A method for optimizing a controller of an engine servo system

Abstract

The application relates to the technical field of engine control, in particular to a controller optimization processing method of an engine servo system. The method comprises the following steps: acquiring environmental data during engine operation in the past and monitoring data of a to-be-analyzed type, initial clustering and an initial clustering center; acquiring a monitoring data segment of the monitoring data of the to-be-analyzed type in an initial cluster, and then calculating the average influence degree of each type of environmental data on each to-be-analyzed type; then, the influence degree of each to-be-analyzed type on the initial clustering center at each moment is obtained, the initial clustering center is updated, and a final cluster is obtained; the average adjustment effect of each final cluster is obtained according to the adjustment effect after each instruction is sent; and the integral gain parameter of a PID algorithm is adjusted according to the average adjustment effect of the final cluster to which the current moment belongs. The application can improve the control stability and accuracy of the engine servo system controller.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of engine control, in particular to a controller optimization processing method of an engine servo system. BACKGROUND

[0002] The engine servo system is a feedback control system for precisely controlling the operation of various components of the engine. By combining sensor feedback and controller algorithms, the engine operation is ensured to be efficient, stable and fast-responding. The controller of the servo system receives target instructions and current engine-related data, and uses control algorithms to generate corresponding output signals to control the engine speed, torque, etc., so that the engine reaches the target state.

[0003] The PID control algorithm is a commonly used control algorithm for the controller of the current engine servo system. According to the difference between the current data and the target value, the required control amount is obtained by combining the proportional, integral and derivative parameters in the PID algorithm, and the engine is controlled to make a responsive action. Among them, the selection of parameters in the PID algorithm is the key to determine the control effect. The existing method mainly obtains the PID parameter value through multiple experiments. However, because the control of the engine under different working conditions will be different, the fixed PID parameter value is difficult to adapt to different situations, resulting in poor stability of the control effect of the servo system, which affects the working efficiency of the engine. SUMMARY

[0004] In order to solve the above technical problems, the purpose of the present application is to provide a controller optimization processing method of an engine servo system, and the technical solution adopted is as follows:

[0005] An embodiment of the present application provides a controller optimization processing method of an engine servo system, which comprises:

[0006] Obtaining different kinds of monitoring data and environmental data of the engine during operation in the history; screening the types of monitoring data to obtain a type to be analyzed, and clustering the monitoring data of the type to be analyzed to obtain an initial cluster and an initial cluster center;

[0007] Segmenting the monitoring data according to the variation degree of each monitoring data of a type to be analyzed in an initial cluster to obtain a monitoring data segment; obtaining the influence degree of an environmental data corresponding to each monitoring data segment in time sequence on the type to be analyzed;

[0008] Obtaining the average influence degree of an environmental data on a type to be analyzed by averaging the influence degrees of the environmental data on the type to be analyzed in each initial cluster;

[0009] The influence degree of each environment data on the initial cluster center of the to-be-analyzed species at a time is obtained based on the average influence degree of each environment data on the to-be-analyzed species, the environment data at the time in history and the environment data at the current time; and the initial cluster center is updated based on the influence degree of each to-be-analyzed species on the initial cluster center at each time in each initial cluster, to obtain a final cluster.

[0010] The adjustment effect after each instruction is issued in history is obtained; the average adjustment effect of a final cluster is obtained according to the adjustment effect after each instruction is issued in the final cluster; and the integral gain parameter is adjusted according to the average adjustment effect of the final cluster to which the current time belongs.

[0011] Preferably, the to-be-analyzed species is obtained by screening the species of the monitoring data, including:

[0012] The principal component analysis method is used to process the monitoring data of different species in history when the engine is working, to obtain the characteristic value of each monitoring data, and a set number of species with the largest characteristic value are taken as the to-be-analyzed species.

[0013] Preferably, the monitoring data segments are obtained by segmenting according to the change degree of each monitoring data of a to-be-analyzed species in an initial cluster, including:

[0014] The monitoring data of a to-be-analyzed species in an initial cluster are arranged in ascending order, to obtain an arrangement sequence; the difference between the latter monitoring data and the former monitoring data of two adjacent monitoring data in the arrangement sequence is obtained and normalized, to obtain the change degree of the latter monitoring data; the monitoring data with a change degree greater than a first threshold value is taken as a demarcation point, and the arrangement sequence is segmented by using the demarcation point to obtain the monitoring data segments.

[0015] Preferably, the influence degree of each environment data on the to-be-analyzed species is obtained based on the environment data corresponding to each monitoring data segment in time sequence, including:

[0016] The mean value of the environment data corresponding to each monitoring data segment in time sequence is obtained as the environment mean value corresponding to the monitoring data segment; the absolute value of the sum of the difference between the environment mean values corresponding to each two adjacent monitoring data segments is calculated, and the mean value is taken to obtain the average change amount of the environment data; the reciprocal of the mean value of the standard deviation of the environment data corresponding to each monitoring data segment in time sequence is calculated, and is recorded as the environment data stability amount; the influence degree of the environment data on the to-be-analyzed species is obtained by multiplying the average change amount of the environment data and the environment data stability amount and normalizing.

