CN-121998162-A - Building material handling optimizing system for multi-type unmanned forklift

CN121998162ACN 121998162 ACN121998162 ACN 121998162ACN-121998162-A

Abstract

The invention discloses a building material handling optimization system for a multi-type unmanned forklift, relates to the technical field of data processing, and solves the problems that safety and efficiency are difficult to balance and faults are difficult to position in building material handling. The system comprises a data acquisition preprocessing module, a parameter calculation module, a primary speed regulation module, a dynamic speed regulation module, an iterative optimization module, a fault diagnosis module and a fault diagnosis module, wherein the data acquisition preprocessing module acquires and preprocesses multi-dimensional data of a forklift and outputs standardized transportation data, the parameter calculation module calculates dumping indexes, efficiency indexes and balance factors based on the data, the primary speed regulation module judges risk types according to the dumping indexes and combines the balance factors to execute primary speed regulation, the dynamic speed regulation module updates parameters and maps the balance factors, calculates target speed regulation values according to the risk types, the dynamic regulation strategy is used for iteration optimization module updates the parameters to generate candidate speed regulation populations, the optimal speed regulation parameters are screened through cross variation, and the fault diagnosis module is used for constructing fault feature vectors based on speed regulation historical data to diagnose road surface problems or forklift faults. The system has the advantages of dynamic balance, safety and efficiency, accurate fault diagnosis, adaptation to multi-type unmanned forklift transportation and improvement of transportation reliability and efficiency.

Inventors

CHEN GANG
WANG JINGXIONG
YU FANGGANG
JI FEI
ZHANG RUOHAO
CAI GUOJUN
LI LEI
MEI JIANGTAO
XU XIAOHUI
XIAO HAN
YUAN CHENG
MA HUAIZHANG
BAO HAN
QUAN YOUWEI

Assignees

南京中建八局智慧科技有限公司
中建八局第三建设有限公司

Dates

Publication Date: 20260508
Application Date: 20251218

Claims (10)

1. A multi-type unmanned transport forklift-oriented building material handling optimization system, comprising: The data acquisition preprocessing module is used for acquiring and preprocessing multidimensional data of the unmanned transport forklift and outputting standardized transport data; The primary speed regulation module judges the risk type based on the dumping index and a preset threshold value, and executes primary speed regulation by combining the balance factor; The dynamic speed regulation module is used for collecting data updating parameters again, mapping balance factors to a preset interval, calculating a target speed regulation value by combining a risk type, and dynamically regulating a speed regulation strategy; the iterative optimization module is used for updating parameters based on real-time data, generating a candidate speed regulation value population, and iteratively screening optimized speed regulation parameters with highest fitness through cross variation; The fault diagnosis module is used for constructing a fault feature vector based on historical data in the speed regulation process, and diagnosing the fault type as a road surface problem or the self fault of the unmanned forklift.
2. The building material handling optimization system for the multi-type unmanned forklift truck according to claim 1, wherein the multi-dimensional data collected by the data collection preprocessing module comprises real-time speed, load, inclination angle and vibration data of the unmanned forklift truck, data cleaning, normalization, outlier rejection and feature extraction preprocessing are performed, average speed, maximum inclination angle and vibration standard deviation are obtained through feature extraction, and standardized transportation data are output by combining the preprocessed multi-dimensional data.
3. The system for optimizing the handling of building materials for multi-type unmanned forklift trucks of claim 1, wherein said parameter calculation module extracts center of gravity offset, tilt angle and vibration amplitude from the transportation data, assigns preset weights to each parameter and sums them up by weight to obtain a dumping index.
4. The system for optimizing the handling of building materials for multi-type unmanned forklift trucks of claim 1, wherein said parameter calculation module extracts average speed, energy consumption and task completion time from the transportation data, calculates the ratio of average speed to energy consumption, and calculates the logarithm of the reciprocal of task completion time plus 1, which are multiplied to obtain the efficiency index.
5. The system for optimizing the handling of building materials for multi-type unmanned transport forklifts of claim 1, wherein the parameter calculation module retrieves dynamic adjustment coefficients from historical transport data, calculates a ratio of the dumping index to the efficiency index, and multiplies the adjustment coefficients to obtain the balance factor.
6. The system for optimizing the handling of building materials for multi-type unmanned forklift trucks according to claim 1, wherein said primary speed regulation module presets low risk and high risk thresholds, compares the dumping index with the thresholds to determine the low, medium and high risk types, and performs primary speed regulation in combination with balancing factors, i.e. low risk to maintain the original speed, medium risk to slow down, and high risk to stop.
7. The building material handling optimization system for the multi-type unmanned forklift truck according to claim 1, wherein the dynamic speed regulation module is used for collecting transportation data again to update relevant parameters, mapping balance factors to preset intervals, presetting speed regulation references corresponding to three types of risks, calculating target speed regulation values by combining boundary values and proportion coefficients of the balance factor intervals, setting efficiency preset requirements and dumping index safety intervals, executing speed increasing, further speed reducing or emergency braking operation according to whether the efficiency reaches the safety intervals or not, and calculating the balance factors again for iterative execution when the efficiency requirements are not met.
8. The building material handling optimization system for the multi-type unmanned forklift truck according to claim 1, wherein the iterative optimization module collects real-time transportation data update related parameters, builds Gaussian distribution by taking a current target speed regulation value as a mean value and a preset standard deviation, randomly generates an initial candidate speed regulation value population, and obtains the fitness of each candidate value by calculating the sum of the related reciprocal of the difference between a balance factor and a target reference value and the efficiency index weighted value.
9. The system for optimizing the handling of building materials for multi-type unmanned forklift trucks according to claim 1, wherein the iterative optimization module performs single-point crossover (crossover rate decreases with iteration number) and gaussian variation (mutation rate decreases with iteration progress) operations on an initial population, calculates fitness and reserves optimal candidate value iteration, outputs optimal speed regulation parameters when a termination condition is met, controls forklift truck operation and updates parameters, and maintains current parameters when reaching standards.
10. The building material handling optimization system for the multi-type unmanned forklift truck according to claim 1, wherein the fault diagnosis module extracts fault related data from historical data to construct fault feature vectors, distributes preset weights for each dimension, inputs a pre-training random forest model, outputs road problems and the probability of the forklift truck self faults, and triggers corresponding alarms and records fault information when the probability exceeds a preset threshold.

