An AI digitalization PaaS basic platform system for manufacturing industry

Abstract

The application discloses a kind of manufacturing-oriented AI digitalization PaaS basic platform, platform includes production equipment multidimensional digitalization traceability module, equipment production environment data influence quantification module, equipment production equivalent running data acquisition module, equipment hierarchical fault weight evaluation module, equipment dynamic depreciation predictive analysis module and PaaS database module, to manufacturing equipment integration production environment, running wear, three key dimensions of inspection maintenance, the implicit erosion of production environment to equipment is converted into quantifiable influence coefficient, different working conditions are captured by running machining data Differentiated wear, quantitatively analyze the inspection health status of equipment and distinguish the fault maintenance history of weight, build a multidimensional, dynamic equipment health index evaluation model, based on health index, provide equipment residual value evaluation replacement recommendation, build comprehensive equipment management data platform, provide data basis for subsequent predictive maintenance, intelligent scheduling.

Description

Technical Field

[0001] This invention relates to the field of intelligent data, specifically to an AI-powered digital PaaS platform system for the manufacturing industry. Background Technology

[0002] PaaS is a cloud computing service model that provides a platform for developing, testing, deploying, and managing applications, supporting automated deployment, elastic scaling, and resource allocation to ensure that applications dynamically adjust performance based on load.

[0003] Currently, the manufacturing industry cannot intelligently assess the condition of all equipment. Existing equipment management in manufacturing simply judges the age of equipment based on its purchase year or the year it was put into use. This method ignores the actual intensity of use, maintenance conditions, and process differences, making it extremely inaccurate. Furthermore, regular manual inspections rely on the experience of maintenance engineers, which is heavily influenced by individual factors, difficult to quantify, and cannot achieve real-time and continuous assessment. Post-failure maintenance record analysis only indirectly reflects the degree of aging through maintenance frequency and cost after equipment failure. This is a lagging, passive assessment method that cannot be used to predict and prevent equipment health indices, cannot form an intelligent monitoring and assessment system for equipment condition, and relies solely on single-item equipment assessment, resulting in an inability to systematically optimize resources and prevent major equipment health problems.

[0004] This application aims to integrate three key dimensions of manufacturing equipment: production environment, operational wear and tear, and inspection and maintenance. It transforms the implicit erosion of equipment by the production environment into quantifiable impact coefficients, captures differentiated wear under different operating conditions through operational processing data, quantifies and analyzes the inspection health status and weighted fault repair history of the equipment, and constructs a multi-dimensional, dynamic equipment health index assessment model. Based on the health index, it provides equipment residual value assessment and replacement recommendations, eliminates subjective judgment differences between equipment in different manufacturing workshops and between different assessors, and builds a comprehensive equipment management data platform, providing a data foundation for subsequent advanced applications such as predictive maintenance and intelligent scheduling. Summary of the Invention

[0005] The purpose of this invention is to provide an AI-powered digital PaaS platform system for the manufacturing industry to address the problems in existing technologies.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] An AI-powered digital PaaS platform system for the manufacturing industry includes a multi-dimensional digital traceability module for production equipment, a module for quantifying the impact of equipment production environment data, a module for collecting equivalent operational data of equipment production, a module for evaluating equipment graded fault weights, a module for predictive analysis of equipment dynamic depreciation, and a PaaS database module.

[0008] The multi-dimensional digital traceability module for production equipment identifies and assesses the initial status of manufacturing equipment, collects and matches the overall configuration data of each piece of equipment with its identity, and uploads it to the PaaS database module for access verification.

[0009] The Equipment Production Environment Data Impact Quantification Module collects equipment production environment data, monitors the standardization of equipment operation and use, performs data quantification scoring, constructs an environmental level scoring model, and analyzes the degree of impact of different comprehensive coefficients on the age of the equipment through the environmental data impact coefficient and the operation standard impact coefficient.

[0010] The equipment production equivalent operation data acquisition module collects equipment production efficiency data and equivalent operating time. Based on real-time data, it performs equipment efficiency decay analysis, constructs equipment efficiency decay model, analyzes the wear coefficient and decay coefficient of different equipment through equipment load rate and benchmark production efficiency, and analyzes the degree of influence of different comprehensive coefficients on the age of the equipment through equipment wear coefficient and decay coefficient.

[0011] The equipment classification fault weight assessment module collects online multi-dimensional inspection data and fault records of the equipment, sets standard equipment inspection parameter thresholds, analyzes the deviation coefficient of equipment inspection parameters, and obtains fault repair methods. It then classifies the equipment repair quality assessment based on the fault repair methods and fault records, analyzes the equipment repair quality coefficient, and analyzes the impact of different comprehensive coefficients on the age of the equipment through the deviation coefficient of equipment inspection parameters and the equipment repair quality coefficient.

[0012] The equipment dynamic depreciation predictive analysis module obtains the influence coefficient of the equipment's age, analyzes the equipment's comprehensive health index, analyzes the depreciation value of different equipment based on the comprehensive health index, and analyzes the replacement cost of the new model of the same equipment and pushes decision-making.

[0013] The PaaS database module acquires data from multiple modules for detection and analysis, and accesses product price data and historical cooperation data from multiple equipment suppliers, including equipment delivery time and after-sales service ratings.

[0014] Further configuration: The multi-dimensional intelligent traceability module for production equipment includes an equipment identification verification submodule and an integrated equipment data acquisition submodule. The equipment identification verification submodule is used to assign a unique identifier to each manufacturer's equipment, perform an initial status assessment on the assigned equipment, including appearance inspection records, functional test reports, comprehensive photographic archiving of the equipment appearance, and inputting the equipment into the database according to the equipment identifier to establish an equipment file. The integrated equipment data acquisition submodule collects basic information of each manufacturer's equipment based on the equipment identifier in the database, including equipment name, model specifications, manufacturer, production date, purchase date, design life, estimated life, initial performance parameters, and technical manual. It matches the basic information data of the equipment with the unique equipment identifier, performs integrity and validity checks on the basic information data, removes duplicate and biased data, and generates a timestamp of the current matching time after a successful match. The basic information data and timestamp of the equipment are added to the equipment file and uploaded to the PaaS database module. The PaaS database module generates an access token, which equipment administrators use to view and modify the equipment file.

