, the dynamic time warping (DTW) distance between the target operating data and the first historical operating data of the target first time period can be calculated in each dimension, and used as the first dimension difference value in the corresponding dimension, thereby obtaining the multiple first dimension difference values.

[0133] Furthermore, the step of obtaining the first correlation value of each dimension includes:

[0134] Acquire a plurality of first feature data and a plurality of first target changes, wherein the plurality of first feature data correspond one-to-one to the plurality of first time periods, the first feature data is used to represent data features of first historical operating data corresponding to the first time period in a target dimension, the target dimension being any one of the plurality of dimensions, the plurality of first target changes correspond one-to-one to the plurality of first time periods, and the first target change is a change in the target speed of the drum at the last historical moment of the corresponding first time period;

[0135] Performing correlation analysis on the plurality of first feature data and the plurality of first target variation amounts to obtain a first correlation value of the target dimension;

[0136] The steps for obtaining the second related value of each dimension include:

[0137] Acquire a plurality of second characteristic data and a plurality of second target changes, wherein the plurality of second characteristic data correspond one-to-one to the plurality of second time periods, the second characteristic data are used to represent data characteristics of the second historical operating data in the target dimension for the corresponding second time period, the plurality of second target changes correspond one-to-one to the plurality of second time periods, and the second target change is a change in the target speed of the propeller at the last historical moment of the corresponding second time period;

[0138] Correlation analysis is performed on the plurality of second feature data and the plurality of second target variations to obtain a second correlation value of the target dimension.

[0139] In the above setting, the first characteristic data indicating the data characteristics under the corresponding dimension and the first target change amount indicating the degree of change of the target speed of the drum in the corresponding first time period are extracted from each first time period to obtain multiple first characteristic data and multiple first target change amounts, and the two are correlated and analyzed to determine the degree of influence of the corresponding dimension on the change of the target speed of the drum.

[0140] Among them, multiple first characteristic data correspond one-to-one to the multiple first time periods, the multiple first target changes also correspond one-to-one to the multiple first time periods, multiple second characteristic data correspond one-to-one to the second time periods, and the multiple second target changes correspond one-to-one to the multiple second time periods.

[0141] In one example, the process of performing correlation analysis on multiple first feature data and multiple first target changes to obtain the first correlation value of the target dimension is: calculating the Pearson correlation coefficient between the multiple first feature data and the multiple first target changes, and using it as the first correlation value of the target dimension.

[0142] The larger the first correlation value is, the greater the impact of the operating data of the corresponding dimension on the change of the target speed of the drum; similarly, the larger the second correlation value is, the greater the impact of the operating data of the corresponding dimension on the change of the propeller speed.

[0143] Similarly, the second correlation value of the target dimension can be understood as: the Pearson correlation coefficient between the multiple second feature data and the multiple second target changes.

[0144] Furthermore, the first feature data includes a plurality of first feature sub-data corresponding to a plurality of feature categories, and the second feature data includes a plurality of second feature sub-data corresponding to the plurality of feature categories;

[0145] The performing correlation analysis on the plurality of first feature data and the plurality of first target variation amounts to obtain the first correlation value of the target dimension includes:

[0146] Performing correlation analysis on a plurality of first feature sub-data corresponding to each feature category and a plurality of first target variation amounts to obtain a first candidate correlation value corresponding to each feature category;

[0147] Determining the largest first candidate correlation value among multiple first candidate correlation values ​​corresponding to multiple feature categories as the first correlation value;

[0148] The performing correlation analysis on the plurality of second feature data and the plurality of second target variation amounts to obtain the second correlation value of the target dimension includes:

[0149] Performing correlation analysis on the plurality of second feature sub-data corresponding to each feature category and the plurality of second target variation amounts to obtain a second candidate correlation value corresponding to each feature category;

[0150] Among multiple second candidate correlation values ​​corresponding to multiple feature categories, the largest second candidate correlation value is determined as the second correlation value.

[0151] For example, the above-mentioned multiple feature categories may include mean / median / mode indicating the trend of the data set, variance / standard deviation / range indicating the degree of dispersion, and skewness / kurtosis indicating the distribution morphology.

