Fault diagnosis system and method for all-in-one integrated controller

Abstract

The application discloses a fault diagnosis system and method for a multi-in-one integrated controller, which comprises a plurality of fault monitoring points, the fault monitoring points being located between the multi-in-one integrated controller and controlled mechanisms and at predetermined positions of the multi-in-one integrated controller; a plurality of fault monitoring units, the fault monitoring units being installed at the corresponding fault monitoring points, each fault monitoring unit being provided with a unique identification code; and a fault diagnosis module connected with the fault monitoring units, which diagnoses the fault category based on the output data of the fault monitoring units and determines the controlled mechanism with the fault by combining the identification code of the fault monitoring unit to complete fault positioning. The application can simultaneously realize fault category diagnosis and fault positioning.

Description

Technical Field

[0001] This invention belongs to the field of fault diagnosis technology, specifically relating to a fault diagnosis system and method for all-in-one integrated controllers. Background Technology

[0002] With the rapid penetration of new energy technologies into heavy transportation and special vehicles, wide-body vehicles, due to their high load capacity, short transport distance, high uptime, and low operating costs, have become important transportation tools in mining areas, ports, and large-scale engineering construction. To improve space utilization and reduce system complexity and potential failure points, the electronic control systems of wide-body vehicles are developing towards high integration, forming "all-in-one controllers." However, compared with passenger cars, new energy wide-body vehicles and their all-in-one controllers face more severe and complex operational challenges, resulting in significantly unique failure modes that are difficult to directly apply or have limited effectiveness with existing fault diagnosis technologies.

[0003] New energy wide-body vehicles (such as electric mining wide-body vehicles and large electric buses) are heavy-duty, high-frequency transportation tools. Their all-in-one integrated controllers integrate multiple functions such as motor control, DC-DC conversion, and on-board chargers, and are the core components of the vehicle's power system. Due to the complex operating conditions of wide-body vehicles (heavy load, climbing, frequent start-stop) and harsh working environment (high temperature, dust, severe vibration), the integrated controllers are prone to problems such as power module damage, communication interruption, and cooling system failure. If these problems are not diagnosed and handled in a timely manner, they may lead to serious consequences such as power interruption of the entire vehicle and component burnout.

[0004] Chinese invention patent application CN120972846 A discloses a method and unit for self-diagnosis of faults in an all-in-one controller for new energy vehicles. This patent proposes a self-diagnosis method for faults in an all-in-one controller for new energy vehicles based on vibration sensing and deep learning. Vibration data of the controller housing in the longitudinal, lateral, and vertical directions is collected by vibration sensors and preprocessed to obtain time-domain and frequency-domain graphs. Feature vectors of specific time periods in the time-domain graph and feature vectors of different vibration frequencies in the frequency-domain graph are input into an LSTM neural network for vibration data prediction. A pre-trained deep belief neural network model then determines whether the data is normal. If the predicted data is abnormal, the fault type is reported and maintenance is recommended to improve the overall vehicle safety and reliability.

[0005] Existing diagnostic systems typically rely on single-type data sources, such as monitoring only temperature, analyzing only current, or examining only communication messages for independent threshold judgments. This "island-style" diagnostic approach fails to effectively capture the complex fault mechanisms of wide-body vehicle multi-function controllers under the coupling effects of multiple physical fields (electricity, heat, mechanics, and environment). Current technologies lack synchronous correlation and fusion analysis of multi-source heterogeneous data, making it impossible to distinguish between "normal temperature rise caused by heavy-load hill climbing" and "abnormal overheating caused by cooling failure," easily leading to false alarms or missed alarms, and severely insufficient accuracy and timeliness of warnings. Even when existing diagnostic methods detect anomalies, their output often remains at the general system-level or board-level alarm level, such as "controller fault," "power module anomaly," or "communication timeout," failing to pinpoint specific faulty components or faulty links. This vague diagnostic result forces maintenance personnel to rely on personal experience for hours or even days of manual troubleshooting, disassembly, and measurement, significantly extending vehicle downtime and increasing maintenance costs and complexity. For highly integrated, complex all-in-one controllers, the lack of precise fault location capabilities makes "rapid repair" difficult to achieve, which seriously affects the high uptime requirements necessary for wide-body vehicles as production tools.

