Motor type selection method and system

Abstract

The invention relates to the technical field of motor model selection, in particular to a motor model selection method and system, and the method comprises the steps: constructing a distributed data query library, and importing a standardized feature vector into the distributed data query library to obtain a candidate motor model set through matching; obtaining the comprehensive performance score of each candidate motor model, triggering a model rejection mechanism based on a preset score threshold value, and carrying out performance parameter sorting on the reserved candidate motor models to generate a preferred motor model set; obtaining a comprehensive energy efficiency score of each preferred motor model, and establishing a Pareto frontier solution set for secondary screening to obtain a recommended motor model set; the recommended motor model is divided into a plurality of motor model selection hierarchies, the motor model selection hierarchies serve as the final motor model selection result to be output, the scientificity, accuracy and practicability of motor model selection are improved through the intelligent motor model selection process, and high-quality model selection decision support is provided for a user.

Description

Technical Field

[0001] The present invention relates to the technical field of motor selection, and in particular to a motor selection method and system. Background Art

[0002] In modern logistics and warehousing systems, the selection of linear RGV motors and motors for heavy-duty stackers is a critical technical step in ensuring efficient system operation. With the logistics industry's increasing demand for automation and intelligence, traditional motor selection methods are no longer able to meet performance requirements under complex operating conditions. As the core drive unit of rail-mounted transportation equipment, linear RGV motors require key considerations for acceleration, positioning accuracy, load adaptability, and energy efficiency. Heavy-duty stacker motors, on the other hand, must meet even higher standards in terms of load capacity, operational stability, impact resistance, and long-term reliability. However, existing motor selection methods often rely on empirical formulas or single performance indicators, lacking the ability to collaboratively optimize multi-dimensional parameters. This often results in selection results that fail to fully meet actual needs. Traditional methods struggle to dynamically adjust weight distribution, especially when faced with diverse operating conditions, and are unable to accurately match performance priorities across different scenarios. Furthermore, existing technologies fail to adequately consider the full lifecycle costs of motors and lack the ability to predict energy efficiency degradation trends, potentially leading to excessively high operational and maintenance costs. In terms of data processing, traditional methods often use a centralized query model, which is difficult to quickly match massive amounts of motor model data and lacks the ability to adaptively correct abnormal data. At the decision support level, existing technologies typically output a single recommendation result, without establishing a hierarchical set of selection options, and unable to provide users with multi-dimensional decision-making references. Therefore, a motor selection method that can integrate multi-source data, support dynamic optimization, and provide hierarchical decision-making is urgently needed to improve the scientificity, accuracy, and practicality of linear RGV motor and heavy-duty stacker motor selection. Summary of the Invention

[0003] The present invention overcomes the deficiencies of the prior art and provides a motor selection method and system.

[0004] In order to achieve the above-mentioned purpose, the technical solution adopted by the present invention is: A first aspect of the present invention discloses a method for selecting a motor, comprising the following steps: Obtaining the selection benchmark parameters input by the user, and converting the selection benchmark parameters into a benchmark measurement system to obtain a standardized feature vector; Building a distributed data query library, importing the standardized feature vector into the distributed data query library to match a set of candidate motor models; Obtain the comprehensive performance score of each candidate motor model, trigger the model elimination mechanism based on the preset score value threshold, and sort the performance parameters of the retained candidate motor models to generate a set of preferred motor models; Obtain the comprehensive energy efficiency score of each preferred motor model and establish a Pareto front solution set for secondary screening to obtain a set of recommended motor models; The recommended motor models are divided into a plurality of motor selection levels, and the motor selection levels are output as final motor selection results.

[0005] Preferably, the selection benchmark parameters are converted into a benchmark measurement system to obtain a standardized feature vector, specifically: Extract the values ​​and unit identifiers of each input selection benchmark parameter and dynamically build a parameter-unit mapping table; Identify the unit identifier of each parameter in the mapping table. If the unit is English or non-standard metric, convert the corresponding selection reference parameter into an equivalent value under the reference unit. For the converted selection benchmark parameters, interval mapping is performed on each parameter according to the preset motor performance parameter threshold range; The normalized numerical parameters and the encoded discrete parameters are concatenated according to the weight priority through the feature fusion layer to form a multi-dimensional standardized feature vector. The order of the vector dimensions is dynamically adjusted according to the ranking of the key influencing factors in the motor selection decision tree. The integrity of the standardized feature vector is checked, and the missing parameters are supplemented by adjacent working condition interpolation or historical data fitting, and a standardized feature vector set that meets the input requirements of the motor performance matching model is output.

[0006] Preferably, a distributed data query library is constructed, and the standardized feature vector is imported into the distributed data query library to match a set of candidate motor models, specifically: Obtain the benchmark parameter data stream of each manufacturer's motor, convert the benchmark parameter data stream of each manufacturer's motor into standardized parameters with unified dimensions through a preset motor industry standard terminology mapping table, and construct a standardized parameter table; Matrixing the standardized parameter table to form a multidimensional feature matrix, wherein each row of the matrix represents a motor model and each column corresponds to a standardized parameter feature; constructing a data query library, and importing the multidimensional feature matrix into the data query library to obtain a distributed data query library; Expanding the dimension of the standardized feature vector to make it consistent with the column dimension of the multidimensional feature matrix to form a query vector matrix; Compare the query vector with each row in the feature matrix row by row, and calculate the Euclidean distance between the two in each feature dimension; if the Euclidean distance of a row is less than the preset distance threshold, mark the motor model in the corresponding row as a candidate model; Prioritize the marked candidate model set and arrange them from small to large according to the Euclidean distance to generate the final candidate motor model set; During the entire process, if the candidate motor model set is empty, the preset distance threshold is automatically adjusted or the user is prompted to re-enter the selection benchmark parameters.

[0007] Preferably, the comprehensive performance score of each candidate motor model is obtained, and a model elimination mechanism is triggered based on a preset score value threshold. The retained candidate motor models are sorted by performance parameters to generate a set of preferred motor models, specifically: Extract key performance parameters of each model from the candidate motor model set, including rated power curves, efficiency distribution maps, and temperature rise characteristic data, and construct a three-dimensional performance matrix as a benchmark data source for multi-dimensional parameter comparison; Automatically allocate torque response coefficient, energy efficiency priority factor, and environmental adaptation weight based on the application scenario characteristics input by the user to form a dynamic weight allocation rule. If the scenario characteristics are not clear, the default weight allocation mode is enabled and logged. Based on dynamic weighting rules, each parameter in the three-dimensional performance matrix is ​​weighted and calculated to generate a comprehensive performance score for each candidate motor model; the comprehensive performance score of each candidate motor model is compared with a preset score threshold; If the comprehensive performance score of a candidate motor model is less than the preset score threshold, the model elimination mechanism is triggered to eliminate the candidate motor model from the candidate motor model set; Sort the retained candidate models by their comprehensive performance scores from highest to lowest to generate a set of preferred motor models; Among them, if the score values ​​are the same, a secondary sorting is performed according to the energy efficiency priority factor to ensure the uniqueness of the sorting result, and the preferred sequence is used as the input data for the load characteristic matching verification in the next stage.

[0008] Preferably, the comprehensive energy efficiency score of each preferred motor model is obtained and a Pareto front solution set is established for secondary screening to obtain a set of recommended motor models, specifically: Acquire rated operating condition data of each preferred motor model, and extract efficiency distribution characteristics of each preferred motor model at different load points based on the rated operating condition data; Based on the energy efficiency priority parameters entered by the user, the efficiency weight coefficient is dynamically assigned. Combined with the efficiency distribution characteristics of each preferred motor model at different load points, the comprehensive energy efficiency score of each preferred motor model is calculated. If the comprehensive energy efficiency score of a preferred motor model falls below the preset score threshold, the model downgrade mechanism is triggered and the model is removed from the preferred queue. A multi-objective particle swarm optimization algorithm is used to establish the Pareto frontier solution set for each preferred motor model, with comprehensive energy efficiency score, power density, and temperature rise characteristics as optimization targets. If the number of Pareto frontier solution sets exceeds the preset upper limit, a fuzzy comprehensive evaluation method is introduced to perform a secondary screening of the solution set until the number of Pareto frontier solution sets falls below the preset upper limit. Subsequently, the embedded simulation engine is called to perform a virtual working condition loading test on each preferred motor model according to the Pareto front solution set of each preferred motor model to obtain the simulated energy efficiency degradation curve of each preferred motor model; Comparing the simulated energy efficiency attenuation curve of each preferred motor model with the preset energy efficiency attenuation curve to obtain the degree of overlap between the simulated energy efficiency attenuation curve of each preferred motor model and the preset energy efficiency attenuation curve; If the overlap between the simulated energy efficiency attenuation curve of a preferred motor model and the preset energy efficiency attenuation curve is no greater than the preset overlap, the model downgrade mechanism is triggered and the model is removed from the preferred queue; The remaining preferred motor models in the preferred motor model set are obtained to obtain a recommended motor model set.

