Digital factory equipment operation and maintenance management platform and method
By deploying multimodal sensors on factory equipment to collect data and perform intelligent processing, the problem of low efficiency of traditional manual inspections has been solved, the automation and intelligence of equipment operation and maintenance management has been achieved, and the accuracy and efficiency of operation and maintenance management have been improved.
Patent Information
- Application Number
- CN202510907675.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-02
- Publication Date
- 2025-10-10
AI Technical Summary
Traditional equipment operation and maintenance management methods rely on manual inspections, which are inefficient, prone to missed inspections and false inspections, and unable to detect potential equipment failures in a timely manner, resulting in low equipment operation and maintenance management efficiency.
By deploying multimodal sensors on factory equipment to collect initial data on equipment operating conditions, the data is processed to obtain equipment status data, which is compared with preset status thresholds and matched with operation and maintenance management plans, realizing automation and intelligence from equipment status monitoring to operation and maintenance decision-making.
It improves the accuracy and efficiency of operation and maintenance management, timely discovers potential equipment failures, avoids missed detection and false detection, reduces operation and maintenance costs, and ensures stable operation of equipment.
Smart Images

Figure CN120762369A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of digital factory management, and in particular to a digital factory equipment operation and maintenance management platform and method. Background Art
[0002] Digital factory equipment operation and maintenance management encompasses daily maintenance, troubleshooting, efficiency optimization, and lifecycle management. The level of equipment operation and maintenance management directly impacts a factory's production efficiency, product quality, and operating costs. Traditional equipment operation and maintenance management relies primarily on manual inspections, paper records, and scheduled maintenance. Staff conduct inspections of equipment according to a pre-defined schedule, recording operating parameters and fault conditions, and scheduling maintenance based on experience. Furthermore, equipment maintenance history and technical documentation are often stored in disparate files and systems, making centralized management and quick access difficult.
[0003] As factories expand and equipment complexity increases, the drawbacks of traditional operations and maintenance management methods become increasingly apparent. Paper records are easily lost or damaged, information is not updated in a timely manner, and equipment maintenance decisions lack accurate data support, resulting in low equipment operation and maintenance management efficiency. Furthermore, manual inspections are inefficient, prone to missed inspections and false detections, and unable to detect potential equipment failures in a timely manner. Summary of the Invention
[0004] In view of this, the present invention proposes a digital factory equipment operation and maintenance management platform and method, aiming to solve the problems of low efficiency of existing manual inspections, prone to missed inspections and false inspections, and inability to timely detect potential equipment failures, resulting in low efficiency of equipment operation and maintenance management.
[0005] In one aspect, the present invention provides a digital factory equipment operation and maintenance management method, comprising:
[0006] Obtain initial equipment operating condition data collected by multimodal sensors deployed on factory equipment over a period of time;
[0007] Processing the initial data of the equipment operating condition to obtain equipment status data representing the degree of equipment degradation;
[0008] Obtaining a device status comparison parameter based on the device status data and a preset status threshold;
[0009] Based on the equipment status comparison parameters, an operation and maintenance plan is matched in a preset operation and maintenance management plan to obtain a result of digital factory equipment operation and maintenance management.
[0010] Furthermore, the step of obtaining initial equipment operating condition data collected by multimodal sensors deployed on factory equipment over a period of time includes:
[0011] Obtain vibration data, temperature data, and current data collected by multimodal sensors deployed on factory equipment over a period of time;
[0012] The vibration data, temperature data and current data are standardized to obtain initial equipment operating condition data.
[0013] Furthermore, the step of processing the initial equipment operating condition data to obtain equipment status data representing the degree of equipment degradation includes:
[0014] Performing denoising on the initial equipment operating condition data to obtain denoised initial equipment operating condition data;
[0015] Extracting key features reflecting the equipment status from the denoised initial equipment operating condition data and normalizing the data to obtain key feature data;
[0016] The key feature data are fused to obtain the equipment status data that characterizes the degree of equipment degradation.
[0017] Furthermore, the step of obtaining a device status comparison parameter based on the device status data and a preset status threshold includes:
[0018] The device status data is compared with a preset status threshold value to obtain a device status comparison parameter.
