Quantitative pump precision evaluation method based on servo motor driven quantitative pump

Abstract

The invention relates to the field of precision evaluation of constant delivery pumps, in particular to a constant delivery pump precision evaluation method based on a servo motor driven constant delivery pump, which comprises the following steps of: continuously sampling flow output of the servo motor driven constant delivery pump, constructing flow time sequence data, and performing window division to obtain a constant delivery pump flow time sequence data window; acquiring a bubble disturbance evaluation factor at a target moment according to the bubble disturbance structural characteristics in the flow time sequence data window of the constant delivery pump and the output characteristics of the constant delivery pump under the current working condition; according to the fluctuation difference of the head area and the tail area in the flow time sequence data window of the constant delivery pump and the bubble disturbance evaluation factor at the target moment, the bubble disturbance degree of the constant delivery pump at the target moment is obtained; and utilizing the bubble disturbance degree of the constant delivery pump at the target moment to optimize the error index of the flow time sequence data of the constant delivery pump, and correspondingly obtaining a dynamic precision evaluation result capable of reflecting the bubble disturbance influence, thereby improving the precision evaluation precision of the constant delivery pump.

Description

Technical Field

[0001] The present invention relates to the field of quantitative pump accuracy assessment, and in particular to a quantitative pump accuracy assessment method based on a servo motor driven quantitative pump. Background Art

[0002] With the continuous development of servo control technology and intelligent manufacturing systems, servo motor-driven metering pumps are widely used in high-precision liquid delivery scenarios, such as pharmaceutical liquid filling, high-purity chemical reagent ratio, fine chemical process control and other fields. The coordination of metering pumps and servo motors can achieve high-precision control of fluid output volume, which is especially suitable for production lines with extremely low tolerance for unit filling errors. Compared with traditional pneumatic or open-loop motor drive systems, servo systems have high responsiveness and strong robustness, and can dynamically adjust the output flow through closed-loop feedback, greatly improving the control performance of the system. In the filling system, the time for a metering pump to complete a filling cycle is usually hundreds of milliseconds. The system needs to monitor the output flow in real time and use this as the basis for evaluating control accuracy and abnormality identification. To this end, building a reasonable filling accuracy evaluation method has become a key link in achieving high-quality manufacturing.

[0003] The accuracy evaluation method commonly used in current filling systems is the instantaneous flow error identification algorithm based on a sliding window. This algorithm mainly compares the real-time flow data sequence with the target filling rate model, evaluates the size and change trend of the instantaneous error in a small time window, and identifies potential output instability behavior. The basic process is as follows: First, the system obtains instantaneous flow data with high-frequency sampling (such as 1kHz) during the filling cycle to form a complete flow time series; then, the sequence is traversed frame by frame through a sliding window, and the error between the current flow value and the target flow model is calculated in each window (such as using mean square error, maximum absolute error, etc.). The calculation result is used to identify whether there is an abnormal fluctuation that deviates from the target model in the current window. If the error of multiple consecutive windows exceeds the preset threshold, it is marked as a "potential accuracy abnormal filling cycle". This algorithm has the advantages of simple implementation and fast response in the control system, and can make a preliminary structured judgment on the flow behavior within the cycle. Therefore, it is widely used in the fast accuracy evaluation module in industrial quantitative pump systems.

[0004] In the actual application scenarios of servo motor driven quantitative pumps, especially in the process of high-speed and high-frequency quantitative filling of liquids, the transient disturbance of the pump working state is closely related to the liquid flow behavior. Because there may be liquid disturbances, residual gas in the pipeline, pressure fluctuations or switching lag at the suction end of the pump, bubbles are mixed into the fluid circuit. This bubble disturbance will destroy the original flow stability, which manifests as instantaneous flow collapse, rebound reflux, micro-periodic oscillation and other phenomena during the filling process.

[0005] However, the existing quantitative pump accuracy assessment methods mainly rely on error statistics (such as mean square error, maximum error) within the sliding window for static judgment, and lack the ability to identify dynamic disturbance behaviors in flow time series, especially when the disturbance duration is short and the overall filling volume is still within a reasonable range, it is impossible to identify hidden structural errors. More seriously, there may be a large number of non-bubble disturbance behaviors in the system (such as pressure disturbances caused by suction reversal, pump control beat gap rebound, liquid transient compression, etc.). These behaviors may be similar to bubble disturbances in terms of flow change morphology, but they do not affect the actual accuracy of the pump body in essence, and are easily misjudged as abnormal by existing methods, resulting in distorted accuracy assessment.

[0006] Therefore, how to effectively identify the bubble disturbance behavior in the flow time series during the filling process of the metering pump, accurately distinguish between real disturbance and non-disturbance behavior, and reasonably introduce the disturbance characteristics into the accuracy evaluation process, so as to construct a metering pump accuracy evaluation method with dynamic recognition ability, strong scene adaptability and reliable evaluation results, has become an important problem that needs to be solved urgently in current technology. Summary of the invention

[0007] In view of this, an embodiment of the present invention provides a method for evaluating the accuracy of a metering pump driven by a servo motor, so as to solve the problem of inaccurate accuracy evaluation caused by bubble disturbance during the accuracy evaluation process of the metering pump driven by a servo motor.

[0008] In an embodiment of the present invention, a method for evaluating the accuracy of a quantitative pump driven by a servo motor is provided, the method comprising the following steps: By continuously sampling the flow output of the quantitative pump driven by the servo motor, flow time series data for evaluating the accuracy of the quantitative pump is constructed, and the flow time series data is divided into windows to obtain the flow time series data window of the quantitative pump; According to the bubble disturbance structural characteristics in the flow time series data window of the metering pump and the output characteristics of the metering pump under the current working condition, the bubble disturbance evaluation factor at the target time is obtained; According to the fluctuation difference between the head and tail areas in the flow time series data window of the metering pump and the bubble disturbance evaluation factor at the target moment, the bubble disturbance degree of the metering pump at the target moment is obtained; The error index of the flow time series data of the metering pump is optimized by using the bubble disturbance degree of the metering pump at the target time, and a dynamic accuracy evaluation result that can reflect the influence of the bubble disturbance is obtained accordingly.