[0015] Further configuration: The equipment production environment data impact quantification module includes an equipment environment data acquisition and analysis submodule and an operator equipment usage training time statistics submodule. The equipment environment data acquisition and analysis submodule includes an external camera data acquisition and recognition unit and a sensor data acquisition unit. The external camera data acquisition and recognition unit connects to a camera within the equipment production area to acquire environmental images of the area and performs image recognition to determine whether the production area is in a high-dust or high-debris environment. The sensor data acquisition unit includes a temperature and humidity sensor and a voltage sensor. These sensors detect the temperature and humidity within the production area and the stability of the equipment power supply voltage, respectively, to acquire image data from the camera. Preprocessing and enhancement are performed to obtain the image display visibility level and the color and texture changes of the equipment surface and large debris on the ground and in the corners within the recognition area. When the visibility level of all images is blurry, it is determined that the air in the equipment production area is in a high dust state. When the color and texture changes of the equipment surface in the area are inconsistent with the appearance inspection record in the equipment file, and the equipment surface color is grayish-brown, it is determined that the equipment production area is in a high dust state. The proportion of pixels of large debris on the ground and in the corners in each image data is detected, the total pixel area of ​​each image is calculated, and the average proportion of pixels of large debris on the ground and in the corners in the image data is analyzed in the total pixel area. When the average proportion is greater than a set threshold, it is determined that the equipment production area is in a state of multiple debris.

[0016] The system acquires temperature, humidity, and power voltage data within the equipment production area. It sets reasonable ranges for these values ​​and compares the detected real-time data with these ranges. An environmental rating model is built based on the production area's condition. A score of 1 is awarded for each of the following conditions: high dust, high dust accumulation, and high debris levels. A score of 1 is also awarded for each of the above conditions if the real-time temperature, humidity, and power voltage data are outside the reasonable ranges. The system then classifies the production area's environmental level based on these scores: 0 for clean, 1 for slightly polluted, 2-3 for moderately polluted, and 4-6 for severely polluted. Different environmental quality scores are intelligently assigned to each environmental level, and these scores are set by the administrator.

[0017] Further settings: The operator equipment usage training time statistics submodule acquires the equipment training and usage time of equipment operators. Simultaneously, it randomly selects images from camera-captured data to determine if the equipment operation is standardized. If both the operator's training and usage time exceed a set threshold, 1 point is awarded for each. If both the extracted images show standardized operation, 1 point is awarded. Based on the equipment usage score, the operation standardization level is divided into four categories: 0 points for unqualified operation, 1 point for qualified operation, 2 points for good operation, and 3 points for excellent operation. Different operation quality scores are intelligently assigned based on the different operation standardization levels. The operation quality score is set by the administrator. Different equipment environment quality scores and operation quality scores are acquired and uploaded to the PaaS database module. When the equipment environment quality score and operation quality score exceed a set threshold, the PaaS database module issues a warning to the administrator. The influence coefficient of the equipment processing and production environment is analyzed through the equipment environment quality score and operation quality score, and a certain equipment environment quality score is set as... The operation quality score is This involves obtaining different environmental quality scores matching different environmental levels and different operational quality scores matching different operational standard levels, and setting the different environmental quality scores matching different environmental levels as follows: , , , Different levels of operational standards correspond to different operational quality scores. , , , The comprehensive impact coefficient of the equipment processing and production environment on the age of the equipment is set as follows: According to the formula:

[0018]

[0019] The comprehensive impact coefficients of different equipment processing and production environments are calculated and uploaded to the PaaS database module for statistical analysis.

[0020] Further configuration: The equipment production equivalent operation data acquisition module includes an equipment equivalent operation time recording submodule and an equipment efficiency attenuation coefficient analysis submodule. The equipment equivalent operation time recording submodule collects the cumulative operation time of different equipment, equipment processing type information, and equipment working data and operating parameters under different operation times. It obtains the hardness and corrosion degree of different materials processed by the equipment. Based on the reasonable range values ​​for material processing hardness and corrosion degree in the technical manual, it sets the maximum value of the reasonable range value for material processing hardness to be [value missing]. and the maximum value of the reasonable range of corrosion Set the hardness of the material being processed by a certain device in real time as... and corrosion Calculate the wear coefficient of the processed materials in real time. Simultaneously, based on equipment operating data, the actual workload of the equipment is obtained. According to the rated workload in the technical manual, the current load rate and temperature of the equipment within the operating parameters are analyzed. Different set temperature ranges are matched based on the equipment temperature, and different equipment temperature influence factors are set for different temperature ranges. The higher the temperature, the higher the equipment temperature influence factor. The set temperature range is set by the administrator, and the equipment operating temperature influence coefficient is set to [value missing]. Based on the equipment's operating data, monitor whether it processes different types of materials, analyze the wear coefficients of different material types and match them with the equipment's operating time for processing different materials, analyze the equipment's equivalent operating time, and set the equipment's equivalent operating time as... Set the current device load rate. According to the formula:

[0021]

[0022] in, The actual cumulative operating time of the equipment is used as the basis for analyzing the comprehensive wear coefficient of different equipment based on the equivalent operating time. The comprehensive wear coefficient of the equipment is then set as follows: According to the formula:

[0023]

[0024] in, The estimated service life of the equipment. This is a factor that accelerates equipment wear over time.

[0025] Further settings: The equipment efficiency attenuation coefficient analysis submodule acquires the initial and real-time production efficiency data of the equipment. Production efficiency includes product defect rate and product rework rate. Product defect rate and rework rate are removed from the real-time production data. The ratio of the current actual production efficiency data to the initial production efficiency data is obtained, and the relative attenuation of the equipment is calculated. The ratio of the current actual production efficiency data to the initial production efficiency data is set to a certain value. Set the actual attenuation of the device to be The relative attenuation of the device is set as According to the formula:

[0026]

[0027]

[0028] in, As the attenuation benchmark coefficient for this equipment, the comprehensive impact coefficient of equipment operation and processing on the age of the equipment is set as follows: According to the formula:

[0029]

[0030] The calculated comprehensive impact coefficient of different equipment operation and processing is uploaded to the PaaS database module for statistical analysis.

