AI-based floor mopping machine production equipment abnormity prediction system and method

Abstract

The invention provides an AI-based floor mopping machine production equipment abnormity prediction system and method, and the method comprises the steps: monitoring operation parameters of floor mopping machine production equipment in real time, comparing the operation parameters with historical data, and separating periodic and non-periodic components; using a clustering algorithm to identify an unexpected fluctuation mode, and mining through association rules to obtain key factors; constructing a reference performance curve by combining performance data of components of the same type, and evaluating a potential abnormal risk level by using a fuzzy logic system based on the deviation degree of an actual performance curve; and adopting a Bayesian network to predict possible faults in a specific time period in the future, and generating a maintenance suggestion report. The maintenance efficiency and reliability of the floor mopping machine production equipment are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of AI technology, and more particularly to an abnormality prediction system and method for floor scrubbing machine production equipment based on AI. Background Art

[0002] In modern industrial production environments, the stable operation of floor scrubber production equipment is crucial to the overall efficiency of the production line and product quality. In order to ensure that the equipment can maintain efficient operation for a long time, it is particularly important to monitor its operating parameters (such as temperature, pressure, vibration, etc.) in real time and compare and analyze them with historical data. Through this comparison, the periodic and non-periodic components in the operating parameters can be separated, thereby identifying unexpected fluctuation patterns that may affect the normal operation of the equipment. Further use of clustering algorithms and association rule mining algorithms can not only discover the causal relationships and co-occurrence patterns behind these fluctuation patterns, but also extract key factors to provide a basis for subsequent equipment health assessment. Combined with the performance data of components of the same type, a baseline performance curve is constructed, and the fuzzy logic system is used to evaluate the potential abnormal risk level based on the degree of deviation between the actual performance curve and the baseline performance curve. Finally, a Bayesian network is used to predict equipment that may fail in a specific time period in the future, and a maintenance recommendation report is generated to achieve preventive maintenance, reduce unexpected downtime, extend the service life of equipment, and improve overall production efficiency.

[0003] At present, the monitoring and maintenance of floor scrubbing machine production equipment mainly rely on traditional threshold alarm mechanisms and methods based on time series analysis. The traditional threshold alarm mechanism monitors the changes of single or multiple operating parameters by setting fixed upper and lower limits, and triggers an alarm once a parameter exceeds the preset range. In addition, some companies have adopted statistical time series analysis methods to try to identify abnormal behavior of equipment from historical data. However, most of these methods can only process data of a single dimension and lack a comprehensive understanding of the complex relationship between multiple parameters. For example, although some solutions can detect abnormal changes in certain parameters, they cannot accurately determine whether these changes actually indicate the occurrence of equipment failure. At the same time, existing solutions are inefficient when processing large-scale data sets, making it difficult to achieve real-time monitoring and rapid response, which limits their application effect in dynamically changing environments.

[0004] Although existing monitoring and maintenance solutions meet basic needs to a certain extent, they have obvious limitations. First, traditional solutions focus on single-point monitoring and static threshold settings, which are difficult to adapt to dynamic changes under different working conditions, and are prone to false positives or false negatives, affecting the accuracy of maintenance decisions. Second, existing methods lack the ability to effectively predict future failures, making it impossible to formulate preventive maintenance plans in advance, increasing the risk of sudden equipment failures. In addition, these solutions perform poorly when processing complex multidimensional data, making it difficult to extract valuable information from massive data, limiting their application in high-precision equipment health management. Summary of the invention

[0005] The embodiments of the present application provide an AI-based abnormality prediction system and method for floor scrubbing machine production equipment, which are used to solve the problems of low maintenance efficiency and poor reliability of floor scrubbing machine production equipment in the prior art.

[0006] In a first aspect, an embodiment of the present application provides an abnormality prediction method for floor scrubbing machine production equipment based on AI, comprising: Receiving operating parameters of a floor scrubber production device from real-time monitoring, comparing the operating parameters with historical data from the operation of the floor scrubber production device, and obtaining periodic and non-periodic components in the operating parameters; identifying unexpected fluctuation patterns occurring in the operating parameters using a clustering algorithm based on the periodic and non-periodic components; Using association rule mining algorithms, the causal relationship and co-occurrence pattern discovery processing of the unexpected fluctuation pattern is performed to obtain key factors; Using the key factors as input, combined with the performance data of the same type of components among floor scrubber production equipment, a baseline performance curve is constructed, and based on the degree of deviation between the baseline performance curve and the actual performance curve, the floor scrubber production equipment is evaluated in combination with a fuzzy logic system to determine the potential abnormal risk level; According to the unexpected fluctuation pattern, the key factors and the potential abnormal risk level, a Bayesian network is used to predict the floor scrubbing machine production equipment that will fail within a preset time period, and a maintenance recommendation report is generated.

[0007] Optionally, the key factors are used as inputs, and the performance data of the same type of components among floor scrubbing machine production equipment are combined to construct a benchmark performance curve. Based on the degree of deviation between the benchmark performance curve and the actual performance curve, the floor scrubbing machine production equipment is evaluated in combination with a fuzzy logic system to determine the potential abnormal risk level, including: Using the key factors as input, combined with the performance data of the same type of components among floor scrubbing machine production equipment, an adaptive filtering algorithm is applied to smooth the historical performance data from multiple sources to obtain smoothed data, and a support vector regression model is used to fit the smoothed data to generate a benchmark performance curve, wherein the multi-source historical performance data includes: performance data of the same type of components, actual operating parameters of the current equipment in different time periods, historical fault records, and maintenance logs; By comparing the actual performance curve with the benchmark performance curve, calculating the degree of deviation between the actual performance curve and the benchmark performance curve, and quantifying the degree of deviation using a root mean square error to obtain a degree of deviation score; According to the deviation degree score, the floor scrubber production equipment is evaluated and processed in combination with a fuzzy logic system to obtain an output result, and the output result is optimized using a particle swarm optimization algorithm to obtain a health status evaluation result of the floor scrubber production equipment; The health status assessment result is used in combination with a time series prediction model to predict the performance change trend of the floor scrubbing machine production equipment within a preset time period to obtain a prediction result, and the prediction result is analyzed to determine the potential abnormal risk level.

[0008] Optionally, the floor scrubber production equipment is evaluated and processed according to the deviation degree score in combination with a fuzzy logic system to obtain an output result, and the output result is optimized using a particle swarm optimization algorithm to obtain a health status evaluation result of the floor scrubber production equipment, including: Using an adaptive neuro-fuzzy inference system to perform fuzzy logic evaluation on the deviation degree score to generate a preliminary evaluation result; Based on the preliminary evaluation results, the fuzzy logic system is optimized by combining the genetic algorithm with the differential evolution algorithm to obtain an optimized fuzzy logic system; Inputting the deviation degree score into the optimized fuzzy logic system to generate an output result, and optimizing the output result by using a particle swarm optimization algorithm and a simulated annealing algorithm to generate an optimized output result; According to the integrated learning method, the preliminary evaluation results, the optimized fuzzy logic system and the optimized output results are integrated to generate the health status evaluation results of the floor scrubbing machine production equipment.

