Vehicle heterogeneous subsystem-oriented control method, device, equipment and medium

Abstract

The application provides a control method and device for vehicle heterogeneous subsystems, equipment and medium, the method comprising: collecting original signals of the rail vehicle heterogeneous subsystems and performing format conversion and standardization processing to obtain multi-source heterogeneous data; constructing a vehicle environment state matrix based on the multi-source heterogeneous data; the vehicle environment state matrix has rows representing different state subsets and columns representing different vehicle monitoring partitions, and the matrix elements include collection time stamps and data verification identifiers; periodically scanning the vehicle environment state matrix through a preset strategy library, generating standardized control instructions according to the trigger conditions of the pre-stored built-in strategy; the preset strategy library is a regularized linkage strategy library of a layered architecture deployed in a virtualization and containerization architecture; and the standardized control instructions are sent to the actuators of each heterogeneous subsystem through a unified output interface to control the actuators to perform corresponding actions. The scheme improves the slow response speed and meets the demand of integrated intelligent management and control of rail vehicles.

Description

Technical Field

[0001] This application relates to the field of rail vehicle technology, and more specifically, to a control method, device, equipment, and medium for heterogeneous subsystems of vehicles. Background Technology

[0002] The electronic architecture of rail vehicles is at a critical juncture, rapidly evolving from a distributed model to an integrated and standardized one. With the continuous improvement of train intelligence, the number of onboard electronic devices is increasing daily, making the need for data interaction and collaborative control between subsystems increasingly urgent. The rail transit sector has clearly stated that future trains need to build a unified communication architecture to support the mixed transmission of multi-level and multi-type data, and has listed "data-driven" and "functional allocation architecture" as key technological directions for the next-generation train network control system. Related development plans also emphasize promoting the deep integration of train control and vehicle control, advocating the construction of an intensive network platform and intelligent integrated control system to improve the system's intelligence and integration level.

[0003] Currently, many controllers in existing rail vehicles employ a distributed architecture. Each controller communicates with the Central Control Unit (CCU) via the vehicle bus to achieve centralized monitoring and control of the entire vehicle. However, because each subsystem is configured as an independent device, hardware redundancy occurs. Furthermore, since the control logic of each subsystem is fixed within its respective controller, modifying a function or upgrading a strategy requires reconfiguring and verifying the relevant independent devices, impacting engineering efficiency and increasing maintenance complexity. Since different subsystems are typically provided by different suppliers, cross-system joint debugging or emergency strategy changes require multi-party coordination, resulting in high collaboration costs and slow response times, making it difficult to meet the integrated intelligent management and control requirements of rail vehicles. Summary of the Invention

[0004] This application provides a control method, apparatus, device, and medium for heterogeneous vehicle subsystems.

[0005] A first aspect of this application provides a control method for a heterogeneous vehicle subsystem, the method comprising: The raw signals from the heterogeneous subsystems of the rail vehicle are collected and processed through format conversion and standardization to obtain multi-source heterogeneous data; the heterogeneous subsystems include at least: fire alarm system, air conditioning system, and door system; A vehicle environment state matrix is ​​constructed based on the multi-source heterogeneous data. The vehicle environment state matrix uses rows to represent different state subsets and columns to represent different vehicle monitoring zones. The matrix elements include collection timestamps and data verification identifiers. The vehicle environment state matrix is ​​periodically scanned by a preset strategy library, and standardized control commands are generated according to the triggering conditions of the pre-stored built-in strategies; the preset strategy library is a rule-based linkage strategy library for a layered architecture deployed in virtualization and containerization. The standardized control commands are sent to the actuators of each heterogeneous subsystem through a unified output interface to control the actuators to perform corresponding actions.

[0006] A second aspect of this application provides a control device for a vehicle heterogeneous subsystem, comprising: A standardization processing module is used to collect raw signals from heterogeneous subsystems of rail vehicles and perform format conversion and standardization processing to obtain multi-source heterogeneous data; the heterogeneous subsystems include at least: fire alarm system, air conditioning system, and door system; The construction module is used to construct a vehicle environment state matrix based on the multi-source heterogeneous data; the vehicle environment state matrix uses rows to represent different state subsets and columns to represent different vehicle monitoring zones, and the matrix elements include collection timestamps and data verification identifiers; The instruction generation module is used to periodically scan the vehicle environment state matrix through a preset strategy library and generate standardized control instructions according to the triggering conditions of the pre-stored built-in strategies; the preset strategy library is a rule-based linkage strategy library for a layered architecture deployed in virtualization and containerization. The control module is used to send the standardized control commands to the actuators of each heterogeneous subsystem through a unified output interface, so as to control the actuators to perform corresponding actions.

[0007] A third aspect of this application provides a computer device, including: a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of any of the above methods.

[0008] A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, characterized in that the computer program, when executed by a processor, implements the steps of the method as described in any of the above.

[0009] Compared with existing technologies, this application provides a control method for heterogeneous vehicle subsystems. This solution acquires raw signals from these subsystems in real time, including signals from fire alarms, air conditioning, and door systems, and performs standardized processing to obtain multi-source heterogeneous data in a unified format. This eliminates data protocol differences caused by different manufacturers, providing a compliant data foundation for globally unified modeling. Based on this unified data, a vehicle environment state matrix is ​​constructed, categorized by state subsets and monitoring zones, and includes timestamps and data verification identifiers. This enables centralized structured storage, time-series tracing, and anomaly identification of the entire system's data. It provides a single standardized decision input for the strategy library; then, through a virtualized, containerized, and layered architecture, it builds a rule-based linkage strategy library, which periodically scans the vehicle environment state matrix and generates unified standardized control commands based on built-in trigger conditions. This avoids the drawbacks of existing technologies where control logic is fixed in each independent controller and upgrades require debugging hardware one by one, eliminating the need for collaborative rectification among multiple suppliers. Finally, it sends commands to drive the actuators of each subsystem through a unified output interface, streamlining multi-level relay links, shortening emergency linkage latency, facilitating rapid strategy response, and simultaneously achieving hardware simplification, reduced operation and maintenance costs, and improved system scalability, meeting the needs of integrated intelligent management and control of rail vehicles. Attached Figure Description

[0010] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A schematic diagram of an existing control system architecture provided for one embodiment of this application; Figure 2 This is a schematic diagram of the structure of a computer device provided in one embodiment of this application; Figure 3 A flowchart illustrating a control method for a heterogeneous vehicle subsystem provided in one embodiment of this application; Figure 4 A schematic flowchart of a control method for a heterogeneous vehicle subsystem provided in another embodiment of this application; Figure 5 This is a schematic diagram illustrating a method for adjusting subsequent control strategies by periodically scanning the vehicle environment state matrix based on a preset strategy library according to an embodiment of this application. Figure 6 This is a schematic diagram of the structure of a control device for a heterogeneous vehicle subsystem provided in one embodiment of this application. Detailed Implementation

[0011] In the process of realizing this application, the inventors discovered that traditional solutions have drawbacks such as redundant hardware equipment, difficulty in system expansion and upgrading, and multiple layers of emergency response signal relay.

[0012] To make the technical solutions and advantages of the embodiments of this application clearer, the exemplary embodiments of this application will be described in further detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not an exhaustive list of all embodiments. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be combined with each other.