[0031] Further configuration: The equipment grading fault weight assessment module includes a multi-faceted online equipment inspection data acquisition submodule and an equipment fault repair quality grading dynamic analysis submodule. The multi-faceted online equipment inspection data acquisition submodule acquires periodic or online inspection data of different equipment, determines different inspection parameters for the equipment, sets standard parameter ranges according to different equipment parameters, and compares the current real-time different inspection parameters of the equipment with the corresponding standard parameter ranges. When a certain inspection parameter of the equipment is not within the corresponding standard parameter range, the deviation index is marked as 1. The module compares each inspection parameter of the equipment with the corresponding standard parameter range, analyzes the comprehensive deviation index of different parameters of the equipment in each inspection data, and sets the number of list types of equipment inspection parameters to be collected. The comprehensive deviation index of different parameters of a certain device in different inspection data is set as follows: Set the total number of equipment inspections to Analysis of the deviation of the comprehensive inspection data of the equipment from the mean index According to the formula:

[0032]

[0033] in, The value is not unique and is determined by the type and quantity of equipment data collected for each equipment inspection parameter.

[0034] The equipment fault repair quality grading dynamic analysis submodule acquires equipment fault data and classifies each equipment fault level according to a fault level classification standard uploaded by the administrator. Fault levels are categorized into minor, moderate, and severe faults. Corresponding fault impact scores are matched based on different fault levels to obtain repair data for each fault. Based on the repair data, repair sources and component replacement records are analyzed. Repair sources are categorized into original equipment manufacturer (OEM) repair and external personnel repair. Component replacement records are used to retrieve whether core components were replaced and the source of the replaced components. Repair quality weights are matched for OEM repair and external personnel repair, with the OEM repair method having a set repair quality weight range. The maintenance quality weighting range for external personnel inspection methods is set as follows: , When equipment malfunctions and the original factory repair method is used, and no core components are replaced, the current equipment malfunction repair quality weight is selected for matching. When equipment malfunctions, original factory repair methods are used, and core components are replaced. The current equipment malfunction repair quality weighting is then matched. When equipment malfunctions and external personnel are used for repairs, and core components are not replaced, the current equipment malfunction repair quality weighting is matched. When equipment malfunctions and external personnel are used for repairs, and core components are replaced, the current equipment malfunction repair quality weighting is matched. Simultaneously, equipment data is monitored within a set timeframe after equipment failure repair. If no similar or related component failures occur within the set time, the repair quality is considered high, and the weighting coefficient for this repair quality is increased. If the same failure occurs again within the set time, the repair is considered flawed, and the weighting coefficient for this repair quality is decreased. The increase and decrease ratios are set by the administrator. Equipment failure data is acquired, and different equipment failure repair quality weights are assigned to each failure data point. If the equipment is not repaired, the equipment failure repair quality weight is 0. Based on the impact score of each equipment failure and the equipment failure repair quality weight, the impact value of a single equipment failure is analyzed to obtain the different failure frequencies and their corresponding failure levels. Different equipment failure impact scores are set as follows: Obtain the different fault repair methods of the equipment, and set the fault repair quality weights corresponding to the different fault repair methods as follows: The overall impact coefficient of the equipment failure is set as follows: According to the formula:

[0035]

[0036] The total number of equipment failures was The deviation index mean of the comprehensive inspection data of the equipment and the comprehensive impact coefficient of equipment failure were obtained respectively. The comprehensive impact coefficient of different equipment inspection and maintenance data on the age of the equipment was set as follows: According to the formula:

[0037]

[0038] The comprehensive impact coefficient of different equipment inspection and maintenance is calculated and uploaded to the PaaS database module for statistical analysis.

[0039] Further settings: The equipment dynamic depreciation predictive analysis module includes an equipment comprehensive health index analysis submodule and an equipment economic depreciation replacement matching recommendation module. The equipment comprehensive health index analysis submodule obtains the comprehensive impact coefficient of different equipment processing and production environments on the age of the equipment. The comprehensive impact coefficient of different equipment operation and processing on the age of equipment. The comprehensive impact coefficient of different equipment inspection and maintenance data on the age of equipment. Different weighting coefficients are assigned to different impact coefficients. These weighting coefficients are preset by the administrator. A comprehensive equipment health index model is constructed based on the different comprehensive impact coefficients. The final comprehensive equipment health index is then integrated and set as follows: According to the formula:

[0040]

[0041] in, The administrator assigns different weighting coefficients to different influence coefficients, among which... The analysis yields a comprehensive health index for different devices, which is then uploaded to the PaaS database module. When the comprehensive health index of a device falls below a set threshold, the PaaS database module sends an alert to the administrator.

[0042] The equipment economic depreciation replacement matching recommendation module obtains the comprehensive health index of different equipment, determines the depreciation price of different equipment based on the comprehensive health index, and when the comprehensive health index of the equipment is lower than the set threshold, it obtains the prices of multiple suppliers of the same new model of equipment from the PaaS database module, analyzes the equipment replacement cost data, and makes a replacement recommendation.

[0043] Compared with existing technologies, the beneficial effects of this invention are: it aims to integrate three key dimensions of manufacturing equipment—production environment, operational wear, and inspection and maintenance—transforming the implicit erosion of equipment by the production environment into quantifiable impact coefficients. By capturing differentiated wear under different working conditions through operational processing data, it quantitatively analyzes the inspection health status of equipment and differentiated weighted fault repair history, constructing a multi-dimensional, dynamic equipment health index assessment model. Based on the health index, it provides equipment residual value assessment and replacement recommendations, eliminating subjective judgment differences between equipment in different manufacturing workshops and between different assessors. It also constructs a comprehensive equipment management data platform, providing a data foundation for subsequent advanced applications such as predictive maintenance and intelligent scheduling. Attached Figure Description

[0044] To make the content of this invention easier to understand, the invention will be further described in detail below with reference to specific embodiments and accompanying drawings.