[0009] Optionally, the step of inputting the deviation degree score into the optimized fuzzy logic system to generate an output result, and optimizing the output result using a particle swarm optimization algorithm and a simulated annealing algorithm to generate an optimized output result comprises: Utilizing the optimized fuzzy logic system, taking the deviation degree score as input data, performing fuzzy reasoning processing on the deviation degree score, and outputting a preliminary equipment health status assessment result; Using a particle swarm optimization algorithm to perform a global search on the preliminary equipment health status assessment results, identify an optimal solution, and based on the optimal solution, optimize the preliminary equipment health status assessment results to obtain a result of the particle swarm optimization algorithm; According to the result of the particle swarm optimization algorithm, combined with the simulated annealing algorithm, the preliminary equipment health status assessment result is optimized again to generate an optimized output result.

[0010] Optionally, the association rule mining algorithm is used to perform causal relationship and co-occurrence pattern discovery processing on the unexpected fluctuation pattern to obtain key factors, including: Constructing a data set using the unexpected fluctuation pattern, performing dimensionality reduction processing on the data set using principal component analysis to obtain an optimized data set, and scanning the optimized data set using an association rule mining algorithm to identify frequent item sets; Using Granger causality test to detect the frequent item sets, obtain the causal relationship of the operation parameters, extract the co-occurrence pattern from the frequent item sets, and combine the causal relationship and the co-occurrence pattern to obtain a key set; Using lift, Jaccard similarity coefficient and Sorenson-Dees coefficient as evaluation indicators, the causal relationship and co-occurrence pattern of the key set are evaluated to generate a comprehensive scoring result; According to the comprehensive scoring result, candidate key factors are screened out from the frequent item set, and the candidate key factors are scored according to their importance using a random forest model to obtain key factors.

[0011] Optionally, the use of lift, Jaccard similarity coefficient and Sorenson-Diese coefficient as evaluation indicators to evaluate the causal relationship and co-occurrence pattern of the key set and generate a comprehensive scoring result includes: Calculating the lift of causal relationships and co-occurrence patterns in the key set to obtain a correlation strength score; Using the Jaccard similarity coefficient, similarity evaluation is performed on the causal relationship and the co-occurrence pattern in the key set, and the similarity degree of the causal relationship and the co-occurrence pattern in the key set is calculated to obtain a similarity score; Using the Sorenson-Dees coefficient, the causal relationship and the co-occurrence pattern are evaluated for uniqueness and importance, and the uniqueness scores of the causal relationship and the co-occurrence pattern are calculated to obtain a uniqueness score; Combined with the correlation strength score, the similarity score and the uniqueness score, a comprehensive scoring process is performed on each causal relationship and co-occurrence pattern in the key set to obtain a comprehensive scoring result.

[0012] Optionally, the identifying the unexpected fluctuation pattern appearing in the operating parameter by using a clustering algorithm according to the periodicity and the non-periodicity components includes: Based on the periodicity and the non-periodicity components, the operating parameters are classified using a clustering algorithm to identify a plurality of operating modes and abnormal modes, and a clustering result is obtained according to the operating modes and the abnormal modes; By comparing the clustering results with known normal operating modes, operating parameters that do not conform to the normal operating modes are identified and marked as unexpected fluctuation modes.

[0013] In a second aspect, the embodiment of the present application provides an abnormality prediction system for floor scrubbing machine production equipment based on AI, including: A receiving module, used for receiving operating parameters of the floor scrubber production equipment from real-time monitoring, comparing the operating parameters with historical data from the operation of the floor scrubber production equipment, and obtaining periodic and non-periodic components in the operating parameters; an identification module, configured to identify unexpected fluctuation patterns occurring in the operating parameters using a clustering algorithm based on the periodic and non-periodic components; A module is used to utilize an association rule mining algorithm to perform causal relationship and co-occurrence pattern discovery processing on the unexpected fluctuation pattern to obtain key factors; A construction module is used to use the key factors as inputs, combine the performance data of the same type of components among floor scrubber production equipment, construct a benchmark performance curve, and evaluate the floor scrubber production equipment in combination with a fuzzy logic system based on the degree of deviation between the benchmark performance curve and the actual performance curve to determine the potential abnormal risk level; The prediction module is used to use a Bayesian network to predict the floor scrubbing machine production equipment that will fail within a preset time period based on the unexpected fluctuation pattern, the key factors and the potential abnormal risk level, and generate a maintenance recommendation report.

[0014] In a third aspect, an embodiment of the present application provides a computing device, comprising a processor and a memory, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute any AI-based floor scrubbing machine production equipment abnormality prediction method described in the first aspect.

[0015] In a fourth aspect, an embodiment of the present application provides a computer storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement the AI-based floor scrubbing machine production equipment abnormality prediction method described in any one of the first aspects.

[0016] In an embodiment of the present application, operating parameters of a floor scrubbing machine production equipment are received from real-time monitoring, and the operating parameters are compared with historical data from the operation of the floor scrubbing machine production equipment to obtain periodic and non-periodic components in the operating parameters; based on the periodic and non-periodic components, a clustering algorithm is used to identify unexpected fluctuation patterns appearing in the operating parameters; an association rule mining algorithm is used to perform causal relationship and co-occurrence pattern discovery processing on the unexpected fluctuation patterns to obtain key factors; using the key factors as input, combined with performance data of similar components among floor scrubbing machine production equipment, a baseline performance curve is constructed, based on the degree of deviation between the baseline performance curve and the actual performance curve, the floor scrubbing machine production equipment is evaluated in combination with a fuzzy logic system to determine the potential abnormal risk level; based on the unexpected fluctuation pattern, the key factors and the potential abnormal risk level, a Bayesian network is used to predict floor scrubbing machine production equipment that will fail within a preset time period, and a maintenance recommendation report is generated.

[0017] The technical solution of this application has the following beneficial effects: This application uses a variety of advanced algorithms such as cluster analysis, association rule mining, fuzzy logic systems and Bayesian networks to not only accurately identify unexpected fluctuation patterns and causal relationships in equipment operation, but also accurately assess potential abnormal risk levels and predict future failure probabilities. This method significantly improves the predictability and effectiveness of equipment maintenance, reduces unexpected downtime, extends equipment service life, and significantly improves production efficiency and economic benefits.

[0018] Furthermore, the embodiment of the present application also uses key factors as input, combines the performance data of the same type of components among floor scrubbing machine production equipment, applies an adaptive filtering algorithm to smooth the multi-source historical performance data, obtains smoothed data, and uses a support vector regression model to fit these data to generate a benchmark performance curve. By comparing the actual performance curve with the benchmark performance curve, the degree of deviation is calculated and the degree of deviation is quantified using the root mean square error to obtain a degree of deviation score. Based on the degree of deviation score, a fuzzy logic system is used to evaluate the health status of the equipment, and a particle swarm optimization algorithm is used to optimize the output results, and finally an equipment health status evaluation result is generated. In addition, the time series prediction model is combined to predict the performance change trend of the equipment within a preset time period, and the prediction results are analyzed to determine the potential abnormal risk level.