[0152] Based on the above settings, it is supported to share the degree to which the operating data of each dimension affects the change of the target speed from multiple perspectives, so that the determination of the first correlation value and the second correlation value is more flexible and accurate.

[0153] Among them, the first candidate correlation value can be understood as the Pearson correlation coefficient between multiple first feature sub-data of the corresponding feature category and multiple first target changes, and the second candidate correlation value can be understood as the Pearson correlation coefficient between multiple second feature sub-data of the corresponding feature category and multiple second target changes.

[0154] For example, when the feature category is mean and the target dimension is vibration data, the multiple first feature sub-data corresponding to the feature category under the target dimension are: multiple data means of multiple groups of vibration data sequences in multiple first time periods.

[0155] Furthermore, obtaining the data similarity probability between the current time period and the target first time period based on the multiple first dimension difference values ​​and the first correlation value of each dimension includes:

[0156] Among the plurality of first dimension difference values, determining the largest first dimension difference value as the first dimension difference extreme value;

[0157] respectively calculating the ratios of the plurality of first dimension difference values ​​to the first dimension difference extreme values ​​to obtain a plurality of first dimension difference indexes;

[0158] According to the plurality of first dimension difference indices, a plurality of first dimension similarity indices corresponding one to one with the plurality of first dimension difference indices are obtained, wherein the sum of the first dimension similarity index and the corresponding first dimension difference index is 1;

[0159] Using the first correlation value of each dimension as a weight, weighted calculation is performed on the multiple first dimension similarity indexes to obtain the data similarity probability between the current time period and the target first time period;

[0160] Obtaining a data similarity probability between the current time period and the target second time period based on the multiple second dimension difference values ​​and the second correlation value of each dimension includes:

[0161] Among the plurality of second dimension difference values, determining the largest second dimension difference value as the second dimension difference extreme value;

[0162] respectively calculating the ratios of the plurality of second dimension difference values ​​to the second dimension difference extreme values ​​to obtain a plurality of second dimension difference indexes;

[0163] According to the plurality of second dimension difference indices, a plurality of second dimension similarity indices corresponding one-to-one to the plurality of second dimension difference indices are obtained, wherein the sum of the second dimension similarity index and the corresponding second dimension difference index is 1;

[0164] The second correlation value of each dimension is used as a weight to perform weighted calculation on the multiple second dimension similarity indexes to obtain the data similarity probability between the current time period and the target second time period.

[0165] For example, the data similarity probability between the current time period and the target first time period is It can be expressed as:

[0166]

[0167] in, is the first correlation value of the rth dimension among multiple dimensions, Represents a normalized function (such as the maximum and minimum normalization method for function processing), Indicates the difference in the first dimension between the current time period and the target first time period in the rth dimension. Indicates the largest first dimension difference value among multiple first dimension difference values ​​corresponding to multiple dimensions between the current time period and the target first time period. Indicates the first dimension difference index corresponding to the rth dimension between the current time period and the target first time period, It represents the similarity index of the first dimension corresponding to the rth dimension between the current time period and the target first time period, and R represents the total number of dimensions of multiple dimensions.

[0168] Step S3: Correct the initial adjustment interval according to the first probability and the second probability to obtain a corrected adjustment interval.

[0169] The adjustment interval is used to indicate the duration of the operation interval between two adjacent PID adjustment operations performed by the centrifuge.

[0170] The above initial adjustment interval can be understood as the maximum operation interval between two adjacent PID adjustment operations of the centrifuge, for example: 100ms.

[0171] Specifically, the correcting the initial adjustment interval according to the first probability and the second probability to obtain a corrected adjustment interval includes:

[0172] Taking the larger of the first probability and the second probability to obtain an extreme value probability;

[0173] Transforming the extreme value probability to obtain a correction coefficient, wherein the sum of the correction coefficient and the extreme value probability is 1;

[0174] The product of the correction coefficient and the initial adjustment interval is calculated to obtain the corrected adjustment interval.

[0175] For example, the modified adjustment interval It can be expressed as:

[0176]

[0177] in, Indicates the initial adjustment interval, represents the first probability, represents the second probability, represents the extreme value probability.