[0009] Preferably, the step of obtaining the bubble disturbance evaluation factor at the target time according to the bubble disturbance structural characteristics in the flow time series data window of the metering pump and the output characteristics of the metering pump under the current working condition comprises: By performing least-squares fitting on the time-series data window of the quantitative pump flow rate at the target moment, the trend performance equation at the target moment is obtained, and the difference between the prediction result of the trend performance equation at the target moment and the monitored data of the quantitative pump flow rate at the target moment is used as the trend deviation evaluation at the target moment; the calculation result of dividing the trend deviation evaluation at the target moment by the flow rate mean of the time-series data window of the quantitative pump flow rate at the target moment is used as the trend deviation degree at the target moment. By performing cumulative difference evaluation on the flow rate change data in the time-series data window of the quantitative pump flow rate at the target moment, the local collapse intensity at the target moment is obtained. By performing cumulative evaluation of the change speed on the flow rate change information in the time-series data window of the quantitative pump flow rate at the target moment, the disturbance diffusion inertia evaluation at the target moment is obtained. By performing non-linear compression fusion analysis on the trend deviation degree, local collapse intensity, and disturbance diffusion inertia evaluation at the target moment, the bubble disturbance evaluation factor at the target moment is obtained.

[0010] Preferably, the step of obtaining the local collapse intensity at the target moment by performing cumulative difference evaluation on the flow rate change data in the time-series data window of the quantitative pump flow rate at the target moment includes: For the time-series data window of the quantitative pump flow rate at the target moment, starting from the flow rate data at the second moment in this time-series data window, the calculation result of subtracting the flow rate data at each moment from the flow rate data at the previous moment is used as the flow rate difference evaluation at this moment; for any moment in the time-series data window of the quantitative pump flow rate at the target moment, if the flow rate difference evaluation at this moment is less than 0, then the flow rate difference evaluation at this moment is used as the downward amplitude evaluation at this moment, otherwise the value 0 is used as the downward amplitude evaluation at this moment; the calculation result of adding up the downward amplitude evaluations at all moments in the time-series data window of the quantitative pump flow rate at the target moment is used as the local collapse intensity at the target moment.

[0011] Preferably, the step of obtaining the disturbance diffusion inertia evaluation at the target moment by performing cumulative evaluation of the change speed on the flow rate change information in the time-series data window of the quantitative pump flow rate at the target moment includes: For the flow rate difference evaluation at each moment in the time-series data window of the quantitative pump flow rate at the target moment, starting from the third moment, the absolute value of the calculation result of subtracting the flow rate difference evaluation at each moment from the flow rate difference evaluation at the previous moment is used as the flow rate change rate difference evaluation at this moment; the mean value of all the flow rate change rate difference evaluations in the time-series data window of the quantitative pump flow rate at the target moment is used as the disturbance diffusion inertia evaluation at the target moment.

[0012] Preferably, the non-linear compression fusion analysis of the trend deviation degree, local collapse intensity and disturbance diffusion inertia evaluation at the target moment to obtain the bubble disturbance evaluation factor at the target moment includes: Obtain the trend deviation degree, local collapse intensity and disturbance diffusion inertia evaluation at the target moment; Take the calculation results of adding 1 to the trend deviation degree, local collapse intensity and disturbance diffusion inertia evaluation at the target moment respectively and performing logarithmic mapping as the first evaluation factor, the second evaluation factor and the third evaluation factor at the target moment; Take the calculation result of multiplying the first evaluation factor, the second evaluation factor and the third evaluation factor at the target moment as the numerator, and take the square of the calculation result of adding the flow mean value of the quantitative pump flow time series data window at the target moment and a set minimum positive number as the denominator, and form a fraction as the first bubble disturbance evaluation factor at the target moment; Take the linear normalization mapping result of the first bubble disturbance evaluation factor at the target moment as the bubble disturbance evaluation factor at the target moment.

[0013] Preferably, obtaining the quantitative pump bubble disturbance degree at the target moment according to the fluctuation difference between the head and tail regions in the quantitative pump flow time series data window and the bubble disturbance evaluation factor at the target moment includes: Obtain the second-order difference data of the quantitative pump flow time series data window at the target moment. For the second-order difference data at any moment in the quantitative pump flow time series data window at the target moment, use it as the disturbance intensity weight at that moment; In the quantitative pump flow time series data window at the target moment, take the data point with the highest disturbance intensity weight as the disturbance center estimation point at the target moment; Take the number of data points in half of the window length of the local area of the disturbance center estimation point at the target moment as the disturbance center area at the target moment; take the area to the left of the disturbance center area in the quantitative pump flow time series data window at the target moment as the head area at the target moment; take the area to the right of the disturbance center area in the quantitative pump flow time series data window at the target moment as the tail area at the target moment; Obtain the quantitative pump bubble disturbance degree at the target moment through the fluctuation difference evaluation between the head area and the tail area at the target moment and the bubble disturbance evaluation factor at the target moment.

[0014] Preferably, obtaining the quantitative pump bubble disturbance degree at the target moment through the fluctuation difference evaluation between the head area and the tail area at the target moment and the bubble disturbance evaluation factor at the target moment includes: Obtain the set smoothing adjustment factor; use the calculation result of subtracting the numerical variance of the head region at the target moment from the numerical variance of the tail region at the target moment as the fluctuation difference evaluation between the head region and the tail region at the target moment; Use the maximum value between the fluctuation difference evaluation between the head region and the tail region at the target moment and the constant 0 as the first confidence evaluation factor at the target moment; Use the calculation result of multiplying the first confidence evaluation factor at the target moment by the set smoothing adjustment factor and taking the negative value as the second confidence evaluation factor at the target moment; Perform an exponential mapping with the natural constant as the base on the second confidence evaluation factor at the target moment, and use the corresponding exponential mapping result as the bubble perturbation confidence optimization factor at the target moment; Use the calculation result of multiplying the bubble perturbation confidence optimization factor at the target moment by the bubble perturbation evaluation factor at the target moment as the quantitative pump bubble perturbation degree at the target moment.