[0019] Through the above method, not only can the benchmark performance curve be accurately constructed and the degree of deviation between the actual performance curve and the benchmark performance curve be quantified, but also the health status of the floor scrubber production equipment can be effectively evaluated. Specifically, by introducing key factors and multi-source historical performance data (such as performance data of similar components, actual operating parameters, historical fault records and maintenance logs), this method improves the accuracy and reliability of the benchmark performance curve. Further combined with the fuzzy logic system and particle swarm optimization algorithm, the accurate evaluation and optimization of the health status of the equipment are realized. Finally, the time series prediction model is used to predict the performance change trend of the equipment in a specific time period in the future, which helps to identify potential abnormal risks in advance and formulate preventive maintenance strategies, thereby significantly improving the operating efficiency and reliability of the equipment, reducing unexpected downtime and maintenance costs, and improving overall production efficiency. Compared with traditional solutions, this method has stronger predictability and higher accuracy, and is suitable for complex and changing industrial environments.

[0020] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 A flowchart of an abnormality prediction method for floor scrubbing machine production equipment based on AI provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of an abnormality prediction system for floor scrubbing machine production equipment based on AI provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0024] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0025] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0026] Figure 1 A flowchart of an abnormality prediction method for floor scrubbing machine production equipment based on AI is provided for the embodiment of the present application, such as Figure 1 As shown, the method includes: Step 101: receiving operating parameters of a floor scrubbing machine production device from real-time monitoring, comparing the operating parameters with historical data from the operation of the floor scrubbing machine production device, and obtaining periodic and non-periodic components in the operating parameters; In this step, operating parameters refer to various data generated in real time by the equipment during operation, such as temperature, pressure, vibration, etc. These parameters reflect the current working status of the equipment. Historical data is the operation record of the same or similar equipment over a period of time in the past. By comparing the current operating parameters with the historical data, it is possible to separate the periodic components (reflecting the normal working mode) and the non-periodic components (which may indicate abnormal behavior or potential failures).

[0027] In actual operation, first, the operating parameters of the floor scrubber production equipment are collected in real time through a sensor network. Then, signal processing technology is used to decompose these parameters into periodic and non-periodic components. The periodic component usually represents the normal working mode of the equipment, while the non-periodic component may indicate potential problems.

[0028] For example, in a large manufacturing plant, engineers installed high-precision sensors to monitor the operation of multiple floor scrubbing machines. They collected temperature and vibration data for each device and compared and analyzed it with historical data from the past year. It was found that the vibration level of some equipment increased significantly during a specific period of time, which may be due to abnormal behavior caused by wear of mechanical parts.

[0029] Step 102: using a clustering algorithm to identify unexpected fluctuation patterns in the operating parameters based on the periodic and non-periodic components; In this step, clustering algorithms are unsupervised learning methods used to divide objects in a dataset into groups or clusters such that objects within the same group are more similar to each other than to objects in other groups. In this context, clustering algorithms are used to identify unexpected fluctuation patterns in operating parameters, i.e., those data points or patterns that deviate from the normal operating mode.

[0030] In actual operation, a suitable clustering algorithm is selected, and the periodic and non-periodic components obtained in step 101 are input into the algorithm as feature vectors. Larger clusters in the clustering results usually represent normal patterns, while smaller clusters or isolated points may be abnormal patterns.

[0031] For example, continuing with the above example, after identifying the periodic and non-periodic components, engineers applied a clustering algorithm to further analyze the data. The results showed that some equipment had significant and unexpected fluctuations during specific time periods, which could indicate an impending failure. This information provided important clues for further analysis.

[0032] Step 103: using an association rule mining algorithm to perform causal relationship and co-occurrence pattern discovery processing on the unexpected fluctuation pattern to obtain key factors; In this step, association rule mining is a data mining technique used to discover interesting relationships between variables in a database. In this scenario, it is used to analyze causal relationships and co-occurrence patterns in unexpected fluctuation patterns to extract key factors. These key factors can help determine which conditions or events may cause abnormal behavior of the equipment.

[0033] In actual operation, the Apriori algorithm or other association rule mining methods are used to analyze the relationship between the variables in the unexpected fluctuation pattern to determine which factors co-occur or cause the anomaly. The key factors finally generated can be used to construct the benchmark performance curve in the subsequent steps.

[0034] For example, based on the previous step, engineers used the Apriori algorithm to conduct an in-depth analysis of unexpected fluctuation patterns. The results showed that the vibration level of some equipment increased significantly when it was running for a long time in a high temperature environment, which may be caused by a cooling system failure. These key factors were recorded and used for the next step of building a baseline performance curve.

[0035] Step 104: Using the key factors as inputs, combined with the performance data of the same type of components among floor scrubbing machine production equipment, a baseline performance curve is constructed, and based on the degree of deviation between the baseline performance curve and the actual performance curve, the floor scrubbing machine production equipment is evaluated in combination with a fuzzy logic system to determine the potential abnormal risk level; In this step, the adaptive filtering algorithm is a technology that dynamically adjusts its parameters to adapt to the changing environment and is commonly used in the field of signal processing. Support vector regression is an extended form of support vector machine and is used for regression analysis. The benchmark performance curve is an ideal performance reference line built based on historical data and current key factors, which is used to evaluate the degree of deviation of actual device performance.

[0036] In actual operation, firstly, the adaptive filtering algorithm is applied to smooth the multi-source historical performance data to remove noise interference. Then, the support vector regression model is used to fit the smoothed data to generate a benchmark performance curve. By comparing the deviation between the actual performance curve and the benchmark performance curve, the potential abnormal risk level of the equipment is evaluated in combination with the fuzzy logic system.

[0037] For example, after identifying the key factors, engineers applied adaptive filtering algorithms to smooth the multi-source historical performance data and used support vector regression models to generate baseline performance curves. By comparing the degree of deviation between the actual performance curve and the baseline performance curve, they found that some equipment had a higher abnormal risk level. These evaluation results provide a basis for subsequent predictions and maintenance recommendations.

[0038] Step 105: Based on the unexpected fluctuation pattern, the key factors and the potential abnormal risk level, a Bayesian network is used to predict the floor scrubbing machine production equipment that may fail within a preset time period, and a maintenance recommendation report is generated.

[0039] In this step, the Bayesian network is a probabilistic graphical model used to represent the dependencies between variables. It can infer the state of unknown variables based on known probability distributions. In this application scenario, the Bayesian network is used to predict the probability of failure within a specific time period in the future and generate a maintenance recommendation report.

[0040] In actual operation, first, a Bayesian network model is constructed, and data such as unexpected fluctuation patterns, key factors, and potential abnormal risk levels are input. Then, the model is used to predict the probability of failure within a specific time period in the future, and a detailed maintenance recommendation report is generated to guide factory managers to take preventive maintenance measures.

[0041] For example, based on the results of the previous steps, engineers built a Bayesian network model to predict the floor scrubber equipment that might fail in the next month. The report showed that some equipment had a high risk of failure in the next two weeks, and it was recommended to conduct inspection and maintenance immediately. Based on this report, the plant managers took preventive maintenance measures in a timely manner, avoiding unexpected downtime.

