A method and apparatus for railway subgrade design based on a rule engine

Abstract

This invention relates to the field of railway subgrade design, specifically to a railway subgrade design method and apparatus based on a rule engine. The method includes acquiring basic engineering data of the railway subgrade design section, including slope height, soil type, cut and fill type, and groundwater depth; performing rule matching processing on the basic engineering data using a preset design rule library to obtain candidate design schemes; calculating multi-dimensional indicators based on the candidate design schemes to obtain evaluation indicator information corresponding to each candidate design scheme; performing weight adaptive configuration processing on the evaluation indicator information corresponding to each candidate design scheme based on the basic engineering data to obtain an evaluation indicator weight vector; and performing multi-objective optimization decision processing based on the evaluation indicator weight vector and the evaluation indicator information to obtain the railway subgrade design scheme. This invention comprehensively improves the intelligence level and decision quality of railway subgrade design.

Description

Technical Field

[0001] This invention relates to the field of railway subgrade design, and more specifically, to a railway subgrade design method and apparatus based on a rule engine. Background Technology

[0002] Railway subgrade design, as a crucial link in railway engineering construction, directly impacts the safety, economy, and construction efficiency of the project. Traditional railway subgrade design primarily relies on engineers' experience, involving consulting design specifications and combining individual project practice to formulate and optimize solutions. This method has accumulated some technical expertise over time. However, as railway engineering evolves towards more complex geological conditions, higher environmental standards, and multi-objective collaborative optimization, existing technologies are gradually revealing several limitations: Firstly, manual design is inefficient, and the results are heavily influenced by individual engineer skill levels, making it difficult to ensure consistency and standardization. Secondly, subgrade design requires comprehensive consideration of multiple objectives, including safety, cost, construction convenience, and environmental impact. Traditional methods lack a systematic multi-objective decision-making mechanism, often relying solely on subjective trade-offs based on experience, making it difficult to achieve a globally optimal solution. Furthermore, existing methods lack dynamic adaptability to engineering scenarios. Evaluation index weights are typically fixed and cannot be flexibly adjusted according to specific engineering conditions. The lack of effective feedback and learning mechanisms prevents the digital accumulation and reuse of historical design experience, hindering the improvement of intelligent design capabilities. Summary of the Invention

[0003] The purpose of this invention is to provide a railway subgrade design method and apparatus based on a rule engine to improve the above-mentioned problems.

[0004] To achieve the above objectives, the embodiments of this application provide the following technical solutions:

[0005] On the one hand, embodiments of this application provide a railway subgrade design method based on a rule engine, the method comprising:

[0006] Obtain basic engineering data for the design cross-section of the railway subgrade, including slope height, soil type, cut and fill type, and groundwater depth;

[0007] The basic engineering data is processed by rule matching using a preset design rule library to obtain candidate design schemes;

[0008] Based on the candidate design schemes, multi-dimensional index calculations are performed to obtain the evaluation index information corresponding to each candidate design scheme.

[0009] Based on the basic engineering data, the evaluation index information corresponding to each candidate design scheme is processed by weight adaptive configuration to obtain the evaluation index weight vector.

[0010] Based on the evaluation index weight vector and the evaluation index information, a multi-objective optimization decision-making process is performed to obtain the railway subgrade design scheme.

[0011] Secondly, embodiments of this application provide a railway subgrade design device based on a rule engine, the device comprising:

[0012] The acquisition module is used to acquire basic engineering data of the railway subgrade design section, including slope height, soil type, cut and fill type, and groundwater depth.

[0013] The first processing module is used to perform rule matching processing on the basic engineering data using a preset design rule library to obtain candidate design schemes.

[0014] The second processing module is used to perform multi-dimensional index calculations based on the candidate design schemes to obtain the evaluation index information corresponding to each candidate design scheme.

[0015] The third processing module is used to perform weight adaptive configuration processing on the evaluation index information corresponding to each candidate design scheme based on the basic engineering data, so as to obtain the evaluation index weight vector.

[0016] The fourth processing module is used to perform multi-objective optimization decision processing based on the evaluation index weight vector and the evaluation index information to obtain the railway subgrade design scheme.

