Automatic control method for equipment in hydraulic station

Abstract

The invention discloses an automatic control method for equipment in a hydraulic station, and particularly relates to the technical field of automatic control of equipment, potential faults of main equipment are found in time by collecting operation data of a main hydraulic pump and conducting fault prediction, and the preloading process of a standby hydraulic pump is started according to the fault occurrence time; oil viscosity abnormal information and load increasing stability information in the pre-loading process of the standby hydraulic pump are obtained, and an oil viscosity abnormal coefficient and a load increasing stability coefficient are calculated based on the information, so that the stability of the standby pump in the switching process is effectively evaluated, the working state of the standby pump is comprehensively analyzed, potential loading hidden dangers are recognized in advance, and the working efficiency of the standby pump is improved. And corresponding control is carried out through output of the risk model, equipment failure or system instability caused by improper switching is avoided, the switching risk of the standby hydraulic pump is dynamically judged according to comparison of the standby switching hidden danger risk index and the preset threshold value, and stable operation and seamless switching of the hydraulic system are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment automation control, and more specifically, to an automatic control method for equipment in a hydraulic station. Background Art

[0002] Hydraulic systems are widely used in various industrial equipment, such as in the fields of machinery manufacturing, aerospace, automobile production, metallurgy, etc., as an efficient means of energy transmission and control. A hydraulic station is a core component of a hydraulic system, mainly responsible for transmitting the power source to the actuators to complete various mechanical operations. During the normal operation of various equipment (such as hydraulic pumps, valves, actuators, etc.) in a hydraulic station, it is often necessary to ensure the stability, reliability, and high-efficiency response of the system. However, in the actual application of hydraulic systems, when the main equipment fails or needs to be switched to standby equipment due to reasons such as load fluctuations, how to ensure seamless switching and rapid response between equipment remains one of the technical problems. Traditional hydraulic station control systems often adopt a hard switching strategy, that is, directly unload the main equipment and then switch to the standby equipment, and the standby equipment usually has not been preheated or operated at a low load, resulting in problems such as startup delay and uneven oil temperature. This switching method cannot restore the high-efficiency response of the system in a short time, and in severe cases, it may even cause hydraulic shock or equipment failure, resulting in the interruption of production or operation, affecting production efficiency and equipment life. Summary of the Invention

[0003] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an automatic control method for equipment in a hydraulic station to solve the problems raised in the above background art.

[0004] To achieve the above object, the present invention provides the following technical solutions: An automatic control method for equipment in a hydraulic station, comprising the following steps: Step S1, collect the operation data of the main hydraulic pump, predict the failure occurrence time of the main hydraulic pump based on the operation data of the main hydraulic pump, and start the preloading process of the standby hydraulic pump according to the failure occurrence time; Step S2, obtain the abnormal oil viscosity information and load increasing stability information during the preloading process of the standby hydraulic pump; Step S3, construct a standby switching hidden danger risk model according to the abnormal oil viscosity information and load increasing stability information during the preloading process of the standby hydraulic pump, output a standby switching hidden danger risk index, and evaluate the potential loading hidden dangers during the preloading process of the standby hydraulic pump; Step S4, compare the standby switching hidden danger risk index with a preset standby switching hidden danger risk index threshold, and classify and control the hydraulic pump.

[0005] In a preferred embodiment, by installing high-precision sensors, the operating data of the main hydraulic pump is collected in real time, including temperature, pressure, flow rate, vibration, and oil viscosity; Data preprocessing of the collected operating data of the main hydraulic pump includes missing value processing and data standardization;

[0006] Take the fault occurrence time as the target variable, the operating data of the main hydraulic pump as the feature variable, and construct a feature vector based on the operating data of the main hydraulic pump; Construct a fault occurrence time prediction model: , where is the output of the fault occurrence time prediction model, is the weight vector is the transpose of is the feature variable, is the bias term; Construct the objective function; Use the historical operating data of the main hydraulic pump to train the fault occurrence time prediction model, and minimize the objective function to find the optimal weight vector and bias term ; Input the real-time collected operating data of the main hydraulic pump into the trained fault occurrence time prediction model to predict the fault occurrence time of the main hydraulic pump; The starting condition for starting the preloading process of the standby hydraulic pump according to the fault occurrence time is: , where is the current time, is the fault occurrence time, is the lead time required for preloading the standby hydraulic pump, indicates that if is numerically equal to start the preloading process of the standby hydraulic pump.