[0019] Furthermore, the step of constructing the preset state threshold includes:
[0020] Obtain historical equipment status data during normal operation of the equipment;
[0021] Performing standardization processing on historical equipment status data to obtain processed historical equipment status data;
[0022] Extract key features from the processed historical equipment status data to obtain key features of historical data;
[0023] Based on the key features of the historical data, a preset status threshold is determined.
[0024] Furthermore, based on the key features of the historical data, the step of determining the preset state threshold further includes:
[0025] Determining a preliminary threshold value for a preset state and a historical volatility parameter based on the key features of the historical data;
[0026] Compare the volatility threshold with the historical volatility parameter to obtain the adjustment update coefficient;
[0027] The preset state threshold is adjusted using the adjustment update coefficient to obtain the preset state threshold.
[0028] Furthermore, the step of performing a difference comparison between the device status data and a preset status threshold to obtain a device status comparison parameter includes:
[0029] confirming device status parameters based on the device status data;
[0030] Verifying the device status parameters to determine the device status coefficient;
[0031] The device state coefficient is compared with a preset state threshold value to obtain a device state comparison parameter.
[0032] Furthermore, in the step of matching the operation and maintenance plan in the preset operation and maintenance management plan based on the equipment status comparison parameter to obtain the result of digital factory equipment operation and maintenance management,
[0033] Identify that the device status comparison parameter is within a corresponding parameter interval in the preset operation and maintenance management solution;
[0034] Based on the parameter range, matching the corresponding operation and maintenance management plan in the preset operation and maintenance management plan;
[0035] Based on the operation and maintenance management plan, confirm the results of digital factory equipment operation and maintenance management.
[0036] Furthermore, the construction of the preset operation and maintenance management plan includes:
[0037] Obtain equipment types, failure modes, preset failure parameter ranges, and historical operation and maintenance plans within the factory;
[0038] Based on the equipment type, failure mode, preset failure parameter range and historical operation and maintenance plans, a preset operation and maintenance management plan is constructed.
[0039] Compared with the prior art, the beneficial effects of the present invention are: by obtaining the initial data of equipment operating conditions collected by multimodal sensors deployed on factory equipment over a period of time, the mechanical, thermal and electrical conditions of the equipment can be fully obtained; by processing the initial data of equipment operating conditions, equipment status data characterizing the degree of equipment degradation is obtained, thereby being able to more accurately and reliably reflect the degree of degradation of the equipment's real-time operating status; after comparing the equipment status data with the preset status threshold, the equipment status comparison parameter is obtained, which can intuitively judge the size of the difference and thus improve the accuracy and efficiency of operation and maintenance management; finally, the operation and maintenance management plan is matched with the preset operation and maintenance management plan by the equipment status comparison parameter, thereby obtaining the result of digital factory equipment operation and maintenance management, which can realize automation and intelligence from equipment status monitoring to operation and maintenance decision-making, timely discover potential faults of equipment, avoid missed detection and false detection of equipment, improve the accuracy of operation and maintenance, and also significantly improve operation and maintenance efficiency, reduce operation and maintenance costs, and ensure stable operation of equipment.
[0040] On the other hand, the present application also provides a digital factory equipment operation and maintenance management platform for applying the digital factory equipment operation and maintenance management method as described in any of the above claims, including:
[0041] An acquisition module is used to obtain initial equipment operating condition data collected by multimodal sensors deployed on factory equipment over a period of time;
[0042] A data processing module is used to process the initial data of the equipment working condition to obtain equipment status data representing the degree of equipment degradation;
[0043] A comparison module, configured to obtain a device status comparison parameter based on the device status data and a preset status threshold;
[0044] The matching module is used to match the operation and maintenance plan in the preset operation and maintenance management plan based on the equipment status comparison parameters to obtain the results of digital factory equipment operation and maintenance management.
[0045] It is understandable that the above-mentioned digital factory equipment operation and maintenance management platform and method have the same beneficial effects and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:
[0047] Figure 1 This is a flow chart of a digital factory equipment operation and maintenance management method provided by an embodiment of the present invention.