[0178] Based on the above settings, when the operating conditions in the current time period show that the target speed (such as the drum target speed or the propeller target speed) has a high probability of entering a transition phase, the adjustment interval can be adaptively shortened to adapt to the high-frequency calibration requirements of the target speed during the transition process, so as to improve the control efficiency and control accuracy of the PID during the target speed transition process. When the operating conditions in the current time period show that the probability of the target speed entering a transition phase is low, the adjustment interval can be adaptively increased to adapt to the smooth control requirements of the target speed during the non-transition phase, thereby reducing resource overhead and suppressing the interference of fine-tuning noise.

[0179] Step S4: performing PID control on the drum speed and the propeller speed of the centrifuge according to the corrected adjustment interval.

[0180] In the application, in order to avoid frequent adjustments to the adjustment interval and ensure the stability of PID control, it can be set that after completing a correction operation of the adjustment interval, at least a set waiting time interval must pass before the next adjustment check correction operation can be performed, wherein the set waiting time can be 5 minutes or 15 minutes, etc.

[0181] In general, the present invention determines a plurality of first time periods and a plurality of second time periods by analyzing the changes in the centrifuge drum speed and the propeller speed in a historical time period, that is, determines a plurality of time periods corresponding to the centrifuge drum target speed transition stage and a plurality of time steps corresponding to the centrifuge propeller target speed transition stage, and then analyzes the similarity between the target operation data of the centrifuge in the current time period and its historical operation data in the plurality of first time periods, and analyzes the similarity between the target operation data and the historical operation data of the centrifuge in the plurality of second time periods, determines the probability that the centrifuge drum target speed transition stage in the current time period, and determines the probability that the centrifuge propeller target speed transition stage The probability that the speed will change stages in the current time period is calculated, and the adjustment interval is corrected accordingly. Then, based on the corrected adjustment interval, PID control is performed on the drum speed and the propeller speed of the centrifuge to adapt to the situation where the PID control intervals of the centrifuge in different working stages are different. This can dynamically reduce the frequency of sampling operations and adjustment operations associated with PID control when the target speed of the centrifuge remains stable, thereby reducing system resource consumption and control disturbances; and dynamically increase the frequency of sampling operations and adjustment operations associated with PID control when the target speed of the centrifuge fluctuates, so as to facilitate fast and accurate speed regulation, and ultimately enable the centrifuge to obtain better speed regulation effect.

[0182] The present invention proposes a rotation speed calibration system for a centrifuge, see Figure 2 , which shows a structural diagram of a centrifuge speed calibration system 200 provided by one embodiment of the present invention, the system comprising:

[0183] a historical analysis module 201 for analyzing changes in the centrifuge drum speed and propeller speed within a historical time period to determine a plurality of first time periods and a plurality of second time periods, wherein the first time periods are used to indicate historical operating periods during which the centrifuge drum was subjected to a target speed transition, and the second time periods are used to indicate historical operating periods during which the propeller was subjected to a target speed transition;

[0184] The real-time analysis module 202 is configured to analyze the similarity between the target operating data of the centrifuge in the current time period and a plurality of first historical operating data of the centrifuge in a plurality of first time periods to obtain a first probability; and to analyze the similarity between the target operating data of the centrifuge in the current time period and a plurality of second historical operating data of the centrifuge in a plurality of second time periods to obtain a second probability, wherein the first probability represents the probability that the target speed of the centrifuge drum changes phases in the current time period, and the second probability represents the probability that the target speed of the centrifuge propeller changes phases in the current time period;

[0185] An interval correction module 203 is configured to correct the initial adjustment interval according to the first probability and the second probability to obtain a corrected adjustment interval, wherein the adjustment interval is used to indicate the duration of an operation interval between two adjacent PID adjustment operations performed by the centrifuge;

[0186] The speed control module 204 is configured to perform PID control on the drum speed and the propeller speed of the centrifuge according to the corrected adjustment interval.

[0187] It should be noted that the system provided in the above embodiment is merely illustrative of the division of the aforementioned functional modules. In actual applications, the aforementioned functions can be assigned to different functional modules as needed, i.e., the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above. Furthermore, the above embodiment provides a centrifuge speed calibration system and a centrifuge speed calibration method, each of which is conceptually similar. The specific implementation process is detailed in the method embodiment and will not be further elaborated here.