[0007] In a preferred embodiment, by obtaining the abnormal information of the oil viscosity during the preloading process of the standby hydraulic pump, analyze the oil viscosity condition during the preloading process of the standby hydraulic pump, and calculate the oil viscosity abnormal coefficient to measure the abnormal degree of the oil viscosity during the preloading process of the standby hydraulic pump; The acquisition logic of the oil viscosity abnormal coefficient is as follows: Collect the oil viscosity during the preloading process of the standby hydraulic pump through high-precision sensors to construct an oil viscosity time series: , where represents the oil viscosity collected at time t, t = {1, 2,..., T}, and T is a positive integer; Perform clustering analysis on the oil viscosity time series, and calculate the oil viscosity abnormal coefficient as follows: Step S21, determine the initial number of clustering centers SL using the silhouette coefficient method, and randomly select the oil viscosities at SL time points from the oil viscosity time series as the initial clustering centers; Step S22, calculate the Euclidean distance between the oil viscosity at each time point in the oil viscosity time series and the clustering centers, and assign the oil viscosity at each time point to the clustering center with the closest Euclidean distance; Step S23, calculate the average value of the oil viscosities in each clustering center and use it as the new clustering center coordinates; Step S24, repeat steps S22 and S23 to iteratively update the clustering centers until the clustering centers no longer change; Calculate the deviation between the oil viscosity at each time point and its corresponding clustering center: , where represents the deviation between the oil viscosity and its corresponding clustering center, represents the oil viscosity value at time point t, represents the oil viscosity value of the k-th clustering center; Calculate the oil viscosity anomaly coefficient: , where is the oil viscosity anomaly coefficient, is the deviation between the oil viscosity at time point t and its corresponding clustering center, time point of the oil viscosity value, is the time point included in the k-th clustering center.

[0008] In a preferred embodiment, by obtaining the load increasing stability information of the standby hydraulic pump during the preloading process, analyzing the load increasing stability situation of the standby hydraulic pump during the preloading process, and calculating the load increasing stability coefficient to measure the load increasing stability degree of the standby hydraulic pump during the preloading process; The acquisition logic of the load increasing stability coefficient is as follows: Gradually apply the system load to the standby hydraulic pump until the system load of the main hydraulic pump is reached, and record the system load values at different times and the response time of the standby hydraulic pump to the system load change at different times ; Calculate the load change speed: , where represents the load change speed at time t, is the system load value at time t, is the system load value at time t - 1, is the sampling time interval; Calculate the response lag time: , where is the response lag time, is the response time of the standby hydraulic pump to the change of system load, is the expected response time; Calculate the stable value of load increment at different times: , where represents the stable value of load increment at time t, is the system transfer function phase angle of, , where is the static gain of the system, is the time constant of the system, is the imaginary unit, is the angular frequency; Calculate the stable coefficient of load increment: , where is the stable coefficient of load increment, is the stable value of load increment at time r, is the time window size.

[0009] In a preferred embodiment, a standby switching hidden danger risk model is constructed according to the abnormal coefficient of oil viscosity and the stable coefficient of load increment, and a standby switching hidden danger risk index is output , and the formula on which the model is based is as follows , in the formula respectively represent the preset proportional coefficients of the abnormal coefficient of oil viscosity and the stable coefficient of load increment, and are all greater than 0.

[0010] In a preferred embodiment, in step S4, the standby switching hidden danger risk index is compared with the preset standby switching hidden danger risk index threshold, and the hydraulic pump is classified and controlled as follows: If the standby switching hidden danger risk index is greater than the standby switching hidden danger risk index threshold, the current standby hydraulic pump is marked as a switching risk device, and early warning maintenance is performed on the marked switching risk device; If the standby switching hidden danger risk index is less than or equal to the standby switching hidden danger risk index threshold, the standby hydraulic pumps not marked as switching risk devices are sorted from small to large according to the standby switching hidden danger risk index, a standby device switching sorting table is generated, and the standby device ranked first is switched.