[0006] Furthermore, most current systems have relatively weak fault data logging capabilities, typically only saving simple snapshots or fault codes at the moment of the fault occurrence, lacking continuous, high-sampling-rate recording of critical data streams throughout the entire process before and after the fault. Especially during the transient phase of a fault, high-frequency data reflecting key stages of fault evolution, such as controller internal status messages, bus communication messages, and drive waveforms, are often lost due to storage capacity or policy limitations. This makes it impossible to fully reconstruct the complete "data chain" from fault occurrence and development to triggering during post-fault analysis, hindering R&D and technical personnel from accurately tracing the root cause of the fault. Fault analysis becomes like "cooking without rice," severely impeding iterative improvements in product quality and the development of targeted maintenance strategies. Summary of the Invention

[0007] To address the aforementioned problems, this invention proposes a fault diagnosis system and method for all-in-one integrated controllers, which can simultaneously achieve fault category diagnosis and fault location.

[0008] To achieve the above-mentioned technical objectives and effects, the present invention is implemented through the following technical solution: In a first aspect, the present invention provides a fault diagnosis system for an all-in-one integrated controller, comprising: Several fault monitoring points are located between the all-in-one integrated controller and the controlled mechanism, as well as at predetermined positions of the all-in-one integrated controller. Several fault monitoring units are installed at corresponding fault monitoring points, and each fault monitoring unit is equipped with a unique identification code; The fault diagnosis module is connected to the fault monitoring unit. It performs fault category diagnosis based on the output data of the fault monitoring unit, and determines the controlled mechanism that has malfunctioned by combining the identification code of the fault monitoring unit, thus completing the fault location.

[0009] In conjunction with the first aspect, the fault diagnosis module may optionally include a fault identification module and a fault classification module; The fault identification module is configured to perform early warning or fault diagnosis based on the output data of the fault monitoring unit, and generate early warning signals or fault signals. In response to the warning signal or fault signal, the fault classification module performs fault category diagnosis based on the output data of the fault monitoring unit.

[0010] In conjunction with the first aspect, optionally, the fault diagnosis system further includes a fault data storage module, which has independent power supply and storage functions. The fault data storage module is connected to the all-in-one integrated controller and each fault monitoring unit via a CAN bus, and is used to store data in the all-in-one integrated controller, the CAN bus, and each fault monitoring unit.

[0011] In conjunction with the first aspect, optionally, the fault data storage module includes an interconnected circular buffer and a non-volatile memory; The circular buffer is used to store data from the all-in-one integrated controller, CAN bus, and various fault monitoring units; When the fault diagnosis module generates a warning signal or a fault signal, it will save the current data in the all-in-one integrated controller, CAN bus and fault monitoring unit, as well as the data in the all-in-one integrated controller, CAN bus and each fault monitoring unit within a predetermined time period before and after the generation of the warning signal or fault signal, from the ring buffer to the non-volatile memory, forming an indelible fault data packet. The fault data packet is used to upload to the cloud analysis platform via the CAN bus for later analysis.

[0012] In conjunction with the first aspect, optionally, the fault classification module is a deep learning model; When the fault classification module cannot output a fault category based on the output data of the fault monitoring unit, it marks the output data as a new type of anomaly and sends it to the cloud analysis platform for manual fault labeling, generating corresponding fault type labels, and updating the deep learning model.