[0042] Through the comprehensive application of the above five steps, this method realizes the full process management from real-time monitoring to fault prediction. First, by real-time collection and analysis of equipment operating parameters, periodic and non-periodic components are identified; then, clustering algorithms and association rule mining algorithms are used to discover unexpected fluctuation patterns and their causal relationships, and extract key factors; then, these key factors are combined to build a baseline performance curve to evaluate the health status of the equipment; finally, the Bayesian network is used to predict the probability of future failures and generate a maintenance recommendation report. This method not only improves the predictability and accuracy of equipment maintenance, but also effectively reduces unexpected downtime, extends the service life of equipment, and greatly improves production efficiency and economic benefits. Throughout the process, each step is closely linked to form a complete equipment health management solution.

[0043] In order to solve the problem of inaccurate equipment health status assessment in the prior art, in some embodiments, the key factors described in step 104 are used as inputs, and the performance data of the same type of components among floor scrubber production equipment are combined to build a benchmark performance curve. Based on the degree of deviation between the benchmark performance curve and the actual performance curve, the floor scrubber production equipment is evaluated in combination with a fuzzy logic system to determine the potential abnormal risk level, including: Using the key factors as input, combined with the performance data of the same type of components among floor scrubbing machine production equipment, an adaptive filtering algorithm is applied to smooth the historical performance data from multiple sources to obtain smoothed data, and the smoothed data is fitted using a support vector regression model to generate a benchmark performance curve, wherein the multi-source historical performance data includes: performance data of the same type of components, actual operating parameters of the current equipment in different time periods, historical fault records, and maintenance logs; by comparing the actual performance curve with the benchmark performance curve, the degree of deviation between the actual performance curve and the benchmark performance curve is calculated, and the degree of deviation is quantified using the root mean square error to obtain a degree of deviation score; according to the degree of deviation score, the floor scrubbing machine production equipment is evaluated and processed in combination with a fuzzy logic system to obtain an output result, and the output result is optimized using a particle swarm optimization algorithm to obtain a health status evaluation result of the floor scrubbing machine production equipment; using the health status evaluation result, combined with a time series prediction model, the performance change trend of the floor scrubbing machine production equipment within a preset time period is predicted and processed to obtain a prediction result, and the prediction result is analyzed to determine the potential abnormal risk level.

[0044] In this embodiment, the adaptive filtering algorithm is a technology that can dynamically adjust its parameters to adapt to the changing environment, and is commonly used in the field of signal processing. Support vector regression is an extended form of support vector machine, which is used for regression analysis. Multi-source historical performance data includes performance data of components of the same type, actual operating parameters of the current equipment in different time periods, historical fault records, and maintenance logs, which are used to generate accurate baseline performance curves. The root mean square error is a standard measurement method for measuring the difference between the predicted value and the true value, and is used to quantify the degree of deviation between the actual performance curve and the baseline performance curve.

[0045] In an embodiment of the present application, first, an adaptive filtering algorithm is applied to smooth multi-source historical performance data to remove noise interference. Then, a support vector regression model is used to fit the smoothed data to generate a benchmark performance curve. By comparing the degree of deviation between the actual performance curve and the benchmark performance curve, and quantifying the degree of deviation using the root mean square error, a deviation degree score is obtained. According to the deviation degree score, the device is evaluated and processed in combination with a fuzzy logic system to obtain an output result, and the output result is optimized using a particle swarm optimization algorithm to finally obtain a health status assessment result of the device. Finally, the time series prediction model is combined to predict the performance change trend of the device within a specific time period in the future, and the prediction results are analyzed to determine the potential abnormal risk level.

[0046] The following is a specific embodiment: In a large manufacturing plant, engineers used the above method to improve the accuracy of health status assessment of floor scrubber production equipment. First, they collected operating parameters, fault records, and maintenance logs of all similar equipment in the past year and applied an adaptive filtering algorithm to smooth the data. Then, a support vector regression model was used to generate a baseline performance curve for each device. By comparing the real-time collected operating parameters with the baseline performance curve, the deviation score was calculated and quantified using the root mean square error. Subsequently, the equipment health status was evaluated in combination with a fuzzy logic system, and the evaluation results were further optimized using a particle swarm optimization algorithm. Based on these evaluation results, engineers also used a time series prediction model to predict the performance change trend of the equipment in the next month. The results showed that some equipment had a high risk of failure in the next two weeks, and it was recommended to perform preventive maintenance immediately. This method not only improved the predictability and accuracy of equipment maintenance, but also significantly reduced unexpected downtime and improved overall production efficiency. With this method, factory managers can identify potential problems in advance and develop effective maintenance strategies to ensure the continuity and stability of the production line.

[0047] In order to further improve the accuracy and robustness of the equipment health status assessment, in some embodiments, the step 104 includes evaluating the floor scrubber production equipment according to the deviation degree score and combining the fuzzy logic system to obtain an output result, and optimizing the output result using a particle swarm optimization algorithm to obtain a health status assessment result of the floor scrubber production equipment, and further includes: An adaptive neural fuzzy inference system is used to perform fuzzy logic evaluation on the deviation degree score to generate a preliminary evaluation result; based on the preliminary evaluation result, the fuzzy logic system is optimized by combining a genetic algorithm with a differential evolution algorithm to obtain an optimized fuzzy logic system; the deviation degree score is input into the optimized fuzzy logic system to generate an output result, and the output result is optimized by using a particle swarm optimization algorithm and a simulated annealing algorithm to generate an optimized output result; according to an integrated learning method, the preliminary evaluation result, the optimized fuzzy logic system and the optimized output result are integrated to generate a health status evaluation result of the floor scrubbing machine production equipment. Optionally, the deviation degree score is input into the optimized fuzzy logic system to generate an output result, and the output result is optimized by using a particle swarm optimization algorithm and a simulated annealing algorithm to generate an optimized output result, including: using the optimized fuzzy logic system, taking the deviation degree score as input data, performing fuzzy reasoning on the deviation degree score, and outputting a preliminary equipment health status assessment result; using a particle swarm optimization algorithm to perform a global search on the preliminary equipment health status assessment result to identify an optimal solution, and based on the optimal solution, optimizing the preliminary equipment health status assessment result to obtain a result of the particle swarm optimization algorithm; and optimizing the preliminary equipment health status assessment result again according to the result of the particle swarm optimization algorithm in combination with a simulated annealing algorithm to generate an optimized output result.

[0048] In this embodiment, the adaptive neuro-fuzzy inference system is an intelligent system that combines neural networks and fuzzy logic to process complex data patterns. Genetic algorithms and differential evolution algorithms are two commonly used global optimization algorithms that simulate biological evolution processes to find the optimal solution. Particle swarm optimization algorithm is an optimization method based on swarm intelligence that simulates bird foraging behavior to search for the global optimal solution. Simulated annealing algorithm is a probabilistic technique for finding approximate optimal solutions in large-scale search spaces. These methods work together to improve the accuracy and reliability of equipment health status assessment.