[0011] The technical effects and advantages of the present invention: 1. By collecting the operation data of the main hydraulic pump and conducting fault prediction, the present invention can timely detect potential faults of the main equipment, and start the preloading process of the standby hydraulic pump according to the fault occurrence time. By obtaining the abnormal oil viscosity information and load increasing stability information during the preloading process of the standby hydraulic pump in real time, and calculating the abnormal oil viscosity coefficient and load increasing stability coefficient based on this, it effectively evaluates the stability of the standby pump during the switching process, comprehensively analyzes the working state of the standby pump. When the oil viscosity is abnormal or the load increasing is unstable, it can identify potential loading hazards in advance, and conduct corresponding control through the output of the risk model to avoid equipment failures or system instability caused by improper switching. According to the comparison between the standby switching hazard risk index and the preset threshold, it dynamically judges the switching risk of the standby hydraulic pump. In the case of high risk, it automatically gives early warnings and conducts maintenance to ensure that the performance of the standby equipment meets the switching requirements. When the risk is low, it preferentially selects the standby hydraulic pump with the lowest risk for switching to ensure the smooth operation and seamless switching of the hydraulic system. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] For the convenience of those skilled in the art to understand, the present invention will be further described below in conjunction with the accompanying drawings; Figure 1 It is a flowchart of the method of the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0013] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0014] Embodiment: Figure 1 A method for automatic control of equipment in a hydraulic station according to the present invention is given, including the following steps: Step S1, collect the operation data of the main hydraulic pump, predict the fault occurrence time of the main hydraulic pump based on the operation data of the main hydraulic pump, and start the preloading process of the standby hydraulic pump according to the fault occurrence time; Step S2, obtain the abnormal oil viscosity information and load increasing stability information during the preloading process of the standby hydraulic pump; Step S3, construct a standby switching hazard risk model according to the abnormal oil viscosity information and load increasing stability information during the preloading process of the standby hydraulic pump, output the standby switching hazard risk index, and evaluate the potential loading hazards during the preloading process of the standby hydraulic pump; Step S4, compare the standby switching hazard risk index with the preset standby switching hazard risk index threshold, and conduct classified control on the hydraulic pump; Step S1: Collect the operating data of the main hydraulic pump, predict the fault occurrence time of the main hydraulic pump based on the operating data of the main hydraulic pump, and start the preloading process of the standby hydraulic pump according to the fault occurrence time; By installing high-precision sensors, the operating data of the main hydraulic pump are collected in real time, including multiple parameters such as temperature, pressure, flow rate, vibration, and oil viscosity; It should be noted that the high-precision sensors for collecting the operating data of the main hydraulic pump include temperature sensors (such as thermocouples, RTDs, which can be installed at the outlet of the hydraulic pump to monitor the oil temperature of the hydraulic pump), pressure sensors (such as strain type pressure sensors, piezoresistive pressure sensors, which can be installed at the outlet of the hydraulic pump to monitor the output pressure in real time), flow sensors (such as vortex flow meters, electromagnetic flow meters, positive displacement flow sensors, which can be installed at the outlet of the hydraulic pump to monitor the flow rate of the pump output), vibration sensors (such as acceleration sensors, which can be installed on the surface of the hydraulic pump body to monitor the surface vibration signal of the hydraulic pump), and oil viscosity sensors (such as rotary viscosity sensors, oscillating viscosity sensors, which can be installed in the hydraulic oil tank to monitor the viscosity of the oil); Data preprocessing of the collected operating data of the main hydraulic pump includes missing value processing (if there is missing data, it can be filled with the mean value or other interpolation methods) and data standardization (since the data dimensions of different sensors are different, it is usually necessary to standardize the data. For example, Z-score standardization is adopted); Take the fault occurrence time as the target variable, take the operating data of the main hydraulic pump as the feature variables, and construct a feature vector based on the operating data of the main hydraulic pump: , where represents the feature vector at time t, respectively represent the temperature, pressure, flow rate, vibration, and oil viscosity at time t; Construct a fault occurrence time prediction model: , where is the output of the fault occurrence time prediction model (the output of the fault occurrence time prediction model is the fault occurrence time), is the weight vector is the transpose of is the feature variable, is the bias term; Construct an objective function: , where is the regularization term, which is used to prevent overfitting, is the prediction error of each sample, , is the total number of samples, is a hyperparameter, which is used to control the trade-off between the error and the model complexity; Train a fault occurrence time prediction model using the historical operation data of the main hydraulic pump, and minimize the objective function to find the optimal weight vector and the bias term ; Input the operation data of the main hydraulic pump collected in real time into the trained fault occurrence time prediction model to predict the fault occurrence time of the main hydraulic pump; The starting condition for starting the preloading process of the standby hydraulic pump according to the fault occurrence time is: , where is the current time, is the fault occurrence time, is the advance time required for the preloading of the standby hydraulic pump, indicates that if is numerically equal to , start the preloading process of the standby hydraulic pump; It should be noted that the above formulas are all calculated by taking the numerical values after dimensionless processing. Common methods for removing dimensions include Min-Max normalization, Z-Score standardization, etc., which will not be elaborated here; Step S2, obtain the abnormal oil viscosity information and load increasing stability information during the preloading process of the standby hydraulic pump; By obtaining the abnormal oil viscosity information during the preloading process of the standby hydraulic pump, analyze the oil viscosity situation during the preloading process of the standby hydraulic pump, and calculate the abnormal oil viscosity coefficient to measure the abnormal degree of the oil viscosity during the preloading process of the standby hydraulic pump; The acquisition logic of the abnormal oil viscosity coefficient is as follows: Construct an oil viscosity time series by collecting the oil viscosity during the preloading process of the standby hydraulic pump through a high-precision sensor: , where represents the oil viscosity collected at time t, t = {1, 2,..., T}, and T is a positive integer; Perform clustering analysis on the oil viscosity time series and calculate the abnormal oil viscosity coefficient as follows: Step S21, use the silhouette coefficient method to determine the initial number of clustering centers SL, and randomly select the oil viscosities at SL time points from the oil viscosity time series as the initial clustering centers; It should be noted that the silhouette coefficient method is a commonly used clustering effect evaluation method. By calculating the silhouette coefficient, it can help select the optimal initial clustering number. The silhouette coefficient is used to measure the compactness of each point with its similar points and the separation degree from the nearest class; the calculation formula of the silhouette coefficient is: , where represents the silhouette coefficient, is the average distance between the sample point and all other sample points in the same class, representing the cohesion of the sample point, The separation degree of a sample point is represented by the average distance between the sample point and all sample points in the nearest different class; by calculating the silhouette coefficient under different numbers of clusters, the number of clusters that maximizes the silhouette coefficient is selected as the initial number of cluster centers SL. Step S22: Calculate the Euclidean distance between the oil viscosity at each time point in the oil viscosity time series and the cluster centers, and assign the oil viscosity at each time point to the cluster center with the nearest Euclidean distance. In an optional example, calculate the Euclidean distance: for each time point t, calculate the Euclidean distance between the oil viscosity value and all cluster centers. , : , where is the oil viscosity value at time point t, is the oil viscosity value of the k-th cluster center. Step S23: Calculate the average value of the oil viscosity in each cluster center and use it as the new cluster center coordinates. Step S24: Repeat Step S22 and Step S23 to iteratively update the cluster centers until the cluster centers no longer change. Calculate the deviation between the oil viscosity at each time point and its corresponding cluster center: , where represents the deviation between the oil viscosity and its corresponding cluster center, represents the oil viscosity value at time point t, represents the oil viscosity value of the k-th cluster center. Calculate the oil viscosity anomaly coefficient: , where is the oil viscosity anomaly coefficient, is the deviation between the oil viscosity at time point t and its corresponding cluster center, time point of the oil viscosity value, is the time point included in the k-th cluster center; It should be noted that the above formulas are all calculated by taking the numerical value after dimensionless processing. Common methods for removing dimensions include Min-Max normalization, Z-Score standardization, etc., which will not be elaborated here; In the present invention, the abnormal coefficient of oil viscosity is a key indicator for measuring the abnormal degree of oil viscosity during the preloading process of the standby hydraulic pump. Oil viscosity is the resistance coefficient of the hydraulic oil flow in the hydraulic system, which directly affects the working efficiency of the hydraulic pump and the stability of the system. During the operation of the hydraulic system, the oil viscosity may be affected by various factors, such as temperature change, oil aging, load fluctuation, etc., thus affecting the working performance of the standby hydraulic pump. By calculating the abnormal coefficient of oil viscosity, potential hidden dangers can be identified in a timely manner, preventing the unstable operation of the standby pump caused by abnormal oil viscosity, so as to achieve more accurate and efficient fault warning and risk control. A larger abnormal coefficient of oil viscosity indicates that during the preloading process of the standby hydraulic pump, the oil viscosity has deviated significantly from the normal range, which may be caused by factors such as too low oil temperature, oil aging, and pollutants entering the system. When the oil viscosity increases abnormally, the working flow rate of the hydraulic pump will be affected, and the pressure fluctuation increases, which may lead to increased wear inside the pump body. In severe cases, it may even cause the hydraulic pump to jam or fail to start. Therefore, a larger abnormal coefficient of oil viscosity is a warning signal for potential faults in the standby pump system, reminding the system to pay special attention to the oil temperature and viscosity when performing standby switching, preventing the standby hydraulic pump from starting unstably or being unable to effectively carry the load due to too high oil viscosity. In contrast, a smaller abnormal coefficient of oil viscosity indicates that during the preloading process of the standby hydraulic pump, the change in oil viscosity is small and within the normal working range. This usually means that the hydraulic oil is in an ideal working state, and the standby pump can maintain stability and efficiency when taking over the load. A smaller abnormal coefficient indicates that the temperature control, filtration, and lubrication effects of the hydraulic system are good, the oil is not contaminated or overly aged, and the working load of the hydraulic pump can be smoothly transferred from the main pump to the standby pump, reducing the response delay during system switching and improving the efficiency and safety of the switching process. Evaluating potential loading hidden dangers during the preloading process of the standby hydraulic pump based on the abnormal coefficient of oil viscosity can provide real-time and accurate oil viscosity deviation information, helping the hydraulic system monitor the working state of the standby pump. By detecting abnormal changes in oil viscosity in a timely manner, potential working risks faced by the hydraulic pump can be identified in advance, such as the pump body being overloaded or having difficulty starting due to too high oil viscosity, or the pump body having insufficient lubrication and increased wear due to too low oil viscosity. In this way, the system can take corresponding preventive measures before problems occur, avoiding the ineffective switching of the standby pump or its long-term unstable operation, thereby improving the reliability and operating efficiency of the entire hydraulic system.

