A method, device and equipment for evaluating rationality of hydraulic support selection

Abstract

The present application relates to the field of data processing, and provides a rationality evaluation method, device and equipment for hydraulic support selection, the method comprising: obtaining multiple monitoring indexes of the hydraulic support, and determining original indexes according to the monitoring indexes; the monitoring indexes include initial support force, step sequence final resistance, safety valve opening pressure, safety valve opening time, column subsidence, roof beam deflection angle and impact acceleration; the original indexes are normalized, the obtained standardized data is input into a trained neural network model, and a rationality prediction result is output; the rationality prediction result is scored based on a target function to obtain a score result, and the rationality grade of the hydraulic support selection is determined according to the score result. The present application solves the problem in the prior art that the evaluation of hydraulic support selection relies on a single static index and lacks dynamic multi-dimensional comprehensive analysis, realizes intelligent comprehensive evaluation based on multi-source monitoring data, and improves the rationality and accuracy of selection.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method, apparatus, and equipment for evaluating the rationality of hydraulic support selection. Background Technology

[0002] In coal mining, hydraulic supports are critical support equipment, and their selection directly affects the stability of the mine roof and operational safety. Hydraulic supports must provide reliable active support under complex geological conditions, controlling roof deformation and preventing delamination or collapse accidents. Traditional selection methods rely on on-site measurements and experience-based judgment, but the underground environment is harsh, and in-situ testing is costly, time-consuming, and risky. Therefore, laboratory simulation technology based on similarity theory has become an important means of optimizing hydraulic support selection. By reproducing real working conditions through physical models, it provides a scientific basis for selection decisions.

[0003] Currently, the rationality analysis of hydraulic support selection mainly relies on similar simulation experiments. However, simulation experiments suffer from insufficient model fidelity, making it difficult to realistically reconstruct the downhole support scenario, thus reducing the reliability of experimental data. Furthermore, existing methods mostly rely on static analysis of single indicators, lacking comprehensive quantitative indicators to determine the compatibility between the support and geological conditions.

[0004] Therefore, establishing a scientific comprehensive evaluation system for hydraulic system selection has become a key issue that the industry urgently needs to address. Summary of the Invention

[0005] This invention provides a method, apparatus, and equipment for evaluating the rationality of hydraulic support selection, which solves the problem that the evaluation of hydraulic support selection in the prior art relies on a single static index and lacks dynamic multi-dimensional comprehensive analysis. It realizes intelligent comprehensive evaluation based on multi-source monitoring data, thereby improving the rationality and accuracy of selection.

[0006] This invention provides a method for evaluating the rationality of hydraulic support selection, comprising the following steps:

[0007] Multiple monitoring indicators of the hydraulic support are obtained, and the original indicators are determined based on the monitoring indicators; the monitoring indicators include initial support force, end resistance of step sequence, safety valve opening pressure, safety valve opening time, column retraction, top beam offset angle, and impact acceleration;

[0008] The original indicators are normalized to obtain standardized data;

[0009] The standardized data is input into a trained neural network model, which outputs a reasonableness prediction result. The neural network model is trained based on a training set, which includes standardized data and reasonableness prediction labels corresponding to multiple monitoring indicators.

[0010] The rationality prediction results are scored based on the objective function to obtain a score result, and the rationality level of the hydraulic support selection is determined based on the score result; the objective function is designed based on the optimal range distribution law of multiple monitoring indicators.

[0011] According to the present invention, a method for evaluating the rationality of hydraulic support selection includes training a neural network model based on a training set. Specifically, this includes: constructing an initial neural network model; determining the consistency constraints of the neural network model based on the convergence time of each monitoring indicator; inputting the standardized data into the initial neural network model, training it based on the consistency constraints, and outputting predicted values; obtaining the difference between the predicted values ​​and the back supervision function value; if the difference is less than a preset threshold, temporarily stopping training and saving the trained neural network model; the back supervision function is used to force the neural network to follow physical laws during training and prediction through the consistency constraints; performing an objective function test on the predicted values ​​output by the neural network model; iteratively training the neural network model and performing an objective function test based on the neural network model obtained in each iteration; when the number of iterations reaches a preset number, ending the iteration loop and saving the trained neural network model.

[0012] According to the present invention, a method for evaluating the rationality of hydraulic support selection includes the following original indicators: dynamic load coefficient, drag increase rate of model support, drag increase rate deviation, drag increase fluctuation stability, initial support force compliance factor, step sequence final resistance ratio factor, relative deviation between the maximum and average values ​​of the pressure rise rate before the safety valve opens, safety valve opening time ratio, safety valve opening frequency evaluation coefficient, relative deviation between the maximum and average values ​​of the column retraction speed, top beam offset angle, top beam offset angular velocity deviation, and impact strength.

[0013] According to the present invention, a method for evaluating the rationality of hydraulic support selection includes determining the original indicators based on the monitoring indicators, specifically comprising: determining the dynamic load coefficient based on the rated working resistance and step-end resistance of the model support; determining the drag increase rate of the model support based on the initial support force and step-end resistance; determining the drag increase rate deviation and drag increase fluctuation stability based on the drag increase rate of the model support; determining the initial support force compliance factor based on the initial support force; determining the step-end resistance ratio factor based on the step-end resistance; determining the relative deviation between the maximum and average values ​​of the pressure rise rate before the safety valve opens based on the safety valve opening pressure; determining the safety valve opening time ratio based on the safety valve opening time and the time required for a complete step sequence; determining the safety valve opening frequency evaluation coefficient based on the safety valve opening time ratio; determining the relative deviation between the maximum and average values ​​of the column retraction speed based on the column retraction amount; determining the top beam offset angular velocity deviation based on the top beam offset angle; and determining the impact intensity based on the impact acceleration.

[0014] According to the present invention, a method for evaluating the rationality of hydraulic support selection, wherein determining the drag increase deviation and drag increase fluctuation stability based on the drag increase ratio of the model support specifically includes: obtaining the ideal value of the drag increase ratio of the model support; determining the drag increase deviation based on the drag increase ratio of the model support and the ideal value of the drag increase ratio of the model support; determining the standard deviation of the drag increase ratio of the model support based on the drag increase ratio of the model support; and determining the drag increase fluctuation stability based on the standard deviation of the drag increase ratio of the model support.

[0015] According to the present invention, a method for evaluating the rationality of hydraulic support selection includes determining the relative deviation between the maximum and average values ​​of the pressure rise rate before the safety valve opens based on the safety valve opening pressure. Specifically, this includes: determining a first pressure rise rate before the safety valve opens based on the safety valve opening pressure using a displacement fitting curve differentiation method, and obtaining a first average value of the pressure rise rate before the safety valve opens; determining a second pressure rise rate before the safety valve opens based on the safety valve opening pressure using an adjacent time displacement difference method, and obtaining a second average value of the pressure rise rate before the safety valve opens; determining a first relative error between the adjacent time displacement difference method and the displacement fitting curve differentiation method based on the first average value, the first pressure rise rate before the safety valve opens, the second average value, and the second pressure rise rate before the safety valve opens; and determining the relative deviation between the maximum and average values ​​of the pressure rise rate before the safety valve opens based on the comparison result between the first relative error and the critical value of the first relative error.

[0016] According to the present invention, a method for evaluating the rationality of hydraulic support selection includes determining the relative deviation between the maximum and average values ​​of the column retraction speed based on the column retraction amount. Specifically, this includes: determining a third column retraction speed based on the column retraction amount using a displacement fitting curve differentiation method, and obtaining a third average value of the column retraction speed; determining a fourth column retraction speed based on the column retraction amount using an adjacent-time displacement difference method, and obtaining a fourth average value of the column retraction speed; determining a second relative error between the adjacent-time displacement difference method and the displacement fitting curve differentiation method based on the third average value, the third column retraction speed, the fourth average value, and the fourth column retraction speed; and determining the relative deviation between the maximum and average values ​​of the column retraction speed based on a comparison between the second relative error and the critical value of the second relative error.

[0017] According to the present invention, a method for evaluating the rationality of hydraulic support selection, when obtaining the rationality prediction label, the method further includes: when the drag increase rate deviates by no less than a first deviation threshold and no more than a second deviation threshold, determining that the hydraulic support selection is unreasonable; when the drag increase rate deviates by more than the second deviation threshold and no more than a third deviation threshold, determining that the hydraulic support selection is at level two reasonable; and when the drag increase rate deviates by more than the third deviation threshold and no more than a fourth deviation threshold, determining that the hydraulic support selection is at level one reasonable.

[0018] According to the present invention, a method for evaluating the rationality of hydraulic support selection, when obtaining the rationality prediction label, the method further includes: when the resistance fluctuation stability is greater than a first stability threshold and not greater than a second stability threshold, determining that the hydraulic support selection is unreasonable; when the resistance fluctuation stability is greater than a second stability threshold and not greater than a third stability threshold, determining that the hydraulic support selection is at level two rationality; and when the resistance fluctuation stability is greater than a third stability threshold and not greater than a fourth stability threshold, determining that the hydraulic support selection is at level one rationality.

[0019] According to the present invention, a method for evaluating the rationality of hydraulic support selection, when obtaining the rationality prediction label, the method further includes: when the initial support force compliance factor is not greater than the ideal threshold, judging that the hydraulic support selection is unreasonable; when the initial support force compliance factor is greater than the ideal threshold, judging that the hydraulic support selection is reasonable.

[0020] According to the present invention, a method for evaluating the rationality of hydraulic support selection, when obtaining the rationality prediction label, the method further includes: when the step-end resistance ratio factor is not greater than a first percentage, determining that the hydraulic support selection is unreasonable; when the step-end resistance ratio factor is greater than the first percentage and not greater than a second percentage, determining that the hydraulic support selection is at level two rationality; when the step-end resistance ratio factor is greater than the second percentage and less than a third percentage, determining that the hydraulic support selection is at level one rationality.

[0021] According to the rationality evaluation method for hydraulic support selection provided by the present invention, when obtaining the rationality prediction label, the method further includes: when the relative deviation between the maximum value and the average value of the pressure rise rate before the safety valve opens is less than a first relative deviation threshold, the rationality of the hydraulic support selection is determined to be Level 1; when the relative deviation between the maximum value and the average value of the pressure rise rate before the safety valve opens is greater than the first relative deviation threshold but not greater than a second relative deviation threshold, the rationality of the hydraulic support selection is determined to be Level 2; when the relative deviation between the maximum value and the average value of the pressure rise rate before the safety valve opens is greater than the second relative deviation threshold, the rationality of the hydraulic support selection is determined to be unreasonable.

[0022] According to the present invention, a method for evaluating the rationality of hydraulic support selection, when obtaining the rationality prediction label, the method further includes: when the safety valve opening frequency evaluation coefficient is not less than a first evaluation coefficient threshold and not greater than a second evaluation coefficient threshold, determining that the hydraulic support selection is unreasonable; when the safety valve opening frequency evaluation coefficient is greater than the second evaluation coefficient threshold and less than a third evaluation coefficient threshold, determining that the hydraulic support selection is level one reasonable; when the safety valve opening frequency evaluation coefficient is not less than the third evaluation coefficient threshold, determining that the hydraulic support selection is level two reasonable.