[0017] Preferably, the influence degree of each environment data on the initial cluster center of the to-be-analyzed species at a time is obtained based on the average influence degree of each environment data on the to-be-analyzed species, the environment data at the time in history and the environment data at the current time, including:

[0018] obtaining an absolute value of a difference between an environment data of a time in history and the environment data of the current time, adding the absolute value and a hyper parameter, and then taking an inverse to obtain an environment similarity; multiplying the environment similarity corresponding to the time in history and an average influence degree of the environment data on a to-be-analyzed species to obtain a first eigenvalue corresponding to the environment data of the time on the initial cluster center; and summing the first eigenvalues corresponding to each environment data of the time to obtain an influence degree of the to-be-analyzed species on the initial cluster center.

[0019] Preferably, the initial cluster center is updated based on the influence degrees of the to-be-analyzed species on the initial cluster center in each initial cluster at each time to obtain a final cluster, including:

[0020] obtaining an influence weight of the to-be-analyzed species on the initial cluster center of the initial cluster at the time by comparing the influence degree of the to-be-analyzed species on the initial cluster center of the initial cluster at the time with a sum of the influence degrees of the to-be-analyzed species on the initial cluster center of the initial cluster at all times;

[0021] weighting and averaging the monitoring data of the to-be-analyzed species at each time by using the influence weights of the to-be-analyzed species on the initial cluster center of the initial cluster at each time to obtain an average monitoring data value corresponding to the to-be-analyzed species; similarly, average monitoring data values corresponding to other to-be-analyzed species are obtained, and data points composed of the average monitoring data values corresponding to all to-be-analyzed species in the initial cluster form a first updated initial cluster center corresponding to the initial cluster center of the initial cluster; clustering the first updated initial cluster centers corresponding to the initial cluster centers of all initial clusters to obtain a first clustering result, and iteratively updating the first updated initial cluster centers in the first clustering result until the data points in the clusters in the clustering result no longer change, and stopping the updating to obtain a final cluster.

[0022] Preferably, the adjustment effect after each instruction is issued in history is obtained, including:

[0023] The parameter corresponding to the engine that needs to be controlled is denoted as a control parameter, and a difference between a stable control parameter of the engine after each instruction is issued in history and a set target control parameter is obtained as the adjustment effect after each instruction is issued.

[0024] Preferably, the average adjustment effect of a final cluster is obtained according to the adjustment effect after each instruction is issued in the final cluster, including:

[0025] The instruction issuing time in each final cluster is obtained according to the time corresponding to the instruction issuing time in history; the reciprocal of the distance between the data point corresponding to the instruction issuing time in a final cluster and the cluster center of the final cluster is obtained, and is recorded as the weight of the data point corresponding to the instruction issuing time; the adjustment effect after each instruction issuing in the final cluster is weighted and averaged by using the weight of the data point corresponding to each instruction issuing time, and a weighted average value is obtained, which is recorded as the average adjustment effect of the final cluster.

[0026] Preferably, the integral gain parameter is adjusted according to the average adjustment effect of the final cluster to which the current time belongs, and the adjustment includes:

[0027] The data point of each to-be-analyzed category of the monitoring data of the current time is obtained, and is recorded as a target data point; the distances between the target data point and the cluster centers of the final clusters are respectively calculated, the final cluster with the minimum distance is the final cluster to which the current time belongs; the average adjustment effect of the final cluster to which the current time belongs is compared with the maximum value of the absolute values of the average adjustment effects of the final clusters to obtain a proportional coefficient; the proportional coefficient is added to the first preset value and multiplied by the original integral gain parameter to obtain the adjusted gain integral parameter of the current time.

[0028] The embodiment of the application has at least the following beneficial effects: the application collects different kinds of monitoring data and environmental data of the engine in history, then screens the kinds of the monitoring data, screens out the kinds which are more important for the engine, obtains the monitoring data of the to-be-analyzed categories, and then reduces the complexity of the analysis while ensuring the accuracy of the analysis; further, in an initial cluster, the average influence degree of one kind of environmental data on one to-be-analyzed category is obtained by combining the influence of various environmental data on each to-be-analyzed category, then the influence degree of one to-be-analyzed category on the center of the initial cluster at one time in the initial cluster is obtained, and the center of the initial cluster is updated to obtain a final cluster, so that the clustering result can accurately reflect the real working condition of the engine, and the accuracy of the subsequent analysis is improved; then the adjustment effect after each instruction issuing in history is obtained, the average adjustment effect of each final cluster is obtained, and the integral gain parameter of the PID control algorithm is adjusted, which can effectively solve the problem that the fixed PID parameter is not applicable to different engine working conditions, and improve the control stability and accuracy of the engine servo system controller. BRIEF DESCRIPTION OF DRAWINGS

[0029] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0030] Figure 1 A method flowchart of an engine servo system controller optimization processing method provided by the embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined purpose, the following will combine the drawings and the preferred embodiments to specifically describe the engine servo system controller optimization processing method according to the present application, its specific implementation, structure, features and effects in detail. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0032] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0033] The following will specifically describe the specific scheme of the engine servo system controller optimization processing method provided by the present application in combination with the drawings.