[0015] It should be noted that the operating state of the standby hydraulic pump is monitored in real time through high-precision sensors to obtain the oil viscosity data at each moment, and these data are constructed into a time series, representing the oil viscosity value collected at time point t. These data can not only provide a basis for subsequent fault prediction and performance evaluation, but also provide real-time feedback on abnormal conditions during the preloading process of the standby hydraulic pump. Next, clustering analysis is used to identify abnormal points in the oil viscosity data. Clustering analysis is an unsupervised learning method that can group the oil viscosity values in the time series and judge whether there are abnormal fluctuations by calculating the characteristic values of each clustering group. In clustering analysis, the number of clustering centers is first determined by the silhouette coefficient method. The silhouette coefficient method is a standard for evaluating the clustering effect, and it judges the most appropriate number of clusters by calculating the similarity between each data point and its clustering center. This method can not only maximize the compactness and separation of clustering, but also automatically select the appropriate number of clusters, thus ensuring the accuracy of clustering analysis. After determining the number of clusters, initial clustering centers are randomly selected from the oil viscosity time series, and the Euclidean distance between the oil viscosity at each time point and all clustering centers is calculated. The oil viscosity at each time point will be assigned to the closest clustering center according to its distance from the clustering center, and this process can divide the data into several groups with similar characteristics. As clustering progresses, continue to calculate the average value of the oil viscosity within each clustering center and use it as the new clustering center coordinates. This process will be repeated until the clustering centers tend to be stable, that is, the positions of the clustering centers no longer change. Through the above clustering analysis, the deviation between the oil viscosity at each time point and its affiliated clustering center can be calculated. The magnitude of the deviation directly reflects the abnormal degree of the oil viscosity at that time point. Generally speaking, if the deviation of the oil viscosity at a certain time point is large, it means that the oil viscosity at that moment is quite different from the normal state, which may indicate that there is an abnormality in the hydraulic system, such as too high or too low oil viscosity. Thus, the oil viscosity abnormality coefficient is further calculated.