[0023] According to the present invention, a method for evaluating the rationality of hydraulic support selection, when obtaining the rationality prediction label, the method further includes: when the relative deviation between the maximum value and the average value of the column retraction speed is not greater than a third relative deviation threshold, the hydraulic support selection is judged to be of Level 1 rationality; when the relative deviation between the maximum value and the average value of the column retraction speed is greater than the third relative deviation threshold but less than the fourth relative deviation threshold, the hydraulic support selection is judged to be of Level 2 rationality; when the relative deviation between the maximum value and the average value of the column retraction speed is not less than the fourth relative deviation threshold, the hydraulic support selection is judged to be unreasonable.

[0024] According to the present invention, a method for evaluating the rationality of hydraulic support selection, when obtaining the rationality prediction label, the method further includes: if the maximum angle of the top beam offset angle is less than the allowable offset angle, then the hydraulic support selection is judged to be reasonable; if the maximum angle of the top beam offset angle is not less than the allowable offset angle, then the hydraulic support selection is judged to be unreasonable.

[0025] According to the rationality evaluation method for hydraulic support selection provided by the present invention, when obtaining the rationality prediction label, the method further includes: when the deviation of the top beam offset angular velocity is not less than a first angular velocity deviation threshold and not greater than a second angular velocity deviation threshold, the rationality of the hydraulic support selection is determined to be unreasonable; when the deviation of the top beam offset angular velocity is greater than the second angular velocity deviation threshold and not greater than a third angular velocity deviation threshold, the rationality of the hydraulic support selection is determined to be level two reasonable; when the deviation of the top beam offset angular velocity is greater than the third angular velocity deviation threshold and not greater than a fourth angular velocity deviation threshold, the rationality of the hydraulic support selection is determined to be level one reasonable.

[0026] According to the present invention, a method for evaluating the rationality of hydraulic support selection, when obtaining the rationality prediction label, the method further includes: when the impact intensity is not greater than a first impact intensity threshold, determining that the rationality of the hydraulic support selection is Level 1; when the impact intensity is greater than the first impact intensity threshold and less than a second impact intensity threshold, determining that the rationality of the hydraulic support selection is Level 2; and when the impact intensity is not greater than the second impact intensity threshold, determining that the rationality of the hydraulic support selection is unreasonable.

[0027] This invention also provides a device for evaluating the rationality of hydraulic support selection, comprising the following modules:

[0028] The indicator acquisition module is used to acquire multiple monitoring indicators of the hydraulic support and determine the original indicators based on the monitoring indicators; the monitoring indicators include initial support force, end resistance of step sequence, safety valve opening pressure, safety valve opening time, column shrinkage, top beam offset angle, and impact acceleration.

[0029] The standardization module is used to normalize the original indicators to obtain standardized data;

[0030] The model prediction module is used to input the standardized data into a trained neural network model and output a reasonableness prediction result; the neural network model is trained based on a training set, which includes standardized data and reasonableness prediction labels corresponding to multiple monitoring indicators.

[0031] The rationality evaluation module is used to score the rationality prediction results based on the objective function to obtain a score result, and to determine the rationality level of the hydraulic support selection based on the score result; the objective function is designed based on the optimal range distribution law of multiple monitoring indicators.

[0032] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the rationality evaluation method for selecting hydraulic supports as described above.

[0033] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the rationality evaluation method for selecting hydraulic supports as described above.

[0034] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements a rationality evaluation method for selecting hydraulic supports as described above.

[0035] This invention provides a method, apparatus, and equipment for evaluating the rationality of hydraulic support selection, which offers the following advantages: By acquiring multi-dimensional dynamic monitoring indicators of the hydraulic support, normalizing the original indicators, and inputting them into a trained neural network model, a comprehensive evaluation based on artificial intelligence is achieved. Simultaneously, by designing an objective function that conforms to the optimal range distribution law, the prediction results are scored, and finally, the rationality level of the selection is output. This solution solves the problems of traditional methods relying on single static indicators and lacking systematic analysis, significantly improving the scientificity and accuracy of hydraulic support selection evaluation, and providing intelligent decision support for safe and efficient coal mining. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0037] Figure 1 This is a schematic diagram of the model support system provided by the present invention.

[0038] Figure 2 This is a schematic diagram of the data acquisition device provided by the present invention.

[0039] Figure 3 This is a schematic diagram of the power system structure of the pump station provided by the present invention.

[0040] Figure 4 This is a partial structural diagram of the power system of the pump station provided by the present invention.

[0041] Figure 5 This is a schematic diagram of the model support provided by the present invention.

[0042] Figure 6 This is a schematic diagram of the software monitoring interface provided by the present invention.

[0043] Figure 7 This is a schematic diagram of the parameter calibration of the model support provided by the present invention.

[0044] Figure 8 This is a schematic diagram of the parameter calibration and analysis of the model support provided by the present invention.

[0045] Figure 9 This is a flowchart illustrating the rationality evaluation method for hydraulic support selection provided by the present invention.

[0046] Figure 10 This is the relationship curve of the working resistance Pt provided by the present invention.

[0047] Figure 11 This is a schematic diagram illustrating the principle of solving the pressure rise rate before the safety valve opens, provided by the present invention.

[0048] Figure 12 This is a Pt curve diagram before and after the safety valve is opened, provided by the present invention.

[0049] Figure 13 This is the Sn-t relationship curve of the column shrinkage provided by the present invention.

[0050] Figure 14 This is a schematic diagram illustrating the principle of solving the top beam offset angular velocity provided by the present invention.

[0051] Figure 15 This is the impact acceleration a-t relationship curve provided by the present invention.

[0052] Figure 16 This is a schematic diagram illustrating the principle of solving the drag ratio of the model support at any time provided by the present invention.

[0053] Figure 17 This is a schematic diagram of the performance evaluation method for hydraulic supports provided by the present invention.

[0054] Figure 18 This is a schematic diagram showing the optimal performance range of the hydraulic support provided by the present invention.

[0055] Figure 19 This is a schematic diagram of the structure of the hydraulic support selection rationality evaluation device provided by the present invention.

[0056] Figure 20 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0058] In coal mine operations, hydraulic supports, by integrating hydraulic cylinders and hydraulic power units, provide reliable active support, effectively controlling roof deformation and suppressing the risks of roof delamination and collapse. Therefore, the appropriate selection of hydraulic supports in the field is a prerequisite for safe and efficient coal mining. The approach of transforming the adaptability of hydraulic supports under complex geological conditions into a more intuitive and controllable physical model analysis process has been widely adopted.

[0059] This method first maps the various performance indicators of candidate hydraulic supports, including but not limited to structural dimensions, load-bearing capacity, and support performance thresholds, to the geometric parameters and key performance indicators such as support strength and stiffness of a physical model support based on similarity theory. Through designed similarity simulation experiments, the field conditions are reproduced under laboratory conditions, thus replacing experiments that are difficult to implement due to field limitations or those that are predictive in the early stages of construction. This step not only significantly reduces the safety risks of in-situ downhole testing and effectively avoids many uncertainties, but also significantly reduces experimental and time costs.

[0060] However, in the existing hydraulic support selection rationality model experiments, the following technical bottlenecks still need to be addressed: ① The physical model of the hydraulic support differs significantly from the on-site prototype, generally exhibiting insufficient reproducibility. The simplified model architecture used as a substitute has fundamental differences in core elements such as mechanical structure design and hydraulic support system, making it difficult to reconstruct the real support scenario in the well; ② There is a lack of dynamic response characteristic analysis. In the field, the hydraulic support is in dynamic cyclic operation, but the existing model monitoring indicators lack the collection and analysis of process data, which cannot fully reflect the working condition adaptability of the model support and makes it difficult to accurately evaluate the rationality of the selection of hydraulic supports in the field.

[0061] To address the aforementioned technical challenges, this invention innovatively develops a novel model support with a high structural fiducial value and full-process construction simulation. By utilizing high-precision monitoring instruments on the model support to collect data, the support effectiveness of the hydraulic supports on-site under different parameter configurations can be accurately evaluated. Based on this detailed data feedback, it is possible to accurately determine whether the candidate hydraulic supports meet the actual on-site requirements, or which key performance indicators (such as support strength and working resistance) need further customization and optimization. This ensures that the final selected hydraulic support can perfectly adapt to the upcoming construction site, achieving efficient and safe support operations.

[0062] The following is combined Figures 1-20 The embodiments of the present invention are described in detail.

[0063] 1.1 Model Composition

[0064] like Figure 1 As shown, the model support system consists of four parts: a power system, a control device, a hydraulic support, and a vacuuming device.

[0065] like Figure 2 As shown, the hydraulic support model 23 is located at the simulated mining face. The pump station power system 21 is connected to the hydraulic control device 22 to provide power to the model device. The hydraulic control device 22 is connected to the support model 23 and can control the extension and retraction of the support column. The evacuation device 24 is connected to the control device 22 and can quickly drain the water from the model device.

[0066] (1) Power system

[0067] like Figure 3 As shown, the power system of the pumping station mainly includes pumps, a pressure regulator, and on / off valves (V0, V3, V6, V9, V12). The inlet provides water as the pressure transmission medium for the entire system. The pressurized water from the pumps is connected to the hydraulic control device via a conduit. The pumps can provide the required water pressure to the hydraulic system, providing sufficient power for the lifting and lowering of the model support, and allowing the setting of the overflow pressure (Pa, Pb, Pc, Pd) of the back pressure valve. The pressure regulator maintains a constant output pressure through an accumulator. During long-term support operations, the pumping station's power system may experience pressure fluctuations due to water leakage, temperature changes, or slow load variations. The pressure regulator automatically replenishes or releases pressure through dynamic adjustment, ensuring that the support force of the supports on the roof remains at the set value, guaranteeing the support effect. Simultaneously, the pressure regulator can coordinate the synchronous operation of multiple supports and improve the system's response speed.

[0068] (2) Control device

[0069] like Figure 4 As shown, the control device includes a five-way valve, a back pressure valve, switching valves (V1, V4, V7, V10), and pressure sensors (P1, P2, P3, P4). The first end of the five-way valve is connected to the booster pump via the switching valves (V1, V4, V7, V10) to provide power water pressure for the entire hydraulic control device; the second end of the five-way valve is connected to the lower end of the back pressure valve, which can transmit the pressure of the hydraulic control device to the back pressure valve; the third end of the five-way valve is connected to the model support, which can control the raising and lowering of the model support; the fourth end of the five-way valve is connected to the pressure sensors (P1, P2, P3, P4), which can accurately monitor the pressure in the column of the model support; the fifth end of the five-way valve is connected to the evacuation device, which can quickly evacuate the water in the entire hydraulic control device when the evacuation device is activated. The back pressure valve has a pressure of Pa (or Pb, Pc, Pd) at one end and P1 (or P2, P3, P4) at the other end. When P1 > Pa, the back pressure valve opens and the safety valve overflows.

[0070] (3) Evacuation device

[0071] like Figure 3 As shown, the evacuation device includes a vacuum pump, a water tank, and switching valves (V2, V5, V8, V11). One port of the water tank is connected to one port of a five-way valve via the switching valves (V2, V5, V8, V11). When the valves are opened, the hydraulic control device is connected to the evacuation device. The other port of the water tank is connected to the vacuum pump. When the vacuum pump starts, air is extracted from the water tank, creating negative pressure, and water from the hydraulic control device flows into the water tank along the conduit. Opening the switching valves allows the water in the hydraulic control device to be drained, enabling the rapid descent of the model support beam and the complete retraction of the columns.