[0009] Preferably, a multi-objective particle swarm optimization algorithm is used to establish the Pareto frontier solution set of each preferred motor model with comprehensive energy efficiency score, power density and temperature rise characteristics as optimization targets, specifically: Initialize the particle swarm, use the comprehensive energy efficiency score, power density, and temperature rise characteristics of each preferred motor model as the three-dimensional target vector of the particle, and randomly assign the initial position and speed; Calculate the fitness value of each particle and construct the initial Pareto solution set; if the number of solution sets is zero, adjust the target weight coefficient and recalculate the fitness value; Execute the particle position update algorithm to dynamically adjust the particle trajectory based on the individual optimal solution and the global optimal solution; if it is detected that the particle is trapped in the local optimum, a mutation operation is introduced to randomly perturb the particle position to jump out of the local extreme value; The updated particles are classified using the non-dominated sorting method to screen out new Pareto solution sets. If the number of solution sets exceeds the preset upper limit, the congestion calculation is started to prioritize the evenly distributed solutions. At the same time, a solution set convergence judgment mechanism is established. If the number of consecutive iterations exceeds the threshold and the solution set change rate is lower than the preset value, the algorithm is judged to have converged; if it has not converged, iterative optimization will continue; Finally, the final Pareto front solution set is output, and the motor model and key parameters corresponding to each solution are marked.

[0010] Preferably, if the number of Pareto front solution sets exceeds a preset upper limit, a fuzzy comprehensive evaluation method is introduced to perform a secondary screening of the solution set until the number of Pareto front solution sets is lower than the preset upper limit, specifically: Extract the comprehensive energy efficiency score, power density and temperature rise characteristic data of each motor model from the Pareto front solution set and construct a multi-dimensional evaluation matrix; Dynamically assign weight coefficients to each evaluation indicator based on the energy efficiency priority parameters input by the user; A fuzzy membership function is established to normalize each evaluation index and eliminate dimensional differences. If uneven distribution of normalized data is detected, the membership function parameters are adjusted. The weighted average method is used to calculate the comprehensive fuzzy evaluation value of each motor model, and the solution set is sorted according to the comprehensive fuzzy evaluation value; Set the upper threshold of the number of solutions, and eliminate the motor models with the lowest comprehensive fuzzy evaluation values ​​in sequence until the number of motor models after elimination is less than the upper threshold of the number of solutions; if the number of solutions after elimination still exceeds the upper threshold, gradually increase the elimination standard until the number requirement is met; Finally, the filtered Pareto front solution set is output, and the comprehensive fuzzy evaluation value and key parameters of each model are marked.

[0011] Preferably, the recommended motor models are divided into multiple motor selection levels, specifically: Extract the comprehensive energy efficiency scores, cost-effectiveness indexes, and compatibility parameters of all models in the recommended motor model set and construct a three-dimensional classification feature matrix; Based on the core performance threshold set by the user, a set of models with comprehensive energy efficiency scores higher than the benchmark value and compatibility that meets the standard are screened and marked as the primary recommended candidate set. If the candidate set is empty, the threshold range is automatically relaxed and the adjustment parameters are recorded. Perform an economic analysis on the remaining models, calculate the full life cycle cost-benefit ratio, and select models with a cost-benefit ratio below the industry average and compatibility parameters within the allowable range. These models are classified as economic alternatives. If missing cost data is detected, the historical procurement database is used to fill in the alternative values. For models that are not selected as the primary recommended models and economic alternative models above, extended compatibility verification will be carried out, and the models that pass the extended compatibility verification will be regarded as extended compatible models.

[0012] The selection benchmark parameters include full load gross weight, full load speed, full load acceleration, travel wheel / drum diameter, energy efficiency level requirements, three-dimensional size restrictions of installation space, energy efficiency priority parameters, ambient temperature and humidity gradient parameters, protection level code, expected life index and application scenario characteristics.

[0013] A second aspect of the present invention discloses a motor selection system, which includes a memory and a processor. The memory stores a motor selection method program. When the motor selection method program is executed by the processor, the steps of any one of the motor selection methods are implemented.

[0014] The present invention solves the technical defects existing in the background technology, and has the following beneficial effects: obtaining the selection benchmark parameters input by the user, and converting the selection benchmark parameters into a benchmark measurement system to obtain a standardized feature vector; constructing a distributed data query library, importing the standardized feature vector into the distributed data query library to match a set of candidate motor models; obtaining the comprehensive performance score of each candidate motor model, triggering a model elimination mechanism based on a preset score value threshold, sorting the performance parameters of the retained candidate motor models to generate a set of preferred motor models; obtaining the comprehensive energy efficiency score of each preferred motor model and establishing a Pareto front solution set for secondary screening to obtain a set of recommended motor models; dividing the recommended motor models into multiple motor selection levels, and outputting the motor selection levels as the final motor selection results. The present invention improves the scientificity, accuracy and practicality of motor selection through an intelligent motor selection process, and provides users with high-quality selection decision support. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, without paying any creative work, they can also obtain drawings of other embodiments based on these drawings.

[0016] Figure 1 The figure is a flow chart of the overall method for selecting a motor; Figure 2 This is a partial flow chart of a motor selection method; Figure 3 This is a system block diagram of a motor selection system; Figure 4 This is a schematic diagram of an example of a comparison of motor energy efficiency attenuation curves; Figure 5 is the trajectory diagram of a single particle; Figure 6 Particle swarm distribution and Pareto front diagram. DETAILED DESCRIPTION

[0017] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0018] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0019] like Figure 1 As shown, the first aspect of the present invention discloses a motor selection method, comprising the following steps: S102, obtaining selection benchmark parameters input by the user, and converting the selection benchmark parameters into a benchmark measurement system to obtain a standardized feature vector; S104, building a distributed data query library, importing the standardized feature vector into the distributed data query library to match a set of candidate motor models; S106, obtaining a comprehensive performance score for each candidate motor model, triggering a model elimination mechanism based on a preset score threshold, and sorting the retained candidate motor models by performance parameters to generate a set of preferred motor models; S108, obtaining the comprehensive energy efficiency score of each preferred motor model and establishing a Pareto front solution set for secondary screening to obtain a set of recommended motor models; S110 , dividing the recommended motor models into multiple motor selection levels, and outputting the motor selection levels as final motor selection results.

[0020] It should be noted that by converting the user-entered selection benchmark parameters into a benchmark measurement system and generating standardized feature vectors, data consistency and comparability are ensured, providing a scientific data foundation for subsequent matching and screening. Constructing a distributed data query library and importing standardized feature vectors for matching improves data processing efficiency and query speed, ensuring the comprehensiveness and accuracy of the candidate motor model set. Next, a model elimination mechanism is triggered based on the comprehensive performance score, and the retained candidate models are ranked by performance parameters to ensure the high quality and adaptability of the preferred motor model set. The selection results are then further optimized through the calculation of comprehensive energy efficiency scores and the construction of Pareto front solutions, ensuring the comprehensiveness and optimality of the solution set. If the number of solution sets exceeds a preset upper limit, a secondary screening mechanism is introduced to improve the accuracy of the selection results. Finally, the recommended motor models are divided into multiple selection levels, providing users with hierarchical, multi-dimensional selection decision support, ensuring the practicality and flexibility of the selection results. In summary, the present invention can effectively improve the accuracy and efficiency of motor selection, providing reliable technical support for motor selection decisions.

[0021] Preferably, the selection reference parameters are converted into a reference measurement system to obtain a standardized feature vector, such as Figure 2 As shown, specifically: S202, extracting the numerical value and unit identifier of each input selection reference parameter, and dynamically constructing a parameter-unit mapping table; S204, identifying the unit identifier of each parameter in the mapping table, and if the unit is English or non-standard metric, converting the corresponding selection reference parameter into an equivalent value under the reference unit; It should be noted that the unit identifier for each parameter in the parameter-unit mapping table (such as "mph" for speed or "inches" for length) is first dynamically parsed. If an imperial unit (such as mph or inches) or a non-standard metric unit (such as the non-ISO standard "kgf") is identified, a preset unit conversion rule library (such as 1 mph = 0.44704 m / s, 1 inch = 25.4 mm) is used to convert the base unit. If the unit is missing (such as the user did not enter the speed unit), a default unit is matched based on the parameter type (such as "m / s" for speed). After conversion, the equivalent value is updated to the mapping table, and the original unit and conversion log are recorded to ensure data traceability. For example, if "6 inches" is converted to 152.4 mm, the "inches → mm" conversion record is retained. Among them, the preset unit conversion rule library is a pre-established database that stores the conversion relationship between various units and base units. It contains conversion coefficients for imperial, metric and other industry-specific units. It is used to uniformly convert parameters of different unit systems into standard base units (such as length is unified into millimeters, speed is unified into meters / second) to ensure data consistency and comparability.