[0016] By obtaining the load increasing stability information during the preloading process of the standby hydraulic pump, analyzing the load increasing stability situation during the preloading process of the standby hydraulic pump, and calculating the load increasing stability coefficient to measure the load increasing stability degree during the preloading process of the standby hydraulic pump; The acquisition logic of the load increasing stability coefficient is as follows: Gradually apply system load to the standby hydraulic pump until the system load of the main hydraulic pump is reached, and record the system load values at different times and the response time of the standby hydraulic pump to the system load change at different times ; Calculate the load change speed: , where represents the load change speed at time t, is the system load value at time t, is the system load value at time t-1, is the sampling time interval; Calculate the response lag time: , where is the response lag time, is the response time of the standby hydraulic pump to the system load change, is the expected response time; Calculate the load increase stability value at different times: , where represents the load increase stability value at time t, is the system transfer function of the phase angle, , where is the static gain of the system, is the time constant of the system, is the imaginary unit, is the angular frequency; It should be noted that the static gain of the system represents the proportional relationship between the system input and output, the time constant of the system is a parameter measuring the system response speed (set according to the time situation), is the imaginary unit ( ), the angular frequency represents the frequency of the load change; Calculate the load increase stability coefficient: , where is the load increase stability coefficient, is the load increase stability value at time r, is the time window size; It should be noted that the above formulas are all dimensionless and take their numerical values for calculation. Common methods for removing dimensions include Min-Max normalization, Z-Score standardization, etc., which will not be elaborated here; In the present invention, the load increasing stability coefficient is used to measure the stability degree of the load increase during the preloading process of the standby hydraulic pump. The load increasing stability coefficient reflects the response stability of the hydraulic pump when the load gradually increases, which is directly related to the working stability and reliability of the hydraulic system under load changes. A larger load increasing stability coefficient usually indicates that the system can maintain a stable response during the gradual increase of the load, the performance of the hydraulic pump is not overly affected by the load fluctuation, the system can smoothly bear the expected load, thus avoiding overload, vibration or other unstable phenomena. While a smaller load increasing stability coefficient may imply that there are response lags or instabilities during the load increase process of the system, which may lead to problems such as overheating of the pump, pressure fluctuations or equipment failures. Even in extreme cases, it may lead to the collapse of the system or equipment damage. Evaluating potential loading hazards during the preloading process of the standby hydraulic pump based on the load increasing stability coefficient has significant beneficial effects. First of all, the load increasing stability coefficient can provide a quantitative basis for the dynamic stability of the hydraulic system. At the initial stage of the startup of the standby hydraulic pump, the load increasing process of the system is usually relatively slow. If the standby hydraulic pump cannot stably adapt to the load change during this process, it may lead to the inability to cope with the main pump failure. At this time, the evaluation based on the load increasing stability coefficient can effectively monitor the stability of the system during the load increase process, provide timely warnings for the system, and improve the reliability and response speed of the standby pump.

