A shield machine excavation parameter adjustment method and system

Abstract

The present invention relates to a shield machine excavation parameter adjustment method and system, and relates to the technical field of shield construction, including: recording the propulsion resistance information in multiple historical moments in the past, obtaining the historical propulsion resistance sequence, predicting the propulsion resistance in multiple future moments in the future, obtaining the predicted propulsion resistance sequence, optimizing the propulsion force of the shield machine for the purpose of improving the propulsion speed and improving the stability of the soil layer, and obtaining the optimized propulsion force; performing fluctuation analysis on the historical propulsion resistance sequence and the predicted propulsion resistance sequence, and calculating and obtaining the minimum fluctuation propulsion resistance and the maximum fluctuation propulsion resistance, respectively performing propulsion speed analysis and soil layer stability analysis, obtaining the minimum propulsion speed and the minimum soil layer stability information, performing auxiliary optimization on the optimized propulsion force, obtaining the optimal propulsion force, and adjusting the excavation parameters of the shield machine. The present invention achieves the technical effect of improving the efficiency, stability and safety of shield construction.

Description

Technical Field

[0001] The invention relates to the technical field of shield construction, and in particular to a shield machine excavation parameter adjustment method and system. Background Art

[0002] During the tunneling process, shield machines face challenges of soil resistance and geological changes. The precise adjustment of tunneling parameters is directly related to construction efficiency and safety. Traditional tunneling parameter adjustment methods often rely on manual experience or simple rule models, lacking the ability to respond to complex soil conditions and dynamic changes in real time, resulting in slow tunneling speed or unstable soil, thus affecting the tunneling effect and construction progress of the shield machine.

[0003] Therefore, how to accurately predict future propulsion resistance based on historical propulsion resistance information and engineering characteristics, optimize the propulsion force of the shield machine, and perform auxiliary optimization in combination with soil layer stability has become a technical problem that needs to be solved urgently. In the existing technology, there is a technical problem that the shield machine excavation parameters are not accurately adjusted, which affects the efficiency and safety of shield construction. Summary of the invention

[0004] The present invention aims at the technical problem in the prior art that the tunneling parameters of a shield machine are not accurately adjusted, which affects the shield construction efficiency and safety, and provides a tunneling parameter adjustment method and system for a shield machine.

[0005] In a first aspect, the present invention provides a shield machine excavation parameter adjustment method, comprising: during the excavation process of the shield machine, recording the propulsion resistance information in multiple historical moments in the past, obtaining a historical propulsion resistance sequence, combining the engineering characteristic information of the excavation project, predicting the propulsion resistance at multiple future moments in the future, and obtaining a predicted propulsion resistance sequence;

[0006] According to the predicted propulsion resistance sequence, the propulsion force of the shield machine is optimized for the purpose of increasing the propulsion speed and improving the stability of the soil layer to obtain an optimized propulsion force;

[0007] Performing fluctuation analysis on the historical advancement resistance sequence and the predicted advancement resistance sequence, and calculating and obtaining the minimum fluctuation advancement resistance and the maximum fluctuation advancement resistance, respectively performing advancement speed analysis and soil layer stability analysis, and obtaining the minimum advancement speed and minimum soil layer stability information;

[0008] According to the minimum propulsion speed and the minimum soil layer stability information, the optimized propulsion force is auxiliary optimized to obtain the optimal propulsion force, and the tunneling parameters of the shield machine are adjusted.

[0009] In a second aspect, the present invention provides a shield machine excavation parameter adjustment system, the system comprising: a propulsion resistance prediction module, which is used to record propulsion resistance information at multiple historical moments in the past during the excavation process of the shield machine, obtain a historical propulsion resistance sequence, and predict propulsion resistance at multiple future moments in the future in combination with engineering characteristic information of the excavation project to obtain a predicted propulsion resistance sequence;

[0010] A propulsion force optimization module is used to optimize the propulsion force of the shield machine according to the predicted propulsion resistance sequence, with the purpose of increasing the propulsion speed and improving the stability of the soil layer, so as to obtain an optimized propulsion force;

[0011] A fluctuation analysis module is used to perform fluctuation analysis on the historical advancement resistance sequence and the predicted advancement resistance sequence, and calculate the minimum fluctuation advancement resistance and the maximum fluctuation advancement resistance, and respectively perform advancement speed analysis and soil layer stability analysis to obtain minimum advancement speed and minimum soil layer stability information;

[0012] The auxiliary optimization module is used to assist in optimizing the optimized propulsion force according to the minimum propulsion speed and the minimum soil layer stability information, obtain the optimal propulsion force, and adjust the tunneling parameters of the shield machine.

[0013] In a third aspect, the present invention provides an electronic device, comprising: a memory for storing a computer software program; and a processor for reading and executing the computer software program, thereby implementing the shield machine excavation parameter adjustment method of the first aspect.

[0014] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer software program stored therein, and when the computer software program is executed by a processor, the shield machine excavation parameter adjustment method of the first aspect is implemented.

[0015] The shield machine excavation parameter adjustment method of the present invention can accurately predict the propulsion resistance in the future time by introducing the historical propulsion resistance sequence and engineering characteristic information, and combining the prediction model to accurately predict the propulsion resistance at multiple moments in the future. Through the analysis of the predicted propulsion resistance sequence, the present invention can optimize the propulsion force of the shield machine, reasonably improve the propulsion speed, and effectively balance the stability of the soil layer. Further, the propulsion force is optimized and adjusted according to the predicted propulsion resistance sequence to improve the propulsion efficiency while ensuring the construction safety. In addition, the fluctuation analysis combined with the historical and predicted propulsion resistance information further optimizes the propulsion force, thereby improving the overall operation efficiency. Through the technical solution of this application, the accuracy and flexibility of the shield machine excavation parameter adjustment are improved, the propulsion force can be adjusted according to the real-time soil layer conditions, the propulsion speed is optimized, the soil layer during excavation is guaranteed to be stable, and the safety and efficiency of the shield construction process are ensured, thereby improving the adaptability of the shield machine under complex geological conditions. Through the adjustment and optimization of the shield machine propulsion force parameters, the technical effect of improving the shield construction efficiency, stability and safety is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of a process flow of a shield machine excavation parameter adjustment method provided by an embodiment of the present invention;

[0017] Figure 2 A schematic diagram of the structure of a shield machine excavation parameter adjustment system provided by an embodiment of the present invention;

[0018] Figure 3 A functional block diagram of an electronic device provided by an embodiment of the present invention;

[0019] Figure 4 A principle block diagram of the computer-readable storage medium provided by the present invention.