[0022] S206 , performing interval mapping on each parameter based on the converted selection reference parameters according to a preset motor performance parameter threshold range; S208. The normalized numerical parameters and the encoded discrete parameters are concatenated according to weight priority through a feature fusion layer to form a multi-dimensional standardized feature vector. The order of the vector dimensions is dynamically adjusted according to the ranking of key influencing factors in the motor selection decision tree. It should be noted that based on the key influencing factors of the motor selection decision tree, each normalized numerical parameter and encoded discrete parameter is assigned a weight. The weight is determined by the parameter's influence on the selection result. The parameters are then sorted from highest to lowest weight, with parameters with higher weights placed at the front of the feature vector and parameters with lower weights placed at the back. If weights are tied, a secondary sorting is performed based on the parameter's data type (continuous parameters take precedence over discrete parameters). The sorted parameters are then concatenated sequentially into a multidimensional standardized feature vector, ensuring that the order of the vector dimensions aligns with the key influencing factors of the motor selection decision tree.

[0023] S210 , performing integrity check on the standardized feature vectors, completing missing parameters by adjacent operating condition interpolation or historical data fitting, and outputting a standardized feature vector set that meets the input requirements of the motor performance matching model.

[0024] In a preferred embodiment of the present invention, in the motor selection scenario for logistics and warehousing AGVs, user-entered benchmark parameters include full-load gross weight (1200 kg, with "kg" as the default if units are missing), full-load speed (2.5 mph, Imperial units), wheel diameter (6 inches), energy efficiency rating (IE3), and installation space restrictions (length × width × height = 400 × 300 × 200 mm). The data parsing module extracts the parameter values ​​and unit identifiers and dynamically constructs a parameter-unit mapping table (e.g., speed is mapped from "mph to m / s," converting the equivalent value to 1.1176 m / s through a formula; a 6-inch wheel diameter is converted to 152.4 mm). Parameters are then range-mapped based on preset motor performance thresholds (e.g., rated power thresholds of 0.5-5 kW): The full-load gross weight of 1200 kg is normalized to 0.6 through linear scaling (thresholds of 0-2000 kg), and the speed of 1.1176 m / s (threshold of 0-3 m / s) is mapped to 0.3725. Discrete parameter energy efficiency level IE3 is one-hot encoded to generate a binary vector [0, 1, 0]. The feature fusion layer concatenates the normalized value and the encoded vector according to weight priority (rated power weight 0.3 > efficiency 0.25 > size 0.2) to form a standardized feature vector [0.6, 0.3725, 0.76 (normalized wheel diameter), 0, 1, 0]. Wheel diameter is prioritized due to the "installation compatibility" factor in the decision tree. If a parameter is missing (such as acceleration), interpolation is performed using adjacent operating conditions (the average acceleration in historical AGV data is 0.8 m / s², which is supplemented to 0.8). The final output is a standardized feature vector set, which is then used in the distributed query library to match candidate motor models.

[0025] In summary, through the systematic data processing process, the standardization and availability of the selection benchmark parameters are improved, providing an accurate and reliable data basis for motor selection decisions, thereby improving the efficiency and accuracy of motor selection.

[0026] Preferably, a distributed data query library is constructed, and the standardized feature vector is imported into the distributed data query library to match a set of candidate motor models, specifically: Obtain the benchmark parameter data stream of each manufacturer's motor, convert the benchmark parameter data stream of each manufacturer's motor into standardized parameters with unified dimensions through a preset motor industry standard terminology mapping table, and construct a standardized parameter table; Among them, the preset motor industry standard terminology mapping table is a pre-prepared comparison table used to unify the naming and dimensions of motor parameters from different manufacturers. It maps the heterogeneous parameter terms (such as "output power" and "rated power") and units (such as "HP" and "kW") of each manufacturer into standard terms and benchmark units to ensure data comparability and calculation consistency.

[0027] It should be noted that the data acquisition module extracts benchmark parameter data streams from the motor technical documentation provided by various manufacturers, including key parameters such as rated power, efficiency, and speed. Next, a pre-set motor industry standard terminology mapping table is loaded to match the parameter terms used by various manufacturers with the standard terminology, standardizing parameter naming and unit identification. If undefined terms are found, a term expansion mechanism is activated, intelligently matching based on contextual semantics and updating the mapping table. Unit conversion is then performed on the uniformly named parameters, converting imperial or non-standard metric units to benchmark units to ensure consistent dimensioning for all parameters.

[0028] Matrixing the standardized parameter table to form a multidimensional feature matrix, wherein each row of the matrix represents a motor model and each column corresponds to a standardized parameter feature; constructing a data query library, and importing the multidimensional feature matrix into the data query library to obtain a distributed data query library; Expanding the dimension of the standardized feature vector to make it consistent with the column dimension of the multidimensional feature matrix to form a query vector matrix; It should be noted that the first step is to obtain the column dimension definition of the multidimensional feature matrix (for example, the order of standardized parameters such as rated power, speed, and size), and then arrange the parameters in the standardized feature vector in the same dimensional order. If the vector is missing a parameter corresponding to a matrix column (for example, if the protection level is not recorded in historical data), the missing item is filled with zero values ​​or interpolated based on the mean of similar motor parameters. Subsequently, by adjusting the feature vector length to match the number of columns in the multidimensional feature matrix, a one-to-one correspondence is ensured for each dimension, ultimately forming a query vector matrix that is fully aligned with the matrix column structure. For example, if the matrix contains six columns of parameters and the original feature vector only has five columns, a default value of 0 is added to the end to complete the expansion.

[0029] Compare the query vector with each row in the feature matrix row by row, and calculate the Euclidean distance between the two in each feature dimension; if the Euclidean distance of a row is less than the preset distance threshold, mark the motor model in the corresponding row as a candidate model; Among them, the Euclidean distance calculation formula is: ; Where, Represents the query vector and the first Euclidean distance of rows; Indicates that the query vector is The value of the dimension; Indicates the first Row, No. The value of the column.

[0030] Prioritize the marked candidate model set and arrange them from small to large according to the Euclidean distance to generate the final candidate motor model set; During the entire process, if the candidate motor model set is empty, the preset distance threshold is automatically adjusted or the user is prompted to re-enter the selection benchmark parameters.

[0031] In the motor selection scenario for logistics and warehousing AGVs, based on the standardized feature vectors generated in the previous example (e.g., [0.6, 0.3725, 0.76, 0,1,0]), when building a distributed data query library, the data acquisition module first obtains the motor parameters of manufacturer A (e.g., "output power: 3.7HP," "efficiency: 92%," and "speed: 2800rpm") and manufacturer B (e.g., "rated power: 2.2kW," "efficiency: IE4," and "speed: 1500r / min"). Using a preset motor industry standard terminology mapping table, "output power" is standardized as "rated power" (with the unit converted to kW, e.g., 3.7HP → 2.76kW), "efficiency: IE4" is mapped to "energy efficiency level code 4," and the speed unit is standardized to "r / min." The standardized parameter table is then matrixed into a 3-row, 6-column multidimensional feature matrix (for example, the model data for manufacturer C is [0.65 (normalized rated power), 0.35 (normalized speed), 0.72 (installation size score), 0,1,0 (energy efficiency code)]). After expanding the standardized feature vector into a 6-dimensional query vector matrix, the Euclidean distance is calculated row by row. For example, if the distance between the query vector Q and the manufacturer C model is approximately 0.18, then if the preset distance threshold is 0.2, the model is marked as a candidate. Finally, a candidate set is generated in ascending distance order (for example, the distance of the manufacturer C model is 0.18 > the manufacturer B model is 0.25). If the initial candidate set is empty, the threshold is automatically adjusted to 0.3 to include more models, ensuring that the matching results are adapted to the low-speed, high-torque requirements of the AGV.

[0032] In summary, this step can improve the efficiency, accuracy, and adaptability of motor model matching through a systematic data processing and matching process, providing reliable technical support for motor selection decisions.