[0013] As mentioned in the background section, please refer to Figure 1 As shown, in existing technical solutions, a large number of controllers are set up in a distributed architecture in the rail vehicle. Each controller communicates with the central control unit (CCU) through the vehicle bus to realize the centralized monitoring and control functions of the whole vehicle. Among them, the human-machine interface (HMI) of the driver's display screen communicates bidirectionally with the display control logic processing module inside the central control unit to realize human-machine command interaction and status feedback. The CCU integrates fire alarm control logic processing modules, air conditioning control logic processing modules, and door control logic processing modules that are connected to each other. Each logic processing module is connected to the fire alarm controller (FAS), air conditioning controller (Heating Ventilation and Air Conditioning, HVAC), and door controller (DoorControl Uni, DCU) respectively. Each controller then interacts bidirectionally with the corresponding fire alarm actuator, air conditioning actuator, and door actuator.

[0014] In actual operation, fire alarm controllers, air conditioning controllers, and door controllers exhibit significant functional coupling. Taking a fire emergency scenario as an example: when a fire occurs in a vehicle, the fire alarm actuator (such as a fire detector) installed on the vehicle transmits the fire alarm signal to the fire alarm control logic processing module inside the CCU via the fire alarm controller (FAS). This module then forwards the signal to the CCU's air conditioning control logic processing module, which sends a command to the HVAC system via the vehicle bus. Upon receiving the signal, the HVAC system immediately controls the air conditioning actuator to shut down the vehicle's air conditioning. Simultaneously, the CCU's fire alarm control logic processing module transmits the fire alarm information to the CCU's display screen control logic processing module, which processes it and triggers an audible and visual alarm on the HMI interface. Furthermore, the CCU's air conditioning control logic processing module receives the air conditioning shutdown confirmation signal from the HVAC system and forwards it to the CCU's display screen control logic processing module, ultimately displaying the air conditioning shutdown status on the driver's HMI display. However, this existing solution has the following drawbacks: Firstly, the existing system adopts a distributed layout, setting the fire alarm controller, air conditioning controller, door controller and central control unit as independent devices. This results in significant equipment redundancy and a bloated overall system structure. This not only significantly increases the cost of hardware procurement and deployment, but also makes the online troubleshooting and debugging process cumbersome, time-consuming and labor-intensive. Furthermore, the functional positioning of each independent device is relatively simple, making it impossible to achieve overall control of multiple subsystems.

[0015] Secondly, the system has poor scalability and maintainability. When the function of any sub-device in the system is changed, upgraded or optimized, the relevant independent devices need to be re-debugged, reconfigured and adapted. This not only seriously affects the progress of the project, but also greatly increases the complexity, uncertainty and maintenance cost of the system.

[0016] Third, the collaborative debugging and integration testing of multiple subsystems is difficult. Since each sub-equipment is provided by different suppliers, the joint debugging and integration testing of multiple subsystems requires the simultaneous participation and cooperation of multiple equipment suppliers, resulting in high communication costs and low collaboration efficiency. This seriously affects the overall implementation efficiency and emergency response speed of the project, making it difficult to meet the actual needs of integrated vehicle management.

[0017] To address the aforementioned shortcomings, this application provides a control method for heterogeneous vehicle subsystems. Compared with related technologies, the technical solution in this application acquires raw signals from heterogeneous vehicle subsystems in real time, including signals from fire alarms, air conditioning, and door systems, and performs standardized processing to obtain multi-source heterogeneous data in a unified format. This eliminates data protocol differences caused by different manufacturers in each subsystem, providing a compliant foundation for globally unified modeling. Based on this unified data, a vehicle environment state matrix is ​​constructed, categorized by state subsets and monitoring zones, and equipped with timestamps and data verification identifiers. This enables centralized structured storage, time-series tracing, and anomaly detection of the entire system's data. This system provides a single standardized decision input for the strategy library. Furthermore, it builds a rule-based, interconnected strategy library through a virtualized, containerized, layered architecture. This library periodically scans the vehicle's environmental state matrix and generates unified, standardized control commands based on built-in trigger conditions. This avoids the drawbacks of existing technologies where control logic is fixed in each independent controller, requiring hardware debugging for upgrades, and eliminating the need for collaborative rectification among multiple suppliers. Finally, commands are issued through a unified output interface to drive the actuators of each subsystem, streamlining multi-level relay links, shortening emergency response latency, facilitating rapid strategy response, and simultaneously achieving hardware simplification, reduced maintenance costs, and improved system scalability, meeting the needs of integrated intelligent management and control of rail vehicles.

[0018] The solutions in this application embodiment can be implemented using various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0019] Please see Figure 2 The present application provides a schematic diagram of the structure of an example computer device. Figure 2 As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media can be, for example, a hard disk. The non-volatile storage media stores files (which can be files to be processed or processed files), an operating system, and computer programs. The internal memory provides an environment for the operating system and computer programs stored in the non-volatile storage media to run. The network interface of the computer device is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a control method for heterogeneous vehicle subsystems. The display screen of the computer device can be a liquid crystal display (LCD) or an e-ink display. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0020] Please see Figure 3 The following embodiments use the aforementioned computer device as the execution subject, and specifically illustrate the application of the control method for heterogeneous vehicle subsystems provided in this application to the aforementioned computer device for data processing. The control method for heterogeneous vehicle subsystems provided in this application includes the following steps 201-204: Step 201: Collect the raw signals of the heterogeneous subsystems of the rail vehicle and perform format conversion and standardization processing to obtain multi-source heterogeneous data; the heterogeneous subsystems include at least: fire alarm system, air conditioning system, and door system.

[0021] It should be noted that the aforementioned raw signals can be the original collected signals from various sensors and points in heterogeneous subsystems such as fire alarm systems, air conditioning systems, and door systems in rail vehicles. Since different subsystems are designed by different manufacturers, the raw signals suffer from differences in communication protocols, physical ranges, and encoding rules, necessitating standardization. By a unified hardware acquisition interface that aggregates all raw signals, standardized processing such as message parsing, format conversion, physical quantity normalization, and anomaly filtering is performed. This eliminates data format barriers between subsystems, unifies data representation standards, and creates multi-source heterogeneous data that can be shared and accessed across subsystems.

[0022] Among them, the aforementioned multi-source heterogeneous data are standardized datasets that can be read and parsed by the strategy library, which may include fire alarm side temperature and smoke sensor data; air conditioning side temperature and humidity and damper opening data; and door side switch, lock and fault feedback data.

[0023] Step 202: Construct a vehicle environment state matrix based on multi-source heterogeneous data; the vehicle environment state matrix uses rows to represent different state subsets and columns to represent different vehicle monitoring zones, and the matrix elements include collection timestamps and data verification identifiers.

[0024] Step 203: Periodically scan the vehicle environment state matrix through the preset strategy library, and generate standardized control commands according to the trigger conditions of the pre-stored built-in strategies; the preset strategy library is a rule-based linkage strategy library for the layered architecture of virtualization and containerization architecture deployment. Step 204: Send standardized control commands to the actuators of each heterogeneous subsystem through a unified output interface to control the actuators to perform corresponding actions.

[0025] Specifically, based on the processed multi-source heterogeneous data, a vehicle environmental state matrix is ​​constructed. The horizontal columns of this matrix represent multiple independent monitoring zones pre-divided into the driver's cab, passenger compartments, etc., while the vertical rows are divided into four independent state subsets: fire alarm, air conditioning, door, and system fault. Each data element in the matrix is ​​accompanied by a corresponding acquisition timestamp and data verification identifier. The timestamp records the acquisition time at the millisecond level, ensuring data time synchronization; the data verification identifier is used to distinguish between normal and valid data and abnormal data due to sensor malfunction. After marking abnormal data, it does not participate in subsequent logical operations, realizing a structured and centralized summary of the operating status of multiple devices in the vehicle.

[0026] The aforementioned rule-based linkage strategy library is deployed based on a virtualized and containerized layered architecture, including a basic support layer for underlying container operation, an intermediate strategy storage layer, and a top-level data interface adaptation layer. Control strategies for different operating conditions, such as fire emergency, routine temperature control, and vehicle door control, are each independently encapsulated in a dedicated container image.

