Intelligent troubleshooting system and method for engineering machinery
By collecting status signals from construction machinery and generating fault work orders, combined with an AI fault diagnosis system, the problem of low efficiency in fault diagnosis of construction machinery is solved, and efficient and accurate fault diagnosis and maintenance are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- JIANGSU ADVANCED CONSTR MASCH INNOVATION CENT LTD
- Filing Date
- 2025-12-05
- Publication Date
- 2026-04-10
AI Technical Summary
Fault diagnosis of engineering machinery systems is difficult to achieve efficient and accurate automated troubleshooting. Traditional methods rely on manual observation and experience, which are inefficient and costly.
Status signals are collected by sensing devices to generate fault work orders. Fault parameters are determined by fault diagnosis devices and compared with standard ranges to generate standard problems. Combined with AI fault diagnosis devices, intelligent diagnosis is performed to output fault causes and repair solutions.
It enables efficient and accurate automated troubleshooting of engineering machinery faults, improves equipment maintenance efficiency, and reduces fault repair time and costs.
Smart Images
Figure CN121836668A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to an intelligent fault diagnosis system and method for construction machinery, belonging to the field of intelligent fault diagnosis technology for construction machinery. Background Technology
[0002] The complex operating parameters and hidden faults of construction machinery systems make fault diagnosis difficult. Currently, traditional fault diagnosis mainly relies on manual observation and experience-based judgment, which suffers from high subjectivity, low efficiency, and high cost.
[0003] With the development of intelligent construction machinery, there is an urgent need for an efficient and accurate fault diagnosis method and system to improve equipment maintenance efficiency and reduce fault repair time and costs. Summary of the Invention
[0004] The purpose of this invention is to provide an intelligent fault diagnosis system and method for construction machinery. A sensing device collects status signals when the construction machinery performs actions. A fault diagnosis module generates a fault work order when the construction machinery's actions malfunction. The fault diagnosis device then determines the associated fault parameters based on the fault vehicle model and fault symptoms in the fault work order, and compares the parameter values with corresponding standard ranges to generate a standard description of parameter anomalies. Subsequently, a standard question is generated based on the fault vehicle model, fault symptoms, and the standard description of parameter anomalies. This achieves automated integration from status signal acquisition to the generation of standard questions for intelligent diagnostic inquiry. Finally, the standard question is input into the AI fault diagnosis device, which outputs a diagnostic answer including the fault cause, fault reasoning, and repair plan, thereby achieving efficient and accurate fault diagnosis and improving equipment maintenance efficiency.
[0005] This invention provides an intelligent fault diagnosis system for construction machinery, comprising: Sensing devices are used to collect status signals when construction machinery performs actions; Fault diagnosis device, including: The repair module is used to generate a fault work order when the engineering machinery performs abnormal actions. The fault work order includes the faulty model and the fault symptoms. The signal input and parsing module is used to receive the status signals collected by the sensing device after the fault work order is generated and parse them into the parameter values of the status parameters. The comparison module is used to determine the fault parameters associated with the fault phenomenon and their corresponding standard ranges in the status parameters based on the fault rule library of the current fault vehicle model, compare the parameter values of the fault parameters with the corresponding standard ranges, and generate a standard description of the parameter anomaly. The question-and-answer module is used to generate standard questions based on the vehicle model of the malfunction, the symptoms of the malfunction, and the standard description of abnormal parameters. The AI-powered fault diagnosis device receives standard questions generated by a fault diagnosis device and outputs diagnostic answers that include the cause of the fault, fault reasoning, and repair solutions.
[0006] Optionally, the status signal includes a voltage signal, a current signal, a velocity signal, and a displacement signal.
[0007] Optionally, the step of the signal input and parsing module receiving the status signal collected by the sensing device and parsing it into the parameter value of the status parameter after the fault work order is generated includes: The state signal is parsed into a binary digital signal; The binary digital signal is converted into decimal status parameter values according to a predefined communication protocol.
[0008] Optionally, before comparing the fault parameter value with the corresponding standard range, the state parameter value needs to be preprocessed, including digital filtering and normalization.