[0049] In the embodiment of the present application, first, the degree of deviation score is subjected to fuzzy logic evaluation processing using an adaptive neural fuzzy inference system to generate a preliminary evaluation result. Then, based on the preliminary evaluation result, the fuzzy logic system is optimized by combining the genetic algorithm with the differential evolution algorithm to obtain an optimized fuzzy logic system. The degree of deviation score is input into the optimized fuzzy logic system to generate an output result, and the output result is optimized using the particle swarm optimization algorithm and the simulated annealing algorithm to generate an optimized output result. Finally, according to the integrated learning method, the preliminary evaluation results, the optimized fuzzy logic system and the optimized output result are integrated to generate a health status evaluation result of the floor scrubber production equipment. Specifically, the degree of deviation score is subjected to fuzzy reasoning processing using the optimized fuzzy logic system to output a preliminary equipment health status evaluation result; the preliminary result is globally searched using the particle swarm optimization algorithm to identify the optimal solution and optimize the preliminary result; according to the result of the particle swarm optimization algorithm, the preliminary result is optimized again in combination with the simulated annealing algorithm to generate the final optimized output result.

[0050] The following is a specific embodiment: In a large manufacturing plant, engineers used the above method to improve the accuracy of health status assessment of floor scrubber production equipment. First, they used an adaptive neuro-fuzzy inference system to perform fuzzy logic assessment on the deviation score of each device and generated preliminary assessment results. Then, based on the preliminary assessment results, engineers optimized the fuzzy logic system by combining genetic algorithm and differential evolution algorithm to obtain a more accurate optimized fuzzy logic system. Subsequently, the deviation score was input into the optimized fuzzy logic system to generate preliminary equipment health status assessment results. To further improve the accuracy of the assessment results, engineers used particle swarm optimization algorithm to perform global search on the preliminary results, found the optimal solution, and optimized the preliminary results based on the optimal solution. Finally, combined with simulated annealing algorithm, the preliminary results were optimized again to generate the final optimized output results. The results showed that some equipment had a high risk of failure in the next two weeks, and it was recommended to perform preventive maintenance immediately. This method not only significantly improved the accuracy and robustness of equipment health status assessment, but also effectively reduced unexpected downtime and improved overall production efficiency. With this method, factory managers can identify potential problems in advance and develop effective maintenance strategies to ensure the continuity and stability of the production line.

[0051] In order to further improve the accuracy of identifying causal relationships and co-occurrence patterns in unexpected fluctuation patterns, in some embodiments, the association rule mining algorithm described in step 103 is used to perform causal relationship and co-occurrence pattern discovery processing on the unexpected fluctuation pattern to obtain key factors, including: A data set is constructed using the unexpected fluctuation pattern, and the data set is subjected to dimensionality reduction processing using principal component analysis to obtain an optimized data set. The optimized data set is scanned using an association rule mining algorithm to identify frequent item sets. The frequent item sets are detected using a Granger causality test to obtain the causal relationship of the operating parameters, and co-occurrence patterns are extracted from the frequent item sets, and a key set is obtained by combining the causal relationship and the co-occurrence pattern. The causal relationship and co-occurrence pattern of the key set are evaluated using lift, Jaccard similarity coefficient, and Sorenson-Dees coefficient as evaluation indicators to generate a comprehensive scoring result. According to the comprehensive scoring result, candidate key factors are screened out from the frequent item set, and the candidate key factors are scored for importance using a random forest model to obtain key factors. Optionally, the use of lift, Jaccard similarity coefficient and Sorenson-Dees coefficient as evaluation indicators to evaluate the causal relationship and co-occurrence pattern of the key set and generate a comprehensive scoring result, including: calculating the lift of the causal relationship and co-occurrence pattern in the key set to obtain a correlation strength score; using the Jaccard similarity coefficient to perform similarity evaluation processing on the causal relationship and co-occurrence pattern in the key set, calculating the degree of similarity between the causal relationship and co-occurrence pattern in the key set, and obtaining a similarity score; using the Sorenson-Dees coefficient to perform uniqueness and importance evaluation processing on the causal relationship and the co-occurrence pattern, calculating the uniqueness score of the causal relationship and the co-occurrence pattern, and obtaining a uniqueness score; combining the correlation strength score, the similarity score and the uniqueness score, performing a comprehensive scoring processing on each causal relationship and co-occurrence pattern in the key set to obtain a comprehensive scoring result.

[0052] In this embodiment, principal component analysis is a technique for dimensionality reduction, which reduces the dimension of a data set by projecting the data into a new coordinate system while retaining the main features of the original data as much as possible. Association rule mining algorithms are used to discover frequent item sets, that is, combinations of items that co-occur in a data set. Granger causality test is a statistical method for detecting causal relationships in time series data. Lift, Jaccard similarity coefficient, and Sorenson-Dees coefficient are evaluation indicators, which are used to evaluate the correlation strength, similarity, and uniqueness of causal relationships and co-occurrence patterns, respectively. The random forest model is an ensemble learning method that makes predictions by constructing multiple decision trees and determines the importance of variables based on the importance score of each tree.

[0053] In the embodiment of the present application, first, a data set is constructed using an unexpected fluctuation pattern, and principal component analysis is used to perform dimensionality reduction processing on it to obtain an optimized data set. Next, an association rule mining algorithm is applied to scan the optimized data set to identify frequent item sets. Then, the Granger causality test is used to detect these frequent item sets, and the causal relationship and co-occurrence pattern of the operating parameters are extracted to form a key set. Using the lifting degree, Jaccard similarity coefficient and Sorenson-Diss coefficient as evaluation indicators, the key set is comprehensively scored and a comprehensive scoring result is generated. Finally, according to the comprehensive scoring result, candidate key factors are screened out from the frequent item set, and the importance scoring of these candidate key factors is performed using the random forest model to finally obtain the key factors.

[0054] The following is a specific embodiment: In a large manufacturing plant, engineers used the above method to more accurately identify the unexpected fluctuation patterns and the causal relationships behind them in the operation of floor scrubber production equipment. First, they used the unexpected fluctuation patterns to construct a data set containing operating parameters such as temperature, pressure, and vibration, and reduced the dimension of the data set through principal component analysis to obtain an optimized data set. Then, the Apriori algorithm was applied to scan the optimized data set to identify frequent item sets. Then, the Granger causality test was used to detect these frequent item sets, and the causal relationships and co-occurrence patterns between the operating parameters were extracted to form key sets. In order to evaluate the quality of these key sets, the engineers calculated the lift, Jaccard similarity coefficient, and Sorenson-Dees coefficient to obtain comprehensive scoring results. Based on these scoring results, they screened out several candidate key factors from the frequent item sets, and used the random forest model to score the importance of these candidate factors, and finally determined the key factors affecting the health status of the equipment. The results show that certain specific operating parameter combinations are significantly associated with the occurrence of equipment failures, which provides an important reference for subsequent preventive maintenance. This approach not only improves the accuracy of causal relationship and co-occurrence pattern recognition, but also effectively improves the predictability and efficiency of equipment maintenance.

[0055] In order to further improve the accuracy of identifying unexpected fluctuation patterns, in some embodiments, the step 102 of identifying unexpected fluctuation patterns occurring in the operating parameters using a clustering algorithm based on the periodicity and the non-periodicity components includes: Based on the periodic and non-periodic components, the operating parameters are classified using a clustering algorithm to identify a variety of operating modes and abnormal modes, and clustering results are obtained based on the operating modes and the abnormal modes; by comparing the clustering results with known normal operating modes, operating parameters that do not conform to the normal operating mode are identified and marked as unexpected fluctuation modes.