[0048] Figure 2 This is a functional block diagram of the digital factory equipment operation and maintenance management platform provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0049] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, unless there is a conflict, the embodiments of the present disclosure and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
[0050] In some embodiments of the present application, see Figure 1 As shown in the figure, a digital factory equipment operation and maintenance management method comprises the following steps:
[0051] S100, acquiring equipment working condition initial data collected by a multi-modal sensor deployed on a factory equipment in a period of time. The multi-modal sensor is selected to at least integrate sensors capable of synchronously collecting vibration data, temperature data and current data. For example, the mechanical vibration signal of the equipment collected by the multi-modal sensor in a period of time is collected by integrating an acceleration sensor or a vibration sensor, so as to reflect the dynamic characteristics of the equipment during operation; the temperature value of the surface or key components of the equipment collected by the multi-modal sensor in a period of time is collected by integrating an infrared temperature sensor or a thermocouple; the power supply current signal of the equipment collected by the multi-modal sensor in a period of time is collected by a current transformer or a power analyzer. Specifically, the period of time can be 1 hour, 6 hours, 12 hours or 24 hours. The equipment working condition initial data is the raw running state information directly collected by the multi-modal sensor deployed on the factory equipment without processing. If the vibration abnormality is shown in the equipment working condition initial data, it may be accompanied by current fluctuation and temperature rise, so as to comprehensively reflect the mechanical, thermal and electrical states of the equipment, and provide original basis for subsequent data processing, state evaluation and operation and maintenance decision; more diverse data is collected, the data is more comprehensive, and thus the potential failure of the equipment can be found in time, and the efficiency of equipment operation and maintenance management is improved.
[0052] S200, data processing and processing of the equipment working condition initial data to obtain equipment state data representing the degree of equipment degradation. The processing includes data cleaning, preprocessing and feature enhancement, so as to facilitate subsequent state evaluation and decision. The equipment state data is obtained after data cleaning, preprocessing and feature enhancement of the equipment working condition initial data, and can more accurately and reliably reflect the degree of degradation of the real-time running state of the equipment.
[0053] S300, obtaining equipment state comparison parameters based on the equipment state data and a preset state threshold. The preset state threshold is the allowable range or reference value of the degree of equipment degradation under normal running state of the equipment. The equipment state comparison parameters are the difference or ratio based on the equipment state data and the preset state threshold, and the size of the equipment state comparison parameters can be directly obtained to improve the accuracy and efficiency of operation and maintenance management.
[0054] S400: Based on the device status comparison parameters, an operation and maintenance plan is matched against a preset operation and maintenance management plan to obtain the results of digital factory device operation and maintenance management. A preset operation and maintenance management plan is a set of predefined operation and maintenance measures, rules, and policies for different device states. It is developed based on the device's historical operating data, failure modes, operation and maintenance experience, and business needs. When the device status exceeds the normal range, the most appropriate operation and maintenance measures are quickly matched to ensure stable operation of the device and optimize operation and maintenance costs. A set of structured operation and maintenance instructions and rules clearly define the operation and maintenance measures to be taken under different device states, along with the required resources, execution sequence, and expected results. Operation and maintenance operations performed by the device include lubrication, component replacement, downtime for maintenance, or parameter adjustment. When the device status comparison parameters exceed the corresponding normal range in the preset operation and maintenance management plan, it indicates that the device is in an abnormal state and requires appropriate operation and maintenance measures such as manual intervention inspection and maintenance, troubleshooting, or efficiency optimization. This allows for matching different types of operation and maintenance plans, such as manual intervention inspection and maintenance, troubleshooting, or efficiency optimization. When the device status comparison parameter does not exceed the normal range value corresponding to the preset operation and maintenance management plan, it indicates that the current device is in normal operation and only normal operation and maintenance measures need to be adopted to match the daily maintenance operation and maintenance plan.
[0055] It can be understood that this application obtains the initial equipment operating condition data collected by multimodal sensors deployed on factory equipment over a period of time, so as to comprehensively obtain the mechanical, thermal and electrical conditions of the equipment, and the data is more comprehensive. By processing the initial equipment operating condition data, equipment status data representing the degree of equipment degradation is obtained, so that the degree of degradation of the equipment's real-time operating status can be more accurately and reliably reflected; after comparing the equipment status data with the preset status threshold, the equipment status comparison parameter is obtained, which can intuitively judge the size of the difference and thus improve the accuracy and efficiency of operation and maintenance management; finally, the operation and maintenance management plan is matched with the preset operation and maintenance management plan through the equipment status comparison parameter, so as to obtain the result of digital factory equipment operation and maintenance management, which can realize automation and intelligence from equipment status monitoring to operation and maintenance decision-making, timely discover potential equipment failures, avoid missed detection and false detection of equipment, improve the accuracy of operation and maintenance, and also significantly improve operation and maintenance efficiency, reduce operation and maintenance costs, and achieve stable operation of equipment.
