337 results about "Signal timing" patented technology

The invention belongs to the technical field of intelligent traffic systems, and particularly relates to an intersection signal timing dynamic coordination system and method based on real-time traffic prediction.The method comprises the steps of collecting multi-source traffic data, generating a space-time prediction digital twin model, dynamically defining an intersection coordination cluster and executing cluster coordination optimization control. And signal timing and closed loop feedback are carried out. By adopting the technical scheme, the cooperative operation efficiency and the intelligent management level of the urban intersection group can be effectively improved, and the fundamental conversion from local and reactive active cooperative control to global and predictive active cooperative control is realized.

The invention discloses a multi-modal traffic large model real-time regulation and control method and system for vehicle-road cooperation, and relates to the technical field of artificial intelligence, and the method comprises the steps: combining multi-modal data fusion, edge intelligent reasoning, federated learning, cross-regional knowledge migration, reinforcement learning optimization and adaptive closed loop iteration; and efficient and accurate vehicle-road cooperative regulation and control are realized. The model is adopted to perform space-time alignment and high-dimensional feature extraction on vehicle-mounted, roadside and cloud data, so that the environmental perception precision is improved; cross-regional traffic knowledge sharing is realized through gradient aggregation and decentralized training, and data privacy leakage is avoided; a transfer learning and self-supervision mechanism is adopted, so that the model can quickly adapt to different cities and different road environments, and the generalization ability is improved; by adopting cloud multi-agent reinforcement learning, the optimal decision of signal lamp timing and path recommendation is realized, the traffic flow change is dynamically adapted, and the problem that efficient and real-time model adjustment cannot be realized in consideration of privacy and global optimization in the prior art is solved.

The invention aims to provide a large-range urban road network intelligent management and control method based on mobile phone signaling data, and belongs to the technical field of traffic management and control. Real-time traffic flow parameters are obtained by preprocessing the mobile phone signaling data, a high-fidelity microscopic traffic simulation environment is constructed, and on the basis, the real-time traffic flow parameters are obtained; the method comprises the following steps: establishing a multi-dimensional evaluation index system containing operation safety and efficiency, constructing a macro-micro collaborative double-layer planning model, adopting a deep reinforcement learning algorithm, taking continuous-discrete mixed decision variables such as intersection signal timing and a variable lane strategy as optimization objects, carrying out strategy learning and iterative optimization through an Actor-Critic architecture, and carrying out optimization on the optimization objects. And outputting the optimal control strategy combination. According to the invention, dynamic and accurate cooperative management and control of the large-range urban road network are realized, and the traffic efficiency is remarkably improved while the operation safety is guaranteed.

The invention discloses a traffic control and guidance system and method based on an ant colony algorithm, belongs to the technical field of road traffic control, and solves the problems that a neural network model in an existing method mainly focuses on respective route conditions of a plurality of bifurcation routes of a bifurcation on a one-way driving road, and the information fusion degree between traffic elements is low. The method comprises the following steps: identifying dynamic characteristic information of vehicles in a road network, pre-constructing a road network optimization model based on an ant colony algorithm combined with deep learning, and analyzing a pheromone spread function cluster solution; according to the invention, the road network optimization model based on the ant colony algorithm and the deep learning is pre-constructed, the collaborative optimization of traffic signal control and vehicle induction is realized, the traffic signal optimization control strategy and the vehicle optimization path strategy are output, so that the signal timing and the induction path can be matched with each other, and the control accuracy is improved. Therefore, the operation efficiency of the traffic system is improved and the accuracy and effectiveness of the guidance strategy are ensured.

The invention relates to the technical field of machine learning, in particular to a cooling pump optimization algorithm of a central air-conditioning water chilling unit based on a knowledge graph, which comprises the following steps of: acquiring an alignment relationship between a pump start-stop signal and current response time, extracting an action section and a path node sequence to construct a logic sequence, and identifying control signal alternation and direction deviation to extract a path limit number, and screening response delay and a load fluctuation section to correspondingly adjust an identification area. According to the method, behavior mapping between the pump action and the signal time sequence is constructed, alternating signals and direction deviation fragments in a control chain are extracted, a path limiting identifier is generated to be used for restraining control interference, a trigger area is regulated and controlled in combination with matching of load response and an equipment action section, and an accessible path is screened to replace a limited section; the path structure is recombined, instruction chains are sorted, the matching capability of path scheduling and the response collaboration of linkage nodes are enhanced, and the control process is promoted to be kept continuous and stable in a differentiated state.