[0027] The aforementioned strategy library includes: a basic support layer, a strategy core layer, and an interface adaptation layer.

[0028] The basic support layer is used to allocate computing resources for policy execution through a virtualization resource scheduling mechanism; the policy core layer is used to encapsulate various collaborative control policies with a core structure of "condition triggering - logical judgment - action output"; the interface adaptation layer is used to read the vehicle environment state matrix as the input condition for policy triggering and convert the policy execution result into a standardized instruction format.

[0029] It should be noted that the rule-based linkage strategy library is located within the integrated central controller. It serves as the core logic carrier for achieving coordinated linkage and integrated control of multiple heterogeneous subsystems, including fire alarms, air conditioning, and doors. The entire system is deployed and runs online based on a virtualization and containerization architecture. It enables modular management of various control strategies, dynamic scheduling of operating resources, and rapid execution of control logic. It dynamically adapts to changes in vehicle operating conditions, establishing a standardized and easily expandable cross-system control logic system for the entire vehicle. The strategy library is divided into three layers from top to bottom: a basic support layer, a strategy core layer, and an interface adaptation layer. These three layers work together to complete the entire process of data access, logical operations, and command output.

[0030] The basic support layer relies on container technology to build an independent software and hardware environment for policy operation. It encapsulates the underlying operating components, computing algorithms, and driver tools that the policy operation depends on into independent container images. By relying on image deployment, various control policies can be quickly ported and deployed online across software and hardware environments. With the virtualization resource scheduling mechanism, dedicated computing resources can be allocated to the running control policies according to the computing power requirements of different working conditions such as normal vehicle operation and fire emergency. This avoids the computing lag caused by multiple policies competing for resources and meets the high real-time operation requirements of rail vehicle on-board control.

[0031] The core layer of the aforementioned strategy serves as the main logic operation body of the strategy library, internally encompassing all cross-subsystem collaborative control strategies. The strategies employ dedicated rule languages ​​such as CLIPS and Prolog to write their logic. Each individual control strategy uniformly follows a "condition trigger - logic judgment - action output" writing architecture. All strategies are categorized and stored in modules according to actual application scenarios such as fire emergency response, in-vehicle temperature and humidity control, and door opening / closing control. Leveraging virtualization management capabilities, target strategies can be remotely and dynamically loaded or unloaded online. Subsequent additions to control scenarios or optimizations of existing control logic only require modification of the corresponding module strategies, significantly reducing the difficulty of strategy iteration and system maintenance.

[0032] The aforementioned interface adaptation layer serves as a data exchange relay, connecting to the data acquisition module and command output module of the central controller. On one hand, it reads real-time parameters such as smoke concentration, ambient temperature and humidity, and door opening / closing status from the vehicle's environmental state matrix through a standardized data interface, transforming the matrix data into trigger judgment conditions recognizable by the strategy core layer. On the other hand, it receives the control logic generated by the strategy core layer, compiles and converts it into standardized control commands applicable to the entire system, and sends them to the command output module, thus establishing a data link between state data input and control command output, enabling seamless linkage between the central controller and the actuators of each subsystem.

[0033] After constructing the vehicle environment state matrix, the entire data of the matrix is ​​scanned periodically through a strategy library. Real-time state parameters of each partition within the matrix are retrieved, and corresponding linkage strategies are automatically matched against preset thresholds and logical conditions to generate standardized control commands in a unified format. All standardized control commands are output through a unified output interface integrated with the system and distributed to the actuators of various heterogeneous subsystems, such as fire alarm actuators, air conditioning damper drive mechanisms, and door drive motors, according to the target partition and device type.

[0034] Please see Figure 4 As shown, Figure 4This is a schematic diagram of the system architecture for a vehicle heterogeneous subsystem provided in an embodiment of this application. The system includes a driver display (HMI), an integrated central controller, and multiple execution structures. The driver display (HMI) communicates bidirectionally with the integrated central controller to issue manual control commands and receive feedback on the vehicle's operating status. Inside the integrated central controller, raw signals from various heterogeneous subsystems such as fire alarm, air conditioning, and doors are collected through a unified hardware interface. After format conversion and standardization cleaning by a multi-source heterogeneous data processing module, multi-source heterogeneous data is generated. A vehicle environmental state matrix is ​​then constructed based on this multi-source heterogeneous data and used as a unified decision input. A rule-based linkage strategy library deployed through a virtualization / containerized architecture periodically reads the vehicle environmental state matrix data. The entire process relies on virtualization resource scheduling and uses rule-based linkage strategies to complete intelligent decision-making and generate standardized control commands.

[0035] The standardized control command is sent to the various actuators (fire alarm actuator, air conditioning actuator, and door actuator) of the fire alarm system, air conditioning system, and door system through a unified output interface. After receiving the command, each actuator can perform actions such as alarm triggering (audible and visual alarm), air conditioning on / off ventilation, and door unlocking / locking according to the standard control command. The action feedback signals of each actuator are sent back to the unified hardware interface and then back to the central controller to update the vehicle environmental status matrix, forming a closed-loop control.

[0036] This application employs a modular and decoupled design for control logic based on virtualization and containerization architecture. It independently encapsulates various operating condition strategies, such as routine vehicle operation, fire emergency response, and equipment anomaly management, into dedicated container images. Leveraging the containerized environment, it enables cross-platform portability, rapid deployment, and independent iteration of control strategies, completely breaking the limitations of traditional control systems with rigid control logic and deep hardware-software integration, thus enhancing system modularity and scalability. Simultaneously, the core data carrier of this application, the vehicle environment state matrix, possesses flexible dimensional expansion capabilities. It can be expanded to include new vehicle subsystems such as ventilation and lighting by adding row vectors, and adapted to scenarios involving vehicle group expansion and increased monitoring zones by adding column vectors. When strategy optimization, function upgrades, subsystem expansion, and parameter calibration adjustments are required, only the corresponding container image needs modification or the matrix dimension parameters need fine-tuning. There is no need to reconstruct the entire vehicle control system architecture, significantly reducing system upgrade, debugging, troubleshooting, and subsequent maintenance costs, and effectively improving the flexibility and versatility of the control system for different vehicle models and operating scenarios.

[0037] Compared to existing technologies, this solution acquires raw signals from heterogeneous vehicle subsystems in real time, including those from fire alarms, air conditioning, and door systems, and performs standardized processing to obtain multi-source heterogeneous data in a unified format. This eliminates data protocol differences caused by different manufacturers, providing a compliant foundation for globally unified modeling. Based on this unified data, a vehicle environment state matrix is ​​constructed, categorized by state subsets and monitoring zones, and includes timestamps and data verification identifiers. This enables centralized, structured storage, time-series tracing, and anomaly identification of the entire system's data, providing a unique, standardized decision input for the strategy library. Furthermore, a rule-based linkage strategy library is built through a virtualized, containerized, and layered architecture. This library periodically scans the vehicle's environmental state matrix and generates unified, standardized control commands based on built-in trigger conditions. This avoids the drawbacks of existing technologies where control logic is fixed in each independent controller and upgrades require debugging hardware one by one, eliminating the need for collaborative rectification among multiple suppliers. Finally, commands are issued through a unified output interface to drive the actuators of each subsystem, simplifying multi-level relay links, shortening emergency linkage latency, facilitating rapid policy response, and simultaneously achieving hardware simplification, reduced maintenance costs, and improved system scalability, thus meeting the needs of integrated intelligent management and control of rail vehicles.

[0038] In one embodiment, the vehicle environment state matrix is ​​a 4×m matrix; m is the number of vehicle monitoring zones and m≥1.