[0013] In conjunction with the first aspect, optionally, the fault monitoring unit includes any one or more of a first temperature sensor, a second temperature sensor, a vibration sensor, a voltage sensor, and a current sensor; The first temperature sensor is used to be installed inside the all-in-one integrated controller; The second temperature sensor is used to install at the inlet and outlet of the cooling circuit of the new energy wide-body vehicle; The vibration sensor is installed at a preset key position on the housing of the all-in-one integrated controller to detect abnormal vibrations caused by loose power modules or malfunctioning cooling fans. The voltage sensor and current sensor are used to be installed between the all-in-one integrated controller and the controlled mechanism.

[0014] In conjunction with the first aspect, optionally, when the fault identification module determines that the output data of the fault monitoring unit exceeds a predetermined range value, a warning signal or a fault signal is generated.

[0015] In conjunction with the first aspect, the fault diagnosis system may optionally include an early warning feedback module, which generates a fault level based on the mapping relationship between fault type and fault level, and provides corresponding early warning prompts according to the fault level.

[0016] In conjunction with the first aspect, optionally, after the fault diagnosis module receives the output data from the fault monitoring unit, it preprocesses the output data and then extracts fault-sensitive features to generate a feature vector. The fault-sensitive features include: Temporal characteristics, including peak value, mean, variance, and kurtosis; Frequency domain characteristics, including spectral peaks and center frequency; Communication characteristics include data frame loss rate and response latency.

[0017] In a second aspect, the present invention provides a fault diagnosis method applicable to any one of the first aspects for a fault diagnosis system of an all-in-one integrated controller for new energy wide-body vehicles, comprising: Data is collected using a fault monitoring unit; The fault diagnosis module uses the output data of the fault monitoring unit to diagnose the fault category, and combines the identification code of the fault monitoring unit to determine the controlled mechanism that has malfunctioned, thus completing the fault location.

[0018] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention proposes a fault diagnosis system and method for an all-in-one integrated controller. It involves setting up several fault monitoring points located between the all-in-one integrated controller and the controlled mechanism, as well as at predetermined positions on the all-in-one integrated controller; and several fault monitoring units installed at corresponding fault monitoring points, each with a unique identification code. A fault diagnosis module performs fault category diagnosis based on the output data of the fault monitoring units, and determines the controlled mechanism experiencing the fault by combining the identification codes of the fault monitoring units, ultimately achieving simultaneous fault category diagnosis and fault location. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly described below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort, wherein: Figure 1 This is a schematic block diagram of a fault diagnosis system for an all-in-one integrated controller according to an embodiment of the present invention. Figure 2 This is a flowchart illustrating a fault diagnosis method for an all-in-one integrated controller according to an embodiment of the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0021] Furthermore, if the embodiments of this invention involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention. Example 1

[0022] This invention provides a fault diagnosis system for all-in-one integrated controllers, such as... Figure 1As shown, it includes: Several fault monitoring points are located between the all-in-one integrated controller and the controlled mechanism, as well as at predetermined positions of the all-in-one integrated controller. Several fault monitoring units are installed at corresponding fault monitoring points, and each fault monitoring unit is equipped with a unique identification code; The fault diagnosis module is connected to the fault monitoring unit. It performs fault category diagnosis based on the output data of the fault monitoring unit, and determines the controlled mechanism that has malfunctioned by combining the identification code of the fault monitoring unit, thus completing the fault location.

[0023] In the above scheme, several fault monitoring points are set up, located between the all-in-one integrated controller and the controlled mechanism, and at predetermined positions of the all-in-one integrated controller; and several fault monitoring units are installed at corresponding fault monitoring points, each with a unique identification code. A fault diagnosis module performs fault category diagnosis based on the output data of the fault monitoring units, and determines the controlled mechanism experiencing the fault by combining the identification code of the fault monitoring unit, ultimately achieving simultaneous fault category diagnosis and fault location. Furthermore, this scheme innovatively advances the fault diagnosis requirement to the hardware topology design stage of the all-in-one integrated controller. Unlike traditional topologies that only pursue optimal electrical performance, this embodiment of the invention introduces fault monitoring points and fault monitoring units with unique identification codes on critical power paths and signal links, giving the hardware topology itself a "fault map" attribute. In specific implementation, the controlled mechanisms include, but are not limited to: motor controllers, PTCs, oil pumps, air pumps, and air compressors.