[0020] In the accompanying drawings, the components represented by the reference numerals are listed as follows:

[0021] Propulsion resistance prediction module 11, propulsion force optimization module 12, fluctuation analysis module 13, auxiliary optimization module 14, electronic device 100, memory 110, processor 120, first computer program 111, computer readable storage medium 200, second computer program 211. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0023] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0024] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0025] Example 1

[0026] like Figure 1 As shown, an embodiment of the present invention provides a shield machine excavation parameter adjustment method, comprising:

[0027] S10: During the tunneling process of the shield machine, the propulsion resistance information at multiple historical moments in the past is recorded to obtain a historical propulsion resistance sequence, and the propulsion resistance at multiple future moments is predicted in combination with the engineering characteristic information of the tunneling project to obtain a predicted propulsion resistance sequence;

[0028] In an embodiment of the present application, during the tunneling process of the shield machine, the propulsion resistance information within multiple historical moments in the past is recorded. By recording the propulsion resistance information at multiple historical moments, the dynamic changes of the propulsion resistance in the tunneling operation can be effectively captured.

[0029] Furthermore, combined with the engineering characteristic information of the tunneling project, the propulsion resistance at multiple moments in the future is accurately predicted, so as to obtain the propulsion resistance at multiple moments in the future as the basis for optimizing and adjusting the propulsion force of the shield machine and obtaining the predicted propulsion resistance sequence.

[0030] Step S10 in the method provided in the embodiment of the present application includes:

[0031] Obtain engineering characteristic information of excavation engineering;

[0032] During the tunneling process of the shield machine, the advancement resistance information in multiple historical moments in the past is recorded to obtain the historical advancement resistance sequence;

[0033] The historical propulsion resistance sequence is input into a pre-trained propulsion resistance predictor, and the propulsion resistance predictions at the multiple future moments are obtained by prediction output to obtain a predicted propulsion resistance sequence, wherein the propulsion resistance predictor is obtained through supervised training.

[0034] In the embodiment of the present application, the engineering characteristic information of the excavation project is first obtained. The excavation project is the project in which the shield machine is currently excavating, such as a tunnel. The engineering characteristic information includes, for example, soil layer type (such as soft soil, hard rock, sandy soil, etc.), soil layer humidity, soil layer hardness, tunnel depth, etc. The engineering characteristic information can reflect the resistance level of the current construction excavation. For example, when the soil layer type is soft soil, the soil layer humidity is high, and the soil layer hardness is low, the excavation resistance is low.

[0035] During the actual tunneling process of the shield machine, the historical thrust resistance sequence is constructed by real-time monitoring and recording the thrust resistance data at multiple historical moments. The thrust resistance is the geological resistance encountered by the shield machine during tunneling, specifically the resistance encountered when the cutterhead is cutting. By installing a pressure sensor on the cutterhead to measure the pressure when the soil layer contacts the cutterhead, the thrust resistance data is obtained and recorded. The thrust resistance data is 175kN, 300kN, etc. For example, the thrust resistance is measured once every 1 second, and the 10 thrust resistance information in the past 10 seconds is recorded to obtain the historical thrust resistance sequence.

[0036] Furthermore, the future propulsion resistance is predicted based on the historical propulsion resistance sequence, and the historical propulsion resistance sequence will be input into the pre-built propulsion resistance predictor. The propulsion resistance predictor is a model trained through supervised learning. The resistance predictor is trained by inputting a set of known historical data (including historical propulsion resistance sequences and corresponding engineering feature information). It can learn the laws and patterns in the historical data and predict the future propulsion resistance value based on these laws. The training process of the resistance predictor is carried out through a large number of historical data sets, optimizing the model parameters so that it can accurately output the propulsion resistance prediction values ​​at multiple moments in the future when facing new historical data, thereby forming a predicted propulsion resistance sequence.

[0037] Predicting the propulsion resistance sequence can not only provide real-time resistance warning for the shield machine operation, but also provide a reliable basis for optimizing the excavation parameters. In this way, it can provide a basis for the shield machine to dynamically adjust the propulsion force in real time, thereby improving the excavation efficiency, reducing energy consumption, and ensuring construction safety.

[0038] In the embodiment of the present application, the supervised training step of the propulsion resistance predictor includes:

[0039] According to the shield machine excavation data in the historical time, the sample engineering characteristic information set, the sample historical advancement resistance sequence set and the sample predicted advancement resistance sequence set are collected;

[0040] The sample engineering feature information set, the sample historical propulsion resistance sequence set and the sample predicted propulsion resistance sequence set are used as supervised training data to perform supervised training of the propulsion resistance predictor until convergence, and then tested. When the requirements are met, the training is completed.

[0041] In the embodiment of the present application, the supervised training step of the propulsion resistance predictor uses historical data to learn and optimize the propulsion resistance predictor, thereby improving its prediction accuracy and reliability in practical applications.

[0042] Specifically, based on the shield machine excavation data recorded in the historical time, the sample engineering feature information set, the sample historical advancement resistance sequence set and the sample predicted advancement resistance sequence set are collected. The sample engineering feature information set includes the soil type (such as soft soil, sand, hard rock, etc.), soil moisture, soil hardness, tunnel depth and other information of multiple sample shield machine construction projects in the historical time. The sample historical advancement resistance sequence set includes multiple sample historical advancement resistance sequences recorded in the construction of sample shield machine construction projects in the historical time, and the collection method is the same as the current historical advancement resistance sequence. The sample predicted advancement resistance sequence set includes multiple advancement resistance sequences formed by the advancement resistance at multiple moments after multiple sample historical advancement resistance sequences, marked as multiple sample predicted advancement resistance sequences, that is, the advancement resistance sequence after each sample historical advancement resistance sequence.

[0043] After collecting the above sample data, the sample engineering feature information set, the sample historical propulsion resistance sequence set and the sample predicted propulsion resistance sequence set are used as supervised training data, wherein the sample engineering feature information set and the sample historical propulsion resistance sequence set are used as input data, and the sample predicted propulsion resistance sequence set is used as output data for training the propulsion resistance predictor. The supervised training data is divided to obtain a training set and a test set, for example, the ratio of the training set to the test set is 4:1.