[0039] The matrix includes four types of row vectors, which correspond to the environmental safety state row vector, the in-vehicle environment state row vector, the vehicle equipment state row vector, and the system-level state row vector, respectively.

[0040] Each element in the environmental safety status row vector is a normalized value, ranging from 0 to 1, used to characterize the overall fire alarm status of the corresponding monitoring zone; Each element in the in-vehicle environment status row vector is a three-dimensional numerical group, representing the real-time temperature, real-time humidity, and real-time damper opening of the corresponding monitoring zone; Each element in the vehicle equipment status row vector is a Boolean code used to represent the open / closed state of the corresponding door area; Each element in the system-level state row vector is an enumerated value, which is used to characterize the online status and fault status of the subsystem to which the corresponding monitoring partition belongs.

[0041] The environmental safety status row vector includes fire alarm status data for each monitoring zone; the in-vehicle environment status row vector includes temperature, humidity, and air conditioning operation status data for each monitoring zone; the vehicle equipment status row vector includes open / closed status data for each door area; and the system-level status row vector includes the operating and fault status data of the subsystems to which each monitoring zone belongs.

[0042] It should be noted that the vehicle environment state matrix is ​​the core data structure of the central controller for achieving multi-source heterogeneous data fusion, unified global state expression, and centralized intelligent decision-making. It serves as a crucial hub connecting the data acquisition module and the decision-making module. Through standardized hardware interfaces, it abstracts the discrete sensing information from multiple heterogeneous subsystems such as fire alarms, air conditioning, and doors into a structured, computable, and shareable global state set, uniformly converting it into a standard data structure. This eliminates data barriers between heterogeneous systems and provides a unified, real-time, and reliable decision input for the rule-based linkage strategy library. It comprehensively expresses the vehicle's current environment, equipment, safety, and operating conditions in matrix form, forming a vehicle-level digital mirror. The expression for the vehicle environment state matrix can be as follows: ; Where M(t,k) is a 4×m matrix, where 4 represents 4 core state subsets (corresponding to fire alarm, air conditioning, door and system-level states), and m represents the number of pre-divided vehicle monitoring zones for the rail vehicle, which can be flexibly configured and adjusted according to the vehicle type and carriage layout, m≥1. The monitoring zones specifically include independent control areas such as the driver's cab, each passenger compartment, and equipment and mechanical room, and the number of zones can be increased or decreased as the vehicle formation expands.

[0043] t is a time dimension parameter, representing the data acquisition timestamp in milliseconds (ms), corresponding to the real-time refresh cycle of the matrix (default refresh cycle ≤ 100ms, adapting to the real-time requirements of vehicle control), ensuring that the matrix data is synchronized with the actual vehicle status; k is a data verification flag (including 0 or 1). When k=1, it indicates that the current matrix data has been verified as valid (no anomalies, no loss) and can be used as input for policy base decision-making; when k=0, it indicates that the data is abnormal (such as sensor failure, data jump), and after being marked, it will not participate in decision-making to avoid incorrect input.

[0044] When the data verification identifier is a valid identifier, the corresponding matrix element participates in the decision-making of the rule-based linkage strategy library; when the data verification identifier is an abnormal identifier, the corresponding matrix element does not participate in the decision-making.

[0045] Understandably, the matrix is ​​vertically divided into four independent rows. These four rows correspond to environmental safety status, in-vehicle environment status, vehicle equipment status, and system-level status. They respectively collect operational data from the fire alarm system, air conditioning system, door system, and vehicle auxiliary subsystems. Specifically, the environmental safety status row vector collects fire alarm status data such as smoke and temperature in each monitoring zone; the in-vehicle environment status row vector collects air conditioning operation status data such as ambient temperature and humidity and air conditioning damper operation in each zone; the vehicle equipment status row vector collects status data such as door opening and closing and locking feedback in each door installation area; and the system-level status row vector collects system operation status data such as communication online status and device failure status of the corresponding subsystems in each monitoring zone.

[0046] The matrix consists of four row vectors, each corresponding to one of four core state subsets. Each row vector is of order 1×m, representing real-time data for a particular state across m vehicle monitoring zones. A.S1(t,k)=[s 11 (t,k),s 12 (t,k),...,s 1m [t,k]: Environmental safety status row vector (related to fire alarm system), corresponding to the fire alarm status data of each monitoring zone; B.S2(t,k)=[s 21 (t,k),s 22 (t,k),...,s 2m [(t,k)]: In-vehicle environmental state row vector (related to air conditioning system), corresponding to temperature and humidity, air conditioning operation status data of each monitoring zone; C.S3(t,k)=[s 31 (t,k),s 32 [(t,k),...,s3m(t,k)]: Vehicle equipment state row vector (related to the door system), corresponding to the open / closed state data of each door area; D.S4(t,k)=[s 41 (t,k),s 42 (t,k),...,s 4m [(t,k)]: System-level state row vector, corresponding to the operating status and fault status data of the subsystems to which each monitoring zone belongs.

[0047] In this embodiment, matrix element s ij (t,k) (where i=1,2,3,4; j=1,2,…,m) represents the specific state data of the i-th state subset and the j-th vehicle monitoring zone at time t and verification state k. Each element has undergone unified format conversion and standardization. The specific parameter meanings are as follows: A. Environmental safety status elements (i=1) s 1j (t,k): The comprehensive fire alarm-related status value of the j-th monitoring zone, represented by a normalized numerical value (range 0~1), corresponding to the specific physical quantity mapping relationship: Basic mapping: Smoke concentration (0-0.5 mg / m³) → normalized value 0-0.5; Temperature (25℃-80℃) → normalized value 0-0.5; the sum of the two yields s. 1j (t,k)(0-1) Threshold definition: when s 1j (t,k)>0.6 (corresponding to smoke concentration>0.3mg / m³ or temperature>60℃), triggering the fire emergency strategy; Anomaly marker: When k=0, s 1j (t,k)=-1 indicates that the fire alarm sensor data for this zone is abnormal.

[0048] B. In-vehicle environment state elements (i=2) S 2j (t,k): The comprehensive air conditioning-related status value of the j-th monitoring zone, represented by a three-dimensional numerical array. 2j (t,k)=(T j (t),H j (t),V j (t)); Among them, T j (t) represents the real-time temperature of the j-th partition (normalized range 0~1, corresponding to physical temperatures of -10℃ to 40℃); H j (t) represents the real-time humidity of the j-th partition (normalized range 0~1, corresponding to physical humidity 0%-100%); V j (t) represents the real-time damper opening of the j-th partition (standardized range 0~1, corresponding to damper opening 0%-100%).

[0049] C. Vehicle equipment state elements (i=3) S 3j (t,k): The device status value of the j-th door area, represented by a Boolean encoding (0 or 1), with the corresponding mapping relationship: 1)s 3j (t,k)=0: The car door is closed and locked normally; 2)s 3j (t,k)=1: The car door is open or unlocked; 3) Anomaly marker: When k=0, s 3j (t,k)=2 indicates that the door motor or sensor is faulty.

[0050] D. System-level state elements (i=4) S4j (t,k): The operating status value of the subsystem to which the j-th monitoring partition belongs, represented by an enumeration value (0, 1, 2), with the corresponding mapping relationship: When S 4j When (t,k)=0, the subsystem (fire alarm / air conditioning / door) is online and communication is normal; when S 4j When (t,k)=1, the subsystem (fire alarm / air conditioning / door) is offline, indicating a communication failure; when S 4j When (t,k)=2, the subsystem is online, but there is a fault in a certain actuator.