[0034] Embodiment:

[0035] The main application scenario of the present application is that the control situation of the engine servo system controller is greatly affected by the working condition of the engine and the environmental situation, resulting in poor stability of the control effect of the fixed PID control algorithm parameters facing different engine situations, which affects the engine running efficiency, and therefore the PID control algorithm parameters are adaptively adjusted.

[0036] Please refer to Figure 1 which shows the method flowchart of the engine servo system controller optimization processing method provided by the embodiment of the present application, and the method comprises the following steps:

[0037] Step S1, obtaining different kinds of monitoring data and environmental data of the engine in history; screening the types of monitoring data to obtain the types to be analyzed, and clustering the monitoring data of the types to be analyzed to obtain initial clusters and initial cluster centers.

[0038] In order to realize accurate control and real-time response, the engine servo system needs to collect various data of the engine in real time for monitoring, so relevant sensors are installed at corresponding positions of the engine for real-time monitoring. Different types of monitoring data of the engine during operation are collected, for example, the engine speed is monitored by using a Hall sensor, the intake pressure is monitored by using a pressure sensor, the mass air flow entering the engine is monitored by using a mass air flow sensor, the throttle opening is monitored by using a throttle position sensor, and the like, and data such as the injection pulse width and the ignition advance angle controlled by the control system are recorded.

[0039] Because changes in external environmental factors will change the operating state and power response characteristics of the engine, thereby affecting the PID control effect, different types of environmental data of the engine during operation also need to be collected, in which temperature, humidity and air pressure are the main environmental factors affecting PID control, and thus a thermistor is used to monitor the intake temperature, a humidity sensor is used to monitor the air humidity, and an air pressure sensor is used to detect the atmospheric pressure.

[0040] In order to facilitate analysis according to the multi-dimensional monitoring data of the engine, the monitoring data of the engine needs to be normalized first. The monitoring data of the engine in the present application are all normalized data.

[0041] Because the adjustment degree of the controller needs to be different when controlling the engine under different working conditions, that is, the control effect of the original PID parameters is different under different engine working conditions, in order to obtain PID parameters suitable for different engine working conditions, the engine working conditions need to be classified first.

[0042] The classification of the engine working conditions is mainly based on comprehensive analysis of multi-dimensional data such as engine speed, intake pressure and torque, but different types of monitoring data reflect the engine working conditions to different degrees, and some monitoring data have weak correlation with the engine working conditions. Therefore, for the monitoring data of the engine, principal component analysis is used for processing, in which the monitoring data with larger eigenvalues are the monitoring data that change more obviously under different states of the engine, that is, the monitoring data that can better reflect the engine working conditions. Specifically, the principal component analysis is used to process different types of monitoring data of the engine during operation in history, the eigenvalues of each type of monitoring data are obtained, and a set number of types with the largest eigenvalues are taken as the types to be analyzed. The value of the preset number is 3, which is a reference value, and the implementer can adjust the value of the preset number according to the actual situation, appropriately increase the accuracy of subsequent analysis, but need to pay attention to the increase of the complexity of calculation.

[0043] According to the operating state of the engine, the engine operating conditions mainly include idle operating condition, acceleration operating condition, deceleration operating condition, uniform speed cruising operating condition, heavy load operating condition and the like. Since the engine characteristics are different under different operating conditions, the required PID parameters are also different. Further, the monitoring data of each to-be-analyzed category corresponding to a moment is composed into a data point; then, according to the common operating conditions of the engine, k is set to 6, and the monitoring data of the to-be-analyzed category is clustered in each data point unit to obtain initial clusters. Specifically, in the three-dimensional space, six initial cluster centers are selected, the distances of other data points to each initial cluster center are calculated, and they are distributed to the cluster represented by the nearest cluster center, so as to obtain the preliminary clustering result, and obtain the initial cluster and the initial cluster center. The clustering algorithm is K-means clustering algorithm.

[0044] In step S2, the monitoring data segments are obtained by segmenting according to the variation degree of each monitoring data of a to-be-analyzed category in an initial cluster; and the influence degree of each environmental data on the to-be-analyzed category is obtained based on the environmental data corresponding to each monitoring data segment in time sequence.

[0045] The performance, combustion efficiency and the like of the engine under different environmental conditions will change, that is, the related monitoring data of the engine under similar operating conditions in different environments may also have large differences, so in order to make the K-means clustering result more reflect the real operating condition of the current engine, the proximity of each data point to the cluster center needs to be adjusted according to the similarity of the environmental conditions of the historical data and the current environment, so that the characteristic values of the cluster centers of the final clustering result are closer to the characteristics of different operating conditions under the current environment.