[0015] Preferably, use the calculation result of subtracting the numerical variance of the head region at the target moment from the numerical variance of the tail region at the target moment as the fluctuation difference evaluation between the head region and the tail region at the target moment, where if there are no data points in the head region or the tail region at the target moment, set the numerical variance of this region to 0.

[0016] Preferably, use the quantitative pump bubble perturbation degree at the target moment to optimize the error index of the quantitative pump flow time series data, and correspondingly obtain a dynamic accuracy evaluation result that can reflect the influence of bubble perturbation, including: Obtain the set error threshold for quantitative pump accuracy evaluation; obtain the reference target flow value set by the quantitative pump working system; use the calculation result of adding the quantitative pump bubble perturbation degree at the target moment to the constant 1 as the error evaluation optimization weight at the target moment; For any moment in the quantitative pump flow time series data window at the target moment, use the square of the difference between the actual flow monitoring value at this moment and the reference target flow value at this moment as the first error evaluation at this moment, weight the first error evaluation at this moment through the error evaluation optimization weight at this moment, and use the corresponding calculation result as the second error evaluation at this moment; use the mean value of the second error evaluations of all moments in the quantitative pump flow time series data window at the target moment as the error optimization evaluation at the target moment; Compare the error optimization evaluation at the target moment with the error threshold to obtain a dynamic accuracy evaluation result that can reflect the influence of bubble perturbation.

[0017] Preferably, comparing the error optimization evaluation at the target moment with the error threshold to obtain a dynamic accuracy evaluation result that can reflect the influence of bubble disturbance, including: Obtain the first error threshold and the second error threshold in the error threshold; if the error optimization evaluation at the target moment is less than the first error threshold, it is considered that the current metering pump is operating stably and in a high-precision state; If the error optimization evaluation at the target moment is greater than or equal to the first error threshold and less than the second error threshold, it is considered that there is a medium degree of disturbance in the current metering pump operation process and it is in a medium-precision state; If the error optimization evaluation at the target moment is greater than or equal to the second error threshold, it is considered that there is a strong disturbance in the current metering pump operation process and it is in a low-precision state.

[0018] The beneficial effects of the embodiments of the present invention compared with the prior art are as follows: This technical solution constructs a two-layer optimization mechanism for bubble disturbance recognition and credibility evaluation, combines the flow time series data characteristics of the servo motor-driven metering pump in the actual filling process, and proposes a precision dynamic evaluation method with the ability to extract disturbance structures and identify pseudo-disturbances. The bubble disturbance evaluation factor is used to sensitively identify the bubble disturbance behavior, and the bubble disturbance confidence optimization factor is combined to correct the credibility of the recovery trend of non-bubble disturbances such as commutation. Further, a disturbance scoring adjustment mechanism is introduced in the error evaluation, enabling the system to accurately distinguish real disturbances from non-disturbance fluctuations and effectively improving the accuracy of precision evaluation. This method has the characteristics of strong real-time performance, simple deployment, and high adaptability, and is especially suitable for the dynamic recognition and quality control of filling abnormal behaviors in high-frequency and high-precision liquid metering pump control systems. Description of the Drawings

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0020] Figure 1 It is a method flow chart of a metering pump accuracy evaluation method based on a servo motor-driven metering pump provided in Embodiment 1 of the present invention. Detailed Embodiments

[0021] The following will describe in detail the embodiments of the present disclosure, and the examples of the embodiments are shown in the drawings. The embodiments described below with reference to the drawings are exemplary and are intended to explain the present disclosure and should not be construed as a limitation of the present disclosure.

[0022] It should be noted that the terms "first", "second", etc. in the specification of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described here can be implemented in an order other than those illustrated or described here. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. On the contrary, they are only examples of devices and methods consistent with some aspects of the present disclosure.

[0023] In order to illustrate the technical solution of the present invention, specific embodiments will be used for illustration below.

[0024] See Figure 1 , which is a method flow chart of a quantitative pump accuracy evaluation method based on a servo motor-driven quantitative pump provided in the first embodiment of the present invention. As Figure 1 shown, the method may include: Step S1, by continuously sampling the flow output of the servo motor-driven quantitative pump, constructing flow time series data for quantitative pump accuracy evaluation, and dividing the flow time series data into windows to obtain a quantitative pump flow time series data window.

[0025] In order to identify and evaluate the dynamic behavior of the servo motor-driven quantitative pump during the working process, it is necessary to first establish a time series data acquisition mechanism based on flow monitoring. This step samples the real-time flow output in the pump control system to construct a continuous flow monitoring data sequence, providing data support for subsequent disturbance identification and error modeling.

[0026] Specifically, in the quantitative pump control system, the sampling end obtains the instantaneous flow output value of the servo motor-controlled pump head in each filling cycle through a flow sensor, and performs continuous sampling at a set frequency to form the original flow time series data. The sampling frequency can be set according to the pump control cycle and fluid characteristics, preferably 100Hz - 500Hz, to ensure the ability to capture micro-disturbance processes.

[0027] For the obtained quantitative pump flow time series data, set the sliding window length , and obtain the sliding window of the flow time series according to the sliding window length. For the quantitative pump flow time series data at time, its corresponding time series data window is: Among them, represents the flow time series data window from time to ; represents the The instantaneous flow rate value at a sampling moment, with the unit of ; Indicates the sliding window length, with the unit of the number of sampling points.

[0028] It should be noted that since this method needs to be deployed in a real-time control system, the judgment at any moment must be based on current and historical data. Therefore, this window adopts a causal structure, that is, a flow time series data window is formed by the data before the current moment, so as to ensure that the entire feature extraction process meets the requirements of real-time determination.

[0029] So far, through continuous sampling of the flow rate output of the servo motor-driven metering pump, flow time series data for the accuracy evaluation of the metering pump is constructed, and the flow time series data is windowed to obtain the flow time series data window of the metering pump.