[0072] (4) Hydraulic support

[0073] like Figure 5 As shown, the hydraulic support model mainly includes a top beam 1, two hydraulic cylinders 2, a water pipe 3, a base 4, and a protective device 7. The bottom ends of the cylinder bodies of the two hydraulic cylinders 2 are fixed to the base 4 at intervals, with their center lines parallel to the long side of the base and located in the center. The top ends of the piston rods of the hydraulic cylinders are connected and fixed to the top beam 1. The two hydraulic cylinders 2 are connected through the water pipe 3; the water pipe 3 is connected to the aforementioned hydraulic control device. The protective device 7 is fixed to the rear of the top beam with screws, providing protection for the data lines of the monitoring system below, preventing large rocks from collapsing and damaging the cables during the experiment.

[0074] 1.2 Monitoring System

[0075] like Figure 5 As shown, the model support condition monitoring device includes a pressure sensor 5, a laser rangefinder 6, an attitude detector 8, and an acceleration sensor 9.

[0076] like Figure 4 As shown, a pressure sensor P1 is connected to water pipe 3 to measure the pressure of the hydraulic cylinder of the model support, while another pressure sensor Pa is connected to the other end of the back pressure valve to measure the pressure of the back pressure valve in the control device. The pressure sensor readings can be processed by calculation software to provide the corresponding pressure.

[0077] The laser rangefinder 6 is mounted on the base 4, positioned on the center line of the two hydraulic cylinders, directly behind the cylinders, and perpendicular to the base to ensure the laser beam is aligned with the top beam. When the hydraulic cylinders drive the top beam to move, the laser rangefinder continuously emits laser light at a high frequency and receives reflected signals, allowing it to measure the displacement of the top beam and obtain dynamic data on the extension of the front and rear columns.

[0078] The attitude detector 8 is fixed below the top beam, inside the model support. It is a MEMS (Micro-Electro-Mechanical Systems) electronic accelerometer that senses the components of gravity along three coordinate axes (X / Y / Z), converting the acceleration signal into angle values. When the top beam tilts, the gravity components along each axis of the accelerometer change. Using the horizontal plane as a reference, the included angle is calculated based on the proportional relationship of the gravity components. , where a x a y and a z The triaxial angular velocity values ​​are measured by the accelerometer, and the included angle θ is the offset angle of the top beam.

[0079] Accelerometer 9 is positioned at the geometric center of the side of top beam 1 to ensure that the measurement point is located on the axis of structural symmetry, thus avoiding measurement deviations caused by asymmetrical loads or local deformations. It also ensures a rigid connection between the sensor and the top beam to prevent signal distortion due to loosening. The sensor's sensitive axis is strictly aligned with the vertical direction to monitor the instantaneous acceleration changes of the top beam in the vertical plane.

[0080] 1.3 Signal Processing System

[0081] like Figure 6 As shown, the signal processing system uses computer software to monitor and process data from pressure sensors, laser rangefinders, and attitude detectors in real time. The signal output terminals of the aforementioned sensors are connected to the computer via cables. The computer is equipped with a data storage device and a control interface. The data storage device is used to store the monitored and calculated data, and the control interface is used to control the working status of the hydraulic control device.

[0082] 2.1 Conversion of Technical Parameters for Simulated Stents

[0083] (1) Support strength and working resistance

[0084] After the physical experiment working face was excavated, a simulated support was used for roof support to simulate the construction of the support under actual conditions. To ensure that the test results were comparable to the measured data of the actual support on site, the measured support strength value of the model support was converted into the equivalent working resistance of the prototype support through the following conversion:

[0085]

[0086] In the formula, F0 represents the working resistance of the prototype support, in kN; p represents the support strength of the prototype support, in kPa.

[0087] Center distance of prototype bracket B, in meters; k The control distance of the prototype support, in meters; p', the test value of the support strength of the model support, in kPa; C σ Stress similarity ratio.

[0088] (2) Geometric parameters

[0089] Similarity model tests are conducted. The model support will undergo displacement during the simulated on-site support operations such as lowering, moving, and raising. The displacement of the model support in the experiment can be converted into the equivalent displacement of the on-site prototype support through geometric similarity ratio:

[0090]

[0091] In the formula, H represents the displacement of the prototype support, in meters (m); h represents the displacement of the model support, in meters (m); C represents the displacement of the prototype support. L It represents the geometric similarity ratio.

[0092] Based on equivalent conversion, the geometric parameters and support strength of the on-site hydraulic supports are transformed into test values ​​for laboratory model supports. Through laboratory-scale model experiments, detailed data support and scientific theoretical basis are provided for the rational selection and design of on-site hydraulic supports, ensuring that the selected model design can accurately match actual needs and effectively improve the working efficiency and safety of hydraulic supports.

[0093] 2.2 Parameter Calibration

[0094] like Figure 7 As shown, a calibration device was used to calibrate the working parameters of the model support. This device includes components such as a force sensor reaction frame and height adjustment pads. During the calibration process, the water pressure of the pump station was adjusted to change the water pressure on the column. The water pressure in the pump station was gradually increased from 0 MPa. The pressure sensor recorded the water pressure on the column, and the force sensor recorded the working resistance of the support. To verify the stability of the model support performance, each model support was calibrated repeatedly using the same method at least three times.

[0095] The repeatability calibration results should demonstrate that the test data exhibits good stability, and that the mechanical properties of the model support are stable and meet experimental requirements. The time history curve of the support's "column water pressure output load" is shown below. Figure 8 As shown. By Figure 8 It can be seen that the hydraulic pressure of the column and the output load of the support maintain a good linear relationship, and the linear regression correlation coefficient is required to reach 0.95 or above.

[0096] 2.3 Operational Steps for Obtaining Monitoring Indicators

[0097] A similar simulation experiment was conducted using four model supports (1#, 2#, 3#, and 4#) as a group to illustrate the experimental acquisition operations for each monitoring indicator. The overall data acquisition structure is as follows: Figure 3 As shown.

[0098] (1) After the working face of the physical similarity simulation experiment is cut, the hydraulic support model is placed into the simulated mining working face, the computer software is turned on, the signal monitoring system is started, and the equipment data is cleared.

[0099] (2) Open the water inlet and wait until the power pump is completely filled with clean water, then close the water inlet. Next, open the main switch valve V0 to prepare for the following operations.

[0100] (3) Set the opening pressure p of the safety valve k Open valves V3, V6, V9, and V12, and pressurize the system using a power pump until the readings of pressure sensors Pa, Pb, Pc, and Pd stabilize at the preset pressure value p. k .

[0101] (4) Control the columns of the model support to extend outward. During this process, V3, V6, V9, and V12 need to be closed, and V1, V4, V7, and V10 need to be opened. Pressurize again with the power pump to ensure that the model support can be raised smoothly.

[0102] (5) Set the initial support force of the model support to p0. After the top beam of the model support is in complete contact with the overlying rock layer, closely observe the changes in the readings of pressure sensors P1, P2, P3, and P4. Once the initial support force p0 is reached, immediately shut off V1, V4, V7, and V10 to maintain the stability of the support.

[0103] (6) After the excavation face is stabilized or the roof collapses, the safety valve of the model support is opened to obtain a stable step-end resistance p. m The vacuum device is activated, which causes the columns of the No. 1 and No. 3 model supports to descend rapidly and advance to the predetermined position. Adjustments are made to ensure that the model supports are accurately positioned.

[0104] (7) Subsequently, pressure was applied to the model support again by the power pump, so that the No. 1 and No. 3 top beams could quickly and effectively support the rock strata above the newly excavated working face, ensuring that the required initial support force p0 was achieved. Immediately afterwards, the No. 2 and No. 4 model supports were lowered, moved and raised in sequence to continue the entire support operation process.

[0105] (8) Wait for a period of time to observe the working status of the model support. After obtaining the displacement of the model support column and the deflection angle of the top beam, continue to excavate the working face forward. The model support will repeat the operation process of steps 6 and 7. Multiple experiments are conducted to avoid accidental errors.

[0106] To comprehensively evaluate the rationality of the selected prototype support, the geometric parameters and support strength of the prototype support were determined using similarity theory. Data on the dynamic changes of the model support were obtained through similarity simulation experiments, and various monitoring indicators were analyzed based on the data. If the model support meets the experimental requirements, it indicates that the prototype support can also meet the needs of coal mining; if some monitoring indicators of the model support do not meet the requirements, a more suitable prototype support will be selected based on the experimental results.

[0107] Figure 9 This is a flowchart illustrating the rationality evaluation method for hydraulic support selection provided by the present invention, as shown below. Figure 9 As shown, the method includes the following steps:

[0108] S910. Obtain multiple monitoring indicators of the hydraulic support and determine the original indicators based on the monitoring indicators.

[0109] The monitoring indicators include initial support force, end resistance of step sequence, safety valve opening pressure, safety valve opening time, column shrinkage, top beam offset angle, and impact acceleration.

[0110] 3.1 Initial support force P0

[0111] The initial support force, as the preset initial working resistance value of the model support, can be set manually based on theoretical calculations. Physical model experiments generally refer to the self-weight stress of the overlying rock strata.

[0112]

[0113] In the formula, This is the density of the rock, measured in kN / m³. 3 H represents the average thickness of the overlying strata, in meters (m); S represents the surface area of ​​the top beam of the model support, in square meters (m²). 2 .

[0114] Setting an initial support force P0 and monitoring and recording it in real time using pressure sensors allows for the assessment of the stability of the model support during the initial support stage, preventing roof delamination, improving the early and overall stiffness of the support system, and increasing the support resistance during column support. A larger initial support force enables the hydraulic support to reach its working resistance more quickly, reducing roof subsidence and preventing early roof delamination and breakage.

[0115] 3.2 The final resistance P of the sequence m

[0116] End-of-step resistance specifically refers to the key working resistance indicator after each excavation step is completed and before the support is moved. Under normal operating conditions, this resistance value represents the maximum working resistance level within a single step, and its data can be collected and recorded using precision pressure sensors. The end-of-step resistance P... m Real-time tracking and monitoring provide an intuitive and effective means to assess the stability and bearing capacity of the model support under the heavy pressure of the rock strata above it, such as... Figure 10 As shown.

[0117] 3.3 Safety valve opening pressure P k and speed V pk

[0118] As a core protective component of the model support, the safety valve's opening pressure setting is crucial for ensuring the support's safety and stability. The working resistance of the model support increases from the set initial support force P0 to the safety valve opening pressure P. k During the process, the safety valve experiences an upward velocity V before reaching the opening pressure. pk The rate of pressure rise before the safety valve opens is used to assess whether the model support meets the test requirements. The average rate of pressure rise before the safety valve opens is calculated. Based on this, it is also necessary to solve for the rate of pressure rise at any given moment before the safety valve opens, and find its maximum value. Based on the formula for calculating the rate of pressure rise at any moment before the safety valve opens, the standard deviation of the rate of pressure rise before the safety valve opens is obtained. ,like Figure 11 As shown.

[0119] Average rate of pressure rise before safety valve opens

[0120] Speed ​​of pressure rise at any moment before safety valve opens

[0121] Standard deviation of pressure rise rate before safety valve opens

[0122] In the formula, t n-1 t n+1 Record t before the safety valve opens. n The time interval between adjacent moments, in seconds (s); p n-1 p n+1 Before the safety valve opens, the pressure sensor records t. n The working resistance corresponding to adjacent time points, in MPa; v pk1 v pk2 …v pki The rate of pressure rise at any given moment before the safety valve opens, expressed in MPa·s. -1 Δp is the change in the safety valve opening pressure; Δt is the change in time; n is the number of data points involved in the calculation.