[0046] Different environmental factors have different influences on the operation of the engine, so the influence degrees of different environmental factors on the above-mentioned three to-be-analyzed categories are different, therefore, the influence degree of each environmental factor on the above-mentioned to-be-analyzed categories is calculated first.

[0047] Because the data points in each initial cluster in the preliminary clustering result obtained in step S1 are data points with relatively high operating condition characteristic proximity, the influence degree of the environmental factor on each to-be-analyzed category is analyzed in each initial cluster of the preliminary clustering result. Because the analysis processes of different to-be-analyzed categories are similar, only one to-be-analyzed category and one environmental factor are taken as an example for analysis here.

[0048] Firstly, the engine has certain adaptability to the change of environmental factors, that is, the air humidity will not cause obvious change of the engine data characteristics within a certain range, but when the air humidity changes beyond a certain range, it will have a relatively obvious influence, so the influence degree of the air humidity on the to-be-analyzed category A cannot be judged only by its linear relationship.

[0049] The monitoring data segments are obtained by segmenting according to the change degree of each monitoring data of a to-be-analyzed species in an initial cluster. Specifically, each monitoring data of a to-be-analyzed species in an initial cluster is arranged in ascending order to obtain an arrangement sequence; the difference between the latter monitoring data and the former data in two adjacent monitoring data in the arrangement sequence is obtained and normalized to obtain the change degree of the latter monitoring data.

[0050] The calculation model of the change degree is specifically as follows:

[0051]

[0052] The change degree of the i+1th monitoring data in the arrangement sequence corresponding to each monitoring data of the to-be-analyzed species A in the uth initial cluster is represented by u(i+1); norm represents a normalization function; The i+1th and ith monitoring data in the arrangement sequence corresponding to each monitoring data of the to-be-analyzed species A in the uth initial cluster are represented by u(i+1) and u(i) respectively.

[0053] Because the characteristic values under similar working conditions should have a high similarity, i.e., the change degree of the to-be-analyzed species A is small, if the to-be-analyzed species A has a relatively obvious change, it indicates that the environmental conditions corresponding to the front and rear monitoring data may have a relatively large change. Thus, the monitoring data with a change degree greater than a first threshold value is taken as a demarcation point, the arrangement sequence is segmented by using the demarcation point to obtain monitoring data segments, and the environmental conditions of different monitoring data segments are relatively different. The intermediate value is taken as the threshold value, and thus the first threshold value is 0.5.

[0054] Finally, the influence degree of air humidity on the to-be-analyzed species A is calculated. If the air humidity has a relatively large influence on the to-be-analyzed species A, the air humidity values corresponding to each monitoring data segment in time sequence should be relatively close, i.e., the air humidity values corresponding to the time corresponding to each monitoring data in the monitoring data segment should be relatively close, i.e., the standard deviation of the air humidity values corresponding to each monitoring data segment in time sequence is small, and the air humidity values corresponding to different monitoring data segments in time sequence should have a relatively large difference and present a certain change trend. Thus, the average value of the air humidity corresponding to each monitoring data segment in time sequence is calculated as the overall level of the air humidity corresponding to each monitoring data segment in time sequence, the influence degree of the air humidity on the to-be-analyzed species A is calculated according to the difference and change trend of the air humidity between adjacent monitoring data segments and the standard deviation of the air humidity corresponding to each monitoring data segment in time sequence.

[0055] ​​​The influence degree of each kind of environment data on the to-be-analyzed category is obtained according to the kind of environment data corresponding to each monitoring data segment in time sequence. Specifically, the mean value of the kind of environment data corresponding to each monitoring data segment is obtained as the environment mean value corresponding to the monitoring data segment; the absolute value of the sum of the difference between the environment mean values corresponding to each two adjacent monitoring data segments is calculated, and the mean value is obtained as the average change amount of the environment data; the reciprocal of the mean value of the standard deviation of the kind of environment data corresponding to each monitoring data segment in time sequence is calculated, and is recorded as the environment data stability amount; and the average change amount of the environment data is multiplied by the environment data stability amount and normalized to obtain the influence degree of the kind of environment data on the to-be-analyzed category. The kind of environment data can be taken as air humidity for example, and the influence degree of the kind of environment data on the to-be-analyzed category in an initial cluster, that is, the influence degree of the monitoring data on the to-be-analyzed category, is analyzed.