[0030] Step S2, according to the bubble disturbance structural characteristics in the flow time series data window of the metering pump and the output characteristics of the metering pump under the current working conditions, obtain the bubble disturbance evaluation factor at the target moment.

[0031] Traditional sliding window error evaluation algorithms generally use static statistics (such as mean square error or maximum absolute error) to evaluate the flow error within the window, without considering the evolution trend and dynamic structure of the error value over time, resulting in the inability to effectively identify the "instantaneous collapse and compensatory recovery" type of disturbance phenomenon caused by bubbles entering the fluid circuit. This phenomenon is particularly common when using plunger or diaphragm metering pumps to handle low-viscosity liquids. If not addressed, it will directly affect the real-time accuracy evaluation and control feedback response of the metering pump.

[0032] In order to achieve targeted modeling and detection of this problem, the present invention extracts three-stage characteristics from the physical evolution process of bubble disturbance: namely, trend deviation, collapse formation, and disturbance diffusion, and constructs three sub-characteristics: trend deviation rate (TDR), local collapse slope (LGF), and disturbance inertia change degree (DIC). Different from the traditional inorganic combination method of simply weighting and summing multiple characteristics, the present invention forms a logical closed-loop model for the above three characteristics in the physical evolution order of "trend deviation trigger → flow collapse expansion → disturbance diffusion intensification" by constructing a structure-dependent functional relationship, forming a disturbance scoring function with semantic consistency and behavioral integrity. The finally obtained bubble disturbance evaluation factor can output in real time whether there is a bubble disturbance behavior within the current sliding window and the continuity evaluation result of the disturbance intensity, and has a high degree of scene binding and problem uniqueness.

[0033] During the actual pumping process, when bubbles are introduced into the fluid circuit, their disturbance occurs gradually, not instantaneously. The specific behavior is as follows: 1. Instantaneous collapse: Since the bubbles are sucked in by the pump instead of the liquid, the volume of fluid output per unit time suddenly decreases, resulting in a short-term drop in flow rate. 2. Overshoot during recovery: After the system detects a flow deviation, it immediately compensates. However, due to inertia or overshoot response of the controller, there is often a short-term compensatory overshoot increase. 3. Delayed stabilization: There may be slight oscillations or short-period rebounds before the flow returns to the stable state. This process as a whole forms an asymmetric combination of peaks and valleys on the time axis, first collapsing and then slightly overshooting and rising.

[0034] For the above scenarios, the present invention performs perturbation mode analysis through the following process to obtain a bubble perturbation evaluation factor for optimizing the error evaluation process of flow time series data.

[0035] After obtaining the flow time series data window of the metering pump, the trend deviation of the flow time series data window can be evaluated to determine trend anomalies. Specifically, by performing least squares fitting on the flow time series data window at the target moment, the trend performance equation at the target moment is obtained, and the difference between the prediction result of the trend performance equation at the target moment and the quantitative pump flow monitoring data at the target moment is used as the trend deviation evaluation at the target moment; the calculation result of dividing the trend deviation evaluation at the target moment by the flow mean value of the flow time series data window at the target moment is used as the degree of trend deviation at the target moment.

[0036] In one embodiment, for the calculation formula for the trend deviation rate of the flow monitoring data at the moment is: where, represents the trend deviation rate of the flow monitoring data at the th moment; represents the fitting trend prediction value at the moment; represents the actual monitored value of the instantaneous flow rate of the metering pump at the moment; represents the flow mean value in the flow time series data window ; represents a very small positive number used to prevent the denominator from being

[0037] It should be noted that when is significantly greater than When it is, it indicates that the current flow rate starts to deviate from the normal trend, which may be a precursor to an abnormal decrease in the local flow rate due to the entry of bubbles. The bubble disturbance initially manifests as a decrease in the flow rate after the metering pump inhales gas. Therefore, this step is used to pre-judge whether the flow rate has deviated from the expected trend, and it is a pre-trigger condition for subsequent disturbance determination. If there is no obvious deviation, the subsequent collapse analysis can be directly skipped, thus saving the system judgment cost.

[0038] After obtaining the trend deviation rate of the flow rate monitoring data, the preliminary determination in the process of bubble disturbance identification is completed. Then, further, the local collapse is identified. For the time series data window of the metering pump flow rate at the target time, starting from the flow rate data at the second moment in this time series data window, the calculation result of subtracting the flow rate data at each moment from the flow rate data at the previous moment is used as the flow rate difference evaluation at this moment; for any moment in the time series data window of the metering pump flow rate at the target time, if the flow rate difference evaluation at this moment is less than 0, then the flow rate difference evaluation at this moment is used as the decline amplitude evaluation at this moment, otherwise the value 0 is used as the decline amplitude evaluation at this moment; the calculation result of adding up the decline amplitude evaluations at all moments in the time series data window of the metering pump flow rate at the target time is used as the local collapse intensity at the target time.

[0039] In one embodiment, the formula for the local collapse intensity at the moment is: wherein, represents the local collapse intensity of the time series data of the metering pump flow rate at the th moment; represents the decline amplitude when a decline occurs; represents the instantaneous flow rate value of the metering pump at the th moment; represents the instantaneous flow rate value of the metering pump at the th moment; represents the absolute value calculation.

[0040] It should be noted that in the process of analyzing the bubble disturbance mode of the time series data of the metering pump flow rate, the trend deviation may be caused by random fluctuations and is not sufficient to prove the existence of disturbance. Therefore, only after the trend deviation, when there is a continuous decline process, can it be considered that the bubble disturbance is forming, so as to prevent misjudging normal fluctuations as abnormal behaviors. The evaluation of the local collapse intensity of the time series data of the metering pump flow rate is used to confirm the actual formation of the "collapse mode" and is the second key determination.