[0017] It should be noted that a gradually increasing load is applied to the standby hydraulic pump until the load reaches the predetermined load level of the main hydraulic pump. The increase in load is carried out step by step to observe the response of the standby hydraulic pump at different load levels. At each load stage, the load value of the system and the response time of the standby hydraulic pump to the load change are recorded, and the load change speed at each time point is calculated. The load change speed reflects the speed of the system load change. The change of the load is usually gradual, but its change speed will have an important impact on the stability of the system. If the load change speed is too fast, the system may not be able to respond in time, resulting in instability or overload. Therefore, by calculating the load change speed, we can identify the load change trend that may cause system instability. The response lag time refers to the delay time for the standby hydraulic pump to respond to the load change. Due to the inertia of the hydraulic pump and the characteristics of the hydraulic oil, the response of the standby pump will not be instantaneous. Therefore, it is necessary to calculate the time required for the standby hydraulic pump to reach the expected response after the load change, further analyze the load increasing stability of the system, and use the phase angle of the system transfer function to calculate the load increasing stability value. The phase angle of the transfer function reflects the dynamic response characteristics of the system to the load change. By calculating the load increasing stability values at different time points, the instantaneous response ability of the system to the load change can be obtained. Finally, the load increasing stability coefficient is a quantitative evaluation of the overall performance of the load increasing stability within a time window. This coefficient evaluates the adaptability of the standby hydraulic pump to the load increase by calculating the load increasing stability values at each time point within this time window; Step S3, construct a standby switching hazard risk model based on the abnormal information of the oil viscosity and the load increasing stability information during the preloading process of the standby hydraulic pump, output the standby switching hazard risk index, and evaluate the potential loading hazards during the preloading process of the standby hydraulic pump; Construct a standby switching hazard risk model based on the abnormal coefficient of oil viscosity and the load increasing stability coefficient, and output the standby switching hazard risk index , and the formula on which the model is based is as follows , where respectively represent the preset proportional coefficients of the abnormal coefficient of oil viscosity and the load increasing stability coefficient, and are both greater than 0; It should be noted that the above formulas are all calculated by taking the numerical values after removing the dimensions. Common methods for removing dimensions include Min-Max normalization, Z-Score standardization, etc., which will not be elaborated here; It is set according to the actual situation. For example, the expert weighting method is adopted, that is, experts in related fields are invited to determine the preset proportional coefficients of each index through professional opinion surveys and comprehensive evaluations. For example, can be 0.5, 0.5; As can be seen from the above calculation expression, the greater the abnormal coefficient of oil viscosity and the smaller the stable coefficient of load increase, the greater the risk index of standby switching hidden danger. This indicates that the abnormal oil viscosity and unstable load increase are relatively serious, and there is a high risk in the preloading process of the standby hydraulic pump, which may lead to instability or even failure during the switching process. On the contrary, the smaller the abnormal coefficient of oil viscosity and the greater the stable coefficient of load increase, the smaller the risk index of standby switching hidden danger, indicating that the preloading process of the standby hydraulic pump is relatively stable, can smoothly take over the main pump load, and the hidden danger during the preloading process is small, and the switching operation can continue; In step S4, the risk index of standby switching hidden danger is compared with the preset risk index threshold of standby switching hidden danger, and the hydraulic pump is classified and controlled as follows: If the risk index of standby switching hidden danger is greater than the risk index threshold of standby switching hidden danger, it indicates that there is a high risk in the preloading process of the standby hydraulic pump. Mark the current standby hydraulic pump as a switching risk device and give early warning and maintenance to the marked switching risk device; If the risk index of standby switching hidden danger is less than or equal to the risk index threshold of standby switching hidden danger, it indicates that the preloading process of the standby hydraulic pump is relatively stable. Sort the standby hydraulic pumps that have not been marked as switching risk devices in ascending order of the risk index of standby switching hidden danger to generate a standby device switching sorting table, and perform the switching operation on the standby device ranked first.