[0051] It should be noted that each element in the above environmental safety status row vector uses a normalized value in the range of 0 to 1 to represent the comprehensive fire alarm condition of the corresponding zone. This normalized value is obtained by superimposing the measured smoke concentration and ambient temperature of the zone. Specifically, the smoke concentration (0~0.5 mg / m³) and ambient temperature (25℃~80℃) are mapped to the normalized range of 0~0.5, and the superposition results in a comprehensive status value s in the range of 0~1. 1j (t,k); Optionally, a preset value of 0.6 can be used as the fire alarm triggering threshold. When the normalized value of the element exceeds the threshold, the fire hazard is determined to exist in the partition, and the corresponding emergency linkage control logic is triggered. At the same time, relying on the data verification mark built into the matrix, a special mark value is uniformly assigned when the collected data is abnormal. The abnormal mark data will no longer participate in the subsequent strategy judgment calculation.

[0052] Each element of the in-vehicle environment state row vector is configured with an independent three-dimensional numerical group structure. The three-dimensional numerical group corresponds to three parameters in sequence: zone-standardized real-time temperature, standardized real-time humidity, and standardized damper opening. The original physical range of temperature is -10℃ to 40℃, the original physical range of humidity is 0% to 100%, and the actual damper opening is 0% to 100%. After the three types of physical quantities are normalized and converted, they are uniformly included in the three-dimensional numerical group, so that a single element can synchronously carry the full-dimensional operating parameters of the zone air conditioning.

[0053] The elements of the vehicle equipment status row vector are assigned values ​​using Boolean encoding rules. Under normal operating conditions, 0 indicates that the corresponding door is fully closed and the locking mechanism is locked in place, while 1 indicates that the door is in the open state or the locking is ineffective. When the door sensing element or drive motor data is abnormal, a dedicated abnormal code is configured to mark the fault location. The element data after the fault mark does not participate in the normal door linkage logic operation.

[0054] The elements of the system-level state row vector are assigned values ​​through hierarchical enumeration. Different enumeration values ​​indicate the operating conditions of the subsystem: when the enumeration value is 0, it means that the hardware of the corresponding subsystem is online and the bus communication link is normal; when the enumeration value is 1, it means that the hardware of the subsystem is offline and the vehicle communication link is interrupted; when the enumeration value is 2, it means that the subsystem is online, but a certain field actuator has a failure. Hierarchical enumeration enables a fine distinction between two types of anomalies: subsystem communication and device failure.

[0055] The vehicle environment state matrix formula in this embodiment clarifies the physical meaning and mapping relationship of each dimension and parameter, achieving a precise correspondence from formula expression to subsystem state to actual physical quantity. Furthermore, all elements of the matrix have undergone unified format conversion and standardized preprocessing in the early stage. Relying on a unified data structure, it completes the normalization of multi-source heterogeneous data. It can not only serve as a standardized input source for the rule-based linkage strategy library to carry out threshold comparison and logical reasoning, but also meet the data modular management requirements under virtualization / containerization architecture. It can also support the modular storage and retrieval of data under containerization architecture, realize the digital unified collection of the state of multiple heterogeneous subsystems of the whole vehicle, and provide a clear data reference standard for subsequent system debugging and strategy optimization.

[0056] In one optional embodiment of this application, the standardized control instructions include: a first control instruction, a second control instruction, and a third control instruction; the standardized control instructions are generated according to the triggering conditions of a pre-stored built-in strategy, including: When the policy library detects that the environmental safety status element of any monitoring zone in the vehicle environmental status matrix is ​​greater than the first preset threshold and the data verification identifier corresponding to the environmental safety status element is a valid identifier, the fire alarm emergency mode is triggered, and the following collaborative control strategy is executed: The currently running routine strategy is interrupted, the pre-stored fire alarm emergency core strategy is invoked first, and the elements in the system-level status row vector of the corresponding monitoring partition are updated to the enumeration values ​​representing the triggering of the emergency state. Generate a first control command; the first control command is used to control the fire alarm actuator of the fire alarm system to activate the audible and visual alarm; Generate a second control command; the second control command is used to control the air conditioning system actuator to close the air conditioning damper of the corresponding monitoring zone and stop the compressor operation; Generate a third control command; the third control command is used to control the door system actuator of the door system to unlock and open the door of the corresponding monitoring zone.

[0057] Specifically, taking the improved integrated control method for vehicle data of a high-speed train as an example, the first stage is the triggering and startup stage. When the rule-based linkage strategy library periodically reads the environmental safety state row vector S1(t,k)=[s from the vehicle environmental state matrix M(t,k) via the interface adaptation layer... 11 (t,k),s 12 (t,k),...,s 1m The real-time data of [(t,k)], where S1(t,k) (j=1,2,…,m, m is the number of vehicle monitoring zones) is the comprehensive status value related to fire alarm in each zone (normalized range 0-1).

[0058] During normal train operation, when a fire breaks out in a carriage of a rail vehicle, the fire actuator (fire detector) in a specific section of that carriage detects a smoke concentration greater than 0.3 mg / m³ or a temperature greater than 60°C. This concentration or temperature signal is immediately transmitted to the unified hardware interface of the central controller. The collected smoke concentration or temperature signal data is converted into an environmental safety status element after standardized cleaning and format conversion. The rule-based linkage strategy library within the integrated central controller is periodically scanned. When the rule-based linkage strategy library detects any detection zone's smoke concentration or temperature signal... 1j When (t,k)>0.6 (i.e., smoke concentration>0.3mg / m³ or temperature>60℃, and k=1, data verification is valid), the fire emergency mode is immediately triggered. Relying on the containerized rapid scheduling mechanism, the currently running conventional strategies (such as temperature and humidity control, door linkage, etc.) are interrupted, and the core fire emergency strategies pre-stored in the strategy library are called first. At the same time, the state value of the partition corresponding to the system-level state row vector S4(t,k) in the vehicle environment state matrix is ​​marked as s. 4j (t,k)=2 (subsystem online, triggering emergency state), complete linkage startup.

[0059] Understandably, when the rule-based linkage strategy library detects that the value of the environmental safety status element corresponding to any monitoring zone exceeds the first preset threshold of 0.6, and the data verification identifier of that point is a valid value k=1, a fire risk is determined to exist on site, and the system immediately triggers the fire alarm emergency mode. After triggering, relying on the rapid scheduling capability of containerized resources, the system suspends the running conventional control strategies such as automatic temperature and humidity adjustment inside the vehicle and normal door control, and prioritizes the retrieval of the pre-packaged and stored core fire alarm emergency strategy by seizing system computing resources. Simultaneously, the system modifies the corresponding element in the system-level status row vector of that monitoring zone, assigning it the enumeration value 2, representing that the subsystem is online and has entered the emergency working state.

[0060] Further, the second phase is executed: the collaborative execution phase. After the rule-based linkage strategy library calls the fire emergency collaborative strategy, it issues standardized control commands to the actuators of each subsystem based on real-time data from the vehicle environmental status matrix, realizing the synchronous linkage of air conditioning, doors, and fire alarm actuators. Each linkage action is based on matrix data to ensure the accuracy of the linkage.

[0061] In this embodiment, multiple sets of standardized control commands are generated step by step based on the real-time parameters of four types of row vectors within the matrix: First, a first control command is generated and sent to the fire alarm actuator to drive the equipment to activate the audible and visual alarm. At the same time, the on-site detectors collect and update smoke and temperature data in real time and send them back to the central controller, and simultaneously refresh the environmental safety status element values. If the element further exceeds the secondary judgment threshold of 0.8, the system upgrades the alarm level, increases the frequency and loudness of the audible and visual alarm, and pushes an advanced fire alarm warning to the driver.