[0056] The specific calculation model of the influence degree of the kind of environment data on the to-be-analyzed category is as follows:

[0057] ,

[0058] wherein, represents the influence degree of air humidity (a kind of environment data) in the u th initial cluster on the to-be-analyzed category A; represents the number of monitoring data segments corresponding to the monitoring data of the to-be-analyzed category A in the u th initial cluster; and respectively represent the mean values of the air humidity values corresponding to the (p+1) th and the p th monitoring data segments in time sequence in the monitoring data segments corresponding to the monitoring data of the to-be-analyzed category A in the u th initial cluster, that is, the environment mean values corresponding to the (p+1) th and the p th monitoring data segments; represents the difference between the environment mean values of the adjacent two monitoring data segments, the absolute value of the difference represents the humidity change degree, and the positive and negative of the difference represent the change direction of the corresponding air humidity when the to-be-analyzed category A increases; represents the sum of the difference between the environment mean values of the adjacent monitoring data segments in the monitoring data segments corresponding to the monitoring data of the to-be-analyzed category A in the u th initial cluster, that is, the greater the difference between the air humidities of different monitoring data segments and the more consistent the change direction of the air humidity between the adjacent monitoring data segments, the greater the influence degree of the air humidity on the to-be-analyzed category A, is the average change amount of the environment data, and the mean value is used to avoid the influence of the different numbers of monitoring data segments corresponding to the monitoring data of the to-be-analyzed category A obtained by different initial clusters on the result;

[0059] represents the standard deviation of the air humidity value corresponding to the p th monitoring data segment in time sequence in the monitoring data segments corresponding to the monitoring data of the to-be-analyzed category A in the u th initial cluster, It is the reciprocal of the mean of the standard deviations of the air humidity values ​​corresponding to the p-th monitoring data segment in the monitoring data segment corresponding to the monitoring data of the species A to be analyzed in the u-th initial cluster. It is also a stationary quantity of environmental data. The smaller the standard deviation, the closer the air humidity values ​​are within the same monitoring data segment, that is, the greater the influence of air humidity on the species A to be analyzed.

[0060] Thus, within each initial cluster, the extent to which each type of environmental data affects each category to be analyzed can be obtained.

[0061] Step S3: Calculate the average value of the influence of one type of environmental data on a type of species to be analyzed in each initial cluster to obtain the average influence of that type of environmental data on the type of species to be analyzed.

[0062] The above steps obtain the degree of influence of one type of environmental data on one type of species to be analyzed in an initial cluster. From this, the average degree of influence of one type of environmental data on the monitoring data of one type of species to be analyzed in all initial clusters can be calculated, and then the average degree of influence of each type of environmental data on each type of species to be analyzed can be obtained in all initial clusters.

[0063] The specific calculation model for the average impact of environmental data on a given category is as follows:

[0064] ,

[0065] in, This indicates the average degree of influence of air humidity (an environmental data point) on engine type A, which is being analyzed. Indicates the initial number of clusters ( ), This indicates the degree of influence of air humidity in the u-th initial cluster on the species A to be analyzed. This represents the average influence of air humidity on the analyzed species A obtained from all initial clusters, which is also the average influence of air humidity on the engine's analyzed species A.

[0066] This allows us to obtain the average impact of each type of environmental data on each category to be analyzed. , This represents the average influence of the s-th type of environmental data on the t-th type of data to be analyzed.

[0067] Step S4: Based on the average influence of each type of environmental data on a type to be analyzed, and the various environmental data at a historical moment and the current moment, obtain the influence of the type to be analyzed on the initial cluster center at that moment; update the initial cluster center based on the influence of each type to be analyzed on the initial cluster center at each moment in each initial cluster to obtain the final cluster.

[0068] After obtaining the average impact of each type of environmental data on each type of analysis, based on the similarity between the environment at each historical moment and the current moment, and combined with the average impact of environmental factors on the types of engines to be analyzed, the impact of each type of analysis on the initial cluster center at each moment can be calculated.

[0069] The influence of each type of environmental data on a given category is determined by the average impact of each type of environmental data on the initial cluster center at a given moment, and by various environmental data from a historical moment and the current moment.

[0070] Specifically, the absolute value of the difference between a type of environmental data at a historical moment and the same type of environmental data at the current moment is obtained, and then added to the hyperparameter and inverted to obtain the environmental similarity. The environmental similarity corresponding to the historical moment is multiplied by the average influence of the environmental data on a type of data to be analyzed to obtain the first feature value corresponding to the environmental data at that moment. The first feature values ​​corresponding to each type of environmental data at that moment are summed to obtain the influence of the type of data to be analyzed on the initial cluster center at that moment.

[0071] The specific calculation model is as follows:

[0072] ,

[0073] in, This represents the degree of influence of the t-th type of the species to be analyzed at the i-th moment in history on the initial cluster center. Represents the number of types of environmental data ( ), This represents the value of the s-th type of environmental data at the i-th moment in history. This represents the value of the s-th type of environmental data at the current time. This represents the similarity between historical and current environmental factors, also known as environmental similarity. The larger the value, the closer the historical and current environmental conditions are, meaning it better reflects the relationship between the current engine operating conditions and the PID control parameters. ε is a hyperparameter used to ensure that the fraction is meaningful; here, ε is specified as 0.01. This represents the average influence of the s-th type of environmental data on the t-th type of data to be analyzed. Let represent the first feature value corresponding to the s-th type of environmental data at time i. After summing, we can obtain the degree of influence of the t-th type of data to be analyzed at time i on the initial cluster center.