The invention provides a traffic corridor signal cooperative control method based on single agent reinforcement learning, and relates to the technical field of traffic management and control, and the control method comprises the steps: obtaining the real-time traffic state data of a traffic corridor comprising a plurality of signal intersections; acquiring a current signal control scheme of the traffic corridor; constructing a state vector according to the real-time traffic state data and the current signal control scheme; inputting the state vector into a pre-trained single-agent reinforcement learning model to obtain a corresponding action vector; based on the action vectors, phase division of all the signal intersections is synchronously adjusted, and a new signal control scheme is generated; according to the invention, signal timing of all signal intersections in a traffic corridor is cooperatively controlled by adopting a centralized single-agent architecture, so that the problems of system complexity and training instability caused by local observation, distributed decision and communication coordination among agents in a multi-agent scheme are fundamentally avoided.

The invention relates to the technical field of large models, in particular to an urban intelligent collaborative decision-making system and method based on a large model, and the system comprises a multi-source heterogeneous data fusion perception layer, a deep learning cognitive engine, a self-adaptive regulation and control decision-making layer and a system efficiency optimization and safety guarantee system. The method has the advantages that multi-modal data of a traffic camera, a geomagnetic sensor, a vehicle-mounted terminal and the like are integrated, space-time correlation characteristics are extracted by using a multi-layer attention mechanism of a large model, and traffic flow prediction and signal timing optimization linkage regulation and control are realized in combination with an incremental learning algorithm. Compared with the prior art, the platform solves the problems that a traditional method is poor in dynamic adaptability to a complex road network and low in prediction precision, the passing efficiency of the urban road network can be improved by 15%-22%, and the abnormal congestion response time is shortened to be within 3 minutes.

The invention discloses an intelligent traffic regulation and control method and system for cities, relates to the technical field of intelligent traffic, and realizes high-precision real-time sensing of complex traffic states of urban intersections by constructing a multi-source traffic data acquisition system. A multi-modal feature fusion and semantic tag matching mechanism is adopted to recognize overlapping and dynamic changes of traffic states, a multi-strategy linkage signal timing scheme is generated in time, and the problems that a traditional signal control system is lagged in response and single in state recognition are solved. According to the method, commuting and logistics interference indexes are introduced, a release sequence adjustment and channel optimization strategy is intelligently generated according to a people flow peak and logistics concurrence situation, and the method aims at solving the problem of intersection signal timing regulation and control under the condition of complex multi-mode traffic flow superposition. And meanwhile, an execution result is collected in a closed-loop manner, a strategy deviation value is calculated in real time, error tolerance is set, adaptive iterative optimization is supported, and stable convergence of the strategy and achievement of a regulation target are ensured.

The invention discloses a traffic drainage signal management method and system based on a Beidou system, and relates to the technical field of Beidou satellite navigation, and the method comprises the steps: obtaining the real-time traffic data of the position and speed of a vehicle at each intersection based on the Beidou system, and transmitting the real-time traffic data to a traffic management platform; carrying out feature matching on the accident identification model trained based on historical emergency data and a deep learning algorithm and real-time traffic data, and identifying an emergency; and constructing a real-time traffic situation map in combination with the identified emergency information and the traffic condition information of the intersections. The vehicle position and speed data are obtained in real time through the Beidou system, emergencies are rapidly recognized and signal lamp timing is dynamically adjusted in combination with a deep learning algorithm, and compared with a traditional fixed timing scheme, traffic flow changes can be responded in real time, frequent start and stop of vehicles are reduced, the road passing efficiency is improved, and the traffic safety is improved. And particularly, in a sudden traffic accident or construction scene, a signal strategy can be quickly optimized, and traffic congestion aggravation is avoided.

The invention provides an urban traffic dynamic deduction and real-time planning method and system based on multi-source position data fusion. Time-space references of signaling, MDT and MR data are unified through a dynamic rasterization mechanism, and the problem of data isomerism is solved by adopting anchor point selection of signal weighting and a triple criterion time expansion algorithm; generating a minute-level updated dynamic OD matrix based on the hierarchical road network constraint model; a METANET macroscopic traffic flow model and EKF extended Kalman filtering are fused to realize traffic state deduction, and parameter online calibration is supported; signal timing optimization, path induction and emergency control schemes are generated in combination with real-time deduction results, and a sensing-deduction-decision-evaluation closed loop is formed. The method can improve road network traffic efficiency, and is especially suitable for response of sudden traffic events.