[0041] Since when there is bubble disturbance during the operation of a fixed-displacement pump, the bubble disturbance is often not static but further develops under pressure and the movement of the pump chamber, that is, the case of structural diffusion. Therefore, it is necessary to further evaluate the disturbance diffusion inertia in the time-series data of the fixed-displacement pump flow monitoring, so as to judge whether the disturbance continues to intensify. Specifically, for the evaluation of the flow difference at each moment in the time-series data window of the fixed-displacement pump flow at the target moment, starting from the third moment, the absolute value of the calculation result obtained by subtracting the evaluation of the flow difference at the previous moment from the evaluation of the flow difference at each moment is used as the evaluation of the flow change rate difference at that moment; the mean value of all the evaluations of the flow change rate differences in the time-series data window of the fixed-displacement pump flow at the target moment is used as the evaluation of the disturbance diffusion inertia at the target moment.

[0042] In one embodiment, the formula for evaluating the disturbance diffusion inertia at the th moment is: where represents the disturbance diffusion inertia at the th moment; represents the set length of the time-series data window of the flow rate; represents the local instantaneous flow change rate at the th moment; represents the local instantaneous flow change rate at the

[0043] th moment.

[0044] In one embodiment, the formula for the bubble disturbance evaluation factor at the in, Indicated in The bubble disturbance evaluation factor used for bubble disturbance pattern recognition at all times; Indicates The trend deviation rate of the flow monitoring data at each moment; Indicates The local collapse strength of the quantitative pump flow time series data at each moment; Indicates The inertia of disturbance diffusion at a moment; Indicates Logarithmic function with base ; Indicated in The mean of the instantaneous flow monitoring values ​​in the local window of the momentary flow time series data; Represents a very small positive number, used to prevent the denominator from being .

[0045] It should be noted that in the calculation formula of the bubble disturbance assessment factor, the numerator part is a stage-by-stage coupling logic formed by the product structure reaction disturbance. The numerator part is composed of three disturbance behavior indicators, namely, trend deviation rate , local collapse strength and disturbance diffusion inertia , the numerical stability and disturbance response sensitivity of these three sub-items are enhanced by logarithmic transformation. Specifically, each sub-item is The nonlinear compression of makes the bubble disturbance assessment factor sensitive to small disturbances and numerically suppresses large anomalies, avoiding the explosion of factor values ​​due to drastic changes in flow, and enhancing the stability of the precision assessment process. This processing method ensures that the output of the bubble disturbance assessment factor approaches 0 under normal filling conditions, and the factor output is gradually amplified in the continuous stage of typical bubble disturbance behavior. For the three sub-items after nonlinear compression, the common bubble disturbance mode is evaluated by multiplication. This structure reflects the continuous evolution chain of disturbance behavior from occurrence to accumulation and then to nonlinear enhancement, effectively highlighting structural disturbances rather than local noise. The mean of the instantaneous flow monitoring value in the denominator represents the basic output level of the quantitative pump under the current working conditions, which is used to convert the disturbance behavior into a relative intensity expression relative to the system operation state. In the high flow stage, the system is less sensitive to slight disturbances, and in the low flow stage, the system is more sensitive to the same absolute disturbance. Finally, the bubble disturbance assessment factor is mapped to the desired behavior response range through linear normalization, so that the output of the bubble disturbance assessment factor is more suitable for different application scenarios, namely different pump types, different liquids, different control accuracy levels, etc.

[0046] In this step, the bubble disturbance evaluation factor is introduced , significantly enhances the perception ability of the quantitative pump precision evaluation system for the bubble disturbance behavior in the fluid, and solves the "structural blind area" problem of the existing sliding window error evaluation method in the face of short-term non-linear dynamic disturbances. First, compared with the static error statistics method, the optimization factor can capture the sudden drop in flow rate caused by air bubbles mixing into the pump chamber through real-time structure analysis, and effectively avoid misjudging normal fluctuations as anomalies through the combined judgment of trend deviation, collapse continuity and disturbance inertia. Secondly, The output of can not only be used as an independent disturbance recognition result, but also further act on the weighted decision-making module in the error evaluation process, assign dynamic confidence to the error results within the disturbance window, and thus improve the robustness of the entire precision evaluation model under non-ideal working conditions.

[0047] In addition, the construction process of this optimization factor has clear engineering feasibility. All feature calculations are based on the collected flow rate data. The dependent quantization features are physically interpretable, do not introduce additional sensors or external model dependencies, and have good system integration capabilities. Finally, the optimization factor The introduction of not only realizes the quantitative recognition of bubble disturbance behavior and the suppression of error interference, but also provides a credible disturbance prior for the subsequent construction of a multi-step disturbance judgment and control feedback mechanism, thus laying a key foundation for the precision evaluation and robust control of the servo motor-driven quantitative pump.

[0048] So far, according to the structural characteristics of bubble disturbance in the quantitative pump flow rate time series data window and the output characteristics of the quantitative pump under the current working conditions, the bubble disturbance evaluation factor at the target moment is obtained.

[0049] Step S3, according to the fluctuation difference between the head and tail regions in the quantitative pump flow rate time series data window and the bubble disturbance evaluation factor at the target moment, obtain the degree of bubble disturbance of the quantitative pump at the target moment.

[0050] In step S2, the bubble disturbance evaluation factor at the target moment has been obtained for the dynamic detection and structure scoring of typical bubble disturbance modes in the quantitative pump flow rate time series data. However, in actual scenarios, there are still non-bubble disturbance behaviors during the operation of the quantitative pump, especially short-term non-linear flow rate mutations caused by liquid suction commutation delay, pipeline pressure difference rebound, etc. Their manifestation forms in the quantitative pump flow rate time series monitoring data are similar to those of bubble disturbances, and they will also be judged as anomalies by the bubble disturbance evaluation factor, thus causing misjudgments in precision evaluation. In order to further improve the disturbance credibility evaluation ability of bubble disturbance recognition, it is necessary to further optimize the accuracy of bubble disturbance recognition, so as to ensure the accuracy of quantitative pump precision evaluation.

[0051] After analyzing a large amount of real canned data, it is found that the most common type of pseudo-bubble disturbance comes from the instantaneous pressure difference disturbance caused by the pump-controlled commutation operation. This type of disturbance usually manifests as the flow rate collapse and recovery rise behavior within a certain period of time. However, the main difference from the real bubble disturbance is that the pseudo-disturbance usually quickly returns to a stable state after the disturbance occurs, while the real bubble disturbance will cause a long oscillation recovery period at the tail of the disturbance, manifested as a significantly higher system fluctuation amplitude within a certain period of time after the disturbance.