[0188] The embodiment of the present invention also provides an electronic device. Figure 3 , the electronic device may include a processor 301, a memory 302, and a program 3021 stored in the memory 302 and executable on the processor 301.

[0189] When the program 3021 is executed by the processor 301, it can achieve Figure 1 Any steps in the corresponding method embodiments and achieving the same beneficial effects will not be repeated here.

[0190] Those skilled in the art will appreciate that all or part of the steps of implementing the above-described embodiment method may be accomplished through hardware associated with program instructions, and the program may be stored in a readable medium.

[0191] The embodiment of the present invention further provides a readable storage medium, wherein the readable storage medium stores a computer program, and when the computer program is executed by a processor, the above Figure 1Any steps in the corresponding method embodiments can achieve the same technical effects and will not be described again here to avoid repetition.

[0192] The computer-readable storage medium of the embodiments of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or component.

[0193] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0194] The program code contained on the storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0195] Computer program code for performing the operations of the present invention may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or terminal. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0196] An embodiment of the present invention further provides a computer program product. When the computer program product is run on a computer, the computer is caused to execute the above-mentioned related steps to implement a rotation speed calibration method for a centrifuge provided in the above embodiment.

[0197] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0198] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A method for calibrating the rotational speed of a centrifuge, characterized in that: The method comprises: Analyzing changes in the centrifuge drum speed and propeller speed over a historical time period to determine a plurality of first time periods and a plurality of second time periods, wherein the first time periods are used to indicate historical operating time periods during which the centrifuge drum was switched to a target speed, and the second time periods are used to indicate historical operating time periods during which the propeller was switched to a target speed; Analyzing the similarity between the target operating data of the centrifuge in the current time period and a plurality of first historical operating data thereof in a plurality of first time periods to obtain a first probability; and analyzing the similarity between the target operating data of the centrifuge in the current time period and a plurality of second historical operating data thereof in a plurality of second time periods to obtain a second probability, wherein the first probability represents a probability that the target speed of the centrifuge drum changes phases in the current time period, and the second probability represents a probability that the target speed of the centrifuge propeller changes phases in the current time period; Correcting the initial adjustment interval according to the first probability and the second probability to obtain a corrected adjustment interval, wherein the adjustment interval is used to indicate the duration of an operation interval between two adjacent PID adjustment operations performed by the centrifuge; According to the corrected adjustment interval, PID control is performed on the drum speed and the propeller speed of the centrifuge.

2. The method for calibrating the rotational speed of a centrifuge according to claim 1, wherein: The analyzing of the changes in the centrifuge drum speed and the propeller speed within the historical time period to determine a plurality of first time periods and a plurality of second time periods includes: Analyzing the degree of change and the degree of dispersion of multiple drum speeds of the centrifuge in a historical time period to obtain a plurality of first segmented probabilities corresponding to the plurality of historical moments, and analyzing the degree of change and the degree of dispersion of multiple propeller speeds of the centrifuge in a historical time period to obtain a plurality of second segmented probabilities corresponding to the plurality of historical moments; Among the multiple historical moments, the larger one between the first segment probability and the second segment probability of each historical moment is determined as the moment segment probability of the historical moment, so as to obtain multiple moment segment probabilities; Among the multiple moment segment probabilities, all moment segment probabilities that are greater than or equal to the probability threshold are determined as target segment probabilities; The multiple target segmentation probabilities are divided into time periods according to the multiple historical moments to obtain the multiple first time periods and the multiple second time periods.

3. The method for calibrating the rotational speed of a centrifuge according to claim 2, wherein: The analysis of the change degree and discrete degree of the multiple drum speeds of the centrifuge in the historical time period to obtain multiple first segmented probabilities corresponding to multiple historical moments includes: Calculating the ratio of the drum variation value and the drum discrete value of the centrifuge at each historical moment to obtain a plurality of first segmented probabilities, wherein the drum variation value is a first-order difference value of the target drum speed of the centrifuge at the corresponding historical moment, and the drum discrete value is a standard deviation corresponding to the actual drum speed of the centrifuge at the corresponding historical moment; Analyzing the degree of change and discreteness of the rotational speeds of multiple propellers of the centrifuge in a historical time period to obtain multiple second segmented probabilities corresponding to the multiple historical moments, including: The ratio of the propeller change value and the propeller discrete value of the centrifuge at each historical moment is calculated to obtain multiple second segmented probabilities, wherein the propeller change value is the first-order difference value of the target speed of the propeller of the centrifuge at the corresponding historical moment, and the propeller discrete value is the standard deviation corresponding to the actual speed of the propeller of the centrifuge at the corresponding historical moment.