[0009] Optionally, it also includes: The communication system is used to enable data interaction between sensing devices, fault diagnosis devices, and AI fault diagnosis devices.
[0010] Optionally, the fault rule base is constructed and updated in real time based on historical data of fault phenomena, fault parameters, and standard ranges, and the fault rule base includes the correlation between fault phenomena, fault parameters, and standard ranges.
[0011] Optionally, the comparison module compares the parameter values of the fault parameters with the corresponding standard ranges and generates a standard description of the parameter anomalies, including: The fault parameter value is compared with the corresponding standard range to determine whether the fault parameter exceeds the standard range; If the value of the fault parameter is lower than the lower limit threshold of the standard range, then the abnormal proportion of parameter values lower than the lower limit threshold is determined based on the lower limit threshold. If the value of the fault parameter is higher than the upper limit threshold of the standard range, the abnormal proportion of parameter values higher than the upper limit threshold shall be determined based on the upper limit threshold. A parameter anomaly standard description is generated based on the parameter values of the fault parameters, the judgment results of whether they exceed the standard range, and the anomaly ratio when they exceed the standard range.
[0012] Optionally, the steps for the AI fault diagnosis device to receive standard questions generated by the fault diagnosis device and output diagnostic answers including fault causes, fault reasoning, and repair solutions include: The standard problem is transformed into a vector space to obtain a problem vector, and the problem vector is matched with a pre-built vector database to retrieve relevant fault causes and repair solutions; Based on the retrieved fault causes and repair solutions, a diagnostic response including fault causes, fault reasoning, and repair solutions is generated according to pre-set analytical reasoning logic.
[0013] Optionally, the training process for the AI fault diagnosis device includes: The AI fault diagnosis device is pre-trained using a general corpus and text from the engineering machinery field. The AI fault diagnosis device is trained using a training set constructed from the standard questions and answers. During the training process, an instruction fine-tuning strategy is adopted, and a trainable low-rank LoRA matrix is injected into the pre-acquired open-source model. During training, the parameters of the low-rank LoRA matrix are optimized in reverse according to the degree of difference between the diagnostic answer and the standard answer.
[0014] Optionally, the fault diagnosis device further includes: The human-computer interaction module is used to send standard questions generated by the question-and-answer module to the display module, and also to send standard questions generated by the question-and-answer module to the AI fault diagnosis device after the confirmation button on the display module is clicked, and to send the diagnostic answers output by the AI fault diagnosis device to the display module.
[0015] Secondly, this invention provides an intelligent fault diagnosis method for engineering machinery, comprising: Collect status signals when construction machinery performs actions; When construction machinery performs abnormal actions, a fault work order is generated. The fault work order includes the faulty model and the fault phenomenon. After a fault work order is generated, the collected status signals are parsed into the parameter values of the status parameters; Based on the fault rule base of the current faulty vehicle model, determine the fault parameters associated with the fault phenomenon and their corresponding standard ranges among the status parameters, compare the parameter values of the fault parameters with the corresponding standard ranges, and generate a standard description of parameter anomalies. Standard questions are generated based on the faulty vehicle model, fault symptoms, and abnormal parameter descriptions. The standard question is input into the AI fault diagnosis device, which outputs a diagnostic answer including the cause of the fault, fault reasoning, and repair solution.