[0056] In this embodiment, the clustering algorithm is an unsupervised learning method for dividing objects in a data set into multiple groups or clusters so that objects in the same group are more similar to each other than objects in other groups. The periodic and non-periodic components refer to the regular and irregular changes in the device operating parameters, respectively. The normal operating mode refers to the typical operating parameter characteristics exhibited by the device under normal working conditions. By comparing the clustering results with the known normal operating mode, the operating parameters that do not conform to the normal mode can be identified and marked as unexpected fluctuation patterns.

[0057] In the embodiment of the present application, firstly, based on the periodic and non-periodic components, the operating parameters are classified and processed using a clustering algorithm, and multiple operating modes and abnormal modes are identified to obtain clustering results. Then, by comparing these clustering results with the known normal operating modes, those operating parameters that do not conform to the normal operating mode are identified and marked as unexpected fluctuation modes. This method can effectively screen out potential problem points from a large amount of data, providing a basis for subsequent fault diagnosis and maintenance.

[0058] The following is a specific embodiment: In a large manufacturing plant, engineers used the above method to more accurately identify unexpected fluctuation patterns in the operation of floor scrubber production equipment. First, they collected operating parameters such as temperature, pressure, and vibration of each device in real time through a sensor network, and used signal processing technology to decompose these parameters into periodic and non-periodic components. Then, the K-means clustering algorithm was applied to classify these components, identify multiple operating modes and abnormal modes, and obtain clustering results. Subsequently, engineers compared these clustering results with known normal operating modes, and identified and marked those operating parameters that did not conform to the normal mode as unexpected fluctuation patterns. For example, some equipment had vibration values ​​significantly higher than normal levels during a specific time period, which may be caused by wear of mechanical parts or other potential problems. With this method, engineers can not only detect abnormal conditions in equipment operation in a timely manner, but also take preventive maintenance measures in advance to avoid production line interruptions caused by sudden failures. This strategy significantly improves the predictability and efficiency of equipment maintenance and ensures the continuity and stability of production.

[0059] This application takes into account that in the field of industrial equipment monitoring and maintenance, accurately assessing the health status of equipment and predicting potential failures are crucial to improving production efficiency, reducing downtime and extending the service life of equipment. Traditional methods usually rely on simple threshold alarm mechanisms or static benchmark performance curves. These methods are difficult to adapt to complex and changeable actual working conditions, and are prone to false alarms or missed alarms, affecting the accuracy of maintenance decisions. In addition, existing solutions are inefficient when processing large-scale data sets and cannot respond to rapidly changing equipment states in real time. Therefore, a new optional solution is proposed, which includes: The step of comparing the actual performance curve with the benchmark performance curve, calculating the degree of deviation between the actual performance curve and the benchmark performance curve, and quantifying the degree of deviation using a root mean square error to obtain a degree of deviation score includes: By comparing the actual value in the actual performance curve with the reference value in the reference performance curve, the degree of deviation between the actual performance curve and the reference performance curve is calculated, wherein the weighted nonlinear difference between the actual value and the reference value is expressed as: ; in, Indicates The weighted nonlinear difference between the actual value and the reference value at a time point, is the attenuation coefficient, is the current time, It's time point timestamp, Indicates The actual operating parameter value at a time point, Indicates The ideal reference value at each time point; The following is a detailed explanation of each parameter: Indicates The weighted nonlinear difference between the actual value and the reference value at a time point. This value is used to measure the degree of deviation between the actual value of the equipment operating parameter at a specific time point and the ideal reference value, and takes into account the time decay effect.

[0060] represents the dynamic weight function, The importance of data at a certain time point. As time moves away from the current time As the value increases, the weight gradually decreases, reflecting that the earlier data has less influence on the current evaluation. The method of obtaining it is to set the attenuation coefficient and the current time To calculate the timestamp of each time point The weight of .

[0061] Represents the attenuation coefficient, which determines how fast the time weight changes over time. The value will cause the weight to drop faster, which means that more emphasis is placed on recent data. The acquisition method is to determine the appropriate value.

[0062] Indicates the current time, used to calculate the time difference between each time point and the current time. The acquisition method is to read it directly from the system clock or real-time monitoring system.

[0063] Indicates The timestamp of a time point is used to calculate the time difference relative to the current time. The acquisition method is to extract the timestamp of each time point from the historical data record.

[0064] Represents a nonlinear transformation function that is used to increase sensitivity to outliers. A nonlinear function is usually selected to better capture the difference between the actual value and the reference value. The method of obtaining is to select an appropriate nonlinear function based on the actual application requirements and use the difference between the actual value and the reference value as input for calculation.

[0065] Indicates The actual operating parameter value at a time point indicates the actual operating status of the device at that time point. The acquisition method is to obtain it in real time from the sensor network or other data acquisition system.

[0066] Indicates The ideal reference value at a certain point in time (i.e., the value on the benchmark performance curve) indicates the operating parameter value that the equipment should achieve under normal working conditions. The acquisition method is based on historical data, experimental tests, or benchmark performance curves established by industry standards.

[0067] Represents the sum of the dynamic weights of all time points, which is used for normalization processing to ensure that the sum of the data weights at different time points is 1. The acquisition method is to obtain the timestamps of all time points Perform traversal calculations and accumulate the dynamic weights at each time point.

[0068] The following is an introduction to the design reasons of each sub-item: Dynamic weight function The reason for the design of the dynamic weight function is to give more recent data a higher weight to reflect its importance to the current evaluation. This method can reduce the impact of old data on the evaluation results and improve the response speed and accuracy of the model.

[0069] Nonlinear transformation function The reason for the design is that the use of nonlinear transformation functions can enhance the sensitivity to outliers, so that even small deviations can be amplified, making it easier to identify potential problems.

[0070] Denominator The reason for the design is to ensure that the sum of the data weights at different time points is 1 through normalization processing, avoiding distortion of the results due to excessive or small weights.

[0071] By multiplying the sub-items together, the dynamic weights The nonlinear transformation results The purpose of multiplication is to combine the time decay effect and the difference between the actual value and the benchmark value to comprehensively evaluate the importance of each time point and its degree of deviation.

[0072] Based on the result of the weighted nonlinear difference, the generalized average of the weighted squared differences at all time points is calculated, and the calculation formula is as follows: ; in, The generalized form of weighted mean square error is expressed by introducing a dynamic exponent Adjust the sensitivity to error, represents the sum of dynamic weights at all time points, is a tuning parameter used to control the amplitude of the dynamic index. is the angular frequency; The following is a detailed explanation of each parameter: It is a generalized form of weighted mean square error, which is used to measure the deviation between the actual performance curve and the benchmark performance curve. It is obtained by calculating the above formula.

[0073] Indicates The absolute value of the weighted nonlinear difference between the actual value and the reference value at a time point.

[0074] Represents a dynamic index, which is used to adjust the sensitivity to errors. The method of obtaining is based on the adjustment parameter and angular frequency Calculate the current time Dynamic index.