[0123] Furthermore, in-depth analysis of relevant parameters such as the ratio of safety valve opening time can provide more detailed guidance on bracket selection.

[0124] 3.4 Safety valve opening time t1

[0125] When the overlying roof collapses, the load on the model support increases dramatically, causing its working resistance to rise rapidly. When the working resistance exceeds the preset safety valve opening pressure threshold P... k At this point, the safety valve is triggered and opens, initiating a pressure relief operation. The increasing trend of the support's working resistance is effectively curbed, and its value stabilizes, ceasing to rise further.

[0126] Once the key data for this operating condition (such as peak pressure and duration) has been collected and all operations in the current test sequence have been successfully completed, the system will automatically start the evacuation device to prepare for the next loading or simulation step (see [link]). Figure 12 ).

[0127] During this process, the precise moment t1 at which the safety valve begins to perform the pressure relief action is recorded by the signal processing system, serving as a key time parameter for analyzing the dynamic response of the support and the performance of the safety valve.

[0128] 3.5 Column shrinkage Sn and velocity V sn

[0129] The shrinkage of the support column in a model support system refers to the length reduction of the column from its maximum extended state to its compressed state during the process of the support system bearing pressure from the roof. This parameter profoundly reveals the support system's adaptability to roof pressure and its own elastic deformation characteristics. The data can be collected in real-time and accurately using a laser rangefinder. The shrinkage of the column is not only a key indicator for measuring the degree of column contraction during compression, but also an important basis for evaluating the stability and compliance of the support system, and can be used as a basis for judging whether the model support system is reasonable.

[0130] By monitoring the dynamic changes in the column's downward shrinkage in real time, it is possible to intuitively understand the stability performance and deformation characteristics of the support structure under roof pressure. Furthermore, the average velocity of the column's downward shrinkage and the velocity of the column's downward shrinkage at any given moment can be analyzed. A thorough analysis of parameters such as these can provide a more detailed assessment of the suitability of the stent.

[0131] By utilizing the real-time measurement function of a laser rangefinder, the downward shrinkage data of the columns during the step sequence can be accurately obtained, and the average downward shrinkage of the columns can be calculated accordingly. The velocity V of the column at any moment of retraction Sni And the standard deviation of the rate of decrease in volume under the column, such as Figure 13 As shown.

[0132] Average rate of decrease in volume under the column

[0133] The rate of decrease in volume at any given moment under the column

[0134] Standard deviation of the rate of decrease in volume under the column

[0135] In the formula, ΔSn is the change in the amount of shrinkage of the column; Δt is the change in time. , The reduction in column size did not reach the set value. At that time, the laser rangefinder recorded Time intervals between adjacent moments, in seconds (s). , The reduction in column size did not reach the set value. At that time, the laser rangefinder recorded The column descent amount at adjacent time points, in mm; , … The reduction in column size did not reach the set value. At any given moment during the contraction phase, the velocity is expressed in mm·s. -1 n represents the number of data points involved in the calculation.

[0136] 3.6 Top beam offset angle θ

[0137] The offset angle of the top beam of the model support is defined as the angle between the centerline of the top beam and the centerline of the model support base on the horizontal plane. It is a key indicator for measuring the degree of horizontal offset of the top beam relative to the base. This data can be collected in real time by a high-precision attitude detection instrument. This offset angle not only intuitively reflects the stability and offset of the support during the pressure process, but also allows for a deeper evaluation of the mechanical performance and offset characteristics of the support by continuously monitoring its changes.

[0138] When the model support retracts, the top beam offset angle is generated due to the difference in descent speed between the front and rear columns. Using the real-time monitoring function of the attitude detector, the top beam offset angle during the step sequence can be accurately obtained, and the average value of the top beam offset angular velocity can be calculated. .

[0139] During the descent of the support structure, the angular velocity of the top beam offset becomes a crucial parameter for evaluating the dynamic response characteristics of the support. This is achieved by calculating the angular velocity of the top beam offset at any given moment. The maximum value of the top beam offset angular velocity can be found. To further understand whether the dynamic performance of the support during the pressure-bearing process meets the requirements, such as... Figure 14 As shown.

[0140] Average angular velocity of top beam offset

[0141] angular velocity of top beam offset at any time

[0142] Standard deviation of top beam offset angular velocity

[0143] In the formula, Δθ is the change in the top beam offset angle; Δt is the change in time. , The top beam offset angle did not reach the expected value. At that time, record Time intervals between adjacent moments, in seconds (s). , The top beam offset angle did not reach the expected value. At that time, the attitude detection device recorded The angle corresponding to adjacent moments is 0; , … The top beam offset angle did not reach the expected value. At any given moment during the descent of the top beam, the angular velocity is expressed in units of 0 / s; n represents the number of data points used in the calculation.

[0144] 3.7 Impact acceleration a

[0145] The rationality of the model support can also be assessed using impact acceleration 'a' as an indicator. The instantaneous impact acceleration of the support can be obtained through an acceleration sensor placed on the top beam of the model support.

[0146] Plot the impact acceleration as a curve, such as Figure 15 As shown in the diagram, during the 0-t1 interval, the top beam of the model support is subjected to a strong impact, and due to the increasing internal resistance of the columns, the instantaneous acceleration gradually decreases from its maximum value to zero, resulting in a rapid descent of the top plate. The descent speed of the top plate reaches its maximum value at time t1. During the t1-t2 interval, due to the continuous increase in the internal resistance of the model support, the top beam generates an acceleration in the opposite direction of the impact, slowing down the descent speed of the top beam. The descent speed of the top plate reaches its minimum value of zero at time t2.

[0147] Calculate the average value of the impact acceleration and select the impact acceleration a. max With minimum value a min And calculate the range.

[0148] Average impact acceleration

[0149] Impact acceleration range

[0150] In the formula, a max The maximum impact acceleration at the start time of zero, in mm·s. -2 ;a min The minimum impact acceleration at the start time t2, in mm·s. -2 .

[0151] According to the present invention, a rationality evaluation method for hydraulic support selection includes the following original indicators: dynamic load coefficient, drag increase rate of model support, drag increase rate deviation, drag increase fluctuation stability, initial support force compliance factor, step sequence final resistance ratio factor, relative deviation between the maximum and average values ​​of the pressure rise rate before the safety valve opens, safety valve opening time ratio, safety valve opening frequency evaluation coefficient, relative deviation between the maximum and average values ​​of the column retraction speed, top beam offset angle, top beam offset angular velocity deviation, and impact strength.

[0152] According to the present invention, a method for evaluating the rationality of hydraulic support selection is provided. The method determines the original indicators based on monitoring indicators, specifically including: determining the drag increase rate deviation and drag increase fluctuation stability based on the drag increase rate of the model support; determining the initial support force compliance factor based on the initial support force; determining the step-by-step resistance ratio factor based on the step-by-step resistance; determining the relative deviation between the maximum and average values ​​of the pressure rise rate before the safety valve opens based on the safety valve opening pressure; determining the safety valve opening frequency evaluation coefficient based on the safety valve opening time ratio; determining the relative deviation between the maximum and average values ​​of the column retraction speed based on the column retraction amount; determining the top beam offset angular velocity deviation based on the top beam offset angle; and determining the impact intensity based on the impact acceleration.

[0153] According to the present invention, a method for evaluating the rationality of hydraulic support selection is provided, which determines the drag increase rate deviation and drag increase fluctuation stability based on the drag increase rate of the model support. Specifically, the method includes: obtaining the ideal value of the drag increase rate of the model support; determining the drag increase rate deviation based on the drag increase rate of the model support and the ideal value of the drag increase rate of the model support; determining the standard deviation of the drag increase rate of the model support based on the drag increase rate of the model support; and determining the drag increase fluctuation stability based on the standard deviation of the drag increase rate of the model support.

[0154] 4.1 Dynamic load factor K d

[0155] The dynamic load factor is a core parameter that measures the ratio of the peak dynamic load to the static working resistance of a hydraulic support under dynamic impact loads on the roof (such as collapses and mine tremors). Its guiding role in the selection of hydraulic supports is crucial.

[0156] The working resistance of the support is matched with the dynamic load requirements:

[0157]

[0158] In the formula, P 额定 P represents the rated working resistance of the hydraulic support, expressed in MPa. m ΔP is the final resistance of the step sequence, in MPa; ΔP is the safety margin, usually taken as 10%-20% of the final resistance of the step sequence, in MPa.

[0159] According to the rationality evaluation method for hydraulic support selection provided by the present invention, when obtaining the rationality prediction label, when the dynamic load factor K... d When the dynamic load coefficient K is not less than the first coefficient threshold and not greater than the second coefficient threshold, the selection of hydraulic support is judged to be of level two rationality; when the dynamic load coefficient K d When the dynamic load coefficient K is greater than the second threshold and not greater than the third threshold, the selection of the hydraulic support is considered to be of level one rationality; when the dynamic load coefficient K... d If the value exceeds the third coefficient threshold, the selection of hydraulic support is deemed unreasonable.

[0160] Specifically, according to the dynamic load factor Kd Determine the appropriateness of the selected hydraulic support on site:

[0161] when At that time, the dynamic load factor K d The size is relatively small, but the stiffness is too large; the selected on-site hydraulic device can be used normally.

[0162] when At that time, the dynamic load factor K d The stiffness is moderate and reasonable, and the selection of hydraulic supports on site is appropriate.

[0163] when At that time, the dynamic load factor K d The load is relatively large, and the support may be crushed or the structure may be damaged under dynamic load impact, indicating that the selection of hydraulic support on site is unreasonable.

[0164] 4.2 Model support drag ratio P v

[0165] Specifically, the drag coefficient P of the model support v The drag increase rate refers to the rate at which the resistance of a hydraulic support increases over time or during a specific operation, provided the model support is in complete contact with the roof and the initial support force P0 is stable. In coal mining, model supports are commonly used to simulate actual working environments to evaluate equipment performance and durability. As one of the evaluation indicators, the drag increase rate of the model support is of great significance for the selection of hydraulic supports in the field.

[0166] like Figure 10 As shown, the dynamic changes in the working resistance of the model support can be accurately captured through real-time measurement by the pressure sensor. When the drag increase rate P of the model support... v A large value indicates insufficient stiffness of the model support, which can easily lead to excessive deformation or instability; when the drag coefficient P of the model support is large... v A smaller value indicates higher stiffness of the model support, making it prone to stress concentration or brittle failure. The drag increase rate of the model support, by quantifying the rate of change of drag over time, directly reflects the dynamic stiffness and structural stability of the support. Its average value is calculated using the following formula:

[0167] Average drag increase of the model support

[0168] In the formula, P0 is the initial support force, which is the force exerted by the model support on the overlying rock strata to provide active support; P m t1 is the working resistance at the end of the step sequence, which is the working resistance for stabilizing the model support before starting the next step; t1 is the time to reach the resistance at the end of the step sequence.

[0169] From the initial support force P0 to the final resistance P of the step sequence m During the process, it is also necessary to solve for the drag increase rate of the model support at any time and find its maximum value P. v,maxThis allows for a more comprehensive reflection of whether the model support meets the requirements. Based on the formula for calculating the drag increase rate of the model support at any given time, the standard deviation of the drag increase rate is obtained. ,like Figure 16 As shown.