[0033] Preferably, the comprehensive performance score of each candidate motor model is obtained, and a model elimination mechanism is triggered based on a preset score value threshold. The retained candidate motor models are sorted by performance parameters to generate a set of preferred motor models, specifically: Extract key performance parameters of each model from the candidate motor model set, including rated power curves, efficiency distribution maps, and temperature rise characteristic data, and construct a three-dimensional performance matrix as a benchmark data source for multi-dimensional parameter comparison; It should be noted that the rated power curve data, including the output power value of the motor at different load points, is extracted through the technical documents or test reports provided by each motor manufacturer. If the data is missing, it is interpolated based on the historical data of similar models. Next, the efficiency values ​​of the motor at different loads and speeds are extracted from the efficiency test report to generate an efficiency distribution map. If the test conditions are incomplete, the simulation model is called to supplement the data. Then, the temperature rise characteristic data of the motor under different working conditions, including steady-state temperature and temperature rise rate, are obtained through temperature rise experiments or thermal simulations. If the experimental data is insufficient, it is extrapolated based on the thermodynamic model. Finally, the extracted data is verified and standardized to ensure that the data format is unified and there are no outliers, and a complete performance parameter data set is constructed as the basis for subsequent analysis.

[0034] Automatically allocate torque response coefficient, energy efficiency priority factor, and environmental adaptation weight based on the application scenario characteristics input by the user to form a dynamic weight allocation rule. If the scenario characteristics are not clear, the default weight allocation mode is enabled and logged. Among them, "application scenario characteristics" refers to key information such as the usage environment, operating conditions and performance requirements specifically described by the user during the motor selection process, including but not limited to load type (such as constant load, periodic load), operating environment (such as high temperature, humidity, dust), energy efficiency requirements (such as high energy efficiency first, cost first), operating frequency (such as continuous operation, intermittent operation) and special requirements (such as low noise, high precision), etc.

[0035] It should be noted that the application scenario features entered by the user are parsed to extract key parameters such as load type, operating environment, and energy efficiency requirements. If the scenario features are unclear or the parameters are missing, the default scenario template is called to complete them and log them. Next, based on the preset scenario feature-weight mapping table, the initial values ​​of the torque response coefficient, energy efficiency priority factor, and environmental adaptation weight are dynamically calculated according to the extracted key parameters. If the current scenario is not defined in the mapping table, the weight inference mechanism is activated and the weight is estimated based on historical data of similar scenarios. The initial weight values ​​are then normalized to ensure that the sum of the three is 1. Subsequently, the final weight values ​​are written to the dynamic weight allocation rule library, and a weight allocation report is generated for user confirmation. If the user requests modification, the weight allocation process is re-executed. Finally, the complete weight allocation process and result log are recorded as a reference for subsequent weight rule optimization.

[0036] Based on dynamic weighting rules, each parameter in the three-dimensional performance matrix is ​​weighted and calculated to generate a comprehensive performance score for each candidate motor model; the comprehensive performance score of each candidate motor model is compared with a preset score threshold; It should be noted that, first, the torque response coefficient, energy efficiency priority factor and environmental adaptation weight value in the current scenario are obtained from the dynamic weight rule library. Next, the rated power curve, efficiency distribution map and temperature rise characteristic data of each candidate motor model in the three-dimensional performance matrix are extracted, and the dot multiplication operation is performed with the corresponding weight value to calculate the weighted score of each parameter. Then, the weighted scores of each parameter are accumulated to generate a comprehensive performance score for each candidate motor model. The calculation formula is as follows: ; Where, Score the overall performance of motor model M; is the torque response coefficient, which indicates the weight of the rated power to the scenario demand; is the energy efficiency priority factor, which indicates the weight of efficiency to the scenario requirements; is the environmental adaptation weight, which indicates the weight of the temperature rise characteristic to the scenario requirements; is the normalized mean of rated power; is the normalized mean of efficiency; is the normalized inverse mean of the temperature rise characteristic.

[0037] If the comprehensive performance score of a candidate motor model is less than the preset score threshold, the model elimination mechanism is triggered to eliminate the candidate motor model from the candidate motor model set; Sort the retained candidate models by their comprehensive performance scores from highest to lowest to generate a set of preferred motor models; Among them, if the score values ​​are the same, a secondary sorting is performed according to the energy efficiency priority factor to ensure the uniqueness of the sorting result, and the preferred sequence is used as the input data for the load characteristic matching verification in the next stage.

[0038] Similarly, in the motor selection scenario for logistics warehousing AGVs, based on the candidate model set matched in the previous example (e.g., Model M1 from Manufacturer C and Model M2 from Manufacturer B), the system first extracted M1's rated power curve (e.g., 2.1kW output at 50% load, 3.0kW at 100% load), efficiency distribution map (92% efficiency at 50% load, 88% efficiency at 100% load), and temperature rise characteristic data (steady-state temperature of 65°C after 2 hours of continuous operation) from the manufacturer's technical documentation to construct a three-dimensional performance matrix. Based on the user-entered scenario characteristics of "high-temperature storage environment, high energy efficiency priority," the system dynamically assigned weights: torque response coefficient α = 0.4 (focusing on load adaptability), energy efficiency priority factor β = 0.5 (high efficiency requirement), and environmental adaptability weight γ = 0.1 (low temperature rise tolerance). Calculate the comprehensive score for M1: The normalized mean rated power is 0.72, the mean efficiency is 0.9, and the inverse mean temperature rise is 0.6. Substituting these into the above comprehensive performance score formula yields a comprehensive performance score of 0.798. If the preset score threshold is 0.75, M1 is retained as meeting the criteria, while M2, with a score of 0.68, is eliminated. The final ranking is based on score (e.g., M1 > 0.78 for model M3 from manufacturer D). If the scores are the same, they are re-ranked by energy efficiency factor (e.g., M3 and M4 both score 0.78, but M3 has a higher energy efficiency factor). This generates a preferred set for subsequent energy efficiency verification.

[0039] In summary, by constructing a three-dimensional performance matrix, dynamic weight allocation, comprehensive performance score calculation, model elimination and performance ranking, efficient and accurate motor model screening and optimization are achieved, thereby improving the efficiency, accuracy and adaptability of motor model selection.

[0040] Preferably, the comprehensive energy efficiency score of each preferred motor model is obtained and a Pareto front solution set is established for secondary screening to obtain a set of recommended motor models, specifically: Acquire rated operating condition data of each preferred motor model, and extract efficiency distribution characteristics of each preferred motor model at different load points based on the rated operating condition data; It should be noted that the rated operating condition data, including key parameters such as rated voltage, rated current, rated speed, and rated load, are extracted from the technical documents or test reports provided by the motor manufacturer. Next, the efficiency values ​​of the motor at different load points (such as 25%, 50%, 75%, and 100% load) are obtained through the efficiency test report or simulation model to generate an efficiency distribution map. The extracted efficiency distribution characteristic data is then verified. If abnormal values ​​or data deviations are found, corrections are made based on adjacent load points or historical data. Subsequently, the verified efficiency distribution characteristic data are stored according to the motor model to construct an efficiency distribution characteristic database. Finally, the efficiency distribution characteristic data of each preferred motor model is output as the basic data source for the subsequent calculation of the comprehensive energy efficiency score.

[0041] Based on the energy efficiency priority parameters entered by the user, the efficiency weight coefficient is dynamically assigned. Combined with the efficiency distribution characteristics of each preferred motor model at different load points, the comprehensive energy efficiency score of each preferred motor model is calculated. If the comprehensive energy efficiency score of a preferred motor model falls below the preset score threshold, the model downgrade mechanism is triggered and the model is removed from the preferred queue. It should be noted that the energy efficiency priority parameters entered by the user are parsed to extract key indicators such as high load efficiency priority, average efficiency priority, or low load efficiency priority. Then, based on the preset energy efficiency priority-weight mapping table, the efficiency weight coefficient of each load point (such as 25%, 50%, 75%, 100% load) is dynamically allocated according to the extracted key indicators. The weight coefficient is then normalized to ensure that the sum of the weights of each load point is 1. Subsequently, the efficiency value of each load point is weighted with the corresponding weight coefficient to generate a comprehensive energy efficiency score for each preferred motor model. The calculation formula is as follows: ; Where, Provide a comprehensive energy efficiency score; For the The dynamic weight of each load point is allocated according to the user's energy efficiency priority (such as 、 ),satisfy ; For the The efficiency (unit: %) at each load point is obtained through actual measurement or simulation (such as ); For the number of user-defined load cases (e.g. , corresponding to 25%, 50%, 75%, and 100%).