[0052] Therefore, the present invention takes the change of system fluctuation stability after the disturbance as the core feature for pseudo-disturbance identification, so as to obtain the bubble disturbance confidence optimization factor for evaluating the credibility of the disturbance score result output by the bubble disturbance evaluation factor.

[0053] In the process of evaluating the credibility of the disturbance score result output by the bubble disturbance evaluation factor, it is necessary to analyze the fluctuation change in the window of the quantitative pump flow rate time series data, so as to judge the difference between the fluctuation caused by the bubble disturbance and the fluctuation caused by the pseudo-bubble disturbance. For the difference analysis of the fluctuation mode, it is necessary to divide the window of the flow rate time series data and evaluate the difference through the tail region and the head region of the window, so as to judge the disturbance change situation.

[0054] However, in the process of dividing the head region and the tail region, the disturbance does not always appear in the front section of the window. Sometimes the disturbance may also occur in the middle section or even the rear position of the window. If only divided by the fixed window sub-region, it will cause the disturbance part to be regarded as the tail region at some moments, resulting in misjudgment. Even if the head region and the tail region are respectively in the middle of the disturbance and the front section of the disturbance, a situation where the evaluation significance is completely lost will occur. Therefore, it is necessary to first evaluate the disturbance position within the window and then divide the head region and the tail region relative to this position.

[0055] For the evaluation of the disturbance position, obtain the second-order difference data of the quantitative pump flow rate time series data window at the target moment. For the second-order difference data at any moment in the quantitative pump flow rate time series data window at the target moment, use it as the disturbance intensity weight at this moment; in the quantitative pump flow rate time series data window at the target moment, take the data point with the highest disturbance intensity weight as the estimated disturbance center point at the target moment; take the number of data points in half of the window length of the local area of the estimated disturbance center point at the target moment as the disturbance center region at the target moment; take the region on the left side of the disturbance center region in the quantitative pump flow rate time series data window at the target moment as the head region at the target moment; take the region on the right side of the disturbance center region in the quantitative pump flow rate time series data window at the target moment as the tail region at the target moment; if there are no data points in the head region or the tail region at the target moment, set the numerical variance of this region to 0.

[0056] After obtaining the head region and the tail region in the quantitative pump flow time series data window at the target time, the confidence optimization factor of bubble perturbation can be evaluated through the fluctuation difference between the head region and the tail region. Specifically, obtain a set smoothing adjustment factor; take the calculation result of subtracting the numerical variance of the head region at the target time from the numerical variance of the tail region at the target time as the evaluation of the fluctuation difference between the head region and the tail region at the target time; take the maximum value between the evaluation of the fluctuation difference between the head region and the tail region at the target time and the constant 0 as the first confidence evaluation factor at the target time; take the calculation result of multiplying the first confidence evaluation factor at the target time by the set smoothing adjustment factor and taking the negative value as the second confidence evaluation factor at the target time; perform an exponential mapping with the natural constant as the base on the second confidence evaluation factor at the target time, and take the corresponding exponential mapping result as the confidence optimization factor of bubble perturbation at the target time.

[0057] In one embodiment, the calculation formula for the confidence optimization factor of bubble perturbation at the th moment is: where, represents the confidence optimization factor of bubble perturbation at the th moment; represents the instantaneous flow variance of the head region in the quantitative pump flow time series data window at the th moment; represents the instantaneous flow variance of the tail region in the quantitative pump flow time series data window at the th moment; represents the smoothing adjustment factor, which is used to control the influence speed of the change of perturbation recovery characteristics on . In this embodiment, it is set that the value range of is , and in this embodiment, it is set that . This smoothing adjustment factor can be adjusted according to the actual scenario and there is no requirement;

[0058] It should be noted that in the quantitative pump flow time series data, if the perturbation is caused by commutation, it usually returns to stability quickly after the perturbation, that is, is significantly positive. At this time, decreases and the perturbation credibility decreases, and it should be suppressed during the process of bubble perturbation identification; if , at this time is , it indicates that the tail fluctuation has not recovered or even increased, and the disturbance trend persists, which is more in line with the real bubble disturbance. At this time, the recognition of the bubble disturbance should be retained.

[0059] After obtaining the bubble disturbance confidence optimization factor at the target moment, the confidence of the bubble disturbance evaluation factor at the target moment can be optimized by the bubble disturbance confidence optimization factor at the target moment. Specifically, the calculation result of multiplying the bubble disturbance confidence optimization factor at the target moment by the bubble disturbance evaluation factor at the target moment is used as the degree of quantitative pump bubble disturbance at the target moment.

[0060] In one embodiment, The formula for calculating the degree of quantitative pump bubble disturbance at the th moment is: where, represents the degree of quantitative pump bubble disturbance at the th moment; represents the bubble disturbance evaluation factor used for bubble disturbance pattern recognition at the th moment; represents the bubble disturbance confidence optimization factor used for evaluating the disturbance evaluation credibility of the bubble disturbance evaluation factor at the

[0061] It should be noted that the evaluation of the degree of quantitative pump bubble disturbance adopts a multiplicative coupling method, which fuses the two dimensions of whether the disturbance exists and whether it is credible. Among them, is the structure score, which is used to judge whether the disturbance shows typical evolution characteristics of bubble disturbance in the time series structure. is the confidence score, which is mainly used to evaluate whether the current disturbance behavior is real, and judges the behavior credibility based on the tail recovery characteristics of the disturbance; adopting a multiplication structure can ensure that only when the disturbance intensity is high and the disturbance credibility is high, the final degree of quantitative pump bubble disturbance will be significantly amplified, thereby effectively reducing misjudgment.

[0062] So far, according to the fluctuation difference between the head and tail regions in the quantitative pump flow time series data window and the bubble disturbance evaluation factor at the target moment, the degree of quantitative pump bubble disturbance at the target moment is obtained.