[0044] Exemplarily, a feedforward neural network in machine learning is used to train the propulsion resistance predictor. The propulsion resistance predictor includes an input layer, a hidden layer, and an output layer. The number of nodes in the input layer is the number of data in the engineering feature information and the historical propulsion resistance sequence. If the engineering feature information includes 4 feature data and the historical propulsion resistance sequence includes 10 historical propulsion resistances, the number of nodes in the input layer is 10. The hidden layer includes multiple neural nodes, and the ReLU activation function is used. The number of nodes in the output layer is the same as the number of data in the predicted propulsion resistance sequence, for example, 10. During the training process, the input data in the supervised training data is input, and the output is transmitted after processing to obtain the output value. The error ratio of the output value and the corresponding sample propulsion resistance sequence in the output data is calculated as the loss. According to the loss, the weights of multiple neural nodes in the hidden layer are adjusted by gradient descent to reduce the loss until the loss is less than the requirement, for example, the error ratio of all predicted propulsion resistances is less than 5%. Further, multiple groups of supervised training data are used for iterative training to gradually reduce the error until the error of the row propulsion resistance predictor is less than the required value, for example, less than 4%, and the training converges.

[0045] After the training is completed, the propulsion resistance predictor is tested using the test set to obtain its accuracy and determine whether it meets the requirements, for example, whether the accuracy is greater than or equal to 96%. If so, the training is completed.

[0046] Based on the trained propulsion resistance predictor, the current historical propulsion resistance sequence can be input, and the predicted propulsion resistance sequences at multiple future moments in the future can be predicted and output.

[0047] S20: optimizing the propulsion force of the shield machine according to the predicted propulsion resistance sequence, with the purpose of increasing the propulsion speed and improving the stability of the soil layer, to obtain an optimized propulsion force;

[0048] In the embodiment of the present application, the thrust force of the shield machine is optimized based on the predicted thrust resistance sequence, with the purpose of increasing the thrust speed and improving the stability of the soil layer. Too much thrust will reduce the stability of the soil layer, while too little thrust will reduce the thrust speed and affect the construction efficiency. Therefore, the two are combined for optimization to improve the construction efficiency and safety when the thrust force is optimized.

[0049] Step S20 in the method provided in the embodiment of the present application includes:

[0050] Acquiring a propulsion force adjustment space of the shield machine, and randomly generating a first propulsion force in the propulsion force adjustment space;

[0051] According to the first propulsion force and the predicted propulsion resistance sequence, propulsion speed prediction and soil layer stability grade prediction are performed to obtain a first predicted propulsion speed sequence and a first predicted soil layer stability grade sequence, wherein a sample propulsion force set, a sample propulsion resistance set, and a sample propulsion speed and a sample soil layer stability grade set are collected in historical excavation data, a propulsion prediction channel is trained, and propulsion prediction is performed;

[0052] Calculating a first propulsion fitness of the first propulsion force according to the first predicted propulsion speed sequence and the first predicted soil layer stability grade sequence;

[0053] Continue to optimize the thrust of the shield machine in the thrust adjustment space until convergence, and output the thrust with the maximum thrust fitness as the optimized thrust.

[0054] In the embodiment of the present application, the thrust refers to the force used by the shield machine to push the shield machine forward along the tunnel direction through the thrust system (usually powered by a hydraulic system or an electric thrust device). The thrust adjustment space is defined, that is, the thrust range of the shield machine that can be adjusted. The thrust range includes the lowest and highest available thrusts, for example, the lowest thrust is 50kN and the highest thrust is 300kN. With the lowest thrust and the highest thrust as the endpoint values, an interval is constructed to obtain the thrust adjustment space.

[0055] A first propulsion force is randomly generated in the propulsion force adjustment space, for example, a propulsion force of 100 kN is randomly generated.

[0056] According to the first propulsion force and the predicted propulsion resistance sequence, the propulsion speed prediction and the soil layer stability grade prediction are performed to obtain the first predicted propulsion speed sequence and the first predicted soil layer stability grade sequence. Exemplarily, based on the feedforward neural network in machine learning, the propulsion prediction channel is trained to perform the current propulsion speed prediction and propulsion soil layer stability prediction.

[0057] For example, in the historical excavation data, the propulsion force in different construction projects, the propulsion resistance of the shield machine, and the propulsion speed and soil stability level under the influence of the propulsion force and propulsion resistance are collected to obtain a sample propulsion force set, a sample propulsion resistance set, and a sample propulsion speed and a sample soil stability level set. The propulsion speed is the speed at which the shield machine cutterhead moves forward during the excavation process, and the unit is, for example, millimeters per minute (mm / min). For example, when the propulsion force is 200kN and the propulsion resistance is 175kN, the propulsion speed is 150 mm / min, which can be obtained by testing. The soil stability grade is, for example, 5 grades from 1 to 5. The larger the grade, the more stable the soil layer. The soil stability grade can be rated by shield construction technicians based on the thrust and thrust resistance. For example, the greater the difference between the thrust and thrust resistance, the smaller the soil stability grade, and vice versa. For example, when the difference between the thrust and thrust resistance is 0 or a negative number, the soil stability grade is 5. When the difference is 0~50kN, the soil stability grade is 4. And so on, a sample soil stability grade set is obtained.

[0058] Using the sample propulsion force set and the sample propulsion resistance set as input data, and the sample propulsion speed and the sample soil layer stability grade set as output data, the propulsion prediction channel is trained based on the feedforward neural network to perform propulsion prediction. Among them, the training method of the propulsion prediction channel is the same as the training process of the propulsion resistance predictor in the above content, but the specific training data is different. The input data is input into the propulsion prediction channel constructed based on the feedforward network to obtain the output value. According to the difference percentage between the output value and the sample propulsion speed and the sample soil layer stability grade in the output data, the network parameters are adjusted to reduce the difference percentage until the requirements are met, and iterative training is performed until the prediction accuracy of all sample data meets the requirements, for example, greater than 95%, and the training is completed.

[0059] The current first propulsion force is combined with multiple predicted propulsion resistances in the predicted propulsion resistance sequence and input into the trained propulsion prediction channel, and multiple first predicted propulsion speeds and multiple first predicted soil layer stability levels are output. The future moments corresponding to the multiple predicted propulsion resistances are combined to obtain the first predicted propulsion speed sequence and the first predicted soil layer stability level sequence.

[0060] According to the first predicted propulsion speed sequence and the first predicted soil layer stability grade sequence, the first propulsion fitness of the first propulsion force is calculated for the purpose of improving the propulsion speed and improving the soil layer stability. The magnitude of the first propulsion fitness is positively correlated with the magnitude of the propulsion speed, soil layer stability, etc.