Description

Building material handling optimizing system for multi-type unmanned forklift Technical Field The invention relates to the technical field of data processing, in particular to a building material handling optimization system for a multi-type unmanned forklift. Background Along with the rapid development of building industrialization and storage logistics intelligence, unmanned transportation forklifts have become core equipment for building material transportation and storage cargo transportation by virtue of automation and high efficiency. In order to solve the safety and efficiency problems in the transportation process, the prior art has carried out many attempts, but the prior art still has obvious defects in deep excavation and comprehensive utilization of the inclination-related indexes, which are specifically expressed in the following aspects: In the Chinese patent with the patent number of CN119706685B, a method and a system for intelligently and cooperatively dispatching a transport forklift for warehouse management are disclosed, wherein vibration amplitude and frequency are acquired through a sensor Fang Zhendong under a fork arm, a dumping risk index TRI is calculated by combining the relative height of the centroid of an object, a constraint function is constructed based on the TRI and the running state (speed, acceleration and the like) of the forklift, and the state of the individual forklift is optimized by adopting a genetic algorithm. However, the patent only uses the dumping risk index as a safety constraint condition, the dumping risk index and the transportation efficiency index (such as actual transportation progress and unit energy consumption) are not subjected to coupling calculation, the safety redundancy and the transportation efficiency cannot be dynamically balanced based on the tilting related index, the application of the TRI is limited to the optimization of individual forklift parameters, the TRI does not extend to a fault diagnosis link, and road bump and forklift self faults cannot be distinguished through the variation trend of the TRI. In chinese patent CN120876602a, an external vision system for forklift operation is proposed, which obtains a cargo mask through a split network, calculates a cargo tilt angle based on a mask geometric feature, and triggers a forced deceleration command when the tilt angle is greater than 10 °. However, the inclination angle in the patent is only used as a single basis for risk alarm, a differential speed regulation strategy is not formulated for different areas of the inclination angle, a balance factor is not built by associating the inclination angle with an efficiency index (such as task completion time), application fragmentation of inclination related data only stays on an early warning level, a closed loop system of index calculation-parameter optimization-state feedback is not integrated, and dynamic load scenes are difficult to adapt. In the chinese patent with the patent number CN115129068B, the disclosed intelligent positioning navigation system based on the AGV forklift mainly performs path adjustment and obstacle avoidance optimization around the transverse occupied area and the path overlapping ratio of the obstacles, and obtains the weight of the goods through the weighing device to calculate the transportation power value so as to adjust the speed, but the patent does not relate to calculation and application of any inclination related index (such as centroid deviation angle and inclination risk index), and the scheduling strategy is formulated completely depending on parameters such as weight, path and the like, so that the potential inclination risk caused by the goods inclination cannot be identified, and potential safety hazards exist under the conditions of irregular goods stacking or road inclination. In chinese patent No. CN116449853B, a path planning method for a forklift type AGV is proposed, in which the centroid offset angle of a moving polygon is calculated to obtain the overall offset degree, and the concentration of a path pheromone is adjusted in combination with the scattered degree. However, the patent only uses the centroid offset angle for path risk assessment, does not construct a multi-objective decision model in a coupling way with an efficiency index (such as the traffic in unit time), does not utilize inclination related historical data for fault tracing, only determines an influence range by matching the current scattered degree with a historical image, cannot judge whether a fault is caused by uneven road surface or a fork truck suspension system fault according to the change amplitude of the inclination angle, and has limited fault diagnosis accuracy. In addition, in the prior art, the speed regulation optimization depends on a fixed threshold or a single parameter, and in the above patent, the early warning is triggered only based on the weight adjustment speed or only based on the inclination a