The invention relates to the technical field of motion control, in particular to a stepping motor monitoring control method and system, and the method comprises the following steps: obtaining a target and feedback signal rising edge sequence, analyzing a periodic change direction, judging a time migration trend, extracting a voltage and current response section, recognizing a disturbance time slice, and positioning high and low level boundaries. And screening signals with consistent frequency, extracting a running rhythm time sequence, and comparing a rhythm sequence to obtain a monitoring control behavior. According to the method, the time sequence of rising edges of a target and a feedback signal is compared, the displacement deviation trend is judged in combination with the periodic change direction, an interference section is identified by utilizing voltage abrupt change and current fluctuation characteristics, a control boundary is delimited according to the distribution of the interference section in high and low levels, and signal segments with consistent frequency characteristics are extracted to construct an operation rhythm. The driving behavior is extracted in combination with the signal time sequence and the rhythm sequence, the responsiveness to rhythm change is enhanced, and the problems of interference fluctuation and control rhythm disjunction caused by rhythm dislocation are relieved.

The invention relates to the technical field of a power distribution network of a power system, in particular to a fault prediction self-healing power distribution method, which comprises the following steps of: firstly, acquiring equivalent admittance and physical residual by controlled disturbance and synchronous phasor measurement, generating a spectrum-topology co-embedded coordinate and an innovation consistency index, and finishing topology check; fusing the space evidence, the time evidence and the physical evidence, and combining hazard rate evaluation to form a control admission intensity value; executing offset search under the constraint of feasible region prior, action shielding and control barrier, and performing power flow optimization by taking a condition in-danger value as a target to obtain a self-healing operation sequence; and finally, the operation threshold is shaped according to the anti-fact energy margin, complete sequence checking is completed according to the signal sequential logic and the satisfiability model theory, an execution packet is generated, low misoperation is achieved, and safety and rapid recovery can be proved.

The invention relates to an automatic parallel traffic simulation analysis method and device. The method comprises the following steps: in response to a received region delimiting instruction, generating an initial digital road network from a map data source, and executing topology calibration and connectivity repair operation on the initial digital road network to generate a digital road network file; generating structured traffic demand data based on the input of the user; generating a basic traffic scene file based on the digital road network file and the traffic demand data, and forming a traffic simulation operation scene based on the configuration of the basic traffic scene file by a user; generating a plurality of signal timing schemes based on the traffic simulation operation scene; and executing traffic simulation based on the plurality of signal timing schemes, analyzing a simulation result to obtain a multi-level key performance index, performing visual comparison on the multi-level key performance index, and generating a natural language evaluation report by using a large language model. Therefore, simulation efficiency, usability and scene construction flexibility can be remarkably improved.

A system includes a processor that is configured to acquire traffic video, analyze the acquired traffic video to determine traffic conditions, and optimize traffic signal timing based on the traffic conditions, and apply the optimized signal timing to a traffic signal.

The invention relates to a low-altitude unmanned aerial vehicle assisted peak period urban intersection coordination control system and method, and belongs to the field of traffic control. The system comprises an equipment deployment layer, a sensing layer, a decision-making layer and a control layer. Based on infrastructures deployed by the equipment deployment layer, the unmanned aerial vehicle cruises, shoots and preliminarily analyzes an image, and transmits structured data to the edge computing equipment; the sensing layer determines intersection state information and transmits the intersection state information to the decision-making layer, and the decision-making layer generates a signal timing strategy and a regional scheduling scheme; and the control layer controls the signal lamp according to the information and feeds back an execution result, and the system can perform self-adaptive optimization and early warning. The method comprises the steps that the unmanned aerial vehicle acquires and processes an image, transmits data to a decision-making layer to optimize timing, issues a strategy to the signal lamp controller and feeds back an execution effect. According to the scheme, the sensing range and precision can be enhanced, the communication load is reduced, the signal timing is optimized, multi-intersection collaboration is supported, a closed-loop control system is constructed, deployment is flexible, and adaptability is high.

