Construction hoist control method and system

Abstract

The application relates to the field of elevator technology and discloses an elevator control method and system for building construction, which comprises the following steps: acquiring a first liquid level position of a hydraulic cylinder when the elevator is not working, acquiring a second liquid level position and operation data when the elevator is working, judging whether to adjust the liquid level fluctuation value based on the relationship between the liquid level fluctuation value and a historical operation database, determining a fluctuation adjustment factor of the liquid level fluctuation value based on the historical operation database or a decision tree model, determining the association result of the operation data and the hydraulic cylinder based on the historical operation database and an association rule algorithm, acquiring all historical adjustment behaviors corresponding to the fluctuation adjustment factor, adjusting the liquid level fluctuation value based on the fluctuation compensation coefficient and the fluctuation adjustment factor, and completing the work of the elevator according to the adjusted liquid level fluctuation value. The application ensures the stability and reliability of the elevator control by determining the liquid level position of the hydraulic cylinder.

Description

Technical Field

[0001] The present invention relates to the technical field of elevators, and in particular to a method and system for controlling an elevator for construction. Background Art

[0002] During construction, elevators are critical equipment for transporting workers and materials. Traditional elevators are typically controlled by hydraulic cylinders. As elevators are used for longer periods of time, the hydraulic level in the cylinders fluctuates. This can range from the initial shock at startup to speed adjustment during operation and braking during stops. Control of the hydraulic cylinders often relies on manual operation and personal experience, with no ability to dynamically adjust based on actual conditions. The lack of a feedback mechanism makes the hydraulic cylinders susceptible to human influence, resulting in deficiencies in the elevator's stability and reliability.

[0003] Therefore, it is necessary to design a construction elevator control method and system to solve the problems existing in the current technology. Summary of the Invention

[0004] In view of this, the present invention proposes a control method and system for a construction elevator, which aims to solve the problem that the control of the hydraulic cylinder often relies on the operator's manual operation and personal experience, cannot be dynamically adjusted according to actual conditions, and lacks a feedback adjustment mechanism, which makes the hydraulic cylinder susceptible to human influence and causes insufficient stability and reliability of the elevator.

[0005] In one aspect, the present invention provides a method for controlling a construction elevator, comprising:

[0006] Acquire a first liquid level position of the hydraulic cylinder when the elevator is not operating, and acquire a second liquid level position and operating data when the elevator is operating;

[0007] determining a liquid level fluctuation value based on the first liquid level position and the second liquid level position, determining whether to adjust the liquid level fluctuation value based on a relationship between the liquid level fluctuation value and a historical operation database, and determining a fluctuation adjustment factor for the liquid level fluctuation value based on the historical operation database or a decision tree model when it is determined that the liquid level fluctuation value should be adjusted;

[0008] When determining the fluctuation adjustment factor of the liquid level fluctuation value based on the decision tree model, determining the association result between the operation data and the hydraulic cylinder based on the historical operation database and the association rule algorithm, and determining the fluctuation adjustment factor based on the association result;

[0009] Acquire all historical adjustment behaviors corresponding to the fluctuation adjustment factor, analyze all historical adjustment behaviors, determine the fluctuation compensation coefficient of the fluctuation adjustment factor based on the analysis results, adjust the liquid level fluctuation value based on the fluctuation compensation coefficient and the fluctuation adjustment factor, and complete the work of the elevator according to the adjusted liquid level fluctuation value.

[0010] Furthermore, when determining the liquid level fluctuation value based on the first liquid level position and the second liquid level position, and determining whether to adjust the liquid level fluctuation value based on the relationship between the liquid level fluctuation value and a historical operation database, the method includes:

[0011] Obtaining an absolute value of a difference between the second liquid level position and the first liquid level position, and determining the absolute value of the difference as the liquid level fluctuation value;

[0012] The historical operation database includes a historical liquid level fluctuation average, a plurality of historical operation data and a plurality of historical data sets, and each historical operation data corresponds to a historical data set, and the historical data set includes a historical liquid level fluctuation value and a historical fluctuation adjustment factor;

[0013] When the liquid level fluctuation value is greater than the historical liquid level fluctuation average, determining to adjust the liquid level fluctuation value;

[0014] When the liquid level fluctuation value is less than or equal to the historical liquid level fluctuation average value, it is determined that the liquid level fluctuation value is not adjusted, and the work of the elevator is completed with the current liquid level fluctuation value.

[0015] Furthermore, when it is determined to adjust the liquid level fluctuation value, determining the fluctuation adjustment factor of the liquid level fluctuation value based on the historical operation database or the decision tree model includes:

[0016] When there is historical operation data identical to the operation data in the historical operation database, determining a fluctuation adjustment factor of the liquid level fluctuation value based on the historical operation database;

[0017] When the historical operation data identical to the operation data does not exist in the historical operation database, a fluctuation adjustment factor of the liquid level fluctuation value is determined based on the decision tree model.