[0061] In the embodiment of the present application, the first propulsion fitness of the first propulsion force is calculated according to the first predicted propulsion speed sequence and the first predicted soil layer stability grade sequence, including:

[0062] Calculating the mean of the historical propulsion resistance sequence and the predicted propulsion resistance sequence to obtain the average propulsion resistance;

[0063] Acquire a propulsion resistance threshold, multiply the ratio of the average propulsion resistance to the propulsion resistance threshold by a preset stability weight to obtain an adjusted stability weight, and subtract the adjusted stability weight from 1 to obtain a speed weight;

[0064] According to the adjusted stability weight and speed weight, the first predicted propulsion speed sequence and the first predicted soil layer stability grade sequence are used to calculate the first propulsion fitness of the first propulsion force, as shown in the following formula:

[0065] ;

[0066] Among them, PRA is the promotion fitness, and is the speed weight and the adjustment stability weight, M is the number of multiple future moments, is the predicted propulsion speed at the ith future moment in the predicted propulsion speed sequence, For the preset propulsion speed, To predict the soil stability level at the ith future moment in the soil stability level sequence, It is the preset soil stability grade.

[0067] In the embodiment of the present application, the average of all propulsion resistances in the historical propulsion resistance sequence and the predicted propulsion resistance sequence is calculated to obtain the average propulsion resistance.

[0068] Further, a propulsion resistance threshold is obtained. Exemplarily, the propulsion resistance threshold is the average of all propulsion resistances in all construction data records of the shield machine in the historical time, reflecting the average propulsion resistance level of the shield machine.

[0069] The ratio of the average propulsion resistance to the propulsion resistance threshold is multiplied by the preset stability weight to obtain the adjusted stability weight. The preset stability weight is the weight of the importance of soil layer stability in the preset propulsion force adjustment, for example, 0.5. The larger the current average propulsion resistance, the more important the stability of the soil layer is in the propulsion construction. The ratio of the average propulsion resistance to the propulsion resistance threshold is multiplied by the preset stability weight to obtain the adjusted adjusted stability weight. The larger the average propulsion resistance, the larger the preset stability weight, and the greater the importance of soil layer stability in the optimization. For example, if the ratio of the average propulsion resistance to the propulsion resistance threshold is 1.1, the adjusted stability weight is 1.1*0.5=0.55.

[0070] For example, in soft soil layers, lower propulsion resistance may result in a greater weighting of velocity, whereas in hard rock layers, greater propulsion resistance may result in a greater weighting of adjusted stability.

[0071] The speed weight is obtained by subtracting the adjustment stability weight from 1, for example, 1-0.55=0.45. The speed weight is the weight of the importance of the propulsion speed in the propulsion force adjustment. The larger the speed weight, the greater the importance of the propulsion speed in the shield machine propulsion force adjustment. And the sum of the speed weight and the adjustment stability weight is 1.

[0072] According to the adjustment of stability weight and speed weight, the first predicted advancement speed sequence and the first predicted soil layer stability grade sequence are used to calculate the first advancement fitness of the first advancement force, as shown in the following formula:

[0073] ;

[0074] Among them, PRA is the promotion fitness, and is the speed weight and the adjustment stability weight, M is the number of multiple future moments, is the predicted propulsion speed at the ith future moment in the predicted propulsion speed sequence, The preset advancing speed is, for example, the average advancing speed in the historical period, for example, 150 mm / min. To predict the soil stability level at the ith future moment in the soil stability level sequence, is a preset soil layer stability level, for example, an average soil layer stability level, such as 3. The greater the predicted advancement speed in the predicted advancement speed sequence, the greater the predicted soil layer stability level in the predicted soil layer stability level sequence, and the greater the advancement adaptability.

[0075] Further, based on the method in the above content, the thrust force of the shield machine is optimized in the thrust force adjustment space, that is, the thrust force is randomly generated, the thrust speed and the soil stability level are predicted, and the thrust fitness is calculated for optimization until convergence, for example, the number of optimizations reaches 100. After the optimization converges, the thrust force with the maximum thrust fitness is output as the optimized thrust force, and the optimization is completed.

[0076] Through the above steps, the thrust of the shield machine can be optimized under the premise of simultaneously considering the improvement of the thrust speed and the stability of the soil layer, and the weights of the thrust speed and the soil layer stability in the configuration optimization can be considered to improve the accuracy of the thrust optimization and the construction safety. During the optimization process, the thrust speed and the soil layer stability level at each future moment have different degrees of influence on the final thrust fitness. The thrust fitness is calculated based on the thrust speed and soil layer stability level predicted at multiple future moments, which can consider the advancement situation in a future period of time, is forward-looking, and thus improves the construction stability. According to the calculation results of the thrust fitness, the thrust of the shield machine will be continuously optimized until the optimal thrust configuration is reached, thereby achieving an efficient and safe excavation process.

[0077] S30: performing fluctuation analysis on the historical advancement resistance sequence and the predicted advancement resistance sequence, and calculating and obtaining the minimum fluctuation advancement resistance and the maximum fluctuation advancement resistance, and performing advancement speed analysis and soil layer stability analysis respectively to obtain minimum advancement speed and minimum soil layer stability information;

[0078] In the embodiment of the present application, due to the changes in the soil structure at different depths during shield construction, the propulsion resistance will fluctuate to a certain extent, resulting in local larger or smaller changes in the propulsion resistance. In the process of adjusting the propulsion resistance, it is necessary to take this change into consideration and further optimize the propulsion force adjustment to avoid a sudden change in the propulsion resistance that causes a decrease in construction speed or a decrease in soil stability, thereby affecting the construction quality.

[0079] Step S30 in the method provided in the embodiment of the present application includes:

[0080] Randomly selecting a plurality of first random propulsion resistances and a plurality of second random propulsion resistances from the historical propulsion resistance sequence and the predicted propulsion resistance sequence;

[0081] Calculating the deviation amplitude of the mean values ​​of the plurality of first random propulsion resistances and the plurality of second random propulsion resistances to obtain the first propulsion resistance fluctuation amplitude;

[0082] Continue to calculate to obtain multiple propulsion resistance fluctuation amplitudes, calculate the average, and obtain the average propulsion resistance fluctuation amplitude;

[0083] Extracting the maximum propulsion resistance and the minimum propulsion resistance in the historical propulsion resistance sequence and the predicted propulsion resistance sequence;

[0084] Using the average propulsion resistance fluctuation amplitude to perform positive compensation calculation and negative compensation calculation on the maximum propulsion resistance and the minimum propulsion resistance, respectively, to obtain the maximum fluctuating propulsion resistance and the minimum fluctuating propulsion resistance;

[0085] The maximum fluctuating propulsion resistance and the minimum fluctuating propulsion resistance are respectively input into the propulsion prediction channel in combination with the optimized propulsion force, and the prediction output obtains the minimum soil layer stability information and the minimum propulsion speed.