[0074] Furthermore, the initial cluster centers need to be updated based on the degree of influence of each type to be analyzed on the initial cluster center at each time point in each initial cluster, so as to obtain the final cluster.

[0075] Specifically, first, the influence weight of each time point (each data point) of each to-be-analyzed species on the initial cluster center of the initial cluster needs to be obtained.

[0076] Specifically, the influence degree of one time point of one to-be-analyzed species in one initial cluster on the initial cluster center of the initial cluster is compared with the sum of the influence degrees of all time points of the to-be-analyzed species on the initial cluster center of the initial cluster to obtain the influence weight of the to-be-analyzed species on the initial cluster center of the initial cluster at the time point.

[0077] The specific calculation model of the influence weight is as follows:

[0078]

[0079] wherein, represents the influence weight of the i-th time point of the t-th to-be-analyzed species on the initial cluster center of the u-th initial cluster, the influence degree of the t-th to-be-analyzed species on the initial cluster center at the i-th time point in the u-th initial cluster, represents the number of data points contained in the u-th initial cluster, that is, the number of time points contained, represents the sum of the influence degrees of the t-th to-be-analyzed species on the initial cluster center at each time point in the u-th initial cluster.

[0080] Finally, the monitoring data of each time point of the to-be-analyzed species is weighted and averaged by using the influence weight of the to-be-analyzed species on the initial cluster center of the initial cluster at each time point in the initial cluster to obtain the average monitoring data value corresponding to the to-be-analyzed species; similarly, the average monitoring data values corresponding to other to-be-analyzed species are obtained, and the data points composed of the average monitoring data values corresponding to all to-be-analyzed species in the initial cluster form a once-updated initial cluster center corresponding to the initial cluster center of the initial cluster; the once-updated initial cluster centers corresponding to the initial cluster centers of each initial cluster are clustered to obtain a first clustering result, and the once-updated initial cluster centers in the first clustering result are updated again, until the data points in the clustering result no longer change, the updating is stopped, and the final clustering is obtained. The engine working conditions of the data points at each time point in the final clustering obtained are similar. Each final cluster obtained represents one working condition of the engine in operation.

[0081] Step S5: obtaining the adjustment effect after each instruction is issued in history; obtaining the average adjustment effect of the final cluster according to the adjustment effect after each instruction is issued in the final cluster; and adjusting the integral gain parameter according to the average adjustment effect of the final cluster to which the current time point belongs.

[0082] ​The approach degree of the stable value and the target value of the engine corresponding data after the engine servo system controller receives the instruction each time reflects the effect of the PID control. Thus, the difference between the stable value of the engine corresponding parameter (such as the output power, the torque and the rotating speed, etc.) that needs to be controlled after the instruction is issued in the history and the set target value is obtained, which represents the adjustment effect after the instruction is issued each time in the history. Specifically, the engine corresponding parameter that needs to be controlled is denoted as the regulation parameter, the difference between the stable regulation parameter of the engine after the instruction is issued each time in the history and the set target regulation parameter is obtained as the adjustment effect after the instruction is issued each time.

[0083] The specific calculation model of the adjustment effect is as follows:

[0084]

[0085] wherein, represents the adjustment effect after the instruction is issued the cth time in the history, represents the value of the regulation parameter of the engine after the instruction is issued the cth time in the history, that is, the stable regulation parameter, represents the target value of the regulation parameter of the engine, that is, the set target regulation parameter. The closer the difference to 0, the better the adjustment effect of the regulation parameter of the engine after the instruction is issued the cth time.

[0086] Further, the adjustment effect after the instruction is issued at the corresponding time point in each final cluster needs to be analyzed. Further, the time point when the instruction is issued in each final cluster is obtained according to the time point when the instruction is issued in the history; the time point when the instruction is issued is also the time point when the data points in a final cluster correspond to the time point when the instruction is issued in the history.

[0087] Thus, the PID control effect under each engine working condition is obtained according to the average value of the adjustment effect after the instruction is issued each time in each final cluster. Since the cluster center of each final cluster corresponds to the engine data most conforming to the engine working condition characteristics of the environment where the current engine is located, the data points closer to the cluster center reflect the PID control effect under the working condition closer to the current time, that is, the weight in the calculation of the average value is greater, which is denoted as represents the reciprocal of the distance between the data point corresponding to the cth instruction issuance time point in the u th final cluster and the cluster center of the u th final cluster.

[0088] ​Specifically, the reciprocal of the distance between a data point corresponding to an instruction issuing time in a final cluster and the cluster center of the final cluster is obtained, denoted as the weight of the data point corresponding to the instruction issuing time; and a weighted average of the adjustment effect after each instruction issuing in the final cluster is obtained by using the weight of the data point corresponding to each instruction issuing time, to obtain a weighted average value, denoted as the average adjustment effect of the final cluster. The adjustment effect after each instruction issuing can also be regarded as the adjustment effect corresponding to each instruction issuing time.