[0075] Represents a tuning parameter used to control the amplitude of the dynamic index. The acquisition method is set according to specific application requirements and is usually determined through experiments or experience.

[0076] Indicates the angular frequency, which determines the periodic change speed of the dynamic index. The acquisition method is determined based on the equipment operation characteristics and historical data analysis.

[0077] Represents the sum of the dynamic weights of all time points, used for normalization. The acquisition method is to obtain the timestamps of all time points Perform traversal calculations and accumulate the dynamic weights at each time point.

[0078] The following is an introduction to the design reasons of each sub-item: Dynamic Index The reason for the design of the dynamic index is that it is designed to meet the different requirements of error sensitivity in different time periods. By introducing periodic changes ( , the sensitivity to error can be adjusted in different time periods, making the evaluation more flexible and accurate.

[0079] Denominator The design reason is to normalize the data to ensure that the sum of the data weights at different time points is 1, avoiding distortion of the results due to excessive or small weights.

[0080] By multiplying the sub-items together, the dynamic weights The absolute value of the difference from the weighted nonlinearity The purpose is to combine the time decay effect with the size and sensitivity of the error to comprehensively evaluate the importance of each time point and its degree of deviation.

[0081] Based on the results of the generalized average, the weighted root mean square error is calculated to obtain the deviation score, which is calculated as follows: ; in, represents the weighted root mean square error, is a tuning parameter used to control the amplitude of the dynamic adjustment factor.

[0082] The following is a detailed explanation of each parameter: Represents the weighted root mean square error, which is used to quantify the degree of deviation between the actual performance curve and the benchmark performance curve. It is obtained by calculating the above formula.

[0083] Represents a tuning parameter that controls the amplitude of the dynamic adjustment factor. The value will make the dynamic adjustment factor have a greater impact. The acquisition method is to determine the appropriate value.

[0084] The following is an introduction to the design reasons of each sub-item: Dynamic Adjustment Factor The reason for the design is that the dynamic adjustment factor is introduced to adapt to the changing trend of the health status of the equipment in different time periods. By using the sine function, the sensitivity of the evaluation results can be adjusted in different time periods, making the evaluation more flexible and accurate.

[0085] Weighted mean square error The design reason is It is the core indicator to measure the degree of deviation between the actual performance curve and the benchmark performance curve. By introducing dynamic weights and dynamic indexes, the evaluation results can adapt to complex and changeable actual working conditions.

[0086] Dynamic weight function The reason for the design of the dynamic weight function is to give more recent data a higher weight to reflect its importance to the current evaluation. This method can reduce the impact of old data on the evaluation results and improve the response speed and accuracy of the model.

[0087] Denominator The design reason is that by accumulating and normalizing the dynamic weights of all time points, it ensures that the sum of the data weights at different time points is 1, avoiding distortion of the results due to excessive or small weights, thereby improving the stability and reliability of the evaluation results.

[0088] The purpose of multiplying the sub-items is to dynamically adjust the factors in the formula. The purpose of multiplying it by the square root of the weighted mean square error is to combine the periodic changes with the size of the error and its sensitivity to comprehensively evaluate the importance of each time point and its degree of deviation.

[0089] Here is a specific example: In a large manufacturing plant, engineers used the above method to evaluate the health of floor scrubber production equipment. Assume we have the following values: Current time is Hour, time point Hour, Hour, Hours, attenuation coefficient , angular frequency , adjustment parameters , actual operating parameter values: , base value: .

[0090] First, the weighted nonlinear difference is calculated at each time point : ; Then, calculate the generalized mean : ; Finally, the weighted root mean square error is calculated : ; From the calculation results, we can see that the weighted root mean square error It is about 1.58. This means that there is a significant deviation between the actual performance curve and the benchmark performance curve, indicating that there may be some problems or abnormalities in the equipment. Based on this result, engineers can take corresponding preventive maintenance measures, such as checking the equipment operation status within a specific time period, troubleshooting possible causes of abnormalities (such as mechanical component wear, sensor failure, etc.), thereby avoiding potential failures and ensuring the continuity and stability of production. This method not only improves the accuracy of equipment health status assessment, but also enhances the predictability and effectiveness of maintenance strategies.

[0091] Figure 2 The present application provides a schematic diagram of the structure of an abnormal prediction system for floor scrubbing machine production equipment based on AI, such as Figure 2 As shown, the system includes: The receiving module 21 is used to receive the operating parameters of the floor scrubber production equipment from real-time monitoring, compare the operating parameters with the historical data from the operation of the floor scrubber production equipment, and obtain the periodic and non-periodic components in the operating parameters; An identification module 22, configured to identify unexpected fluctuation patterns occurring in the operating parameters using a clustering algorithm based on the periodic and non-periodic components; Utilizing module 23, for utilizing association rule mining algorithm to perform causal relationship and co-occurrence pattern discovery processing on the unexpected fluctuation pattern to obtain key factors; A construction module 24 is used to use the key factors as inputs, combine the performance data of the same type of components among the floor scrubber production equipment, construct a benchmark performance curve, and evaluate the floor scrubber production equipment in combination with a fuzzy logic system based on the degree of deviation between the benchmark performance curve and the actual performance curve to determine the potential abnormal risk level; The prediction module 25 is used to use the Bayesian network to predict the floor scrubbing machine production equipment that will fail within a preset time period based on the unexpected fluctuation pattern, the key factors and the potential abnormal risk level, and generate a maintenance recommendation report.

[0092] Figure 2 The AI-based floor scrubber production equipment abnormality prediction system can perform Figure 1The implementation principle and technical effect of the AI-based floor scrubber production equipment abnormality prediction method described in the illustrated embodiment will not be repeated. The specific way in which each module and unit performs operations in the AI-based floor scrubber production equipment abnormality prediction system in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0093] In one possible design, Figure 2 The AI-based abnormal prediction system for floor scrubbing machine production equipment of the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0094] The processing component 32 is described above Figure 1 The embodiment of the invention is an AI-based method for predicting abnormalities in floor scrubbing machine production equipment.

[0095] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0096] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0097] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0098] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0099] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0100] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0101] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The illustrated embodiment is an AI-based method for predicting abnormalities in floor scrubbing machine production equipment.

[0102] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0103] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0104] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0105] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. The AI-based method for predicting abnormalities in floor scrubbing machine production equipment is characterized by: include: Receiving operating parameters of a floor scrubber production device from real-time monitoring, comparing the operating parameters with historical data from the operation of the floor scrubber production device, and obtaining periodic and non-periodic components in the operating parameters; identifying unexpected fluctuation patterns occurring in the operating parameters using a clustering algorithm based on the periodic and non-periodic components; Using association rule mining algorithms, the causal relationship and co-occurrence pattern discovery processing of the unexpected fluctuation pattern is performed to obtain key factors; Using the key factors as input, combined with the performance data of the same type of components among floor scrubber production equipment, a baseline performance curve is constructed, and based on the degree of deviation between the baseline performance curve and the actual performance curve, the floor scrubber production equipment is evaluated in combination with a fuzzy logic system to determine the potential abnormal risk level; According to the unexpected fluctuation pattern, the key factors and the potential abnormal risk level, a Bayesian network is used to predict the floor scrubbing machine production equipment that will fail within a preset time period, and a maintenance recommendation report is generated.