The invention relates to the technical field of traffic planning, in particular to a road congestion shunting system suitable for urban design, which comprises a node congestion identification module, a signal time sequence adjustment module, a path interference screening module, a signal priority ordering module and a linkage time period correction module. According to the method, a multi-direction traffic pressure concentration area is formed through path overlapping structure identification, an association boundary of a path group and a node state is opened, a green light starting time sequence is adjusted in combination with a column head static continuous behavior, a vehicle response and period synchronization relation is reconstructed, and structural proximity judgment is introduced in path conflict screening. High-interference paragraphs are identified by utilizing the correlation degree of guidance, speed and lane parameters, a node sorting mechanism dynamically generates priorities through the consistency of a frequent path and a queuing trend, real-time refreshing of a signal response sequence is realized, linkage rhythm correction is bidirectionally verified according to release delay and an adjacent node blocking state, a starting segment is dynamically adjusted, and the linkage rhythm is corrected. Chained dislocation is avoided.

The invention provides a ramp traffic signal adaptive control method and system based on unmanned aerial vehicle cooperation, and belongs to the technical field of intelligent traffic control, and the method comprises the steps: collecting traffic data in real time based on an unmanned aerial vehicle cluster dynamically deployed over a ramp, constructing a global traffic state matrix, and carrying out the initial processing through edge calculation; carrying out edge calculation on the primarily processed data by utilizing an edge node to generate a local optimal signal timing suggestion in real time; the local optimal signal timing suggestions uploaded by the multiple unmanned aerial vehicles are integrated at the cloud, and a global optimal signal timing strategy is generated through unified training; signal lamp parameters are adjusted in real time on the basis of a global optimal signal timing strategy, the direct intervention capability on site traffic is enhanced through an air guiding function, and a high-reliability solution is provided for an intelligent traffic system.

The invention relates to the technical field of vehicles, in particular to a collaborative decision-making system and method under mixed traffic flow, a vehicle and a storage medium, and the method comprises the steps: obtaining the traffic environment information under the mixed traffic flow in a target range through a roadside sensing unit, and calculating the behavior intention probability of a manual driving vehicle through a preset intention prediction model; a vehicle end decision-making unit is utilized to construct, adjust and expand a perception domain based on traffic environment information and behavior intention probability in combination with vehicle-mounted sensor data, generate a risk constraint trajectory and a collaborative decision of the vehicle, and re-plan a driving path of the vehicle; and the cloud optimization unit is used for updating a preset intention prediction model, receiving traffic environment information, reconstructing an area-level traffic situation under mixed traffic flow, and transmitting optimized signal timing and formation parameters to the road side sensing unit and the vehicle end decision-making unit. Therefore, the problems of single adaptability of a traffic collaborative decision-making scene, no fusion of real-time road side data and the like in related technologies are solved.

The invention relates to the field of traffic planning, and discloses an urban road network multi-path coordination control method and system considering multi-dimensional dynamic characteristics, and the method comprises the steps: obtaining the traffic flow data, congestion indexes and bidirectional green wave bandwidth difference data of each path in a road network at an intersection; calculating the multi-dimensional dynamic weight of each path at the intersection according to the traffic flow data, the congestion index and the bidirectional green wave bandwidth difference data; constructing a target function by taking the maximum weighted green wave bandwidth sum as a target, and embedding a multi-dimensional dynamic weight into the target function; constructing a collaborative optimization system comprising a high-weight path guarantee constraint, a dynamic adaptability constraint and an auxiliary constraint; and solving an optimal signal timing parameter based on the objective function and the collaborative optimization system, and generating a multi-path coordination control scheme. According to the method, through high-weight path guarantee constraint, dynamic adaptability constraint, flexible breakpoint constraint and the like, the length of a green wave band is increased, and the continuity of green waves and the anti-interference capability of a road network are improved.

The invention discloses a traffic signal control method and system based on multi-source event and double-loop phase cooperation, and relates to the technical field of traffic signal control, a road intersection mathematical model is constructed, a double-loop phase structure is set, and multi-source sensing data is collected in real time; based on the multi-source sensing data, modeling an intersection traffic signal control problem by adopting a deep Q network model, defining a state space, an action space and a reward function, decomposing a double-ring phase structure, and performing cooperative control by a plurality of agents; the reward function is constructed based on a vehicle delay time difference, a waiting time difference, a parking frequency difference and a queuing length difference; the intelligent agents are controlled to execute actions based on rewards fed back to the intelligent agents by the environment, phase keeping or phase switching is determined, an optimal phase scheme of signal control is obtained, timestamp driving, multi-event coupling analysis and a double-ring phase structure are fused, and intersection signal timing optimization is achieved in combination with a deep reinforcement learning algorithm.