[0017] Thirdly, embodiments of this application provide a railway subgrade design device based on a rule engine, the device including a memory and a processor. The memory is used to store a computer program; the processor is used to execute the computer program to implement the steps of the above-described railway subgrade design method based on a rule engine.

[0018] Fourthly, embodiments of this application provide a readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described rule engine-based railway subgrade design method.

[0019] The beneficial effects of this invention are as follows:

[0020] This invention achieves automated design scheme generation by acquiring basic engineering data of railway subgrade design sections and using a pre-set design rule base for rule matching to generate candidate design schemes, effectively improving design efficiency and standardization. Through multi-dimensional index calculations and adaptive weight configuration based on basic engineering data, it can accurately quantify and dynamically adjust multiple objectives such as safety, cost, and construction convenience for specific engineering scenarios, thereby finding the optimal balance among multiple design objectives and significantly improving the rationality and economy of the scheme. Furthermore, the final scheme is obtained through multi-objective optimization decision processing, and the weight configuration is continuously optimized by combining a feedback learning mechanism, enabling the system to continuously learn from engineering practice, constantly accumulating and solidifying excellent design experience, thus comprehensively improving the intelligence level and decision-making quality of railway subgrade design.

[0021] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings. Attached Figure Description

[0022] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a schematic diagram of the railway subgrade design method based on a rule engine as described in an embodiment of the present invention.

[0024] Figure 2 This is a schematic diagram of the railway subgrade design equipment based on a rule engine as described in an embodiment of the present invention.

[0025] The diagram is labeled as follows: 800, Railway subgrade design equipment based on rule engine; 801, Processor; 802, Memory; 803, Multimedia component; 804, I / O interface; 805, Communication component. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present 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 the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0027] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0028] Example 1:

[0029] This embodiment provides a railway subgrade design method based on a rule engine. It can be understood that a scenario can be set up in this embodiment, such as a scenario that requires the design of high slope subgrade under complex geological conditions.

[0030] See Figure 1 The figure shows that the method includes steps S1-S5.

[0031] Step S1: Obtain the basic engineering data of the railway subgrade design section, including slope height, soil type, cut and fill type, and groundwater depth;

[0032] Step S2: Use a preset design rule library to perform rule matching processing on the basic engineering data to obtain candidate design schemes;

[0033] Step S2 further includes steps S21-S23, which specifically include:

[0034] Step S21: Perform rule base query processing based on the basic engineering data to obtain a set of rules that match the current project;

[0035] This step is the initialization phase of rule matching. Its core is to quickly filter all rules potentially related to the current input cross-sectional conditions from a pre-set design rule base, forming a preliminary set of candidate rules. Specifically, each rule in the rule base predefines its applicable key condition range, such as applicable to slope heights greater than 10 meters or applicable to soft soil types. The input basic engineering data, such as slope height, soil type, cut / fill type, and groundwater depth, are used as query conditions and quickly compared with the triggering conditions of each rule in the rule base. This process is not exact matching, but rather a coarse-screening based on an index, aiming to eliminate obviously inapplicable rules; for example, a rule for a high slope will not be triggered by a low slope cross-section. This is particularly important for handling knowledge bases containing a large number of rules, significantly improving the efficiency of subsequent exact matching and ensuring that, in complex and ever-changing engineering contexts, a targeted and controllable subset of rules can be quickly identified, laying the foundation for subsequent refined decision-making. It should be noted that the design rule base is based on engineering specifications. The rule base includes cross-section condition matching rules, engineering measure combination rules, and parameter adaptive adjustment rules. Each rule includes a rule identifier, rule name, triggering conditions, measure combination, and priority. The rule base supports complex condition matching logic, including: 1. Key indicator matching, such as slope height ranges of 0-8m, 8-15m, and above 15m; 2. Geological condition matching, such as soil, rock, and soft soil strata; 3. Special condition matching, such as proximity to existing lines and environmental sensitivity.