[0042] A multi-objective particle swarm optimization algorithm is used to establish the Pareto frontier solution set for each preferred motor model, with comprehensive energy efficiency score, power density, and temperature rise characteristics as optimization targets. If the number of Pareto frontier solution sets exceeds the preset upper limit, a fuzzy comprehensive evaluation method is introduced to perform a secondary screening of the solution set until the number of Pareto frontier solution sets falls below the preset upper limit. Subsequently, the embedded simulation engine is called to perform a virtual working condition loading test on each preferred motor model according to the Pareto front solution set of each preferred motor model to obtain the simulated energy efficiency degradation curve of each preferred motor model; The simulation engine is a software tool based on physical models and mathematical algorithms that simulates the operating status and performance of motors under different operating conditions. Its core function is to input motor parameters (such as rated power, efficiency, and temperature rise characteristics) and operating conditions (such as load, speed, and ambient temperature) and provide a scientific basis for motor selection, performance optimization, and fault prediction by providing realistic operating data, including energy efficiency, temperature rise, and vibration.

[0043] It should be noted that the key parameters of each preferred motor model, including rated power, efficiency distribution, and temperature rise characteristics, are extracted from the Pareto front solution set, and a virtual working condition input data set is constructed. Next, the operating environment of the embedded simulation engine is configured, the motor physical model and working condition simulation scenario are loaded, and test parameters such as test time, load fluctuation frequency, and ambient temperature are set. Then, the simulation engine is started, and a virtual working condition loading test is performed on each preferred motor model in turn. The energy efficiency values ​​of the motor at different time points are recorded to generate raw data on energy efficiency changes over time. Subsequently, the raw data is smoothed to remove noise and extract the energy efficiency decay trend to generate a simulated energy efficiency decay curve.

[0044] Comparing the simulated energy efficiency attenuation curve of each preferred motor model with the preset energy efficiency attenuation curve to obtain the degree of overlap between the simulated energy efficiency attenuation curve of each preferred motor model and the preset energy efficiency attenuation curve; If the overlap between the simulated energy efficiency attenuation curve of a preferred motor model and the preset energy efficiency attenuation curve is no greater than the preset overlap, the model downgrade mechanism is triggered and the model is removed from the preferred queue; For example, Figure 4 As shown in the figure, the preset energy efficiency attenuation curve (dashed line) is used as a standard reference curve to represent the energy efficiency attenuation trend under ideal conditions. Figure 4 As can be seen from the figure, the curve of motor C deviates significantly from the preset curve, so it is removed from the preferred queue.

[0045] The remaining preferred motor models in the preferred motor model set are obtained to obtain a recommended motor model set.

[0046] It is important to note that the efficiency distribution characteristics extracted from rated operating condition data and dynamically calculated based on user-entered energy efficiency priority parameters ensure the scientific and adaptable scoring results. A model downgrade mechanism is triggered by a preset score threshold, improving the accuracy of the selection process. Secondly, a multi-objective particle swarm optimization algorithm is used to construct a Pareto front solution set, comprehensively considering the comprehensive energy efficiency score, power density, and temperature rise characteristics to ensure the comprehensiveness and optimality of the solution set. If the number of solution sets exceeds a preset upper limit, a fuzzy comprehensive evaluation method is introduced for secondary screening to further optimize the solution set quality. Next, an embedded simulation engine is used to perform a virtual operating condition load test to obtain a simulated energy efficiency decay curve. The motor's energy efficiency performance in actual operation is verified by analyzing the degree of overlap with the preset curve, ensuring the reliability of the selection results. Finally, the model downgrade mechanism is triggered to eliminate models that do not meet the requirements, generating a final set of recommended motor models, providing users with high-quality and highly adaptable selection results.

[0047] Similarly, in the motor selection scenario for logistics warehousing AGVs, based on the preferred model set generated in the previous example (e.g., models M1 and M3), the rated operating data for M1 (rated voltage 48V, rated current 15A, rated speed 1200 rpm) was first extracted from the manufacturer's technical documentation. Its efficiency distribution characteristics at load points of 25% (89% efficiency), 50% (92%), 75% (90%), and 100% (88%) were then obtained. Based on the user-entered "high load efficiency priority" parameter, efficiency weights were dynamically assigned (25%: 0.1, 50%: 0.2, 75%: 0.3, 100%: 0.4), resulting in a calculated comprehensive energy efficiency score for M1 of 0.1 × 89 + 0.2 × 92 + 0.3 × 90 + 0.4 × 88 = 89.3 (pre-set threshold of 85, retained if meeting the threshold). Subsequently, using M1's comprehensive energy efficiency score (89.3), power density (2.1 kW / kg), and temperature rise characteristics (65°C @ 2 hours) as optimization targets, a Pareto front solution set (e.g., a solution set containing M1, M3, and M5) was generated. If the number of solution sets exceeded a preset upper limit (e.g., 5), M1 (with a comprehensive fuzzy evaluation value of 0.82) and M3 (with a 0.78) were selected. An embedded simulation engine was used to perform a virtual load test on M1 (simulating 1000 hours of continuous AGV operation). An energy efficiency decay curve was generated (e.g., efficiency decayed to 87% after 100 hours, 85% after 500 hours, and 82% after 1000 hours). This curve had a 92% overlap with the preset curve (88% after 100 hours, 86% after 500 hours, and 83% after 1000 hours), exceeding the preset threshold of 90%), and was retained. The final recommended set, containing M1 and M3, met the requirements for long-term, efficient operation in high-temperature warehousing scenarios.

[0048] Preferably, a multi-objective particle swarm optimization algorithm is used to establish the Pareto frontier solution set of each preferred motor model with comprehensive energy efficiency score, power density and temperature rise characteristics as optimization targets, specifically: Initialize the particle swarm, use the comprehensive energy efficiency score, power density, and temperature rise characteristics of each preferred motor model as the three-dimensional target vector of the particle, and randomly assign the initial position and speed; If data missing or abnormality is detected in the three-dimensional target vector, the data repair mechanism is activated to perform interpolation and completion based on the adjacent model data; Calculate the fitness value of each particle and construct the initial Pareto solution set; if the number of solution sets is zero, adjust the target weight coefficient and recalculate the fitness value; the particle fitness value calculation formula is: ; Where, is the particle fitness value; is the energy efficiency weight coefficient; is the power density weight coefficient; is the temperature rise characteristic weight coefficient; is the normalized mean of rated power; is the normalized mean of efficiency; is the normalized inverse mean of the temperature rise characteristic.

[0049] Execute the particle position update algorithm to dynamically adjust the particle trajectory based on the individual optimal solution and the global optimal solution; if it is detected that the particle is trapped in the local optimum, a mutation operation is introduced to randomly perturb the particle position to jump out of the local extreme value; It should be noted that the difference between each particle's current position and its individual optimal solution and the global optimal solution is calculated to determine the particle's direction of movement in the target space. If the difference between the particle's position and the optimal solution is too small, the particle is considered to be trapped in a local optimum. Next, the particle's velocity vector is adjusted based on the preset inertia weight, individual learning factor, and social learning factor to update the particle's position. If the particle's position still does not escape the local minimum after the update, a mutation operation is introduced to randomly perturb the particle's position parameters, causing it to explore a new direction in the target space. The updated particle position and velocity are then recorded as the basis for the next iteration. Finally, the updated particle swarm is output as input for the subsequent non-dominated sorting and Pareto solution set construction.

[0050] The updated particles are classified using the non-dominated sorting method to screen out new Pareto solution sets. If the number of solution sets exceeds the preset upper limit, the congestion calculation is started to prioritize the evenly distributed solutions. It should be noted that the updated particle swarm is non-dominated and sorted, and the particles are divided into multiple levels according to the dominance relationship. The first level is the particles that are not dominated by any other particles, which constitute the initial Pareto solution set; if the number of solution sets is zero, the target weight coefficient is adjusted and the fitness value is recalculated. If the number of solution sets exceeds the preset upper limit, the crowding distance of each particle in the target space is calculated. The larger the crowding distance, the sparser the distribution of particles in the solution set; then, particles with larger crowding distances are retained first to ensure that the solution set is evenly distributed in the target space. Finally, the new Pareto solution set is output as the basic data for subsequent solution set convergence judgment. Among them, the formula for calculating the crowding distance of each particle in the target space is: ; Where, For particles crowding distance; To optimize the number of targets; For the target Dimensionally, particles The fitness value of the adjacent particle on the right; For the target Dimensionally, particles The fitness value of the neighboring particle on the left; Target is the maximum value among all particles; Target is the minimum value among all particles.