[0018] By collecting the operation data of the main hydraulic pump and conducting fault prediction, the present invention can timely detect potential faults of the main equipment, start the preloading process of the standby hydraulic pump according to the fault occurrence time, obtain the abnormal information of oil viscosity and the stable information of load increase during the preloading process of the standby hydraulic pump in real time, calculate the abnormal coefficient of oil viscosity and the stable coefficient of load increase based on this, effectively evaluate the stability of the standby pump during the switching process, comprehensively analyze the working state of the standby pump, and can identify potential loading hidden dangers in advance when the oil viscosity is abnormal or the load increase is unstable, and perform corresponding control through the output of the risk model to avoid equipment failure or system instability caused by improper switching. According to the comparison between the risk index of standby switching hidden danger and the preset threshold, dynamically judge the switching risk of the standby hydraulic pump. In the case of high risk, automatically give early warning and maintenance to ensure that the performance of the standby equipment meets the switching requirements. When the risk is low, preferentially select the standby hydraulic pump with the minimum risk for switching to ensure the smooth operation and seamless switching of the hydraulic system.

[0019] The above formulas are all dimensionless and take their numerical values for calculation. The formula is obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formula are set by those skilled in the art according to the actual situation.

[0020] It should be understood that in various embodiments of the present application, the magnitudes of the serial numbers of the above processes do not imply the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0021] As described above, the above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, and all should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the said claims.

Claims

1. An automatic control method for equipment in a hydraulic station, characterized in that: It includes the following steps: Step S1: Collect the operation data of the main hydraulic pump, predict the fault occurrence time of the main hydraulic pump based on the operation data of the main hydraulic pump, and start the preloading process of the standby hydraulic pump according to the fault occurrence time; Step S2: Obtain the abnormal oil viscosity information and load increasing stability information during the preloading process of the standby hydraulic pump; Step S3: Construct a standby switching hidden danger risk model based on the abnormal oil viscosity information and load increasing stability information during the preloading process of the standby hydraulic pump, output the standby switching hidden danger risk index, and evaluate the potential loading hidden dangers during the preloading process of the standby hydraulic pump; Step S4: Compare the standby switching hidden danger risk index with the preset standby switching hidden danger risk index threshold, and perform classified control on the hydraulic pump.

2. The automatic control method for the equipment in a hydraulic station according to claim 1, wherein: By installing high-precision sensors, the operation data of the main hydraulic pump are collected in real time, including temperature, pressure, flow rate, vibration, and oil viscosity; Perform data preprocessing on the collected operation data of the main hydraulic pump, including missing value processing and data standardization; Take the fault occurrence time as the target variable, take the operation data of the main hydraulic pump as the feature variables, and construct a feature vector according to the operation data of the main hydraulic pump; Build a failure occurrence time prediction model: , where is the output of the failure occurrence time prediction model, is the weight vector transpose of, is the feature variable, is the bias term; Construct an objective function; Train a fault occurrence time prediction model using the historical operation data of the main hydraulic pump, and minimize the objective function to find the optimal weight vector and the bias term ; Input the operation data of the main hydraulic pump collected in real time into the trained fault occurrence time prediction model to predict the fault occurrence time of the main hydraulic pump; The starting conditions for initiating the preloading process of the standby hydraulic pump according to the fault occurrence time are as follows: , where is the current time, is the fault occurrence time, is the advance time required for the preloading of the standby hydraulic pump, indicates that if and are numerically equal, initiate the preloading process of the standby hydraulic pump.