[0036] Step S22: Determine the valid rules that satisfy all triggering conditions based on the rule set;

[0037] After obtaining the initial rule set, this step involves a rigorous and logically sound precise matching judgment to identify valid rules that are fully adapted to the specific parameters of the current cross-section. The judgment process is based on complex conditional logic defined in the rules and typically includes multiple matching modes: for continuous variables such as slope height, range matching is performed to check if the input value falls within the interval specified by the rule; for discrete variables such as soil type and cut / fill type, enumeration matching is performed to check if the input value belongs to the category set specified by the rule; for parameters with specific requirements, such as groundwater depth, precise matching may be performed. A rule is only deemed valid when all its triggering conditions are met. This refined judgment mechanism ensures that every adopted rule strictly conforms to the actual constraints of the current engineering cross-section, avoiding the misuse of inapplicable rules in specific high-risk or complex situations such as proximity to existing lines or the presence of weak strata, thereby guaranteeing the technical rationality and safety of the generated scheme from the outset.

[0038] Step S23: Perform a combination of measures based on the effective rules to generate candidate design schemes.

[0039] The engineering measures corresponding to the multiple valid rules selected in the previous step are combined into a complete and executable roadbed design scheme according to predefined logic. Each valid rule usually includes not only triggering conditions but also specific engineering measures (such as setting up retaining walls, easing slopes, and constructing drainage ditches) and key parameter suggestions for these measures (such as slope ratio and height). By parsing these rules, the measures are sorted and combined according to certain engineering logic (such as supporting first and then draining, or based on priority) to form a structured list of measures. A specific structured list of measures is as follows: ["retaining wall", "slope", "platform", "drainage ditch"], parameters for each measure (slope height 8m, slope ratio 1:1.5), and measure description (e.g., when the rock slope height is 15-20m, a gravity retaining wall should be set up, and the retaining wall height should not exceed 6m). It should be noted that multiple candidate design schemes will be generated for each design section.

[0040] Step S3: Calculate multi-dimensional indicators based on the candidate design schemes to obtain the evaluation indicator information corresponding to each candidate design scheme;

[0041] Step S3 further includes steps S31-S33, which specifically include:

[0042] Step S31: Calculate the safety factor of the candidate design scheme based on the simplified Bishop method to obtain the safety index;

[0043] In this step, the specific formula for calculating the safety factor is as follows:

[0044]

[0045] In the above formula, Indicates cohesion; Indicates the length of the sliding surface; This represents the sum of the normal forces on the sliding surface; Indicates the angle of internal friction; Indicates soil weight; Indicates the slope height; This indicates the slope angle. It should be noted that when considering the influence of groundwater, the safety factor should be multiplied by the groundwater influence factor.

[0046] Step S32: Calculate the cost index based on the geometric parameters of the measures in the candidate design scheme to obtain the cost index;

[0047]

[0048] In the above formula, The value of C represents earthwork cost, derived from engineering quotas; C_structure represents the cost of structural measures, derived from engineering quotas. represents the comprehensive adjustment coefficient of construction conditions, and the specific calculation process is , where represents the height factor. When the slope height is 0 - 5m, it is 1.0; when it is 5 - 10m, it is 1.1; when it is 10 - 15m, it is 1.3; when it is greater than 15m, it is 1.5; represents the soil quality factor. For rock, it is 1.4; for ordinary soil, it is 1.0; for soft soil, it is 1.2; for loess, it is 1.1; represents the groundwater factor. When the water level depth is 0 - 1m, it is 1.4; when it is 1 - 3m, it is 1.2; when it is greater than 3m, it is 1.0.

[0049] Step S33: Calculate the construction difficulty of the candidate design solution to obtain the construction convenience index.

[0050] Take the slope height, formation factor, etc. as the construction convenience evaluation indexes, and calculate the construction difficulty coefficient. The height factor is classified according to the slope height. For 0 - 5m, it is 1.0; for 5 - 10m, it is 1.1; for 10 - 15m, it is 1.3; for more than 15m, it is 1.5. The formation factor: for rock, it is 1.4; for ordinary soil, it is 1.0; for soft soil, it is 1.2; for loess, it is 1.1. The groundwater factor: for a depth of 0 - 1m, it is 1.4; for 1 - 3m, it is 1.2; for more than 3m, it is 1.0.