[0086] In the embodiment of the present application, multiple first random propulsion resistances and multiple second random propulsion resistances are randomly selected from the historical propulsion resistance sequence and the predicted propulsion resistance sequence in the aforementioned content. The number of the multiple first random propulsion resistances and the number of the multiple second random propulsion resistances are the same, and each randomly selected random propulsion resistance may be a historical propulsion resistance or a predicted propulsion resistance. In this way, the fluctuation of propulsion resistance at multiple historical moments and multiple future moments can be analyzed.

[0087] Calculate the average of the plurality of first random propulsion resistances and the plurality of second random propulsion resistances to obtain the first random propulsion resistance average and the second random propulsion resistance average, and calculate the deviation amplitude between the two, for example, calculate the ratio of the absolute value of the difference between the first random propulsion resistance average and the second random propulsion resistance average to the second random propulsion resistance average, and obtain the first propulsion resistance fluctuation amplitude. The larger the first propulsion resistance fluctuation amplitude, the greater the overall difference between the plurality of first random propulsion resistances and the plurality of second random propulsion resistances, and the greater the propulsion resistance fluctuation amplitude.

[0088] Continue to randomly select multiple groups of first random propulsion resistances and second random propulsion resistances, and calculate the propulsion resistance fluctuation amplitudes in the same manner to obtain multiple propulsion resistance fluctuation amplitudes.

[0089] The average of multiple propulsion resistance fluctuations is further calculated to obtain the average propulsion resistance fluctuation. The larger the average propulsion resistance fluctuation, the greater the gap between the propulsion resistance in the historical propulsion resistance sequence and the predicted propulsion resistance sequence table, the greater the fluctuation, and the greater the propulsion resistance changes that may occur in multiple future moments.

[0090] The maximum and minimum values ​​of the propulsion resistance in the historical propulsion resistance sequence and the predicted propulsion resistance sequence are extracted to obtain the maximum propulsion resistance and the minimum propulsion resistance.

[0091] The average propulsion resistance fluctuation amplitude is used to perform positive compensation calculation and negative compensation calculation on the maximum propulsion resistance and the minimum propulsion resistance, respectively. For example, the maximum propulsion resistance is compensated and amplified, and the minimum propulsion resistance is compensated and reduced, so as to obtain the maximum and minimum fluctuating propulsion resistance in extreme cases where the propulsion resistance may fluctuate in multiple future moments. In this way, the maximum fluctuating propulsion resistance and the minimum fluctuating propulsion resistance are obtained.

[0092] Exemplarily, the maximum propulsion resistance is obtained by multiplying the sum of 1 and the average propulsion resistance fluctuation amplitude by the maximum propulsion resistance, and the minimum propulsion resistance is obtained by multiplying the difference between 1 and the average propulsion resistance fluctuation amplitude by the minimum propulsion resistance.

[0093] Furthermore, the maximum fluctuation propulsion resistance and the minimum fluctuation propulsion resistance after fluctuation analysis compensation are respectively combined with the optimized propulsion force obtained by preliminary optimization in step S20 as input data, and input into the propulsion prediction channel in the aforementioned content, and the propulsion speed corresponding to the maximum fluctuation propulsion resistance, that is, the minimum propulsion speed, is output. Among them, the greater the propulsion resistance, the greater the obstruction to the advancement of the shield machine, and the smaller the propulsion speed. The minimum propulsion speed reflects the minimum propulsion speed under the influence of propulsion resistance fluctuation when the shield is advanced according to the optimized propulsion force. And the minimum fluctuation propulsion resistance after fluctuation analysis compensation is combined with the optimized propulsion force as input data, and input into the propulsion prediction channel in the aforementioned content, and the soil layer stability level corresponding to the minimum fluctuation propulsion resistance, that is, the minimum soil layer stability information, is output. Among them, the smaller the propulsion resistance, the smaller the soil layer stability level, and the minimum soil layer stability information reflects the minimum soil layer stability level under the influence of propulsion resistance fluctuation when the shield is advanced according to the optimized propulsion force.

[0094] By analyzing the fluctuation of the propulsion resistance and compensating for the calculation to obtain the maximum and minimum propulsion resistance under the fluctuation condition, the minimum soil stability information and the minimum propulsion speed under the fluctuation condition are further analyzed to obtain the influence of the propulsion resistance fluctuation on the propulsion stability, which will serve as the basis for subsequent adjustments to the optimized propulsion force.

[0095] S40: According to the minimum propulsion speed and the minimum soil layer stability information, the optimized propulsion force is auxiliary optimized to obtain the optimal propulsion force, and the tunneling parameters of the shield machine are adjusted.

[0096] In the embodiment of the present application, the minimum propulsion speed and minimum soil layer stability information caused by the fluctuation of the propulsion resistance are taken into consideration, and the optimized propulsion force optimized in the aforementioned content is further auxiliary optimized and adjusted to reduce the influence of the propulsion speed and soil layer stability caused by the fluctuation of the propulsion resistance.

[0097] Step S40 in the method provided in the embodiment of the present application includes:

[0098] Obtaining the optimized predicted propulsion speed and the optimized predicted soil stability grade of the optimized propulsion force;

[0099] Calculating the ratio of the minimum propulsion speed to the optimized predicted propulsion speed to obtain a speed attenuation amplitude, and adding 1 to the speed attenuation amplitude to obtain a speed correction coefficient;

[0100] Calculating the ratio of the minimum soil layer stability information to the optimized predicted soil layer stability grade to obtain a stable attenuation amplitude, and subtracting the stable attenuation amplitude from 1 to obtain a stable correction coefficient;

[0101] The speed correction coefficient is multiplied by the optimized propulsion force to obtain the speed optimized propulsion force, and the stability correction coefficient is multiplied by the optimized propulsion force to obtain the stable optimized propulsion force;

[0102] The average of the speed-optimized propulsion force and the stability-optimized propulsion force is calculated to obtain the optimal propulsion force.

[0103] In an embodiment of the present application, an optimized predicted propulsion speed and an optimized predicted soil layer stability grade of an optimized propulsion force are obtained. Specifically, a predicted propulsion speed sequence and a predicted soil layer stability grade sequence are obtained by inputting the optimized propulsion force into a propulsion prediction channel output in combination with multiple predicted propulsion resistances in a predicted propulsion resistance sequence. Then, the means of the predicted propulsion speed sequence and the predicted soil layer stability grade sequence are calculated to obtain an average predicted propulsion speed and an average predicted soil layer stability grade of the optimized propulsion force as the optimized predicted propulsion speed and the optimized predicted soil layer stability grade.