[0062] Secondly, a second control command is generated and sent to the air conditioning actuator. Referring to the three-dimensional parameters of temperature, humidity and damper opening in the vehicle interior environment state row vector, the command closes all air conditioning dampers in the zone and stops the compressor, cuts off the air duct to prevent smoke from spreading across the cabin, and simultaneously sets the corresponding damper opening parameter Vj(t) in the matrix to 0, and provides real-time feedback on the execution result of the air conditioning equipment.

[0063] Third, a third control command is generated and sent to the door drive actuator. Combined with the door lock status code of the vehicle equipment status row vector, door unlocking and opening commands are uniformly issued. After the command is executed, the corresponding code is updated to 1. If the matrix feedback door fault code 2, which means that the door is stuck and cannot be opened, the unlocking command is retried three times. After multiple actions fail, the system-level status element is modified to fault enumeration value 2. The fault information is uploaded to the HMI human-machine interface through a unified interface to prompt the driver for inspection and handling.

[0064] Understandably, during the linkage process with the fire alarm execution mechanism, the strategy library issues audible and visual alarm commands to the fire alarm execution mechanism, and simultaneously updates the vehicle environment state matrix through the interface adaptation layer, adjusting the corresponding partition s 1j The value of (t,k) is synchronously updated to the real-time collected smoke and temperature superimposed values, facilitating real-time monitoring of fire changes by the strategy library; if s is detected... 1j When (t,k)>0.8 (corresponding to smoke concentration>0.4mg / m³ or temperature>70℃), the strategy library triggers a graded alarm, increases the alarm volume and frequency, and pushes a high-level fire alarm warning to the central controller.

[0065] During the emergency response of the air conditioning system, the strategy library is based on the row vector s of the in-vehicle environment state in the matrix. 2j (t,k)=(T j (t),H j (t),Vj Based on the real-time temperature, humidity, and damper opening data of (t), and combined with the fire emergency strategy logic, immediately issue a second control command: close all air conditioning dampers (corresponding to V in the matrix). j (t)=0, damper opening 0%), stop the compressor operation, cut off the air circulation in the air conditioning duct, and prevent the smoke from spreading through the duct; at the same time, start the air conditioning fresh air exhaust function to accelerate the exhaust of smoke in the vehicle. At this time, the air conditioning operation status parameters of the corresponding partition in the matrix are updated synchronously to provide feedback on the execution of the air conditioning emergency action.

[0066] During the emergency linkage process of the door system, the strategy library reads the real-time door status data (S3j(t,k) from the vehicle equipment status row vector S3j(t,k) in the vehicle environment state matrix. 3j (t,k)=0 indicates that the latch is closed, S 3j (t,k)=1 indicates open / unlocked), and a third control command is issued to all door actuators (door motors). This third control command is used to control the door system actuators to unlock and open the doors in the corresponding monitoring zones, ensuring that the doors are in a fully open state (update matrix S). 3j (t,k)=1); if the policy base discovers a certain door S through matrix feedback, 3j (t,k)=2 (Door motor / sensor malfunction, jammed and not open), immediately issue a second unlock command and reissue it to the door system actuator. If it still fails to open after 3 retries, update the corresponding system-level state row vector S of the matrix. 4j (t,k)=2 (subsystem fault), and a fault signal is fed back to the central controller. This fault signal is output to the driver's cab display screen (HMI) through a unified interface to remind relevant personnel to take action.

[0067] This embodiment improves the collaborative reliability and emergency response efficiency of multiple heterogeneous subsystems. Specifically, it achieves the normalization, fusion, and real-time updating of heterogeneous data from multiple subsystems such as fire alarm, air conditioning, and doors through the vehicle environmental state matrix M(t,k). The environmental safety state row vector S1(t,k) can accurately collect smoke concentration and temperature data from each zone and perform normalization processing in the 0~1 range. With 0.6 as the emergency trigger threshold, it provides a unified, accurate, and standardized decision input for the rule-based linkage strategy library, completely eliminating the problems of data fragmentation and information asymmetry between subsystems in traditional distributed architectures. By leveraging a rule-based linkage strategy library and containerized rapid scheduling capabilities, conventional strategies such as temperature and humidity control and routine door management can be immediately interrupted during fire emergency situations. The fire emergency linkage logic is executed first, simultaneously completing multiple linkage actions such as closing the air conditioning damper, unlocking and opening the door, and activating the fire alarm. This keeps the overall emergency response latency of the system within 100ms, effectively shortening the emergency response time, suppressing the risk of fire and smoke spread, comprehensively protecting the safety of vehicle equipment and occupants, and significantly improving the collaborative linkage accuracy and emergency response efficiency of multiple heterogeneous subsystems.

[0068] In one embodiment, after the control actuator performs the corresponding action, please refer to... Figure 5 As shown, the above method also includes: Step 301: Collect the status feedback signals generated by each actuator after performing the action in real time through a unified hardware interface.

[0069] Step 302: Perform format conversion and standardization processing on each state feedback signal to update the vehicle environment state matrix, and re-periodically scan based on the updated vehicle environment state matrix using a preset strategy library to adjust the subsequent control strategy.

[0070] Specifically, the actual operating status of each subsystem's actuators after completing the command actions is collected and uploaded in real time through the unified hardware interface of the integrated central controller. The collected raw feedback data is converted into a standardized format and normalized, and the corresponding element parameters in the vehicle environment state matrix are rewritten accordingly. This constructs a closed-loop control logic that spans perception, decision-making, execution, and feedback. The rule-based linkage strategy library dynamically optimizes the emergency control logic based on the real-time updated matrix data.

[0071] After the fire alarm emergency mode is triggered, the above methods also include: When an element in the environmental safety status row vector exceeds the second preset threshold, a graded alarm command is generated to trigger a graded alarm; the second preset threshold is greater than the first preset threshold; when an element in the vehicle equipment status row vector retains the coded value representing whether the door is closed or unlocked after the door opening command is issued, a secondary unlock command is generated and resent to the door system actuator; when an element in the environmental safety status row vector is less than the release threshold and the duration exceeds the preset time, the fire emergency mode is automatically deactivated, the normal operation strategy is restored, and the element in the corresponding system-level status row vector is updated to the enumeration value representing the normal operation of the subsystem.

[0072] In this embodiment, real-time status feedback and matrix synchronization updates are performed first. Actual on-site conditions such as fire alarm actuator activation / deactivation, air conditioning damper closure degree, and door opening / closing / locking are fed back to the central controller in real time. Based on this feedback information, the system synchronously corrects the damper opening parameter V in the vehicle interior environment status vector. j (t), the door state s of the vehicle equipment state row vector. 3j Matrix elements such as (t,k) ensure that the data stored in the matrix is ​​synchronized with the actual emergency conditions on the train carriage in real time.

[0073] Then, the emergency control strategy is dynamically iterated based on matrix data. The strategy library continuously polls and reads the real-time data of the environmental safety status row vector S1(t,k). When the value of the corresponding partition S1(t,k) continues to rise, it indicates that the smoke and temperature on site are constantly increasing and the fire situation is continuously deteriorating. The system immediately optimizes the control strategy, increases the output power of the air conditioning exhaust and keeps the fire alarm sound and light alarms uninterrupted; when s is detected... 1j If (t,k)≤0.4, corresponding to a measured smoke concentration not exceeding 0.2mg / m³ and an ambient temperature below or equal to 50℃, and this stable state is maintained continuously for 30s, then the fire is determined to be extinguished and the danger eliminated. The strategy library automatically exits the fire emergency mode and updates the corresponding element of the system-level state row vector S4(t,k) to s. 4j (t,k)=0 indicates that the subsystem communication and equipment operation have returned to normal, and the normal control strategy is automatically retrieved, and the air conditioner and doors switch back to the daily control mode.