[0089] The specific calculation model of the average adjustment effect of a final cluster is specifically:

[0090]

[0091] The average adjustment effect of the u-th final cluster, that is, the weighted average value of the difference between the actual value after the historical instruction adjustment and the set target value in the u-th final cluster, The number of instruction issuing times in the u-th final cluster, The adjustment effect after the c-th instruction issuing in the u-th final cluster, The reciprocal of the distance between the data point corresponding to the c-th instruction issuing time in the u-th final cluster and the cluster center of the final cluster, that is, the weight of the data point corresponding to the instruction issuing time, the greater the value, the closer the environmental condition corresponding to the c-th instruction issuing time to the environmental condition at the current time, so the weight is greater, The sum of the weights of the data points corresponding to the instruction issuing times in the final cluster. Thus, the difference between the PID control result and the set target value after the instruction issuing, that is, the adjustment effect, under each working condition can be obtained.

[0092] Further, the integral gain parameter of the PID algorithm is adjusted according to the average adjustment effect of the final cluster to which the current time belongs. Specifically, the data point composed of the monitoring data of each to-be-analyzed category at the current time is obtained, denoted as the target data point; the distances between the target data point and the cluster centers of the final clusters are calculated respectively, to obtain the final cluster with the smallest distance, that is, the cluster to which the target data point belongs, that is, the final cluster to which the current time belongs.

[0093] After obtaining the final cluster to which the current time belongs, the average adjustment effect of the final cluster to which the current time belongs under the current working condition is obtained . Because the integral gain parameter in the PID algorithm is the size of the stable value reached after the engine servo system responds, the integral gain parameter value of the PID algorithm at the current time is adjusted according to the difference between the PID control result and the set target value under the current working condition .​​

[0094] The proportional coefficient is obtained by comparing the average adjustment effect of the final cluster to which the current moment belongs with the maximum value of the absolute values of the average adjustment effects of each final cluster, and the adjusted gain integral parameter at the current moment is obtained by adding the proportional coefficient to the first preset value and multiplying the result by the original integral gain parameter.

[0095] The calculation model of the adjusted gain integral parameter is specifically:

[0096] ,

[0097] wherein, represents the adjusted gain integral parameter at the current moment, represents the average adjustment effect of the final cluster to which the current moment belongs, represents the maximum value of the absolute values of the average adjustment effects of each final cluster, and max represents a maximum value operation, represents the proportional coefficient, which is used to control the adjustment degree of the integral gain parameter and avoid system instability caused by excessively large adjustment degree, represents the original PID integral gain parameter value. Thus, the adjusted gain integral parameter at the current moment can be obtained.

[0098] In summary, the present application analyzes the influence relationship between the PID control algorithm parameters and the control effect under different working conditions according to the historical data of the engine, so as to realize self-adaptive adjustment of the PID parameters according to the working condition of the engine and improve the stability and efficiency of the engine servo system control.

[0099] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The above describes a specific embodiment of the present application. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

[0100] Each embodiment in the present application is described in a progressive manner, and the same or similar parts of each embodiment can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0101] The above only describes the preferred embodiments of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method of controller optimization processing for an engine servo system, characterized by, The method comprises: acquiring different kinds of monitoring data and environmental data during engine operation in history; screening the kinds of monitoring data to obtain kinds to be analyzed, and clustering the monitoring data of the kinds to be analyzed to obtain initial clusters and initial cluster centers; segmenting the monitoring data according to the variation degree of each monitoring data of a kind to be analyzed in an initial cluster to obtain monitoring data segments; and obtaining the influence degree of each kind of environmental data on the kind to be analyzed based on the kind of environmental data corresponding to each monitoring data segment in time sequence; calculating the average of the influence degree of each kind of environmental data on the kind to be analyzed in each initial cluster to obtain the average influence degree of the kind of environmental data on the kind to be analyzed; obtaining the influence degree of the kind to be analyzed on the initial cluster center at a time point based on the average influence degree of each kind of environmental data on the kind to be analyzed, the kinds of environmental data at the time point and the current time point; and updating the initial cluster center based on the influence degree of each kind to be analyzed on the initial cluster center at each time point in each initial cluster to obtain a final cluster; obtaining the adjustment effect after each instruction is issued in history; obtaining the average adjustment effect of each final cluster based on the adjustment effect after each instruction is issued in the final cluster; and adjusting the integral gain parameter based on the average adjustment effect of the final cluster to which the current time point belongs.

2. The method of claim 1, wherein the controller optimization process is for an engine servo system. The screening of the kinds of monitoring data to obtain the kinds to be analyzed comprises: processing the different kinds of monitoring data during engine operation in history by using a principal component analysis method to obtain characteristic values of each kind of monitoring data, and taking the set number of kinds with the largest characteristic values as the kinds to be analyzed.