[0018] Furthermore, when the historical operation database contains historical operation data identical to the operation data, determining the fluctuation adjustment factor of the liquid level fluctuation value based on the historical operation database includes:

[0019] When there is historical operation data identical to the operation data in the historical operation database, and the historical liquid level fluctuation value corresponding to the historical operation data is identical to the liquid level fluctuation value, then determining the historical fluctuation adjustment factor corresponding to the historical operation data as the fluctuation adjustment factor of the liquid level fluctuation value;

[0020] When there is historical operation data identical to the operation data in the historical operation database, and the historical liquid level fluctuation value corresponding to the historical operation data is different from the liquid level fluctuation value, a fluctuation adjustment factor of the liquid level fluctuation value is determined based on a clustering algorithm.

[0021] Furthermore, when determining the fluctuation adjustment factor of the liquid level fluctuation value based on the clustering algorithm, it includes:

[0022] The operating data, liquid level fluctuation values ​​and historical operating database are used as the data sets to be clustered, and the historical fluctuation adjustment factors corresponding to the historical liquid level fluctuation values ​​in the data sets to be clustered are extracted, the expected number of clusters k is determined to be 2, and the parameters of the Gaussian distribution are initialized, the probability that each data in the data sets to be clustered belongs to each Gaussian distribution is determined, and the responsibility value is obtained. According to the responsibility value, a cluster set corresponding to the operating data and liquid level fluctuation values ​​is obtained, and the mean of the historical fluctuation adjustment factors in the cluster set is used as the fluctuation adjustment factor of the liquid level fluctuation value.

[0023] Furthermore, when determining the association result between the operation data and the hydraulic cylinder based on the historical operation database and the association rule algorithm, and determining the fluctuation adjustment factor based on the association result, the method includes:

[0024] The historical operation database and the operation data are used to generate a plurality of candidate item sets based on the Eclat algorithm, a frequent item set is determined according to the support of the candidate item set, the association result is determined based on the frequent item set, the historical operation database and the association result are constructed into a model data set, a decision tree model is determined based on the model data set, and the fluctuation adjustment factor is output according to the decision tree model.

[0025] Furthermore, when determining a decision tree model based on the model data set and outputting the fluctuation adjustment factor according to the decision tree model, the method includes:

[0026] The model data set is divided into a training set and a test set, a grid search is used to find model parameters of a decision tree model, a decision tree model is established, the decision tree model is trained using the training set, the test set is substituted into the decision tree model and the accuracy is determined; when the accuracy is greater than or equal to an accuracy threshold, the operating data and the liquid level fluctuation value are substituted into the trained decision tree model and the fluctuation adjustment factor is output; otherwise, the decision tree model is continued to be trained until the accuracy is greater than or equal to the accuracy threshold.

[0027] Furthermore, when all historical adjustment behaviors corresponding to the volatility adjustment factor are obtained and analyzed, and the volatility compensation coefficient of the volatility adjustment factor is determined based on the analysis results, the following steps are included:

[0028] Analyzing all historical adjustment behaviors to determine adjustment overflow behaviors, normal adjustment behaviors, and under-adjustment behaviors, determining fluctuation adjustment factors corresponding to all adjustment overflow behaviors and constructing a first adjustment set, determining fluctuation adjustment factors corresponding to all under-adjustment behaviors and constructing a second adjustment set, counting a first number of fluctuation adjustment factors in the first adjustment set, and counting a second number of fluctuation adjustment factors in the second adjustment set;

[0029] The fluctuation compensation coefficient of the fluctuation adjustment factor is determined according to the ratio of the first quantity to the second quantity.

[0030] Furthermore, when adjusting the liquid level fluctuation value based on the fluctuation compensation coefficient and the fluctuation adjustment factor, the method includes:

[0031] The liquid level fluctuation value is directly proportional to the fluctuation adjustment factor, and the fluctuation adjustment factor is directly proportional to the fluctuation compensation coefficient.

[0032] Compared with the prior art, the present invention has the following beneficial effects: by obtaining the first liquid level position of the hydraulic cylinder when the elevator is not operating and the second liquid level position when it is operating, as well as operating data, it is possible to accurately determine the liquid level fluctuation value in real time. A judgment is made based on the relationship between the liquid level fluctuation value and the historical operation database. When adjustment is required, the fluctuation adjustment factor is determined using the historical operation database or a decision tree model. This ensures the control stability of historical experience control and data-driven control, enables the control of the hydraulic cylinder to adapt to different working conditions, improves the accuracy of elevator control, avoids control instability caused by traditional manual operation or human judgment errors, and analyzes the correlation between operating data and the hydraulic cylinder through an association rule algorithm, which can mine potential patterns and causal relationships. It reduces the interference of human factors and improves the intelligence level of the entire control. According to the fluctuation adjustment factor, all corresponding historical adjustment behaviors are determined and analyzed, and the adjustment process of the liquid level fluctuation value is further optimized. The historical adjustment behavior contains the adjustment experience under various working conditions in the past. By analyzing it, the results of different adjustment strategies can be identified, so that the fluctuation adjustment factor can be compensated and corrected in a targeted manner, realizing the fine adjustment of the liquid level fluctuation value, suppressing the impact of the elevator at startup, speed fluctuation during operation, and unstable braking when stopping, thereby improving the overall stability of the elevator operation and realizing precise control of the elevator.