[0170] Model support drag ratio at any time

[0171] Standard deviation of drag increase rate of model support

[0172] In the formula, , When the working resistance does not reach the set value, record t. n The time interval between adjacent moments, in seconds; , When the working resistance does not reach the set value, the pressure sensor records t. n The resistance corresponding to adjacent time points, in MPa; The velocity at any moment during the ascent phase when the working resistance has not reached the set value, expressed in MPa·S. -1 .

[0173] 4.3 Resistor deviation from h

[0174] After the physical experiment working face is excavated, a simulated support frame is used for roof support. Under load, the frame deforms rapidly, leading to a significant increase in dynamic resistance, which may cause structural instability or plastic deformation. The frame also has weak deformation capacity and insufficient energy absorption, making it prone to sudden failure due to localized stress concentration or brittle fracture. Therefore, the drag coefficient deviation h is used to describe this.

[0175]

[0176] The top plate applies pressure, increasing the drag coefficient P of the model support. v Value compared to ideal value P v If the value is too large, it indicates that the stiffness of the model support is insufficient and does not meet the experimental requirements. The model support is prone to excessive deformation or instability. If the drag increase ratio P of the model support is too large... v When the value is small, it indicates that the stiffness of the model support is large, which can easily lead to stress concentration or brittle failure, and may not meet the test requirements.

[0177] According to the rationality evaluation method for hydraulic support selection provided by the present invention, when obtaining the rationality prediction label, if the deviation of the drag coefficient is not less than a first deviation threshold and not greater than a second deviation threshold, the rationality of the hydraulic support selection is judged to be unreasonable; if the deviation of the drag coefficient is greater than the second deviation threshold and not greater than a third deviation threshold, the rationality of the hydraulic support selection is judged to be level two reasonable; if the deviation of the drag coefficient is greater than the third deviation threshold and not greater than a fourth deviation threshold, the rationality of the hydraulic support selection is judged to be level one reasonable.

[0178] Specifically, the rationality of the selected hydraulic support on site is judged based on the deviation of the drag ratio from h:

[0179] when At that time, the deviation of the drag coefficient is large and the stiffness is unbalanced, indicating that the selection of the on-site hydraulic device is unreasonable;

[0180] when At that time, the deviation of the drag coefficient is small, the stiffness is reasonable, and the hydraulic support can be used normally on site;

[0181] when When the deviation of the drag ratio approaches the optimal value, the selection of the hydraulic support on site is reasonable.

[0182] 4.4 Resistance fluctuation stability w

[0183] Ideally, the drag coefficient of the model support should be constant, which best meets the usage requirements. However, in actual use, fluctuations occur due to factors such as internal friction. Figure 16 As shown. The stability of drag fluctuation is an indicator used to describe the changes and fluctuations in drag ratio.

[0184]

[0185] Standard deviation The larger the value, the smaller the stability w of the resistance increase fluctuation, indicating that the resistance increase process is more unstable.

[0186] According to the rationality evaluation method for hydraulic support selection provided by the present invention, when obtaining the rationality prediction label, if the stability of the increased resistance fluctuation is greater than the first stability threshold but not greater than the second stability threshold, the rationality of the hydraulic support selection is judged to be unreasonable; if the stability of the increased resistance fluctuation is greater than the second stability threshold but not greater than the third stability threshold, the rationality of the hydraulic support selection is judged to be level two reasonable; if the stability of the increased resistance fluctuation is greater than the third stability threshold but not greater than the fourth stability threshold, the rationality of the hydraulic support selection is judged to be level one reasonable.

[0187] Specifically, the rationality of stent selection is determined through parameters, such as:

[0188] when At that time, the support had significant defects, and the selection of hydraulic support on site was unreasonable;

[0189] when At that time, the support structure was basically reasonable, but the hydraulic support on site needed some local optimization.

[0190] when At that time, the support structure was well-designed, and the on-site hydraulic supports met the actual usage requirements.

[0191] 4.5 Initial support force compliance factor m

[0192] The initial support force needs to reach a certain threshold. Pressure sensors are used to verify in real time whether the initial support force meets the standard. During the installation or commissioning stage of the support, the initial support force is actively applied through the hydraulic control system and locked through the switching valve to ensure that it is within a reasonable range and to avoid insufficient initial support force due to unreasonable selection of model support.

[0193]

[0194] The initial support force compliance factor is used to measure whether the initial support force of the support meets the usage requirements. That is, the initial support force reaching more than 85% of the rated initial support force of the support is considered to be within the reasonable range.

[0195] According to the rationality evaluation method for hydraulic support selection provided by the present invention, when obtaining the rationality prediction label, if the initial support force compliance factor is not greater than the ideal threshold, the rationality of hydraulic support selection is judged to be unreasonable; if the initial support force compliance factor is greater than the ideal threshold, the rationality of hydraulic support selection is judged to be reasonable.

[0196] Specifically, based on the initial support force compliance factor m, it is determined whether the on-site hydraulic support meets the standard:

[0197] when At that time, the initial support force was insufficient and did not meet the standard, and the selection of hydraulic supports on site was unreasonable;

[0198] when At that time, the initial support force reached the ideal threshold and was within a reasonable range, indicating that the selection of the hydraulic support on site was appropriate.

[0199] 4.6 Step-by-step resistance ratio factor I

[0200] Whether the resistance at the end of the step sequence is within the expected range is one of the important indicators for evaluating the performance of the model support. Too high a resistance indicates excessive stiffness leading to stress concentration, while too low a resistance indicates insufficient stiffness leading to excessive deformation. Both indicate that the hydraulic support on site is not reasonable. Therefore, the step sequence resistance ratio factor is used to quantitatively describe this.

[0201]

[0202] According to the rationality evaluation method for hydraulic support selection provided by the present invention, when obtaining the rationality prediction label, if the resistance ratio factor at the end of the step sequence is not greater than the first percentage, the rationality of the hydraulic support selection is judged to be unreasonable; if the resistance ratio factor at the end of the step sequence is greater than the first percentage and not greater than the second percentage, the rationality of the hydraulic support selection is judged to be level two reasonable; if the resistance ratio factor at the end of the step sequence is greater than the second percentage and less than the third percentage, the rationality of the hydraulic support selection is judged to be level one reasonable.

[0203] Specifically, the step-end resistance ratio factor describes the proportion of the final resistance to the rated resistance, reflecting the load-bearing efficiency. Based on its characteristics, it can be classified as follows:

[0204] when At that time, the resistance at the end of the step sequence was smaller than the rated resistance, resulting in wasted bearing capacity of the hydraulic support on site and unreasonable selection.

[0205] when At that time, the resistance at the end of the step sequence is close to the ideal load, and the on-site hydraulic support meets the actual use requirements;

[0206] when Sometimes, or When the safety valve of the model support is opened, the resistance at the end of the step is at the ideal load, and the on-site hydraulic support is reasonably selected.

[0207] 4.7 Pressure rise rate before safety valve opens

[0208] According to the present invention, a method for evaluating the rationality of hydraulic support selection is provided. This method determines the relative deviation between the maximum and average values ​​of the pressure rise rate before the safety valve opens, based on the safety valve opening pressure. Specifically, it includes: determining the first pressure rise rate before the safety valve opens using a displacement fitting curve differentiation method based on the safety valve opening pressure, and obtaining a first average value of the pressure rise rate before the safety valve opens; determining the second pressure rise rate before the safety valve opens using an adjacent-time displacement difference method based on the safety valve opening pressure, and obtaining a second average value of the pressure rise rate before the safety valve opens; determining the first relative error between the adjacent-time displacement difference method and the displacement fitting curve differentiation method based on the first average value, the first pressure rise rate before the safety valve opens, the second average value, and the second pressure rise rate before the safety valve opens; and determining the relative deviation between the maximum and average values ​​of the pressure rise rate before the safety valve opens based on the comparison result of the first relative error and its critical value. The adjacent-time displacement difference method is sensitive to measurement noise and easily affected by instantaneous disturbances, which may lead to large fluctuations in the speed value. Therefore, the displacement fitting curve differentiation method is introduced, and the combination of the two methods improves the rationality judgment of the model support.

[0209] Specifically, a graph is plotted based on the pressure data obtained before the safety valve opens, such as... Figure 12 As shown. Obtain the fitted curve. Required goodness of fit Differentiating the fitted curve yields the pressure rise rate at any moment before the safety valve opens. Calculate the maximum rate of pressure rise before the safety valve opens, based on the fitted curve. The average rate of pressure rise before the safety valve opens, and the fitted curve. .

[0210]

[0211] in, and H represents the average value obtained by the adjacent time displacement difference method and the velocity at any given time. H is the relative error between the adjacent time displacement difference method and the displacement fitting curve differentiation method. The critical value H for determining the relative error can be chosen according to actual needs; for example, it can be set to... .

[0212] when This indicates that the velocity curves of both methods show a high degree of consistency, meaning that the pressure data before the safety valve opens has low noise and a stable upward trend, and the instantaneous fluctuations of the difference method match the trend of the fitting method well. In short-term abrupt changes, the adjacent time displacement difference method is chosen to find the maximum velocity. Because the direct method preserves the details of the original data, it can more sensitively capture the instantaneous peak value of the pressure rise before the safety valve opens, while the fitting method may underestimate the extreme values ​​due to the smoothing effect;

[0213] According to the rationality evaluation method for hydraulic support selection provided by the present invention, when obtaining the rationality prediction label, if the relative deviation between the maximum value and the average value of the pressure rise rate before the safety valve opens is less than the first relative deviation threshold, the rationality of the hydraulic support selection is judged to be Level 1; if the relative deviation between the maximum value and the average value of the pressure rise rate before the safety valve opens is greater than the first relative deviation threshold but not greater than the second relative deviation threshold, the rationality of the hydraulic support selection is judged to be Level 2; if the relative deviation between the maximum value and the average value of the pressure rise rate before the safety valve opens is greater than the second relative deviation threshold, the rationality of the hydraulic support selection is judged to be unreasonable.

[0214] Specifically, the rationality of the model support is quantified by the relative deviation (denoted as Δ) between the maximum and average values ​​of the pressure rise rate before the safety valve opens.

[0215]

[0216] Based on the parameter Δ value, the rationality of the stent is divided into three levels, for example:

[0217] This indicates that the speed fluctuation is small, the pressure increase of the safety valve is relatively stable, and the selection of the hydraulic support on site is reasonable;

[0218] This indicates that the speed dispersion is large, the pressure increase of the safety valve changes greatly, and the on-site hydraulic support basically meets the usage requirements.

[0219] This indicates that the speed fluctuates drastically, posing a risk of instability due to instantaneous overload, and that the selection of the hydraulic support on site is inappropriate.

[0220] when The significant difference in the velocity curves between the two methods is likely due to data noise or deviation of the fitted model from the actual deformation pattern. Therefore, the method of finding the maximum velocity value using the derivative of the fitted curve is chosen. The fitting method, by smoothing noise and removing outliers, more reliably reflects the overall trend of roof deformation and avoids spurious extreme values ​​caused by local disturbances in the difference method, thus making it more suitable for assessing roof stability.

[0221] The rationality of the model support is quantified by the relative deviation (denoted as Δ´) between the maximum and average values ​​of the pressure rise rate before the safety valve opens.

[0222]

[0223] Based on the parameter Δ´ value, the rationality of the stent is divided into three levels, for example:

[0224] This indicates that the speed fluctuation is small, the pressure increase of the safety valve is relatively stable, and the selection of the hydraulic support on site is reasonable;

[0225] This indicates that the speed dispersion is large, the pressure increase of the safety valve changes greatly, and the on-site hydraulic support basically meets the usage requirements.