The invention provides a multi-scene-oriented intelligent rail signal timing optimization method and device, and relates to the technical field of intelligent public transportation, and the method comprises the steps: building a basic signal model according to the total number of current arriving vehicles and a signal constraint condition, and carrying out the calculation of each lane operation scene, and obtaining the optimal period duration; calculating the priority buffer time according to the parameters of the lane operation scene and the geometric parameters of the intelligent rail, and constructing the unified period duration through the priority buffer time and the optimal period duration; inputting the unified period duration into the basic signal optimization model, and respectively solving each lane operation scene to generate a signal timing scheme; optimizing signal timing in the remaining time of the current period based on the signal timing scheme to obtain a transition scheme; and performing signal timing switching on the signal timing scheme of the current scene according to the transition scheme to obtain a signal timing result. According to the invention, the problem that the signal timing scheme cannot be smoothly switched in a complex traffic scene is solved.

The invention discloses an intelligent traffic management method based on traffic flow adjustment, and relates to the field of intelligent traffic management. Constructing a backtracking and predicting window through the vehicle density and the vehicle flow, dividing a traffic flow interval of the backtracking window based on a vehicle density first-order derivative and a threshold value, and calculating to obtain a global congestion wave velocity; constructing a directed graph and calculating to obtain a congestion wave arrival time; a standardized phase value is obtained by dividing a phase interval, defining a signal phase function and combining a phase offset, a green light core passing time period is determined, and a resonance index is obtained through calculation; when the resonance index is lower than a threshold value, phase deviation, green light duration and a signal period are adjusted in a layered mode, and a timing scheme is optimized through parameter adjustment. According to the scheme, accurate recognition of the congestion state, congestion wave propagation prediction and dynamic optimization of signal timing are realized, and the traffic efficiency of a road network is improved.

The invention discloses an intersection signal control method based on minimum blocking probability and highest traffic capacity, and relates to the technical field of intelligent traffic systems. A bilevel planning optimization model is constructed, an upper layer model takes minimization of intersection blocking probability as a core target, a blocking probability function is established through dynamic quantification of traffic flow random volatility, and a sequential quadratic programming algorithm is fused to optimize a signal period and effective green light time parameters of each phase; the lower layer model is based on a Webster delay model, and feeds back the traffic state in real time by taking the minimization of the total delay of the vehicle as a target. The upper layer model and the lower layer model realize collaborative optimization through a closed loop mechanism of parameter adjustment-delay feedback-iterative optimization, and meanwhile, a dynamic weight coefficient is introduced to flexibly coordinate multi-target conflicts of the blocking probability, delay and traffic capacity. According to the method, the dynamic response capability of signal timing to the real-time traffic demand is remarkably improved, the peak delay of the intersection is effectively reduced by 20%, the average peak delay is effectively reduced by 15%, and the road network toughness is enhanced.

The invention belongs to the technical field of traffic flow green wave control, and particularly relates to a green wave control method based on traffic flow prediction driving. The method comprises the following steps: acquiring multi-dimensional real-time data in a distributed manner; performing abnormal value detection and data interpolation based on space-time neighborhood analysis to generate high-quality time sequence traffic flow data; modeling a road network into a dynamic graph fusing static connectivity and real-time traffic flow coupling degree, and constructing a double-time-scale time sequence diagram sequence; inputting an improved space-time diagram neural network, extracting time features by optimizing Bi-GRU, capturing spatial association by a multi-head attention mechanism, and outputting an accurate road section-level traffic flow prediction result through residual fusion; and finally, constructing a multi-objective optimization model based on prediction, solving by using an improved multi-objective particle swarm algorithm, obtaining a signal timing scheme, and issuing and executing the signal timing scheme. The method can dynamically adapt to traffic changes, improves the traffic efficiency, and avoids green wave failure and congestion.

The invention relates to the technical field of vehicle lamp testing, in particular to a vehicle lamp full-function automatic testing method and system, a storage medium and electronic equipment. The full-function automatic test method for the vehicle lamp comprises four steps of test configuration, test execution, diagnostic function test and test report generation, and the test configuration selects a test type through an upper computer developed by Python and configures a corresponding project file path; the test execution respectively executes a hard wire function test, a bus function test and a diagnosis function test; and test report generation: a test result, an oscilloscope screenshot and analysis data are stored in a structured report, and the test report is directly viewed or exported through an upper computer. The method covers a hard wire function test, a bus function test and a diagnosis function test, can perform comprehensive detection on electrical performance, signal time sequence, fault diagnosis and the like of the vehicle lamp module, and avoids the problems of tedious process and low efficiency of a traditional manual test.