3. A method for automatically controlling equipment in a hydraulic station according to claim 1, characterized in that: By obtaining the abnormal oil viscosity information during the preloading process of the standby hydraulic pump, analyze the oil viscosity condition during the preloading process of the standby hydraulic pump, and calculate the abnormal oil viscosity coefficient to measure the abnormal degree of the oil viscosity during the preloading process of the standby hydraulic pump; The acquisition logic of the abnormal oil viscosity coefficient is as follows: Construct the oil viscosity time series by collecting the oil viscosity during the preloading process of the standby hydraulic pump through a high-precision sensor: , where represents the oil viscosity collected at time t, t = {1, 2,..., T}, and T is a positive integer; Perform clustering analysis on the oil viscosity time series, and calculate the abnormal oil viscosity coefficient specifically as follows: Step S21: Use the silhouette coefficient method to determine the initial number of clustering centers SL, and randomly select the oil viscosities at SL time points from the oil viscosity time series as the initial clustering centers; Step S22: Calculate the Euclidean distance between the oil viscosity at each time point in the oil viscosity time series and the clustering centers, and assign the oil viscosity at each time point to the clustering center with the closest Euclidean distance; Step S23: Calculate the average value of the oil viscosities in each clustering center, and take it as the new clustering center coordinates; Step S24: Repeat Step S22 and Step S23 to iteratively update the clustering centers until the clustering centers no longer change; Calculate the deviation of the oil viscosity at each time point from its cluster center: , where represents the deviation of the oil viscosity from its cluster center, represents the oil viscosity value at time point t, represents the oil viscosity value of the k-th cluster center; Calculate the abnormal coefficient of oil viscosity: , where is the abnormal coefficient of oil viscosity, is the deviation of the oil viscosity at time point t from its cluster center, time point oil viscosity value of, is the time point included in the k-th cluster center.

4. A method for automatic control of equipment in a hydraulic station according to claim 1, characterized in that: By obtaining the load increasing stability information during the preloading process of the standby hydraulic pump, analyze the load increasing stability condition during the preloading process of the standby hydraulic pump, and calculate the load increasing stability coefficient to measure the load increasing stability degree during the preloading process of the standby hydraulic pump; The acquisition logic of the load increasing stability coefficient is as follows: Gradually apply the system load to the standby hydraulic pump until it reaches the system load of the main hydraulic pump, and record the system load values at different times and the response time of the standby hydraulic pump to the system load change at different times ; Calculate the load change rate: , where represents the load change rate at time t, is the system load value at time t, is the system load value at time t-1, is the sampling time interval; Calculate the response lag time: , where is the response lag time, is the response time of the standby hydraulic pump to the change of system load, is the expected response time; Calculate the load increasing stability value at different times: , where represents the load increasing stability value at time t, is the system transfer function of the phase angle, , where is the static gain of the system, is the time constant of the system, is the imaginary unit, is the angular frequency; Calculate the load increase stability coefficient: , where is the load increase stability coefficient, is the load increase stability value at time r, is the time window size.

5. The automated control method for the equipment in a hydraulic station according to claim 4, wherein: Construct a spare switch hidden danger risk model based on the abnormal coefficient of oil viscosity and the load increasing stability coefficient, and output the spare switch hidden danger risk index , the formula on which the model is based is as follows , where respectively represent the preset proportionality coefficients of the abnormal coefficient of oil viscosity and the load increasing stability coefficient, and are both greater than 0.

6. A method for automatically controlling equipment in a hydraulic station according to claim 1, characterized in that: In Step S4, compare the standby switching hidden danger risk index with the preset standby switching hidden danger risk index threshold, and perform classified control on the hydraulic pump, specifically as follows: If the standby switching hidden danger risk index is greater than the standby switching hidden danger risk index threshold, mark the current standby hydraulic pump as a switching risk device, and perform early warning maintenance on the marked switching risk device; If the risk index of standby switch hidden danger is less than or equal to the threshold value of the risk index of standby switch hidden danger, the standby hydraulic pumps that are not marked as equipment with switching risks are sorted in ascending order according to the risk index of standby switch hidden danger, a standby equipment switching sorting table is generated, and the switching operation is performed on the standby equipment ranked first.

Images