[0033] On the other hand, the present application also provides a construction elevator control system, which is used to apply the above construction elevator control system, including:

[0034] a collecting unit configured to obtain a first liquid level position of the hydraulic cylinder when the elevator is not operating, and obtain a second liquid level position and operation data when the elevator is operating;

[0035] an analyzing unit configured to determine a liquid level fluctuation value based on the first liquid level position and the second liquid level position, determine whether to adjust the liquid level fluctuation value based on a relationship between the liquid level fluctuation value and a historical operation database, and, when it is determined that the liquid level fluctuation value should be adjusted, determine a fluctuation adjustment factor for the liquid level fluctuation value based on the historical operation database or a decision tree model;

[0036] a processing unit configured to, when determining the fluctuation adjustment factor of the liquid level fluctuation value based on the decision tree model, determine an association result between the operation data and the hydraulic cylinder based on the historical operation database and an association rule algorithm, and determine the fluctuation adjustment factor based on the association result;

[0037] A control unit is configured to obtain all historical adjustment behaviors corresponding to the fluctuation adjustment factor, analyze all historical adjustment behaviors, determine the fluctuation compensation coefficient of the fluctuation adjustment factor based on the analysis result, adjust the liquid level fluctuation value based on the fluctuation compensation coefficient and the fluctuation adjustment factor, and complete the work of the elevator according to the adjusted liquid level fluctuation value.

[0038] It is understandable that the above-mentioned construction elevator control method and system have the same beneficial effects, which will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0040] Figure 1 A flowchart of a construction elevator control method provided by an embodiment of the present invention;

[0041] Figure 2 This is a functional block diagram of a construction elevator control system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, unless there is a conflict, the embodiments of the present disclosure and the features described in the embodiments may be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0043] In some embodiments of this application, see Figure 1 As shown, a method for controlling a construction elevator includes:

[0044] S100: Acquire a first liquid level position of the hydraulic cylinder when the elevator is not working, and acquire a second liquid level position and operation data when the elevator is working.

[0045] S200: Determine the liquid level fluctuation value based on the first liquid level position and the second liquid level position, determine whether to adjust the liquid level fluctuation value based on the relationship between the liquid level fluctuation value and the historical operation database, and when it is determined to adjust the liquid level fluctuation value, determine the fluctuation adjustment factor of the liquid level fluctuation value based on the historical operation database or the decision tree model.

[0046] S300: When determining the fluctuation adjustment factor of the liquid level fluctuation value based on the decision tree model, the association result between the operation data and the hydraulic cylinder is determined based on the historical operation database and the association rule algorithm, and the fluctuation adjustment factor is determined based on the association result.

[0047] S400: Obtain all historical adjustment behaviors corresponding to the fluctuation adjustment factor, analyze all historical adjustment behaviors, determine the fluctuation compensation coefficient of the fluctuation adjustment factor based on the analysis results, adjust the liquid level fluctuation value based on the fluctuation compensation coefficient and the fluctuation adjustment factor, and complete the work of the elevator according to the adjusted liquid level fluctuation value.

[0048] Specifically, during the control process of a construction elevator, data collection is first performed to obtain the first liquid level position of the hydraulic cylinder when the elevator is not working. This position is the liquid level reference when the hydraulic system is in a static equilibrium state, providing a stable reference point for subsequent dynamic analysis. When the elevator is working, the second liquid level position of the hydraulic cylinder and operating data are obtained. The operating data covers parameters such as the elevator's speed, load weight, and operating direction. The liquid level fluctuation value is determined based on the first liquid level position and the second liquid level position. The liquid level fluctuation value can intuitively reflect the changes in the liquid level in the hydraulic cylinder when the elevator is working, and this change is closely related to the operating status of the elevator. For example, the impact at startup, speed adjustment during operation, and braking operation at stop will all cause the liquid level to fluctuate to varying degrees. The historical operation database stores a large amount of information such as the liquid level fluctuation values, corresponding operating data, and corresponding adjustment strategies of the previous elevator operations. By analyzing the relationship between the current fluid level fluctuation value and the data in the historical operation database, it is possible to determine whether the current fluid level fluctuation is within a reasonable range. If adjustment is determined, a fluctuation adjustment factor for the fluid level fluctuation value is determined based on either the historical operation database or a decision tree model. When using the historical operation database, the fluctuation adjustment factor is determined by directly searching the database for historical cases that are similar to the current fluid level fluctuation value and operating data. When using the decision tree model, an association rule algorithm is first used to analyze the operating data and hydraulic cylinder status in the historical operation database to determine the association between the operating data and the hydraulic cylinder. The association rule algorithm can uncover potential connections between different operating data parameters and their impact on the hydraulic cylinder fluid level fluctuation. For example, it was found that when the load weight exceeds a certain threshold and the operating speed is high, the fluid level fluctuation increases. The fluctuation adjustment factor is then determined based on these association results.