4. The method for calibrating the rotational speed of a centrifuge according to claim 2, wherein: The step of dividing the time periods according to the multiple historical moments at which the multiple target segmentation probabilities are located to obtain the multiple first time periods and the multiple second time periods includes: Divide the time period according to the multiple historical moments where the multiple target segmentation probabilities are located to obtain multiple candidate time periods; Distinguishing the plurality of candidate time periods based on a preset differentiation rule to determine the plurality of first time periods and the plurality of second time periods; The differentiation rules include: When the first segment probability of the last historical moment of the candidate time period is greater than or equal to the second segment probability, the candidate time period is determined as the first time period; When the first segment probability of the last historical moment of the candidate time period is less than the second segment probability, the candidate time period is determined as the second time period.

5. The method for calibrating the rotational speed of a centrifuge according to claim 1, wherein: The first probability is obtained by analyzing the similarity between the target operating data of the centrifuge in the current time period and the plurality of first historical operating data in the plurality of first time periods, including: Under each dimension, calculating the degree of difference between the target operating data and the first historical operating data of the target first time period to obtain a plurality of first dimension difference values, wherein the target first time period is any first time period among the plurality of first time periods; Obtaining a data similarity probability between the current time period and the target first time period based on the multiple first dimension difference values ​​and the first correlation value of each dimension, wherein the first correlation value is used to indicate a degree of correlation between the data of the corresponding dimension and the drum speed; Among a plurality of data similarity probabilities between the current time period and a plurality of first time periods, determining the greatest data similarity probability as the first probability; The second probability is obtained by analyzing the similarity between the target operating data of the centrifuge in the current time period and a plurality of second historical operating data in a plurality of second time periods, including: Under each dimension, calculating the degree of difference between the target operating data and the second historical operating data of the target second time period to obtain a plurality of second dimension difference values, wherein the target second time period is any second time period among the plurality of second time periods; Obtaining a data similarity probability between the current time period and the target second time period based on the plurality of second dimension difference values ​​and a second correlation value of each dimension, wherein the second correlation value is used to indicate a degree of correlation between the data of the corresponding dimension and the propeller speed; Among a plurality of data similarity probabilities between the current time period and a plurality of second time periods, the greatest data similarity probability is determined as the second probability.

6. The method for calibrating the rotational speed of a centrifuge according to claim 5, wherein: The steps for obtaining the first relevant value of each dimension include: Acquire a plurality of first feature data and a plurality of first target changes, wherein the plurality of first feature data correspond one-to-one to the plurality of first time periods, the first feature data is used to represent data features of first historical operating data corresponding to the first time period in a target dimension, the target dimension being any one of the plurality of dimensions, the plurality of first target changes correspond one-to-one to the plurality of first time periods, and the first target change is a change in the target speed of the drum at the last historical moment of the corresponding first time period; Performing correlation analysis on the plurality of first feature data and the plurality of first target variation amounts to obtain a first correlation value of the target dimension; The steps for obtaining the second related value of each dimension include: Acquire a plurality of second characteristic data and a plurality of second target changes, wherein the plurality of second characteristic data correspond one-to-one to the plurality of second time periods, the second characteristic data are used to represent data characteristics of the second historical operating data in the target dimension for the corresponding second time period, the plurality of second target changes correspond one-to-one to the plurality of second time periods, and the second target change is a change in the target speed of the propeller at the last historical moment of the corresponding second time period; Correlation analysis is performed on the plurality of second feature data and the plurality of second target variations to obtain a second correlation value of the target dimension.