[0226] This indicates that the speed fluctuates drastically, posing a risk of instability due to instantaneous overload, and that the selection of the hydraulic support on site is inappropriate.

[0227] 4.8 Safety valve opening time ratio η t

[0228] In one step of the safety valve opening sequence, the ratio of the safety valve opening time to the total sequence time is η. t Safety valve opening time ratio η t :

[0229]

[0230] In the formula, t1 is the opening time of the column safety valve, in seconds; t2 is the total sequence time, with each sequence time set to the same value, in seconds.

[0231] η t As an evaluation metric, it quantifies the opening frequency and efficiency of the safety valve. This ratio is calculated using the actual opening time t of the column safety valve. k With the total step time t n The ratio is calculated and serves as the basis for evaluating the performance of safety valves, providing an intuitive model of the safety valve opening pressure P. k Proof that the size is reasonable.

[0232] 4.9 Evaluation coefficient C for safety valve opening frequency

[0233] Specifically, by monitoring the opening time ratio η of the safety valve t The following formula is used to determine the rationality of the model support and then whether the selected hydraulic support on site meets the usage requirements.

[0234]

[0235] According to the rationality evaluation method for hydraulic support selection provided by the present invention, when obtaining the rationality prediction label, if the evaluation coefficient of safety valve opening frequency is not less than the first evaluation coefficient threshold and not greater than the second evaluation coefficient threshold, the rationality of hydraulic support selection is judged to be unreasonable; if the evaluation coefficient of safety valve opening frequency is greater than the second evaluation coefficient threshold and less than the third evaluation coefficient threshold, the rationality of hydraulic support selection is judged to be level one reasonable; if the evaluation coefficient of safety valve opening frequency is not less than the third evaluation coefficient threshold, the rationality of hydraulic support selection is judged to be level two reasonable.

[0236] Specifically, based on the C value, it is divided into three levels:

[0237] when This indicates that the model support is frequently opened, the working resistance of the support is close to or reaches the rated limit for a long time, the external load is too large and exceeds the design bearing capacity, and the selection of the model support on site is unreasonable.

[0238] when This indicates that the safety valve is rarely opened, the external load is small, the surrounding rock pressure is lower than the design value of the support, and the support is not able to fully utilize its own bearing capacity, but the hydraulic support on site can meet basic needs.

[0239] when This indicates that the model support is well-matched with the external load, the safety valve operates reasonably, and the selected hydraulic support meets the requirements.

[0240] 4.10 Column retraction speed

[0241] According to the present invention, a method for evaluating the rationality of hydraulic support selection is provided. The method determines the relative deviation between the maximum and average values ​​of the column retraction speed based on the column retraction amount. Specifically, it includes: determining a third column retraction speed based on the column retraction amount using the displacement fitting curve differentiation method, and obtaining a third average value of the column retraction speed; determining a fourth column retraction speed based on the column retraction amount using the adjacent time displacement difference method, and obtaining a fourth average value of the column retraction speed; determining a second relative error between the adjacent time displacement difference method and the displacement fitting curve differentiation method based on the third average value, the third column retraction speed, the fourth average value, and the fourth column retraction speed; and determining the relative deviation between the maximum and average values ​​of the column retraction speed based on the comparison result of the second relative error and the critical value of the second relative error.

[0242] Specifically, the adjacent time displacement difference method is sensitive to measurement noise and easily affected by instantaneous disturbances, which may lead to large fluctuations in velocity values. Therefore, the displacement fitting curve differentiation method is introduced, and the combination of the two improves the rationality judgment of the model support.

[0243] Draw a diagram based on the obtained column reduction data, such as... Figure 13 As shown. Obtain the fitted curve. Required goodness of fit Differentiating the fitted curve yields the velocity of the column at any given moment during its downward contraction. Calculate the maximum shrinkage velocity of the column in the fitted curve. The average shrinkage rate of the column in the fitted curve .

[0244]

[0245] in, and H1 represents the average velocity obtained by the adjacent time displacement difference method and the velocity at any given time. H1 is the relative error between the adjacent time displacement difference method and the displacement fitting curve differentiation method. The value of H1 for determining the relative error can be chosen according to actual needs, such as a critical value. .

[0246] when This indicates that the velocity curves of both methods show a high degree of consistency, meaning that the displacement data has low noise, the deformation pattern is stable, and the instantaneous fluctuations of the difference method match the trend of the fitting method well. In short-time abrupt changes, the displacement difference method with adjacent time intervals is chosen to find the maximum velocity. Because the direct method preserves the details of the original data, it can more sensitively capture the instantaneous peak value of the column shrinkage, while the fitting method may underestimate the extreme value due to the smoothing effect.

[0247] According to the rationality evaluation method for hydraulic support selection provided by the present invention, when obtaining the rationality prediction label, if the relative deviation between the maximum value and the average value of the column retraction speed is not greater than the third relative deviation threshold, the rationality of the hydraulic support selection is judged to be Level 1; if the relative deviation between the maximum value and the average value of the column retraction speed is greater than the third relative deviation threshold but less than the fourth relative deviation threshold, the rationality of the hydraulic support selection is judged to be Level 2; if the relative deviation between the maximum value and the average value of the column retraction speed is not less than the fourth relative deviation threshold, the rationality of the hydraulic support selection is judged to be unreasonable.

[0248] Specifically, the rationality of the model support is quantified by the relative deviation (denoted as Δ1) between the maximum and average values ​​of the column retraction speed:

[0249]

[0250] Based on the parameter Δ1 value, the hydraulic supports are divided into three levels, for example:

[0251] This indicates that the speed fluctuation is small, the downward displacement of the model support column is uniform, and the stability of the selected hydraulic support on site is good.

[0252] This indicates that the velocity dispersion has increased, there is local disturbance due to the shrinkage of the model support column, and the stability of the selected hydraulic support on site is generally poor.

[0253] This indicates that the speed fluctuates drastically, the stiffness of the model support is too small, the control capability is weak, the risk of instability is high, and the on-site hydraulic support does not meet the requirements.

[0254] when The significant difference in velocity curves between the two methods is likely due to data noise or deviation of the fitted model from the actual deformation pattern. Therefore, the displacement fitting curve differentiation method should be chosen to find the maximum velocity value. The fitting method, by smoothing noise and removing outliers, more reliably reflects the overall trend of roof deformation, avoiding spurious extreme values ​​caused by local disturbances in the difference method, and is therefore more suitable for evaluating the stability of the model support.

[0255] The rationality of the model support is quantified by the relative deviation (denoted as Δ´1) between the maximum and average values ​​of the top plate deformation rate.

[0256]

[0257] Based on the parameter Δ´1 value, the hydraulic supports are divided into three levels, for example:

[0258] This indicates that the speed fluctuation is small, the downward displacement of the model support column is uniform, and the stability of the selected hydraulic support on site is good.

[0259] This indicates that the velocity dispersion has increased, there is local disturbance due to the shrinkage of the model support column, and the stability of the selected hydraulic support on site is generally poor.

[0260] This indicates that the speed fluctuates drastically, the stiffness of the model support is too small, the control capability is weak, the risk of instability is high, and the on-site hydraulic support does not meet the requirements.

[0261] 4.11 Top beam offset angle

[0262] During the load-bearing process of the support structure, the top beam offset angle is the tilt angle of the top beam's central axis relative to its initial position, reflecting the posture stability of the support structure under load. The rationality of the model support structure is judged by monitoring the magnitude of the top beam offset angle.

[0263] According to the rationality evaluation method for hydraulic support selection provided by the present invention, when obtaining the rationality prediction label, if the maximum angle of the top beam offset angle is less than the allowable offset angle, the hydraulic support selection is judged to be reasonable; if the maximum angle of the top beam offset angle is not less than the allowable offset angle, the hydraulic support selection is judged to be unreasonable.

[0264] Specifically, if This indicates that the offset angle of the top beam is within a safe range, demonstrating that the stiffness of the support is matched with the load and the model design is reasonable.

[0265] like This indicates that the stiffness of the model support is unreasonable, and the selection of the corresponding on-site hydraulic support does not meet the requirements. The stiffness characteristics need to be adjusted.

[0266] 4.12 The angular velocity of the top beam offset deviates from L

[0267] During the descent of the support structure, the angular velocity of the top beam offset becomes a crucial parameter for evaluating the dynamic response characteristics of the support. This is achieved by calculating the angular velocity of the top beam offset at any given moment. The maximum value of the top beam offset angular velocity can be found. To further understand the dynamic performance of the support during the pressure-bearing process and to determine the rationality of the model support, angular velocity deviation L is used to describe the following:

[0268]

[0269] During the descent of the top beam, the angular velocity value at any given moment is offset. Compared to the average If the value is too large, it indicates that the rigidity of the model support is insufficient and does not meet the test requirements. The model support is prone to excessive deformation or instability. If the top beam deviates by any given moment, the angular velocity value... A smaller value indicates that the model support has greater stiffness, which can easily lead to stress concentration or structural jamming, and may not meet the test requirements.

[0270] According to the rationality evaluation method for hydraulic support selection provided by the present invention, when obtaining the rationality prediction label, if the deviation of the top beam offset angular velocity is not less than the first angular velocity deviation threshold and not greater than the second angular velocity deviation threshold, the rationality of the hydraulic support selection is judged to be unreasonable; if the deviation of the top beam offset angular velocity is greater than the second angular velocity deviation threshold but not greater than the third angular velocity deviation threshold, the rationality of the hydraulic support selection is judged to be level two reasonable; if the deviation of the top beam offset angular velocity is greater than the third angular velocity deviation threshold but not greater than the fourth angular velocity deviation threshold, the rationality of the hydraulic support selection is judged to be level one reasonable.

[0271] Specifically, the rationality of the on-site hydraulic support is judged based on the deviation of the angular velocity from the L value:

[0272] when At that time, the top beam offset angular velocity was large, the rigidity of the model support was insufficient, and the selection of the on-site hydraulic device was unreasonable.

[0273] when At that time, the offset angular velocity of the top beam was relatively small, the stiffness of the model support was relatively reasonable, and the hydraulic support on site could be used normally.

[0274] when When the offset angular velocity of the top beam approaches the optimal value, the selection of the on-site hydraulic support is reasonable.

[0275] 4.13 Impact Strength G

[0276] The range R between the maximum and minimum impact accelerations a and average impact acceleration The ratio of can be used to describe the impact intensity G of the top plate during the impact process.

[0277]

[0278] According to the rationality evaluation method for hydraulic support selection provided by the present invention, when obtaining the rationality prediction label, if the impact intensity is not greater than the first impact intensity threshold, the rationality of the hydraulic support selection is judged to be Level 1; if the impact intensity is greater than the first impact intensity threshold and less than the second impact intensity threshold, the rationality of the hydraulic support selection is judged to be Level 2; if the impact intensity is not greater than the second impact intensity threshold, the rationality of the hydraulic support selection is judged to be unreasonable.

[0279] Specifically, based on the impact strength G of the roof plate, the rationality classification standard for on-site hydraulic supports is as follows:

[0280] when In this case, it can be determined that the stiffness of the hydraulic support on site is reasonable, the impact of the roof plate has little harm to production, and accidents are unlikely to occur.