[0016] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: This invention first collects status signals when construction machinery performs actions using a sensing device. These status signals can be parsed into parameter values of status parameters. A fault diagnosis device generates a fault work order when the construction machinery performs abnormal actions. Based on the fault vehicle model and fault symptoms in the fault work order, it determines the fault parameters associated with the fault symptoms and their corresponding standard ranges from the status parameters. The fault parameters are compared with the corresponding standard ranges to generate a parameter anomaly standard description. Finally, a standard question is generated based on the fault vehicle model, fault symptoms, and parameter anomaly standard description. An AI fault diagnosis device receives the standard question generated by the fault diagnosis device and outputs a diagnostic answer including the fault cause, fault reasoning, and repair plan. This invention's fault diagnosis device can convert fault symptoms into standard questions in a standard format for inquiry. The pre-trained AI fault diagnosis device can accurately understand key semantic information for standard questions in the standard format to obtain a diagnostic answer including the fault cause, fault reasoning, and repair plan through retrieval and reasoning, achieving efficient and accurate fault diagnosis and improving equipment maintenance efficiency. Attached Figure Description
[0017] Figure 1 This is a schematic diagram of the architecture of an intelligent fault diagnosis system for engineering machinery provided in an embodiment of the present invention; Figure 2 A flowchart illustrating the troubleshooting process of an intelligent fault diagnosis system for engineering machinery, provided as an embodiment of the present invention. Detailed Implementation
[0018] It should be noted that: The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations thereof. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.
[0019] The term "and / or" simply describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. Additionally, the character " / " generally indicates that the preceding and following related objects have an "or" relationship.
[0020] Combination Figure 1 This embodiment introduces an intelligent fault diagnosis system for engineering machinery, which includes a sensing device (sensing layer), a fault diagnosis device (application layer), and an AI fault diagnosis device (platform layer).
[0021] The sensing device is used to collect status signals when the engineering machinery performs actions. Specifically, the sensing device continuously monitors the physical parameters of each component of the equipment through a multi-source heterogeneous sensor array to realize the real-time acquisition of status signals. As an example, the status signals include voltage signals, current signals, speed signals, displacement signals and other equipment signals, and the status parameters include main pump pressure, amplitude change speed, amplitude change angle and other equipment parameters.
[0022] The fault diagnosis device includes a repair reporting module, a signal input and analysis module, a comparison module, and a question and answer module.
[0023] The repair reporting module is used to generate a fault work order when the engineering machinery performs abnormal actions. The fault work order includes the faulty model and the fault phenomenon. For example, the fault work order means that a user of a certain model reports that the extension and retraction action is slow, and the slow extension and retraction action is the fault phenomenon.
[0024] The signal input and parsing module receives and parses the status signals collected by the sensing device into status parameter values after a fault work order is generated. This module essentially comprises a signal input module and a signal parsing module. The signal input module receives various status signals collected by the sensing device from the engineering machinery controller, including multi-type sensor interfaces, signal conditioning circuits, and AD conversion units, for real-time acquisition of signals such as voltage, current, speed, and displacement from the equipment. It then parses these analog signals into binary digital signals that the system can recognize, store, and process. The signal parsing module, based on a predefined communication protocol, locates the signal definition by identifying the frame ID, extracts the target byte from the data field according to rules, converts it into a decimal digital quantity according to the specified byte order, and finally calculates the decimal parameter values with actual physical meaning using a scaling factor and offset, thus converting the binary digital signal into decimal status parameter values.
[0025] The comparison module is used to determine the fault parameters associated with the fault phenomenon and their corresponding standard ranges among the status parameters based on the fault rule base of the current faulty vehicle model. It then compares the parameter values of the fault parameters with the corresponding standard ranges and generates a standard description of the parameter anomaly. Specifically, different fault phenomena may be associated with the same fault parameter, but the corresponding standard ranges may differ. For example, the standard ranges for slow extension / retraction speed and slow luffing speed are different. Furthermore, the same fault phenomenon may correspond to different fault parameters and different standard ranges on different faulty vehicle models (e.g., cranes or excavators). Therefore, the fault parameters and their corresponding standard ranges need to be determined based on the fault phenomenon within the fault rule base of the current faulty vehicle model. The fault rule base is constructed based on historical data of fault phenomena, fault parameters, and standard ranges and is updated in real time. The fault rule base includes the relationships between fault phenomena, fault parameters, and standard ranges, with each fault phenomenon entry associated with a corresponding fault parameter and standard range.
[0026] Before comparing the fault parameter value with the corresponding standard range, the comparison module in this embodiment needs to preprocess the state parameter value. The preprocessing includes digital filtering and normalization to obtain standard data.