[0051] Step S4: Perform weight adaptive configuration processing on the evaluation index information corresponding to each candidate design solution according to the basic engineering data to obtain the evaluation index weight vector;

[0052] In step S4, it also includes steps S41 - S44, which specifically include:

[0053] Step S41: Perform risk level division according to the basic engineering data to obtain the risk feature vector;

[0054] The goal of this step is to transform the original and continuous basic engineering data into discrete features that can represent the engineering risk level, providing a structured input for subsequent weight configuration. Specifically, according to the predefined classification rules, independent risk level judgments are made for each key parameter in the input section. For example, for the slope height, the rule is set as: H ≤ 2.5 meters is low risk, 2.5 meters < H ≤ 15 meters is medium risk, H > 15 meters is high risk. Similarly, for the soil type, it can be classified as stable (such as hard rock), general (such as clay), unstable (such as soft soil); for the groundwater depth, it can be classified as low risk (burial depth > 5 meters), medium risk (burial depth 2 - 5 meters), high risk (burial depth < 2 meters). Finally, these classification results (such as [medium risk, unstable, high risk]) are combined into a formal risk feature vector.

[0055] Step S42: Calculate the complexity level of the candidate design scheme based on the number of measures in the candidate design scheme, and obtain the complexity feature vector;

[0056] In this formula, the specific process for calculating the complexity level of candidate solutions is as follows:

[0057]

[0058] In the above formula, This represents the score for the i-th type of roadbed structure; This represents the number of roadbed structural measures of type i; The height bonus is represented by I_h, which is classified based on the slope height sharing. I_h can take the values ​​0 (low height), 0.3 (medium height), and 1 (high slope). Indicates additional points for soil quality; This represents the additional score for groundwater; it's understandable that the principles for determining the additional scores for soil quality and groundwater are the same as for slope height. It should be noted that the score tables for different types of roadbed structures are as follows:

[0059] Table 1. Scoring Table for Different Types of Subgrade Structures

[0060]

[0061] Step S43: Construct a context feature vector based on the risk feature vector and the complexity feature vector;

[0062] In this step, the risk feature vector and the complexity feature vector are concatenated to form a unified situation feature vector. This comprehensive situation feature vector uniquely defines the current engineering scenario.

[0063] Step S44: Configure the evaluation index weights of the candidate solutions according to the scenario feature vector to obtain the evaluation index weight vector.

[0064] This step is the core decision point for adaptive weight configuration. Its function is to map abstract situational features into specific indicator weight values ​​that can be used for multi-objective decision-making. The implementation mechanism relies on a pre-built situation-weight mapping rule base. This rule base defines the weight preferences of various evaluation indicators (safety, cost, construction convenience, etc.) under different situations. The situational feature vector is taken as input and matched with the conditions in this rule base. For example, the rule base may contain a rule: "IF soil risk is 'unstable' AND groundwater risk is 'high risk' THEN safety weight increased to 0.7, cost weight decreased to 0.2". After a successful match, an evaluation indicator weight vector can be output, such as [safety: 0.7, cost: 0.2, construction convenience: 0.1]. This method gets rid of the rigid mode of fixed weight ratios and can dynamically adjust the decision focus. In high-risk conditions with poor geological conditions, the system will automatically place safety as the highest priority; while in conditions with good geological conditions and simple solutions, it may prefer the most economical solution. This greatly enhances the adaptability to complex and ever-changing engineering practices, making the design recommendations more targeted and engineering-appropriate.

[0065] Step S5: Perform multi-objective optimization decision processing based on the evaluation index weight vector and the evaluation index information to obtain the railway subgrade design scheme.

[0066] Step S5 further includes steps S51-S54, which specifically include:

[0067] Step S51: Standardize the evaluation index information to obtain a standardized evaluation index matrix;

[0068] The standardization process in this step is specifically a normalization process, which aims to eliminate the incomparability between different evaluation indicators (such as safety, cost, and ease of construction) due to differences in dimensions and magnitudes.