2. The method according to claim 1, characterized in that The method uses the key factors as inputs, combines the performance data of the same type of components among floor scrubber production equipment to build a benchmark performance curve, evaluates the floor scrubber production equipment based on the degree of deviation between the benchmark performance curve and the actual performance curve, and combines the fuzzy logic system to determine the potential abnormal risk level, including: Using the key factors as input, combined with the performance data of the same type of components among floor scrubbing machine production equipment, an adaptive filtering algorithm is applied to smooth the historical performance data from multiple sources to obtain smoothed data, and a support vector regression model is used to fit the smoothed data to generate a benchmark performance curve, wherein the multi-source historical performance data includes: performance data of the same type of components, actual operating parameters of the current equipment in different time periods, historical fault records, and maintenance logs; By comparing the actual performance curve with the benchmark performance curve, calculating the degree of deviation between the actual performance curve and the benchmark performance curve, and quantifying the degree of deviation using a root mean square error to obtain a degree of deviation score; According to the deviation degree score, the floor scrubber production equipment is evaluated and processed in combination with a fuzzy logic system to obtain an output result, and the output result is optimized using a particle swarm optimization algorithm to obtain a health status evaluation result of the floor scrubber production equipment; The health status assessment result is used in combination with a time series prediction model to predict the performance change trend of the floor scrubbing machine production equipment within a preset time period to obtain a prediction result, and the prediction result is analyzed to determine the potential abnormal risk level.

3. The method according to claim 2, characterized in that According to the deviation degree score, the floor scrubber production equipment is evaluated and processed in combination with the fuzzy logic system to obtain an output result, and the output result is optimized by the particle swarm optimization algorithm to obtain the health status evaluation result of the floor scrubber production equipment, including: Using an adaptive neuro-fuzzy inference system to perform fuzzy logic evaluation on the deviation degree score to generate a preliminary evaluation result; Based on the preliminary evaluation results, the fuzzy logic system is optimized by combining the genetic algorithm with the differential evolution algorithm to obtain an optimized fuzzy logic system; Inputting the deviation degree score into the optimized fuzzy logic system to generate an output result, and optimizing the output result by using a particle swarm optimization algorithm and a simulated annealing algorithm to generate an optimized output result; According to the integrated learning method, the preliminary evaluation results, the optimized fuzzy logic system and the optimized output results are integrated to generate the health status evaluation results of the floor scrubbing machine production equipment.

4. The method according to claim 3, characterized in that The step of inputting the deviation degree score into the optimized fuzzy logic system to generate an output result, and optimizing the output result by using a particle swarm optimization algorithm and a simulated annealing algorithm to generate an optimized output result includes: Utilizing the optimized fuzzy logic system, taking the deviation degree score as input data, performing fuzzy reasoning processing on the deviation degree score, and outputting a preliminary equipment health status assessment result; Using a particle swarm optimization algorithm to perform a global search on the preliminary equipment health status assessment results, identify an optimal solution, and based on the optimal solution, optimize the preliminary equipment health status assessment results to obtain a result of the particle swarm optimization algorithm; According to the result of the particle swarm optimization algorithm, combined with the simulated annealing algorithm, the preliminary equipment health status assessment result is optimized again to generate an optimized output result.

5. The method according to claim 1, characterized in that The association rule mining algorithm is used to perform causal relationship and co-occurrence pattern discovery processing on the unexpected fluctuation pattern to obtain key factors, including: Constructing a data set using the unexpected fluctuation pattern, performing dimensionality reduction processing on the data set using principal component analysis to obtain an optimized data set, and scanning the optimized data set using an association rule mining algorithm to identify frequent item sets; Using Granger causality test to detect the frequent item sets, obtain the causal relationship of the operation parameters, extract the co-occurrence pattern from the frequent item sets, and combine the causal relationship and the co-occurrence pattern to obtain a key set; Using lift, Jaccard similarity coefficient and Sorenson-Dees coefficient as evaluation indicators, the causal relationship and co-occurrence pattern of the key set are evaluated to generate a comprehensive scoring result; According to the comprehensive scoring result, candidate key factors are screened out from the frequent item set, and the candidate key factors are scored according to their importance using a random forest model to obtain key factors.

6. The method according to claim 5, characterized in that The lift, Jaccard similarity coefficient and Sorenson-Dees coefficient are used as evaluation indicators to evaluate the causal relationship and co-occurrence pattern of the key set and generate a comprehensive scoring result, including: Calculating the lift of causal relationships and co-occurrence patterns in the key set to obtain a correlation strength score; Using the Jaccard similarity coefficient, similarity evaluation is performed on the causal relationship and the co-occurrence pattern in the key set, and the similarity degree of the causal relationship and the co-occurrence pattern in the key set is calculated to obtain a similarity score; Using the Sorenson-Dees coefficient, the causal relationship and the co-occurrence pattern are evaluated for uniqueness and importance, and the uniqueness scores of the causal relationship and the co-occurrence pattern are calculated to obtain a uniqueness score; Combined with the correlation strength score, the similarity score and the uniqueness score, a comprehensive scoring process is performed on each causal relationship and co-occurrence pattern in the key set to obtain a comprehensive scoring result.

7. The method according to claim 1, characterized in that The step of identifying unexpected fluctuation patterns in the operating parameters using a clustering algorithm based on the periodic and non-periodic components includes: Based on the periodicity and the non-periodicity components, the operating parameters are classified using a clustering algorithm to identify a plurality of operating modes and abnormal modes, and a clustering result is obtained according to the operating modes and the abnormal modes; By comparing the clustering results with known normal operating modes, operating parameters that do not conform to the normal operating modes are identified and marked as unexpected fluctuation modes.

8. The AI-based abnormal prediction system for floor scrubber production equipment is characterized by: include: A receiving module, used for receiving operating parameters of a floor scrubber production device from real-time monitoring, comparing the operating parameters with historical data from the operation of the floor scrubber production device, and obtaining periodic and non-periodic components in the operating parameters; an identification module, configured to identify unexpected fluctuation patterns occurring in the operating parameters using a clustering algorithm based on the periodic and non-periodic components; A module is used to utilize an association rule mining algorithm to perform causal relationship and co-occurrence pattern discovery processing on the unexpected fluctuation pattern to obtain key factors; A construction module is used to use the key factors as inputs, combine the performance data of the same type of components among floor scrubbing machine production equipment, construct a benchmark performance curve, and evaluate the floor scrubbing machine production equipment in combination with a fuzzy logic system based on the degree of deviation between the benchmark performance curve and the actual performance curve to determine the potential abnormal risk level; The prediction module is used to use a Bayesian network to predict the floor scrubbing machine production equipment that will fail within a preset time period based on the unexpected fluctuation pattern, the key factors and the potential abnormal risk level, and generate a maintenance recommendation report.

9. A computing device, characterized in that It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the AI-based floor cleaning machine production equipment abnormality prediction method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, the abnormality prediction method for floor scrubbing machine production equipment based on AI as described in any one of claims 1 to 7 is implemented.

Images