7. The method for calibrating the rotational speed of a centrifuge according to claim 5, wherein: Obtaining a data similarity probability between the current time period and the target first time period based on the multiple first dimension difference values ​​and the first correlation value of each dimension includes: Among the plurality of first dimension difference values, determining the largest first dimension difference value as the first dimension difference extreme value; respectively calculating the ratios of the plurality of first dimension difference values ​​to the first dimension difference extreme values ​​to obtain a plurality of first dimension difference indexes; According to the plurality of first dimension difference indices, a plurality of first dimension similarity indices corresponding one to one with the plurality of first dimension difference indices are obtained, wherein the sum of the first dimension similarity index and the corresponding first dimension difference index is 1; Using the first correlation value of each dimension as a weight, weighted calculation is performed on the multiple first dimension similarity indexes to obtain the data similarity probability between the current time period and the target first time period; Obtaining a data similarity probability between the current time period and the target second time period based on the multiple second dimension difference values ​​and the second correlation value of each dimension includes: Among the plurality of second dimension difference values, determining the largest second dimension difference value as the second dimension difference extreme value; respectively calculating the ratios of the plurality of second dimension difference values ​​to the second dimension difference extreme values ​​to obtain a plurality of second dimension difference indexes; According to the plurality of second dimension difference indices, a plurality of second dimension similarity indices corresponding one-to-one to the plurality of second dimension difference indices are obtained, wherein the sum of the second dimension similarity index and the corresponding second dimension difference index is 1; The second correlation value of each dimension is used as a weight to perform weighted calculation on the multiple second dimension similarity indexes to obtain the data similarity probability between the current time period and the target second time period.

8. The method for calibrating the rotational speed of a centrifuge according to claim 6, wherein: The first feature data includes a plurality of first feature sub-data corresponding to a plurality of feature categories, and the second feature data includes a plurality of second feature sub-data corresponding to the plurality of feature categories; The performing correlation analysis on the plurality of first feature data and the plurality of first target variation amounts to obtain the first correlation value of the target dimension includes: Performing correlation analysis on a plurality of first feature sub-data corresponding to each feature category and a plurality of first target variation amounts to obtain a first candidate correlation value corresponding to each feature category; Determining the largest first candidate correlation value among multiple first candidate correlation values ​​corresponding to multiple feature categories as the first correlation value; The performing correlation analysis on the plurality of second feature data and the plurality of second target variation amounts to obtain the second correlation value of the target dimension includes: Performing correlation analysis on the plurality of second feature sub-data corresponding to each feature category and the plurality of second target variation amounts to obtain a second candidate correlation value corresponding to each feature category; Among multiple second candidate correlation values ​​corresponding to multiple feature categories, the largest second candidate correlation value is determined as the second correlation value.

9. The method for calibrating the rotational speed of a centrifuge according to claim 1, wherein: The step of correcting the initial adjustment interval according to the first probability and the second probability to obtain a corrected adjustment interval includes: Taking the larger of the first probability and the second probability to obtain an extreme value probability; Transforming the extreme value probability to obtain a correction coefficient, wherein the sum of the correction coefficient and the extreme value probability is 1; The product of the correction coefficient and the initial adjustment interval is calculated to obtain the corrected adjustment interval.

10. A rotation speed calibration system for a centrifuge, characterized in that: The system comprises: a historical analysis module, configured to analyze changes in the centrifuge drum speed and propeller speed within a historical time period to determine a plurality of first time periods and a plurality of second time periods, wherein the first time periods are used to indicate historical operating time periods during which the centrifuge drum was subjected to a target speed transition, and the second time periods are used to indicate historical operating time periods during which the propeller was subjected to a target speed transition; a real-time analysis module configured to analyze a degree of similarity between target operating data of the centrifuge in a current time period and a plurality of first historical operating data thereof in a plurality of first time periods to obtain a first probability; and to analyze a degree of similarity between target operating data of the centrifuge in the current time period and a plurality of second historical operating data thereof in a plurality of second time periods to obtain a second probability, wherein the first probability represents a probability that the target speed of the centrifuge drum changes phases in the current time period, and the second probability represents a probability that the target speed of the centrifuge propeller changes phases in the current time period; an interval correction module, configured to correct an initial adjustment interval according to the first probability and the second probability to obtain a corrected adjustment interval, wherein the adjustment interval is used to indicate a duration of an operation interval between two adjacent PID adjustment operations performed by the centrifuge; The speed control module is used to perform PID control on the drum speed and the propeller speed of the centrifuge according to the corrected adjustment interval.

Images