[0281] when At that time, it can be determined that the stiffness of the hydraulic support on site is basically reasonable, the impact of the roof plate poses a risk of danger, and the possibility of an accident is generally low.

[0282] when If this is the case, it can be determined that the stiffness of the hydraulic support on site is unreasonable, and an accident is very likely to occur.

[0283] in and This is a critical value that can be set according to requirements.

[0284] 5.1 Algorithm Model Steps

[0285] For monitoring indicators, a large amount of repeated experimental data is needed to verify the rationality of the selection of hydraulic supports on site. However, the repetitive data analysis of individual indicators relies entirely on manual experience, making efficient and accurate classification and evaluation difficult. Therefore, after completing a small number of individual indicator analyses, this invention provides a comprehensive method for evaluating the rationality of the selection of hydraulic supports on site based on a semi-supervised model algorithm. The flowchart of this method is shown below. Figure 17 As shown.

[0286] This algorithm helps artificial intelligence understand experimental data and adheres to physical principles when processing data, enabling a rational evaluation of the selection of hydraulic supports on site.

[0287] (1) Original indicators

[0288] The rationality index for selecting on-site hydraulic supports is x(i,j), where i represents the i-th index and j represents the j-th test value, for a total of m.

[0289] Based on the foregoing, the data analysis includes 13 indicators such as drag deviation, drag increase fluctuation stability, initial support force compliance factor, and impact intensity.

[0290] (2) Data normalization

[0291] S920. Normalize the original indicators to obtain standardized data.

[0292] Specifically, normalization refers to the process of transforming 13 original index data of different dimensions and orders of magnitude into standardized data with unified dimensions and numerical ranges through mathematical transformation.

[0293]

[0294] Let be the normalized value of the i-th original index and the j-th test value.

[0295] S930. Input standardized data into the trained neural network model and output reasonable prediction results.

[0296] The neural network model is trained based on a training set, which includes standardized data and reasonableness prediction labels corresponding to multiple monitoring indicators.

[0297] According to the present invention, a method for evaluating the rationality of hydraulic support selection includes training a neural network model based on a training set. Specifically, this includes: constructing an initial neural network model; determining the consistency constraints of the neural network model based on the convergence time of each monitoring indicator; inputting standardized data into the initial neural network model, training it based on the consistency constraints, and outputting predicted values; obtaining the difference between the predicted values ​​and the back supervision function values; if the difference is less than a preset threshold, temporarily stopping training and saving the trained neural network model; the back supervision function is used to force the neural network to follow physical laws during training and prediction through consistency constraints; performing an objective function test on the predicted values ​​output by the neural network model; iteratively training the neural network model and performing an objective function test based on the neural network model obtained in each iteration; when the number of iterations reaches a preset number, ending the iteration loop and saving the trained neural network model.

[0298] (3) Predicted value y j With index value y i

[0299] The original index test values ​​are input into the neural network to obtain the predicted value y. j With index value y i Predicted value y j Each prediction corresponds one-to-one with the input test values; for example, inputting 100 test values ​​will result in 100 predicted values. The indicator value y... i These are the original index predictions of the neural network in the same step sequence. Four of these indices are selected as the completion markers of key actions and used as material for training the neural network to determine the order in which they occur.

[0300] (4) Criteria

[0301] The first criterion is the loop criterion, which repeats the neural network training and objective function testing steps. The loop ends when the number of repetitions reaches k.

[0302] The second criterion is the difference criterion. If the difference between the neural network training function and the back supervision function is less than the criterion, the loop training ends, the model is saved, and the objective function test begins.

[0303]

[0304] Among them, y j * represents the value of the reverse supervision function, y j These are the predicted values ​​of the neural network training function.

[0305] Reverse supervision function: Select a consistency function with 4 parameters as a semi-supervised function. The purpose of using the consistency function is to force the model to comply with physical rules. For example, the percentage of drag at the end of the step must be measured after the drag increase rate is zero.

[0306]

[0307] Where, x 1,j For increased resistivity stability, x 2,j The percentage of resistance at the end of the step, x 3,j The rate of pressure rise before the safety valve opens, x 4,j This is the offset angle of the top beam.

[0308] (5) Objective function test

[0309] S940. Scoring the rationality prediction results based on the objective function to obtain the scoring results, and determining the rationality level of hydraulic support selection based on the scoring results.

[0310] The objective function is designed based on the optimal range distribution law of multiple monitoring indicators.

[0311] Specifically, the objective function is used to calculate y from this model. j The likelihood value is used to evaluate the rationality of the selected hydraulic support on site; essentially, it's a scoring system. A higher likelihood value results in a higher objective function score. For example, a likelihood value of 0.75 (3 / 4) indicates that three out of the four predicted convergence times are met.

[0312] 1) Test method:

[0313] ① Maximize the conditional log-likelihood function

[0314] Assumption The standard deviation function is proportional to the distance from the target force to the optimal target force of the stent. Here, σ represents the standard deviation function, used to measure the dispersion and other related characteristics of the distance from the target force to the optimal target force of the stent. p is the actual target force and other related physical quantities, a mechanical parameter value obtained through actual measurement or calculation. μ represents the optimal target force of the stent, a theoretical and ideal mechanical parameter value, serving as a reference standard for evaluating the rationality of the actual target force. k is a proportionality coefficient, used to describe the proportional relationship between the standard deviation function and the distance from the target force to the optimal target force of the stent.

[0315]

[0316] in, It is the conditional log-likelihood function, used to calculate a quantified value of the likelihood given parameters k and μ; m represents the number of data points or samples, i.e., the number of relevant data points involved in the calculation; y j This represents the j-th observation or measurement.

[0317] ② Solve directly using numerical optimization methods (such as gradient descent):

[0318]

[0319] in, These are the estimated values ​​of parameters k and μ, respectively. argmax represents the parameter value that will maximize the function.

[0320] 2) Objective function:

[0321] In the on-site hydraulic support selection rationality test, the model support design has an optimal range. For example, during the test, the initial support force p0, the column rise L, and the final resistance p of the step sequence are set. m Safety valve opening pressure p k Standard parameters such as the column shrinkage Sn and the top beam offset angle θ fall within this range. Within this optimal range, most monitoring indicators show that the target values ​​deviate relatively close, while a few target values ​​deviate significantly. If the test is not within the optimal range, the target values ​​show that a few deviate relatively close, while most deviate significantly.

[0322] Based on this standard, design an objective function that conforms to this rule, such as... Figure 18 As shown.

[0323] The objective function should satisfy the following conditions: when the target force is within the optimal range of stent performance, the target value of the objective function is relatively concentrated; when the target force is outside the optimal range of stent performance, the target force of the objective function is relatively dispersed.

[0324] The objective function is obtained by fitting a model, which follows a normal distribution with a constant mean and varying variance.

[0325]

[0326] Where μ is the optimal target force of the stent, (p-μ) is the distance from the target force to the optimal target force of the stent, and σ(p-μ) is the standard deviation, which is positively correlated with the distance from the target force to the optimal target force of the stent.

[0327] 5.2 Comprehensive Grade Determination

[0328] Specifically, Table 1 shows the correspondence between the objective function score and the performance level. A key constraint exists: a likelihood value less than 0.50 directly indicates the model scaffold is unqualified.

[0329] Table 1

[0330]

[0331] 5.3 Model Adjustment Methods

[0332] The functions used in the algorithm can all be dynamically adjusted according to requirements, for example:

[0333] 1) Select another function that is positively correlated with the distance from the target force to the optimal target force on the support as the variance function;

[0334] 2) Select other x i y was calculated j The model;

[0335] 3) Choose another backpropagation function to represent x corresponding to this index.

[0336] The rationality evaluation device for hydraulic support selection provided by the present invention will be described below. The rationality evaluation device for hydraulic support selection described below can be referred to in correspondence with the rationality evaluation method for hydraulic support selection described above.

[0337] like Figure 19 The image shows a device for evaluating the rationality of hydraulic support selection provided by the present invention, comprising:

[0338] The indicator acquisition module 1910 is used to acquire multiple monitoring indicators of the hydraulic support and determine the original indicators based on the monitoring indicators. The monitoring indicators include initial support force, end resistance of step sequence, safety valve opening pressure, safety valve opening time, column shrinkage, top beam offset angle and impact acceleration.

[0339] Standardization module 1920 is used to normalize the original indicators to obtain standardized data;

[0340] The model prediction module 1930 is used to input standardized data into a trained neural network model and output reasonableness prediction results. The neural network model is trained based on a training set, which includes standardized data and reasonableness prediction labels corresponding to multiple monitoring indicators.

[0341] The rationality evaluation module 1940 is used to score the rationality prediction results based on the objective function to obtain the score results, and to determine the rationality level of the hydraulic support selection based on the score results; the objective function is designed based on the optimal range distribution law of multiple monitoring indicators.

[0342] Figure 20 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 20As shown, the electronic device may include: a processor 2010, a communications interface 2020, a memory 2030, and a communication bus 2040, wherein the processor 2010, the communications interface 2020, and the memory 2030 communicate with each other through the communication bus 2040. The processor 2010 can call logic instructions in the memory 2030 to execute a rationality evaluation method for hydraulic support selection. This method includes: acquiring multiple monitoring indicators of the hydraulic support; determining raw indicators based on these indicators; monitoring indicators include initial support force, final resistance of the step sequence, safety valve opening pressure, safety valve opening time, column shrinkage, top beam offset angle, and impact acceleration; normalizing the raw indicators to obtain standardized data; inputting the standardized data into a trained neural network model to output a rationality prediction result; the neural network model is trained using a training set, which includes standardized data corresponding to multiple monitoring indicators and rationality prediction labels; scoring the rationality prediction result based on an objective function to obtain a score result; and determining the rationality level of the hydraulic support selection based on the score result; the objective function is designed based on the optimal range distribution law of multiple monitoring indicators.

[0343] Furthermore, the logical instructions in the aforementioned memory 2030 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0344] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the rationality evaluation method for hydraulic support selection provided by the above methods. The method includes: acquiring multiple monitoring indicators of the hydraulic support; determining original indicators based on the monitoring indicators; the monitoring indicators include initial support force, step-end resistance, safety valve opening pressure, safety valve opening time, column shrinkage, top beam offset angle, and impact acceleration; normalizing the original indicators to obtain standardized data; inputting the standardized data into a trained neural network model and outputting a rationality prediction result; the neural network model is trained based on a training set, which includes standardized data corresponding to multiple monitoring indicators and rationality prediction labels; scoring the rationality prediction result based on an objective function to obtain a scoring result; and determining the rationality level of hydraulic support selection based on the scoring result; the objective function is designed based on the optimal range distribution law of multiple monitoring indicators.

[0345] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements a method for evaluating the rationality of hydraulic support selection provided by the methods described above. This method includes: acquiring multiple monitoring indicators of the hydraulic support; determining original indicators based on the monitoring indicators; the monitoring indicators include initial support force, step-end resistance, safety valve opening pressure, safety valve opening time, column shrinkage, top beam offset angle, and impact acceleration; normalizing the original indicators to obtain standardized data; inputting the standardized data into a trained neural network model and outputting a rationality prediction result; the neural network model is trained based on a training set, which includes standardized data corresponding to multiple monitoring indicators and rationality prediction labels; scoring the rationality prediction result based on an objective function to obtain a scoring result; and determining the rationality level of hydraulic support selection based on the scoring result; the objective function is designed based on the optimal range distribution law of multiple monitoring indicators.