[0049] It is understandable that after determining the fluctuation adjustment factor, all historical adjustment behaviors corresponding to the fluctuation adjustment factor are obtained. These historical adjustment behaviors include the specific operations and effect feedback for adjusting the liquid level fluctuation value in similar situations in the past. By analyzing these historical adjustment behaviors, the fluctuation compensation coefficient of the fluctuation adjustment factor is determined. The fluctuation compensation coefficient is a further optimization and correction of the fluctuation adjustment factor. It takes into account the influence of uncertain factors in the actual adjustment process, ensures the accuracy of the adjustment, and adjusts the liquid level fluctuation value based on the fluctuation compensation coefficient and the fluctuation adjustment factor. According to the adjusted liquid level fluctuation value, the working state of the hydraulic cylinder can be accurately controlled, thereby completing the work of the elevator, avoiding the control of the hydraulic cylinder being affected by the instability of human experience, and ensuring the stability and safety of the elevator during the start-up, operation and stop stages.

[0050] In some embodiments of the present application, when determining the liquid level fluctuation value based on the first liquid level position and the second liquid level position, and judging whether to adjust the liquid level fluctuation value based on the relationship between the liquid level fluctuation value and the historical operation database, it includes: obtaining the absolute value of the difference between the second liquid level position and the first liquid level position, and determining the absolute value of the difference as the liquid level fluctuation value, the historical operation database includes the historical liquid level fluctuation average, a number of historical operation data and a number of historical data sets, and each historical operation data corresponds to a historical data set, the historical data set includes the historical liquid level fluctuation value and the historical fluctuation adjustment factor, when the liquid level fluctuation value is greater than the historical liquid level fluctuation average, it is determined to adjust the liquid level fluctuation value, when the liquid level fluctuation value is less than or equal to the historical liquid level fluctuation average, it is determined not to adjust the liquid level fluctuation value, and the work of the elevator is completed with the current liquid level fluctuation value.

[0051] Specifically, by obtaining the absolute value of the difference between the second liquid level position of the hydraulic cylinder when the elevator is working and the first liquid level position when it is not working, it is determined as the liquid level fluctuation value. The use of absolute value calculation can eliminate the difference in the direction of the liquid level rising or falling, and only focus on the amplitude of the fluctuation, ensuring the uniformity of the data. When the real-time calculated liquid level fluctuation value is greater than the historical liquid level fluctuation mean, it indicates that the elevator cannot brake in time and the impact force is large. It is then determined that the current fluctuation is beyond the normal range and needs to be adjusted. If it is less than or equal to the historical liquid level fluctuation mean, it reflects that the elevator can brake softly and ensure the safety of personnel, and no adjustment is required. Through historical mean quantification, the accumulation of errors in human experience that may cause safety risks is avoided, and the operational stability of the elevator is improved.

[0052] In some embodiments of the present application, when determining to adjust the liquid level fluctuation value, the fluctuation adjustment factor of the liquid level fluctuation value is determined based on the historical operation database or the decision tree model, including: when there is historical operation data identical to the operation data in the historical operation database, the fluctuation adjustment factor of the liquid level fluctuation value is determined based on the historical operation database; when there is no historical operation data identical to the operation data in the historical operation database, the fluctuation adjustment factor of the liquid level fluctuation value is determined based on the decision tree model.

[0053] Specifically, the system determines the degree of match between current conditions and historical successful conditions. When matching historical operating data is found, this data can be directly used to determine the fluctuation adjustment factor, thereby ensuring the reliability and consistency of control. In cases where current conditions do not fully match historical data, the fluctuation adjustment factor of the liquid level fluctuation value is determined based on the decision tree model to respond to changes in conditions. Through data-driven automated adjustments, reliance on human experience and intuition is reduced. The combination of historical data and decision tree models not only ensures control under normal operating conditions, but also has the ability to adapt to new operating conditions. This reduces the uncertainty and operational risks caused by human judgment, thereby improving the automation level and accuracy of control.

[0054] In some embodiments of the present application, when there is historical operation data identical to the operation data in the historical operation database, the fluctuation adjustment factor of the liquid level fluctuation value is determined based on the historical operation database, including: when there is historical operation data identical to the operation data in the historical operation database, and the historical liquid level fluctuation value corresponding to the historical operation data is the same as the liquid level fluctuation value, then the historical fluctuation adjustment factor corresponding to the historical operation data is determined as the fluctuation adjustment factor of the liquid level fluctuation value; when there is historical operation data identical to the operation data in the historical operation database, and the historical liquid level fluctuation value corresponding to the historical operation data is different from the liquid level fluctuation value, then the fluctuation adjustment factor of the liquid level fluctuation value is determined based on the clustering algorithm.