[0056] In some embodiments of the present application, step S100: obtaining initial equipment operating condition data collected by multimodal sensors deployed on factory equipment over a period of time includes:
[0057] The vibration data, temperature data and current data collected by the multi-modal sensors deployed on the factory equipment over a period of time are acquired. Among them, the mechanical vibration signal of the equipment collected by the acceleration sensor or vibration sensor over a period of time reflects the dynamic characteristics of the equipment when it is running. To detect mechanical faults of the equipment (such as bearing wear, gear meshing abnormality and rotor imbalance). The temperature data is the temperature value of the surface or key components of the equipment collected by the infrared temperature sensor or thermocouple over a period of time; to monitor the thermal state of the equipment (such as motor winding temperature or bearing temperature). The current data is the power supply current signal of the equipment collected by the current transformer or power analyzer over a period of time; for evaluating the electrical system state (such as motor load or power factor), which can detect electrical faults (such as inter-turn short circuit, three-phase imbalance and overload).
[0058] The vibration data, temperature data and current data are standardized to obtain initial equipment working condition data. Specifically, the existing standardization method is used for standardization processing, so that the data of different dimensions and different orders of magnitude are converted to the same dimension or the same order of magnitude, so as to facilitate subsequent analysis and eliminate the influence of different sensor dimensions and orders of magnitude. At the same time, it is convenient to process the initial equipment working condition data. By obtaining the initial equipment working condition data including vibration data, temperature data and current data, the data is more comprehensive, which can make the subsequent matching operation and maintenance scheme more accurate, and the potential faults of the equipment can be found in time, and the efficiency of equipment operation and maintenance management is improved.
[0059] In some embodiments of the present application, the step of processing the initial equipment working condition data to obtain equipment state data representing the degree of equipment degradation comprises:
[0060] The initial equipment working condition data is denoised to obtain denoised initial equipment working condition data. In this embodiment, the existing denoising algorithm is used to denoise the initial equipment working condition data, such as using wavelet threshold denoising method to denoise the vibration data; using moving average filtering or Kalman filtering to remove noise in the temperature data or current data. So as to remove abnormal values such as vibration impact or current peak. To improve the accuracy and data quality of the initial equipment working condition data.
[0061] Key features reflecting the equipment state are extracted from the denoised initial equipment working condition data and normalized to obtain key feature data. The key features are the core parameters or indexes extracted from the equipment state data that can directly reflect the health status and running state of the equipment. Specifically, the mean value is extracted from the denoised initial equipment working condition data as the key feature. Then the key feature is normalized, and the dimension is unified, which is convenient for subsequent state evaluation and decision making, such as using Z-Score standardization method to normalize the key feature to obtain key feature data. Thus, high-quality quantitative data is obtained.
[0062] The key feature data is fused to obtain device status data representing the degree of device degradation. In this embodiment, the multimodal data (vibration, temperature, current) is subjected to correlation analysis using an existing fusion algorithm to obtain device status data representing the degree of device degradation.
[0063] By fusing key characteristic data, we generate device status data that characterizes the degree of equipment degradation. This prevents a single sensor from accurately reflecting the overall equipment status due to factors such as installation location, measurement range, or environmental interference. By integrating information from multiple sensors, data fusion can overcome the shortcomings of a single sensor and comprehensively reflect the mechanical, thermal, and electrical status of the equipment, reducing errors and improving data integrity, thereby providing more accurate judgment data.
[0064] In some embodiments of the present application, the step of obtaining a device status comparison parameter based on the device status data and a preset status threshold includes:
[0065] The device status data is compared with a preset status threshold value to obtain a device status comparison parameter. By calculating the difference between the device status data and the preset status threshold value as the device status comparison parameter, the device status comparison parameter can be intuitively judged to determine whether the current status of the device is normal, thereby improving the accuracy and efficiency of operation and maintenance management.