[0104] The ratio of the minimum propulsion speed to the optimized predicted propulsion speed is calculated and used as the speed attenuation amplitude, that is, the amplitude at which the propulsion speed changes to the minimum due to possible propulsion resistance fluctuations. 1 plus the speed attenuation amplitude is used as the speed correction coefficient.

[0105] And, the ratio of the minimum soil layer stability information and the optimized predicted soil layer stability grade is calculated, and the ratio is used as the stability attenuation amplitude, that is, the amplitude at which the soil layer stability grade changes to the minimum due to possible propulsion resistance fluctuations. The stability correction coefficient is obtained by subtracting the stability attenuation amplitude from 1.

[0106] The speed correction coefficient is adopted and multiplied by the optimized propulsion force to amplify the optimized propulsion force and obtain the speed optimized propulsion force, so as to increase the propulsion speed when possible propulsion resistance fluctuation occurs and reduce the propulsion speed reduction caused by the propulsion resistance fluctuation.

[0107] And adopt a stability correction coefficient, multiply it by the optimized propulsion force, reduce the optimized propulsion force, and obtain a stable optimized propulsion force, so as to reduce the propulsion force when possible propulsion resistance fluctuations occur, improve the soil stability level, and reduce the reduction in soil stability caused by propulsion resistance fluctuations.

[0108] During the adjustment process, in addition to improving the advancing speed and soil stability level under fluctuating conditions, the soil stability level and advancing speed when no advancing resistance fluctuation occurs will also be affected. Therefore, the average of the adjusted speed-optimized advancing force and the stability-optimized advancing force is calculated, and the speed-optimized advancing force and the stability-optimized advancing force adjusted in the two directions are integrated to obtain the optimal advancing force after the optimal auxiliary optimization processing. This can maximize the advancing speed and soil stability when possible advancing resistance fluctuations occur, thereby improving the stability, efficiency and safety of shield construction.

[0109] The embodiments of the present application achieve the following technical effects through the above specific implementation methods:

[0110] The shield machine excavation parameter adjustment method of the present invention can accurately predict the propulsion resistance in the future time by introducing the historical propulsion resistance sequence and engineering characteristic information, and combining the prediction model to accurately predict the propulsion resistance at multiple moments in the future. Through the analysis of the predicted propulsion resistance sequence, the present invention can optimize the propulsion force of the shield machine, reasonably improve the propulsion speed, and effectively balance the stability of the soil layer. Further, the propulsion force is optimized and adjusted according to the predicted propulsion resistance sequence to improve the propulsion efficiency while ensuring the construction safety. In addition, the fluctuation analysis combined with the historical and predicted propulsion resistance information further optimizes the propulsion force, thereby improving the overall operation efficiency. Through the technical solution of this application, the accuracy and flexibility of the shield machine excavation parameter adjustment are improved, the propulsion force can be adjusted according to the real-time soil layer conditions, the propulsion speed is optimized, the soil layer during excavation is guaranteed to be stable, and the safety and efficiency of the shield construction process are ensured, thereby improving the adaptability of the shield machine under complex geological conditions. Through the adjustment and optimization of the shield machine propulsion force parameters, the technical effect of improving the shield construction efficiency, stability and safety is achieved.

[0111] Example 2

[0112] like Figure 2 As shown, based on the same inventive concept as the shield machine excavation parameter adjustment method provided in Example 1, an embodiment of the present invention provides a shield machine excavation parameter adjustment system, the system comprising:

[0113] The propulsion resistance prediction module 11 is used to record the propulsion resistance information at multiple historical moments in the past during the tunneling process of the shield machine, obtain the historical propulsion resistance sequence, and predict the propulsion resistance at multiple future moments in the future in combination with the engineering characteristic information of the tunneling project to obtain the predicted propulsion resistance sequence;

[0114] A propulsion force optimization module 12 is used to optimize the propulsion force of the shield machine according to the predicted propulsion resistance sequence, with the purpose of increasing the propulsion speed and improving the stability of the soil layer, so as to obtain an optimized propulsion force;

[0115] The fluctuation analysis module 13 is used to perform fluctuation analysis on the historical advancement resistance sequence and the predicted advancement resistance sequence, and calculate the minimum fluctuation advancement resistance and the maximum fluctuation advancement resistance, and respectively perform advancement speed analysis and soil layer stability analysis to obtain the minimum advancement speed and minimum soil layer stability information;

[0116] The auxiliary optimization module 14 is used to perform auxiliary optimization on the optimized propulsion force according to the minimum propulsion speed and the minimum soil layer stability information, obtain the optimal propulsion force, and adjust the tunneling parameters of the shield machine.

[0117] Furthermore, the propulsion resistance prediction module 11 is also used for:

[0118] Obtain engineering characteristic information of excavation engineering;

[0119] During the tunneling process of the shield machine, the advancement resistance information in multiple historical moments in the past is recorded to obtain the historical advancement resistance sequence;

[0120] The historical propulsion resistance sequence is input into a pre-trained propulsion resistance predictor, and the propulsion resistance predictions at the multiple future moments are obtained by prediction output to obtain a predicted propulsion resistance sequence, wherein the propulsion resistance predictor is obtained through supervised training.

[0121] The supervised training step of the propulsion resistance predictor comprises:

[0122] According to the shield machine excavation data in the historical time, the sample engineering characteristic information set, the sample historical advancement resistance sequence set and the sample predicted advancement resistance sequence set are collected;

[0123] The sample engineering feature information set, the sample historical propulsion resistance sequence set and the sample predicted propulsion resistance sequence set are used as supervised training data to perform supervised training of the propulsion resistance predictor until convergence, and then tested. When the requirements are met, the training is completed.

[0124] Furthermore, the propulsion optimization module 12 is also used for:

[0125] Acquiring a propulsion force adjustment space of the shield machine, and randomly generating a first propulsion force in the propulsion force adjustment space;

[0126] According to the first propulsion force and the predicted propulsion resistance sequence, propulsion speed prediction and soil layer stability grade prediction are performed to obtain a first predicted propulsion speed sequence and a first predicted soil layer stability grade sequence, wherein a sample propulsion force set, a sample propulsion resistance set, and a sample propulsion speed and a sample soil layer stability grade set are collected in historical excavation data, a propulsion prediction channel is trained, and propulsion prediction is performed;

[0127] Calculating a first propulsion fitness of the first propulsion force according to the first predicted propulsion speed sequence and the first predicted soil layer stability grade sequence;

[0128] Continue to optimize the thrust of the shield machine in the thrust adjustment space until convergence, and output the thrust with the maximum thrust fitness as the optimized thrust.