[0051] At the same time, a solution set convergence judgment mechanism is established. If the number of consecutive iterations exceeds the threshold and the solution set change rate is lower than the preset value, the algorithm is judged to have converged; if it has not converged, iterative optimization will continue; Finally, the final Pareto front solution set is output, and the motor model and key parameters corresponding to each solution are marked.

[0052] For example, Figure 5 As shown, Figure 5 The black curve in the figure is the complete motion trajectory of a single particle in the three-dimensional target space; the red dot is the starting position of the particle; the blue dot is the ending position of the particle; the orange dot is the global optimal solution position; the three coordinate axes represent: comprehensive energy efficiency score, power density and temperature rise characteristics.

[0053] like Figure 6 As shown, Figure 6 This is a particle swarm distribution and Pareto front diagram. The colored scattered points represent the distribution of each particle in the particle swarm in the three-dimensional target space; the gray surface represents the Pareto front, that is, the distribution area of ​​non-dominated solutions; the color depth represents the fitness value of the particle; the three coordinate axes also represent the three optimization objectives: comprehensive energy efficiency score, power density and temperature rise characteristics.

[0054] In summary, Figure 5 、 Figure 6 The diagrams intuitively demonstrate how individual particles gradually optimize their positions, influenced by both the individual optimal solution and the global optimal solution; how the entire particle swarm is distributed in the target space and their relationship to the Pareto front; and how the algorithm finds the optimal balance between the three objectives. These diagrams fully demonstrate the working principle and optimization process of the multi-objective particle swarm optimization algorithm in the motor selection process.

[0055] It should be noted that the initial Pareto solution set is constructed using fitness value calculation and a non-dominated sorting method, and the particle motion trajectory is dynamically optimized through a particle position update algorithm to ensure the optimality and diversity of the solution set. If a particle is trapped in a local optimum, a mutation operation is introduced to jump out of the local extreme value, improving the global search capability of the solution. Next, a uniformly distributed solution set is screened through crowding calculation to ensure that the solution set has extensive coverage in the target space. At the same time, a solution set convergence judgment mechanism is established to ensure that the algorithm terminates promptly when the optimal solution is reached, avoiding invalid iterations. Finally, the final Pareto front solution set is output, and the motor model and key parameters corresponding to each solution are annotated, providing users with a high-quality, multi-dimensional selection reference.

[0056] Similarly, in the motor selection scenario for logistics and warehousing AGVs, based on the set of preferred models selected in the previous example (e.g., model M1: comprehensive energy efficiency score 89.3, power density 2.1 kW / kg, temperature rise 65°C), when initializing the particle swarm, the three-dimensional target vectors (\[89.3, 2.1, 65\]) of M1 and its similar preferred models are used as the initial positions of the particles, and initial velocities (e.g., \[0.2, -0.1, 0.3\]) are randomly assigned. If missing temperature rise characteristic data for a model is detected (e.g., missing temperature rise data for model M3), the data of adjacent models M1 and M5 are interpolated to complete the data (M1 temperature rise 65°C, M5 temperature rise 68°C, and the average value is 66.5°C). When calculating the fitness value, based on the user-defined weights (μ=0.5, ρ=0.3, τ=0.2), we substitute the formula F=0.5×0.89 (normalized energy efficiency) + 0.3×0.72 (normalized power density) + 0.2×(1-0.65)=0.763. When updating the particle position, if the difference between M1's individual optimal solution (F=0.763) and the global optimal solution (F=0.78) is less than a threshold (e.g., 5%), a mutation operation is triggered, randomly perturbing its power density parameter (e.g., from 0.72 to 0.75), resulting in a new position of [89.3, 2.25, 65]. The initial Pareto solution set (such as M1, M3, and M5) is screened out through non-dominated sorting. If the number of solution sets exceeds the preset upper limit (such as 5), the crowding distance is calculated (for example, the adjacent particle distance of M1 in the energy efficiency dimension is 0.15, the power density dimension is 0.12, the temperature rise dimension is 0.08, and the total crowding distance CD=0.35), and the high CD value model is retained first. When the solution set change rate is less than 2% for 10 consecutive iterations, convergence is determined, and the Pareto frontier solution set (such as Figure 6 As shown in the figure, M1 and M5 are distributed in the gray surface area), with key parameters marked (such as M1: energy efficiency 89.3, power density 2.1kW / kg, temperature rise 65°C), adapting to the high-efficiency and long-term operation requirements of AGV.

[0057] In summary, in order to solve the problems of difficulty in simultaneously optimizing multiple objective parameters such as energy efficiency, power density, and temperature rise characteristics during motor selection, as well as the problem that traditional methods are prone to falling into local optimality and uneven distribution of solution sets, the present invention dynamically balances various optimization objectives through a multi-objective particle swarm optimization algorithm, automatically generates a uniformly distributed Pareto optimal solution set; uses data repair and mutation operations to ensure the integrity of the solution and global search capability; combines non-dominated sorting and congestion calculation to maintain the diversity of the solution set, and finally outputs a set of motor models that covers the optimal balance of comprehensive energy efficiency, power density, and temperature rise characteristics, providing a scientific basis for multi-objective decision-making.

[0058] Preferably, if the number of Pareto front solution sets exceeds a preset upper limit, a fuzzy comprehensive evaluation method is introduced to perform a secondary screening of the solution set until the number of Pareto front solution sets is lower than the preset upper limit, specifically: Extract the comprehensive energy efficiency score, power density and temperature rise characteristic data of each motor model from the Pareto front solution set and construct a multi-dimensional evaluation matrix; Dynamically assign weight coefficients to each evaluation indicator based on the energy efficiency priority parameters entered by the user; if the deviation between the weight assignment result and the historical optimal mode is greater than the preset deviation value, the weight adjustment mechanism is triggered to reallocate the weight value; It should be noted that the energy efficiency priority parameters entered by the user are parsed to extract key indicators such as high-load efficiency priority, average efficiency priority, or low-load efficiency priority. Based on the preset energy efficiency priority-weight mapping table, the initial weight values ​​of each evaluation indicator (such as comprehensive energy efficiency score, power density, and temperature rise characteristics) are dynamically assigned according to the extracted key indicators. Then, the initial weight values ​​are normalized to ensure that the sum of the weights of each evaluation indicator is 1. Subsequently, the final weight values ​​are written into the dynamic weight rule library, and a weight allocation report is generated for user confirmation. If the user requests a modification, the weight allocation process is re-executed. Finally, the complete weight allocation process and result log are recorded as a reference for subsequent weight rule optimization.

[0059] Among them, the preset energy efficiency priority-weight mapping table is a predefined rule comparison table, which is used to automatically match and assign weight coefficients of efficiency evaluation indicators of each load point according to the energy efficiency priority specified by the user (such as high load efficiency priority, average efficiency priority, etc.), to ensure that the weight allocation accurately corresponds to user needs.

[0060] A fuzzy membership function is established to normalize each evaluation index and eliminate dimensional differences. If uneven distribution of normalized data is detected, the membership function parameters are adjusted. It should be noted that, first, based on the data distribution characteristics of each evaluation metric (such as energy efficiency rating and power density), a triangular or trapezoidal membership function type is selected, and initial parameters (such as triangle vertex positions and trapezoidal boundary values) are set. The data is then normalized (e.g., mapping 0-100% efficiency to the interval [0,1]). If the normalized data distribution is uneven (e.g., energy efficiency ratings are concentrated in the high-end interval of 0.8-1.0, while temperature rise data are dispersed between 0.3-0.9), the membership function parameters are adjusted: for dense intervals (e.g., energy efficiency 0.8-1.0), the triangle vertex spacing is reduced to improve resolution; for dispersed intervals (e.g., temperature rise 0.3-0.9), the trapezoidal boundaries are expanded to cover a wider data domain, and the distribution curve is refitted. For example, the temperature rise membership function can be expanded from the original trapezoidal boundaries of [0.5, 0.7] to [0.3, 0.9] to ensure uniform membership of the data points. After adjustments, the function fit is verified until the normalized data distribution approaches uniformity.

[0061] The weighted average method is used to calculate the comprehensive fuzzy evaluation value of each motor model, and the solution set is sorted according to the comprehensive fuzzy evaluation value; It should be noted that the normalized weight coefficients of each evaluation index (such as energy efficiency weight 0.5, power density 0.3, temperature rise 0.2) are obtained from the dynamic weight rule library, and the normalized evaluation index data of each motor model are extracted (such as a certain model with energy efficiency 0.9, power density 0.7, and temperature rise 0.8); each index value is multiplied by the corresponding weight (0.9×0.5+0.7×0.3+0.8×0.2=0.82), and the cumulative value is obtained to obtain a comprehensive fuzzy evaluation value; the solution set is sorted from high to low according to the evaluation value, and if the evaluation values ​​are the same, they are sorted again according to the energy efficiency score, and finally a sorted list of preferred models is generated for user decision-making.