[0045] Figure 1 This is a schematic diagram of the system structure of an AI-powered digital PaaS platform system for the manufacturing industry according to the present invention.

[0046] Figure 2 This is a schematic diagram of the module structure of an AI-powered digital PaaS platform system for the manufacturing industry according to the present invention. Figure 1 ;

[0047] Figure 3 This is a schematic diagram of the module structure of an AI-powered digital PaaS platform system for the manufacturing industry according to the present invention. Figure 2 ;

[0048] Figure 4 This is a schematic diagram of the module structure of an AI-powered digital PaaS platform system for the manufacturing industry according to the present invention. Figure 3 ;

[0049] Figure 5 This is a schematic diagram of the module structure of an AI-powered digital PaaS platform system for the manufacturing industry according to the present invention. Figure 4 ;

[0050] Figure 6 This is a schematic diagram of the module structure of an AI-powered digital PaaS platform system for the manufacturing industry according to the present invention. Figure 5 . Detailed Implementation

[0051] 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 some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0052] Please see Figures 1-6 In this embodiment of the invention, an AI-powered digital PaaS basic platform system for the manufacturing industry is provided. The platform includes a multi-dimensional digital traceability module for production equipment, a data impact quantification module for equipment production environment, a data acquisition module for equivalent operation data of equipment production, a graded fault weight evaluation module for equipment, a predictive analysis module for equipment dynamic depreciation, and a PaaS database module.

[0053] The multi-dimensional digital traceability module for production equipment identifies and assesses the initial status of manufacturing equipment, collects and matches the overall configuration data of each piece of equipment with its identity, and uploads it to the PaaS database module for access verification.

[0054] like Figure 2 As shown, it is important to note that the multi-dimensional intelligent traceability module for production equipment includes an equipment identification verification submodule and an integrated equipment data acquisition submodule. The equipment identification verification submodule assigns a unique identifier to each manufacturer's equipment, performs an initial status assessment on the assigned equipment (including appearance inspection records, functional test reports, comprehensive photographic archiving of the equipment's appearance, inputting the information into the database according to the equipment identifier, and establishing an equipment file). The integrated equipment data acquisition submodule collects basic information about each manufacturer's equipment based on the equipment identifiers in the database, including equipment name, model specifications, manufacturer, production date, purchase date, design life, estimated life, initial performance parameters, and technical manual. It matches the basic equipment information data with the unique equipment identifier, performs integrity and validity checks on the basic information data, removes duplicate and biased data, and generates a timestamp for the current matching time upon successful matching. The basic equipment information data and the timestamp are then added to the equipment file and uploaded to the PaaS database module. The PaaS database module generates an access token, which equipment administrators use to view and modify the equipment file.

[0055] The Equipment Production Environment Data Impact Quantification Module collects equipment production environment data, monitors the standardization of equipment operation and use, performs data quantification scoring, constructs an environmental level scoring model, and analyzes the degree of impact of different comprehensive coefficients on the age of the equipment through the environmental data impact coefficient and the operation standard impact coefficient.

[0056] like Figure 3 As shown, it needs to be specifically explained that the equipment production environment data impact quantification module includes an equipment environment data acquisition and analysis submodule and an operator equipment usage training time statistics submodule. The equipment environment data acquisition and analysis submodule includes an external camera data acquisition and recognition unit and a sensor data acquisition unit. The external camera data acquisition and recognition unit connects to a camera within the equipment production area. It acquires environmental images of the equipment production area through the camera and performs image recognition to determine whether the equipment production area is in a high-dust, high-debris environment. The sensor data acquisition unit includes a temperature and humidity sensor and a voltage sensor. These sensors detect the temperature and humidity within the equipment production area and the stability of the equipment power supply voltage, respectively, to obtain the images captured by the camera. Like the data, preprocessing and enhancement are performed to obtain the image display visibility level and identify the color and texture changes of the equipment surface and large debris on the ground and in the corners within the recognition area. When the visibility level of all images is blurry, it is determined that the air in the equipment production area is in a high dust state. When the color and texture changes of the equipment surface in the area are inconsistent with the appearance inspection record in the equipment file, and the equipment surface color is grayish-brown, it is determined that the equipment production area is in a high dust state. The proportion of pixels of large debris on the ground and in the corners in each image data is detected, the total pixel area of ​​each image is calculated, and the average proportion of pixels of large debris on the ground and in the corners in the image data is analyzed in the total pixel area. When the average proportion is greater than a set threshold, it is determined that the equipment production area is in a state of multiple debris.

[0057] The system acquires temperature, humidity, and power voltage data within the equipment production area. It sets reasonable ranges for these values ​​and compares the detected real-time data with these ranges. An environmental rating model is built based on the production area's condition. A score of 1 is awarded for each of the following conditions: high dust, high dust accumulation, and high debris levels. A score of 1 is also awarded for each of the above conditions if the real-time temperature, humidity, and power voltage data are outside the reasonable ranges. The system then classifies the production area's environmental level based on these scores: 0 for clean, 1 for slightly polluted, 2-3 for moderately polluted, and 4-6 for severely polluted. Different environmental quality scores are intelligently assigned to each environmental level, and these scores are set by the administrator.