[0024] In one specific embodiment of the present invention, the fault diagnosis module includes a fault identification module and a fault classification module; The fault identification module is configured to perform early warning or fault diagnosis based on the output data of the fault monitoring unit, and generate early warning signals or fault signals. In response to the warning signal or fault signal, the fault classification module performs fault category diagnosis based on the output data of the fault monitoring unit.

[0025] In one specific embodiment of the present invention, the fault diagnosis system further includes a fault data storage module. The fault data storage module has independent power supply and storage functions. The fault data storage module is connected to the all-in-one integrated controller and each fault monitoring unit through a CAN bus, and is used to store data in the all-in-one integrated controller, the CAN bus and each fault monitoring unit.

[0026] In the above solution, the fault data storage module enables full-cycle data recording and cloud synchronization, ensuring the complete traceability of the fault process.

[0027] In one specific embodiment of the present invention, the fault data storage module includes a connected circular buffer and a non-volatile memory; The circular buffer is used to store data from the all-in-one integrated controller, CAN bus, and various fault monitoring units; When the fault diagnosis module generates a warning signal or fault signal, it saves the current data from the all-in-one integrated controller, CAN bus, and fault monitoring unit, as well as the data from the all-in-one integrated controller, CAN bus, and each fault monitoring unit within a predetermined time period before and after the generation of the warning signal or fault signal, from the ring buffer to non-volatile memory, forming an indelible fault data packet. This fault data packet is then uploaded to the cloud analysis platform via the CAN bus for later analysis. In specific implementation, the fault data storage module continuously records key status parameters, CAN bus communication messages, drive signals, and raw data from the fault monitoring unit within the all-in-one integrated controller at a high sampling rate, storing them in a ring buffer with a capacity to cover 6 hours of continuous operation data. This 6-hour window design is sufficient to completely capture the typical entire process from the emergence and accumulation of potential faults to their final outbreak. When the fault diagnosis module generates a warning signal or fault signal, it not only records the current snapshot but also automatically saves the complete high-density data stream before and after the event trigger point (e.g., 5 minutes before and 1 minute after) from the buffer to non-volatile memory, forming an indelible "accident record" (i.e., fault data packet). When the entire system is in a safe state (such as when connected to Wi-Fi or cellular network), it automatically uploads the fixed fault data packets to the cloud analysis platform. This completely solves the cumbersome and delayed problem of traditional methods that require technicians to carry equipment to the site to connect cables and read data. It realizes "zero-contact" remote acquisition of fault data, providing a complete and reliable first-hand data source for subsequent big data analysis and in-depth root cause mining.

[0028] In one specific embodiment of this invention, the fault classification module is a deep learning model. During implementation, historical normal operation data and known fault data are used to train the deep learning model to learn the dynamic health evolution of the all-in-one integrated controller under multi-dimensional feature spaces (electrical, thermal, vibration, and operating conditions). The deep learning model can identify early abnormal patterns that are weakly below the alarm threshold and characterize performance degradation, thereby issuing warnings hundreds or even thousands of hours before the actual occurrence of a fault, achieving true predictive maintenance. When the fault classification module cannot output a fault category based on the output data of the fault monitoring unit, the output data is marked as a new type of anomaly and sent to the cloud analysis platform for manual fault labeling, generating corresponding fault type labels, and updating the deep learning model. This enables the fault diagnosis system in this embodiment of the invention to have the ability to evolve autonomously and continuously improve the diagnostic boundary, fundamentally solving the shortcomings of traditional systems in dealing with new types of faults.