[0027] The comparison module compares the parameter values of the fault parameters with the corresponding standard ranges and generates a parameter anomaly standard description, including: comparing the parameter values of the fault parameters with the corresponding standard ranges to determine whether the fault parameters exceed the standard ranges; if the parameter values of the fault parameters are lower than the lower threshold of the standard range, then determining the anomaly ratio of parameter values below the lower threshold based on the lower threshold; if the parameter values of the fault parameters are higher than the upper threshold of the standard range, then determining the anomaly ratio of parameter values above the upper threshold based on the upper threshold; generating a parameter anomaly standard description based on the parameter values of the fault parameters, the judgment result of whether they exceed the standard ranges, and the anomaly ratio when they exceed the standard ranges. For example, the parameter anomaly standard description generated based on the parameter values of the fault parameters, the judgment result of whether they exceed the standard ranges, and the anomaly ratio when they exceed the standard ranges is expressed as: the current main pump pressure is 120 bar, lower than the lower threshold of 200 bar, and the anomaly ratio below the lower threshold is 40%.
[0028] The question-and-answer module is used to generate standard questions based on the faulty vehicle model, fault symptoms, and abnormal parameter descriptions; for example, the telescopic movement is slow, the main pump pressure is 120 bar, which is lower than the lower limit threshold of 200 bar, and the abnormality rate below the lower limit threshold is 40%. Please help me list the cause of the fault and the repair plan.
[0029] Combination Figure 2The AI fault diagnosis device in this embodiment receives standard questions generated by the fault diagnosis device and outputs diagnostic answers including fault causes, fault reasoning, and repair solutions. The cloud-based AI fault diagnosis device can provide intelligent fault Q&A and maintenance guidance services based on large language models and knowledge base technology.
[0030] The steps by which the AI fault diagnosis device receives standard questions generated by the fault diagnosis device and outputs diagnostic answers including fault causes, fault reasoning, and repair solutions include: The standard questions are transformed into a vector space to obtain question vectors. These question vectors are then matched with a pre-built vector database to retrieve relevant fault causes and repair solutions. This embodiment constructs a specialized private knowledge base for equipment fault diagnosis, integrating operation manuals, fault cases, repair manuals, and expert experience for engineering machinery. The vectorization model converts text into high-dimensional vectors, which are stored in the vector database. When a user asks a question, the system performs similarity matching between the question vector and the knowledge base to retrieve the most relevant fault cases and solutions. Based on the retrieved fault causes and repair solutions, a diagnostic answer including fault causes, fault reasoning, and repair solutions is generated according to pre-set analytical reasoning logic.
[0031] The AI fault diagnosis device in this embodiment differs from the general large-scale model. The large-scale model used in this system has undergone in-depth optimization and training specifically for the field of engineering machinery fault diagnosis. The domain-specific pre-training and fine-tuning strategies for the large-scale model of the AI fault diagnosis device include: Based on a general corpus, the model deeply integrates massive amounts of text in the field of engineering machinery, including structured maintenance manuals for various brands of equipment, unstructured fault case reports, sensor technical documents, and summaries of maintenance experience. This enables it to understand professional terms and concepts such as "hydraulic system," "pilot pressure," "PID control," and "CAN message."
[0032] The AI fault diagnosis device is trained using a training set constructed from the standard questions and answers. During training, an instruction fine-tuning strategy is adopted, and a trainable low-rank LoRA matrix is injected into the pre-acquired open-source model. During training, the parameters of the low-rank LoRA matrix are back-optimized based on the degree of difference between the diagnostic answer and the standard answer, thereby improving the accuracy of the model's answer, reducing the knowledge illusion of the large model, and achieving the effects of saving resources, maintaining performance, and switching in seconds. This enables the model to learn how to transform general language capabilities into professional answers that generate fault causes, fault reasoning, and repair solutions.
[0033] The AI fault diagnosis device in this embodiment utilizes its built-in attention mechanism to accurately analyze user-reported faults and perform parallel analysis of multi-source heterogeneous data such as system logs, performance metrics, and topology relationships. It supports efficient fine-tuning of domain-specific fault data, enabling rapid adaptation to specific operational environments and shortening fault location time. Furthermore, the AI fault diagnosis device in this embodiment employs user account and permission management to achieve multi-tenant isolation and access control, ensuring that different users (maintenance personnel, administrators, customers, etc.) can only access data and functions within their authorized scope.