[0058] Further explanation is needed. The operator equipment usage training time statistics submodule acquires the equipment training and usage time of equipment operators. Simultaneously, it randomly selects images from camera-collected images to determine if the equipment operation is standardized. When both the operator's training and usage time exceed a set threshold, 1 point is awarded for each. When both the operator's usage and the selected image demonstrate standardized operation, 1 point is awarded. Based on the equipment usage score, the standardization of equipment operation is categorized into levels: 0 points for unqualified operation, 1 point for qualified operation, 2 points for good operation, and 3 points for excellent operation. Different operation quality scores are intelligently assigned based on the different standardization levels. These operation quality scores are set by the administrator. Different equipment environment quality scores and operation quality scores are acquired and uploaded to the PaaS database module. When either the equipment environment quality score or the operation quality score exceeds a set threshold, the PaaS database module issues a warning to the administrator. The impact coefficient of the equipment processing and production environment is analyzed using the equipment environment quality score and operation quality score, and a specific equipment environment quality score is set as... The operation quality score is This involves obtaining different environmental quality scores matching different environmental levels and different operational quality scores matching different operational standard levels, and setting the different environmental quality scores matching different environmental levels as follows: , , , Different levels of operational standards correspond to different operational quality scores. , , , The comprehensive impact coefficient of the equipment processing and production environment on the age of the equipment is set as follows: According to the formula:

[0059]

[0060] The comprehensive impact coefficients of different equipment processing and production environments are calculated and uploaded to the PaaS database module for statistical analysis.

[0061] The equipment production equivalent operation data acquisition module collects equipment production efficiency data and equivalent operating time. Based on real-time data, it performs equipment efficiency decay analysis, constructs equipment efficiency decay model, analyzes the wear coefficient and decay coefficient of different equipment through equipment load rate and benchmark production efficiency, and analyzes the degree of influence of different comprehensive coefficients on the age of the equipment through equipment wear coefficient and decay coefficient.

[0062] like Figure 4As shown, it should be specifically noted that the equipment production equivalent operation data acquisition module includes an equipment equivalent operation time recording submodule and an equipment efficiency attenuation coefficient analysis submodule. The equipment equivalent operation time recording submodule collects the cumulative operation time of different equipment, equipment processing type information, and equipment working data and operating parameters under different operation times. It obtains the hardness and corrosion degree of different materials processed by the equipment. Based on the reasonable range values ​​for material processing hardness and corrosion degree in the technical manual, the maximum value of the reasonable range value for material processing hardness is set to... and the maximum value of the reasonable range of corrosion Set the hardness of the material being processed by a certain device in real time as... and corrosion Calculate the wear coefficient of the processed materials in real time. Simultaneously, based on equipment operating data, the actual workload of the equipment is obtained. According to the rated workload in the technical manual, the current load rate and temperature of the equipment within the operating parameters are analyzed. Different set temperature ranges are matched based on the equipment temperature, and different equipment temperature influence factors are set for different temperature ranges. The higher the temperature, the higher the equipment temperature influence factor. The set temperature range is set by the administrator, and the equipment operating temperature influence coefficient is set to [value missing]. Based on the equipment's operating data, monitor whether it processes different types of materials, analyze the wear coefficients of different material types and match them with the equipment's operating time for processing different materials, analyze the equipment's equivalent operating time, and set the equipment's equivalent operating time as... Set the current device load rate. According to the formula:

[0063]

[0064] in, The actual cumulative operating time of the equipment is used as the basis for analyzing the comprehensive wear coefficient of different equipment based on the equivalent operating time. The comprehensive wear coefficient of the equipment is then set as follows: According to the formula:

[0065]

[0066] in, The estimated service life of the equipment. This is a factor that accelerates equipment wear over time.

[0067] Further explanation is needed: the equipment efficiency attenuation coefficient analysis submodule acquires the initial and real-time production efficiency data of the equipment. Production efficiency includes product defect rate and product rework rate. Product defect rate and product rework rate are removed from the real-time production data. The ratio of the current actual production efficiency data to the initial production efficiency data is obtained, and the relative attenuation of the equipment is calculated. The ratio of the current actual production efficiency data to the initial production efficiency data is set as [value missing]. Set the actual attenuation of the device to be The relative attenuation of the device is set as According to the formula:

[0068]

[0069]

[0070] in, As the attenuation benchmark coefficient for this equipment, the comprehensive impact coefficient of equipment operation and processing on the age of the equipment is set as follows: According to the formula:

[0071]

[0072] The calculated comprehensive impact coefficient of different equipment operation and processing is uploaded to the PaaS database module for statistical analysis.

[0073] The equipment classification fault weight assessment module collects online multi-dimensional inspection data and fault records of the equipment, sets standard equipment inspection parameter thresholds, analyzes the deviation coefficient of equipment inspection parameters, and obtains fault repair methods. It then classifies the equipment repair quality assessment based on the fault repair methods and fault records, analyzes the equipment repair quality coefficient, and analyzes the impact of different comprehensive coefficients on the age of the equipment through the deviation coefficient of equipment inspection parameters and the equipment repair quality coefficient.

[0074] like Figure 5 As shown, further explanation is needed. The equipment classification fault weight assessment module includes a multi-dimensional equipment online inspection data acquisition submodule and an equipment fault repair quality classification dynamic analysis submodule. The multi-dimensional equipment online inspection data acquisition submodule acquires periodic or online inspection data of different equipment, determines different inspection parameters for the equipment, sets standard parameter ranges based on different equipment parameters, and compares the current real-time inspection parameters of the equipment with the corresponding standard parameter ranges. When a certain inspection parameter of the equipment is not within the corresponding standard parameter range, the deviation index is marked as 1. Each inspection parameter of the equipment is compared with the corresponding standard parameter range, and the comprehensive deviation index of different parameters of the equipment in each inspection data is analyzed. The number of list types of equipment inspection parameters collected is set to [number missing]. The comprehensive deviation index of different parameters of a certain device in different inspection data is set as follows: Set the total number of equipment inspections to Analysis of the deviation of the comprehensive inspection data of the equipment from the mean index According to the formula:

[0075]

[0076] in, The value is not unique and is determined by the type and quantity of equipment data collected for each equipment inspection parameter.