The present invention provides a compensation method for a silicon resonant pressure sensor, which relates to the technical field of pressure measurement and includes: collecting the frequency signal timing output by the silicon resonant pressure sensor and analyzing to obtain the real-time pressure value; obtaining a predetermined compensation item, collecting multi-dimensional compensation features, and obtaining multi-dimensional compensation information; traversing and screening a historical compensation database with the multi-dimensional compensation information as a screening constraint to obtain a target sensor; normalizing and comparing the pressure value deviation obtained from the detected pressure value of the target sensor and a preset pressure value to obtain a multi-dimensional compensation coefficient; performing compensation adjustment to obtain an effective pressure value. The present invention solves the technical problem that most of the existing compensation methods only adjust for a single influencing factor, ignoring the comprehensive influence of multi-dimensional factors, resulting in the inability to effectively cope with multiple error sources under complex environmental conditions, and further leading to insufficient accuracy and reliability of the silicon resonant pressure sensor.

An AI-based adaptive traffic signal control system (100) for optimizing urban mobility, comprising: (a) a plurality of traffic sensors and cameras configured to collect real-time traffic data at one or more intersections; (b) a preprocessing and data management module to clean and normalize the collected data; (c) a traffic pattern recognition module configured to classify traffic conditions based on real-time and historical traffic data; (d) an AI-based signal timing optimization module that uses reinforcement learning to dynamically determine optimal signal phase sequences and green time assignments; (e) a communication and control execution module configured to transmit and implement the optimized signal timing plans to traffic signal control devices; and (f) a monitoring and system feedback module configured to evaluate traffic performance and provide feedback to the AI-based signal timing optimization module, whereby the system dynamically adjusts traffic signal phase schedules in real time to improve traffic flow and reduce congestion.

The invention relates to the technical field of intelligent traffic, in particular to a traffic signal lamp control method based on vehicle path prediction under vehicle-road cooperation, and the method comprises the steps: collecting the driving path data of each vehicle within a set distance range in front of a designated intersection in real time; predicting the traffic flow of each signal phase of the specified intersection in a set future time period based on the acquired driving path data of the vehicle; the signal phase refers to a time period which is divided according to a passing direction and a passing mode and allows vehicles to pass in a signal period; calculating total vehicle delay time of each signal phase based on the predicted traffic flow, traffic capacity, queuing length and saturation flow rate of each signal phase; dynamically optimizing and adjusting the green light time of each signal phase based on the vehicle total delay time of each signal phase to obtain an optimized green light timing scheme; and issuing the optimized green light timing scheme to a signal controller at a specified intersection in real time so as to execute a corresponding signal timing control action.

The invention provides a bus signal priority control method considering coordination of a phase deviation state, and belongs to the technical field of vehicle-road cooperation. The method comprises the following steps: constructing an end-side-cloud architecture system for an intersection implementing bus signal priority control, acquiring basic data of the intersection and buses, establishing a signal priority control method considering coordination phase deviation state constraint, and calculating the maximum bus signal priority time of the intersection. And signal timing schemes under different priorities are generated in advance according to the priority time, so that the accuracy and the real-time performance of bus priority execution are ensured. According to the invention, a reliable control means for passing without stopping is provided for buses, interference to social vehicle passing benefits is reduced, the coordination offset time is fully utilized, the success rate of bus signal priority control is increased, the riding experience of passengers can be improved, the energy consumption of the buses can be reduced, and the cost is reduced. The method is of great significance to further development of an urban public transport system.

The invention discloses a traffic signal control system based on traffic flow prediction, and relates to the technical field of traffic signal control, and the traffic signal control system comprises an edge calculation unit which is deployed at each intersection and is used for bearing the following modules: a digital twin module which is used for providing data and topological information for a graph transformation flow prediction module; the graph transformation flow prediction module is used for carrying out combined prediction on the vehicle flow and the pedestrian flow of a plurality of adjacent intersections in the future 1-2 minutes through a multi-head self-attention mechanism and position coding; and the local twinborn simulation module is used for simulating short-term congestion, queuing length and average delay effect of various signal timing strategies in a second level by adopting a simulation time step length smaller than or equal to 5s. By designing an edge digital twinning and graph transformation prediction closed loop, short-time multi-intersection flow combined prediction is realized, the problems of high time delay, low prediction precision and single-intersection decision isolation in central cloud computing are solved, the prediction precision and response speed are improved, the communication delay is reduced, and end-side autonomous decision is realized.