3. The method of claim 1, wherein: The segmentation of the monitoring data according to the variation degree of each monitoring data of a kind to be analyzed in an initial cluster comprises: arranging each monitoring data of a kind to be analyzed in an initial cluster in ascending order to obtain an arrangement sequence; obtaining the difference between the latter monitoring data and the former data in two adjacent monitoring data in the arrangement sequence and normalizing the difference to obtain the variation degree of the latter monitoring data; taking the monitoring data with a variation degree greater than a first threshold value as a demarcation point, and segmenting the arrangement sequence by using the demarcation point to obtain monitoring data segments.

4. The method of claim 1, wherein: The obtaining of the influence degree of each kind of environmental data on the kind to be analyzed based on the kind of environmental data corresponding to each monitoring data segment in time sequence comprises: obtaining the average of the kind of environmental data corresponding to a monitoring data segment in time sequence as the environmental average corresponding to the monitoring data segment; calculating the absolute value of the sum of the difference between the environmental average corresponding to each two adjacent monitoring data segments, and taking the average to obtain the average variation of the environmental data; calculating the reciprocal of the average of the standard deviation of the kind of environmental data corresponding to each monitoring data segment in time sequence, denoted as the environmental data stability; multiplying the average variation of the environmental data and the environmental data stability and normalizing to obtain the influence degree of the kind of environmental data on the kind to be analyzed.

5. The method of claim 1 wherein the controller optimization process is for an engine servo system. The obtaining of the influence degree of the kind to be analyzed on the initial cluster center at a time point based on the average influence degree of each kind of environmental data on the kind to be analyzed, the kinds of environmental data at the time point and the current time point comprises: Obtain the absolute value of the difference between environmental data at a historical moment and the environmental data at the current moment, add it to the hyperparameter, and then calculate the inverse to obtain the environmental similarity. Multiply the environmental similarity corresponding to that historical moment by the average influence of that environmental data on a category to be analyzed to obtain the first feature value corresponding to that environmental data at that moment. Sum the first feature values ​​corresponding to each type of environmental data at that moment to obtain the influence of that category to be analyzed on the initial cluster center at that moment.

6. The method of claim 1, wherein: The process of updating the initial cluster centers based on the influence of each type to be analyzed at each time point on the initial cluster centers, to obtain the final clusters, includes: The influence weight of a species to be analyzed on the initial cluster center at a given time is obtained by comparing the influence of a species to be analyzed on the initial cluster center at a given time within an initial cluster with the sum of the influence of the species to be analyzed on the initial cluster center at all times within the initial cluster. The average monitoring data of a species to be analyzed at each time step is weighted and averaged to obtain the average monitoring data value corresponding to that species. Similarly, the average monitoring data values ​​corresponding to other species to be analyzed are obtained. The data points composed of the average monitoring data values ​​of all species to be analyzed in the initial cluster are the first-updated initial cluster centers corresponding to the initial cluster centers of the initial cluster. Clustering is performed based on the first-updated initial cluster centers corresponding to the initial cluster centers of each initial cluster to obtain the first clustering result. This process is repeated to update the first-updated initial cluster centers in the first clustering result until the data points in the clusters no longer change, at which point the update stops, and the final cluster is obtained.

7. The method of claim 1 wherein the controller optimization process is for an engine servo system. The process of obtaining the adjustment effect after each instruction was issued in history includes: The parameters that need to be controlled for the engine are recorded as control parameters. The difference between the stable control parameters after the engine control parameters have stabilized after each command is issued in history and the set target control parameters is obtained as the adjustment effect after each command is issued.

8. The method of claim 1, wherein: The step of obtaining the average adjustment effect of a final cluster based on the adjustment effect after each instruction is issued in the final cluster includes: Based on the historical times when instructions were issued, the time of instruction issuance in each final cluster is searched to obtain the instruction issuance time in each final cluster; the reciprocal of the distance between the data point corresponding to the instruction issuance time in a final cluster and the cluster center of the final cluster is obtained, and it is recorded as the weight of the data point corresponding to the instruction issuance time; the adjustment effect after each instruction issuance in the final cluster is weighted and averaged using the weight of the data point corresponding to each instruction issuance time, and the weighted average value is recorded as the average adjustment effect of the final cluster.

9. The method of claim 1, wherein: The adjustment of the integral gain parameter based on the average adjustment effect of the final cluster to which it belongs at the current time includes: The data point of each to-be-analyzed category of monitoring data at the current moment is obtained, and is recorded as a target data point; the distance between the target data point and the cluster center of each final cluster is calculated respectively, and the final cluster with the minimum distance is the final cluster to which the current moment belongs; the proportional coefficient is obtained by comparing the average adjustment effect of the final cluster to which the current moment belongs with the maximum value of the absolute values of the average adjustment effects of the final clusters; the proportional coefficient is added to the first preset value and multiplied by the original integral gain parameter to obtain the adjusted gain integral parameter at the current moment.

Images