[0077] The equipment fault repair quality grading dynamic analysis submodule acquires equipment fault data and classifies each equipment fault level according to a fault level classification standard uploaded by the administrator. Fault levels are categorized into minor, moderate, and severe faults. Corresponding fault impact scores are matched based on different fault levels to obtain repair data for each fault. Based on the repair data, repair sources and component replacement records are analyzed. Repair sources are categorized into original equipment manufacturer (OEM) repair and external personnel repair. Component replacement records are used to retrieve whether core components were replaced and the source of the replaced components. Repair quality weights are matched for OEM repair and external personnel repair, with the OEM repair method having a set repair quality weight range. The maintenance quality weighting range for external personnel inspection methods is set as follows: , When equipment malfunctions and the original factory repair method is used, and no core components are replaced, the current equipment malfunction repair quality weight is selected for matching. When equipment malfunctions, original factory repair methods are used, and core components are replaced. The current equipment malfunction repair quality weighting is then matched. When equipment malfunctions and external personnel are used for repairs, and core components are not replaced, the current equipment malfunction repair quality weighting is matched. When equipment malfunctions and external personnel are used for repairs, and core components are replaced, the current equipment malfunction repair quality weighting is matched. Simultaneously, equipment data is monitored within a set timeframe after equipment failure repair. If no similar or related component failures occur within the set time, the repair quality is considered high, and the weighting coefficient for this repair quality is increased. If the same failure occurs again within the set time, the repair is considered flawed, and the weighting coefficient for this repair quality is decreased. The increase and decrease ratios are set by the administrator. Equipment failure data is acquired, and different equipment failure repair quality weights are assigned to each failure data point. If the equipment is not repaired, the equipment failure repair quality weight is 0. Based on the impact score of each equipment failure and the equipment failure repair quality weight, the impact value of a single equipment failure is analyzed to obtain the different failure frequencies and their corresponding failure levels. Different equipment failure impact scores are set as follows: Obtain the different fault repair methods of the equipment, and set the fault repair quality weights corresponding to the different fault repair methods as follows: The overall impact coefficient of the equipment failure is set as follows: According to the formula:

[0078]

[0079] The total number of equipment failures was The deviation index mean of the comprehensive inspection data of the equipment and the comprehensive impact coefficient of equipment failure were obtained respectively. The comprehensive impact coefficient of different equipment inspection and maintenance data on the age of the equipment was set as follows: According to the formula:

[0080]

[0081] The comprehensive impact coefficient of different equipment inspection and maintenance is calculated and uploaded to the PaaS database module for statistical analysis.

[0082] The equipment dynamic depreciation predictive analysis module obtains the influence coefficient of the equipment's age, analyzes the equipment's comprehensive health index, analyzes the depreciation value of different equipment based on the comprehensive health index, and analyzes the replacement cost of the new model of the same equipment and pushes decision-making.

[0083] like Figure 6 As shown, it needs to be specifically explained that the equipment dynamic depreciation predictive analysis module includes an equipment comprehensive health index analysis submodule and an equipment economic depreciation replacement matching recommendation module. The equipment comprehensive health index analysis submodule obtains the comprehensive impact coefficient of different equipment processing and production environments on the age of the equipment. The comprehensive impact coefficient of different equipment operation and processing on the age of equipment. The comprehensive impact coefficient of different equipment inspection and maintenance data on the age of equipment. Different weighting coefficients are assigned to different impact coefficients. These weighting coefficients are preset by the administrator. A comprehensive equipment health index model is constructed based on the different comprehensive impact coefficients. The final comprehensive equipment health index is then integrated and set as follows: According to the formula:

[0084]

[0085] in, The administrator assigns different weighting coefficients to different influence coefficients, among which... The analysis yields a comprehensive health index for different devices, which is then uploaded to the PaaS database module. When the comprehensive health index of a device falls below a set threshold, the PaaS database module sends an alert to the administrator.

[0086] The equipment economic depreciation replacement matching recommendation module obtains the comprehensive health index of different equipment, determines the depreciation price of different equipment based on the comprehensive health index, and when the comprehensive health index of the equipment is lower than the set threshold, it obtains the prices of multiple suppliers of the same new model of equipment from the PaaS database module, analyzes the equipment replacement cost data, and makes a replacement recommendation.

[0087] The PaaS database module accesses detection and analysis data from multiple modules, as well as product price data and historical cooperation data from multiple equipment suppliers, including equipment delivery time and after-sales service ratings.