[0029] In one specific embodiment of the present invention, the fault monitoring unit includes any one or more of a first temperature sensor, a second temperature sensor, a vibration sensor, a voltage sensor, and a current sensor; The first temperature sensor is used to be installed inside the all-in-one integrated controller; The second temperature sensor is used to install at the inlet and outlet of the cooling circuit of the new energy wide-body vehicle; The vibration sensor is installed at a preset key position on the housing of the all-in-one integrated controller to detect abnormal vibrations caused by loose power modules or malfunctioning cooling fans. The voltage and current sensors are installed between the all-in-one integrated controller and the controlled mechanism. In specific implementation, the output data of the fault monitoring unit includes: the bus voltage of the all-in-one integrated controller, the three-phase output current of the all-in-one integrated controller, the temperature of the IGBT chip inside the all-in-one integrated controller, the inlet and outlet temperatures of the cooling circuit, the vibration signal of the all-in-one integrated controller housing, and the communication data between the all-in-one integrated controller and the vehicle (from the CAN bus), etc., with timestamps added to achieve data synchronization. The sampling frequency is 1kHz-10kHz.

[0030] In one specific embodiment of the present invention, when the fault identification module determines that the output data of the fault monitoring unit exceeds a predetermined range value, a warning signal or a fault signal is generated.

[0031] In one specific embodiment of the present invention, the fault diagnosis system further includes an early warning feedback module, which generates a fault level based on the mapping relationship between fault type and fault level, and provides corresponding early warning prompts according to the fault level.

[0032] In the above scheme, the mapping relationship between fault type and fault level can be set according to actual needs during implementation. For example, a level one warning is for minor faults (such as slightly high cooling circuit temperature), a level two warning is for moderate faults (such as excessive communication frame loss rate), and an emergency alarm is for severe faults (such as IGBT chip overheating or sudden drop in bus voltage). The warning prompt can be an audible and visual alarm of the corresponding level issued to the driver, while simultaneously uploading fault information (fault code, fault time, operating condition data, and fault location results) to the vehicle controller and the background monitoring platform to provide a basis for maintenance.

[0033] In one specific embodiment of the present invention, after the fault diagnosis module receives the output data of the fault monitoring unit, it preprocesses the output data and then extracts fault-sensitive features to generate a feature vector. The fault-sensitive features include: Temporal characteristics, including peak value, mean, variance, and kurtosis; Frequency domain characteristics, including spectral peaks and center frequency; Communication characteristics include data frame loss rate and response latency.

[0034] In the above scheme, the preprocessing includes: filtering and denoising, outlier removal, and data standardization. Example 2

[0035] This invention provides a fault diagnosis method applicable to any one of the fault diagnosis methods in Embodiment 1 for a multi-integrated controller fault diagnosis system for new energy wide-body vehicles, comprising: (1) Data is collected using a fault monitoring unit; (2) The fault diagnosis module is used to diagnose the fault category based on the output data of the fault monitoring unit, and the fault location is completed by combining the identification code of the fault monitoring unit to determine the controlled mechanism that has a fault.

[0036] like Figure 2 As shown, the fault diagnosis method specifically includes the following steps: S1: Utilize the fault monitoring unit to achieve synchronous acquisition of multi-dimensional data; S2: Preprocess the collected data; S3: Perform feature engineering on the preprocessed data, i.e., extract fault-sensitive features; S4: Use the fault diagnosis module to diagnose fault categories based on fault-sensitive features; S5: Combine the identification code of the fault monitoring unit to determine the controlled mechanism that has malfunctioned, and classify the fault level according to the fault category diagnosis results; S6: Provide early warning feedback based on the results in S5, and upload the data.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

[0042] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A fault diagnosis system for an all-in-one integrated controller, characterized in that, include: Several fault monitoring points are located between the all-in-one integrated controller and the controlled mechanism, as well as at predetermined positions of the all-in-one integrated controller. Several fault monitoring units are installed at corresponding fault monitoring points, and each fault monitoring unit is equipped with a unique identification code; The fault diagnosis module is connected to the fault monitoring unit. It performs fault category diagnosis based on the output data of the fault monitoring unit, and determines the controlled mechanism that has malfunctioned by combining the identification code of the fault monitoring unit, thus completing the fault location.