[0069] Step S52: Based on the standardized evaluation index matrix and the evaluation index weight vector, a weighted decision matrix is ​​constructed to obtain a weighted scheme evaluation matrix;

[0070] In this step, each index value in the standardized matrix is ​​multiplied by its corresponding weight to assign the evaluation index weight vector, which reflects the current focus of the project, to the standardized index data.

[0071] Step S53: Perform ideal solution distance calculation based on the weighted scheme evaluation matrix to obtain the relative closeness of the schemes;

[0072] In this step, the maximum and minimum values ​​of each indicator are found from the weighted matrix, forming a positive ideal solution (all indicators take their best values) and a negative ideal solution (all indicators take their worst values), respectively. Then, the Euclidean distance formula is used to calculate the distance from each candidate solution to the positive ideal solution (D). + ) and to the negative ideal solution (D - The distance is calculated. Finally, the relative proximity C=D for each solution is calculated. - / (D + +D - The larger the C value (ranging from 0 to 1), the closer the solution is to the ideal solution, and the further it is from the worst solution.

[0073] Step S54: Sort the schemes according to the relative proximity to obtain the railway subgrade design scheme.

[0074] Following step S5, steps S6-S9 are further included, specifically including:

[0075] Step S6: Perform preference learning processing based on the feedback of the railway subgrade design scheme to obtain the updated index weights;

[0076] In this step, after an engineer reviews the optimal solution recommended by the system, their decision-making behavior is considered a preference feedback. By capturing this decision-making behavior and triggering a learning algorithm, specifically, the evaluation index weight corresponding to the engineer's final adopted solution is used as the baseline weight. Simultaneously, the engineer is made aware of their implicit preference vector in this decision. For example, in this specific design, if the engineer actually values ​​cost control more, then the cost weight preference will be higher. The learning algorithm uses incremental updates, specifically: New weight = Baseline weight + α × (Preference vector - Baseline weight), where α is a learning rate (e.g., 0.1) used to control the adjustment magnitude of each learning iteration. The effect of this mechanism is that it continuously and quantitatively accumulates the engineer's individual, implicit, and project-specific valuable experience into the system's weight configuration logic, enabling the system to gradually approach the true decision-making preferences of enterprises or experts.

[0077] Step S7: Perform historical data management processing based on the updated indicator weights to obtain a complete history of weight changes;

[0078] This step ensures the traceability and stability of the learning process by constructing a complete weight evolution archive. In implementation, a weight change log database is first established. Each weight update creates a new record in this database. This record not only contains the weight values ​​before and after the update but also must store key contextual information, including the engineering context feature vector that triggered the update, the corresponding timestamp, the identity of the engineer providing feedback, the learning rate α used, and the confidence level of the adjustment (which can be set based on the clarity of the feedback). This approach enriches an isolated weight adjustment event into a complete learning case with cause and effect. This step allows any weight change to be queried, audited, and analyzed, providing a solid data foundation for subsequent learning performance evaluation and anomaly rollback, preventing the system from forgetting or learning biases due to a few abnormal feedbacks.

[0079] Step S8: Based on the weight change history, perform learning effect evaluation processing, smooth weight fluctuations and evaluate the stability of weight configuration through the exponential moving average algorithm, and obtain optimized stable weight values.

[0080] This step aims to address the inherent noise and fluctuations in the learning process, extracting stable and reliable long-term trends. This is achieved through an exponential moving average algorithm, which assigns higher weights to recent records while the weights of older records decay exponentially. The specific formula is: Final Weight [i] = b × New Weight + (1-b) × Historical Weight, where b is a smoothing coefficient. This process weakens the impact of single, accidental, and potentially unrepresentative weight adjustments on the final stable weights, while strengthening and highlighting recurring weight adjustment trends across a series of similar engineering scenarios.

[0081] Step S9: Based on the optimized stable weight values ​​and the corresponding context feature vectors, perform knowledge base update processing by establishing a new context-weight mapping relationship and updating it to the weight adjustment rule base.

[0082] The final weight values ​​of the feature vectors for a specific context obtained from the above steps are used to construct a new context-weight mapping rule. When a new design task arises and its context features match this rule, the system will directly apply this weight configuration, which has been verified and optimized through historical practice.