[0034] Furthermore, the fault diagnosis device in this embodiment also includes a human-computer interaction module. This module is used to send standard questions generated by the question-and-answer module to the display module, and also to send the standard questions generated by the question-and-answer module to the AI fault diagnosis device after the confirmation button on the display module is clicked. Additionally, it is used to send the diagnostic answers output by the AI fault diagnosis device to the display module. In practical applications, maintenance personnel can confirm the information through the display module, or they can supplement the description based on the standard questions and input the problem via voice into the AI fault diagnosis device. The AI troubleshooting device in this embodiment features Chinese speech recognition and semantic understanding capabilities. It integrates an advanced speech recognition engine, supporting accurate conversion of technical terms. The semantic understanding module, based on a large AI model, accurately understands the fault phenomena and problems described by users in natural language. Furthermore, this AI troubleshooting device supports context-aware multi-turn dialogue capabilities, accurately understanding subsequent user questions based on historical dialogue content, enabling in-depth and coherent troubleshooting dialogue. Maintenance personnel can also "accept," "correct," or "reject" diagnostic results, which are anonymized to form high-quality feedback data. This feedback data is used for periodic fine-tuning or reinforcement learning of the model, allowing it to continuously adapt to new fault modes, improve maintenance suggestions, and achieve continuous evolution of diagnostic capabilities.
[0035] In this embodiment, the sensing device, fault diagnosis device, and AI fault investigation device interact with each other through a communication system. The communication system provides multiple communication interfaces, including Ethernet, Wi-Fi, 4G / 5G, etc., and supports industrial protocols such as CAN / CANopen, Modbus, and PROFIBUS-DP to ensure device compatibility.
[0036] Another embodiment provides an intelligent fault diagnosis method for construction machinery, which includes: Collect status signals when construction machinery performs actions; When construction machinery performs abnormal actions, a fault work order is generated. The fault work order includes the faulty model and the fault phenomenon. After a fault work order is generated, the collected status signals are parsed into the parameter values of the status parameters; Based on the fault rule base of the current faulty vehicle model, determine the fault parameters associated with the fault phenomenon and their corresponding standard ranges among the status parameters, compare the parameter values of the fault parameters with the corresponding standard ranges, and generate a standard description of parameter anomalies. Standard questions are generated based on the faulty vehicle model, fault symptoms, and abnormal parameter descriptions. The standard question is input into the AI fault diagnosis device, which outputs a diagnostic answer including the cause of the fault, fault reasoning, and repair solution.
[0037] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention 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 invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. 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 illustrations and / or block diagrams. 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.
Claims
1. An intelligent fault diagnosis system for engineering machinery, characterized in that, include: Sensing devices are used to collect status signals when construction machinery performs actions; Fault diagnosis device, including: The repair module is used to generate a fault work order when the engineering machinery performs abnormal actions. The fault work order includes the faulty model and the fault symptoms. The signal input and parsing module is used to receive the status signals collected by the sensing device after the fault work order is generated and parse them into the parameter values of the status parameters. The comparison module is used to determine the fault parameters associated with the fault phenomenon and their corresponding standard ranges in the status parameters based on the fault rule library of the current fault vehicle model, compare the parameter values of the fault parameters with the corresponding standard ranges, and generate a standard description of the parameter anomaly. The question-and-answer module is used to generate standard questions based on the vehicle model of the malfunction, the symptoms of the malfunction, and the standard description of abnormal parameters. The AI-powered fault diagnosis device receives standard questions generated by a fault diagnosis device and outputs diagnostic answers that include the cause of the fault, fault reasoning, and repair solutions.