[0055] Specifically, when the historical operation database contains identical operating data and the historical liquid level fluctuation values ​​are identical to the current fluctuation values, the corresponding historical fluctuation adjustment factors are directly reused. This allows for the precise reuse of the operating condition-fluctuation-adjustment mapping. When the operating data is identical but the historical liquid level fluctuation values ​​differ from the current liquid level fluctuation values ​​(i.e., the fluctuation amplitudes differ under similar operating conditions), the historical operation database is analyzed using a clustering algorithm. Essentially, the clustering algorithm uses data clustering to discover the implicit association between the fluctuation amplitudes and adjustment strategies under similar operating conditions, thereby achieving precise adaptation of the liquid level fluctuation values ​​and enhancing the adaptive capability of elevator control in complex operating conditions.

[0056] In some embodiments of the present application, when determining the fluctuation adjustment factor of the liquid level fluctuation value based on the clustering algorithm, it includes: taking the operating data, the liquid level fluctuation value and the historical operating database as the data sets to be clustered, and extracting the historical fluctuation adjustment factors corresponding to the historical liquid level fluctuation values ​​in the data sets to be clustered, determining the expected number of clusters k to be 2, and initializing the parameters of the Gaussian distribution, determining the probability that each data in the data sets to be clustered belongs to each Gaussian distribution, obtaining the responsibility value, obtaining the cluster set corresponding to the operating data and the liquid level fluctuation value according to the responsibility value, and taking the mean of the historical fluctuation adjustment factors in the cluster set as the fluctuation adjustment factor of the liquid level fluctuation value.

[0057] Specifically, the historical operation database is analyzed through a clustering algorithm to find the cluster set closest to the current conditions, which improves the accuracy of determining the fluctuation adjustment factor and ensures that the liquid level fluctuation value can be adaptively adjusted under different conditions, thereby ensuring the stability of the elevator control, reducing dependence on manual experience and judgment, reducing human errors in operation, and improving the overall automation level and reliability.

[0058] In some embodiments of the present application, when determining the association results between operation data and hydraulic cylinders based on a historical operation database and an association rule algorithm, and determining a fluctuation adjustment factor based on the association results, it includes: generating several candidate item sets based on the Eclat algorithm from the historical operation database and the operation data, determining frequent item sets based on the support of the candidate item sets, determining the association results based on the frequent item sets, constructing the historical operation database and the association results into a model data set, determining a decision tree model based on the model data set, and outputting the fluctuation adjustment factor according to the decision tree model.

[0059] Specifically, historical operating data and the hydraulic cylinder's status (historical fluid level fluctuations) are used as transaction items, and candidate item sets are generated based on the Eclat algorithm (a vertical mining algorithm for equivalence class transformation). The Eclat algorithm generates frequent item sets through a vertical data structure (the intersection of TID sets). It can automatically mine hidden association patterns from massive amounts of historical data, thereby discovering potential parameter combinations and providing a data foundation for appropriate adjustments. The decision tree model transforms association rules into an intuitive logic tree. When encountering new operating conditions not previously recorded, the decision tree can generate adjustment data through the generalization capabilities of association rules. Even if the historical data cannot be fully matched, the Eclat algorithm can still provide relevant data support for the emerging operating condition, thereby improving the safety of the elevator and ensuring good stability during operation.

[0060] In some embodiments of the present application, when determining a decision tree model based on a model data set and outputting a fluctuation adjustment factor according to the decision tree model, it includes: dividing the model data set into a training set and a test set, using grid search to find model parameters of the decision tree model, establishing a decision tree model, using the training set to train the decision tree model, substituting the test set into the decision tree model and determining the accuracy rate, when the accuracy rate is greater than or equal to the accuracy rate threshold, substituting the operating data and the liquid level fluctuation value into the trained decision tree model and outputting the fluctuation adjustment factor, otherwise, continuing to train the decision tree model until the accuracy rate is greater than or equal to the accuracy rate threshold.

[0061] Specifically, the model dataset records the operating conditions of the elevator over different time periods and is divided into a training set and a test set. Typically, 50%-70% of the data is used as the training set, and the remainder as the test set. Ensuring that both the training and test sets contain data from a variety of operating conditions improves the model's generalization. GridSearch is used to find the model parameters for the decision tree model. GridSearch exhaustively searches the parameter space for optimal parameter combinations, such as the number of trees and the maximum tree depth. The decision tree model is trained using the training set data. By ensembling multiple decision trees and averaging their predictions, the decision tree model reduces the risk of overfitting and improves model accuracy and stability. The test set data is then fed into the trained decision tree model to determine its accuracy. Accuracy reflects the model's performance on unseen data and is an important metric for evaluating model performance. Once the model reaches or exceeds the accuracy threshold, the operating data and liquid level fluctuation values ​​are substituted into the trained decision tree model and the fluctuation adjustment factor is output. Otherwise, the decision tree model continues training until the accuracy reaches or exceeds the threshold. Using the training set to train the decision tree model fully leverages the elevator's operational history and enhances the model's predictive capabilities. The incorporation of grid search ensures the stability of the model, resulting in consistent and reliable performance across diverse datasets. During the model training and validation process, continuous parameter adjustments and performance verification ultimately resulted in a highly accurate model, improving the accuracy of the model's predictions and ensuring the stability and safety of elevator control.