[0129] The first propulsion fitness of the first propulsion force is calculated according to the first predicted propulsion speed sequence and the first predicted soil layer stability grade sequence, including:

[0130] Calculating the mean of the historical propulsion resistance sequence and the predicted propulsion resistance sequence to obtain the average propulsion resistance;

[0131] Acquire a propulsion resistance threshold, multiply the ratio of the average propulsion resistance to the propulsion resistance threshold by a preset stability weight to obtain an adjusted stability weight, and subtract the adjusted stability weight from 1 to obtain a speed weight;

[0132] According to the adjusted stability weight and speed weight, the first predicted propulsion speed sequence and the first predicted soil layer stability grade sequence are used to calculate the first propulsion fitness of the first propulsion force, as shown in the following formula:

[0133] ;

[0134] Among them, PRA is the promotion fitness, and is the speed weight and the adjustment stability weight, M is the number of multiple future moments, is the predicted propulsion speed at the ith future moment in the predicted propulsion speed sequence, For the preset propulsion speed, To predict the soil stability level at the ith future moment in the soil stability level sequence, It is the preset soil stability grade.

[0135] Furthermore, the fluctuation analysis module 13 is also used for:

[0136] Randomly selecting a plurality of first random propulsion resistances and a plurality of second random propulsion resistances from the historical propulsion resistance sequence and the predicted propulsion resistance sequence;

[0137] Calculating the deviation amplitude of the mean values ​​of the plurality of first random propulsion resistances and the plurality of second random propulsion resistances to obtain the first propulsion resistance fluctuation amplitude;

[0138] Continue to calculate to obtain multiple propulsion resistance fluctuation amplitudes, calculate the average, and obtain the average propulsion resistance fluctuation amplitude;

[0139] Extracting the maximum propulsion resistance and the minimum propulsion resistance in the historical propulsion resistance sequence and the predicted propulsion resistance sequence;

[0140] Using the average propulsion resistance fluctuation amplitude to perform positive compensation calculation and negative compensation calculation on the maximum propulsion resistance and the minimum propulsion resistance, respectively, to obtain the maximum fluctuating propulsion resistance and the minimum fluctuating propulsion resistance;

[0141] The maximum fluctuating propulsion resistance and the minimum fluctuating propulsion resistance are respectively input into the propulsion prediction channel in combination with the optimized propulsion force, and the prediction output obtains the minimum soil layer stability information and the minimum propulsion speed.

[0142] Furthermore, the auxiliary optimization module 14 is also used to: obtain the optimized predicted propulsion speed and the optimized predicted soil stability grade of the optimized propulsion force;

[0143] Calculating the ratio of the minimum propulsion speed to the optimized predicted propulsion speed to obtain a speed attenuation amplitude, and adding 1 to the speed attenuation amplitude to obtain a speed correction coefficient;

[0144] Calculating the ratio of the minimum soil layer stability information to the optimized predicted soil layer stability grade to obtain a stable attenuation amplitude, and subtracting the stable attenuation amplitude from 1 to obtain a stable correction coefficient;

[0145] The speed correction coefficient is multiplied by the optimized propulsion force to obtain the speed optimized propulsion force, and the stability correction coefficient is multiplied by the optimized propulsion force to obtain the stable optimized propulsion force;

[0146] The average of the speed-optimized propulsion force and the stability-optimized propulsion force is calculated to obtain the optimal propulsion force.

[0147] See also Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 100, including a memory 110, a processor 120, and a first computer program 111 stored in the memory 110 and executable on the processor 120. When the processor 120 executes the first computer program 111, the steps of the method in Example 1 are implemented.

[0148] See also Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 200 on which a second computer program 211 is stored. When the second computer program 211 is executed by a processor, the steps of the method in Embodiment 1 are implemented.

[0149] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0150] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0151] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0152] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0153] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0154] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0155] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for adjusting tunneling parameters of a shield machine, characterized in that: The method comprises: During the tunneling process of the shield machine, the propulsion resistance information at multiple historical moments in the past is recorded to obtain a historical propulsion resistance sequence. Combined with the engineering characteristic information of the tunneling project, the propulsion resistance at multiple future moments is predicted to obtain a predicted propulsion resistance sequence. According to the predicted propulsion resistance sequence, the propulsion force of the shield machine is optimized for the purpose of increasing the propulsion speed and improving the stability of the soil layer to obtain an optimized propulsion force; Performing fluctuation analysis on the historical advancement resistance sequence and the predicted advancement resistance sequence, and calculating and obtaining the minimum fluctuation advancement resistance and the maximum fluctuation advancement resistance, respectively performing advancement speed analysis and soil layer stability analysis, and obtaining the minimum advancement speed and minimum soil layer stability information; According to the minimum propulsion speed and the minimum soil layer stability information, the optimized propulsion force is auxiliary optimized to obtain the optimal propulsion force and adjust the tunneling parameters of the shield machine; According to the predicted propulsion resistance sequence, the propulsion force of the shield machine is optimized for the purpose of increasing the propulsion speed and improving the stability of the soil layer to obtain the optimized propulsion force, including: Acquiring a propulsion force adjustment space of the shield machine, and randomly generating a first propulsion force in the propulsion force adjustment space; According to the first propulsion force and the predicted propulsion resistance sequence, propulsion speed prediction and soil layer stability grade prediction are performed to obtain a first predicted propulsion speed sequence and a first predicted soil layer stability grade sequence, wherein a sample propulsion force set, a sample propulsion resistance set, and a sample propulsion speed and a sample soil layer stability grade set are collected in historical excavation data, a propulsion prediction channel is trained, and propulsion prediction is performed; Calculating a first propulsion fitness of the first propulsion force according to the first predicted propulsion speed sequence and the first predicted soil layer stability grade sequence; Continue to optimize the thrust of the shield machine in the thrust adjustment space until convergence, and output the thrust with the maximum thrust fitness as the optimized thrust.

2. The shield machine excavation parameter adjustment method according to claim 1, characterized in that: During the tunneling process of the shield machine, the propulsion resistance information in multiple historical moments in the past is recorded to obtain the historical propulsion resistance sequence. Combined with the engineering characteristic information of the tunneling project, the propulsion resistance at multiple future moments is predicted to obtain the predicted propulsion resistance sequence, including: Obtain engineering characteristic information of excavation engineering; During the tunneling process of the shield machine, the advancement resistance information in multiple historical moments in the past is recorded to obtain the historical advancement resistance sequence; The historical propulsion resistance sequence is input into a pre-trained propulsion resistance predictor, and the propulsion resistance predictions at the multiple future moments are obtained by prediction output to obtain a predicted propulsion resistance sequence, wherein the propulsion resistance predictor is obtained through supervised training.