[0063] Step S4, using the degree of quantitative pump bubble disturbance at the target moment, optimize the error index of the quantitative pump flow time series data, and correspondingly obtain a dynamic accuracy evaluation result that can reflect the influence of bubble disturbance.

[0064] In step S3, the degree of bubble disturbance of the metering pump is obtained, which can reflect the structural strength and credibility of the flow anomaly in the current window in real time. The purpose of this step is to optimize the actual filling accuracy evaluation through the degree of bubble disturbance of the metering pump, so as to improve the accuracy of the metering pump in the presence of bubble disturbance. Specifically, a set error threshold is obtained for the accuracy evaluation of the metering pump; a reference target flow value set by the metering pump working system is obtained; the calculation result of adding 1 to the degree of bubble disturbance of the metering pump at the target moment is used as the error evaluation optimization weight at the target moment; for any moment in the metering pump flow time series data window at the target moment, the square of the difference between the actual flow monitoring value at this moment and the reference target flow value at this moment is used as the first error evaluation at this moment, and the first error evaluation at this moment is weighted by the error evaluation optimization weight at this moment, and the corresponding calculation result is used as the second error evaluation at this moment; the average value of the second error evaluations of all moments in the metering pump flow time series data window at the target moment is used as the error optimization evaluation at the target moment.

[0065] In one embodiment, the formula for the error optimization evaluation at the th moment is: where represents the error optimization evaluation at the th moment; represents the set length of the metering pump flow time series data window; represents the degree of bubble disturbance of the metering pump at the th moment; represents the actual flow value at the th moment; represents the reference target flow value set by the system at the

[0066] After obtaining the metering pump optimization evaluation error for the accuracy optimization evaluation of the metering pump, the accuracy can be evaluated through the error threshold, and the first error threshold and the second error threshold in the error threshold are obtained; If the error optimization evaluation at the target moment is less than the first error threshold, it is considered that the current metering pump working process is stable and in a high-precision state; If the error optimization evaluation at the target moment is greater than or equal to the first error threshold and less than the second error threshold, it is considered that there is a medium degree of disturbance in the current metering pump working process and it is in a medium-precision state; If the error optimization evaluation at the target moment is greater than or equal to the second error threshold, it is considered that there is a strong disturbance in the current metering pump working process and it is in a low-precision state.

[0067] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for evaluating the accuracy of a metering pump driven by a servo motor, characterized in that, The quantitative pump accuracy evaluation method based on a servo motor-driven metering pump includes: By continuously sampling the flow output of the servo motor-driven metering pump, constructing flow time-series data for evaluating the accuracy of the metering pump, and dividing windows for the flow time-series data, a flow time-series data window of the metering pump is obtained; According to the structural characteristics of bubble disturbances in the quantitative pump flow time-series data window and the output characteristics of the quantitative pump under the current working conditions, a bubble disturbance evaluation factor at the target moment is obtained; According to the fluctuation difference between the head and tail regions in the quantitative pump flow time-series data window and the bubble disturbance evaluation factor at the target moment, the bubble disturbance degree of the quantitative pump at the target moment is obtained; Using the bubble disturbance degree of the quantitative pump at the target moment to optimize the error index of the quantitative pump flow time-series data, and correspondingly obtaining a dynamic accuracy evaluation result that can reflect the influence of bubble disturbances.

2. The method for evaluating the accuracy of a metering pump driven by a servo motor according to claim 1, characterized in that, The obtaining of the bubble disturbance evaluation factor at the target moment according to the structural characteristics of bubble disturbances in the quantitative pump flow time-series data window and the output characteristics of the quantitative pump under the current working conditions includes: By performing least squares fitting on the quantitative pump flow time-series data window at the target moment, a trend representation equation at the target moment is obtained. The difference between the prediction result of the trend representation equation at the target moment and the quantitative pump flow monitoring data at the target moment is used as the trend deviation evaluation at the target moment; the calculation result of dividing the trend deviation evaluation at the target moment by the flow mean value of the quantitative pump flow time-series data window at the target moment is used as the trend deviation degree at the target moment; By performing cumulative difference evaluation on the flow change data in the quantitative pump flow time-series data window at the target moment, the local collapse intensity at the target moment is obtained; By performing cumulative evaluation of the change speed on the flow change information in the quantitative pump flow time-series data window at the target moment, the disturbance diffusion inertia evaluation at the target moment is obtained; By performing non-linear compression fusion analysis on the trend deviation degree, local collapse intensity, and disturbance diffusion inertia evaluation at the target moment, the bubble disturbance evaluation factor at the target moment is obtained.

3. The method for evaluating the accuracy of a metering pump driven by a servo motor according to claim 2, characterized in that, The obtaining of the local collapse intensity at the target moment by performing cumulative difference evaluation on the flow change data in the quantitative pump flow time-series data window at the target moment includes: For the quantitative pump flow time-series data window at the target moment, starting from the flow data at the second moment in this time-series data window, the calculation result of subtracting the flow data at each moment from the flow data at the previous moment is used as the flow difference evaluation at this moment; for any moment in the quantitative pump flow time-series data window at the target moment, if the flow difference evaluation at this moment is less than 0, then the flow difference evaluation at this moment is used as the downward amplitude evaluation at this moment, otherwise the value 0 is used as the downward amplitude evaluation at this moment; the calculation result of adding up all the downward amplitude evaluations in the quantitative pump flow time-series data window at the target moment is used as the local collapse intensity at the target moment.

4. The method for evaluating the accuracy of a metering pump driven by a servo motor according to claim 2, characterized in that, The obtaining of the disturbance diffusion inertia evaluation of the target moment by performing a change speed cumulative evaluation on the flow rate change information in the quantitative pump flow rate time series data window of the target moment includes: For the flow rate difference evaluation at each moment in the quantitative pump flow rate time series data window of the target moment, starting from the third moment, the absolute value of the calculation result obtained by subtracting the flow rate difference evaluation at each moment from the flow rate difference evaluation at the previous moment is used as the flow rate change rate difference evaluation at that moment; the mean value of all the flow rate change rate difference evaluations in the quantitative pump flow rate time series data window of the target moment is used as the disturbance diffusion inertia evaluation of the target moment.