[0062] In some embodiments of the present application, when acquiring all historical adjustment behaviors corresponding to the fluctuation adjustment factor, analyzing all historical adjustment behaviors, and determining the fluctuation compensation coefficient of the fluctuation adjustment factor based on the analysis results, it includes: analyzing all historical adjustment behaviors, determining adjustment overflow behaviors, normal adjustment behaviors, and insufficient adjustment behaviors, determining the fluctuation adjustment factors corresponding to all adjustment overflow behaviors, and constructing a first adjustment set, determining the fluctuation adjustment factors corresponding to all insufficient adjustment behaviors, and constructing a second adjustment set, counting a first number of fluctuation adjustment factors in the first adjustment set, counting a second number of fluctuation adjustment factors in the second adjustment set, and determining the fluctuation compensation coefficient of the fluctuation adjustment factor according to the ratio of the first number to the second number.

[0063] Specifically, historical adjustment behaviors include adjustment overflow behaviors, normal adjustment behaviors, and under-adjustment behaviors. In the actual adjustment process, even if adjustments are made according to the determined fluctuation adjustment factor, adjustment overflow behaviors and under-adjustment behaviors may occur, and they are not fixed. The ratio Q of the first quantity and the second quantity is determined. When Q≤1, the first preset fluctuation compensation coefficient is used as the fluctuation compensation coefficient of the fluctuation adjustment factor. When 1<Q≤1.5, the second preset fluctuation compensation coefficient is used as the fluctuation compensation coefficient of the fluctuation adjustment factor. When 1.5<Q, the third preset fluctuation compensation coefficient is used as the fluctuation compensation coefficient of the fluctuation adjustment factor. The first preset fluctuation compensation coefficient is preferably 1.2, the second preset fluctuation compensation coefficient is preferably 0.9, and the third preset fluctuation compensation coefficient is preferably 0.6. The fluctuation compensation coefficient of the fluctuation adjustment factor is determined according to the first quantity and the second quantity. By determining the fluctuation compensation coefficient, dynamic adjustment of the fluctuation adjustment factor is achieved, the phenomenon of adjustment overflow behaviors and under-adjustment behaviors is avoided, and intelligent adjustment of the elevator control is achieved.

[0064] In some embodiments of the present application, when adjusting the liquid level fluctuation value based on the fluctuation compensation coefficient and the fluctuation adjustment factor, it includes: the liquid level fluctuation value and the fluctuation adjustment factor are in direct proportion, and the fluctuation adjustment factor and the fluctuation compensation coefficient are in direct proportion.

[0065] Specifically, the liquid level fluctuation value is adjusted according to the fluctuation adjustment factor, and the fluctuation adjustment factor is adjusted according to the fluctuation compensation coefficient. Assuming that the basic liquid level fluctuation value is L, the adjustment coefficient is Z, and the adjustment factor is G, the adjusted liquid level fluctuation value is determined to be L×Z×G. Through the dual adjustment of the fluctuation adjustment factor and the fluctuation compensation coefficient, precise control of the liquid level fluctuation value is achieved, reducing the interference and error of human judgment, and improving the adaptability and reliability of the liquid level fluctuation value under dynamic changes, so that it can be adjusted according to actual needs, thereby ensuring the stability of the elevator control.

[0066] In summary, the beneficial effect of the present invention is that by obtaining the first liquid level position of the hydraulic cylinder when the elevator is not working and the second liquid level position and operation data when the elevator is working, the liquid level fluctuation value can be accurately determined in real time. Based on the relationship between the liquid level fluctuation value and the historical operation database, judgment is made. When adjustment is required, the fluctuation adjustment factor is determined using the historical operation database or decision tree model, ensuring the control stability of historical experience control and data-driven control, allowing the control of the hydraulic cylinder to adapt to different working conditions, improving the accuracy of elevator control, avoiding traditional manual operation or control instability caused by human judgment errors, and analyzing the correlation results between operation data and hydraulic cylinders through association rule algorithms to discover potential laws and causal relationships. It reduces the interference of human factors and improves the intelligence level of the entire control. According to the fluctuation adjustment factor, all corresponding historical adjustment behaviors are determined and analyzed, and the adjustment process of the liquid level fluctuation value is further optimized. The historical adjustment behavior contains the adjustment experience under various working conditions in the past. By analyzing it, the results of different adjustment strategies can be identified, so that the fluctuation adjustment factor can be compensated and corrected in a targeted manner, realizing the fine adjustment of the liquid level fluctuation value, suppressing the impact of the elevator at startup, speed fluctuation during operation, and unstable braking when stopping, thereby improving the overall stability of the elevator operation and realizing precise control of the elevator.