[0088] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. An AI-powered digital PaaS platform system for the manufacturing industry, characterized by: The platform includes a multi-dimensional digital traceability module for production equipment, a data impact quantification module for equipment production environment, a data acquisition module for equivalent operation data of equipment production, a graded fault weight assessment module for equipment, a predictive analysis module for equipment dynamic depreciation, and a PaaS database module. The multi-dimensional digital traceability module for production equipment identifies and assesses the initial state of manufacturing equipment, collects and matches the overall configuration data of each piece of equipment with its identity, and uploads it to the PaaS database module for access verification. The equipment production environment data impact quantification module collects equipment production environment data, monitors the standardization of equipment operation and use, performs data quantification scoring, constructs an environmental level scoring model, and analyzes the degree of impact of different comprehensive coefficients on the age of the equipment through the environmental data impact coefficient and the operation standard impact coefficient. The equipment production environment data impact quantification module includes an equipment environment data acquisition and analysis submodule and an operator equipment usage training time statistics submodule. The equipment environment data acquisition and analysis submodule includes an external camera data acquisition and recognition unit and a sensor data acquisition unit. The external camera data acquisition and recognition unit connects to a camera within the equipment production area. It acquires environmental images of the production area and performs image recognition to determine whether the production area is in a high-dust, high-debris environment. The sensor data acquisition unit includes a temperature and humidity sensor and a voltage sensor. These sensors detect the temperature and humidity within the production area and the stability of the equipment power supply voltage, respectively, acquiring the image data from the camera for further processing. Preprocessing and enhancement are performed to obtain the visibility level of the image display and the color and texture changes of the equipment surface and large debris on the ground and in the corners within the recognition area. When the visibility level of all images is blurry, it is determined that the air in the equipment production area is in a high dust state. When the color and texture changes of the equipment surface in the area are inconsistent with the appearance inspection record in the equipment file, and the equipment surface color is grayish-brown, it is determined that the equipment production area is in a high dust state. The proportion of pixels of large debris on the ground and in the corners in each image data is detected, the total pixel area of ​​each image is calculated, and the average proportion of pixels of large debris on the ground and in the corners in the image data is analyzed in the total pixel area. When the average proportion is greater than a set threshold, it is determined that the equipment production area is in a state of multiple debris. The system acquires temperature, humidity, and power supply voltage data within the equipment production area. It sets reasonable value ranges for these parameters and compares the detected real-time data with these ranges. An environmental rating model is built based on the equipment production area's condition. A score of 1 is awarded for each of the following conditions: high dust, high dust accumulation, and high debris levels. A score of 1 is also awarded for each of the following conditions: temperature, humidity, and power supply voltage data are outside the reasonable ranges. The system then assigns environmental levels based on these levels: 0 for clean, 1 for slightly polluted, 2-3 for moderately polluted, and 4-6 for severely polluted. Different environmental quality scores are intelligently assigned to each environmental level, and these scores are set by the administrator. The operator training time statistics submodule acquires the equipment training and usage time of equipment operators. Simultaneously, it randomly selects images from camera-captured data to assess whether the equipment operation is standardized. If both the operator's training and usage time exceed a set threshold, 1 point is awarded for each. If both the extracted images show standardized operation, 1 point is awarded. Based on the equipment usage score, the standardization of equipment operation is categorized into levels: 0 for unqualified operation, 1 for qualified operation, 2 for good operation, and 3 for excellent operation. Different operation quality scores are intelligently assigned to different standardization levels. These operation quality scores are set by the administrator. The submodule also acquires and uploads equipment environment quality scores and operation quality scores to the PaaS database module. When either the equipment environment quality score or the operation quality score exceeds a set threshold, the PaaS database module issues a warning to the administrator. The module analyzes the impact coefficient of the equipment's processing and production environment using the equipment environment quality scores and operation quality scores, and sets a specific equipment environment quality score as... The operation quality score is This involves obtaining different environmental quality scores matching different environmental levels and different operational quality scores matching different operational standard levels, and setting the different environmental quality scores matching different environmental levels as follows: , , , Different levels of operational standards correspond to different operational quality scores. , , , The comprehensive impact coefficient of the equipment processing and production environment on the age of the equipment is set as follows: According to the formula: The comprehensive impact coefficients of different equipment processing and production environments are calculated and uploaded to the PaaS database module for statistical analysis; The equipment production equivalent operation data acquisition module collects equipment production efficiency data and equivalent operation time, performs equipment efficiency decay analysis based on real-time data, constructs equipment efficiency decay model, analyzes the wear coefficient and decay coefficient of different equipment through equipment load rate and benchmark production efficiency, and analyzes the degree of influence of different comprehensive coefficients on the newness and age of equipment through equipment wear coefficient and decay coefficient. The equipment production equivalent operation data acquisition module includes an equipment equivalent operation time recording submodule and an equipment efficiency attenuation coefficient analysis submodule. The equipment equivalent operation time recording submodule collects the cumulative operation time of different equipment, equipment processing type information, and equipment working data and operating parameters under different operation times. It also obtains the hardness and corrosion resistance of different materials processed by the equipment. Based on the reasonable hardness and corrosion resistance ranges in the technical manual, it sets the maximum value of the reasonable hardness range. and the maximum value of the reasonable range of corrosion Set the hardness of the material being processed by a certain device in real time as... and corrosion Calculate the wear coefficient of the processed materials in real time. Simultaneously, based on equipment operating data, the actual workload of the equipment is obtained. According to the rated workload in the technical manual, the current load rate and temperature of the equipment within the operating parameters are analyzed. Different set temperature ranges are matched based on the equipment temperature, and different equipment temperature influence factors are set for different temperature ranges. The higher the temperature, the higher the equipment temperature influence factor. The set temperature range is set by the administrator, and the equipment operating temperature influence coefficient is set to [value missing]. Based on the equipment's operating data, monitor whether it processes different types of materials, analyze the wear coefficients of different material types and match them with the equipment's operating time for processing different materials, analyze the equipment's equivalent operating time, and set the equipment's equivalent operating time as... Set the current device load rate. According to the formula: in, The actual cumulative operating time of the equipment is used as the basis for analyzing the comprehensive wear coefficient of different equipment based on the equivalent operating time. The comprehensive wear coefficient of the equipment is then set as follows: According to the formula: in, The estimated service life of the equipment. It is a factor that accelerates equipment wear over time; The equipment efficiency attenuation coefficient analysis submodule acquires the initial and real-time production efficiency data of the equipment. Production efficiency includes product defect rate and product rework rate. Product defect rate and rework rate are removed from the real-time production data. The ratio of the current actual production efficiency data to the initial production efficiency data is obtained, and the relative attenuation rate of the equipment is calculated. The ratio of the current actual production efficiency data to the initial production efficiency data is set as [value missing]. Set the actual attenuation of the device to be The relative attenuation of the device is set as According to the formula: in, As the attenuation benchmark coefficient for this equipment, the comprehensive impact coefficient of equipment operation and processing on the age of the equipment is set as follows: According to the formula: The comprehensive impact coefficients of different equipment operation and processing are calculated and uploaded to the PaaS database module for statistical analysis; The equipment classification fault weight assessment module collects online multi-dimensional inspection data and fault records of the equipment, sets standard equipment inspection parameter thresholds, analyzes the deviation coefficient of equipment inspection parameters, and simultaneously obtains fault repair methods. It then performs a classification equipment repair quality assessment on the fault repair methods and fault records, analyzes the equipment repair quality coefficient, and analyzes the degree of influence of different comprehensive coefficients on the age of the equipment through the deviation coefficient of equipment inspection parameters and the equipment repair quality coefficient. The equipment classification fault weight assessment module includes a multi-dimensional online equipment inspection data acquisition submodule and an equipment fault repair quality classification dynamic analysis submodule. The multi-dimensional online equipment inspection data acquisition submodule acquires periodic or online inspection data from different equipment, determines different inspection parameters for each equipment, sets standard parameter ranges based on these parameters, and compares the current real-time inspection parameters of the equipment with their corresponding standard ranges. When a current inspection parameter is outside its standard range, a deviation index of 1 is marked. This process is repeated for each inspection parameter, comparing it to its corresponding standard range and analyzing the comprehensive deviation index of different parameters for each inspection. The number of itemized lists for equipment inspection parameters is set to a certain limit. The comprehensive deviation index of different parameters of a certain device in different inspection data is set as follows: Set the total number of equipment inspections to Analysis of the deviation of the comprehensive inspection data of the equipment from the mean index According to the formula: in, The value is not unique and is determined by the type and quantity of equipment data collected for each equipment inspection parameter. The equipment fault repair quality grading dynamic analysis submodule acquires equipment fault data and classifies each equipment fault level according to a fault level classification standard uploaded by the administrator. Fault levels are categorized into minor, moderate, and severe faults. Corresponding fault impact scores are matched based on different fault levels to obtain repair data for each fault. Based on the repair data, repair sources and component replacement records are analyzed. Repair sources are categorized into original equipment manufacturer (OEM) repair and external personnel repair. Component replacement records are used to retrieve whether core components were replaced and the source of the replaced components. Repair quality weights are matched for OEM repair and external personnel repair, with the OEM repair method having a set repair quality weight range. The maintenance quality weighting range for external personnel inspection methods is set as follows: , When equipment malfunctions and the original factory repair method is used, and no core components are replaced, the current equipment malfunction repair quality weight is selected for matching. When equipment malfunctions, original factory repair methods are used, and core components are replaced. The current equipment malfunction repair quality weighting is then matched. When equipment malfunctions and external personnel are used for repairs, and core components are not replaced, the current equipment malfunction repair quality weighting is matched. When equipment malfunctions and external personnel are used for repairs, and core components are replaced, the current equipment malfunction repair quality weighting is matched. Simultaneously, equipment data is monitored within a set timeframe after equipment failure repair. If no similar or related component failures occur within the set time, the repair quality is considered high, and the weighting coefficient for this repair quality is increased. If the same failure occurs again within the set time, the repair is considered flawed, and the weighting coefficient for this repair quality is decreased. The increase and decrease ratios are set by the administrator. Equipment failure data is acquired, and different equipment failure repair quality weights are assigned to each failure data point. If the equipment is not repaired, the equipment failure repair quality weight is 0. Based on the impact score of each equipment failure and the equipment failure repair quality weight, the impact value of a single equipment failure is analyzed to obtain the different failure frequencies and their corresponding failure levels. Different equipment failure impact scores are set as follows: Obtain the different fault repair methods of the equipment, and set the fault repair quality weights corresponding to the different fault repair methods as follows: The overall impact coefficient of the equipment failure is set as follows: According to the formula: The total number of equipment failures was The deviation index mean of the comprehensive inspection data of the equipment and the comprehensive impact coefficient of equipment failure were obtained respectively. The comprehensive impact coefficient of different equipment inspection and maintenance data on the age of the equipment was set as follows: According to the formula: The comprehensive impact coefficients of different equipment inspection and maintenance are calculated and uploaded to the PaaS database module for statistical analysis; The equipment dynamic depreciation predictive analysis module obtains the influence coefficient of the equipment's age, analyzes the equipment's comprehensive health index, analyzes the depreciation value of different equipment based on the comprehensive health index, and analyzes the replacement cost of the new model of the same equipment and makes decision recommendations. The equipment dynamic depreciation predictive analysis module includes an equipment comprehensive health index analysis submodule, which obtains the comprehensive impact coefficient of different equipment processing and production environments on the age of the equipment. The comprehensive impact coefficient of different equipment operation and processing on the age of equipment. The comprehensive impact coefficient of different equipment inspection and maintenance data on the age of equipment. Different weighting coefficients are assigned to different impact coefficients. These weighting coefficients are preset by the administrator. A comprehensive equipment health index model is constructed based on the different comprehensive impact coefficients. The final comprehensive equipment health index is then integrated and set as follows: According to the formula: in, The administrator assigns different weighting coefficients to different influence coefficients, among which... The analysis yields a comprehensive health index for different devices, which is then uploaded to the PaaS database module. When the comprehensive health index of a device falls below a set threshold, the PaaS database module sends an alert to the administrator. The PaaS database module acquires data from multiple modules for detection and analysis, and accesses product price data and historical cooperation data from multiple equipment suppliers, including equipment delivery time and after-sales service ratings.