2. The intelligent fault diagnosis system for engineering machinery according to claim 1, characterized in that, The steps by which the signal input and parsing module receives the status signal collected by the sensing device and parses it into the parameter values of the status parameters after the fault work order is generated include: The state signal is parsed into a binary digital signal; The binary digital signal is converted into decimal status parameter values according to a predefined communication protocol.
3. The intelligent fault diagnosis system for engineering machinery according to claim 2, characterized in that, Before comparing the fault parameter values with the corresponding standard range, the state parameter values need to be preprocessed, including digital filtering and normalization.
4. The intelligent fault diagnosis system for engineering machinery according to claim 1, characterized in that, Also includes: The communication system is used to enable data interaction between sensing devices, fault diagnosis devices, and AI fault diagnosis devices.
5. The intelligent fault diagnosis system for engineering machinery according to claim 1, characterized in that, The fault rule base is built and updated in real time based on historical data of fault phenomena, fault parameters, and standard ranges. The fault rule base includes the correlation between fault phenomena, fault parameters, and standard ranges.
6. The intelligent fault diagnosis system for engineering machinery according to claim 1, characterized in that, The comparison module compares the fault parameter values with the corresponding standard ranges and generates a standard description of the parameter anomaly, including: The fault parameter value is compared with the corresponding standard range to determine whether the fault parameter exceeds the standard range; If the value of the fault parameter is lower than the lower limit threshold of the standard range, then the abnormal proportion of parameter values lower than the lower limit threshold is determined based on the lower limit threshold. If the value of the fault parameter is higher than the upper limit threshold of the standard range, the abnormal proportion of parameter values higher than the upper limit threshold shall be determined based on the upper limit threshold. A parameter anomaly standard description is generated based on the parameter values of the fault parameters, the judgment results of whether they exceed the standard range, and the anomaly ratio when they exceed the standard range.
7. The intelligent fault diagnosis system for engineering machinery according to claim 1, characterized in that, The steps by which the AI fault diagnosis device receives standard questions generated by the fault diagnosis device and outputs diagnostic answers including fault causes, fault reasoning, and repair solutions include: The standard problem is transformed into a vector space to obtain a problem vector, and the problem vector is matched with a pre-built vector database to retrieve relevant fault causes and repair solutions; Based on the retrieved fault causes and repair solutions, a diagnostic response including fault causes, fault reasoning, and repair solutions is generated according to pre-set analytical reasoning logic.
8. The intelligent fault diagnosis system for engineering machinery according to claim 1, characterized in that, The training process for the AI fault diagnosis device includes: The AI fault diagnosis device is pre-trained using a general corpus and text from the engineering machinery field. The AI fault diagnosis device is trained using a training set constructed from the standard questions and answers. During the training process, an instruction fine-tuning strategy is adopted, and a trainable low-rank LoRA matrix is injected into the pre-acquired open-source model. During training, the parameters of the low-rank LoRA matrix are optimized in reverse according to the degree of difference between the diagnostic answer and the standard answer.
9. The intelligent fault diagnosis system for engineering machinery according to claim 1, characterized in that, The fault diagnosis device also includes: The human-computer interaction module is used to send standard questions generated by the question-and-answer module to the display module, and also to send standard questions generated by the question-and-answer module to the AI fault diagnosis device after the confirmation button on the display module is clicked, and to send the diagnostic answers output by the AI fault diagnosis device to the display module.
10. A method for intelligent fault diagnosis of engineering machinery, characterized in that, include: Collect status signals when construction machinery performs actions; When construction machinery performs abnormal actions, a fault work order is generated. The fault work order includes the faulty model and the fault phenomenon. After a fault work order is generated, the collected status signals are parsed into the parameter values of the status parameters; Based on the fault rule library of the current faulty vehicle model, determine the fault parameters associated with the fault phenomenon and their corresponding standard ranges among the status parameters, compare the parameter values of the fault parameters with the corresponding standard ranges, and generate a standard description of the parameter anomaly. Standard questions are generated based on the faulty vehicle model, fault symptoms, and abnormal parameter descriptions. The standard questions are input into the AI fault diagnosis device to output a diagnostic answer that includes the cause of the fault, fault reasoning, and repair plan.