3. The shield machine excavation parameter adjustment method according to claim 2, characterized in that: The supervised training steps of the propulsion resistance predictor include: According to the shield machine excavation data in the historical time, the sample engineering characteristic information set, the sample historical advancement resistance sequence set and the sample predicted advancement resistance sequence set are collected; The sample engineering feature information set, the sample historical propulsion resistance sequence set and the sample predicted propulsion resistance sequence set are used as supervised training data to perform supervised training of the propulsion resistance predictor until convergence, and then tested. When the requirements are met, the training is completed.

4. The shield machine excavation parameter adjustment method according to claim 1, characterized in that: Calculating a first propulsion fitness of the first propulsion force according to the first predicted propulsion speed sequence and the first predicted soil layer stability grade sequence includes: Calculating the mean of the historical propulsion resistance sequence and the predicted propulsion resistance sequence to obtain the average propulsion resistance; Acquire a propulsion resistance threshold, multiply the ratio of the average propulsion resistance to the propulsion resistance threshold by a preset stability weight to obtain an adjusted stability weight, and subtract the adjusted stability weight from 1 to obtain a speed weight; According to the adjusted stability weight and speed weight, the first predicted propulsion speed sequence and the first predicted soil layer stability grade sequence are used to calculate the first propulsion fitness of the first propulsion force, as shown in the following formula: ； Among them, PRA is the promotion fitness, and is the speed weight and the adjustment stability weight, M is the number of multiple future moments, is the predicted propulsion speed at the ith future moment in the predicted propulsion speed sequence, For the preset propulsion speed, To predict the soil stability level at the ith future moment in the soil stability level sequence, It is the preset soil stability grade.

5. The shield machine excavation parameter adjustment method according to claim 4, characterized in that: The historical advancement resistance sequence and the predicted advancement resistance sequence are subjected to fluctuation analysis, and the minimum fluctuation advancement resistance and the maximum fluctuation advancement resistance are calculated and obtained. The advancement speed analysis and the soil layer stability analysis are respectively performed to obtain the minimum advancement speed and the minimum soil layer stability information, including: Randomly selecting a plurality of first random propulsion resistances and a plurality of second random propulsion resistances from the historical propulsion resistance sequence and the predicted propulsion resistance sequence; Calculating the deviation amplitude of the mean values ​​of the plurality of first random propulsion resistances and the plurality of second random propulsion resistances to obtain the first propulsion resistance fluctuation amplitude; Continue to calculate to obtain multiple propulsion resistance fluctuation amplitudes, calculate the average, and obtain the average propulsion resistance fluctuation amplitude; Extracting the maximum propulsion resistance and the minimum propulsion resistance in the historical propulsion resistance sequence and the predicted propulsion resistance sequence; Using the average propulsion resistance fluctuation amplitude to perform positive compensation calculation and negative compensation calculation on the maximum propulsion resistance and the minimum propulsion resistance, respectively, to obtain the maximum fluctuating propulsion resistance and the minimum fluctuating propulsion resistance; The maximum fluctuating propulsion resistance and the minimum fluctuating propulsion resistance are respectively input into the propulsion prediction channel in combination with the optimized propulsion force, and the prediction output obtains the minimum soil layer stability information and the minimum propulsion speed.

6. The shield machine excavation parameter adjustment method according to claim 5, characterized in that: According to the minimum propulsion speed and the minimum soil layer stability information, the optimized propulsion force is auxiliary optimized to obtain the optimal propulsion force, including: Obtaining the optimized predicted propulsion speed and the optimized predicted soil stability grade of the optimized propulsion force; Calculating the ratio of the minimum propulsion speed to the optimized predicted propulsion speed to obtain a speed attenuation amplitude, and adding 1 to the speed attenuation amplitude to obtain a speed correction coefficient; Calculating the ratio of the minimum soil layer stability information to the optimized predicted soil layer stability grade to obtain a stable attenuation amplitude, and subtracting the stable attenuation amplitude from 1 to obtain a stable correction coefficient; The speed correction coefficient is multiplied by the optimized propulsion force to obtain the speed optimized propulsion force, and the stability correction coefficient is multiplied by the optimized propulsion force to obtain the stable optimized propulsion force; The average of the speed-optimized propulsion force and the stability-optimized propulsion force is calculated to obtain the optimal propulsion force.

7. A shield machine excavation parameter adjustment system, characterized in that: The system comprises: The propulsion resistance prediction module is used to record the propulsion resistance information at multiple historical moments in the past during the tunneling process of the shield machine, obtain the historical propulsion resistance sequence, and predict the propulsion resistance at multiple future moments in combination with the engineering characteristic information of the tunneling project to obtain the predicted propulsion resistance sequence; A propulsion force optimization module is used to optimize the propulsion force of the shield machine according to the predicted propulsion resistance sequence, with the purpose of increasing the propulsion speed and improving the stability of the soil layer, so as to obtain an optimized propulsion force; A fluctuation analysis module is used to perform fluctuation analysis on the historical advancement resistance sequence and the predicted advancement resistance sequence, and calculate the minimum fluctuation advancement resistance and the maximum fluctuation advancement resistance, and respectively perform advancement speed analysis and soil layer stability analysis to obtain minimum advancement speed and minimum soil layer stability information; An auxiliary optimization module, used to perform auxiliary optimization on the optimized propulsion force according to the minimum propulsion speed and the minimum soil layer stability information, obtain the optimal propulsion force, and adjust the tunneling parameters of the shield machine; According to the predicted propulsion resistance sequence, the propulsion force of the shield machine is optimized for the purpose of increasing the propulsion speed and improving the stability of the soil layer to obtain the optimized propulsion force, including: Acquiring a propulsion force adjustment space of the shield machine, and randomly generating a first propulsion force in the propulsion force adjustment space; According to the first propulsion force and the predicted propulsion resistance sequence, propulsion speed prediction and soil layer stability grade prediction are performed to obtain a first predicted propulsion speed sequence and a first predicted soil layer stability grade sequence, wherein a sample propulsion force set, a sample propulsion resistance set, and a sample propulsion speed and a sample soil layer stability grade set are collected in historical excavation data, a propulsion prediction channel is trained, and propulsion prediction is performed; Calculating a first propulsion fitness of the first propulsion force according to the first predicted propulsion speed sequence and the first predicted soil layer stability grade sequence; Continue to optimize the thrust of the shield machine in the thrust adjustment space until convergence, and output the thrust with the maximum thrust fitness as the optimized thrust.

8. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the shield machine excavation parameter adjustment method described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer software program, and when the computer software program is executed by the processor, the shield machine excavation parameter adjustment method according to any one of claims 1 to 6 is implemented.

Images