2. The AI-powered digital PaaS platform system for manufacturing as described in claim 1, characterized in that... The multi-dimensional intelligent traceability module for production equipment includes an equipment identification verification submodule and an integrated equipment data acquisition submodule. The equipment identification verification submodule assigns a unique identifier to each manufacturer's equipment, performs an initial status assessment on the assigned equipment (including appearance inspection records, functional test reports, comprehensive photographic archiving of the equipment's appearance, inputting the equipment identifier into the database, and establishing an equipment file). The integrated equipment data acquisition submodule collects basic information about each manufacturer's equipment based on the equipment identifier in the database, including equipment name, model specifications, manufacturer, production date, purchase date, design life, estimated life, initial performance parameters, and technical manual. It matches the basic information data with the unique equipment identifier, performs integrity and validity checks on the basic information data, removes duplicate and biased data, and generates a timestamp for the current matching time upon successful matching. The basic information data and timestamp are then added to the equipment file and uploaded to the PaaS database module. The PaaS database module generates an access token, which equipment administrators use to view and modify the equipment file.

3. The AI-powered digital PaaS platform system for manufacturing as described in claim 1, characterized in that... The equipment dynamic depreciation predictive analysis module includes an equipment economic depreciation replacement matching recommendation module. This module obtains the comprehensive health index of different equipment, determines the depreciation price of different equipment based on the comprehensive health index, and when the comprehensive health index of the equipment is lower than a set threshold, it obtains the prices of multiple suppliers matching the new model of the same equipment from the PaaS database module, analyzes the equipment replacement cost data, and makes a replacement recommendation.

Images