[0083] Example 2:

[0084] This embodiment provides a railway subgrade design device based on a rule engine. The device includes an acquisition module, a first processing module, a second processing module, a third processing module, and a fourth processing module, specifically including:

[0085] The acquisition module is used to acquire basic engineering data of the railway subgrade design section, including slope height, soil type, cut and fill type, and groundwater depth.

[0086] The first processing module is used to perform rule matching processing on the basic engineering data using a preset design rule library to obtain candidate design schemes.

[0087] The second processing module is used to perform multi-dimensional index calculations based on the candidate design schemes to obtain the evaluation index information corresponding to each candidate design scheme.

[0088] The third processing module is used to perform weight adaptive configuration processing on the evaluation index information corresponding to each candidate design scheme based on the basic engineering data, so as to obtain the evaluation index weight vector.

[0089] The fourth processing module is used to perform multi-objective optimization decision processing based on the evaluation index weight vector and the evaluation index information to obtain the railway subgrade design scheme.

[0090] In one specific embodiment of this disclosure, the first processing module further includes a first processing unit, a second processing unit, and a third processing unit, specifically including:

[0091] The first processing unit is used to perform rule base query processing based on the basic engineering data to obtain a set of rules that match the current project.

[0092] The second processing unit is used to determine, based on the rule set, the valid rules that satisfy all triggering conditions;

[0093] The third processing unit is used to perform measure combination generation processing according to the effective rules to obtain candidate design schemes.

[0094] In one specific embodiment of this disclosure, the second processing module further includes a fourth processing unit, a fifth processing unit, and a sixth processing unit, specifically including:

[0095] The fourth processing unit is used to calculate the safety factor of the candidate design scheme based on the simplified Bishop method, and obtain the safety index.

[0096] The fifth processing unit is used to calculate the cost index based on the geometric parameters of the measures in the candidate design scheme, and obtain the cost index.

[0097] The sixth processing unit is used to calculate the construction difficulty of the candidate design scheme and obtain the construction convenience index.

[0098] In one specific embodiment of this disclosure, the third processing module further includes a seventh processing unit, an eighth processing unit, a ninth processing unit, and a tenth processing unit, specifically comprising:

[0099] The seventh processing unit is used to classify risk levels based on the basic engineering data and obtain risk feature vectors;

[0100] The eighth processing unit is used to calculate the complexity level of the candidate scheme based on the number of measures of the candidate design scheme, and obtain the complexity feature vector;

[0101] The ninth processing unit is used to construct a context feature vector based on the risk feature vector and the complexity feature vector;

[0102] The tenth processing unit is used to configure the evaluation index weights of the candidate schemes according to the context feature vector, and obtain the evaluation index weight vector.

[0103] In one specific embodiment of this disclosure, the fourth processing module further includes an eleventh processing unit, a twelfth processing unit, a thirteenth processing unit, and a fourteenth processing unit, specifically including:

[0104] The eleventh processing unit is used to standardize the evaluation index information to obtain a standardized evaluation index matrix.

[0105] The twelfth processing unit is used to construct a weighted decision matrix based on the standardized evaluation index matrix and the evaluation index weight vector to obtain a weighted scheme evaluation matrix.

[0106] The thirteenth processing unit is used to perform ideal solution distance calculation processing based on the weighted scheme evaluation matrix to obtain the relative closeness of the schemes;

[0107] The fourteenth processing unit is used to sort the schemes according to the relative proximity to obtain the railway subgrade design scheme.

[0108] In one specific embodiment of this disclosure, the fourth processing module is followed by a fifth processing module, a sixth processing module, a seventh processing module, and an eighth processing module, specifically including:

[0109] The fifth processing module is used to perform preference learning processing based on the feedback of the railway subgrade design scheme to obtain updated index weights;

[0110] The sixth processing module is used to perform historical data management processing based on the updated indicator weights to obtain a complete history of weight changes.

[0111] The seventh processing module is used to evaluate the learning effect based on the weight change history, smooth weight fluctuations and evaluate the stability of weight configuration through the exponential moving average algorithm, and obtain the optimized stable weight value.