5. The method for evaluating the accuracy of a metering pump driven by a servo motor according to claim 2, characterized in that, The obtaining of the bubble disturbance evaluation factor of the target moment by performing a non-linear compression fusion analysis on the trend deviation degree, local collapse intensity and disturbance diffusion inertia evaluation of the target moment includes: Obtain the trend deviation degree, local collapse intensity and disturbance diffusion inertia evaluation of the target moment; The calculation results obtained by adding the trend deviation degree, local collapse intensity and disturbance diffusion inertia evaluation of the target moment to the constant 1 respectively and performing a logarithmic mapping are used as the first evaluation factor, the second evaluation factor and the third evaluation factor of the target moment; The calculation result obtained by multiplying the first evaluation factor, the second evaluation factor and the third evaluation factor of the target moment is used as the numerator, the square of the calculation result obtained by adding the flow rate mean value of the quantitative pump flow rate time series data window of the target moment to a set extremely small positive number is used as the denominator, and the formed fraction is used as the first bubble disturbance evaluation factor of the target moment; The linear normalization mapping result of the first bubble disturbance evaluation factor of the target moment is used as the bubble disturbance evaluation factor of the target moment.

6. The method for evaluating the accuracy of a metering pump driven by a servo motor according to claim 1, characterized in that, The obtaining of the quantitative pump bubble disturbance degree of the target moment according to the fluctuation difference between the head and tail regions in the quantitative pump flow rate time series data window and the bubble disturbance evaluation factor of the target moment includes: Obtain the second-order difference data of the quantitative pump flow rate time series data window of the target moment. For the second-order difference data at any moment in the quantitative pump flow rate time series data window of the target moment, use it as the disturbance intensity weight at that moment; In the quantitative pump flow rate time series data window of the target moment, use the data point with the highest disturbance intensity weight as the estimated disturbance center point of the target moment; Use the number of data points in a window length of one-half of the local area of the estimated disturbance center point of the target moment as the disturbance center area of the target moment; use the area on the left side of the disturbance center area in the quantitative pump flow rate time series data window of the target moment as the head area of the target moment; use the area on the right side of the disturbance center area in the quantitative pump flow rate time series data window of the target moment as the tail area of the target moment; Obtain the quantitative pump bubble disturbance degree of the target moment through the fluctuation difference evaluation between the head area and the tail area of the target moment and the bubble disturbance evaluation factor of the target moment.

7. The method for evaluating the accuracy of a metering pump driven by a servo motor according to claim 6, characterized in that, Evaluating the degree of bubble perturbation of the metering pump at the target moment through the fluctuation difference evaluation between the head region and the tail region at the target moment, and the bubble perturbation evaluation factor at the target moment, includes: Obtaining a set smoothing adjustment factor; using the calculation result of subtracting the numerical variance of the head region at the target moment from the numerical variance of the tail region at the target moment as the fluctuation difference evaluation between the head region and the tail region at the target moment; Using the maximum value between the fluctuation difference evaluation between the head region and the tail region at the target moment and the constant 0 as the first confidence evaluation factor at the target moment; Using the calculation result of multiplying the first confidence evaluation factor at the target moment by the set smoothing adjustment factor and taking the negative value as the second confidence evaluation factor at the target moment; Performing an exponential mapping with the natural constant as the base on the second confidence evaluation factor at the target moment, and using the corresponding exponential mapping result as the bubble perturbation confidence optimization factor at the target moment; Using the calculation result of multiplying the bubble perturbation confidence optimization factor at the target moment by the bubble perturbation evaluation factor at the target moment as the degree of bubble perturbation of the metering pump at the target moment.

8. The quantitative pump accuracy evaluation method based on a servo motor-driven metering pump according to claim 6, characterized in that, Using the calculation result of subtracting the numerical variance of the head region at the target moment from the numerical variance of the tail region at the target moment as the fluctuation difference evaluation between the head region and the tail region at the target moment, where if there are no data points in the head region or the tail region at the target moment, the numerical variance of this region is set to 0.

9. The quantitative pump accuracy evaluation method based on a servo motor-driven metering pump according to claim 1, characterized in that, Using the degree of bubble perturbation of the metering pump at the target moment to optimize the error index of the metering pump flow time series data, and correspondingly obtaining a dynamic accuracy evaluation result that can reflect the influence of bubble perturbation, includes: Obtaining a set error threshold for evaluating the accuracy of the metering pump; obtaining the reference target flow value set by the metering pump working system; using the calculation result of adding the degree of bubble perturbation of the metering pump at the target moment to the constant 1 as the error evaluation optimization weight at the target moment; For any moment in the metering pump flow time series data window at the target moment, using the square of the difference between the actual flow monitoring value at this moment and the reference target flow value at this moment as the first error evaluation at this moment, weighting the first error evaluation at this moment through the error evaluation optimization weight at this moment, and using the corresponding calculation result as the second error evaluation at this moment; using the mean value of the second error evaluations of all moments in the metering pump flow time series data window at the target moment as the error optimization evaluation at the target moment; Comparing the error optimization evaluation at the target moment with the error threshold to obtain a dynamic accuracy evaluation result that can reflect the influence of bubble perturbation.

10. The quantitative pump accuracy evaluation method based on a servo motor-driven metering pump according to claim 9, characterized in that, Comparing the error optimization evaluation at the target moment with the error threshold to obtain a dynamic accuracy evaluation result that can reflect the influence of bubble perturbation, includes: Obtaining the first error threshold and the second error threshold in the error threshold; if the error optimization evaluation at the target moment is less than the first error threshold, it is considered that the current metering pump working process is stable and in a high-precision state; If the error optimization evaluation at the target moment is greater than or equal to the first error threshold and less than the second error threshold, it is considered that there is a medium-level disturbance in the current operation process of the metering pump, and it is in the medium-precision state; If the error optimization evaluation at the target moment is greater than or equal to the second error threshold, it is considered that there is a strong disturbance in the current operation process of the metering pump, and it is in the low-precision state.

Images