[0074] In addition, this phase leverages the built-in log storage function of containerization to fully retain all operational data, including original matrix data, policy matching records, issued control commands, and device feedback status, facilitating subsequent policy iteration and optimization as well as device fault tracing and repair. Meanwhile, the fire emergency control strategy adopts a container redundancy backup deployment scheme, configuring a backup container image. If the main container carrying the emergency strategy malfunctions, it can quickly switch to the backup image to continue executing the control logic, preventing emergency linkage failure and significantly improving the stability of the vehicle's emergency control.

[0075] This application constructs a closed-loop control system covering the entire chain of "perception-decision-execution-feedback," including the actual action states of the actuators of each subsystem, such as the air conditioning damper opening degree Vj(t) and the door opening / closing state s. 3j Key parameters such as (t, k) can be transmitted back in real time through a unified hardware interface and synchronously updated to the vehicle environment state matrix, ensuring that the system decision data is synchronized with the actual on-site conditions. The rule-based linkage strategy library adaptively adjusts the control logic based on dynamically updated matrix data, realizing dynamic iterative optimization of the control strategy as the operating conditions change, thus overcoming the shortcomings of traditional fixed logic that cannot adapt to the operating conditions in real time. At the same time, the matrix's built-in data verification identifier k accurately identifies abnormal data, isolating invalid data such as sensor failures, data loss, and signal jumps, ensuring the reliability of decision data from the source. The core emergency strategy adopts a containerized redundant deployment mode, configuring a backup container image, which can quickly and seamlessly switch when the main container fails, avoiding interruption of emergency control logic. This effectively solves the defects of existing technologies that lack dynamic adjustment capabilities and fault tolerance mechanisms, and significantly improves the operational stability, data accuracy, and linkage reliability of the vehicle control system.

[0076] In summary, the system in this application collects signals from external actuators in real time through a unified hardware interface, including smoke and temperature sensor signals from the fire alarm system, temperature and humidity and damper status signals from the air conditioning system, and open / closed status signals from the door system. These multi-source heterogeneous data, after being converted and standardized in a unified format, are integrated within the central controller to form a globally shared vehicle environment state matrix. This provides a unified, structured, and computable real-time data representation of the vehicle environment and equipment status. The central controller, based on a virtualization and containerization architecture, has a built-in rule-based linkage strategy library and pre-stores cross-system collaborative control strategies for various operating conditions. Using the vehicle environment state matrix as a unified decision input, it performs centralized intelligent reasoning and collaborative decision-making to generate standardized control commands. Control commands are sent to the actuators of various subsystems, such as the air conditioning damper motor, door motor, and fire alarm actuator, through a unified output interface. The action status of each actuator is fed back to the signal acquisition module of the integrated central controller hardware interface in real time. The central controller updates the vehicle environment status matrix, forming a complete closed-loop control of perception, decision-making, execution, and feedback. Relying on containerized isolation deployment and virtualized resource scheduling, it realizes the decoupled operation, collaborative linkage, and integrated intelligent control of multiple heterogeneous subsystems such as fire alarm, air conditioning, and doors, thereby improving the integration, reliability, real-time performance, and scalability of the vehicle control system.

[0077] It should be understood that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order constraint on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the diagram may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0078] In another embodiment provided in this application, a control device for a heterogeneous vehicle subsystem is also provided; please refer to [link to relevant documentation]. Figure 6 As shown, the device includes: The standardization processing module 610 is used to collect raw signals from heterogeneous subsystems of rail vehicles and perform format conversion and standardization processing to obtain multi-source heterogeneous data; the heterogeneous subsystems include at least: fire alarm system, air conditioning system, and door system; Module 620 is used to construct a vehicle environment state matrix based on multi-source heterogeneous data. The vehicle environment state matrix uses rows to represent different state subsets and columns to represent different vehicle monitoring zones. The matrix elements include collection timestamps and data verification identifiers. The instruction generation module 630 is used to periodically scan the vehicle environment state matrix through a preset policy library and generate standardized control instructions according to the triggering conditions of the pre-stored built-in policies; the preset policy library is a rule-based linkage policy library for the layered architecture of virtualization and containerization architecture deployment. The control module 640 is used to send standardized control commands to the actuators of various heterogeneous subsystems through a unified output interface, so as to control the actuators to perform corresponding actions.

[0079] Optionally, the vehicle environment state matrix is ​​a 4×m matrix; m is the number of vehicle monitoring zones and m≥1; The matrix includes four types of row vectors, which correspond to the environmental safety state row vector, the in-vehicle environment state row vector, the vehicle equipment state row vector, and the system-level state row vector, respectively. Each element in the environmental safety status row vector is a normalized value, ranging from 0 to 1, used to characterize the overall fire alarm status of the corresponding monitoring zone; Each element in the in-vehicle environment status row vector is a three-dimensional numerical group, representing the real-time temperature, real-time humidity, and real-time damper opening of the corresponding monitoring zone; Each element in the vehicle equipment status row vector is a Boolean code used to represent the open / closed state of the corresponding door area; Each element in the system-level state row vector is an enumerated value, which is used to characterize the online status and fault status of the subsystem to which the corresponding monitoring partition belongs.

[0080] The environmental safety status row vector includes fire alarm status data for each monitoring zone; the in-vehicle environment status row vector includes temperature, humidity, and air conditioning operation status data for each monitoring zone; the vehicle equipment status row vector includes open / closed status data for each door area; and the system-level status row vector includes the operating and fault status data of the subsystems to which each monitoring zone belongs.

[0081] Optionally, when the data verification identifier is a valid identifier, the corresponding matrix element participates in the decision-making of the rule-based linkage strategy library; When the data verification flag is an anomaly flag, the corresponding matrix element will not participate in the decision-making process.

[0082] Optionally, the instruction generation module 630 is specifically used for: When the policy library detects that the environmental safety status element of any monitoring zone in the vehicle environmental status matrix is ​​greater than the first preset threshold and the data verification identifier corresponding to the environmental safety status element is a valid identifier, the fire alarm emergency mode is triggered, and the following collaborative control strategy is executed: The currently running routine strategy is interrupted, the pre-stored fire alarm emergency core strategy is invoked first, and the elements in the system-level status row vector of the corresponding monitoring partition are updated to the enumeration values ​​representing the triggering of the emergency state. Generate a first control command; the first control command is used to control the fire alarm actuator of the fire alarm system to activate the audible and visual alarm; Generate a second control command; the second control command is used to control the air conditioning system actuator to close the air conditioning damper of the corresponding monitoring zone and stop the compressor operation; Generate a third control command; the third control command is used to control the door system actuator of the door system to unlock and open the door of the corresponding monitoring zone.

[0083] Optionally, the above-mentioned device is also used for: When the number of elements in the environmental safety status row vector exceeds the second preset threshold, a graded alarm command is generated to trigger the graded alarm; the second preset threshold is greater than the first preset threshold. When an element in the vehicle equipment status row vector retains the encoded value representing whether the door is closed or unlocked after the door opening command is issued, a secondary unlock command is generated and resent to the door system actuator. When the elements in the environmental safety status row vector are less than the release threshold and the duration exceeds the preset time, the fire alarm emergency mode is automatically released, the normal operation strategy is restored, and the elements in the corresponding system-level status row vector are updated to the enumeration values ​​representing the normal operation of the subsystem.