[0066] In some embodiments of the present application, the step of establishing the preset state threshold includes:
[0067] Acquire historical device status data during normal operation. Specifically, historical device status data includes at least vibration data, temperature data, and current data, obtained by removing outliers and noise during normal operation. This ensures the quality and reliability of the data acquired during normal operation.
[0068] The historical equipment status data is standardized to obtain the processed historical equipment status data. Through the standardization process, the historical equipment status data is unified in dimension, which is convenient for subsequent data extraction.
[0069] Key features are extracted from the processed historical device status data to obtain historical data key features. Historical data key features are average values extracted from the device's historical operating data during normal operation, enabling better device status assessment, fault diagnosis, and operation and maintenance decision-making. In this embodiment, historical data key features are obtained by extracting the minimum, mean, or maximum value from the processed historical device status data using a fusion formula.
[0070] Based on the key features of the historical data, a preset state threshold is determined. The preset state threshold is determined by referencing the allowable range or baseline value of the device degradation degree using the key features of the historical data. The preset state threshold is then used to compare device state comparison parameters and determine the device parameter state.
[0071] In some embodiments of the present application, the step of determining the preset status threshold based on the key features of the historical data further includes:
[0072] Based on the key features of the historical data, a preliminary threshold for the preset state and a historical volatility parameter are determined. The preliminary threshold for the preset state is the initial allowable range or baseline value for the degree of equipment degradation under normal operating conditions. The historical volatility parameter is an indicator used to quantify the degree of fluctuation in equipment status data over a historical period.
[0073] The volatility threshold is compared with the historical volatility parameter to obtain an adjustment update coefficient. The volatility threshold is a baseline value used to quantify the permissible range of fluctuations in device status data within a historically normal time period. The adjustment update coefficient is calculated by comparing the volatility threshold with the historical volatility parameter to obtain the ratio of the volatility threshold to the historical volatility parameter. This ratio is used as the adjustment update coefficient to dynamically adjust the initial threshold for the preset status, thereby determining a more accurate threshold for the preset status.
[0074] The preset state threshold is adjusted using the adjustment update coefficient to obtain the preset state threshold. Specifically, the preset state threshold is used as a reference, and the product of the adjustment update coefficient and the preset state threshold is added to the preset state threshold to obtain the preset state threshold, thereby achieving dynamic adjustment of the preset state threshold.
[0075] As can be understood, the initial threshold for the preset state and the historical volatility parameter are determined based on key features of historical data. The adjustment update coefficient is obtained by comparing the volatility threshold with the historical volatility parameter. The initial threshold for the preset state is adjusted using the adjustment update coefficient to obtain the preset state threshold. This allows for dynamic adjustment to device state changes, avoiding errors in the preset state threshold and ensuring its accuracy and effectiveness. Comparing the updated preset state threshold with device state data more accurately reflects the device's actual operating status, thereby improving the accuracy and efficiency of operation and maintenance management.
[0076] In some embodiments of the present application, the step of obtaining a device status comparison parameter based on the device status data and a preset status threshold includes:
[0077] Based on the device status data, device status parameters are determined, wherein the device status parameters are quantifiable and comparable evaluation indicators extracted from the device status data.
[0078] In this embodiment, the device state data is fused by using a fusion formula to determine the device state parameter. The fusion formula is as follows:
[0079] D f =α·D v +β·D t +γ·D c ;
[0080] wherein D f represents a device state parameter, D v represents an absolute value of a mean value of vibration data in a period of time, D t represents an absolute value of a mean value of temperature data in a period of time, D c represents an absolute value of a mean value of current data in a period of time, and α, β, and γ are weight coefficients, and α+β+γ=1. It can be understood that α, β, and γ are empirically set according to different devices, for example, α=0.6, β=0.3, and γ=0.1 for a rotating machine.
[0081] The device state parameter is verified to determine a device state coefficient. By verifying the device state parameter, fusion errors are avoided, the correctness of the device state coefficient is determined, errors are reduced, and the accuracy of operation and maintenance management is improved.