[0062] Set the upper threshold of the number of solutions, and eliminate the motor models with the lowest comprehensive fuzzy evaluation values ​​in sequence until the number of motor models after elimination is less than the upper threshold of the number of solutions; if the number of solutions after elimination still exceeds the upper threshold, gradually increase the elimination standard until the number requirement is met; Finally, the filtered Pareto front solution set is output, and the comprehensive fuzzy evaluation value and key parameters of each model are marked.

[0063] Similarly, in the motor selection scenario for AGVs in logistics and warehousing, the Pareto front solution set generated in the previous example (e.g., including 10 candidate models, such as M1, M3, and M5, with a preset upper limit of 5) is first extracted from each model's key parameters (e.g., M1: comprehensive energy efficiency score of 89.3, power density of 2.1kW / kg, and temperature rise of 65°C) to construct a multi-dimensional evaluation matrix. Based on the user-entered "high load efficiency priority" parameter, weight coefficients are dynamically assigned (energy efficiency score of 0.5, power density of 0.3, and temperature rise of 0.2). If the temperature rise weight in the historical optimization mode is typically 0.15 (the current 0.2 deviates by 15% from the preset threshold), a weight adjustment mechanism is triggered, correcting the temperature rise weight to 0.15 and adjusting the energy efficiency and power density to 0.55 and 0.3 respectively. Subsequently, a triangular membership function was established to normalize the parameters (e.g., energy efficiency score mapped to [0.8, 1.0], power density to [0.6, 0.9], and temperature rise reversely mapped to [0.7, 1.0]). If the temperature rise data was detected to be concentrated between 60°C and 70°C (normalized to 0.6-0.8), the membership function parameters were adaptively adjusted to expand the coverage range to 0.5-0.9. A weighted average method was used to calculate the comprehensive fuzzy evaluation value (e.g., M1 score: 0.55 × 0.893 + 0.3 × 0.7 + 0.15 × 0.8 = 0.801). The models were sorted by score and the bottom five (e.g., models with a score < 0.7) were eliminated. If the remaining seven models still exceeded the upper limit (e.g., the upper limit was 5), the elimination criteria was raised to a score < 0.75. Finally, the final five models were selected (e.g., M1: 0.801, M5: 0.78), with key parameters annotated to meet the high energy efficiency requirements of AGVs.

[0064] In summary, the present invention dynamically adjusts the evaluation weights based on user needs to ensure that the screening results are in line with the actual application scenarios; eliminates dimensional differences through adaptive membership functions to improve evaluation accuracy; and adopts a quantitative scoring mechanism to achieve accurate sorting and screening of solution sets, ultimately outputting a controllable number of motor model sets with the best quality, thereby improving selection efficiency and decision reliability.

[0065] Preferably, the recommended motor models are divided into multiple motor selection levels, specifically: Extract the comprehensive energy efficiency scores, cost-effectiveness indexes, and compatibility parameters of all models in the recommended motor model set and construct a three-dimensional classification feature matrix; Based on the core performance threshold set by the user, a set of models with comprehensive energy efficiency scores higher than the benchmark value and compatibility that meets the standard are screened and marked as the primary recommended candidate set. If the candidate set is empty, the threshold range is automatically relaxed and the adjustment parameters are recorded. Perform an economic analysis on the remaining models, calculate the full life cycle cost-benefit ratio, and select models with a cost-benefit ratio below the industry average and compatibility parameters within the allowable range. These models are classified as economic alternatives. If missing cost data is detected, the historical procurement database is used to fill in the alternative values. For models that are not selected as the primary recommended models and economic alternative models above, extended compatibility verification will be carried out, and the models that pass the extended compatibility verification will be regarded as extended compatible models.

[0066] It should be noted that "Extended Compatibility Verification" refers to the cross-platform and cross-scenario applicability assessment of motor models that are not included in the primary recommended models or economical alternatives. By simulating their adaptability in different operating environments, load types, and control systems, the compatibility and flexibility in diverse application scenarios are verified. Specifically, this includes interface adaptability analysis, load fluctuation tolerance testing, and multi-condition operational stability verification to ensure that these models can meet the requirements of non-core application scenarios or special demand scenarios, thereby providing users with more comprehensive and flexible selection options.

[0067] Similarly, in the motor selection scenario for logistics warehousing AGVs, based on the recommended motor model set generated in the previous example (e.g., including models M1, M3, and M5), key parameters for each model were first extracted to construct a three-dimensional classification feature matrix (e.g., M1: comprehensive energy efficiency score 89.3, cost-effectiveness index 0.85, compatibility score 92). Based on user-defined core performance thresholds (energy efficiency ≥ 85, compatibility ≥ 90), M1 (89.3 / 92) was selected as the primary recommendation; if the candidate set was empty, the energy efficiency threshold was automatically relaxed to 80. An economic analysis was performed on the remaining models, M3 (energy efficiency 82 / cost-effectiveness 0.78) and M5 (energy efficiency 79 / cost-effectiveness 0.72), calculating the full lifecycle cost-effectiveness ratio (industry average 0.8), and classifying M3 as an economic alternative. The M5 was verified for extended compatibility through simulation tests of its stability (efficiency fluctuation <5%) in a cold chain environment (-20°C) and variable frequency control system, confirming its extended compatibility. The final hierarchical selection results are: the primary recommendation type M1 (efficiently adapted to normal temperature warehousing), the economic alternative type M3 (balanced cost-effectiveness), and the extended compatible type M5 (backup for special scenarios), meeting the needs of different AGV deployment scenarios.

[0068] In summary, this step improves the scientificity, accuracy, and practicality of motor selection through a systematic multi-level division process, providing users with high-quality, multi-dimensional selection decision support.

[0069] The selection benchmark parameters include full load gross weight, full load speed, full load acceleration, travel wheel / drum diameter, energy efficiency level requirements, three-dimensional size restrictions of installation space, energy efficiency priority parameters, ambient temperature and humidity gradient parameters, protection level code, expected life index and application scenario characteristics.

[0070] like Figure 3 As shown, the second aspect of the present invention discloses a motor selection system 6, which includes a memory 41 and a processor 52. The memory 41 stores a motor selection method program. When the motor selection method program is executed by the processor 52, the steps of any one of the motor selection methods are implemented.

[0071] The above are only specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed by the present invention, which should be covered by the scope of protection of the present invention.

Claims

1. A motor selection method, characterized in that: The following steps are involved: Obtaining the selection benchmark parameters input by the user, and converting the selection benchmark parameters into a benchmark measurement system to obtain a standardized feature vector; Building a distributed data query library, importing the standardized feature vector into the distributed data query library to match a set of candidate motor models; Obtain the comprehensive performance score of each candidate motor model, trigger the model elimination mechanism based on the preset score value threshold, and sort the performance parameters of the retained candidate motor models to generate a set of preferred motor models; Obtain the comprehensive energy efficiency score of each preferred motor model and establish a Pareto front solution set for secondary screening to obtain a set of recommended motor models; The recommended motor models are divided into a plurality of motor selection levels, and the motor selection levels are output as final motor selection results.

2. A motor selection method according to claim 1, characterized in that: The selection benchmark parameters are converted into a benchmark measurement system to obtain a standardized feature vector, specifically: Extract the values ​​and unit identifiers of each input selection benchmark parameter and dynamically build a parameter-unit mapping table; Identify the unit identifier of each parameter in the mapping table. If the unit is English or non-standard metric, convert the corresponding selection reference parameter into an equivalent value under the reference unit. For the converted selection benchmark parameters, interval mapping is performed on each parameter according to the preset motor performance parameter threshold range; The normalized numerical parameters and the encoded discrete parameters are concatenated according to the weight priority through the feature fusion layer to form a multi-dimensional standardized feature vector. The order of the vector dimensions is dynamically adjusted according to the ranking of the key influencing factors in the motor selection decision tree. The integrity of the standardized feature vector is checked, and the missing parameters are supplemented by adjacent working condition interpolation or historical data fitting, and a standardized feature vector set that meets the input requirements of the motor performance matching model is output.