[0346] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0347] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0348] 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 them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for evaluating the rationality of hydraulic support selection, characterized in that, The method comprises the following steps: obtaining a plurality of monitoring indexes of a hydraulic support, and determining original indexes according to the monitoring indexes; the monitoring indexes comprise initial support force, step sequence end resistance, safety valve opening pressure, safety valve opening time, column subsidence amount, roof beam deflection angle and impact acceleration; the step sequence end resistance is used to represent the influence of rigidity on the performance of the hydraulic support; the roof beam deflection angle is used to represent the inclination angle of the central axis of the roof beam relative to the initial position; normalizing the original indexes to obtain standardized data; inputting the standardized data into a trained neural network model to output a rationality prediction result; the neural network model is trained according to a training set; the training set comprises standardized data corresponding to the plurality of monitoring indexes and rationality prediction labels; scoring the rationality prediction result based on a target function to obtain a score result, and determining a hydraulic support selection rationality level according to the score result; the target function is designed according to the optimal range distribution law of the plurality of monitoring indexes; the original indexes comprise dynamic load coefficient, model support resistance increase rate, resistance increase rate deviation, resistance increase fluctuation stability, initial support force compliance factor, step sequence end resistance proportion factor, relative deviation of the maximum value and the average value of the pressure rise speed before the safety valve is opened, safety valve opening time ratio, safety valve opening frequency evaluation coefficient, relative deviation of the maximum value and the average value of the column subsidence speed, roof beam deflection angle, roof beam deflection angle speed deviation and impact strength.

2. The method for evaluating the reasonability of hydraulic support selection according to claim 1, characterized in that, The neural network model is trained according to the training set, specifically comprising: constructing an initial neural network model; the consistency constraint condition of the neural network model is determined based on the convergence time of each monitoring index; inputting the standardized data into the initial neural network model, training based on the consistency constraint condition, and outputting a prediction value; obtaining the difference between the prediction value and the value of the inverse supervision function; if the difference is less than a preset threshold, temporarily stopping training and saving the trained neural network model; the inverse supervision function is used to force the neural network to follow the physical law in the training and prediction process through the consistency constraint condition; performing target function test on the prediction value output by the neural network model; iteratively training the neural network model, and performing target function test on the neural network model obtained based on each iteration; when the number of iterations reaches a preset number, ending the iteration cycle and saving the trained neural network model.

3. The method for evaluating the reasonability of hydraulic support selection according to claim 1, characterized in that, The original indexes are determined according to the monitoring indexes, specifically comprising: determining the dynamic load coefficient according to the rated working resistance of the model support and the step sequence end resistance; determining the model support resistance increase rate according to the initial support force and the step sequence end resistance; determining the resistance increase rate deviation and the resistance increase fluctuation stability according to the model support resistance increase rate; determining the initial support force compliance factor according to the initial support force; determining the step sequence end resistance proportion factor according to the step sequence end resistance; determining the relative deviation of the maximum value and the average value of the pressure rise speed before the safety valve is opened according to the safety valve opening pressure; determining the safety valve opening time ratio according to the safety valve opening time and the time required for a complete step sequence; determining the safety valve opening frequency evaluation coefficient according to the safety valve opening time ratio; Determine the relative deviation of the maximum value and the average value of the column shrinkage speed according to the column shrinkage; Determine the deviation of the roof beam offset angle speed according to the roof beam offset angle; Determine the impact strength according to the impact acceleration.

4. The method for evaluating the reasonability of hydraulic support selection according to claim 3, characterized in that, The determination of the resistance increase rate deviation and the resistance fluctuation stability according to the model support resistance increase rate, specifically comprising: Obtain the ideal value of the model support resistance increase rate, and determine the resistance increase rate deviation according to the model support resistance increase rate and the ideal value of the model support resistance increase rate; Determine the standard deviation of the model support resistance increase rate according to the model support resistance increase rate, and determine the resistance fluctuation stability according to the standard deviation of the model support resistance increase rate.

5. The method for evaluating the reasonability of hydraulic support selection according to claim 1, characterized in that, In obtaining the rationality prediction label, the method further comprises: When the resistance increase rate deviation is not less than the first deviation threshold and not greater than the second deviation threshold, it is judged that the hydraulic support selection rationality belongs to unreasonable; When the resistance increase rate deviation is greater than the second deviation threshold and not greater than the third deviation threshold, it is judged that the hydraulic support selection rationality belongs to the second level of rationality; When the resistance increase rate deviation is greater than the third deviation threshold and not greater than the fourth deviation threshold, it is judged that the hydraulic support selection rationality belongs to the first level of rationality.

6. The method for evaluating the reasonability of hydraulic support selection according to claim 1, characterized in that, In obtaining the rationality prediction label, the method further comprises: When the resistance fluctuation stability is greater than the first stability threshold and not greater than the second stability threshold, it is judged that the hydraulic support selection rationality belongs to unreasonable; When the resistance fluctuation stability is greater than the second stability threshold and not greater than the third stability threshold, it is judged that the hydraulic support selection rationality belongs to the second level of rationality; When the resistance fluctuation stability is greater than the third stability threshold and not greater than the fourth stability threshold, it is judged that the hydraulic support selection rationality belongs to the first level of rationality.

7. The method for evaluating the reasonability of hydraulic support selection according to claim 1, characterized in that, In obtaining the rationality prediction label, the method further comprises: When the initial support force compliance factor is not greater than the ideal threshold, it is judged that the hydraulic support selection rationality belongs to unreasonable; When the initial support force compliance factor is greater than the ideal threshold, it is judged that the hydraulic support selection rationality belongs to reasonable.

8. The method for evaluating the reasonability of hydraulic support selection according to claim 1, characterized in that, In obtaining the rationality prediction label, the method further comprises: When the step sequence end resistance proportion factor is not greater than the first percentage, it is judged that the hydraulic support selection rationality belongs to unreasonable; When the step sequence end resistance proportion factor is greater than the first percentage and not greater than the second percentage, it is judged that the hydraulic support selection rationality belongs to the second level of rationality; When the step sequence end resistance proportion factor is greater than the second percentage and less than the third percentage, it is judged that the hydraulic support selection rationality belongs to the first level of rationality.

9. The method for evaluating the reasonability of hydraulic support selection according to claim 1, characterized in that, In obtaining the rationality prediction label, the method further comprises: When the relative deviation of the maximum value and the average value of the pressure rise speed before the safety valve opens is less than the first relative deviation threshold, it is judged that the hydraulic support selection rationality belongs to the first level of rationality; When the relative deviation of the maximum value and the average value of the pressure rise speed before the safety valve opens is greater than the first relative deviation threshold and not greater than the second relative deviation threshold, it is judged that the hydraulic support selection rationality belongs to the second level of rationality; When the relative deviation of the maximum value and the average value of the pressure rise speed before the safety valve opens is greater than the second relative deviation threshold, it is judged that the hydraulic support selection rationality belongs to unreasonable.

10. The method for evaluating the reasonability of hydraulic support selection according to claim 1, characterized in that, In obtaining the rationality prediction label, the method further comprises: When the safety valve opening frequency evaluation coefficient is not less than the first evaluation coefficient threshold and not greater than the second evaluation coefficient threshold, it is determined that the hydraulic support selection rationality is unreasonable; When the safety valve opening frequency evaluation coefficient is greater than the second evaluation coefficient threshold and less than the third evaluation coefficient threshold, it is determined that the hydraulic support selection rationality is first-level rational; When the safety valve opening frequency evaluation coefficient is not less than the third evaluation coefficient threshold, it is determined that the hydraulic support selection rationality is second-level rational.

11. The method for evaluating the reasonability of hydraulic support selection according to claim 1, characterized in that, In the process of obtaining the rationality prediction label, the method further comprises: When the relative deviation of the maximum value and the average value of the column subsidence speed is not greater than the third relative deviation threshold, it is determined that the hydraulic support selection rationality is first-level rational; When the relative deviation of the maximum value and the average value of the column subsidence speed is greater than the third relative deviation threshold and less than the fourth relative deviation threshold, it is determined that the hydraulic support selection rationality is second-level rational; When the relative deviation of the maximum value and the average value of the column subsidence speed is not less than the fourth relative deviation threshold, it is determined that the hydraulic support selection rationality is unreasonable.

12. The method for evaluating the reasonability of hydraulic support selection according to claim 1, characterized in that, In the process of obtaining the rationality prediction label, the method further comprises: If the maximum angle of the top beam offset angle is less than the offset allowed angle, it is determined that the hydraulic support selection rationality is reasonable; If the maximum angle of the top beam offset angle is not less than the offset allowed angle, it is determined that the hydraulic support selection rationality is unreasonable.

13. The method for evaluating the reasonability of hydraulic support selection according to claim 1, characterized in that, In the process of obtaining the rationality prediction label, the method further comprises: When the top beam offset angle velocity deviation is not less than the first angular velocity deviation threshold and not greater than the second angular velocity deviation threshold, it is determined that the hydraulic support selection rationality is unreasonable; When the top beam offset angle velocity deviation is greater than the second angular velocity deviation threshold and not greater than the third angular velocity deviation threshold, it is determined that the hydraulic support selection rationality is second-level rational; When the top beam offset angle velocity deviation is greater than the third angular velocity deviation threshold and not greater than the fourth angular velocity deviation threshold, it is determined that the hydraulic support selection rationality is first-level rational.

14. The method for evaluating the reasonability of hydraulic support selection according to claim 1, characterized in that, In the process of obtaining the rationality prediction label, the method further comprises: When the impact intensity is not greater than the first impact intensity threshold, it is determined that the hydraulic support selection rationality is first-level rational; When the impact intensity is greater than the first impact intensity threshold and less than the second impact intensity threshold, it is determined that the hydraulic support selection rationality is second-level rational; When the impact intensity is not greater than the second impact intensity threshold, it is determined that the hydraulic support selection rationality is unreasonable.

15. A device for evaluating the rationality of hydraulic support selection, characterized in that, It comprises: An index acquisition module is configured to acquire multiple monitoring indexes of a hydraulic support, and determine original indexes according to the monitoring indexes; the monitoring indexes include initial support force, step sequence final resistance, safety valve opening pressure, safety valve opening time, column subsidence amount, top beam offset angle, and impact acceleration; A standardization module is configured to normalize the original indexes to obtain standardized data; A model prediction module is configured to input the standardized data into a trained neural network model, and output a rationality prediction result; the neural network model is trained according to a training set, and the training set includes standardized data corresponding to multiple monitoring indexes and a rationality prediction label. A rationality evaluation module is configured to score the rationality prediction result based on a target function to obtain a score result, and determine a hydraulic support selection rationality level according to the score result; The target function is designed according to optimal range distribution rules of multiple monitoring indexes; The original indexes include a dynamic load coefficient, a model support resistance increasing rate, a resistance increasing rate deviation, a resistance increasing fluctuation stability, an initial support force compliance factor, a step sequence final resistance proportion factor, a relative deviation of a maximum value and an average value of a safety valve opening pressure rising speed, a safety valve opening time ratio, a safety valve opening frequency evaluation coefficient, a relative deviation of a maximum value and an average value of a stand column subsidence speed, a top beam deflection angle, a top beam deflection angle speed deviation, and an impact intensity.

16. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein, The processor executes the computer program to implement the hydraulic support selection rationality evaluation method according to any one of claims 1 to 14.

17. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the hydraulic support selection rationality evaluation method according to any one of claims 1 to 14.

Images