[0082] In this embodiment, the device state coefficient is compared with a preset state threshold value by difference to obtain a device state comparison parameter. The device state comparison parameter is a difference between the device state coefficient and the preset state threshold value, which reflects the gap between the device state coefficient and the preset state threshold value. Specifically, by comparing the device state coefficient with the preset state threshold value, the device state comparison parameter is obtained, which can accurately reflect the device health condition and provide a quantitative basis for predictive maintenance, fault diagnosis, and operation and maintenance decision-making, and finally realize optimization of device life cycle management.
[0083] In some embodiments of the present application, the construction of the preset operation and maintenance management scheme includes:
[0084] Obtaining device types, failure modes, preset failure parameter intervals, and historical operation and maintenance schemes in a factory.
[0085] Based on the device types, failure modes, preset failure parameter intervals, and historical operation and maintenance schemes, a preset operation and maintenance management scheme is constructed.
[0086] Specifically, the preset operation and maintenance management scheme is a collection of a series of operation and maintenance measures, rules and strategies defined in advance for different equipment states. Based on the historical operation data, failure mode, operation and maintenance experience and business requirements of the equipment, the knowledge base is classified, including: classified by equipment type: such as numerical control machine tool operation and maintenance scheme and industrial robot operation and maintenance scheme; classified by failure mode: such as bearing wear operation and maintenance scheme and motor overheating operation and maintenance scheme; classified by operation and maintenance target: such as preventive maintenance scheme and emergency repair scheme. It can be understood that the scheme matching process is triggered according to the ratio between the equipment state comparison parameter and the preset state threshold value. According to the ratio, the information of the equipment type, failure mode and operation and maintenance target mapped by the preset failure parameter interval is retrieved in the scheme library to find the most suitable preset operation and maintenance scheme. For example, when the equipment state comparison parameter exceeds the normal range, the most suitable operation and maintenance measures such as lubrication, component replacement, shutdown maintenance or parameter adjustment, as well as the required spare parts list, tool list and estimated working hours, etc. can be quickly matched; so as to realize equipment failure elimination, performance recovery and reliability improvement, etc.; to ensure the stable operation of the equipment and optimize the operation and maintenance cost.
[0087] In another preferred mode based on the above embodiment, referring to Figure 2 The present embodiment provides a digital factory equipment operation and maintenance management platform for applying the above-mentioned digital factory equipment operation and maintenance management method, which includes an acquisition module 210, a data processing module 220, a comparison module 230 and a matching module 240.
[0088] The acquisition module 210 is used to acquire the initial equipment working condition data collected by the multi-modal sensor deployed on the factory equipment within a period of time.
[0089] The data processing module 220 is used to process the initial equipment working condition data to obtain equipment state data representing the degree of equipment degradation.
[0090] The comparison module 230 is used to obtain the equipment state comparison parameter based on the equipment state data and the preset state threshold value.
[0091] The matching module 240 is used to match the operation and maintenance scheme in the preset operation and maintenance management scheme based on the equipment state comparison parameter to obtain the result of the digital factory equipment operation and maintenance management.
[0092] Acquisition module 210 acquires initial equipment operating condition data collected over a period of time by multimodal sensors deployed on factory equipment, thereby comprehensively capturing the mechanical, thermal, and electrical conditions of the equipment. Data processing module 220 processes the initial equipment operating condition data to obtain equipment status data representing the degree of equipment degradation, thereby more accurately and reliably reflecting the degree of degradation of the equipment's real-time operating status. Comparison module 230 obtains equipment status comparison parameters based on the equipment status data and preset status thresholds, enabling intuitive judgment of the difference and improving the accuracy and efficiency of operation and maintenance management. Matching module 240 matches the equipment status comparison parameters with the preset operation and maintenance management plan to obtain the results of digital factory equipment operation and maintenance management. This enables automation and intelligence from equipment status monitoring to operation and maintenance decision-making, improving the accuracy of operation and maintenance, while also significantly improving operation and maintenance efficiency and reducing operation and maintenance costs to ensure stable equipment operation.
[0093] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or a combination of software and hardware embodiments. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0094] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0095] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.
[0096] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.