[0067] In another preferred embodiment based on the above embodiment, refer to Figure 2 As shown, this embodiment provides a construction elevator control system for applying the above construction elevator control method, including:

[0068] The acquisition unit is configured to obtain a first liquid level position of the hydraulic cylinder when the elevator is not working, and to obtain a second liquid level position and operation data when the elevator is working.

[0069] The analysis unit is configured to determine a liquid level fluctuation value based on a first liquid level position and a second liquid level position, determine whether to adjust the liquid level fluctuation value based on a relationship between the liquid level fluctuation value and a historical operation database, and when it is determined to adjust the liquid level fluctuation value, determine a fluctuation adjustment factor of the liquid level fluctuation value based on the historical operation database or a decision tree model.

[0070] The processing unit is configured to determine the association result between the operation data and the hydraulic cylinder based on the historical operation database and the association rule algorithm when determining the fluctuation adjustment factor of the liquid level fluctuation value based on the decision tree model, and determine the fluctuation adjustment factor based on the association result.

[0071] The control unit is configured to obtain all historical adjustment behaviors corresponding to the fluctuation adjustment factor, analyze all historical adjustment behaviors, determine the fluctuation compensation coefficient of the fluctuation adjustment factor based on the analysis result, adjust the liquid level fluctuation value based on the fluctuation compensation coefficient and the fluctuation adjustment factor, and complete the work of the elevator according to the adjusted liquid level fluctuation value.

[0072] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0073] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0074] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0075] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A method for controlling a construction elevator, characterized in that: include: Acquire a first liquid level position of the hydraulic cylinder when the elevator is not operating, and acquire a second liquid level position and operating data when the elevator is operating; determining a liquid level fluctuation value based on the first liquid level position and the second liquid level position, determining whether to adjust the liquid level fluctuation value based on a relationship between the liquid level fluctuation value and a historical operation database, and determining a fluctuation adjustment factor for the liquid level fluctuation value based on the historical operation database or a decision tree model when it is determined that the liquid level fluctuation value should be adjusted; When determining the fluctuation adjustment factor of the liquid level fluctuation value based on the decision tree model, determining the association result between the operation data and the hydraulic cylinder based on the historical operation database and the association rule algorithm, and determining the fluctuation adjustment factor based on the association result; Acquiring all historical adjustment behaviors corresponding to the fluctuation adjustment factor, analyzing all historical adjustment behaviors, determining a fluctuation compensation coefficient of the fluctuation adjustment factor based on the analysis results, adjusting the liquid level fluctuation value based on the fluctuation compensation coefficient and the fluctuation adjustment factor, and completing the operation of the elevator according to the adjusted liquid level fluctuation value; When determining the fluctuation adjustment factor of the liquid level fluctuation value based on the clustering algorithm, it includes: The operating data, liquid level fluctuation values, and a historical operating database are used as a data set to be clustered, and historical fluctuation adjustment factors corresponding to historical liquid level fluctuation values ​​in the data set to be clustered are extracted. The expected number of clusters k is determined to be 2, and the parameters of the Gaussian distribution are initialized. The probability that each data in the data set to be clustered belongs to each Gaussian distribution is determined to obtain a responsibility value. Based on the responsibility value, a cluster set corresponding to the operating data and liquid level fluctuation values ​​is obtained, and the mean of the historical fluctuation adjustment factors in the cluster set is used as the fluctuation adjustment factor of the liquid level fluctuation value. When determining the association result between the operation data and the hydraulic cylinder based on the historical operation database and the association rule algorithm, and determining the fluctuation adjustment factor based on the association result, the method includes: The historical operation database and the operation data are used to generate a plurality of candidate item sets based on the Eclat algorithm, a frequent item set is determined according to the support of the candidate item set, the association result is determined based on the frequent item set, the historical operation database and the association result are constructed into a model data set, a decision tree model is determined based on the model data set, and the fluctuation adjustment factor is output according to the decision tree model.

2. The construction elevator control method according to claim 1, characterized in that: When determining a liquid level fluctuation value based on the first liquid level position and the second liquid level position, and determining whether to adjust the liquid level fluctuation value based on a relationship between the liquid level fluctuation value and a historical operation database, the method includes: Obtaining an absolute value of a difference between the second liquid level position and the first liquid level position, and determining the absolute value of the difference as the liquid level fluctuation value; The historical operation database includes a historical liquid level fluctuation average, a plurality of historical operation data and a plurality of historical data sets, and each historical operation data corresponds to a historical data set, and the historical data set includes a historical liquid level fluctuation value and a historical fluctuation adjustment factor; When the liquid level fluctuation value is greater than the historical liquid level fluctuation average, determining to adjust the liquid level fluctuation value; When the liquid level fluctuation value is less than or equal to the historical liquid level fluctuation average value, it is determined that the liquid level fluctuation value is not adjusted, and the work of the elevator is completed with the current liquid level fluctuation value.