2. The fault diagnosis system for an all-in-one integrated controller according to claim 1, characterized in that: The fault diagnosis module includes a fault identification module and a fault classification module; The fault identification module is configured to perform early warning or fault diagnosis based on the output data of the fault monitoring unit, and generate early warning signals or fault signals. In response to the warning signal or fault signal, the fault classification module performs fault category diagnosis based on the output data of the fault monitoring unit.

3. The fault diagnosis system for an all-in-one integrated controller according to claim 2, characterized in that: The fault diagnosis system also includes a fault data storage module, which has independent power supply and storage functions. The fault data storage module is connected to the all-in-one integrated controller and each fault monitoring unit via a CAN bus, and is used to store data from the all-in-one integrated controller, the CAN bus and each fault monitoring unit.

4. A fault diagnosis system for an all-in-one integrated controller according to claim 3, characterized in that: The fault data storage module includes a connected circular buffer and a non-volatile memory; The circular buffer is used to store data from the all-in-one integrated controller, CAN bus, and various fault monitoring units; When the fault diagnosis module generates a warning signal or a fault signal, it will save the current data in the all-in-one integrated controller, CAN bus and fault monitoring unit, as well as the data in the all-in-one integrated controller, CAN bus and each fault monitoring unit within a predetermined time period before and after the generation of the warning signal or fault signal, from the ring buffer to the non-volatile memory, forming an indelible fault data packet. The fault data packet is used to upload to the cloud analysis platform via the CAN bus for later analysis.

5. A fault diagnosis system for an all-in-one integrated controller according to claim 2, characterized in that: The fault classification module is a deep learning model; When the fault classification module cannot output a fault category based on the output data of the fault monitoring unit, it marks the output data as a new type of anomaly and sends it to the cloud analysis platform for manual fault labeling, generating corresponding fault type labels, and updating the deep learning model.

6. A fault diagnosis system for an all-in-one integrated controller according to claim 2, characterized in that: The fault monitoring unit includes any one or more of a first temperature sensor, a second temperature sensor, a vibration sensor, a voltage sensor, and a current sensor; The first temperature sensor is used to be installed inside the all-in-one integrated controller; The second temperature sensor is used to install at the inlet and outlet of the cooling circuit of the new energy wide-body vehicle; The vibration sensor is installed at a preset key position on the housing of the all-in-one integrated controller to detect abnormal vibrations caused by loose power modules or malfunctioning cooling fans. The voltage sensor and current sensor are used to be installed between the all-in-one integrated controller and the controlled mechanism.

7. A fault diagnosis system for an all-in-one integrated controller according to claim 6, characterized in that: When the fault identification module determines that the output data of the fault monitoring unit exceeds a predetermined range, it generates a warning signal or a fault signal.

8. A fault diagnosis system for an all-in-one integrated controller according to claim 1, characterized in that: The fault diagnosis system also includes an early warning feedback module, which generates a fault level based on the mapping relationship between fault type and fault level, and provides corresponding early warning prompts according to the fault level.

9. A fault diagnosis system for an all-in-one integrated controller according to claim 1, characterized in that: After the fault diagnosis module receives the output data from the fault monitoring unit, it preprocesses the output data and then extracts fault-sensitive features to generate a feature vector. The fault-sensitive features include: Temporal characteristics, including peak value, mean, variance, and kurtosis; Frequency domain characteristics, including spectral peaks and center frequency; Communication characteristics include data frame loss rate and response latency.

10. A fault diagnosis method applicable to the fault diagnosis system of the multi-integrated controller for new energy wide-body vehicles according to any one of claims 1-9, characterized in that, include: Data is collected using a fault monitoring unit; The fault diagnosis module uses the output data of the fault monitoring unit to diagnose the fault category, and combines the identification code of the fault monitoring unit to determine the controlled mechanism that has malfunctioned, thus completing the fault location.

Images