Claims
1. A digital factory equipment operation and maintenance management method, characterized in that: include: Obtain initial equipment operating condition data collected by multimodal sensors deployed on factory equipment over a period of time; Processing the initial data of the equipment operating condition to obtain equipment status data representing the degree of equipment degradation; Obtaining a device status comparison parameter based on the device status data and a preset status threshold; Based on the equipment status comparison parameters, an operation and maintenance plan is matched in a preset operation and maintenance management plan to obtain a result of digital factory equipment operation and maintenance management.
2. The digital factory equipment operation and maintenance management method according to claim 1 is characterized in that: The step of obtaining initial equipment operating condition data collected by multimodal sensors deployed on factory equipment over a period of time includes: Obtain vibration data, temperature data, and current data collected by multimodal sensors deployed on factory equipment over a period of time; The vibration data, temperature data and current data are standardized to obtain initial equipment operating condition data.
3. The digital factory equipment operation and maintenance management method according to claim 1, characterized in that: The step of processing the initial equipment operating condition data to obtain equipment status data representing the degree of equipment degradation includes: Performing denoising on the initial equipment operating condition data to obtain denoised initial equipment operating condition data; Extracting key features reflecting the equipment status from the denoised initial equipment operating condition data and normalizing the data to obtain key feature data; The key feature data are fused to obtain the equipment status data that characterizes the degree of equipment degradation.
4. The digital factory equipment operation and maintenance management method according to claim 1, characterized in that: The step of obtaining a device status comparison parameter based on the device status data and a preset status threshold comprises: The device status data is compared with a preset status threshold value to obtain a device status comparison parameter.
5. The digital factory equipment operation and maintenance management method according to claim 1, characterized in that: The step of constructing the preset state threshold comprises: Obtain historical equipment status data during normal operation of the equipment; Performing standardization processing on historical equipment status data to obtain processed historical equipment status data; Extract key features from the processed historical equipment status data to obtain key features of historical data; Based on the key features of the historical data, a preset status threshold is determined.
6. The digital factory equipment operation and maintenance management method according to claim 5, characterized in that: The step of determining the preset status threshold based on the key features of the historical data further includes: Determining a preliminary threshold value for a preset state and a historical volatility parameter based on the key features of the historical data; Compare the volatility threshold with the historical volatility parameter to obtain the adjustment update coefficient; The preset state threshold is adjusted using the adjustment update coefficient to obtain the preset state threshold.
7. The digital factory equipment operation and maintenance management method according to claim 4, characterized in that: The step of performing a difference comparison between the device status data and a preset status threshold to obtain a device status comparison parameter includes: confirming device status parameters based on the device status data; Verifying the device status parameters to determine the device status coefficient; The device state coefficient is compared with a preset state threshold value to obtain a device state comparison parameter.
8. The digital factory equipment operation and maintenance management method according to claim 1, characterized in that: In the step of matching the operation and maintenance plan with the preset operation and maintenance management plan based on the equipment status comparison parameters to obtain the result of digital factory equipment operation and maintenance management, Identify that the device status comparison parameter is within a corresponding parameter interval in the preset operation and maintenance management solution; Based on the parameter range, matching the corresponding operation and maintenance management plan in the preset operation and maintenance management plan; Based on the operation and maintenance management plan, confirm the results of digital factory equipment operation and maintenance management.
9. The digital factory equipment operation and maintenance management method according to claim 8, characterized in that: The construction of the preset operation and maintenance management plan includes: Obtain equipment types, failure modes, preset failure parameter ranges, and historical operation and maintenance plans within the factory; Based on the equipment type, failure mode, preset failure parameter range and historical operation and maintenance plans, a preset operation and maintenance management plan is constructed.
10. A digital factory equipment operation and maintenance management platform, used for applying the digital factory equipment operation and maintenance management method according to any one of claims 1 to 9, characterized in that: include: An acquisition module is used to obtain initial equipment operating condition data collected by multimodal sensors deployed on factory equipment over a period of time; A data processing module is used to process the initial data of the equipment working condition to obtain equipment status data representing the degree of equipment degradation; A comparison module, configured to obtain a device status comparison parameter based on the device status data and a preset status threshold; The matching module is used to match the operation and maintenance plan in the preset operation and maintenance management plan based on the equipment status comparison parameters to obtain the results of digital factory equipment operation and maintenance management.