[0112] The eighth processing module is used to update the knowledge base based on the optimized stable weight values ​​and the corresponding context feature vectors, by establishing a new context-weight mapping relationship and updating it to the weight adjustment rule base.

[0113] It should be noted that the specific manner in which each module performs its operation in the apparatus described in the above embodiments has been described in detail in the embodiments of the method, and will not be elaborated here.

[0114] Example 3:

[0115] Corresponding to the above method embodiments, this embodiment also provides a railway subgrade design device based on a rule engine. The railway subgrade design device based on a rule engine described below and the railway subgrade design method based on a rule engine described above can be referred to in correspondence.

[0116] Figure 2 This is a block diagram illustrating a rule engine-based railway subgrade design device 800 according to an exemplary embodiment. Figure 2 As shown, the rule engine-based railway subgrade design device 800 may include a processor 801 and a memory 802. The rule engine-based railway subgrade design device 800 may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0117] The processor 801 controls the overall operation of the rule engine-based railway subgrade design device 800 to complete all or part of the steps in the rule engine-based railway subgrade design method described above. The memory 802 stores various types of data to support the operation of the rule engine-based railway subgrade design device 800. This data may include, for example, instructions for any application or method operating on the rule engine-based railway subgrade design device 800, and application-related data such as contact data, sent and received messages, images, audio, video, etc. The memory 802 can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or transmitted via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. I / O interface 804 provides an interface between processor 801 and other interface modules, such as keyboards, mice, and buttons. These buttons can be virtual or physical. Communication component 805 is used for wired or wireless communication between the rule engine-based railway subgrade design device 800 and other devices. Wireless communication includes Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof. Therefore, the corresponding communication component 805 may include a Wi-Fi module, a Bluetooth module, and an NFC module.

[0118] In an exemplary embodiment, the rule engine-based railway subgrade design device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute the rule engine-based railway subgrade design method described above.

[0119] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the rule-engine-based railway subgrade design method described above. For example, the computer-readable storage medium may be the memory 802 including the program instructions described above, which may be executed by the processor 801 of the rule-engine-based railway subgrade design device 800 to complete the rule-engine-based railway subgrade design method described above.

[0120] Example 4:

[0121] Corresponding to the above method embodiments, this embodiment also provides a readable storage medium. The readable storage medium described below can be referred to in conjunction with the rule engine-based railway subgrade design method described above.

[0122] A readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the rule engine-based railway subgrade design method described in the above method embodiments.

[0123] Specifically, the readable storage medium can be a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or any other readable storage medium capable of storing program code.

[0124] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0125] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A railway subgrade design method based on a rule engine, characterized in that, include: Obtain basic engineering data for the design cross-section of the railway subgrade, including slope height, soil type, cut and fill type, and groundwater depth; The basic engineering data is processed by rule matching using a preset design rule library to obtain candidate design schemes; Based on the candidate design schemes, multi-dimensional index calculations are performed to obtain the evaluation index information corresponding to each candidate design scheme. Based on the basic engineering data, the evaluation index information corresponding to each candidate design scheme is processed by weight adaptive configuration to obtain the evaluation index weight vector. Based on the evaluation index weight vector and the evaluation index information, a multi-objective optimization decision-making process is performed to obtain the railway subgrade design scheme.

2. The railway subgrade design method based on a rule engine according to claim 1, characterized in that, The basic engineering data is processed by rule matching using a preset design rule base, including: Based on the basic engineering data, a rule base query is performed to obtain a set of rules that match the current project. Based on the set of rules, a valid rule that satisfies all triggering conditions is obtained; Based on the effective rules, measures are combined and processed to generate candidate design schemes.

3. The railway subgrade design method based on a rule engine according to claim 1, characterized in that, Multi-dimensional index calculations are performed based on the candidate design schemes, including: The safety factor of the candidate design scheme is calculated based on the simplified Bishop method, and the safety index is obtained. Cost indicators are calculated based on the geometric parameters of the measures in the candidate design schemes. The construction difficulty of the candidate design scheme is calculated to obtain the construction convenience index.