[0084] Optionally, the strategy library includes: a basic support layer, a strategy core layer, and an interface adaptation layer; The basic support layer is used to allocate computing resources for policy execution through a virtualization resource scheduling mechanism; The core strategy layer is used to encapsulate various collaborative control strategies with a core structure of "condition triggering - logic judgment - action output"; The interface adaptation layer is used to: read the vehicle environment state matrix as the input condition for policy triggering, and convert the policy execution result into a standardized instruction format.

[0085] Optionally, the above-mentioned device is also used for: The status feedback signals generated by each actuator after performing an action are collected in real time through a unified hardware interface. The various state feedback signals are formatted and standardized to update the vehicle environment state matrix. Based on the updated vehicle environment state matrix, a pre-defined strategy library is used to perform periodic scanning to adjust subsequent control strategies.

[0086] Specific limitations regarding the control device for the aforementioned heterogeneous vehicle subsystems can be found in the limitations of the control method for heterogeneous vehicle subsystems described above, and will not be repeated here. Each module in the aforementioned control device for heterogeneous vehicle subsystems can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0087] In one embodiment, a computer device is provided, the internal structure of which can be as follows: Figure 1 As shown. The computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores data. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements the control method for a heterogeneous vehicle subsystem described above. It includes: a memory and a processor; the memory stores a computer program; and the processor executes the computer program to implement any step of the control method for a heterogeneous vehicle subsystem described above.

[0088] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, can implement any of the steps in the control method for heterogeneous vehicle subsystems described above.

[0089] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0090] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0091] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0092] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0093] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0094] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A control method for heterogeneous vehicle subsystems, characterized in that, The method includes: The raw signals from the heterogeneous subsystems of the rail vehicle are collected and processed through format conversion and standardization to obtain multi-source heterogeneous data; the heterogeneous subsystems include at least: fire alarm system, air conditioning system, and door system; A vehicle environment state matrix is ​​constructed based on the multi-source heterogeneous data. The vehicle environment state matrix uses rows to represent different state subsets and columns to represent different vehicle monitoring zones. The matrix elements include collection timestamps and data verification identifiers. The vehicle environment state matrix is ​​periodically scanned by a preset strategy library, and standardized control commands are generated according to the triggering conditions of the pre-stored built-in strategies; the preset strategy library is a rule-based linkage strategy library for a layered architecture deployed in virtualization and containerization. The standardized control commands are sent to the actuators of each heterogeneous subsystem through a unified output interface to control the actuators to perform corresponding actions.

2. The control method for heterogeneous vehicle subsystems according to claim 1, characterized in that, The vehicle environment state matrix is ​​a 4×m matrix; m is the number of vehicle monitoring zones and m≥1; The matrix includes four types of row vectors, which correspond to environmental safety state row vectors, in-vehicle environment state row vectors, vehicle equipment state row vectors, and system-level state row vectors, respectively. Each element in the environmental safety status row vector is a normalized value, ranging from 0 to 1, used to characterize the overall fire alarm status of the corresponding monitoring zone; Each element in the in-vehicle environment state row vector is a three-dimensional numerical group, representing the real-time temperature, real-time humidity, and real-time damper opening of the corresponding monitoring zone; Each element in the vehicle equipment status row vector is a Boolean code used to represent the open / closed state of the corresponding door area. Each element in the system-level state row vector is an enumerated value, which is used to characterize the online status and fault status of the subsystem to which the corresponding monitoring partition belongs; The environmental safety status row vector includes fire alarm status data for each monitoring zone; the in-vehicle environment status row vector includes temperature, humidity, and air conditioning operation status data for each monitoring zone; the vehicle equipment status row vector includes open / closed status data for each door area; and the system-level status row vector includes the operating and fault status data of the subsystems to which each monitoring zone belongs.

3. The control method for heterogeneous vehicle subsystems according to claim 2, characterized in that, When the data verification identifier is a valid identifier, the corresponding matrix element participates in the decision-making of the rule-based linkage strategy library; When the data verification identifier is an anomaly identifier, the corresponding matrix element does not participate in the decision-making process.

4. The control method for heterogeneous vehicle subsystems according to claim 3, characterized in that, The standardized control commands include: a first control command, a second control command, and a third control command; standardized control commands are generated according to the trigger conditions of a pre-stored built-in strategy, including: When the strategy library detects that the environmental safety status element of any monitoring zone in the vehicle environmental status matrix is ​​greater than a first preset threshold and the data verification identifier corresponding to the environmental safety status element is a valid identifier, the fire alarm emergency mode is triggered, and the following collaborative control strategy is executed: The currently running routine strategy is interrupted, the pre-stored fire alarm emergency core strategy is invoked first, and the elements in the system-level status row vector of the corresponding monitoring partition are updated to the enumeration values ​​representing the triggering of the emergency state. Generate a first control command; the first control command is used to control the fire alarm actuator of the fire alarm system to activate the audible and visual alarm; Generate a second control command; the second control command is used to control the air conditioning system actuator of the air conditioning system to close the air conditioning damper of the corresponding monitoring zone and stop the compressor operation; A third control command is generated; the third control command is used to control the door system actuator of the door system to unlock and open the door of the corresponding monitoring zone.

5. The control method for heterogeneous vehicle subsystems according to claim 4, characterized in that, After triggering the fire emergency mode, the method further includes: When the elements in the environmental safety status row vector exceed the second preset threshold, a graded alarm command is generated to trigger a graded alarm; the second preset threshold is greater than the first preset threshold. When an element in the vehicle equipment state row vector retains the encoded value representing whether the door is closed or unlocked after a door opening command is issued, a secondary unlock command is generated and resent to the door system actuator. When the element in the environmental safety status row vector is less than the release threshold and the duration exceeds the preset time, the fire alarm emergency mode is automatically released, the normal operation strategy is restored, and the element in the corresponding system-level status row vector is updated to the enumeration value representing the normal operation of the subsystem.

6. The control method for heterogeneous vehicle subsystems according to claim 1, characterized in that, The strategy library includes: a basic support layer, a strategy core layer, and an interface adaptation layer; The basic support layer is used to allocate computing resources for strategy execution through a virtualization resource scheduling mechanism; The core strategy layer is used to encapsulate various collaborative control strategies with a core structure of "condition triggering - logic judgment - action output"; The interface adaptation layer is used to: read the vehicle environment state matrix as the input condition for policy triggering, and convert the policy execution result into a standardized instruction format.

7. The control method for heterogeneous vehicle subsystems according to claim 1, characterized in that, After controlling the actuator to perform the corresponding action, the method further includes: The unified hardware interface is used to collect the status feedback signals generated by each actuator after performing an action in real time. The various state feedback signals are format-converted and standardized to update the vehicle environment state matrix. Based on the updated vehicle environment state matrix, a pre-defined strategy library is used to perform a periodic scan to adjust the subsequent control strategy.

8. A control device for heterogeneous vehicle subsystems, characterized in that, The device includes: A standardization processing module is used to collect raw signals from heterogeneous subsystems of rail vehicles and perform format conversion and standardization processing to obtain multi-source heterogeneous data; the heterogeneous subsystems include at least: fire alarm system, air conditioning system, and door system; The construction module is used to construct a vehicle environment state matrix based on the multi-source heterogeneous data; the vehicle environment state matrix uses rows to represent different state subsets and columns to represent different vehicle monitoring zones, and the matrix elements include collection timestamps and data verification identifiers; The instruction generation module is used to periodically scan the vehicle environment state matrix through a preset strategy library and generate standardized control instructions according to the triggering conditions of the pre-stored built-in strategies; the preset strategy library is a rule-based linkage strategy library for a layered architecture deployed in virtualization and containerization. The control module is used to send the standardized control commands to the actuators of each heterogeneous subsystem through a unified output interface, so as to control the actuators to perform corresponding actions.

9. A computer device, comprising: A memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images