3. A motor selection method according to claim 1, characterized in that: Construct a distributed data query library, import the standardized feature vector into the distributed data query library to match the candidate motor model set, specifically: Obtain the benchmark parameter data stream of each manufacturer's motor, convert the benchmark parameter data stream of each manufacturer's motor into standardized parameters with unified dimensions through a preset motor industry standard terminology mapping table, and construct a standardized parameter table; Matrixing the standardized parameter table to form a multidimensional feature matrix, wherein each row of the matrix represents a motor model and each column corresponds to a standardized parameter feature; constructing a data query library, and importing the multidimensional feature matrix into the data query library to obtain a distributed data query library; Expanding the dimension of the standardized feature vector to make it consistent with the column dimension of the multidimensional feature matrix to form a query vector matrix; Compare the query vector with each row in the feature matrix row by row, and calculate the Euclidean distance between the two in each feature dimension; if the Euclidean distance of a row is less than the preset distance threshold, mark the motor model in the corresponding row as a candidate model; Prioritize the marked candidate model set and arrange them from small to large according to the Euclidean distance to generate the final candidate motor model set; During the entire process, if the candidate motor model set is empty, the preset distance threshold is automatically adjusted or the user is prompted to re-enter the selection benchmark parameters.

4. A motor selection method according to claim 1, characterized in that: Obtain the comprehensive performance score of each candidate motor model, trigger the model elimination mechanism based on the preset score value threshold, and sort the performance parameters of the retained candidate motor models to generate a set of preferred motor models, specifically: Extract key performance parameters of each model from the candidate motor model set, including rated power curves, efficiency distribution maps, and temperature rise characteristic data, and construct a three-dimensional performance matrix as a benchmark data source for multi-dimensional parameter comparison; Automatically allocate torque response coefficient, energy efficiency priority factor, and environmental adaptation weight based on the application scenario characteristics input by the user to form a dynamic weight allocation rule. If the scenario characteristics are not clear, the default weight allocation mode is enabled and logged. Based on dynamic weighting rules, each parameter in the three-dimensional performance matrix is ​​weighted and calculated to generate a comprehensive performance score for each candidate motor model; the comprehensive performance score of each candidate motor model is compared with a preset score threshold; If the comprehensive performance score of a candidate motor model is less than the preset score threshold, the model elimination mechanism is triggered to eliminate the candidate motor model from the candidate motor model set; Sort the retained candidate models by their comprehensive performance scores from highest to lowest to generate a set of preferred motor models; Among them, if the score values ​​are the same, a secondary sorting is performed according to the energy efficiency priority factor to ensure the uniqueness of the sorting result, and the preferred sequence is used as the input data for the load characteristic matching verification in the next stage.

5. A motor selection method according to claim 1, characterized in that: Obtain the comprehensive energy efficiency score of each preferred motor model and establish a Pareto front solution set for secondary screening to obtain a set of recommended motor models, specifically: Acquire rated operating condition data of each preferred motor model, and extract efficiency distribution characteristics of each preferred motor model at different load points based on the rated operating condition data; Based on the energy efficiency priority parameters entered by the user, the efficiency weight coefficient is dynamically assigned. Combined with the efficiency distribution characteristics of each preferred motor model at different load points, the comprehensive energy efficiency score of each preferred motor model is calculated. If the comprehensive energy efficiency score of a preferred motor model falls below the preset score threshold, the model downgrade mechanism is triggered and the model is removed from the preferred queue. A multi-objective particle swarm optimization algorithm is used to establish the Pareto frontier solution set for each preferred motor model, with comprehensive energy efficiency score, power density, and temperature rise characteristics as optimization targets. If the number of Pareto frontier solution sets exceeds the preset upper limit, a fuzzy comprehensive evaluation method is introduced to perform a secondary screening of the solution set until the number of Pareto frontier solution sets falls below the preset upper limit. Subsequently, the embedded simulation engine is called to perform a virtual working condition loading test on each preferred motor model according to the Pareto front solution set of each preferred motor model to obtain the simulated energy efficiency degradation curve of each preferred motor model; Comparing the simulated energy efficiency attenuation curve of each preferred motor model with the preset energy efficiency attenuation curve to obtain the degree of overlap between the simulated energy efficiency attenuation curve of each preferred motor model and the preset energy efficiency attenuation curve; If the overlap between the simulated energy efficiency attenuation curve of a preferred motor model and the preset energy efficiency attenuation curve is no greater than the preset overlap, the model downgrade mechanism is triggered and the model is removed from the preferred queue; The remaining preferred motor models in the preferred motor model set are obtained to obtain a recommended motor model set.

6. A motor selection method according to claim 5, characterized in that: A multi-objective particle swarm optimization algorithm is used to establish the Pareto frontier solution set of each preferred motor model with comprehensive energy efficiency score, power density and temperature rise characteristics as optimization targets. Specifically, Initialize the particle swarm, use the comprehensive energy efficiency score, power density, and temperature rise characteristics of each preferred motor model as the three-dimensional target vector of the particle, and randomly assign the initial position and speed; Calculate the fitness value of each particle and construct the initial Pareto solution set; if the number of solution sets is zero, adjust the target weight coefficient and recalculate the fitness value; Execute the particle position update algorithm to dynamically adjust the particle trajectory based on the individual optimal solution and the global optimal solution; if it is detected that the particle is trapped in the local optimum, a mutation operation is introduced to randomly perturb the particle position to jump out of the local extreme value; The updated particles are classified using the non-dominated sorting method to screen out new Pareto solution sets. If the number of solution sets exceeds the preset upper limit, the congestion calculation is started to prioritize the evenly distributed solutions. At the same time, a solution set convergence judgment mechanism is established. If the number of consecutive iterations exceeds the threshold and the solution set change rate is lower than the preset value, the algorithm is judged to have converged; if it has not converged, iterative optimization will continue; Finally, the final Pareto front solution set is output, and the motor model and key parameters corresponding to each solution are marked.

7. A motor selection method according to claim 5, characterized in that: If the number of Pareto frontier solution sets exceeds the preset upper limit, the fuzzy comprehensive evaluation method is introduced to perform a secondary screening of the solution set until the number of Pareto frontier solution sets is lower than the preset upper limit. Specifically: Extract the comprehensive energy efficiency score, power density and temperature rise characteristic data of each motor model from the Pareto front solution set and construct a multi-dimensional evaluation matrix; Dynamically assign weight coefficients to each evaluation indicator based on the energy efficiency priority parameters input by the user; A fuzzy membership function is established to normalize each evaluation index and eliminate dimensional differences. If uneven distribution of normalized data is detected, the membership function parameters are adjusted. The weighted average method is used to calculate the comprehensive fuzzy evaluation value of each motor model, and the solution set is sorted according to the comprehensive fuzzy evaluation value; Set the upper threshold of the number of solution sets, and eliminate the motor models with the lowest comprehensive fuzzy evaluation values ​​in sequence until the number of motor models after elimination is less than the upper threshold of the number of solution sets; If the number of solutions still exceeds the upper limit after elimination, the elimination standard will be gradually increased until the quantity requirement is met; Finally, the filtered Pareto front solution set is output, and the comprehensive fuzzy evaluation value and key parameters of each model are marked.

8. A motor selection method according to claim 1, characterized in that: The recommended motor models are divided into multiple motor selection levels, specifically: Extract the comprehensive energy efficiency scores, cost-effectiveness indexes, and compatibility parameters of all models in the recommended motor model set and construct a three-dimensional classification feature matrix; Based on the core performance threshold set by the user, a set of models with comprehensive energy efficiency scores higher than the benchmark value and compatibility that meets the standards are screened out and marked as the primary recommended candidate set; If the candidate set is empty, the threshold range is automatically relaxed and the adjustment parameters are recorded; Perform an economic analysis on the remaining models, calculate the full life cycle cost-benefit ratio, and select models with a cost-benefit ratio below the industry average and compatibility parameters within the allowable range. These models are classified as economic alternatives. If missing cost data is detected, the historical procurement database is used to fill in the alternative values. For models that are not selected as the primary recommended models and economic alternative models above, extended compatibility verification will be carried out, and the models that pass the extended compatibility verification will be regarded as extended compatible models.

9. The motor selection method according to claim 1, characterized in that: The selection benchmark parameters include full load gross weight, full load speed, full load acceleration, travel wheel / drum diameter, energy efficiency level requirements, three-dimensional size restrictions of installation space, energy efficiency priority parameters, ambient temperature and humidity gradient parameters, protection level code, expected life index and application scenario characteristics.

10. A motor selection system, characterized in that: The motor selection system includes a memory and a processor. The memory stores a motor selection method program. When the motor selection method program is executed by the processor, the steps of the motor selection method according to any one of claims 1 to 9 are implemented.

Images