4. The railway subgrade design method based on a rule engine according to claim 1, characterized in that, Based on the aforementioned basic engineering data, the evaluation index information corresponding to each candidate design scheme is subjected to weight adaptive configuration processing, including: Based on the aforementioned basic engineering data, risk levels are classified to obtain risk feature vectors; The complexity level of the candidate design scheme is calculated based on the number of measures in the candidate design scheme, and a complexity feature vector is obtained. Construct a context feature vector based on the risk feature vector and the complexity feature vector; The evaluation index weights of the candidate solutions are configured according to the context feature vector to obtain the evaluation index weight vector.

5. The railway subgrade design method based on a rule engine according to claim 1, characterized in that, Multi-objective optimization decision processing is performed based on the evaluation index weight vector and the evaluation index information, including: The evaluation index information is standardized to obtain a standardized evaluation index matrix; The weighted decision matrix is ​​constructed based on the standardized evaluation index matrix and the evaluation index weight vector to obtain the weighted scheme evaluation matrix. The ideal solution distance is calculated based on the weighted scheme evaluation matrix to obtain the relative closeness of the schemes; The railway subgrade design scheme is obtained by sorting the schemes according to their relative proximity.

6. A railway subgrade design device based on a rule engine, characterized in that, include: The acquisition module is used to acquire basic engineering data of the railway subgrade design section, including slope height, soil type, cut and fill type, and groundwater depth. The first processing module is used to perform rule matching processing on the basic engineering data using a preset design rule library to obtain candidate design schemes. The second processing module is used to perform multi-dimensional index calculations based on the candidate design schemes to obtain the evaluation index information corresponding to each candidate design scheme. The third processing module is used to perform weight adaptive configuration processing on the evaluation index information corresponding to each candidate design scheme based on the basic engineering data, so as to obtain the evaluation index weight vector. The fourth processing module is used to perform multi-objective optimization decision processing based on the evaluation index weight vector and the evaluation index information to obtain the railway subgrade design scheme.

7. The railway subgrade design device based on a rule engine according to claim 6, characterized in that, The first processing module includes: The first processing unit is used to perform rule base query processing based on the basic engineering data to obtain a set of rules that match the current project. The second processing unit is used to determine, based on the rule set, the valid rules that satisfy all triggering conditions; The third processing unit is used to perform measure combination generation processing according to the effective rules to obtain candidate design schemes.

8. The railway subgrade design device based on a rule engine according to claim 6, characterized in that, The second processing module includes: The fourth processing unit is used to calculate the safety factor of the candidate design scheme based on the simplified Bishop method, and obtain the safety index. The fifth processing unit is used to calculate the cost index based on the geometric parameters of the measures in the candidate design scheme, and obtain the cost index. The sixth processing unit is used to calculate the construction difficulty of the candidate design scheme and obtain the construction convenience index.

9. The railway subgrade design device based on a rule engine according to claim 6, characterized in that, The third processing module includes: The seventh processing unit is used to classify risk levels based on the basic engineering data and obtain risk feature vectors; The eighth processing unit is used to calculate the complexity level of the candidate scheme based on the number of measures of the candidate design scheme, and obtain the complexity feature vector; The ninth processing unit is used to construct a context feature vector based on the risk feature vector and the complexity feature vector; The tenth processing unit is used to configure the evaluation index weights of the candidate schemes according to the context feature vector, and obtain the evaluation index weight vector.

10. The railway subgrade design device based on a rule engine according to claim 6, characterized in that, The fourth processing module includes: The eleventh processing unit is used to standardize the evaluation index information to obtain a standardized evaluation index matrix. The twelfth processing unit is used to construct a weighted decision matrix based on the standardized evaluation index matrix and the evaluation index weight vector to obtain a weighted scheme evaluation matrix. The thirteenth processing unit is used to perform ideal solution distance calculation processing based on the weighted scheme evaluation matrix to obtain the relative closeness of the schemes; The fourteenth processing unit is used to sort the schemes according to the relative proximity to obtain the railway subgrade design scheme.

Images