3. The construction elevator control method according to claim 2, characterized in that: When it is determined to adjust the liquid level fluctuation value, determining the fluctuation adjustment factor of the liquid level fluctuation value based on the historical operation database or the decision tree model includes: When there is historical operation data identical to the operation data in the historical operation database, determining a fluctuation adjustment factor of the liquid level fluctuation value based on the historical operation database; When the historical operation data identical to the operation data does not exist in the historical operation database, a fluctuation adjustment factor of the liquid level fluctuation value is determined based on the decision tree model.

4. The construction elevator control method according to claim 3, characterized in that: When the historical operation database contains historical operation data identical to the operation data, determining the fluctuation adjustment factor of the liquid level fluctuation value based on the historical operation database includes: When there is historical operation data identical to the operation data in the historical operation database, and the historical liquid level fluctuation value corresponding to the historical operation data is identical to the liquid level fluctuation value, then determining the historical fluctuation adjustment factor corresponding to the historical operation data as the fluctuation adjustment factor of the liquid level fluctuation value; When there is historical operation data identical to the operation data in the historical operation database, and the historical liquid level fluctuation value corresponding to the historical operation data is different from the liquid level fluctuation value, a fluctuation adjustment factor of the liquid level fluctuation value is determined based on a clustering algorithm.

5. The construction elevator control method according to claim 4, characterized in that: When determining a decision tree model based on the model data set and outputting the fluctuation adjustment factor according to the decision tree model, the method includes: The model data set is divided into a training set and a test set, a grid search is used to find model parameters of a decision tree model, a decision tree model is established, the decision tree model is trained using the training set, the test set is substituted into the decision tree model and the accuracy is determined; when the accuracy is greater than or equal to an accuracy threshold, the operating data and the liquid level fluctuation value are substituted into the trained decision tree model and the fluctuation adjustment factor is output; otherwise, the decision tree model is continued to be trained until the accuracy is greater than or equal to the accuracy threshold.

6. The construction elevator control method according to claim 5, characterized in that: Acquiring all historical adjustment behaviors corresponding to the volatility adjustment factor, analyzing all historical adjustment behaviors, and determining the volatility compensation coefficient of the volatility adjustment factor based on the analysis results includes: Analyzing all historical adjustment behaviors to determine adjustment overflow behaviors, normal adjustment behaviors, and under-adjustment behaviors, determining fluctuation adjustment factors corresponding to all adjustment overflow behaviors and constructing a first adjustment set, determining fluctuation adjustment factors corresponding to all under-adjustment behaviors and constructing a second adjustment set, counting a first number of fluctuation adjustment factors in the first adjustment set, and counting a second number of fluctuation adjustment factors in the second adjustment set; The fluctuation compensation coefficient of the fluctuation adjustment factor is determined according to the ratio of the first quantity to the second quantity.

7. The construction elevator control method according to claim 6, characterized in that: When adjusting the liquid level fluctuation value based on the fluctuation compensation coefficient and the fluctuation adjustment factor, the method includes: The liquid level fluctuation value is directly proportional to the fluctuation adjustment factor, and the fluctuation adjustment factor is directly proportional to the fluctuation compensation coefficient.

8. A construction elevator control system, for applying the construction elevator control method according to any one of claims 1 to 7, characterized in that: include: a collecting unit configured to obtain a first liquid level position of the hydraulic cylinder when the elevator is not operating, and obtain a second liquid level position and operation data when the elevator is operating; an analyzing unit configured to determine a liquid level fluctuation value based on the first liquid level position and the second liquid level position, determine whether to adjust the liquid level fluctuation value based on a relationship between the liquid level fluctuation value and a historical operation database, and, when it is determined that the liquid level fluctuation value should be adjusted, determine a fluctuation adjustment factor for the liquid level fluctuation value based on the historical operation database or a decision tree model; a processing unit configured to, when determining the fluctuation adjustment factor of the liquid level fluctuation value based on the decision tree model, determine an association result between the operation data and the hydraulic cylinder based on the historical operation database and an association rule algorithm, and determine the fluctuation adjustment factor based on the association result; A control unit is configured to obtain all historical adjustment behaviors corresponding to the fluctuation adjustment factor, analyze all historical adjustment behaviors, determine the fluctuation compensation coefficient of the fluctuation adjustment factor based on the analysis result, adjust the liquid level fluctuation value based on the fluctuation compensation coefficient and the fluctuation adjustment factor, and complete the work of the elevator according to the adjusted liquid level fluctuation value.

Images